Publications

Abdilla, A & Fitch, R 2017, 'FCJ-209 Indigenous Knowledge Systems and Pattern Thinking: An Expanded Analysis of the First Indigenous Robotics Prototype Workshop', Fibreculture Journal: internet theory criticism research, no. 28, pp. 1-14.
View/Download from: UTS OPUS or Publisher's site
View description>>

In November 2014, the lead researcher’s interest in the conceptual development of digital technology and her cultural connection to Indigenous Knowledge Systems created an opportunity to explore a culturally relevant use of technology with urban Indigenous youth: the Indigenous Robotics Prototype Workshop. The workshop achieved a sense of cultural pride and confidence in Indigenous traditional knowledge while inspiring the youth to continue with their engagement in coding and programming through building robots. Yet, the outcomes from the prototype workshop further revealed a need to investigate how Indigenous Knowledge Systems, and particularly Pattern Thinking, might hint toward a possible paradigm shift for the ethical and advanced design of new technologies. This article examines the implications of such a hypothetical shift in autonomous systems in robotics and artificial intelligence (AI), using the Indigenous Robotics Prototype Workshop as a case study and springboard.

Ayanian, N, Fitch, R, Franchi, A & Sabattini, L 2017, 'Multirobot systems', IEEE Robotics and Automation Magazine, vol. 24, no. 2, pp. 12-16.
View/Download from: UTS OPUS or Publisher's site
View description>>

The Technical Committee (TC) on Multirobot Systems (MRS) was founded in 2014 to create a focal point for the wide and diverse community of researchers interested in MRS. Researchers interested in MRS represent an inherently diverse community because several competences are needed in this field, including control systems, mechanical design, coordination, cooperation, estimation, perception, and interaction. MRS research comprises three broad research areas. These areas of interest are modeling and control of MRS, planning and decision making for MRS, and applications of MRS and technological and methodological issues. The MRS TC sponsors many activities that bring our members together, both in person and online. Our flagship achievement to date is the founding of a new conference dedicated to multirobot and multiagent systems, the International Symposium on Multirobot and Multiagent Systems.

Banihashemi, S, Ding, G & Wang, J 2017, 'Developing a Hybrid Model of Prediction and Classification Algorithms for Building Energy Consumption', Energy Procedia, vol. 110, pp. 371-376.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 The Authors. Artificial intelligence algorithms have been applied separately or integrally for prediction, classification or optimization of buildings energy consumption. However, there is a salient gap in the literature on the investigation of hybrid objective function development for energy optimization problems including qualitative and quantitative datasets in their constructs. To tackle with this challenge, this paper presents a hybrid objective function of machine learning algorithms in optimizing energy consumption of residential buildings through considering both continuous and discrete parameters of energy simultaneously. To do this, a comprehensive dataset including significant parameters of building envelop, building design layout and HVAC was established, Artificial Neural Network as a prediction and Decision Tree as a classification algorithm were employed via cross-training ensemble equation to create the hybrid function and the model was finally validated via the weighted average of the error decomposed for the performance. The developed model could effectively enhance the accuracy of the objective functions used in the building energy prediction and optimization problems. Furthermore, the results of this novel approach resolved the inclusion issue of both continuous and discrete parameters of energy in a unified objective function without threatening the integrity and consistency of the building energy datasets.

Carmichael, MG, Liu, D & Waldron, KJ 2017, 'A framework for singularity-robust manipulator control during physical human-robot interaction', International Journal of Robotics Research.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017, The Author(s) 2017. Collaborative robot manipulators are being used to assist human workers performing physically intensive tasks. The finite reach of the manipulator often results in the robot being operated in proximity to kinematic singularity, negatively affecting the stability and performance of operation. Methods of controlling manipulators in the proximity of singularities and mitigating their effects on performance have been widely researched. However, little attention has been given to developing suitable methods for handling singularities specifically for applications where the manipulator physically interacts with a human operator. In these applications additional factors such as human comfort and interaction experience need to be considered. This work presents a framework for handling robotic singularities developed with the human operator in mind. Singularity robustness is achieved using a novel approach to dampen motion of the manipulator along singular directions. An exponential scaling shapes the damping to create a smooth behavior beneficial for physical human–robot interaction. The damping is applied asymmetrically depending on if the robot is heading towards or away from singular configurations, improving the interaction experience for the human operator. Additionally, bounded virtual forces are used to subtly guide the operator away from singular configurations. The proposed framework is validated in simulation and tested on an industrial manipulator.

Falque, R, Vidal-Calleja, T & Miro, JV 2017, 'Defect Detection and Segmentation Framework for Remote Field Eddy Current Sensor Data.', Sensors (Basel, Switzerland), vol. 17, no. 10.
View/Download from: UTS OPUS or Publisher's site
View description>>

Remote-Field Eddy-Current (RFEC) technology is often used as a Non-Destructive Evaluation (NDE) method to prevent water pipe failures. By analyzing the RFEC data, it is possible to quantify the corrosion present in pipes. Quantifying the corrosion involves detecting defects and extracting their depth and shape. For large sections of pipelines, this can be extremely time-consuming if performed manually. Automated approaches are therefore well motivated. In this article, we propose an automated framework to locate and segment defects in individual pipe segments, starting from raw RFEC measurements taken over large pipelines. The framework relies on a novel feature to robustly detect these defects and a segmentation algorithm applied to the deconvolved RFEC signal. The framework is evaluated using both simulated and real datasets, demonstrating its ability to efficiently segment the shape of corrosion defects.

Fitch, R, Best, G & Martens, W 2017, 'Path Planning With Spatiotemporal Optimal Stopping for Stochastic Mission Monitoring', IEEE Transactions on Robotics, vol. 33, no. 3, pp. 629-646.
View/Download from: UTS OPUS or Publisher's site
View description>>

We consider an optimal stopping formulation of the mission monitoring problem, in which a monitor vehicle must remain in close proximity to an autonomous robot that stochastically follows a predicted trajectory. This problem arises in a diverse range of scenarios, such as autonomous underwater vehicles supervised by surface vessels, pedestrians monitored by aerial vehicles, and animals monitored by agricultural robots. The key problem characteristics we consider are that the monitor must remain stationary while observing the robot, robot motion is modeled in general as a stochastic process, and observations are modeled as a spatial probability distribution. We propose a resolution-complete algorithm that runs in a polynomial time. The algorithm is based on a sweep-plane approach and generates a motion plan that maximizes the expected observation time and value. A variety of stochastic models may be used to represent the robot trajectory. We present results with data drawn from real AUV missions, a real pedestrian trajectory dataset and Monte Carlo simulations. Our results demonstrate the performance and behavior of our algorithm, and relevance to a variety of applications.

Ge, XJ, Livesey, P, Wang, J, Huang, SD, He, X & Zhang, CQ 2017, 'Deconstruction waste management through 3D reconstruction and BIM: a case study', Visualization in Engineering, vol. 5, no. 1.
View/Download from: UTS OPUS or Publisher's site
View description>>

The construction industry is responsible for 50% of the solid waste generated worldwide. Governments around the world formulate legislation and regulations concerning recycling and re-using building materials, aiming to reduce waste and environmental impact. Researchers have also been developing strategies and models of waste management for construction and demolition of buildings. The application of Building Information Modeling (BIM) is an example of this. BIM is emergent technology commonly used to maximize the efficiency of design, construction and maintenance throughout the entire lifecycle. The uses of BIM on deconstruction or demolition are not common; especially the fixtures and fittings of buildings are not considered in BIM models. The development of BIM is based on two-dimensional drawings or sketches, which may not be accurately converted to 3D BIM models. In addition, previous researches mainly focused on construction waste management. There are few studies about the deconstruction waste management focusing on demolition. To fill this gap, this paper aims to develop a framework using a reconstructed 3D model with BIM, for the purpose of improving BIM accuracy and thus developing a deconstruction waste management system to improve demolition efficiency, effective recycling and cost savings. In particular, the developed as-built BIM will be used to identify and measure recyclable materials, as well as to develop a plan for the recycling process.

Ghaffari Jadidi, M, Miro, JV & Dissanayake, G 2017, 'Warped Gaussian Processes Occupancy Mapping With Uncertain Inputs', IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 680-687.
View/Download from: UTS OPUS or Publisher's site

Hassan, M & Liu, D 2017, 'Simultaneous area partitioning and allocation for complete coverage by multiple autonomous industrial robots', Autonomous Robots, vol. 41, no. 8, pp. 1609-1628.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017, Springer Science+Business Media New York. For tasks that require complete coverage of surfaces by multiple autonomous industrial robots, it is important that the robots collaborate to appropriately partition and allocate the surface areas amongst themselves such that the robot team’s objectives are optimized. An approach to this problem is presented, which takes into account unstructured and complex 3D environments, and robots with different capabilities. The proposed area partitioning and allocation approach utilizes Voronoi partitioning to partition objects’ surfaces, and multi-objective optimization to allocate the partitioned areas to the robots whilst optimizing robot team’s objectives. In addition to minimizing the overall completion time and achieving complete coverage, which are objectives particularly useful for applications such as surface cleaning, manipulability measure and joint’s torque are also optimized so as to help autonomous industrial robots to operate better in applications such as spray painting and grit-blasting. The approach is validated using six case studies that consist of comparative studies, complex simulated scenarios as well as real scenarios using data obtained from real objects and applications.

Huang, S & Dissanayake, G 2017, 'Special Issue on Localization and Mapping in Challenging Environments', Robotics and Autonomous Systems, vol. 97, pp. 16-17.
View/Download from: UTS OPUS or Publisher's site

Li, Q, Xiong, R & Vidal-Calleja, T 2017, 'A GMM based uncertainty model for point clouds registration', Robotics and Autonomous Systems, vol. 91, pp. 349-362.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2016 Elsevier B.V.The existing methods for the registration of point clouds acquired by laser scanners have some limitations. Firstly, as some samples of surface, a point cloud acquired by the laser scanner, which normally works in a spherical fashion, has very limited density when the surface is far away from the laser scanner and the density varies a lot at different ranges. Current registration methods cannot accurately model the surface uncertainty for such kind of point clouds of limited and large varying density. Secondly, when the point cloud is acquired while the platform is simultaneously moving, the estimation error of the platform motion makes the acquired point cloud distorted. To deal with these problems, in this paper, we propose an uncertainty model based on the Gaussian Mixture Model (GMM) to represent the point cloud. Specifically, we construct the GMM piece-wisely on the underlying surface of point cloud, which will accurately model the surface uncertainty. Also a hierarchical structure is employed to increase the robustness of the registration. Furthermore, by assigning each Gaussian component with a pose, a probabilistic graph can be constructed to tackle the problem of registration when the platform is moving while scanning. In this way the distorted point cloud, caused by the estimation error of the platform's motion, can be corrected by performing graph optimization. Simulation and real world experimental results show that our method leads to better convergence than the state-of-the-art methods due to the accurate modeling of the surface uncertainty and the hierarchical structure, and it also enables us to correct the distorted point clouds.

Liao, Y, Kodagoda, S, Wang, Y, Shi, L & Liu, Y 2017, 'Place Classification With a Graph Regularized Deep Neural Network', IEEE Transactions on Cognitive and Developmental Systems, vol. 9, no. 4, pp. 304-315.
View/Download from: UTS OPUS or Publisher's site

Martens, W, Poffet, Y, Soria, PR, Fitch, R & Sukkarieh, S 2017, 'Geometric Priors for Gaussian Process Implicit Surfaces', IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 373-380.
View/Download from: UTS OPUS or Publisher's site
View description>>

This paper presents an extension of Gaussian process implicit surfaces (GPIS) by the introduction of geometric object priors. The proposed method enhances the probabilistic reconstruction of objects from three-dimensional (3-D) pointcloud data, providing a rigorous way of incorporating prior knowledge about objects expected in a scene. The key ideas, including the systematic use of surface normal information, are illustrated with one-dimensional and two-dimensional examples, and then applied to simulated and real pointcloud data for 3-D objects. The performance of our method is demonstrated in two different application scenarios, using complete and partial surface observations. Qualitative and quantitative analysis of the results reveals the superiority of the proposed approach over existing GPIS configurations that do not exploit prior knowledge.

Nguyen, LV, Kodagoda, S, Ranasinghe, R & Dissanayake, G 2017, 'Adaptive Placement for Mobile Sensors in Spatial Prediction under Locational Errors', IEEE Sensors Journal, vol. 17, no. 3, pp. 794-802.
View/Download from: UTS OPUS or Publisher's site

Nguyen, LV, Nguyen, HT & Le, HX 2017, 'Efficient Approach for Maximizing Lifespan in Wireless Sensor Networks by Using Mobile Sinks', ETRI Journal, vol. 39, no. 3, pp. 353-363.
View/Download from: UTS OPUS or Publisher's site
View description>>

Recently, sink mobility has been shown to be highly beneficial in improving network lifetime in wireless sensor networks (WSNs). Numerous studies have exploited mobile sinks (MSs) to collect sensed data in order to improve energy efficiency and reduce WSN operational costs. However, there have been few studies on the effectiveness of MS operation on WSN closed operating cycles. Therefore, it is important to investigate how data is collected and how to plan the trajectory of the MS in order to gather data in time, reduce energy consumption, and improve WSN network lifetime. In this study, we combine two methods, the cluster‐head election algorithm and the MS trajectory optimization algorithm, to propose the optimal MS movement strategy. This study aims to provide a closed operating cycle for WSNs, by which the energy consumption and running time of a WSN is minimized during the cluster election and data gathering periods. Furthermore, our flexible MS movement scenarios achieve both a long network lifetime and an optimal MS schedule. The simulation results demonstrate that our proposed algorithm achieves better performance than other well‐known algorithms.

Norouzi, M, Miro, JV & Dissanayake, G 2017, 'Planning Stable and Efficient Paths for Reconfigurable Robots On Uneven Terrain', Journal of Intelligent and Robotic Systems: Theory and Applications, vol. 87, no. 2, pp. 291-312.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017, Springer Science+Business Media Dordrecht. An analytical strategy to generate stable paths for reconfigurable mobile robots such as those equipped with manipulator arms and/or flippers, operating in an uneven environment whilst also meeting additional navigational objectives is hereby proposed. The suggested solution looks at minimising the length of the traversed path and the energy expenditure in changing postures, and also accounts for additional constraints in terms of sensor visibility and traction. This is particularly applicable to operations such as search and rescue where observing the environment for locating victims is the major objective, although this technique can be generalised to incorporate other potentially conflicting objectives (e.g. maximising ground clearance for a legged robot). The validity of the proposed approach is evaluated with two popular graph-based planners (A* and RRT) on a multi-tracked robot fitted with a manipulator arm and a range camera. Two challenging 3D terrain data sets have been employed: one obtained whilst operating the robot in a mock-up urban search and rescue (USAR) arena, and a second one, a reference on-line data set acquired on the quasi-outdoor rover testing facility at the University of Toronto Institute for Aerospace Studies (UTIAS).

Pagano, D & Liu, D 2017, 'An approach for real-time motion planning of an inchworm robot in complex steel bridge environments', Robotica, vol. 35, no. 6, pp. 1280-1309.
View/Download from: UTS OPUS or Publisher's site
View description>>

Copyright © Cambridge University Press 2016 Path planning can be difficult and time consuming for inchworm robots especially when operating in complex 3D environments such as steel bridges. Confined areas may prevent a robot from extensively searching the environment by limiting its mobility. An approach for real-time path planning is presented. This approach first uses the concept of line-of-sight (LoS) to find waypoints from the start pose to the end node. It then plans smooth, collision-free motion for a robot to move between waypoints using a 3D-F2 algorithm. Extensive simulations and experiments are conducted in 2D and 3D scenarios to verify the approach.

Quin, P, Paul, G & Liu, D 2017, 'Experimental Evaluation of Nearest Neighbour Exploration Approach in Field Environments', IEEE Transactions on Automation Science and Engineering, vol. 14, no. 2, pp. 869-880.
View/Download from: UTS OPUS or Publisher's site
View description>>

Inspecting surface conditions in 3-D environments such as steel bridges is a complex, time-consuming, and often hazardous undertaking that is an essential part of tasks such as bridge maintenance. Developing an autonomous exploration strategy for a mobile climbing robot would allow for such tasks to be completed more quickly and more safely than is possible with human inspectors. The exploration strategy tested in this paper, called the nearest neighbors exploration approach (NNEA), aims to reduce the overall exploration time by reducing the number of sensor position evaluations that need to be performed. NNEA achieves this by first considering at each time step only a small set of poses near to the current robot as candidates for the next best view. This approach is compared with another exploration strategy for similar robots performing the same task. The improvements between the new and previous strategy are demonstrated through trials on a test rig, and also in field trials on a ferromagnetic bridge structure.

Skinner, B, McPhee, MJ, Walmsley, BJ, Littler, B, Siddell, J, M.Cafe, L, Wilkins, JF, Oddy, VH & Alempijevic, A 2017, 'Live animal assessments of rump fat and muscle score in Angus cows and steers using 3-dimensional imaging', Journal of Animal Science, vol. 95, no. 4, pp. 1847-1857.
View/Download from: UTS OPUS or Publisher's site
View description>>

The objective of this study was to develop a proof of concept for using off-the-shelf Red Green Blue-Depth (RGB-D) Microsoft Kinect cameras to objectively assess P8 rump fat (P8 fat; mm) and muscle score (MS) traits in Angus cows and steers. Data from low and high muscled cattle (156 cows and 79 steers) were collected at multiple locations and time points. The following steps were required for the 3-dimensional (3D) image data and subsequent machine learning techniques to learn the traits: 1) reduce the high dimensionality of the point cloud data by extracting features from the input signals to produce a compact and representative feature vector, 2) perform global optimization of the signatures using machine learning algorithms and a parallel genetic algorithm, and 3) train a sensor model using regression-supervised learning techniques on the ultrasound P8 fat and the classified learning techniques for the assessed MS for each animal in the data set. The correlation of estimating hip height (cm) between visually measured and assessed 3D data from RGB-D cameras on cows and steers was 0.75 and 0.90, respectively. The supervised machine learning and global optimization approach correctly classified MS (mean [SD]) 80 (4.7) and 83% [6.6%] for cows and steers, respectively. Kappa tests of MS were 0.74 and 0.79 in cows and steers, respectively, indicating substantial agreement between visual assessment and the learning approaches of RGB-D camera images. A stratified 10-fold cross-validation for P8 fat did not find any differences in the mean bias ( = 0.62 and = 0.42 for cows and steers, respectively). The root mean square error of P8 fat was 1.54 and 1.00 mm for cows and steers, respectively. Additional data is required to strengthen the capacity of machine learning to estimate measured P8 fat and assessed MS. Data sets for and continental cattle are also required to broaden the use of 3D cameras to assess cattle. The results demonstrate the importance of capturing curv...

Ulapane, N, Alempijevic, A, Vidal Calleja, T & Valls Miro, J 2017, 'Pulsed Eddy Current Sensing for Critical Pipe Condition Assessment.', Sensors (Basel, Switzerland), vol. 17, no. 10.
View/Download from: UTS OPUS or Publisher's site
View description>>

Pulsed Eddy Current (PEC) sensing is used for Non-Destructive Evaluation (NDE) of the structural integrity of metallic structures in the aircraft, railway, oil and gas sectors. Urban water utilities also have extensive large ferromagnetic structures in the form of critical pressure pipe systems made of grey cast iron, ductile cast iron and mild steel. The associated material properties render NDE of these pipes by means of electromagnetic sensing a necessity. In recent years PEC sensing has established itself as a state-of-the-art NDE technique in the critical water pipe sector. This paper presents advancements to PEC inspection in view of the specific information demanded from water utilities along with the challenges encountered in this sector. Operating principles of the sensor architecture suitable for application on critical pipes are presented with the associated sensor design and calibration strategy. A Gaussian process-based approach is applied to model a functional relationship between a PEC signal feature and critical pipe wall thickness. A case study demonstrates the sensor's behaviour on a grey cast iron pipe and discusses the implications of the observed results and challenges relating to this application.

Wang, S, Kodagoda, S, Shi, L & Wang, H 2017, 'Road-Terrain Classification for Land Vehicles: Employing an Acceleration-Based Approach', IEEE Vehicular Technology Magazine, vol. 12, no. 3, pp. 34-41.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. The perception of the environment around a land vehicle plays a crucial role for its driving assistant system. Knowledge of the road terrain is useful for handling its characteristics while driving the vehicles and improving passengers' safety and comfort. In this article, an approach to classifying road-terrain vehicles is presented. An accelerometer is mounted on the suspension of the vehicle to measure the vibration that represents the characteristics of the road terrain, and the road profile can be calculated by knowing the speed and one-quarter-dynamic model of the vehicle. The optimized classifier and features, speed independency, and the effect of employing principal component analysis (PCA) are investigated, and the simulation shows that this acceleration-based approach is feasible for land vehicles in a range of outdoor scenarios.

Wang, S, Kodagoda, S, Shi, L & Xu, N 2017, 'Lidar-based road terrain recognition for passenger vehicles', International Journal of Vehicle Design, vol. 74, no. 2, pp. 153-165.
View/Download from: UTS OPUS or Publisher's site
View description>>

Copyright © 2017 Inderscience Enterprises Ltd. The road terrain type is important information about a passenger vehicle’s surroundings. It suggests an appropriate control algorithm and driving strategy. In this paper, a Lidar sensor is employed to reconstruct the road surface and extract features for terrain classification. The experiment vehicle was driven on four specific road terrains at a variety of speeds. The speed dependency and the effect of using principal component analysis were investigated. The simulation experimental results show that this Lidar sensor-based approach is feasible and robust for passenger vehicles in a range of outdoor scenarios.

Wang, X & Wang, JG 2017, 'Detecting glass in Simultaneous Localisation and Mapping', Robotics and Autonomous Systems, vol. 88, pp. 97-103.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2016 Simultaneous Localisation and Mapping (SLAM) has become one of key technologies used in advanced robot platform. The current state-of-art indoor SLAM with laser scanning rangefinders can provide accurate realtime localisation and mapping service to mobile robotic platforms such as PR2 robot. In recent years, many modern building designs feature large glass panels as one of the key interior fitting elements, e.g. large glass walls. Due to the transparent nature of glass panels, laser rangefinders are unable to produce accurate readings which causes SLAM functioning incorrectly in these environments. In this paper, we propose a simple and effective solution to identify glass panels based on the specular reflection of laser beams from the glass. Specifically, we use a simple technique to detect the reflected light intensity profile around the normal incident angle to the glass panel. Integrating this glass detection method with an existing SLAM algorithm, our SLAM system is able to detect and localise glass obstacles in realtime. Furthermore, the tests we conducted in two office buildings with a PR2 robot show the proposed method can detect ∼95% of all glass panels with no false positive detection. The source code of the modified SLAM with glass detection is released as a open source ROS package along with this paper.

Zhang, J, Xiao, W, Zhang, S & Huang, S 2017, 'Device-Free Localization via an Extreme Learning Machine with Parameterized Geometrical Feature Extraction.', Sensors (Basel, Switzerland), vol. 17, no. 4.
View/Download from: UTS OPUS or Publisher's site
View description>>

Device-free localization (DFL) is becoming one of the new technologies in wireless localization field, due to its advantage that the target to be localized does not need to be attached to any electronic device. In the radio-frequency (RF) DFL system, radio transmitters (RTs) and radio receivers (RXs) are used to sense the target collaboratively, and the location of the target can be estimated by fusing the changes of the received signal strength (RSS) measurements associated with the wireless links. In this paper, we will propose an extreme learning machine (ELM) approach for DFL, to improve the efficiency and the accuracy of the localization algorithm. Different from the conventional machine learning approaches for wireless localization, in which the above differential RSS measurements are trivially used as the only input features, we introduce the parameterized geometrical representation for an affected link, which consists of its geometrical intercepts and differential RSS measurement. Parameterized geometrical feature extraction (PGFE) is performed for the affected links and the features are used as the inputs of ELM. The proposed PGFE-ELM for DFL is trained in the offline phase and performed for real-time localization in the online phase, where the estimated location of the target is obtained through the created ELM. PGFE-ELM has the advantages that the affected links used by ELM in the online phase can be different from those used for training in the offline phase, and can be more robust to deal with the uncertain combination of the detectable wireless links. Experimental results show that the proposed PGFE-ELM can improve the localization accuracy and learning speed significantly compared with a number of the existing machine learning and DFL approaches, including the weighted K-nearest neighbor (WKNN), support vector machine (SVM), back propagation neural network (BPNN), as well as the well-known radio tomographic imaging (RTI) DFL approach.

Zhang, T, Wu, K, Song, J, Huang, S & Dissanayake, G 2017, 'Convergence and Consistency Analysis for a 3-D Invariant-EKF SLAM', IEEE Robotics and Automation Letters, vol. 2, no. 2, pp. 733-740.
View/Download from: UTS OPUS or Publisher's site

Alvarez, JK, Sutjipto, S & Kodagoda, S 2017, 'Validated Ground Penetrating Radar Simulation Model for Estimating Rebar Location in Infrastructure Monitoring', 2017 IEEE 12th Conference on Industrial Electronics and Applications, Siem Reap, pp. 1457-1462.
View/Download from: UTS OPUS

Arora, A, Fitch, R & Sukkarieh, S 2017, 'An Approach to Autonomous Science by Modeling Geological Knowledge in a Bayesian Framework', Proc. of IEEE/RSJ IROS, International Conference on Intelligent Robots and Systems, IEEE, Vancouver, BC, Canada.
View/Download from: UTS OPUS or Publisher's site
View description>>

Autonomous Science is a field of study which aims to extend the autonomy of exploration robots from low level functionality, such as on-board perception and obstacle avoidance, to science autonomy, which allows scientists to specify missions at task level. This will enable more remote and extreme environments such as deep ocean and other planets to be studied, leading to significant science discoveries. This paper presents an approach to extend the high level autonomy of robots by enabling them to model and reason about scientific knowledge on-board. We achieve this by using Bayesian networks to encode scientific knowledge and adapting Monte Carlo Tree Search techniques to reason about the network and plan informative sensing actions. The resulting knowledge representation and reasoning framework is anytime, handles large state spaces and robust to uncertainty making it highly applicable to field robotics. We apply the approach to a Mars exploration mission in which the robot is required to plan paths and decide when to use its sensing modalities to study a scientific latent variable of interest. Extensive simulation results show that our approach has significant performance benefits over alternative methods. We also demonstrate the practicality of our approach in an analog Martian environment where our experimental rover, Continuum, plans and executes a science mission autonomously.

Arukgoda, J, Ranasinghe, R, Dantanarayana, L, Dissanayake, G & Furukawa, T 2017, 'Vector Distance Function Based Map Representation for Robot Localisation', Australasian Conference on Robotics and Automation, Australasian Conference on Robotics and Automation, ACRA, Sydney Australia, pp. 1-8.
View/Download from: UTS OPUS
View description>>

This paper introduces the use of the vector distance function (VDF) for representing environments, particularly for the use in localisation algorithms. It is shown that VDF has a continuous derivative at the object boundary in contrast to unsigned distance transform, and does not require an environment populated with closed object as in the case of the signed distance transforms, the two most common strategies reported in the literature for representing environments based on distances to nearest occupied regions. As such VDF overcomes the main disadvantages of the existing distance transform based representations in the context of robot localisation. The key properties of VDF are demonstrated and the use of VDF in robot localisation using an optimization based algorithm is illustrated using three examples. It is shown that the proposed environment representation and the localisation algorithm is effective in providing accurate location estimates as well as the associated uncertainties

Arukgoda, J, Ranasinghe, R, Danthanarayana, L, Dissanayake, G & Furukawa, T 2017, 'Vector distance function based map representation for robot localisation', Australasian Conference on Robotics and Automation, ACRA, pp. 165-172.
View description>>

This paper introduces the use of the vector distance function (VDF) for representing environments, particularly for the use in localisation algorithms. It is shown that VDF has a continuous derivative at the object boundary in contrast to unsigned distance transform, and does not require an environment populated with closed object as in the case of the signed distance transforms, the two most common strategies reported in the literature for representing environments based on distances to nearest occupied regions. As such VDF overcomes the main disadvantages of the existing distance transform based representations in the context of robot localisation. The key properties of VDF are demonstrated and the use of VDF in robot localisation using an optimization based algorithm is illustrated using three examples. It is shown that the proposed environment representation and the localisation algorithm is effective in providing accurate location estimates as well as the associated uncertainties.

Carmichael, MG, Aldini, S & Liu, D 2017, 'Human user impressions of damping methods for singularity handling in human-robot collaboration', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Australia, pp. 107-113.
View/Download from: UTS OPUS
View description>>

Kinematic singularity is a fundamental and well understood problem of robot manipulators, with many methods having been developed to ensure safe and robust operation in proximity to singularity. However little attention has been given to the scenario where the robot and human are working in physical contact to collaboratively perform a task. In such a scenario the feelings and impressions of the human operator should be considered when developing solutions for handling singularity. This work presents an experimental study comparing three modes of handling kinematic singularities with respect to the impressions of the human operator. Two of the modes are based on traditional Damped-Least-Squares. The third method uses an asymmetric damping behavior proposed as being well suited for applications involving physical human-robot interaction. The three modes are tested and compared by subjects performing a mock industrial task, and feedback from the subjects analyzed to identify the preferred mode. Results indicate that the choice of method used affects the user's impressions of the interaction, and the asymmetrical damping behavior can produce a preferred interaction experience with human operators during tasks.

Chen, S, Doan, VH & Zhao, L 2017, 'Heart simulator: A periodic pump to simulate the cardiac motion in an aortic test-rig', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Sydney, Australia, pp. 100-106.
View/Download from: UTS OPUS
View description>>

A periodic pump that simulates blood ejection from human heart to aorta is the core element for building an aortic robotics test-rig. This paper is to describe the design of such a prototype human heart simulator and its performance under different working status, such as simulating the physiological states of a healthy adult and/or a child in sleep, relax and physical exercise. By balancing the cost and performance, this prototype has these specifications: (1) Using ordinary plumbing components and water to simulate the cardiac motion and blood flow. (2) Simulating the volume change of human heart chamber by controlling movement of a mechanical piston. (3) Performing a friendly user interface and delicate control via a MCU system with high reliability. (4) Simulated physiological output parameters such as volume per stroke, heart beat rate and waveform can be easily adjusted and monitored in real-time.

Chen, Y, Huang, S, Fitch, R & Yu, J 2017, 'Efficient Active SLAM based on Submap Joining', Proc. of ARAA ACRA, Australasian Conference on Robotics and Automation, ARAA, Sydney, Australia, pp. 1-7.
View/Download from: UTS OPUS
View description>>

This paper considers the active SLAM problem where a robot is required to cover a given area while at the same time performing simultaneous localization and mapping (SLAM) for understanding the environment and localizing the robot itself. We propose a model predictive control (MPC) framework, and the minimization of uncertainty in SLAM and coverage problems are solved respectively by the Sequential Quadratic Programming (SQP) method. Then, a decision making process is used to control the switching of two control inputs. In order to reduce the estimation and planning time, we use Linear SLAM, which is a submap joining approach. Simulation results are presented to validate the effectiveness of the proposed active SLAM strategy.

Collart, J, Fitch, R & Alempijevic, A 2017, 'Motion States Inference through 3D Shoulder Gait Analysis and Hierarchical Hidden Markov Models', Australasian Conference on Robotics and Automation 2017, Australasian Conference on Robotics and Automation, ARAA, Sydney, Australia, pp. 1-8.
View/Download from: UTS OPUS
View description>>

Automatically inferring human intention from walking movements is an important research concern in robotics and other fields of study. It is generally derived from temporal motion of limb position relative to the body. These changes can also be reflected in the change of stance and gait. Conventional systems relying on gait are usually based on tracking the lower body motion (hip, foot) and are extracted from monocular camera data. However, such data can be inaccessible in crowded environments where occlusions of the lower body are prevalent. This paper proposes a novel approach to utilize upper body 3D-motion and Hierarchical Hidden Markov Models to estimate human ambulatory states, such as quietly standing, starting to walk (gait initiation), walking (gait cycle), or stopping (gait termination). Methods have been tested on real data acquired through a motion capture system where foot measurements (heels and toes) were used as ground truth data for labeling the states to train and test the models. Current results demonstrate the feasibility of using such a system to infer lower-body motion states and sub-states through observations of 3D shoulder motion online. Our results enable applications in situations where only upper body motion is readily observable.

Furukawa, T, Kang, C, Li, B & Dissanayake, G 2017, 'Multi-stage Bayesian target estimation by UAV using fisheye lens camera and pan/tilt camera', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vancouver, BC, Canada, pp. 4167-4172.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. This paper presents a generalized multi-stage Bayesian approach for an unmanned aerial vehicle to estimate the location of a mobile target. The major hardware components of the proposed approach are a camera with a fisheye lens and another camera with a normal lens and a pan/tilt unit. With wide angle of view (AOV), the fisheye lens camera first detects the bearing of the target, and the PT camera next captures the target in its AOV. The recursive Bayesian estimation steadily locates the target in a globally defined space. The paper also proposes a multi-stage detection method for the fisheye lens camera. The level of confidence is defined in association with the probability of detection (POD) for each detection technique, and the fisheye lens enables continuous detection by gradually increasing the POD. The observation likelihood is finally derived from the POD in a generalized manner. The proposed approach was applied to the detection of a mobile target by a multi-rotor helicopter, and results have demonstrated the effectiveness of both the proposed multi-stage Bayesian approach and multi-stage fisheye lens detection method.

Han, H, Paul, G & Matsubara, T 2017, 'Model-Based Reinforcement Learning Approach for Deformable Linear Object Manipulation', 2017 13th IEEE Conference on Automation Science and Engineering (CASE), IEEE Conference on Automation Science and Engineering, IEEE, Xi'an, China.
View/Download from: UTS OPUS
View description>>

Deformable Linear Object (DLO) manipulation has wide application in industry and in daily life. Conventionally, it is difficult for a robot to manipulate a DLO to achieve the target configuration due to the absence of the universal model that specifies the DLO regardless of the material and environment. Since the state variable of a DLO can be very high dimensional, identifying such a model may require a huge number of samples. Thus, model-based planning of DLO manipulation would be impractical and unreasonable. In this paper, we explore another approach based on reinforcement learning. To this end, our approach is to apply a sample-efficient model-based reinforcement learning method, so-called PILCO, to resolve the high dimensional planning problem of DLO manipulation with a reasonable number of samples. To investigate the effectiveness of our approach, we developed an experimental setup with a dual-arm industrial robot and multiple sensors. Then, we conducted experiments to show that our approach is efficient by performing a DLO manipulation task.

Huang, S, Wu, K, Zhang, T, Su, D & Dissanayake, G 2017, 'An Invariant-EKF VINS Algorithm for Improving Consistency', IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vancouver, Canada, pp. 1578-1585.
View/Download from: UTS OPUS

Iversen, TF, Ellekilde, LP & Miro, JV 2017, 'Adaptive motion planning in bin-picking with object uncertainties', International Conference on Control, Automation and Systems, International Conference on Control, Automation and Systems, IEEE, Jeju, South Korea, pp. 921-928.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 Institute of Control, Robotics and Systems - ICROS. Doing motion planning for bin-picking with object uncertainties requires either a re-grasp of picked objects or an online sensor system. Using the latter is advantageous in terms of computational time, as no time is wasted doing an extra pick and place action. It does, however, put extra requirements on the motion planner, as the target position may change on-the-fly. This paper solves that problem by using a state adjusting Partial Observable Markov Decision Process, where the state space is modified between runs, to better fit earlier solved problems. The approach relies on a set of waypoints, containing information about which parts of the state space may contain feasible solutions. Waypoints are pushed around the state space by observing which states in the neighborhood lead to successfully solved problems. Two bin-picking scenarios are modeled with the proposed method. One scenario in which the system receives an object pose update while moving towards the place position. Another where the update includes the object type being grasped out of a fixed number of options, each class to be deposited in a different place. When an online POMDP solver is utilized, the state adjusting POMDP is improving performance by up to 28% on execution times compared to a not adjusted POMDP.

Jadidi, MG, Patel, M & Miro, JV 2017, 'Gaussian processes online observation classification for RSSI-based low-cost indoor positioning systems', Proceedings - IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Singapore, Singapore, pp. 6269-6275.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. In this paper, we propose a real-time classification scheme to cope with noisy Radio Signal Strength Indicator (RSSI) measurements utilized in indoor positioning systems. RSSI values are often converted to distances for position estimation. However due to multipathing and shadowing effects, finding a unique sensor model using both parametric and non-parametric methods is highly challenging. We learn decision regions using the Gaussian Processes classification to accept measurements that are consistent with the operating sensor model. The proposed approach can perform online, does not rely on a particular sensor model or parameters, and is robust to sensor failures. The experimental results achieved using hardware show that available positioning algorithms can benefit from incorporating the classifier into their measurement model as a meta-sensor modeling technique.

Khonasty, R, Carmichael, MG, Liu, D & Aldini, S 2017, 'Effect of External Force and Bimanual Operation on Upper Limb Pose during Human-Robot Collaboration', Australasian Conference on Robotics and Automation 2017, Australasian Conference on Robotics and Automation, ARAA, Sydney Australia, pp. 1-9.
View/Download from: UTS OPUS
View description>>

During physical Human-Robot Interaction (pHRI) in industrial applications such as human-robot collaborative abrasive blasting, the operator often interacts with the robot using two hands, exchanging forces through handle bars. For the robot to provide appropriate assistance to the operator and for safe interaction, it would be beneficial for the robot to know the pose of the user. This problem is often challenging due to environmental factors, limited sensing capability in the environment and the robot, and redundancy of the human upper-limb. This paper presents experimental study on how two-hand interaction and force exchange affect the operators upper-limb pose, which can be characterized by swivel angle. The poses of ten subjects were recorded as they interacted with a collaborative robot. Differences in the adopted upper limb pose were analyzed with respect to factors such as unimanual versus bimanual operation, and the amplitude of interaction force between an operator and the robot. The results discovered that the the effect of bimanual operation on the upper limb pose differs between individuals and the magnitude of the force had a varying effect on the pose. The requirement of applying a force forward produced an overall lower swivel angle

Khonasty, R, Carmichael, MG, Liu, D & Waldron, K 2017, 'Upper Body Pose Estimation Utilizing Kinematic Constraints from Physical Human-Robot Interaction', Australasian Conference on Robotics and Automation 2017, Australasian Conference on Robotics and Automation, ARAA, Sydney Australia, pp. 1-10.
View/Download from: UTS OPUS
View description>>

In physical Human-Robot Interaction (pHRI), knowing the pose of the operator is beneficial and may allow the robot to better accommodate the human operator. Due to a large redundancy in the human body, determining the pose of the human operator is difficult to achieve in unstructured environments especially in human-robot collaborative operations where the robot often occludes the human from vision-based sensors. This work presents an upper body pose estimation method based on exploiting known positions of the human operator’s hands while performing a task with the robot. Upper body pose is estimated using upper limb kinematic models alongside sensor information and model approximations to produce solutions that are biomechanically feasible. The pose estimation method was compared to upper body poses obtained using a motion capture system. It was shown to be able to perform robustly with varying amounts of available information. This approach is well suited in applications where robots are controlled using well-defined interfaces such as handlebars, operating in unstructured environments.

Lee, JJH, Yoo, C, Hall, R, Anstee, S & Fitch, R 2017, 'Energy-optimal kinodynamic planning for underwater gliders in flow fields', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Sydney, Australia, pp. 42-51.
View/Download from: UTS OPUS
View description>>

We consider energy-optimal navigation planning in ow fields, which is a long-standing optimisation problem with no known analytical solution. Using the motivating example of an underwater glider subject to ocean currents, we present an asymptotically optimal planning framework that considers realistic vehicle dynamics and provably returns an optimal solution in the limit. One key idea that we introduce is to reformulate the dynamic control problem as a kinematic problem with trim states, which encapsulate the dynamics over suitably long distances. We report simulation examples that, surprisingly, contravene the use of regular 'sawtooth' paths currently in widespread use. We show that, when internal control mechanics are taken into account, energy-efficient paths do not necessarily follow a regular up-and-down pattern. Our work represents a principled planning framework for underwater gliders that will enable improved navigation capability for both commercial and defence applications.

Leighton, B, Zhao, L, Huang, S & Dissanayake, G 2017, 'Extending Parallax Parameterised Bundle Adjustment to Stereo', Australasian Conference on Robotics and Automation 2017, Australasian Conference on Robotics and Automation, ARAA, University of Technology, Sydney, pp. 1-9.
View/Download from: UTS OPUS
View description>>

The main contribution of this paper is the extension of the ParllaxBA algorithm proposed by [Zhao et al., 2015] into stereo. Simulated and experimental datasets are used to evaluate Cartesian and parallax angle parameterisation for stereo bundle adjustment. It is demonstrated that, like monocular ParallaxBA, under normal conditions the two algorithms perform similarly. However, when the parallax angle of landmarks is low, parallax parameterisation can converge to a lower cost and in less time than the traditional Cartesian parameterisation

Li, B, Fan, X, Zhang, J, Wang, Y, Chen, F, Kodagoda, S, Wells, T, Vorreiter, L, Vitanage, D, Iori, G, Cunningham, D & Chen, T 2017, 'Predictive Analytics Toolkit for H2S Estimation and Sewer Corrosion', OZWater, Australian Water Association, Sydney.
View/Download from: UTS OPUS
View description>>

This paper presents a predictive analytics toolkit, which is based on the emerging spatiotemporal data analysis techniques, for the estimation of hydrogen sulphide (H2S) gas distribution and prediction of sewer concrete corrosion level. The toolkit is an easy-to-use desktop application with a user-friendly interface for querying and producing output results on GIS. The inputs to the toolkit are the sewer network geometry, monitored factors, and hydraulic information; the outputs of the toolkit are spatiotemporal estimates of H2S gas concentration and concrete corrosion levels on the entire sewer network with uncertainties of the predictions. The toolkit is also able to integrate experts’ domain knowledge or existing physical model’s results as prior knowledge into the analytics model. The final outcomes of the toolkit can be used to prioritise high risk areas, recommend chemical dosing locations, and suggest deployment of sensors. A simulation of H2S and corrosion level prediction on a subsystem of the sewer network in the greater Sydney area is reported to demonstrate the capability of the toolkit

Liao, Y, Huang, L, Wang, Y, Kodagoda, S, Yu, Y & Liu, Y 2017, 'Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation', 2017 IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, IEEE, Singapore, pp. 5059-5066.
View/Download from: UTS OPUS
View description>>

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera. Although those platforms do not have sensors for 3D depth sensing capability, knowledge of full geometry is an essential part in many robotics activities. Therefore, recently, there is an increasing interest in depth estimation using monocular images, of which the estimated depth might be unreliable in robotics applications as this task is inherently ambiguous. In this paper, we have attempted to improve the precision of monocular depth estimation by introducing 2D planar observation from the remaining laser range finder without extra cost. Specifically, we construct a dense reference map from the sparse laser range data, redefining the depth estimation task as estimating the distance between the real and the reference depth. To solve the problem, we construct a novel residual of residual neural network, and tightly combine the classification and regression losses for continuous depth estimation. Experimental results suggest that our method achieves considerable promotion compared to the state-of-the-art methods on both NYUD2 and KITTI, validating the effectiveness of our method on leveraging the additional sensory information. We further demonstrate the potential usage of our method in obstacle avoidance where our methodology provides comprehensive depth information compared to the solution using monocular camera or 2D laser range finder alone.

Liu, D & Nguyen, KD 2017, 'Robust Control of a Brachiating Robot', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), International Conference on Intelligent Robots and Systems, IEEE, Vancouver Canada.
View/Download from: UTS OPUS or Publisher's site
View description>>

This paper investigates the robust control of an underactuated brachiating robot. Inspired by the pendulumlike movements in gibbons' arboreal locomotion, the controllers are designed to synchronize the brachiator with a virtual oscillator. Two schemes are proposed: a model-dependent feedback linearization scheme and a sliding-mode scheme that is independent of the system model. The simulation results illustrate that the proposed schemes are robust to the arbitrary initial configurations of the brachiator and the limitation in the motor torque at the elbow joint. Furthermore, both controllers enable the underactuated robot to brachiate along a structural member with an upward slope.

Liu, L, Wang, Y, Zhao, L & Huang, S 2017, 'Evaluation of Different SLAM Algorithms using Google Tangle Data', 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), IEEE Conference on Industrial Electronics and Applications, IEEE, Siem Reap, Cambodia..
View/Download from: UTS OPUS or Publisher's site
View description>>

In this paper, we evaluate three state-of-the-art Simultaneous Localization and Mapping (SLAM) methods using data extracted from a state-of-the-art device for indoor navigation - the Google Tango tablet. The SLAM algorithms we investigated include Preintegration Visual Inertial Navigation System (VINS), ParallaxBA and ORB-SLAM. We first describe the detailed process of obtaining synchronized IMU and image data from the Google Tango device, then we present some of the SLAM results obtained using the three different SLAM algorithms, all with the datasets collected from Tango. These SLAM results are compared with that obtained from Tango's inbuilt motion tracking system. The advantages and failure modes of the different SLAM algorithms are analysed and illustrated thereafter. The evaluation results presented in this paper are expected to provide some guidance on further development of more robust SLAM algorithms for robotic applications.

Lu, W & Liu, D 2017, 'Active Task Design in Adaptive Control of Redundant Robotic Systems', Australasian Conference on Robotics and Automation 2017, Australasian Conference on Robotics and Automation, ARAA, Sydney Australia, pp. 1-6.
View/Download from: UTS OPUS
View description>>

This paper seeks for possibilities of using robots' kinematic redundancy to excite the system persistently, through actively designing a secondary task in the null space of a primary task. Resulted parameter convergence in adaptive control leads to better system stability and performance. A measure in Grassmannian, referred to as Subspace Discrepancy Measure (SDM), is proposed for evaluating the additional benefit from the secondary task in converging unknown parameters to their true values. This measure evaluates the angles among subspaces that the parameter estimations are converging to, given different secondary tasks. The subspaces are obtained from Principal Component Analysis (PCA) on a small amount of samples of parameter estimations. The SDM is used to determine the choice of the secondary task online through a trial-and-evaluation procedure actively. Numerical simulations demonstrated that the secondary task chosen by SDM enhances the parameter convergence.

Lv, J, Wang, Y, Wu, K, Dissanayake, G, Kobayashi, Y & Xiong, R 2017, 'Planar scan matching using incident angle', IEEE International Conference on Intelligent Robots and Systems, pp. 4049-4056.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. The main contribution of this paper is a planar scan matching algorithm that makes use of the incident angle of a scan point as a feature to enhance the robustness to large relative transformations, particularly in orientation. A new definition of the incident angle is introduced and its consistency with respect to relative transformation between scans is demonstrated. A method that uses the Radial distance and Incident Angle (RIA) for scan alignment, that can efficiently estimate the relative transformation between two scans, is proposed. This approach is designed as a preprocessor for fine scan matching and it is able to pre-align scans that have large angular but limited translational displacement. Scans collected with aggressive robot motion in two typical indoor environments as well as benchmark datasets, are used to demonstrate the effectiveness of RIA when compared with a range of scan matching algorithms reported in the literature.

Munoz, F, Valls Miro, J, Dissanayake, G, Ulapane, N & Nguyen, LV 2017, 'Design of a Lock-in Amplifier Integrated with a Coil System for Eddy-Current Non-Destructive Inspection', Proceedings of the 12th IEEE Conference on Industrial Electronics and Applications, 12th IEEE Conference on Industrial Electronics and Applications, IEEE, Siem Reap, Cambodia, pp. 1948-1953.
View/Download from: UTS OPUS
View description>>

Eddy-current non-destructive inspections of conductive components are of great interest in several industries including civil infrastructure and the mining industry. In this work, we have used a driver-pickup coil system as the probe to carry out inspection of ferromagnetic plates. The specific geometric configuration of the probe generates weak electric signals that are buried in a noisy environment. In order to detect these weak signals, we have designed and implemented a lock-in amplifier as part of the signal processing technique to increase the signal-to-noise ratio and also improve the sensitivity of the probe. We have used Comsol as a finite element method (FEM) to design the probe and conducted experiments with the probe and the lock-in amplifier. The experimental results, which are in agreement with the FEM results, indicate that the designed probe along with a lock-in amplifier can potentially be used to estimate the thickness of thin plates

Nguyen, LV, Hu, G & Spanos, CJ 2017, 'Efficient spatio-temporal sensor deployments: A smart building application', Control & Automation (ICCA), 2017 13th IEEE International Conference on, IEEE, Ohrid, Macedonia, pp. 612-617.
View/Download from: UTS OPUS or Publisher's site
View description>>

The paper addresses the problem of efficiently deploying sensors in spatial environments, e.g. smart buildings, for the purpose of monitoring environmental phenomena. By modelling the environmental fields using spatio-temporal Gaussian processes, a new and efficient optimality criterion of minimizing prediction uncertainties is proposed to find the best sensor locations. Though the environmental processes spatially and temporally vary, the proposed approach of choosing sensor positions is not affected by time variations, which significantly reduces computational complexity of the optimization problem. The sensor deployment problem is then solved by a practically and feasibly polynomial algorithm, where its solutions are guaranteed. The proposed approaches were implemented in a real tested space in a university building, where the obtained results are highly promising.

Nguyen, LV, Hu, G & Spanos, CJ 2017, 'Spatio-temporal environmental monitoring for smart buildings', Control & Automation (ICCA), 2017 13th IEEE International Conference on, IEEE, Ohrid, Macedonia, pp. 277-282.
View/Download from: UTS OPUS or Publisher's site
View description>>

The paper addresses the problem of efficiently monitoring environmental fields in a smart building by the use of a network of wireless noisy sensors that take discretely-predefined measurements at their locations through time. It is proposed that the indoor environmental fields are statistically modeled by spatio-temporal non-parametric Gaussian processes. The proposed models are able to effectively predict and estimate the indoor climate parameters at any time and at any locations of interest, which can be utilized to create timely maps of indoor environments. More importantly, the monitoring results are practically crucial for building management systems to efficiently control energy consumption and maximally improve human comfort in the building. The proposed approach was implemented in a real tested space in a university building, where the obtained results are highly promising.

Nguyen, LV, Ulapane, N, Valls Miro, J, Dissanayake, G & Munoz, F 2017, 'Improved Signal Interpretation for Cast Iron Thickness Assessment based on Pulsed Eddy Current Sensing', Proceedings of the 12th IEEE Conference on Industrial Electronics and Applications, IEEE Conference on Industrial Electronics and Applications, IEEE, Siem Reap, Cambodia, pp. 2005-2010.
View/Download from: UTS OPUS
View description>>

This paper presents a novel signal processing approach for computing thickness of ferromagnetic cast iron material, widely employed in older infrastructure such as water mains or bridges. Measurements are gathered from a Pulsed Eddy Current (PEC) based sensor placed on top of the material, with unknown lift-off, as commonly used during non-destructive testing (NDT). The approach takes advantage of an analytical logarithmic model proposed in the literature for the decaying voltage induced at the PEC sensor pick-up coil. An increasingly more accurate and robust algorithm is proven here by means of an Adaptive Least Square Fitting Line (ALSFL) recursive strategy, suitable to recognize the most linear part of the sensor’s logarithmic output voltage for subsequent gradient computation, from which thickness is then derived. Moreover, efficiency is also gained as processing can be carried out on only one decaying voltage signal, unlike averaging over multiple measurements as is usually done in the literature. Importantly, the new signal processing methodology demonstrates highest accuracy at the lower thicknesses, a circumstance most relevant to NDT evaluation. Experiments that verify the proposed method in real-world thickness assessment of cast iron material are presented and compared with current practices, showing promising results.

Perera, A, Arukgoda, J, Ranasinghe, RS & Dissanayake, G 2017, 'Localization System for Carers to Track Elderly People in Visits to a Crowded Shopping Mall', 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN), International Conference on Indoor Positioning and Indoor Navigation, IEEE, Sapporo, Japan, pp. 1-8.
View/Download from: UTS OPUS or Publisher's site
View description>>

This work presents a real-time localization system developed for professional care givers to track residents of an aged care facility during their visits to a crowded, multi-story shopping mall. The proposed system consists of a Wi-Fi based self-localization platform integrated into a wheeled walking frame and an application installed in a hand-held tablet device for displaying the locations of walker users. The density of people in the shopping mall changes significantly during the day thus the expected Wi-Fi signal strength at a given location is subject to large variations. However, Identifying the location to be within a given area is adequate and the average speed of motion is less than 0.5 m/sec. In this paper, an algorithm that addresses these unique requirements is presented. We exploit the signal strength characteristics of existing Wi-Fi network and prior knowledge of the building floor plans for developing our core algorithm. The environments is divided in to cells that are either enclosed spaces or divisions of larger open regions. The probability density function of the Wi-Fi signal strength of each cell is estimated using Kernel Density Estimation (KDE) and is used in a probabilistic framework to estimate the user location. Motion model of the users as well as the detection of floor transition events are used to enhance the performance of the location estimator. The algorithm was implemented using an Odroid-C1 computer and a tablet with Android operating system. Results obtained during field trials at Roselands Shopping Mall in Sydney are presented.

Perera, K, Ranasinghe, R & Dissanayake, G 2017, 'A Neural Network Based Place Recognition Technique for a Crowded Indoor Environment', The 13th IEEE conference on industrial electronics and applications, IEEE, Siem Reap, Cambodia, pp. 1937-1942.
View/Download from: UTS OPUS or Publisher's site
View description>>

Place recognition in a crowded and cluttered environment is a challenging task due to its dynamic characteristics such as moving obstacles, varying lighting conditions and occlusions. This work presents a robust place recognition technique that could be applied into a similar environment, by combining well known Bag of Words technique with a feedforward neural network. The feedforward neural network we use have three layers with a single hidden layer and it relies on rectifier and softmax activation functions. We employ cross entropy function to model the cost of our neural network and utilize Adam algorithm for minimizing this cost at the training phase. The output layer with softmax activation in the neural network, produces a vector of probabilities which represent the likelihood of test image being captured from a given region. These values are further improved by incorporating a transition matrix which is based on the building layout. We have evaluated our neural network based place recognition technique with data collected from a crowded indoor shopping mall and promising results have been observed by this approach. We also have analyzed the behavior of neural network for changes in hyper-parameters and presented the results.

Poon, JT, Cui, Y, Valls Miro, J, Matsubara, T & Sugimoto, K 2017, 'Local Driving Assistance from Demonstration for Mobility Aids', 2017 IEEE International Conference on Robotics and Automation (ICRA), International Conference on Robotics and Automation, IEEE, Singapore.
View/Download from: UTS OPUS or Publisher's site
View description>>

Active assistive mobility systems are largely limited to a-priori mapped environments, whereas their reactive assistive counterparts are in general location independent and focus on the provision of collision avoidance in the immediate space surrounding the platform. This paper presents a framework capable of providing active short-term navigation, combining the intelligence of active assistance with the freedom of location independence. Demonstration data from an able expert while driving the mobility aid in a standard indoor setting is used off-line to learn reference behavioral models of navigation given perceptual information from the platform surroundings and the input controls exerted by the user while navigating. These serve as the foundation for on-line probabilistic short-term destination inference using the instantaneously available data from the user and on-board sensors. This is coupled with a real-time stochastic optimal path generation able to exploit the same short term demonstration paths from the expert with the belief they capture both the driver's awareness of the platform's physical geometry and appropriate behaviors for their surroundings. Experimental results with users of varying proficiency in a setting unvisited in training data show promise in using the framework in assisting users experiencing difficulty in safe power mobility aid use.

Popovic, M, Vidal Calleja, TA, Hitz, G, Sa, I, Siegwart, R & Nieto, J 2017, 'Multiresolution Mapping and Informative Path Planning for UAV-based Terrain Monitoring', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vancouver, Canada.
View/Download from: UTS OPUS or Publisher's site
View description>>

Unmanned aerial vehicles (UAVs) can offer timely and cost-effective delivery of high-quality sensing data. However, deciding when and where to take measurements in complex environments remains an open challenge. To address this issue, we introduce a new multiresolution mapping approach for informative path planning in terrain monitoring using UAVs. Our strategy exploits the spatial correlation encoded in a Gaussian Process model as a prior for Bayesian data fusion with probabilistic sensors. This allows us to incorporate altitude-dependent sensor models for aerial imaging and perform constant-time measurement updates. The resulting maps are used to plan information-rich trajectories in continuous 3-D space through a combination of grid search and evolutionary optimization. We evaluate our framework on the application of agricultural biomass monitoring. Extensive simulations show that our planner performs better than existing methods, with mean error reductions of up to 45% compared to traditional “lawnmower” coverage. We demonstrate proof of concept using a multi rotor to map color in different environments.

Ranasinghe, R, Dissanayake, G, Furukawa, T, Arukgoda, J & Dantanarayana, L 2017, 'Environment Representation for Mobile Robot Localisation (Invited Paper)', 2017 IEEE International Conference on Industrial and Information Systems (ICIIS), IEEE International Conference on Industrial and Information Systems, IEEE, Peradeniya, Sri Lanka, pp. 296-301.
View/Download from: UTS OPUS or Publisher's site
View description>>

An adequate representation of the environment is an essential component of a mobile robot navigation system. This paper reviews the techniques reported in the literature for capturing the geometry of the space surrounding a mobile robot. In particular, the use of distance functions that combine some of the advantages of feature based and occupancy grid based representations for mobile robot localisation is described in detail. The effectiveness of various distance function based representations is demonstrated using a number of practical examples for localising ground and air vehicles.

Shakor, P, Renneberg, J, Nejadi, S & Paul, G 2017, 'Optimisation of Different Concrete Mix Designs for 3D Printing by Utilising 6DOF Industrial Robot', 34th International Symposium on Automation and Robotics in Construction, Taipei, Taiwan.
View/Download from: UTS OPUS
View description>>

Additive Manufacturing (AM) technologies are becoming increasingly viable for commercial and research implementation into various applications. AM refers to the process of forming structures layer upon layer and finds application in prototyping and manufacturing for building construction. It has recently begun to be considered as a viable and attractive alternative in certain circumstances in the construction industry. This paper focuses on the utilisation of different concrete mixtures paired with extrusion techniques facilitated by a six Degree of Freedom (DOF) industrial robot. Using methods of Damp Least Squares (DLS) in conjunction with Resolved Motion Rate Control (RMRC), it is possible to plan stable transitions between several waypoints representing the various print cross-sections. Calculated paths are projected via ‘spline’ interpolation into the manipulator controlled by custom software. This article demonstrates the properties of different concrete mixture designs, showing their performance when used as a filament in 3D Printing and representing a comparison of the results that were found. In this study, the prepared materials consist of ordinary Portland cement, fine sand between (425~150) micron, coarse aggregate ranges (3) mm and chemical admixtures which have been used to accelerate setting times and reduce water content. Numerous tests were performed to check the buildability, flowability, extrudability and moldability of the concrete mixtures. The horizontal test was used to determine the flowability and consistency, while the vertical and squeeze-flow tests were used to determine the buildability of the layers. The extrudability and moldability of the concrete mixtures were controlled by the robot and associated extruder speeds.

Shi, L, Valls Miro, J, Vidal Calleja, T, Vitanage, D & Rajalingam, J 2017, 'Innovative Data-driven “along-the-pipe” Condition Assessment for Critical Water Mains', OZWATER’17 Australia’s International Water Conference & Exhibition, OZWATER’17 Australia’s International Water Conference & Exhibition, Australian Water Association, Sydney, pp. 1-8.
View/Download from: UTS OPUS
View description>>

Recent research findings on remaining life prediction for older Cast Iron critical water mains suggest increasing reliability by calculating stress concentration factors from the corrosion patch geometries expected to be present in the asset, not just extreme pitting as is generally carried out within the industry. This study proposes an innovative data-driven “along-the-pipe” framework able to utilise local inspection results further by capturing data correlations present in the remaining wall thickness measurement. This knowledge can in turn be utilised to produce estimates for “along-the-pipe” patch geometry predictions, hence remaining life. Results from inspections in a real pipeline in the Sydney Water network are compared to conventional Extreme Value Analysis (EVA) to validate the improvements of the proposed strategy.

Shiozaki, T & Dissanayake, G 2017, 'Monocular 3D Metric Scale Reconstruction using Depth from Defocus and Image Velocity', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE, Vancouver, pp. 6723-6728.
View/Download from: UTS OPUS or Publisher's site
View description>>

This paper presents a novel approach to metric scale reconstruction of a three-dimensional (3D) scene using a monocular camera. Using a sequence of images from a monocular camera with a fixed focus lens, metric distance to a set of features in the environment is estimated from image blur due to defocus. The blur texture ambiguity which causes scale errors in depth from defocus is corrected in an EKF framework that exploits image velocity measurements. We show in real experiments that our method converges to a metric scale, accurate, sparse depth map and 3D camera poses with images from a monocular camera. Therefore, the proposed approach has the potential to enhance robot navigation algorithms that rely on monocular cameras.

Song, B, Wang, H, Xiao, W, Shi, L & Huang, S 2017, 'Gaussian Process Model Enabled Particle Filter for Device-Free Localization', 2017 20th International Conference on Information Fusion (Fusion), International Conference on Information Fusion, IEEE, Xi'an, China, pp. 1-7.
View/Download from: UTS OPUS or Publisher's site
View description>>

Device-free localization (DFL) is an emerging wireless network target localization technique that does not need to attach any electronic device with the target. It is remaining as a challenging research problem due to the weak wireless signals and the uncertain wireless communication environment. In this paper, a novel Gaussian Process (GP) based wireless propagation model is proposed to describe the likelihood relationship between the target location and the changes of the RSS measurement for a wireless link. Sequentially Particle Filter (PF) is applied to the DFL for estimating the location of the target, after the GP model is trained using the experimental measurements of the link. Experimental results demonstrate that the proposed GP-PF algorithm can track the target with much better localization accuracy than the Support Vector Machine (SVM) based PF approach.

Song, J, wang, J, Zhao, L, Huang, S & Dissanayake, G 2017, 'Deformable Soft-tissue Reconstruction using Stereo Scope for Minimal Invasive Surgery', CARS 2017 -- Computer Assisted Radiology and Surgery, 31st International Congress and Exhibition, CARS 2017 -- Computer Assisted Radiology and Surgery, 31st International Congress and Exhibition.
View/Download from: UTS OPUS

song, J, wang, J, Zhao, L, huang, S & Dissanayake, G 2017, 'Robust Shape Recovery of Deformable Soft-tissue Based on Information from Stereo Scope for Minimal Invasive Surgery', Hamlyn Symposium on Medical Robotics (HSMR 2017), Hamlyn Symposium on Medical Robotics, Kensington, England.
View/Download from: UTS OPUS
View description>>

Overcoming small field of view of scopes is an important challenge in minimal invasive surgery (MIS). Efforts have been devoted in 3D soft-tissue construction and camera localization [1-2]. This paper proposes a robust strategy for simultaneous camera localization and dense reconstruction of deformable surfaces. The robustness is achieved by: (1) using a sequence of images collected from a stereoscope by considering uncertainty map; (2) filtering images with low intensity; (3) filtering depth by normals. Our approach greatly reduces depth estimation parameter adjustment efforts while still generates good results and preserves topological details. Experiments reveal that the proposed approach is convenient for dynamically rebuild and visualize the latest shape of soft-tissue to mitigate unnecessary tissue damages in minimal invasive surgery.

Su, D, Vidal Calleja, TA & Valls Miro, J 2017, 'Towards Real-Time 3D Sound Sources Mapping with Linear Microphone Arrays', Proceedings of the 2017 IEEE International Conference on Robotics and Automation (ICRA), 2017 IEEE International Conference on Robotics and Automation, IEEE, Singapore, Singapore.
View/Download from: UTS OPUS or Publisher's site
View description>>

In this paper, we present a method for real-time 3D sound sources mapping using an off-the-shelf robotic perception sensor equipped with a linear microphone array. Conventional approaches to map sound sources in 3D scenarios use dedicated 3D microphone arrays, as this type of arrays provide two degrees of freedom (DOF) observations. Our method addresses the problem of 3D sound sources mapping using a linear microphone array, which only provides one DOF observations making the estimation of the sound sources location more challenging. In the proposed method, multi hypotheses tracking is combined with a new sound source parametrisation to provide with a good initial guess for an online optimisation strategy. A joint optimisation is carried out to estimate 6 DOF sensor poses and 3 DOF landmarks together with the sound sources locations. Additionally, a dedicated sensor model is proposed to accurately model the noise of the Direction of Arrival (DOA) observation when using a linear microphone array. Comprehensive simulation and experimental results show the effectiveness of the proposed method. In addition, a real-time implementation of our method has been made available as open source software for the benefit of the community.

Sun, L, Vidal Calleja, TA & Valls Miro, JAIME 2017, 'Coupling Conditionally Independent Submaps for Large-Scale 2.5D Mapping with Gaussian Markov Random Fields', IEEE International Conference on Robotics and Automation : ICRA : [proceedings] IEEE International Conference on Robotics and Automation, IEEE International Conference on Robotics and Automation, IEEE, Singapore, Singapore, pp. 3131-3137.
View/Download from: UTS OPUS or Publisher's site
View description>>

Building large-scale 2.5D maps when spatial correlations are considered can be quite expensive, but there are clear advantages when fusing data. While optimal submapping strategies have been explored previously in covariance-form using Gaussian Process for large-scale mapping, this paper focuses on transferring such concepts into information form. By exploiting the conditional independence property of the Gaussian Markov Random Field (GMRF) models, we propose a submapping approach to build a nearly optimal global 2.5D map. In the proposed approach data is fused by first fitting a GMRF to one sensor dataset; then conditional independent submaps are inferred using this model and updated individually with new data arrives. Finally, the information is propagated from submap to submap to later recover the fully updated map. This is efficiently achieved by exploiting the inherent structure of the GMRF, fusion and propagation all in information form. The key contribution of this paper is the derivation of the algorithm to optimally propagate information through submaps by only updating the common parts between submaps. Our results show the proposed method reduces the computational complexity of the full mapping process while maintaining the accuracy. The performance is evaluated on synthetic data from the Canadian Digital Elevation Data.

Thiyagarajan, K, Kodagoda, S & Nguyen, LV 2017, 'Predictive Analytics for Detecting Sensor Failure Using Autoregressive Integrated Moving Average Model', Proceedings of the 12th IEEE Conference on Industrial Electronics and Applications, IEEE Conference on Industrial Electronics and Applications, IEEE, Siem Reap, Cambodia, pp. 1926-1931.
View/Download from: UTS OPUS
View description>>

Sensors play a vital role in monitoring the important parameters of critical infrastructure. Failure of such sensors causes destabilization to the entire system. In this regard, this paper proposes a predictive analytics solution for detecting the failure of a sensor that measures surface temperature from an urban sewer. The proposed approach incorporates a forecasting technique based on the past time series of sparse data using an autoregressive integrated moving average (ARIMA) model. Based on the 95% forecast interval and continuity of faulty data, a criterion was set to detect anomalies and to issue a warning for sensor failure. The forecasted and faulty data were assumed Gaussian distributed. By using the probability density of the distribution, the mean and variance were computed for faulty data to examine the abnormality in the variance value of each day to detect the sensor failure. The experimental results on the sewer temperature data are appealing.

Ulapane, N, Nguyen, LV, Valls Miro, J, Alempijevic, A & Dissanayake, G 2017, 'Designing A Pulsed Eddy Current Sensing Set-up for Cast Iron Thickness Assessment', Proceedings of the 12th IEEE Conference on Industrial Electronics and Applications, IEEE Conference on Industrial Electronics and Applications, IEEE, Siem Reap, Cambodia, pp. 901-906.
View/Download from: UTS OPUS
View description>>

Pulsed Eddy Current (PEC) sensors possess proven functionality in measuring ferromagnetic material thickness. However, most commercial PEC service providers as well as researchers have investigated and claim functionality of sensors on homogeneous structural steels (steel grade Q235 for example). In this paper, we present design steps for a PEC sensing set-up to measure thickness of cast iron, which is unlike steel, is a highly inhomogeneous and non-linear ferromagnetic material. The setup includes a PEC sensor, sensor excitation and reception circuits, and a unique signal processing method. The signal processing method yields a signal feature which behaves as a function of thickness. The signal feature has a desirable characteristic of being lowly influenced by lift-off. Experimental results show that the set-up is usable for Non-destructive Evaluation (NDE) applications such as cast iron water pipe assessment.

Unicomb, J, Dantanarayana, L, Arukgoda, J, Ranasinghe, R, Dissanayake, G & Furukawa, T 2017, 'Distance function based 6DOF localization for unmanned aerial vehicles in GPS denied environments', 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Vancouver, BC, Canada.
View/Download from: UTS OPUS or Publisher's site
View description>>

This paper presents an algorithm for localizing an unmanned aerial vehicle (UAV) in GPS denied environments. Localization is performed with respect to a pre-built map of the environment represented using the distance function of a binary mosaic, avoiding the need for extraction and explicit matching of visual features. Edges extracted from images acquired by an on-board camera are projected to the map to compute an error metric that indicates the misalignment between the predicted and true pose of the UAV. A constrained extended Kalman filter (EKF) framework is used to generate an estimate of the full 6-DOF location of the UAV by enforcing the condition that the distance function values are zero when there is no misalignment. Use of an EKF also makes it possible to seamlessly incorporate information from any other system on the UAV, for example, from its auto-pilot, a height sensor or an optical flow sensor. Experiments using a hexarotor UAV both in a simulation environment and in the field are presented to demonstrate the effectiveness of the proposed algorithm.

Wang, J, Huang, S, Zhao, L, Ge, X, He, X, Zhang, C & Wang, X 2017, 'High Quality 3D Reconstruction of Indoor Environments using RGB-D Sensors', Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), IEEE 12th Conference on Industrial Electronics and Applications (ICIEA), IEEE, Siem Reap, Cambodia, pp. 1736-1741.
View/Download from: UTS OPUS or Publisher's site
View description>>

High-quality 3D reconstruction of large-scale indoor scene is the key to combine Simultaneous Localization And Mapping (SLAM) with other applications, such as building inspection and construction monitoring. However, the requirement of global consistency brings challenges to both localization and mapping. In particular, significant localization and mapping error can happen when standard SLAM techniques are used when dealing with the area of featureless walls and roofs. This paper proposed a novel framework aiming to reconstruct a high-quality, globally consistent 3D model for indoor environments using only a RGB-D sensor. We first introduce the sparse and dense feature constraints in the local bundle adjustment. Then, the planar constraints are incorporated in the global bundle adjustment. We fuse the point clouds in a truncated signed distance function volume, from which the high quality mesh can be extracted. Our framework leads to a comprehensive 3D scanning solution for indoor scene, enabling high-quality results and potential applications in building information system. The video of 3D models reconstructed by the method proposed in this paper is available at https://youtu.be/DWMP4YfeNeY.

Wang, J, Song, J, Zhao, L & Huang, S 2017, 'A Submap Joining Based RGB-D SLAM Algorithm using Planes as Features', 11th Conference on Field and Service Robotics (FSR 2017), 11th Conference on Field and Service Robotics (FSR 2017), Springer, Zurich, Switzerland.
View/Download from: UTS OPUS

Wang, JJ, Gowripalan, N, Li, J & Nguyen, VV 2016, 'Close-range photogrammetry for accurate deformation distribution measurement', Mechanics of Structures and Materials: Advancements and Challenges - Proceedings of the 24th Australasian Conference on the Mechanics of Structures and Materials, ACMSM24 2016, Australian Conference on the Mechanics of Structures and Materials, Taylor and Francis, Perth, Australia, pp. 793-799.
View/Download from: UTS OPUS
View description>>

© 2017 Taylor & Francis Group, London. This paper introduces a methodology for improving the accuracy of Deformation Distribution Measurement (DDM) using close-range photogrammetry. After reviewing various algorithms for 2D Digital Image Correlation (DIC), Zero-Normalized Cross-Correlation (ZNCC) is selected for deformation measurement. The impact of several other factors on DIC measurement accuracy has been investigated, including the type of imaging sensors, the contrast and pattern of a specimen, and searching window size. Optimal option of these factors is proposed. The technique is utilized in the experiment of applying static loading on a replica of a concrete structural component used for Sydney Harbour Bridge. Test results presented in the paper include DIC measurements and validation data from conventional sensors.

Wang, M, Su, D, Shi, L, Liu, Y & Miro, JV 2017, 'Real-time 3D human tracking for mobile robots with multisensors', Proceedings - IEEE International Conference on Robotics and Automation, pp. 5081-5087.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. Acquiring the accurate 3-D position of a target person around a robot provides fundamental and valuable information that is applicable to a wide range of robotic tasks, including home service, navigation and entertainment. This paper presents a real-time robotic 3-D human tracking system which combines a monocular camera with an ultrasonic sensor by the extended Kalman filter (EKF). The proposed system consists of three sub-modules: monocular camera sensor tracking model, ultrasonic sensor tracking model and multi-sensor fusion. An improved visual tracking algorithm is presented to provide partial location estimation (2-D). The algorithm is designed to overcome severe occlusions, scale variation, target missing and achieve robust re-detection. The scale accuracy is further enhanced by the estimated 3-D information. An ultrasonic sensor array is employed to provide the range information from the target person to the robot and Gaussian Process Regression is used for partial location estimation (2-D). EKF is adopted to sequentially process multiple, heterogeneous measurements arriving in an asynchronous order from the vision sensor and the ultrasonic sensor separately. In the experiments, the proposed tracking system is tested in both simulation platform and actual mobile robot for various indoor and outdoor scenes. The experimental results show the superior performance of the 3-D tracking system in terms of both the accuracy and robustness.

Webster, C, Jusufi, A & Liu, D 2017, 'A Comparative Survey of Climbing Robots and Arboreal Animals in Scaling Complex Environments', International Symposium on Robotics & Mechatronics, ISRM IFToMM, Sydney, Australia.
View/Download from: UTS OPUS
View description>>

The inchworm style climbing robots in current literature will only take us so far in regard to the robotic maintenance of transmission towers. To continue to push towards developing robots that can perform work in reticular structures we must consider a broader spectrum of animals for inspiration. The abilities of Primates in climbing have long been a benchmark in climbing standards, but due to the mechanical and control complexity associated with their development, they are seldom developed. Birds on the other hand offer an alternate solution, utilising less degrees-of-freedom whilst maintaining stability and manoeuvrability. These ancient arboreal specialists may hold they keys to unlocking the next stage in the development of climbing robotics. This work presents lessons learned from a review on primates as well as some preliminary observations on the climbing capabilities of parrots.

Wu, K, Li, X, Ranasinghe, R, Dissanayake, G & Liu, Y 2017, 'RISAS: A novel rotation, illumination, scale invariant appearance and shape feature', Proceedings - IEEE International Conference on Robotics and Automation, International Conference on Robotics and Automation, IEEE, Singapore, Singapore, pp. 4008-4015.
View/Download from: UTS OPUS or Publisher's site
View description>>

© 2017 IEEE. This paper presents a novel appearance and shape feature, RISAS, which is robust to viewpoint, illumination, scale and rotation variations. RISAS consists of a keypoint detector and a feature descriptor both of which utilise texture and geometric information present in the appearance and shape channels. A novel response function based on the surface normals is used in combination with the Harris corner detector for selecting keypoints in the scene. A strategy that uses the depth information for scale estimation and background elimination is proposed to select the neighbourhood around the keypoints in order to build precise invariant descriptors. Proposed descriptor relies on the ordering of both grayscale intensity and shape information in the neighbourhood. Comprehensive experiments which confirm the effectiveness of the proposed RGB-D feature when compared with CSHOT [1] and LOIND[2] are presented. Furthermore, we highlight the utility of incorporating texture and shape information in the design of both the detector and the descriptor by demonstrating the enhanced performance of CSHOT and LOIND when combined with RISAS detector.

Zainudin, Z, Mat Ibrahim, M & Kodagoda, S 2017, 'Non-Parametric Data Optimization for 2D Laser Based People Tracking', Proceedings of the 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), IEEE Conference on Industrial Electronics and Applications, Siem Reap, Cambodia.
View/Download from: UTS OPUS or Publisher's site
View description>>

Generally, a model on describing human motion patterns should have an ability to enhance tracking performance particularly when dealing with long term occlusions. These patterns can be efficiently learned by applying Gaussian Processes (GPs). However, the GPs can become computationally expensive with increasing training data with time. Thus, with the proposed data selection and management using Mutual Information (MI) and Mahalanobis Distance (MD)approach, we have be able to keep the necessary portion of informative data and discard the others. This approach is then experimented by using the measurements of horizontal 2D scan of public area of our research centre with a stationary laser range finder. Experimental results show that even 90% reduction of data did not contribute to significantly increased Root Mean Square Error (RMSE). Implementation of Gaussian Process - Particle filter tracker for people tracking with long term occlusions produces a remarkable tracking performance when compared to Extended Kalman Filter (EKF) tracker.