Müller, R, Drouin, N & Sankaran, S 2021, Balanced Leadership Making the Best Use of Personal and Team Leadership in Projects, Oxford University Press.
View description>>
"This book describes balanced leadership in projects.
Drouin, N, van Marrewijk, A, Sankaran, S & Müller, R 2021, 'What is done through the lens of megaproject leaders life stories' in Megaproject Leaders, Edward Elgar Publishing, pp. 2-11.
View/Download from: Publisher's site
View description>>
The novel ideas presented will appeal to academics, practitioners and university students.
Freeder, D, Sankaran, S & Clegg, S 2021, 'The Museum of New Zealand Te Papa Tongarewa: a labour of love and learning' in Megaproject Leaders, Edward Elgar Publishing, Cheltenham, pp. 139-149.
View/Download from: Publisher's site
Freeder, D, Sankaran, S & Clegg, S 2021, 'The project owner and the project manager: the M4 motorway connecting Sydney from the west to the east' in Megaproject Leaders, Edward Elgar Publishing, pp. 119-138.
View/Download from: Publisher's site
Metcalf, G, Kijima, K, Deguchi, H, Edson, M, Jones, P, Kineman, J, Martin, J, Sankaran, S & Wessman, C 2021, 'Introduction to the Handbook of Systems Sciences' in Handbook of Systems Sciences, Springer Singapore, pp. 1-24.
View/Download from: Publisher's site
Metcalf, GS, Kijima, K, Deguchi, H, Edson, MC, Jones, P, Kineman, JJ, Martin, J, Sankaran, S & Wessman, CA 2021, 'Introduction to the Handbook of Systems Sciences' in Metcalf, G, Kijima, K & Deguchi, H (eds), Handbook of Systems Sciences, Springer Singapore, Singapore, pp. 3-25.
View/Download from: Publisher's site
Müller, R, Drouin, N & Sankaran, S 2021, 'Governance of Organizational Project Management and Megaprojects Using the Viable Project Governance Model' in Metcalf, G, Kijima, K & Deguchi, H (eds), Handbook of Systems Sciences, Springer Singapore, Singapore, pp. 501-527.
View/Download from: Publisher's site
Müller, R, van Marrewijk, A, Drouin, N & Sankaran, S 2021, 'Insights from personal perspectives' in Megaproject Leaders, Edward Elgar Publishing, Cheltenham, UK, pp. 270-287.
View/Download from: Publisher's site
View description>>
The novel ideas presented will appeal to academics, practitioners and university students.
Sankaran, S, van Marrewijk, A, Drouin, N & Müller, R 2021, 'Conclusions and reflections: what have we learnt about megaproject leaders?' in Megaproject Leaders, Edward Elgar Publishing, Cheltenham, UK, pp. 288-297.
View/Download from: Publisher's site
View description>>
The novel ideas presented will appeal to academics, practitioners and university students.
van Marrewijk, A, Sankaran, S, Müller, R & Drouin, N 2021, 'A biographical research approach' in Drouin, N, Sankaran, S, Marrewijk, AV & Muller, R (eds), Megaproject Leaders, Edward Elgar Publishing, Cheltenham, UK, pp. 12-19.
View/Download from: Publisher's site
View description>>
The novel ideas presented will appeal to academics, practitioners and university students.
Agarwal, UA, Dixit, V, Nikolova, N, Jain, K & Sankaran, S 2021, 'A psychological contract perspective of vertical and distributed leadership in project-based organizations', International Journal of Project Management, vol. 39, no. 3, pp. 249-258.
View/Download from: Publisher's site
Alempijevic, A, Vidal-Calleja, T, Falque, R, Quin, P, Toohey, E, Walmsley, B & McPhee, M 2021, 'Lean meat yield estimation using a prototype 3D imaging approach', Meat Science, vol. 181, pp. 108470-108470.
View/Download from: Publisher's site
Azzam, R, Alkendi, Y, Taha, T, Huang, S & Zweiri, Y 2021, 'A Stacked LSTM-Based Approach for Reducing Semantic Pose Estimation Error', IEEE Transactions on Instrumentation and Measurement, vol. 70, pp. 1-14.
View/Download from: Publisher's site
View description>>
© 1963-2012 IEEE. Achieving high estimation accuracy is significant for semantic simultaneous localization and mapping (SLAM) tasks. Yet, the estimation process is vulnerable to several sources of error, including limitations of the instruments used to perceive the environment, shortcomings of the employed algorithm, environmental conditions, or other unpredictable noise. In this article, a novel stacked long short-term memory (LSTM)-based error reduction approach is developed to enhance the accuracy of semantic SLAM in presence of such error sources. Training and testing data sets were constructed through simulated and real-time experiments. The effectiveness of the proposed approach was demonstrated by its ability to capture and reduce semantic SLAM estimation errors in training and testing data sets. Quantitative performance measurement was carried out using the absolute trajectory error (ATE) metric. The proposed approach was compared with vanilla and bidirectional LSTM networks, shallow and deep neural networks, and support vector machines. The proposed approach outperforms all other structures and was able to significantly improve the accuracy of semantic SLAM. To further verify the applicability of the proposed approach, it was tested on real-time sequences from the TUM RGB-D data set, where it was able to improve the estimated trajectories.
Azzam, R, Kong, FH, Taha, T & Zweiri, Y 2021, 'Pose-Graph Neural Network Classifier for Global Optimality Prediction in 2D SLAM', IEEE Access, vol. 9, pp. 80466-80477.
View/Download from: Publisher's site
Bai, F, Vidal-Calleja, T & Grisetti, G 2021, 'Sparse Pose Graph Optimization in Cycle Space', IEEE Transactions on Robotics, vol. 37, no. 5, pp. 1381-1400.
View/Download from: Publisher's site
View description>>
The state-of-the-art modern pose-graph optimization (PGO) systems are vertex based. In this context, the number of variables might be high, albeit the number of cycles in the graph (loop closures) is relatively low. For sparse problems particularly, the cycle space has a significantly smaller dimension than the number of vertices. By exploiting this observation, in this article, we propose an alternative solution to PGO that directly exploits the cycle space. We characterize the topology of the graph as a cycle matrix, and reparameterize the problem using relative poses, which are further constrained by a cycle basis of the graph. We show that by using a minimum cycle basis, the cycle-based approach has superior convergence properties against its vertex-based counterpart, in terms of convergence speed and convergence to the global minimum. For sparse graphs, our cycle-based approach is also more time efficient than the vertex-based. As an additional contribution of this work, we present an effective algorithm to compute the minimum cycle basis. Albeit known in computer science, we believe that this algorithm is not familiar to the robotics community. All the claims are validated by experiments on both standard benchmarks and simulated datasets. To foster the reproduction of the results, we provide a complete open-source C++ implementation (1) of our approach.
Chen, R, Yin, H, Jiao, Y, Dissanayake, G, Wang, Y & Xiong, R 2021, 'Deep Samplable Observation Model for Global Localization and Kidnapping', IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2296-2303.
View/Download from: Publisher's site
Chen, Y, Huang, S, Zhao, L & Dissanayake, G 2021, 'Cramér–Rao Bounds and Optimal Design Metrics for Pose-Graph SLAM', IEEE Transactions on Robotics, vol. 37, no. 2, pp. 627-641.
View/Download from: Publisher's site
View description>>
Two-dimensional (2-D)/3-D pose-graph simultaneous localization and mapping (SLAM) is a problem of estimating a set of poses based on noisy measurements of relative rotations and translations. This article focuses on the relation between the graphical structure of pose-graph SLAM and Fisher information matrix (FIM), Cramér–Rao lower bounds (CRLB), and its optimal design metrics (T-optimality and D-optimality). As a main contribution, based on the assumption of isotropic Langevin noise for rotation and block-isotropic Gaussian noise for translation, the FIM and CRLB are derived and shown to be closely related to the graph structure, in particular, the weighted Laplacian matrix. We also prove that total node degree and weighted number of spanning trees, as two graph connectivity metrics, are, respectively, closely related to the trace and determinant of the FIM. The discussions show that, compared with the D-optimality metric, the T-optimality metric is more easily computed but less effective. We also present upper and lower bounds for the D-optimality metric, which can be efficiently computed and are almost independent of the estimation results. The results are verified with several well-known datasets, such as Intel, KITTI, sphere, and so on.
Cilliers, EJ, Sankaran, S, Armstrong, G, Mathur, S & Nugapitiya, M 2021, 'From Urban-Scape to Human-Scape: COVID-19 Trends That will Shape Future City Centres', Land, vol. 10, no. 10, pp. 1038-1038.
View/Download from: Publisher's site
View description>>
The COVID-19 pandemic did not only impact all spheres of life but came abruptly to redefine our understanding of the urban-scape. With changing user-values and user-needs, there is a renewed realisation of the importance of the human-scape and how human capital, social issues, and liveability considerations will progressively lead urban development discussions. The urban-scape risk is far more complex and fragile than previously anticipated, with the future of the city centre dependent on our ability to successfully manage the transition from an urban-scape to a human-scape. This research employed a narrative review methodology to reflect on COVID-19 trends that will shape future city centres, based on expert contributions pertaining to (1) the community sector, (2) the public sector, and (3) the private sector within the Sydney Metropolitan area of Australia. The research highlighted the changing human-scape needs and associated impacts of (1) changing movement patterns, (2) changing social infrastructure, and (3) increasing multifunctionality, which will be crucial factors in shaping attractive (future) city centres. The research contributes to the notion that future city centres will embrace and prioritise the human-scape in a response to ‘build back better’, and accordingly, identified how the human-scape can be articulated in broader spatial planning approaches to create attractive future city centres.
Drouin, N, Müller, R, Sankaran, S & Vaagaasar, A-L 2021, 'Balancing leadership in projects: Role of the socio-cognitive space', Project Leadership and Society, vol. 2, pp. 100031-100031.
View/Download from: Publisher's site
Gil Aparicio, A & Valls Miro, J 2021, 'An Efficient Stochastic Constrained Path Planner for Redundant Manipulators', Applied Sciences, vol. 11, no. 22, pp. 10636-10636.
View/Download from: Publisher's site
View description>>
This brief proposes a novel stochastic method that exploits the particular kinematics of mechanisms with redundant actuation and a well-known manipulability measure to track the desired end-effector task-space motion in an efficient manner. Whilst closed-form optimal solutions to maximise manipulability along a desired trajectory have been proposed in the literature, the solvers become unfeasible in the presence of obstacles. A manageable alternative to functional motion planning is thus proposed that exploits the inherent characteristics of null-space configurations to construct a generic solution able to improve manipulability along a task-space trajectory in the presence of obstacles. The proposed Stochastic Constrained Optimization (SCO) solution remains close to optimal whilst exhibiting computational tractability, being an attractive proposition for implementation on real robots, as shown with results in challenging simulation scenarios, as well as with a real 7R Sawyer manipulator, during surface conditioning tasks.
Gunatilake, A, Piyathilaka, L, Tran, A, Vishwanathan, VK, Thiyagarajan, K & Kodagoda, S 2021, 'Stereo Vision Combined With Laser Profiling for Mapping of Pipeline Internal Defects', IEEE Sensors Journal, vol. 21, no. 10, pp. 11926-11934.
View/Download from: Publisher's site
View description>>
Underground potable water pipes are essential infrastructure assets for any country. A significant proportion of those assets are deteriorating due to pipe corrosion which results in premature failure of pipes causing enormous disruptions to the public and loss to the economy. To address such adverse effects, the water utilities in Australia exploit advanced pipelining technologies with a motive of extending the service life of their pipe assets. However, the linings are prone to defects due to improper liner application and unfavorable environmental conditions during the liner curing phase. To monitor the imperfections of the pipe linings, in this article, we propose a mobile robotic sensing system that can scan, detect, locate and measure pipeline internal defects by generating three-dimensional RGB-Depth maps using stereo camera vision combined with infrared laser profiling unit. The system does not require complex calibration procedures and it utilizes orientation correction to provide accurate real-time RGB-D maps. The defects are identified and color mapped for easier visualization. The robotic sensing system was extensively tested in laboratory conditions followed by field deployments in buried water pipes in Sydney, Australia. The experimental results show that the RGB-D maps were generated with millimeter (mm) level accuracy with demonstrated liner defect quantification.
Jiao, Y, Wang, Y, Ding, X, Fu, B, Huang, S & Xiong, R 2021, '2-Entity Random Sample Consensus for Robust Visual Localization: Framework, Methods, and Verifications', IEEE Transactions on Industrial Electronics, vol. 68, no. 5, pp. 4519-4528.
View/Download from: Publisher's site
Kim, J, Guivant, J, Sollie, ML, Bryne, TH & Johansen, TA 2021, 'Compressed pseudo-SLAM: pseudorange-integrated compressed simultaneous localisation and mapping for unmanned aerial vehicle navigation', Journal of Navigation, vol. 74, no. 5, pp. 1091-1103.
View/Download from: Publisher's site
View description>>
AbstractThis paper addresses the fusion of the pseudorange/pseudorange rate observations from the global navigation satellite system and the inertial–visual simultaneous localisation and mapping (SLAM) to achieve reliable navigation of unmanned aerial vehicles. This work extends the previous work on a simulation-based study [Kim et al. (2017). Compressed fusion of GNSS and inertial navigation with simultaneous localisation and mapping. IEEE Aerospace and Electronic Systems Magazine, 32(8), 22–36] to a real-flight dataset collected from a fixed-wing unmanned aerial vehicle platform. The dataset consists of measurements from visual landmarks, an inertial measurement unit, and pseudorange and pseudorange rates. We propose a novel all-source navigation filter, termed a compressed pseudo-SLAM, which can seamlessly integrate all available information in a computationally efficient way. In this framework, a local map is dynamically defined around the vehicle, updating the vehicle and local landmark states within the region. A global map includes the rest of the landmarks and is updated at a much lower rate by accumulating (or compressing) the local-to-global correlation information within the filter. It will show that the horizontal navigation error is effectively constrained with one satellite vehicle and one landmark observation. The computational cost will be analysed, demonstrating the efficiency of the method.
Liu, L, Fryc, S, Wu, L, Vu, TL, Paul, G & Vidal-Calleja, T 2021, 'Active and Interactive Mapping With Dynamic Gaussian Process Implicit Surfaces for Mobile Manipulators', IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 3679-3686.
View/Download from: Publisher's site
View description>>
In this letter, we present an interactive probabilistic mapping framework for a mobile manipulator picking objects from a pile. The aim is to map the scene, actively decide where to go next and which object to pick, make changes to the scene by picking the chosen object, and then map these changes alongside. The proposed framework uses a novel dynamic Gaussian Process (GP) Implicit Surface method to incrementally build and update the scene map that reflects environment changes. Actively the framework computes the next-best-view, balancing the terms of object reachability for picking and map information gain (IG) for fidelity and coverage. To enforce a priority of visiting boundary segments over unknown regions, the IG formulation includes an uncertainty gradient-based frontier score by exploiting the GP kernel derivative. This leads to an efficient strategy that addresses the often conflicting requirement of unknown environment exploration and object picking exploitation given a limited execution horizon. We demonstrate the effectiveness of our framework with software simulation and real-life experiments.
Mao, Z, Zhao, L, Huang, S, Fan, Y & Pui-Wai Lee, A 2021, 'Direct 3D ultrasound fusion for transesophageal echocardiography', Computers in Biology and Medicine, vol. 134, pp. 104502-104502.
View/Download from: Publisher's site
View description>>
BACKGROUND: Real-time three-dimensional transesophageal echocardiography (3D TEE) has been increasingly used in clinic for fast 3D analysis of cardiac anatomy and function. However, 3D TEE still suffers from the limited field of view (FoV). It is challenging to adopt conventional multi-view fusion methods to 3D TEE images because feature-based registration methods tend to fail in the ultrasound scenario, and conventional intensity-based methods have poor convergence properties and require an iterative coarse-to-fine strategy. METHODS: A novel multi-view registration and fusion method is proposed to enlarge the FoV of 3D TEE images efficiently. A direct method is proposed to solve the registration problem in the Lie algebra space. Fast implementation is realized by searching voxels on three orthogonal planes between two volumes. Besides, a weighted-average 3D fusion method is proposed to fuse the aligned images seamlessly. For a sequence of 3D TEE images, they are fused incrementally. RESULTS: Qualitative and quantitative results of in-vivo experiments indicate that the proposed registration algorithm outperforms a state-of-the-art PCA-based registration method in terms of accuracy and efficiency. Image registration and fusion performed on 76 in-vivo 3D TEE volumes from nine patients show apparent enlargement of FoV (enlarged around two times) in the obtained fused images. CONCLUSIONS: The proposed methods can fuse 3D TEE images efficiently and accurately so that the whole Region of Interest (ROI) can be seen in a single frame. This research shows good potential to assist clinical diagnosis, preoperative planning, and future intraoperative guidance with 3D TEE.
Mathur, S, Ninan, J, Vuorinen, L, Ke, Y & Sankaran, S 2021, 'An exploratory study of the use of social media to assess benefits realization in transport infrastructure projects', Project Leadership and Society, vol. 2, pp. 100010-100010.
View/Download from: Publisher's site
McCammon, S, Marcon dos Santos, G, Frantz, M, Welch, TP, Best, G, Shearman, RK, Nash, JD, Barth, JA, Adams, JA & Hollinger, GA 2021, 'Ocean front detection and tracking using a team of heterogeneous marine vehicles', Journal of Field Robotics, vol. 38, no. 6, pp. 854-881.
View/Download from: Publisher's site
View description>>
AbstractOcean monitoring is an expensive and time consuming endeavor, but it can be made more efficient through the use of teams of autonomous robots. In this paper, we present a system for the autonomous identification and tracking of ocean fronts by coordinating the sampling efforts of a heterogeneous team of autonomous surface vehicles (ASVs) and autonomous underwater vehicles (AUVs). The primary contributions of this study are (1) our algorithm for performing autonomous coordination using general autonomy principles: Sequential Allocation Monte Carlo Tree Search (SA‐MCTS) which incorporates domain knowledge into the environmental estimation through both augmenting a standard Gaussian process with a nearest neighbors prior and planning in a drifting reference frame, (2) our decision support user interface to help human operators oversee the autonomous system, and (3) the demonstration of the system's operation in a 2‐week long deployment in the Gulf of Mexico using a heterogeneous team of four Slocum gliders and two robotic ocean surface samplers. With these contributions, we aim to bridge the gap between state of the art autonomy algorithms and marine vehicle planning methods that have been tested in large‐scale field trials. This paper presents the first deployment of a general, heuristic‐based, multi‐robot coordination algorithm for an extended sampling mission.
Munasinghe, N & Paul, G 2021, 'Radial slicing for helical-shaped advanced manufacturing applications', The International Journal of Advanced Manufacturing Technology, vol. 112, no. 3-4, pp. 1089-1100.
View/Download from: Publisher's site
View description>>
The fourth industrial revolution (Industry 4.0) is transforming industries all around the world focusing on areas including advanced robotics and automation, sensor technology and data analytics. The authors are involved in a project developing a multi-robot material extrusion 3D printer to print a Gravity Separation Spiral (GSS), an instrument used in the mining industry to separate mineral slurry into different density components. Compared to traditional mould-based manufacturing, this new additive manufacturing method will significantly reduce manufacturing tooling costs, improve the customisation to enable the production of bespoke GSS that each process different minerals, and reduce worker exposure to hazardous materials. Slicing and printing large scale helical objects in conventional horizontal layer addition would result in an unreasonable amount of waste material from support structures, and poor surface quality due to step-wise bumps. This paper presents a novel slicing algorithm using concentric vertical ray lines to slice objects radially, enabling layers to be deposited progressively in the same fashion. This method can be applied in large scale additive manufacturing where objects are printed by a robot in a radial direction, which is different from layered vertical printing in conventional additive systems. An example GSS is sliced to generate motion plans for a print head affixed to the end effector of a robot arm. Then through simulations, it is shown how a robot's expected manipulability measure can be used to predict and ensure the successful completion of the print.
Ng, Y, Li, H & Kim, J 2021, 'Uncertainty Estimation of Dense Optical Flow for Robust Visual Navigation', Sensors, vol. 21, no. 22, pp. 7603-7603.
View/Download from: Publisher's site
View description>>
This paper presents a novel dense optical-flow algorithm to solve the monocular simultaneous localisation and mapping (SLAM) problem for ground or aerial robots. Dense optical flow can effectively provide the ego-motion of the vehicle while enabling collision avoidance with the potential obstacles. Existing research has not fully utilised the uncertainty of the optical flow—at most, an isotropic Gaussian density model has been used. We estimate the full uncertainty of the optical flow and propose a new eight-point algorithm based on the statistical Mahalanobis distance. Combined with the pose-graph optimisation, the proposed method demonstrates enhanced robustness and accuracy for the public autonomous car dataset (KITTI) and aerial monocular dataset.
Nguyen, L, Kodagoda, S, Ranasinghe, R & Dissanayake, G 2021, 'Mobile Robotic Sensors for Environmental Monitoring using Gaussian Markov Random Field', Robotica, vol. 39, no. 5, pp. 862-884.
View/Download from: Publisher's site
View description>>
SUMMARYThis paper addresses the issue of monitoring spatial environmental phenomena of interest utilizing information collected by a network of mobile, wireless, and noisy sensors that can take discrete measurements as they navigate through the environment. It is proposed to employ Gaussian Markov random field (GMRF) represented on an irregular discrete lattice by using the stochastic partial differential equations method to model the physical spatial field. It then derives a GMRF-based approach to effectively predict the field at unmeasured locations, given available observations, in both centralized and distributed manners. Furthermore, a novel but efficient optimality criterion is then proposed to design centralized and distributed adaptive sampling strategies for the mobile robotic sensors to find the most informative sampling paths in taking future measurements. By taking advantage of conditional independence property in the GMRF, the adaptive sampling optimization problem is proven to be resolved in a deterministic time. The effectiveness of the proposed approach is compared and demonstrated using pre-published data sets with appealing results.
Pakdaman, M, Abbasi, A & Sankaran, S 2021, 'Translating organisational strategies to projects using balanced scorecard and AHP: a case study', International Journal of Project Organisation and Management, vol. 13, no. 2, pp. 111-111.
View/Download from: Publisher's site
Pan, Y, Xu, X, Ding, X, Huang, S, Wang, Y & Xiong, R 2021, 'GEM: Online Globally Consistent Dense Elevation Mapping for Unstructured Terrain', IEEE Transactions on Instrumentation and Measurement, vol. 70, no. 99, pp. 1-13.
View/Download from: Publisher's site
View description>>
IEEE Online dense mapping gives a representation of the unstructured terrain, which is indispensable for safe robotic motion planning. In this paper, we propose such an elevation mapping system, namely GEM, to generate a dense local elevation map in constant real-time for fast responsive local planning, and maintain a globally consistent dense map for path routing at the same time. We model the global elevation map as a collection of submaps. When the trajectory estimation of the robot is corrected by SLAM, only relative poses between submaps are updated without re-building the submap. As a result, this deformable global dense map representation is able to keep the global consistency online. Besides, we accelerate the local mapping by integrating traversability analysis into the mapping system to save the computation cost by obstacle awareness. The system is implemented by CPU-GPU coordinated processing to guarantee constant real-time performance for in-time handling of dynamic obstacles. Substantial experimental results on both simulated and real-world dataset validate the efficiency and effectiveness of GEM.
Popovic, M, Thomas, F, Papatheodorou, S, Funk, N, Vidal-Calleja, T & Leutenegger, S 2021, 'Volumetric Occupancy Mapping With Probabilistic Depth Completion for Robotic Navigation', IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5072-5079.
View/Download from: Publisher's site
Qayyum, U & Kim, J 2021, 'Depth-Camera-Aided Inertial Navigation Utilizing Directional Constraints', Sensors, vol. 21, no. 17, pp. 5913-5913.
View/Download from: Publisher's site
View description>>
This paper presents a practical yet effective solution for integrating an RGB-D camera and an inertial sensor to handle the depth dropouts that frequently happen in outdoor environments, due to the short detection range and sunlight interference. In depth drop conditions, only the partial 5-degrees-of-freedom pose information (attitude and position with an unknown scale) is available from the RGB-D sensor. To enable continuous fusion with the inertial solutions, the scale ambiguous position is cast into a directional constraint of the vehicle motion, which is, in essence, an epipolar constraint in multi-view geometry. Unlike other visual navigation approaches, this can effectively reduce the drift in the inertial solutions without delay or under small parallax motion. If a depth image is available, a window-based feature map is maintained to compute the RGB-D odometry, which is then fused with inertial outputs in an extended Kalman filter framework. Flight results from the indoor and outdoor environments, as well as public datasets, demonstrate the improved navigation performance of the proposed approach.
Quin, P, Nguyen, DDK, Vu, TL, Alempijevic, A & Paul, G 2021, 'Approaches for Efficiently Detecting Frontier Cells in Robotics Exploration.', Frontiers Robotics AI, vol. 8, pp. 616470-616470.
View/Download from: Publisher's site
View description>>
Many robot exploration algorithms that are used to explore office, home, or outdoor environments, rely on the concept of frontier cells. Frontier cells define the border between known and unknown space. Frontier-based exploration is the process of repeatedly detecting frontiers and moving towards them, until there are no more frontiers and therefore no more unknown regions. The faster frontier cells can be detected, the more efficient exploration becomes. This paper proposes several algorithms for detecting frontiers. The first is called Naïve Active Area (NaïveAA) frontier detection and achieves frontier detection in constant time by only evaluating the cells in the active area defined by scans taken. The second algorithm is called Expanding-Wavefront Frontier Detection (EWFD) and uses frontiers from the previous timestep as a starting point for searching for frontiers in newly discovered space. The third approach is called Frontier-Tracing Frontier Detection (FTFD) and also uses the frontiers from the previous timestep as well as the endpoints of the scan, to determine the frontiers at the current timestep. Algorithms are compared to state-of-the-art algorithms such as Naïve, WFD, and WFD-INC. NaïveAA is shown to operate in constant time and therefore is suitable as a basic benchmark for frontier detection algorithms. EWFD and FTFD are found to be significantly faster than other algorithms.
Roche, CD, Zhou, Y, Zhao, L & Gentile, C 2021, 'A World-First Surgical Instrument for Minimally Invasive Robotically-Enabled Transplantation of Heart Patches for Myocardial Regeneration: A Brief Research Report', Frontiers in Surgery, vol. 8, p. 653328.
View/Download from: Publisher's site
View description>>
Graphical Abstract
Romeijn, T, Singh, K, Behrens, M & Paul, G 2021, 'Effect of accelerated weathering on the creep behaviour of additively manufactured Polyethylene Terephthalate Glycol (PETG)', Journal of Polymer Research, vol. 28, no. 9, p. 352.
View/Download from: Publisher's site
View description>>
As additively manufactured components move away from short-term usability, such as single-use prototypes, towards commercial products used for longer periods of time, the long-term material properties, such as ageing and creep, are becoming increasingly important design considerations. Moreover, when additively manufactured components are designed for outdoor use, environmental stressors affect these long-term material properties in a process known as ‘weathering’. In this research paper, an initial set of experiments assessed the flexural creep behaviour of pellet-printed PETG after exposure to three accelerated environmental stressors: UV radiation, temperature and humidity. The outcomes thereof indicated that UV exposure was the only stressor to increase the creep compliance. A subsequent set of experiments increase the UV exposure duration from 100 to 200 h and excluded the effects of ageing on creep behaviour during creep tests. The outcome of this second series of experiments showed that the increase in creep compliance can be attributed to the effects of UV alone.
Sankaran, S & Presier, R 2021, 'Systemic change towards sustainable development: Innovative and integrative approaches', Systems Research and Behavioral Science, vol. 38, no. 5, pp. 579-582.
View/Download from: Publisher's site
Sankaran, S, Freeder, D, Pitsis, A, Clegg, S, Drouin, N & Caron, M-A 2021, 'Megaprojects', Oxford Bibliographies in Urban Studies. Ed. Richardson Dilworth.
View/Download from: Publisher's site
View description>>
“Megaprojects” is a term used to refer to projects and events that encompass large-scale projects in size, cost, space, time, energy, and influence. They are synonymous with large engineering projects, complex projects, large transport or energy projects, and large infrastructure projects, and are often composed of multilayered discrete projects forming a larger scale complex project. Some of the complexity deals with difficulty in quantifying the long-terms costs or benefits or fully realising the whole life cycle of the megaproject prior to commencement. Megaprojects are often shaped by contextual factors. Where complexity is related to technical aspects of the project it also includes organizational aspects and the scope of the project. Some of these projects are multifaceted and relate to science research, engineering infrastructure, or private and public construction of buildings and/or other venues. Megaprojects affect societies that undertake them, urban planning aspects, and social relationships between stakeholders engaged in executing all the elements involved in creating them. They have an impact on a number of areas both locally and globally. This includes extending notions of urban planning to accommodate large-scale construction. These projects can be significant in terms of social and/or economic factors in a positive or negative sense. There have been debates and criticism on the need and function of megaprojects and whether they are beneficial constructs or detrimental to society.
Sankaran, S, Jacobsson, M & Blomquist, T 2021, 'The history and future of projects as a transition innovation: Towards a sustainable project management framework', Systems Research and Behavioral Science, vol. 38, no. 5, pp. 696-714.
View/Download from: Publisher's site
View description>>
AbstractProject management practices have evolved as the discipline grew from managing defence and engineering projects to delivering information systems, supporting organizational transformation, and managing megaprojects supporting national infrastructure needs. Thus, from starting as a tactical tool, project management grew to deliver organizational and national strategies. The next challenge for project management is to support the achievement of sustainable development goals to tackle societal challenges. How can it do this? In this article, we chart a way forward for project management to contribute to global sustainability by tracing the history of projects from prehistoric times to the 21st. We outline the development using the lens of socio‐technical transitions to analyse technological niches developed to advance the field, and socio‐technical regimes that have supported the development of project management to adopt these technological niches to meet changes that appear at the landscape level. By analysing the history of projects and project management, we argue that the discipline has continuously evolved as a transition innovation that can meet the challenges posed by sustainable development. However, further investigation is required. A sustainable development framework has been proposed in this article to enable project management researchers and managers to achieve this transition.
Saroya, M, Best, G & Hollinger, GA 2021, 'Roadmap Learning for Probabilistic Occupancy Maps With Topology-Informed Growing Neural Gas', IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4805-4812.
View/Download from: Publisher's site
View description>>
We address the problem of generating navigation roadmaps for uncertain and cluttered environments represented with probabilistic occupancy maps. A key challenge is to generate roadmaps that provide connectivity through tight passages and paths around uncertain obstacles. We propose the topology-informed growing neural gas algorithm that leverages estimates of probabilistic topological structures computed using persistent homology theory. These topological structure estimates inform the random sampling distribution to focus the roadmap learning on challenging regions of the environment that have not yet been learned correctly. We present experiments for three real-world indoor point-cloud datasets represented as Hilbert maps. Our method outperforms baseline methods in terms of graph connectivity, path solution quality, and search efficiency. Compared to a much denser PRM*, our method achieves similar performance while enabling a 27× faster query time for shortest-path searches.
Su, D, Kong, H, Sukkarieh, S & Huang, S 2021, 'Necessary and Sufficient Conditions for Observability of SLAM-Based TDOA Sensor Array Calibration and Source Localization', IEEE Transactions on Robotics, vol. 37, no. 5, pp. 1451-1468.
View/Download from: Publisher's site
View description>>
Sensor array-based systems, which adopt time difference of arrival (TDOA) measurements among the sensors, have found many robotic applications. However, for existing frameworks and systems to be useful, the sensor array needs to be calibrated accurately. Of particular interest in this article are microphone array-based robot audition systems. In our recent work, by using a moving sound source, and the graph-based formulation of simultaneous localization and mapping (SLAM), we have proposed a framework for joint sound source localization and calibration of microphone array geometrical information, together with the estimation of microphone time offset and clock difference/drift rates. However, a thorough study on the identifiability question, termed observability analysis here, in the SLAM framework for microphone array calibration and sound source localization, is still lacking in the literature. In this article, we will fill the abovementioned gap via a Fisher information matrix approach. Motivated by the equivalence between the full column rankness of the Fisher information matrix and the Jacobian matrix, we leverage the structure of the latter associated with the SLAM formulation, and present necessary and sufficient conditions guaranteeing its full column rankness, which lead to parameter identifiability. We have thoroughly discussed the 3-D case with asynchronous (with both time offset and clock drifts, or with only one of them) and synchronous microphone array, respectively. These conditions are closely related to the motion varieties of the sound source and the microphone array configuration, and have intuitive and physical interpretations. Based on the established conditions, we have also discovered some particular cases where observability is impossible. Connections with calibration of other sensors will also be discussed, amongst others. To our best knowledge, this is the first systematic work on observability analysis of SLAM-based microphone...
Svejvig, P, Sankaran, S & Lindhult, E 2021, 'Guest editorial', International Journal of Managing Projects in Business, vol. 14, no. 1, pp. 1-12.
View/Download from: Publisher's site
Ucar, A, Grizzle, JW, Ghaffari, M, Wahde, M, Akin, HL, Baltes, J, Bozma, HI & Miro, JV 2021, 'IEEE Access Special Section Editorial: Real-Time Machine Learning Applications in Mobile Robotics', IEEE Access, vol. 9, pp. 89694-89698.
View/Download from: Publisher's site
Ulapane, N, Thiyagarajan, K, Miro, JV & Kodagoda, S 2021, 'Surface Representation of Pulsed Eddy Current Sensor Signals for Improved Ferromagnetic Material Thickness Quantification', IEEE Sensors Journal, vol. 21, no. 4, pp. 5413-5422.
View/Download from: Publisher's site
Wang, K, Ke, Y, Sankaran, S & Xia, B 2021, 'Problems in the home and community‐based long‐term care for the elderly in China: A content analysis of news coverage', The International Journal of Health Planning and Management, vol. 36, no. 5, pp. 1727-1741.
View/Download from: Publisher's site
View description>>
AbstractPurposeThe purpose of this paper is to identify the issues that limited the supply of home and community‐based Long‐Term‐Care (LTC) for the elderly, offer essential insights into the sustainable development of China's LTC.Design/methodology/approachA content analysis of news coverage on 12 major portals in China has been conducted to identify the issues.FindingsThe results demonstrate that there are 12 significant problems in the supply of home and community‐based LTC for the elderly. For the service providers, the lack of qualified LTC professionals, limited service types/low service quality and unrealised integrated care, lack of steady profit patterns are the three major problems. The deficiencies of the LTC system and the lack of incentive policies and legislation for private investors’ participation are the two major problems faced by the government. The public is confronted with a shortage of home and community support resources and unable to adapt to a change due to their mindsets.Practical implicationsThe issues identified in this paper can not only provide some opportunities to various stakeholders in this area but also offer insights into the sustainable development of China's LTC.Originality/valueThe findings presented in this paper provide the means to understand the home and community‐based LTC market in China for private investors and government, which will help to promote the cooperation between the two.
Wilkinson, S, Carmichael, M & Khonasty, R 2021, 'Towards smart green wall maintenance and Wallbot technology', Property Management, vol. 39, no. 4, pp. 466-478.
View/Download from: Publisher's site
View description>>
PurposeThe UN forecast of a 3-degree Celsius global temperature increase by 2,100 will exacerbate excessive heat. Population growth, urban densification, climate change and global warming contribute to heat waves, which are more intense in high-density environments. With urbanisation, vegetation is replaced by impervious materials which contribute to the urban heat island effect. Concurrently, adverse health outcomes and heat- related deaths are increasing, and heat stress affects labour productivity. More green infrastructure, such as green walls, is needed to mitigate these effects; however maintenance costs, OH&S issues and perceptions of fire risk inhibit take up. What if these barriers could be overcome by a green Wallbot? This research examines the feasibility of integrating smart technology in the form of a Wallbot.Design/methodology/approachThe research design comprised two workshops with key stakeholders; comprising green wall designers and installers, green wall maintenance teams, project managers and building owners with green wall installations, horticulture scientists, designers and mechatronics engineers. The aim was to gain a deeper understanding of the issues affecting maintenance of green walls on different building types in New South Wales Australia to inform the design of a prototype robot to maintain green walls.FindingsThe Wallbot has great potential to overcome the perceived barriers associated with maintaining green walls and also fire risk and detection. If these barriers are addressed, other locations, such as the sides of motorways or rail corridors, could be used for more green wall installations thereby increasing mitigation of UHI. This innovation woul...
Woolfrey, J, Lu, W & Liu, D 2021, 'Predictive End-Effector Control of Manipulators on Moving Platforms Under Disturbance', IEEE Transactions on Robotics, vol. 37, no. 6, pp. 2210-2217.
View/Download from: Publisher's site
View description>>
This article proposes a predictive end-effector control method for manipulators operating on mobile platforms subjected to unwanted base motion. Time series is used to forecast the base motion using historical state information. Then, a trajectory specified in the inertial frame is transformed to a predicted trajectory with respect to the manipulator. By tracking this transformed trajectory, the manipulator negates the base motion. A model-predictive control problem is formulated via quadratic programming (QP) to track said trajectory over the prediction horizon. Only the first control action in the control sequence is constrained by kinematic feasibility. In this manner, QP can be swiftly solved with linear inequality constraints. It is shown that the actual joint trajectory executed by the manipulator is always kinematically feasible. Moreover, tracking error can still be reduced despite future predicted control actions being infeasible. The method is validated through both simulation and experiment. The proposed method can reduce pose error by over 60% compared to a proportional-integral feedback controller.
Wu, L, Lee, KMB, Liu, L & Vidal-Calleja, T 2021, 'Faithful Euclidean Distance Field From Log-Gaussian Process Implicit Surfaces', IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 2461-2468.
View/Download from: Publisher's site
Yang, Y, Ma, B, Liu, X, Zhao, L & Huang, S 2021, 'GSAP: A Global Structure Attention Pooling Method for Graph-Based Visual Place Recognition', Remote Sensing, vol. 13, no. 8, pp. 1467-1467.
View/Download from: Publisher's site
View description>>
The Visual Place Recognition problem aims to use an image to recognize the location that has been visited before. In most of the scenes revisited, the appearance and view are drastically different. Most previous works focus on the 2-D image-based deep learning method. However, the convolutional features are not robust enough to the challenging scenes mentioned above. In this paper, in order to take advantage of the information that helps the Visual Place Recognition task in these challenging scenes, we propose a new graph construction approach to extract the useful information from an RGB image and a depth image and fuse them in graph data. Then, we deal with the Visual Place Recognition problem as a graph classification problem. We propose a new Global Pooling method—Global Structure Attention Pooling (GSAP), which improves the classification accuracy by improving the expression ability of the Global Pooling component. The experiments show that our GSAP method improves the accuracy of graph classification by approximately 2–5%, the graph construction method improves the accuracy of graph classification by approximately 4–6%, and that the whole Visual Place Recognition model is robust to appearance change and view change.
Yin, H, Wang, Y, Tang, L, Ding, X, Huang, S & Xiong, R 2021, '3D LiDAR Map Compression for Efficient Localization on Resource Constrained Vehicles', IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 2, pp. 837-852.
View/Download from: Publisher's site
Zhang, S, Zhao, L, Huang, S, Ye, M & Hao, Q 2021, 'A Template-Based 3D Reconstruction of Colon Structures and Textures From Stereo Colonoscopic Images', IEEE Transactions on Medical Robotics and Bionics, vol. 3, no. 1, pp. 85-95.
View/Download from: Publisher's site
View description>>
This article presents a framework for 3D reconstruction of colonic surface using stereo colonoscopic images. Due to the limited overlaps between consecutive frames and the nonexistence of large loop closures during a normal screening colonoscopy, the state-of-art simultaneous localization and mapping (SLAM) algorithms cannot be directly applied to this scenario, thus a colon model segmented from CT scans is used together with the colonosocopic images to achieve the colon 3D reconstruction with high accuracy. The proposed framework includes 3D scan (point cloud with RGB information) reconstruction from stereo images, a visual odometry (VO) based camera pose initialization module, a 3D registration scheme for matching texture scans to the segmented colon model, and a barycentric-based texture rendering module for mapping textures from colonoscopic images to the reconstructed colonic surface. A realistic simulator is developed using Unity to simulate the procedures of colonoscopy and used to provide experimental datasets in different scenarios. Experimental results demonstrate the good performance of the proposed 3D colonic surface reconstruction method in terms of accuracy and robustness. Currently, the framework requires a pre-operative colon model as the template for colon reconstruction and can reconstruct 3D colon maps when the colon has no large deformation and the colon structure is clearly visible. The datasets used in this article and the developed simulator are made publicly available for other researchers to use (https://github.com/zsustc/colon_reconstruction_dataset).
Zhao, J, Li, T, Yang, T, Zhao, L & Huang, S 2021, '2D Laser SLAM With Closed Shape Features: Fourier Series Parameterization and Submap Joining', IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1527-1534.
View/Download from: Publisher's site
View description>>
One of the valuable directions in feature based SLAM is to parameterize and estimate features accurately. In the real world, closed shape features are especially common. It is necessary to study the feature based SLAM problem on closed shape features. The main contribution of this letter is a 2D laser SLAM approach with Fourier series based feature parameterization and submap joining. In this letter, the Fourier series are introduced to parameterize irregular closed shape features and the SLAM problem with Fourier series feature parameterization is formulated. A submap joining process is also derived in order to reduce the high dependence on precise initial guess and the computing time. The proposed method has been evaluated on both synthetic and actual data and is able to obtain accurate trajectory and feature boundaries. The practical experiment also shows that our method surpasses Cartographer under certain scenarios. We also show that our method has the ability to be applied to the general environment.
Aldini, S, Lai, Y, Carmichael, MG, Paul, G & Liu, D 1970, 'Real-time Estimation of the Strength Capacity of the Upper Limb for Physical Human-Robot Collaboration', 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, Mexico, pp. 4533-4536.
View/Download from: Publisher's site
View description>>
In physical Human-Robot Collaboration (pHRC), having an estimate of the operator’s strength capacity can help implement control strategies. Currently, the trend is to integrate devices that can measure physiological signals. This is not always a viable option, especially for highly dynamic tasks. For pHRC tasks, the physical interaction point usually occurs at the operator’s hand. Therefore, a musculo-skeletal model was used to have a real-time estimation of the strength capacity of the operator’s upper limb. First, the model has been simplified to reduce the complexity of the problem. The model was used to obtain offline estimations of the strength capacity, that were then curve-fitted to enable real-time estimation. An experiment was carried out to compare the results of the approximated model with human data. Results suggest that this method for estimating the strength capacity of the upper limb is a viable solution for real-time applications.
Aldini, S, Singh, AK, Carmichael, M, Wang, Y-K, Liu, D & Lin, C-T 1970, 'Prediction-Error Negativity to Assess Singularity Avoidance Strategies in Physical Human-Robot Collaboration', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Xi'an, China, pp. 3241-3247.
View/Download from: Publisher's site
View description>>
In physical human-robot collaboration (pHRC), singularity avoidance strategies are often critical to obtain stable interaction dynamics. It is hypothesised a predictable singularity avoidance strategy is preferred in pHRC as humans tend to maximise predictability when using complex systems. By using an electroencephalogram (EEG), it is possible to assess the predictability of a task through a feature found in event-related potentials (ERP) and called prediction-error negativity (PEN). In this paper, two research questions are addressed. Can a complex pHRC singularity avoidance strategy generate a detectable PEN? Are PEN and human preferences related when comparing different control settings in a singularity avoidance strategy? Fourteen participants compared two different sets of parameters (modes) in a singularity avoidance strategy based on the exponentially damped least-squared (EDLS) method. ERP results are presented in terms of power spectral density (PSD). ERP results were then compared with human preferences to see whether they are related. Results show that the mode that causes PEN is also the one that participants did not like, suggesting that a lack of predictability might have an impact on human preference.
Banuelos, DP, Falque, R, Patten, T & Alempijevic, A 1970, 'Skirting Line Annotation via Deformation Modelling', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Melbourne, VIC.
View description>>
Automating the process of wool handling has the potential to drastically improve the productivity of on-farm operations that would result in significant cost savings for wool growers. Towards this goal, we present a method to automatically extract the skirting line (i.e., the separation between clean and contaminated wool) by comparing pre- and post-skirted RGB images of freshly shorn wool fleece. The intention is to provide annotation to support downstream learning methods. Our approach detects feature correspondences then performs non-rigid outlier rejection to overcome the challenge of deformation when the wool is handled. The final alignment, and hence identification of the skirting line, is achieved through the use of a non-rigid deformation method. A controlled experiment shows, quantitatively, that our approach outperforms a rigid registration baseline. We then demonstrate the applicability to the real use case by presenting qualitative results on images of skirted fleeces collected from a wool shed.
Brian Lee, KM, Kong, F, Cannizzaro, R, Palmer, JL, Johnson, D, Yoo, C & Fitch, R 1970, 'An Upper Confidence Bound for Simultaneous Exploration and Exploitation in Heterogeneous Multi-Robot Systems', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Byun, H, Kim, J, Liu, D & Woolfrey, J 1970, 'Towards a Pantograph-based Interventional AUV for Under-ice Measurements', Australasian Conference on Robotics and Automation, ACRA.
View description>>
This paper addresses the design of a novel interventional robotic platform, aiming to perform an autonomous sampling and measurement under the thin ice in the Antarctic environment. We propose a pantograph mechanism, which can effectively generate a constant interaction force to the surface during the contact, which is crucial for reliable measurements. We provide the proof-of-concept design of the pantograph with a robotic prototype with foldable actuation. Preliminary results of the pantograph mechanism and the localisation system are provided, confirming the feasibility of the system.
Chen, S, Han, R, Zhao, L, Hang, S & Hao, Q 1970, 'Multi-robot Feature-based SLAM using Submap Joining', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Melbourne, Australia, pp. 1-8.
View description>>
This paper considers the feature-based SLAM using multiple robots. To reduce the computational complexity and data storage, a distributed multi-robot feature-based SLAM algorithm under submap joining scheme is proposed. Each robot first independently builds a submap using the information collected by its sensors. Once the robots can observe each other, the submaps can then be fused together to obtain a global map. We implemented and tested the proposed algorithm in both simulation and real world environments. Both simulation and experimental results have validated the robustness and accuracy of the proposed algorithm.
Chotisathiantham, P, Lai, Y & Paul, G 1970, 'Design of a Wearable Robotic Glove for Rehabilitation', Australasian Conference on Robotics and Automation, ACRA.
View description>>
This paper presents the design and prototype of a wearable robotic glove, integrating additive manufacturing (AM) processes to enhance the customisability and bio-compatibility of the glove. Each feature of the design is tested and evaluated to achieve the optimal design which assists the user to achieve their desired grasp. The glove is lightweight, sleek in design, customisable, comfortable to wear, and simple to use as a result of employing AM in the fabrication process. AM enables bespoke parts to be constructed and assembled quickly with soft and flexible material, as well as allowing designs to be easily revised. Experimental results show that the glove is able to perform the four frequently used grasp types and grasp various primitive-shaped objects. Overall, the prototype is able to demonstrate a simplistic design that can provide sufficient force during flexion and extension of the fingers to assist users with lowered hand mobility.
Devkar, G, Sankaran, S, Ke, Y, Ninan, J, Mathur, S, Tsang, I & Vuorinen, L 1970, 'Data Analytics to Evaluate Public Value from Megaprojects', 6th PMI Research and Academic Virtual Conference, PMI India, India, pp. 30-40.
View description>>
The unprecedented investment in megaprojects that has been witnessed in recent years seems likely to accelerate post Covid-19 with several countries, like Australia and the United Kingdom, announcing large infrastructure projects for economic revival. COVID-19 has also created social challenges due to increased unemployment that could result in increase in poverty which could be helped when these projects become a reality. However, some scholars caution that rapid urbanisation and inappropriate development of infrastructure could work against containing a pandemic like COVID-19. The creation of value delivered by megaprojects has been gaining a lot of interest by scholars studying megaprojects. Big data sets are increasingly used to help public managers derive real-time insights into behavioural changes, public opinion, or daily life. Big data has been used to evaluate customer agility and responsiveness for public value creation. Based on this need this paper we would like to address the following question in our paper: How can data science enable evaluation and monitoring of delivery of public value over the life cycle of a megaproject?. Some work towards this aim has already been carried out by the authors but more is needed. The authors have been collected and analyzed social media data from transport projects from Australia and India to see how large amounts data collected from these media can aid in the evaluation of benefits realized from these projects
D'Urso, G, Heon Lee, JJ, Pizarro, O, Yoo, C & Fitch, R 1970, 'Hierarchical MCTS for Scalable Multi-Vessel Multi-Float Systems', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Furukawa, T, Steckenrider, JJ & Dissanayake, G 1970, 'State Estimation of a Partially Observable Multi-Link System with No Joint Encoders Incorporating External Dead-Reckoning', 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 7342-7348.
View/Download from: Publisher's site
Gunasekara, SR, Jayasuriya, M, Harischandra, N, Samaranayake, L & Dissanayake, G 1970, 'A Convolutional Neural Network Based Early Warning System to Prevent Elephant-Train Collisions.', ICIIS, 2021 IEEE 16th International Conference on Industrial and Information Systems, IEEE, Kandy, Sri Lanka, pp. 271-276.
View/Download from: Publisher's site
View description>>
One serious facet of the worsening Human-Elephant Conflict (HEC) in nations such as Sri Lanka involves elephant-train collisions. Endangered Asian elephants are maimed or killed during such accidents, which also often results in orphaned or disabled elephants. Furthermore, railway services incur significant financial losses and disruptions to services annually due to such accidents. Most elephant-train collisions occur due to a lack of adequate reaction time due to poor driver visibility at sharp turns, night-time operation, and poor weather conditions. Initial investigations also indicate that most collisions occur in localised “hotspots” where elephant pathways/corridors intersect with railway tracks. Taking these factors into consideration, this work proposes the leveraging of recent developments in Convolutional Neural Network (CNN) technology to detect elephants using an RGB/infrared capable camera, around known hotspots along the railway track. The CNN was trained using a curated dataset of elephants collected on field visits to elephant sanctuaries and wildlife parks in Sri Lanka. With this vision-based detection system at its core, a prototype unit of an early warning system was designed and tested. Initial results indicate that detection accuracy is sufficient under varying lighting situations, provided that comprehensive training datasets that represent a wide range of challenging conditions are available. The overall hardware prototype was shown to be robust and reliable. We envision a network of such units may help contribute to reducing the problem of elephanttrain collisions and has the potential to act as an important surveillance mechanism in dealing with the broader issue of the human-elephant conflict.
Gunatilake, A, Galea, M, Thiyagarajan, K, Kodagoda, S, Piyathilaka, L & Darji, P 1970, 'Using UHF-RFID Signals for Robot Localization Inside Pipelines', 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), IEEE, pp. 1109-1114.
View/Download from: Publisher's site
View description>>
Underground water pipes are important to any country's infrastructure. Overtime, the metallic pipes are prone to corrosion, which can lead to water leakage and pipe bursts. In order to prolong the service life of those assets, water utilities in Australia apply protective pipe linings. Long-term monitoring and timely intervention are crucial for maintaining those lining assets. However, the water utilities do not possess the comprehensive technology to achieve it. The main reasons for lacking such technology are the unavailability of sensors and accurate robot localization technologies. Feature based localization methods such as SLAM has limited use as the application of liners alters the features and the environment. Encoder based localization is not accurate enough to observe the evolution of defects over a long period of time requiring unique defect correspondence. This motivates us to explore accurate contact-less and wireless based localization methods. We propose a cost-effective localization method using UHF-RFID signals for robot localization inside pipelines based on Gaussian process combined particle filter. Experiments carried out in field extracted pipe samples from the Sydney water pipe network show that using the RSSI and Phase data together in the measurement model with particle filter algorithm improves the localization accuracy up to 15 centimeters precision.
Gunatilake, A, Thiyagarajan, K & Kodagoda, S 1970, 'Evaluation of Battery-free UHF-RFID Sensor Wireless Signals for In-pipe Robotic Applications', 2021 IEEE Sensors, 2021 IEEE Sensors, IEEE, pp. 1-4.
View/Download from: Publisher's site
Hanna, P, Carmichael, M & Clemon, L 1970, 'Development of an Organisational Framework for the Optimal and Efficient Selection of Actuators', Volume 5: Biomedical and Biotechnology, ASME 2021 International Mechanical Engineering Congress and Exposition, American Society of Mechanical Engineers, Virtual.
View/Download from: Publisher's site
View description>>
Abstract Actuators are a vital component, and more often than not one of the limiting factors in robotics and robotics related applications. For the use of actuators in robotics related to humanoids, exoskeletons, prosthetics and orthoses, there are more factors that influence the selected actuator than the basic mechanical outputs, size, backlash, material and power consumption. The main interest within these applications is that because the device is being carried by the human user, thus weight, power consumption and form factor are important selection parameters. The correct selection of an actuator for these applications is a difficult and lengthy process to perform. This paper creates an organizational framework and database for searching the wide range of actuators. This dataset is organized into a design tool that plots the properties of each actuator on varying graphs creating trade-off Ashby charts to rapidly narrow the selection space for designers. A case study is performed to demonstrate the use of this design tool in human-centric actuation applications. The database is utilized in the selection of the ideal actuator based on lines of best fit and a multivariate regression analysis for the optimization of parameters about the required specifications. In addition, a meta-analysis identifies clusters of current actuators, gaps for new developments, and trends. This work provides research direction into developing specific actuators to fit into these trend gaps which offers substantial benefits to humanoids, exoskeletons, prosthetics and orthosis.
Huang, S, Chen, Y, Zhao, L, Zhang, Y & Xu, M 1970, 'Some Research Questions for SLAM in Deformable Environments', 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 7653-7660.
View/Download from: Publisher's site
Katuwandeniya, K, Kiss, SH, Shi, L & Miro, JV 1970, 'Intention Modelling with Normalizing Flows for User-centric Collaborative Navigation', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Australian Robotics and Automation Association, Melbourne.
View description>>
A predictive agent to help the operator of an assistive mobility device like a wheelchair to cooperatively navigate in accordance with the environment is proposed. The framework is predicated on interpreting a user’s intended future trajectory to take intervention decisions in real time and collaboratively operate the robotic agent. The work incorporates user control signals alongside information from the surroundings via visual feedback and the recent history of the agent’s motions to learn a conditional Normalizing Flow, an advanced deep generative model with the crucial ability to recover exact likelihoods for each of its samples. The integration leads to a uniform probabilistic framework for user intention estimation conditioned on different types of information. Experimental results in an urban navigation simulator (CARLA) demonstrate prediction accuracy increases up to 22.89% when user control inputs are being modelled jointly by the proposed end-to-end framework. A baseline comparison where user controls are considered independent and subsequently fused also suggests that the proposed deep learning based solution provides a stepped improvement. The framework paves the way for a fully functional shared-control navigation strategy for intelligent collaborative control intervention.
Katuwandeniya, K, Kiss, SH, Shi, L & Valls Miro, J 1970, 'Multi-modal Scene-compliant User Intention Estimation in Navigation', 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 1001-1006.
View/Download from: Publisher's site
Kiss, SH, Katuwandeniya, K, Alempijevic, A & Vidal-Calleja, T 1970, 'Probabilistic Dynamic Crowd Prediction for Social Navigation', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 9269-9275.
View/Download from: Publisher's site
Kong, FH, To, KYC, Brassington, G, Anstee, S & Fitch, R 1970, '3D Ensemble-Based Online Oceanic Flow Field Estimation for Underwater Glider Path Planning', 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Prague, pp. 4358-4365.
View/Download from: Publisher's site
Lai, Y, Sutjipto, S, Carmichael, MG & Paul, G 1970, 'Preliminary Validation of Upper Limb Musculoskeletal Model using Static Optimization', 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), IEEE, Mexico, pp. 4509-4512.
View/Download from: Publisher's site
View description>>
Musculoskeletal models are powerful analogues to simulate human motion through kinematic and dynamic analysis. When coupled with feature-rich software, musculoskeletal models form an attractive platform for the integration of machine learning for human motion analysis. Performing realistic simulations using these models provide an avenue to overcome constraints when collecting real-world data sets. This motivates the need to further investigate the validity, efficacy, and accuracy of each available model to ensure that the resultant simulations are transferable to real-world applications. Using the open-source software, OpenSim, the primary aim of this paper is to validate an upper limb musculoskeletal model widely used in research. Muscle activation results from static optimization are evaluated against real-world data. A secondary aim is to investigate the effects of two muscle force generation constraints when evaluating the model’s validity. Results show an agreement between the optimized muscle activation trends and real-world sEMG readings. However, it was found that static optimization of the musculoskeletal model is unable to identify voluntary co-contractions since the redundant model has more muscles than the system’s degrees of freedom. Thus, future work will look to utilize additional channels of information to incorporate this during analysis.
Lee, CYH, Best, G & Hollinger, GA 1970, 'Optimal Sequential Stochastic Deployment of Multiple Passenger Robots', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Lee, CYH, Best, G & Hollinger, GA 1970, 'Stochastic Assignment for Deploying Multiple Marsupial Robots', 2021 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), 2021 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), IEEE.
View/Download from: Publisher's site
Lee, KMB, Yoo, C & Fitch, R 1970, 'Signal Temporal Logic Synthesis as Probabilistic Inference', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 5483-5489.
View/Download from: Publisher's site
Mao, Z, Zhao, L, Huang, S, Fan, Y & Lee, AP-W 1970, 'Direct Bundle Adjustment for 3D Image Fusion with Application to Transesophageal Echocardiography', 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Prague, Czech Republic, pp. 548-554.
View/Download from: Publisher's site
View description>>
In this paper, we propose a novel algorithm for fusing a sequence of 3D images, named as Direct Bundle Adjustment (DBA). This algorithm simultaneously optimizes the global pose parameters of image frames and the intensity values of the fused global image using the 3D image data directly (without extracting features from the images). This one-step 3D image fusion approach is achieved by formulating the problem as an optimization problem to minimize the intensity differences between the global image and the corresponding points in the different local images. The proposed DBA method is particularly useful in the scenarios where distinct features are not available, such as Transesophageal Echocardiography (TEE) images. We validate the proposed method via simulated and in-vivo 3D TEE images. It is shown that the proposed method is robust to intensity noises and much more accurate than the conventional sequential fusion method.
Mathur, S, Sankaran, S, Macaulay, S & Tsang, I 1970, 'A framework to manage data science initiatives', PMI Research and Academic Conference 2021, PM India, Mubai, pp. 20-29.
Munasinghe, N, Masangkay, J & Paul, G 1970, 'Temperature Compensated 3D Printed Strain Sensor for Advanced Manufacturing Applications', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Xi’an China, pp. 7006-7012.
View/Download from: Publisher's site
Nguyen, L, Thiyagarajan, K, Ulapane, N & Kodagoda, S 1970, 'Multimodal Sensor Selection for Multiple Spatial Field Reconstruction', 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), IEEE, pp. 1181-1186.
View/Download from: Publisher's site
View description>>
The paper addresses the multimodal sensor selection problem where selected colocated sensor nodes are employed to effectively monitor and efficiently predict multiple spatial random fields. It is first proposed to exploit multivariate Gaussian processes (MGP) to model multiple spatial phenomena jointly. By the use of the Matérn cross-covariance function, cross-covariance matrices in the MGP model are sufficiently positive semi-definite, concomitantly providing efficient prediction of all multivariate processes at unmeasured locations. The multimodal sensor selection problem is then formulated and solved by an approximate algorithm with an aim to select the most informative sensor nodes so that prediction uncertainties at all the fields are minimized. The proposed approach was validated in the real-life experiments with promising results.
Nguyen, L, Thiyagarajan, K, Ulapane, N & Kodagoda, S 1970, 'Multivariate versus Univariate Sensor Selection for Spatial Field Estimation', 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), IEEE, pp. 1187-1192.
View/Download from: Publisher's site
View description>>
The paper discusses the sensor selection problem in estimating spatial fields. It is demonstrated that selecting a subset of sensors depends on modelling spatial processes. It is first proposed to exploit Gaussian process (GP) to model a univariate spatial field and multivariate GP (MGP) to jointly represent multivariate spatial phenomena. A Matérn cross-covariance function is employed in the MGP model to guarantee its cross-covariance matrices to be positive semi-definite. We then consider two corresponding univariate and multivariate sensor selection problems in effectively monitoring multiple spatial random fields. The sensor selection approaches were implemented in the real-world experiments and their performances were compared. Difference of results obtained by the univariate and multivariate sensor selection techniques is insignificant; that is, either of the methods can be efficiently used in practice.
Nikoloska, R, Vitanage, D, Bykerk, L, Valls Miro, J, Liang, B, Xu, J & Wang, Y 1970, 'Advances in Leak Prevention to Minimise Unaccounted Water', Australia's International Water Conference and Exhibition, OzWater'21 Australia's International Water Conference and Exhibition, Adelaide.
Patten, T, Alempijevic, A & Fitch, R 1970, 'Learning Image-Based Contaminant Detection in Wool Fleece from Noisy Annotations', Computer Vision Systems, Springer International Publishing, pp. 234-244.
View/Download from: Publisher's site
View description>>
This paper addresses the problem of detecting natural contaminants in freshly shorn wool fleece in RGB images using deep learning-based semantic segmentation. The challenge of inconsistent annotation is overcome by learning the probability of contamination as opposed to a discrete class. From the continuous value predictions, contaminated regions can be extracted by selectively thresholding on the probability of contamination. Furthermore, the imbalance of the class distributions is accounted for by adaptively weighting each pixel’s contribution to the loss function. Results show that the adaptive weight improves the prediction accuracy and overall outperforms learning an approximated representation by quantising the distributions.
Rizvi, MA, Sankaran, S, Yip, MH & Carnemolla, P 1970, 'Value Co-creation in Developing Sustainable Cyber-Physical Product Service Systems: Applying Design Science Research Method', EURAM 2021, EURAM 2021, Online.
View description>>
Current market trends show that customers no longer perceive value in a product but in the solution it provides. Consequently, businesses are realigning their value proposition to provide solutions than just selling products. Such offerings combined with the advancement in smart capabilities have given rise to cyber-physical product-service systems (CPPSS), which enable customised solution through value co-creation between customers and providers. Among other benefits, CPPSS could support Sustainable Development Goals 9, 12 and 17 by creating partnerships to transform industry towards responsible production and consumption. Therefore, industry and academia are looking for a holistic design method to build CPPSSs catering to evolving customer needs. This research used the design science research method to propose a service-centric CPPSS design model and demonstrated its application using multiple case studies. This study has implications for project management practice as using the Design Science Research process explains how CPPSS projects are managed.
Scheide, E, Best, G & Hollinger, GA 1970, 'Behavior Tree Learning for Robotic Task Planning through Monte Carlo DAG Search over a Formal Grammar', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Sutjipto, S, Woolfrey, J, Carmichael, M & Paul, G 1970, 'Cartesian Inertia Reshaping for Physical Human Robot Interaction', Conference on Automation Science and Engineering, IEEE Conference on Automation Science and Engineering, Lyon, France.
Sutjipto, S, Woolfrey, J, Carmichael, MG & Paul, G 1970, 'Cartesian Inertia Optimization via Redundancy Resolution for Physical Human-Robot Interaction', 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), IEEE, Lyon, France, pp. 570-575.
View/Download from: Publisher's site
View description>>
The objective of introducing robotic manipulators into human-centric domains is to improve the efficacy of tasks in a safe and practical manner. The shift toward collaborative manipulator platforms has facilitated physical human-robot interaction (pHRI) in such environments. Often, these platforms are kinematically redundant and possess more degrees of freedom (DOF) than needed to complete a desired task. When no additional task is defined, it is possible for the manipulator to converge upon joint configurations that are unfavourable for the collaborative task. Consequently, there is potential for the posture of the manipulator to affect the interaction experienced. This paper investigates an inertia-based optimization control method for redundant manipulators interacting with an active agent. The inertia-based reconfiguration is evaluated through simulations and quantified with real-life experiments conducted with a robot-robot dyad. It was found that resolving redundancy to reconfigure the Cartesian inertia reduced the energy expenditure of the active agent during the interaction.
To, KYC, Kong, FH, Lee, KMB, Yoo, C, Anstee, S & Fitch, R 1970, 'Estimation of Spatially-Correlated Ocean Currents from Ensemble Forecasts and Online Measurements', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Ulapane, N, Thiyagarajan, K & Kodagoda, S 1970, 'Gaussian Process As a Benchmark for Optimal Sensor Placement Strategy', 2021 IEEE Sensors, 2021 IEEE Sensors, IEEE.
View/Download from: Publisher's site
Ulapane, N, Thiyagarajan, K, Kodagoda, S & Nguyen, L 1970, 'D-Optimal Design for Information Driven Identification of Static Nonlinear Elements', 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), 2021 IEEE 16th Conference on Industrial Electronics and Applications (ICIEA), IEEE, Chengdu, China, pp. 492-497.
View/Download from: Publisher's site
View description>>
Identification of static nonlinear elements (i.e., nonlinear elements whose outputs depend only on the present value of inputs) is crucial for the success of system identification tasks. Identification of static nonlinear elements though can pose several challenges. Two of the main challenges are: (1) mathematical models describing the elements being unknown and thus requiring black-box identification; and (2) collection of sufficiently informative measurements. With the aim of addressing the two challenges, we propose in this paper a method of predetermining informative measurement points offline (i.e., prior to conducting experiments or seeing any measured data), and using those measurements for online model calibration. Since we deal with an unknown model structure scenario, a high order polynomial model is assumed. Over fit and under fit avoidance are achieved via checking model convergence via an iterative means. Model dependent information maximization is done via a D-optimal design of experiments strategy. Due to experiments being designed offline and being designed prior to conducting measurements, this method eases off the computation burden at the point of conducting measurements. The need for in-the-loop information maximization while conducting measurements is avoided. We conclude by comparing the proposed D-optimal design method with a method of in-the-loop information maximization and point out the pros and cons. The method is demonstrated for the single-input-single-output (SISO) static nonlinear element case. The method can be extended to MISO systems as well.
Valls Miro, J, Hunt, D, Hussein, M, Rossi, R, Gladigau, C, Dissanayake, G, Vitanage, D, McDonald, S & Sunarho, J 1970, 'Internal Robotic Tool for Remote Wall Condition Assessment and Inspection of Rising Mains', Australia's International Water Conference and Exhibition, OzWater'21 Australia's International Water Conference and Exhibition, Adelaide.
Vu, TL, Le, DT, Nguyen, DDK, Sutjipto, S & Paul, G 1970, 'Investigating the Effect of Sensor Data Visualization Variances in Virtual Reality', Proceedings of the 27th ACM Symposium on Virtual Reality Software and Technology, VRST '21: 27th ACM Symposium on Virtual Reality Software and Technology, ACM, pp. 1-5.
View/Download from: Publisher's site
Xu, M, Song, Y, Chen, Y, Huang, S & Hao, Q 1970, 'Invariant EKF based 2D Active SLAM with Exploration Task', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Xi'an, China, pp. 5350-5356.
View/Download from: Publisher's site
View description>>
Right invariant extended Kalman filter (RIEKF) based simultaneous localization and mapping (SLAM) proposed recently has shown to be able to produce more consistent SLAM estimates as compared with traditional EKF based SLAM methods, including some improved EKF SLAM methods such as observability constrained-EKF (OC-EKF) SLAM. Latest results have demonstrated that its performance is very close to optimization based SLAM algorithms such as iSAM. In this paper, we propose to use RIEKF SLAM algorithm in active SLAM where both the predicted SLAM results for choosing control actions and the actual estimated SLAM results applying the selected control actions are computed using RIEKF algorithms. The advantages over traditional EKF based active SLAM are the more accurate and consistent predicted uncertainty estimates which result in robustness of the active SLAM algorithm. The advantages over optimization based active SLAM is the reduced computational cost. Simulation results are presented to validate the advantages of the proposed algorithm3.
Yang, T, Miro, JV, Wang, Y & Xiong, R 1970, 'Optimal Object Placement for Minimum Discontinuity Non-revisiting Coverage Task', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 8422-8428.
View/Download from: Publisher's site
Yoo, C, Heon Lee, JJ, Anstee, S & Fitch, R 1970, 'Path Planning in Uncertain Ocean Currents using Ensemble Forecasts', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Xi'an, China, pp. 8323-8329.
View/Download from: Publisher's site
View description>>
We present a path planning framework for marine robots subject to uncertain ocean currents that exploits data from ensemble forecasting, which is a technique for current prediction used in oceanography. Ensemble forecasts represent a distribution of predicted currents as a set of flow fields that are considered to be equally likely. We show that the typical approach of computing the vector-wise mean and variance over this set can yield meaningless results, and propose an alternative approach that considers each flow field in the ensemble simultaneously. Our framework finds a sequence of vehicle controls that minimises the root-mean-square error distance (RMSE) over the full set of ensemble-induced trajectories. The key to achieving computational efficiency in this approach is our use of Monte Carlo tree search (MCTS) with a specialised heuristic that improves convergence rate while preserving asymptotic optimality and the anytime property. We demonstrate our results using real ensemble forecasts provided by the Australian Bureau of Meteorology, and provide comparisons with the deterministic mean-based approach where we observe RMSE reductions of 92% and 43% in two example scenarios. Further, we argue that the framework can be used in a plan-as-you-go manner where ensemble forecasts change over time. These results help to introduce ensemble forecasts as a viable source of data to improve path planning in marine robotics.
Zhang, S, Zhao, L, Huang, S, Ma, R, Hu, B & Hao, Q 1970, '3D Reconstruction of Deformable Colon Structures based on Preoperative Model and Deep Neural Network', 2021 IEEE International Conference on Robotics and Automation (ICRA), 2021 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Xi'an, China, pp. 1875-1881.
View/Download from: Publisher's site
View description>>
In colonoscopy procedures, it is important to rebuild and visualize the colonic surface to minimize the missing regions and reinspect for abnormalities. Due to the fast camera motion and deformation of the colon in standard forward-viewing colonoscopies, traditional simultaneous localization and mapping (SLAM) systems work poorly for 3D reconstruction of colon surfaces and are prone to severe drift. Thus in this paper, a preoperative colon model segmented from CT scans is used together with the colonoscopic images to achieve the 3D colon reconstruction. The proposed framework includes dense depth estimation from monocular colonoscopic images using a deep neural network (DNN), visual odometry (VO) based camera motion estimation and an embedded deformation (ED) graph based non-rigid registration algorithm for deforming 3D scans to the segmented colon model. A realistic simulator is used to generate different simulation datasets with ground truth. Simulation results demonstrate the good performance of the proposed 3D colonic surface reconstruction method in terms of accuracy and robustness. In-vivo experiments are also conducted and the results show the practicality of the proposed framework for providing useful shape and texture information in colonoscopy applications.
Zhao, L, Mao, Z & Huang, S 1970, 'Feature-Based SLAM: Why Simultaneous Localisation and Mapping?', Robotics: Science and Systems XVII, Robotics: Science and Systems 2021, Robotics: Science and Systems Foundation, virtual.
View/Download from: Publisher's site
Byun, H, Kim, J, Liu, D & Woolfrey, J 2021, 'Towards a Pantograph-based Interventional AUV for Under-ice Measurement'.
Byun, H, Kim, J, Vanegas, F & Gonzalez, F 2021, 'Schmidt or Compressed filtering for Visual-Inertial SLAM?'.
Chris, Lee, Best, G & Hollinger, GA 2021, 'Optimal Sequential Stochastic Deployment of Multiple Passenger Robots'.
Chris, Lee, Best, G & Hollinger, GA 2021, 'Stochastic Assignment for Deploying Multiple Marsupial Robots'.
Gunatilake, A, Thiyagarajan, K, kodagoda, S, Piyathilaka, L & Darji, P 2021, 'Using UHF-RFID Signals for Robot Localization Inside Pipelines', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Hassan, S, Byun, H & Kim, J 2021, 'Iterative Smoothing and Outlier Detection for Underwater Navigation'.
Kong, FH, To, KYC, Brassington, G, Anstee, S & Fitch, R 2021, '3D Ensemble-Based Online Oceanic Flow Field Estimation for Underwater Glider Path Planning'.
Lee, KMB, Kong, FH, Cannizzaro, R, Palmer, JL, Johnson, D, Yoo, C & Fitch, R 2021, 'An Upper Confidence Bound for Simultaneous Exploration and Exploitation in Heterogeneous Multi-Robot Systems', arXiv.
Lee, KMB, Kong, FH, Cannizzaro, R, Palmer, JL, Johnson, D, Yoo, C & Fitch, R 2021, 'Decentralised Intelligence, Surveillance, and Reconnaissance in Unknown Environments with Heterogeneous Multi-Robot Systems', arXiv.
Lee, KMB, Yoo, C & Fitch, R 2021, 'Signal Temporal Logic Synthesis as Probabilistic Inference', arXiv.
Mao, Z, Zhao, L, Huang, S, Fan, Y & Lee, AP-W 2021, 'DSR: Direct Simultaneous Registration for Multiple 3D Images'.
Ng, Y, Li, H & Kim, J 2021, 'Uncertainty Estimation of Dense Optical-Flow for Robust Visual Navigation'.
Nguyen, L, Thiyagarajan, K, Ulapane, N & kodagoda, S 2021, 'Multimodal Sensor Selection for Multiple Spatial Field Reconstruction', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Nguyen, L, Thiyagarajan, K, Ulapane, N & kodagoda, S 2021, 'Multivariate versus Univariate Sensor Selection for Spatial Field Estimation', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Song, Y, Zhang, Z, Wu, J, Wang, Y, Zhao, L & Huang, S 2021, 'A Right Invariant Extended Kalman Filter for Object based SLAM'.
To, KYC, Kong, FH, Lee, KMB, Yoo, C, Anstee, S & Fitch, R 2021, 'Estimation of Spatially-Correlated Ocean Currents from Ensemble Forecasts and Online Measurements', arXiv.
Ulapane, N, Thiyagarajan, K, kodagoda, S & Nguyen, L 2021, 'D-Optimal Design for Information Driven Identification of Static Nonlinear Elements', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Zhang, Z, Jiao, Y, Huang, S, Wang, Y & Xiong, R 2021, 'Toward Consistent Drift-free Visual Inertial Localization on Keyframe Based Map'.