Bykerk, L & Valls Miro, J 2022, 'Detection of Water Leaks in Suburban Distribution Mains with Lift and Shift Vibro-Acoustic Sensors', Vibration, vol. 5, no. 2, pp. 370-382.
View/Download from: Publisher's site
View description>>
Leaks in Water Distribution Networks (WDNs) account for a large proportion of Non-Revenue Water (NRW) for utilities worldwide. Typically, a leak is only confirmed once water surfaces, allowing the leak to be traced; however, a high percentage of leaks may never surface, incurring large water losses and costs for utilities. Active Leak Detection (ALD) methods can be used to detect hidden leaks; however, the success of such methods is highly dependent on the available detection instrumentation and the experience of the operator. To aid in the detection of both hidden and surfacing leaks, deployment of vibro-acoustic sensors is being increasingly explored by water utilities for temporary structural health monitoring. In this paper, data were collected and curated from a range of temporary Lift and Shift (L&S) vibro-acoustic sensor deployments across suburban Sydney. Time-frequency and frequency-domain features were generated to assess the performance and suitability of two state-of-the-art binary classification models for water leak detection. The results drawn from the extensive field data sets are shown to provide reliable leak detection outcomes, with accuracies of at least 97% and low false positive rates. Through the use of such a reliable leak detection system, utilities can streamline their leak detection and repair processes, effectively mitigating NRW and reducing customer disruptions.
Bykerk, L & Valls Miro, J 2022, 'Vibro-Acoustic Distributed Sensing for Large-Scale Data-Driven Leak Detection on Urban Distribution Mains', Sensors, vol. 22, no. 18, pp. 6897-6897.
View/Download from: Publisher's site
View description>>
Non-surfacing leaks constitute the dominant source of water losses for utilities worldwide. This paper presents advanced data-driven analysis methods for leak monitoring using commercial field-deployable semi-permanent vibro-acoustic sensors, evaluated on live data collected from extensive multi-sensor deployments across a sprawling metropolitan city. This necessarily includes a wide variety of pipeline sizes, materials and surrounding soils, as well as leak sources and rates brought about by external factors. The novel proposition for structural pipe health monitoring shows that excellent leak/no-leak classification results (>94% accuracy) can be observed using Convolutional Neural Networks (CNNs) trained with Short-Time Fourier Transforms (STFTs) of the raw audio files. Most notably, it is shown how this can be achieved irrespective of the sensor used, with four models from different manufactures being part of the investigation, and over time across extended densely populated areas.
Chen, Y, Zhao, L, Zhang, Y, Huang, S & Dissanayake, G 2022, 'Anchor Selection for SLAM Based on Graph Topology and Submodular Optimization', IEEE Transactions on Robotics, vol. 38, no. 1, pp. 329-350.
View/Download from: Publisher's site
View description>>
This article considers simultaneous localization and mapping (SLAM) problem for robots in situations where accurate estimates for some of the robot poses, termed anchors, are available. These may be acquired through external means, for example, by either stopping the robot at some previously known locations or pausing for a sufficient period of time to measure the robot poses with an external measurement system. The main contribution is an efficient algorithm for selecting a fixed number of anchors from a set of potential poses that minimizes estimated error in the SLAM solution. Based on a graph-topological connection between the D-optimality design metric and the tree-connectivity of the pose-graph, the anchor selection problem can be formulated approximately as a submatrix selection problem for reduced weighted Laplacian matrix, leading to a cardinality-constrained submodular maximization problem. Two greedy methods are presented to solve this submodular optimization problem with a performance guarantee. These methods are complemented by Cholesky decomposition, approximate minimum degree permutation, order reuse, and rank-1 update that exploit the sparseness of the weighted Laplacian matrix. We demonstrate the efficiency and effectiveness of the proposed techniques on public-domain datasets, Gazebo simulations, and real-world experiments.
Dai, P, Hassan, M, Sun, X, Zhang, M, Bian, Z & Liu, D 2022, 'A framework for multi-robot coverage analysis of large and complex structures', Journal of Intelligent Manufacturing, vol. 33, no. 5, pp. 1545-1560.
View/Download from: Publisher's site
Darwish, A, Halkon, B, Rothberg, S, Oberst, S & Fitch, R 2022, 'A comparison of time and frequency domain-based approaches to laser Doppler vibrometer instrument vibration correction', Journal of Sound and Vibration, vol. 520, pp. 116607-116607.
View/Download from: Publisher's site
Fan, Y, Liu, D & Ye, L 2022, 'A Novel Continuum Robot With Stiffness Variation Capability Using Layer Jamming: Design, Modeling, and Validation', IEEE Access, vol. 10, pp. 130253-130263.
View/Download from: Publisher's site
View description>>
This paper presents a novel continuum robot (OctRobot-I) that has controllable stiffness variation capability in both the transverse and axial directions. Robot design, stiffness variation analysis and experimental testing are discussed in detail. Stiffness models based on the Euler-Bernoulli beam theory are developed, and then four static deflection cases are analysed. Experiments are conducted with two types of layer jamming sheaths (overlap numbers n =3, 5) and four different vacuum pressures (0kPa, 25kPa, 50kPa, 75kPa) at three different bending angles (0°, 90°, 180°). The results demonstrate that the stiffness changing tendency is in compliance with the derived models and show that the robot has a good stiffness variable capability. With the jamming sheath of n =3, the stiffness ranges (ratios) are 36.4 to 241.7 N/m (6.6) and 92.9 to 19.3×103 N/m (207.8) in the transverse and axial directions, respectively. With the jamming sheath of n =5, the stiffness ranges (ratios) are 65.7 to 398.3 N/m (6.1) and 106.7 to 20.8×103 N/m (194.9) in the transverse and axial directions, respectively. Additionally, the actuating and gripping experiments demonstrate that this robot has good performance in real-world applications.
Gunatilake, A, Kodagoda, S & Thiyagarajan, K 2022, 'A Novel UHF-RFID Dual Antenna Signals Combined With Gaussian Process and Particle Filter for In-Pipe Robot Localization', IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 6005-6011.
View/Download from: Publisher's site
View description>>
Condition assessment of underground infrastructures such as pipe networks is crucial for aging cities around the globe. The development of robotic technologies over the years led to the application of them in the condition assessment of pipe networks. However, there is a gap for accurate localization technology due to the complexity of the environment. In this letter, we propose a novel ultra-high frequency radio frequency identification (UHF-RFID) technology dual antenna system combined with Gaussian process and Particle filter algorithms to achieve millimetre level localization accuracy. The system is capable of achieving millimetre level accuracy over 50m of length without an apparent estimation drift. The results were validated through experiments conducted using an extracted water pipe section.
Gunatilake, A, Kodagoda, S & Thiyagarajan, K 2022, 'Battery-Free UHF-RFID Sensors-Based SLAM for In-Pipe Robot Perception', IEEE Sensors Journal, vol. 22, no. 20, pp. 20019-20026.
View/Download from: Publisher's site
Huang, S & Zhao, L 2022, '2021 IEEE RAS Winter School on Simultaneous Localization and Mapping in Deformable Environments [Education]', IEEE Robotics & Automation Magazine, vol. 29, no. 1, pp. 120-122.
View/Download from: Publisher's site
View description>>
Simultaneous localization and mapping (SLAM) is an important research problem for robot navigation in unknown environments, particularly when GPS is not available. SLAM requires a robot to be able to build a map of the environment in real time and simultaneously estimate its own location within the map. In the past two decades, significant progress has been made in the research for SLAM in static environments. However, when an environment has deformations, such as when a surgical robot is navigating in internal body environments, SLAM needs to build a time-varying 3D map of the soft tissues and estimate the location of the robot/sensor within the map. This poses a challenging problem since the robot/sensor is moving while the environment is deforming.
Jin, L, Ruckin, J, Kiss, SH, Vidal-Calleja, T & Popovic, M 2022, 'Adaptive-Resolution Field Mapping Using Gaussian Process Fusion With Integral Kernels', IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 7471-7478.
View/Download from: Publisher's site
Kiss, SH, Katuwandeniya, K, Alempijevic, A & Vidal-Calleja, T 2022, 'Constrained Gaussian Processes With Integrated Kernels for Long-Horizon Prediction of Dense Pedestrian Crowd Flows', IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 7343-7350.
View/Download from: Publisher's site
Lai, Y, Paul, G, Cui, Y & Matsubara, T 2022, 'User intent estimation during robot learning using physical human robot interaction primitives', Autonomous Robots, vol. 46, no. 2, pp. 421-436.
View/Download from: Publisher's site
View description>>
AbstractAs robotic systems transition from traditional setups to collaborative work spaces, the prevalence of physical Human Robot Interaction has risen in both industrial and domestic environments. A popular representation for robot behavior is movement primitives which learn, imitate, and generalize from expert demonstrations. While there are existing works in context-aware movement primitives, they are usually limited to contact-free human robot interactions. This paper presents physical Human Robot Interaction Primitives (pHRIP), which utilize only the interaction forces between the human user and robot to estimate user intent and generate the appropriate robot response during physical human robot interactions. The efficacy of pHRIP is evaluated through multiple experiments based on target-directed reaching and obstacle avoidance tasks using a real seven degree of freedom robot arm. The results are validated against Interaction Primitives which use observations of robotic trajectories, with discussions of future pHRI applications utilizing pHRIP.
Masangkay, J, Munasinghe, N, Watterson, P & Paul, G 2022, 'Simulation and experimental characterisation of a 3D-printed electromagnetic vibration sensor', Sensors and Actuators A: Physical, vol. 338, pp. 113470-113470.
View/Download from: Publisher's site
View description>>
Additive manufacturing, also known as 3D printing has already transformed from a rapid prototyping tool to a final end-product manufacturing technique. 3D printing can be used to develop various types of sensors. This paper investigates the ability to use the electromagnetic induction properties of 3D printed carbon-based filament for developing sensors. The paper presents a novel prototype vibration sensor which is 3D-printable, except for an included NdFeB magnet. Motion is detected from the voltage induced by the relative motion of the magnet. The devised vibration sensor is simulated using ANSYS, and a novel prototype is 3D-printed for physical testing to characterise and understand its electromagnetic properties. Simulation helped establish constraints for the design. Two types of experimental setups were physically tested, one setup with a magnet freely sliding inside a cylindrical cavity within an oscillating coil, and the other setup with a stationary coil and oscillating magnet. At a frequency of 10 Hz and a motion travel of about 12 mm, the induced voltage for the moving coil case varied from 5.4 mV RMS for pure sliding motion of the internal magnet to 22.1 mV RMS. The findings of this paper suggest that future sensors can be developed using the electromagnetic induction properties of the carbon-based filament.
Mehami, J, Falque, R, Vidal-Calleja, T & Alempijevic, A 2022, 'Multi-Modal Non-Isotropic Light Source Modelling for Reflectance Estimation in Hyperspectral Imaging', IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 10336-10343.
View/Download from: Publisher's site
View description>>
Estimating reflectance is key when working with hyperspectral cameras. The modelling of light sources can aid reflectance estimation, however, it is commonly overlooked. The key contribution of this letter is a physics-based, data-driven model formed by a Gaussian Process (GP) with a unique mean function capable of modelling a light source with an asymmetric radiant intensity distribution (RID) and a configurable attenuation function. This is referred to as the light-source-mean model. Moreover, we argue that by utilising multi-modal sensing information, we can achieve improved reflectance estimation using the proposed light source model with shape information obtained by depth cameras. An existing reflectance estimation method, that solves the dichromatic reflectance model (DRM) via quadratic programming optimisation, is augmented with terms that allow input of shape information. Experiments in simulation show that the light-source-mean GP model had less error when compared to a parametric model. The improved reflectance estimation outperforms existing methods in simulation by reducing the error by 96.8% on average when compared to existing works. We further validate the improved reflectance estimation method through a multi-modal classification application.
Pietroni, N, Dumery, C, Guenot-Falque, R, Liu, M, Vidal-Calleja, TA & Sorkine-Hornung, O 2022, 'Computational Pattern Making from 3D Garment Models.', CoRR, vol. abs/2202.10272, no. 4, pp. 1-14.
View/Download from: Publisher's site
View description>>
We propose a method for computing a sewing pattern of a given 3D garment model. Our algorithm segments an input 3D garment shape into patches and computes their 2D parameterization, resulting in pattern pieces that can be cut out of fabric and sewn together to manufacture the garment. Unlike the general state-of-the-art approaches for surface cutting and flattening, our method explicitly targets garment fabrication. It accounts for the unique properties and constraints of tailoring, such as seam symmetry, the usage of darts, fabric grain alignment, and a flattening distortion measure that models woven fabric deformation, respecting its anisotropic behavior. We bootstrap a recent patch layout approach developed for quadrilateral remeshing and adapt it to the purpose of computational pattern making, ensuring that the deformation of each pattern piece stays within prescribed bounds of cloth stress. While our algorithm can automatically produce the sewing patterns, it is fast enough to admit user input to creatively iterate on the pattern design. Our method can take several target poses of the 3D garment into account and integrate them into the sewing pattern design. We demonstrate results on both skintight and loose garments, showcasing the versatile application possibilities of our approach.
Rajamohan, D, Kim, J, Garratt, M & Pickering, M 2022, 'Image based Localization under large perspective difference between Sfm and SLAM using split sim(3) optimization', Autonomous Robots, vol. 46, no. 3, pp. 437-449.
View/Download from: Publisher's site
View description>>
AbstractImage based Localization (IbL) uses both Structure from Motion (SfM) and Simultaneous Localization and Mapping (SLAM) data for accurate pose estimation. However, under conditions where there is a large perspective difference between the SfM images and SLAM keyframes, the SfM-SLAM co-visibility graph becomes sparse. As a result, the scale drift can increase especially when using monocular SLAM as part of the IbL framework. The drift rarely gets corrected at loop closure due to its large magnitude. We propose a split affine transformation approach that uses SfM-SLAM information along with Sim(3) optimization to minimize the scale drift. Experiments are performed using an image dataset collected in a campus environment with different trajectories, showing the improvement in scale drift correction with the proposed method. The SLAM data was collected close to plainly textured structures like buildings while SfM images were captured from a larger distance from the building facade which leads to a challenging navigation scenario in the context of IbL. Localizing mobile platforms moving close to buildings is an example of such a case. The paper positively impacts the widespread use of small autonomous robotic platforms, which is to perform an accurate outdoor localization under urban conditions using only a monocular camera.
Rees, N, Thiyagarajan, K, Wickramanayake, S & Kodagoda, S 2022, 'Ground-Penetrating Radar Signal Characterization for Non-destructive Evaluation of Low-Range Concrete Sub-surface Boundary Conditions', IEEE Sensors Letters, vol. 6, no. 4, pp. 1-4.
View/Download from: Publisher's site
Romeijn, T, Behrens, M, Paul, G & Wei, D 2022, 'Experimental analysis of water and slurry flows in gravity-driven helical mineral separators', Powder Technology, vol. 405, pp. 117538-117538.
View/Download from: Publisher's site
Romeijn, T, Behrens, M, Paul, G & Wei, D 2022, 'Instantaneous and long-term mechanical properties of Polyethylene Terephthalate Glycol (PETG) additively manufactured by pellet-based material extrusion', Additive Manufacturing, vol. 59, pp. 103145-103145.
View/Download from: Publisher's site
View description>>
Polyethylene Terephthalate Glycol (PETG) is a highly popular feedstock for extrusion-based additive manufacturing. While data are available on the instantaneous properties of additively manufactured PETG, few research have been done on forecasting the creep behaviour of additively manufactured PETG while accounting for the material altering effects of ageing. This research article aims to enhance the understanding of both the instantaneous and time-dependent mechanical properties of additively manufactured PETG through a series of tensile, FEA simulations, Dynamic Mechanical Analysis (DMA), and two types of creep experiments. The details of experimental and mathematical calculations of the instantaneous and time-dependent properties of additively manufactured PETG are provided. Nine independent material parameters have been determined including three Young's moduli, three shear moduli and three Poisson's ratios, to fully quantify an orthotropic material model of additively manufactured PETG. The printed material exhibited a Young's modulus that is 86.5% of the theoretically possible value in direction 1, a Young's modulus in direction 2 is 66.0% of the theoretical optimum, and a Young's modulus in direction 3 is within 1% of its theoretical maximum. In addition to reporting the creep behaviour of PETG, the novel application of the Time-Temperature Superposition Principle (TTSP) to additively manufactured PETG has been shown to produce an age-affected creep prediction for up to 3.88 years based on samples aged for 221 h and at 23 °C. The methodology and data models have been found to enable predictions for other ages and temperatures. It was concluded that the application of the TTSP creep methodology was limited by the creep test temperature, 60 °C, after which the material began to behave in a non rheologically-simple manner.
Sankaran, S & McIntyre‐Mills, J 2022, 'Energy justice in renewable energy projects: How learning about indigenous knowledge systems could inform systemic practice', Systems Research and Behavioral Science, vol. 39, no. 5, pp. 962-974.
View/Download from: Publisher's site
View description>>
AbstractThis article is aimed at organisations and researchers to urge them to adopt more systemic ways to deal with energy justice issues in renewable energy projects being built around the world to help meet the United Nations Sustainable Development Goal (UNSDG) 7. It will focus on solar and wind farms. While these projects positively contribute towards achieving UNSDG 7 (viz., affordable clean energy), they have also created a variety of justice issues, which need to be addressed. While measures have been taken more recently to redress these issues, we make the case that the application of systemic thinking and practice could maximise the positives and minimise negative impacts of creating short‐term fixes without addressing the underlying root causes of the issues. Using two case studies, we will show how working systemically with indigenous populations and considering indigenous knowledge systems could help in dealing with justice issues.
Sankaran, S, Clegg, S, Müller, R & Drouin, N 2022, 'Energy justice issues in renewable energy megaprojects: implications for a socioeconomic evaluation of megaprojects', International Journal of Managing Projects in Business, vol. 15, no. 4, pp. 701-718.
View/Download from: Publisher's site
View description>>
PurposeThe purpose of this paper is to investigate and discuss stakeholder issues faced by renewable energy megaprojects and in particular solar and wind power projects and their relevance to socioeconomic evaluation of megaprojects.Design/methodology/approachThe paper uses secondary data collected from the recent literature published on stakeholder issues face by mega solar and wind power energy generation projects around the world. The issues are then analysed across specific challenges in five continents where these projects are being developed. The paper then focuses on the literature on energy justice to elaborate the type of issues being faced by renewable energy megaprojects contributing to the achievement of UN Sustainable Goal 7 and their impact on vulnerable communities where these projects are situated.FindingsRenewable energy megaprojects are rarely discussed in the project management literature on megaprojects despite their size and importance in delivering sustainable development goals. While these projects provide social benefits they also create issues of justice due to their impact of vulnerable populations living is locations where these projects are situated. The justice issues faced include procedural justice, distributive justice, recognition inequalities. The type of justice issues was found to vary intensity in the developed, emerging and developing economies. It was found that nonprofit organisations are embarking on strategies to alleviate energy justice issues in innovative ways. It was also found that, in some instances, smaller local projects developed with community participation could actually contribute more equitable to the UN sustainable development go...
Scherer, S, Agrawal, V, Best, G, Cao, C, Cujic, K, Darnley, R, DeBortoli, R, Dexheimer, E, Drozd, B, Garg, R, Higgins, I, Keller, J, Kohanbash, D, Nogueira, L, Pradhan, R, Tatum, M, Viswanathan, V, Willits, S, Zhao, S, Zhu, H, Abad, D, Angert, T, Armstrong, G, Boirum, R, Dongare, A, Dworman, M, Hu, S, Jaekel, J, Ji, R, Lai, A, Lee, YH, Luong, A, Mangelson, J, Maier, J, Picard, J, Pluckter, K, Saba, A, Saroya, M, Scheide, E, Shoemaker-Trejo, N, Spisak, J, Teza, J, Yang, F, Wilson, A, Zhang, H, Choset, H, Kaess, M, Rowe, A, Singh, S, Zhang, J, Hollinger, G & Travers, M 2022, 'Resilient and Modular Subterranean Exploration with a Team of Roving and Flying Robots', Field Robotics, vol. 2, no. 1, pp. 678-734.
View/Download from: Publisher's site
View description>>
Subterranean robot exploration is difficult, with many mobility, communications, and navigation challenges that require an approach with a diverse set of systems, and reliable autonomy. While prior work has demonstrated partial successes in addressing the problem, here we convey a comprehensive approach to address the problem of subterranean exploration in a wide range of tunnel, urban, and cave environments. Our approach is driven by the themes of resiliency and modularity, and we show examples of how these themes influence the design of the different modules. In particular, we detail our approach to artifact detection, pose estimation, coordination, planning, control, and autonomy, and we discuss our performance in the tunnel, urban, and self-organized cave circuits of the DARPA Subterranean Challenge. Our approach led to a winning result in the tunnel circuit, and placing second in the urban circuit event. We convey lessons learned in designing and testing a resilient system for subterranean exploration that can generalize to a large range of operating conditions, and potential improvements for the future.
Song, Y, Zhang, Z, Wu, J, Wang, Y, Zhao, L & Huang, S 2022, 'A Right Invariant Extended Kalman Filter for Object Based SLAM', IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 1316-1323.
View/Download from: Publisher's site
View description>>
With the recent advance of deep learning based object recognition and estimation, it is possible to consider object level SLAM where the pose of each object is estimated in the SLAM process. In this letter, based on a novel Lie group structure, a right invariant extended Kalman filter (RI-EKF) for object based SLAM is proposed. The observability analysis shows that the proposed algorithm automatically maintains the correct unobservable subspace, while standard EKF (Std-EKF) based SLAM algorithm does not. This results in a better consistency for the proposed algorithm comparing to Std-EKF. Finally, simulations and real world experiments validate not only the consistency and accuracy of the proposed algorithm, but also the practicability of the proposed RI-EKF for object based SLAM problem. The MATLAB code of the algorithm is made publicly available.
Spindler, KP, Imrey, PB, Yalcin, S, Beck, GJ, Calbrese, G, Cox, CL, Fadale, PD, Farrow, L, Fitch, R, Flanigan, D, Fleming, BC, Hulstyn, MJ, Jones, MH, Kaeding, C, Katz, JN, Kriz, P, Magnussen, R, McErlean, E, Melgaard, C, Owens, BD, Saluan, P, Strnad, G, Winalski, CS & Wright, R 2022, 'Design Features and Rationale of the BEAR-MOON (Bridge-Enhanced ACL Restoration Multicenter Orthopaedic Outcomes Network) Randomized Clinical Trial', Orthopaedic Journal of Sports Medicine, vol. 10, no. 1, pp. 232596712110654-232596712110654.
View/Download from: Publisher's site
View description>>
Background: BEAR (bridge-enhanced anterior cruciate ligament [ACL] restoration), a paradigm-shifting technology to heal midsubstance ACL tears, has been demonstrated to be effective in a single-center 2:1 randomized controlled trial (RCT) versus hamstring ACL reconstruction. Widespread dissemination of BEAR into clinical practice should also be informed by a multicenter RCT to demonstrate exportability and compare efficacy with bone--patellar tendon–bone (BPTB) ACL reconstruction, another clinically standard treatment. Purpose: To present the design and initial preparation of a multicenter RCT of BEAR versus BPTB ACL reconstruction (the BEAR: Multicenter Orthopaedic Outcomes Network [BEAR-MOON] trial). Design and analytic issues in planning the complex BEAR-MOON trial, involving the US National Institute of Arthritis and Musculoskeletal and Skin Diseases, the US Food and Drug Administration, the BEAR implant manufacturer, a data and safety monitoring board, and institutional review boards, can usefully inform both clinicians on the trial’s strengths and limitations and future investigators on planning of complex orthopaedic studies. Study Design: Clinical trial. Methods: We describe the distinctive clinical, methodological, and operational challenges of comparing the innovative BEAR procedure with the well-established BPTB operation, and we outline the clinical motivation, experimental setting, study design, surgical challenges, rehabilitation, outcome measures, and planned analysis of the BEAR-MOON trial. Results: BEAR-MOON is a 6-center, 12-surgeon, 200-patient randomized, partially blinded, noninferiority RCT comparing BEAR with BPTB ACL reconstruction for trea...
Thiyagarajan, K, Kodagoda, S, Luu, M, Harper, T, Ritchie, D, Prentice, K & Martin, J 2022, 'Intelligent Guide Robots for People who are Blind or have Low Vision: A Review', Vision Rehabilitation International, vol. 13, no. 1, pp. 1-15.
View/Download from: Publisher's site
Walker, P, Li, T, Khonasty, R, Ponnanna, KM, Kuo, A, Zhao, L & Huang, S 2022, 'Proof of concept study for using UR10 robot to help total hip replacement', The International Journal of Medical Robotics and Computer Assisted Surgery, vol. 18, no. 2, p. e2359.
View/Download from: Publisher's site
View description>>
AbstractBackgroundThe demand for total hip replacement (THR) for treating osteoarthritis has grown substantially worldwide. The existing robotic systems used in THR are invasive and costly. This study aims to develop a less‐invasive and low‐cost robotic system to assist THR surgery.MethodsA preliminary robotic reaming system was developed based on a UR10 robot equipped with a reamer to cut acetabulum. A novel approach was proposed to cut through a 5 mm hole in femur such that the operation is less invasive to the patients.ResultsThe average error of the cutting hemisphere by the robotic reaming system is 0.1182 mm which is smaller than the average result reaming by hand (0.1301 mm).ConclusionThe robotic reaming can help make THR procedures less invasive and more accurate. Moreover, the system is expected to be significantly less expensive than the robotic systems available in the market at present.
Wang, K, Ke, Y, Liu, T & Sankaran, S 2022, 'Social sustainability in Public–Private Partnership projects: case study of the Northern Beaches Hospital in Sydney', Engineering, Construction and Architectural Management, vol. 29, no. 6, pp. 2437-2460.
View/Download from: Publisher's site
View description>>
PurposeThe purpose of this paper is to present evidence to the heated debate “whether Public-Private Partnership (PPP) model should be introduced into the hospitals” and, if so, how to promote the social sustainability of such PPP projects.Design/methodology/approachThis paper has established an analytical framework to analyse the social sustainability of PPP projects. Using content analysis method, a single case study was carried out on the Northern Beaches Hospital in Sydney, Australia.FindingsThe results show that there are many problems related to social sustainability in the project, due to which employees and patients were exposed to most of them. Some recommendations are provided, including to strengthen the supervision of the project, provide sufficient information, establish communication channels and stakeholder participation, improve hospital policies and procedures, and strengthen government support.Practical implicationsThis paper can provide guidance for the stakeholders in a partnership, including the public and private sectors, to analyse the social sustainability implications, and then plan and implement hospital PPP projects to achieve social sustainability goals. Meanwhile, it can also provide important reference for the employees, patients, local community and society to assess social sustainability issues, and provide relevant inputs to inform decision-makers in the development, delivery and management of hospital projects.Originality/valueThe research will contribute to ...
Wang, Q, Liu, D, Carmichael, MG, Aldini, S & Lin, C-T 2022, 'Computational Model of Robot Trust in Human Co-Worker for Physical Human-Robot Collaboration', IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 3146-3153.
View/Download from: Publisher's site
View description>>
Trust is key to achieving successful Human-Robot Interaction (HRI). Besides trust of the human co-worker in the robot, trust of the robot in its human co-worker should also be considered. A computational model of a robot's trust in its human co-worker for physical human-robot collaboration (pHRC) is proposed. The trust model is a function of the human co-worker's performance which can be characterized by factors including safety, robot singularity, smoothness, physical performance and cognitive performance. Experiments with a collaborative robot are conducted to verify the developed trust model.
Wickramanayake, S, Thiyagarajan, K & Kodagoda, S 2022, 'Deep Learning for Estimating Low-Range Concrete Sub-Surface Boundary Depths Using Ground Penetrating Radar Signals', IEEE Sensors Letters, vol. 6, no. 3, pp. 1-4.
View/Download from: Publisher's site
Wickramanayake, S, Thiyagarajan, K, Kodagoda, S & Piyathilaka, L 2022, 'Ultrasonic thickness measuring in-pipe robot for real-time non-destructive evaluation of polymeric spray linings in drinking water pipe infrastructure', Mechatronics, vol. 88, pp. 102913-102913.
View/Download from: Publisher's site
Yang, T, Miro, JV, Wang, Y & Xiong, R 2022, 'Optimal Task-Space Tracking With Minimum Manipulator Reconfiguration', IEEE Robotics and Automation Letters, vol. 7, no. 2, pp. 5079-5086.
View/Download from: Publisher's site
View description>>
An optimal solution to the task-space tracking problem using a non-redundant manipulator is proposed. This is a recurring occurrence in automated manufacturing settings, e.g. welding, deburring, painting, or quality control inspections. Given a pre-defined path for the end-effector to follow, there may not exist a joint-space continuous solution for task-space tracking when the non-linear manipulator kinematics and collision avoidance with obstacles in the workcell are considered. This introduces undesirable manipulator reconfigurations where the end-effector is required to deviate temporarily from the pre-defined path. The unwanted motion results in pausing task-space tracking, often incurring not only ineffective time and energy demands but potentially compromising the quality of the task at hand due to the additional discontinuities. An algorithm is proposed that provides a globally optimal perspective to the choice of suitable joint-space connected segments so that the minimum number of manipulator reconfigurations during task-space tracking is guaranteed. By carefully selecting the inverse kinematic solutions, all sequences ensuring minimum reconfigurability are proven collected by Dynamic Programming. Moreover, a faster greedy strategy is suggested to increase the computational efficiency of the tracker whilst still preserving global optimality and completeness. The effectiveness of the proposed algorithm is validated against traditional sampling-based solvers in simulation and illustrated on challenging real-world tracking experimentation with a Universal Robotics manipulator and a curved-surface object, depicted also in an accompanying video. An open-source implementation has also been provided for the benefit of the robotics community.
Yang, Y, Zhao, L & Liu, X 2022, 'Iterative Zero-Shot Localization via Semantic-Assisted Location Network', IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 5974-5981.
View/Download from: Publisher's site
View description>>
This paper considers zero-shot localization problem where the images used for localization are taken from new locations that are not included in the training dataset. We propose the Semantic-Assisted Location Network (SLN), which considers a new location essentially as a new combination of certain semantic classes. Moreover, we propose an iterative zero-shot learning method based on Expectation-Maximization (EM) algorithm to deal with the problem that the inter-class relationships of class representations in image embedding space and class embedding space are inconsistent. Experiments show that the proposed iterative zero-shot learning method outperforms start-of-the-art zero-shot localization methods by a large margin.
Zhao, X, Liu, Y, Wang, Z, Wu, K, Dissanayake, G & Liu, Y 2022, 'TG: Accurate and Efficient RGB-D Feature With Texture and Geometric Information', IEEE/ASME Transactions on Mechatronics, vol. 27, no. 4, pp. 1973-1981.
View/Download from: Publisher's site
Best, G, Garg, R, Keller, J, Hollinger, GA & Scherer, S 1970, 'Resilient Multi-Sensor Exploration of Multifarious Environments with a Team of Aerial Robots', Robotics: Science and Systems XVIII, Robotics: Science and Systems 2022, Robotics: Science and Systems Foundation.
View/Download from: Publisher's site
Bourahmoune, K, Ishac, K, Carmichael, M & Amagasa, T 1970, 'Owro: A Novel Robot For Sitting Posture Training Based On Adaptive Human Robot Interaction', 2022 IEEE International Conference on Big Data (Big Data), 2022 IEEE International Conference on Big Data (Big Data), IEEE.
View/Download from: Publisher's site
Byun, H, Zhao, L, Kim, J & Huang, S 1970, 'Comparison Between MATLAB Bundle Adjustment Function and Parallax Bundle Adjustment', 2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV), 2022 17th International Conference on Control, Automation, Robotics and Vision (ICARCV), IEEE, pp. 60-65.
View/Download from: Publisher's site
View description>>
Bundle Adjustment (BA) takes a crucial part in Structure from Motion (SfM) which refines a visual reconstruction by optimizing the camera poses and feature positions. The performance of BA can differ depending on the parametrization methods. This paper evaluates two bundle adjustment techniques using standard BA function from MATLAB and Parallax BA. The two BA techniques are compared using data from the 'Starry Night' and 'MALAGA Parking-6L' with different initial inputs. The accuracy and convergence properties of the two BA methods have been evaluated. The effect of the different parameterization techniques and initial information was also analyzed. In most cases, the results of Parallax BA show better accuracy with lower final reprojection error and are less sensitive to the initialization values. It is evaluated that the parallax angle avoids the singularity issue commonly found in Standard BA, which shows that Parallax BA outperforms Standard BA. Furthermore, visual-inertial SLAM (VI-SLAM), based on Parallax BA, has been presented. It is much more reliable than a pure-vision system, showing further improved performance in terms of robustness and accuracy, even with less feature observation. The open-source code can be found in: https://github.com/uts-hb/ParallaxBA.git
Caro, F & Carmichael, MG 1970, 'Laminar Jamming with Trapezoidal Pin Mechanism for Variable Stiffness Robotic Arms', 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2022 IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, pp. 1061-1066.
View/Download from: Publisher's site
Chen, S, Zhao, L, Huang, S & Hao, Q 1970, 'Multi-robot Active SLAM based on Submap-joining for Feature-based Representation Environments', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Brisbane.
View description>>
The ability to acquire knowledge of the environment actively is essential for autonomous system. In this paper, we propose a multi-robot active simultaneous localization and mapping (SLAM) algorithm based on mutual information for feature-based representation environments that do not depend on the grid map. A multi-layer motion planner and virtual landmarks are introduced to improve exploration efficiency and reduce planning time. To improve the system's accuracy and scalability, we also developed a decentralized version of the active SLAM based on the submap-joining approach. Both simulations and real-world experiments are performed to validate the effectiveness of the proposed methods.
Dai, B, Gentil, CL & Vidal-Calleja, T 1970, 'A Tightly-Coupled Event-Inertial Odometry using Exponential Decay and Linear Preintegrated Measurements', 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 9475-9482.
View/Download from: Publisher's site
View description>>
In this paper, we introduce an event-based visual odometry and mapping framework that relies on decaying event-based corners. Event cameras, unlike conventional cam-eras, can provide sensor data during high-speed motions or in scenes with high dynamic ranges. Rather than providing intensity information at a global shutter rate, events are trig-gered asynchronously depending on whether there is a change in brightness at the pixel location. This novel sensing paradigm calls for unconventional ego-motion estimation techniques to address these new challenges. The key aspect of our framework is the use of a continuous representation of inertial measurements to characterise the system's motion which accommodates the asynchronous nature of the event data while estimating a discrete state in an optimisation-based approach. The proposed method relies on corners extracted from events-only data and associates them with a spatio-temporal locality scheme based on exponential decay. Event tracks are then tightly coupled with temporally accurate preintegrated inertial measurements, allowing for the estimation of ego-motion and a sparse map. The proposed method is evaluated on the Event Camera Dataset showing performance against the state-of-art in event-based visual-inertial odometry.
Fernandez, L & Carmichael, MG 1970, 'Preliminary Analysis of a Redundancy Resolution Method for Mobile Manipulators used in Physical Human Robot Interaction', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Brisbane.
View description>>
Adding mobility to a manipulator significantly increases its reachable workspace, allowing it to perform a wider variety of tasks. However, this advantage introduces the problem of expanding the system's solution space, resulting in an increase of different possible joint configurations for one specific end effector pose. Existing frameworks and algorithms have been developed that resolve this redundancy for a specific task. However, special care must be taken when mobile manipulators are used for Physical Human Robot Interaction (pHRI) applications. This paper proposes a basic framework utilising the Projected Gradient (PG) method that can be implemented on mobile manipulators used in pHRI. It illustrates how this redundancy resolution method has characteristics that makes it favourable for pHRI applications. The framework effectively makes use of the manipulator's high degree of precision when the task being executed is within its immediate workspace, while making use of the mobile platform's mobility when the task to be performed is outside of the manipulator's immediate workspace. This framework is validated firstly in simulation and then in a physical experiment. Both experiments successfully demonstrate the desired behaviour of a mobile manipulator system when used in the context of pHRI.
Giubilato, R, Vayugundla, M, Le Gentil, C, Schuster, MJ, McDonald, W, Vidal-Calleja, T, Wedler, A & Triebel, R 1970, 'Robust place recognition with Gaussian Process Gradient Maps for teams of robotic explorers in challenging lunar environments', Proceedings of the International Astronautical Congress, IAC.
View description>>
Teams of mobile robots will play a key role towards future planetary exploration missions. In fact, plans for upcoming lunar exploration, and other extraterrestrial bodies, foresee an extensive usage of robots for the purposes of in-situ analysis, building infrastructure and realizing maps of the environment for its exploitation. To enable prolonged robotic autonomy, however, it is critical for the robotic agents to be able to robustly localize themselves during their motion and, concurrently, to produce maps of the environment. To this end, visual SLAM (Simultaneous Localization and Mapping) techniques have been developed during the years and found successful application in several terrestrial fields, such as autonomous driving, automated construction and agricultural robotics. To this day, autonomous navigation has been demonstrated in various robotic missions to Mars, e.g., from NASA's Mars Exploration Rover (MER) Missions, to NASA's Mars Science Laboratory (Curiosity) and the current Mars2020 Perseverance, thanks to the implementation of Visual Odometry, using cameras to robustly estimate the rover's ego-motion. While VO techniques enable the traversal of large distances from one scientific target to the other, future operations, e.g., for building or maintenance of infrastructure, will require robotic agents to repeatedly visit the same environment. In this case, the ability to re-localize themselves with respect to previously visited places, and therefore the ability to create consistent maps of the environment, is paramount to achieve localization accuracies, that are far above what is achievable from global localization approaches. The planetary environment, however, poses significant challenges to this goal, due to extreme lighting conditions, severe visual aliasing and a lack of uniquely identifiable natural “features”. For this reason, we developed an approach for re-localization and place recognition, that relies on Gaussian Processes, to ef...
Gunasinghe, D, Suddrey, G, Lamont, R, Mount, J, Sukkar, F, Vidal-Calleja, T & Roberts, J 1970, 'A Novel Passive Grasping Robot Control Framework Towards Vision-Based Industrial Steel Bar Conveyor Removal', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Brisbane, QLD Australia.
View description>>
Material handling using robotic automation is critical for enabling efficient and safe environments for numerous industries. In the steel bar manufacturing industry bars of shorter length are occasionally produced that do not match the required batch length. Currently human operators visually classify and manually remove the short bar from a batch of rods moving on a conveyor. This can present a manual handling health and safety risk. This paper demonstrates the output of a feasibility study investigating this problem; resulting in a novel, passive grasping robotic control framework that: (a) emulates the human operator's technique; and (b) successfully removes multiple bar types from a moving conveyor using closed-loop visual control.
Hanna, P, Carmichael, M & Clemon, L 1970, 'Benefit of Optimal Actuator Selection – A Comparative Study', Volume 4: Biomedical and Biotechnology; Design, Systems, and Complexity, ASME 2022 International Mechanical Engineering Congress and Exposition, American Society of Mechanical Engineers.
View/Download from: Publisher's site
View description>>
Abstract Actuators are a vital component, and often the limiting factor in robotics and robotic-related applications like humanoids, exoskeletons, prosthetics and orthosis. Actuator selection is critical due to system design flow-on effects including weight, energy consumption and form factor. A designer’s challenge is often to optimize the actuator to minimize size or weight and meet the performance specifications usually with trade-offs. This paper investigates the design impacts of selecting more suited actuators on the system through a representative humanoid configuration performing a task. It also looks at variations based on the scale of the humanoid using human anthropometric data for variations in limb lengths. The torques and speeds required at each joint to complete the task is simulated and the system design is updated to keep a constant member stress across all designs. The total energy and weight are calculated and used to compare actuator selection impacts. By knowing the extent of the flow-on effects actuator selection has on a configuration, and how this effect scales, designers are able to determine what investment should be allocated to locating the ideal actuator for their task.
Hassan, S, Kim, J & Huang, S 1970, 'An Incremental Robust Underwater Navigation with Expectation-Maximisation', Australasian Conference on Robotics and Automation, ACRA.
View description>>
This paper presents a robust navigation solution using low-cost visual-inertial sensors in a 6-Degree of Freedom (DoF) environment. That is an incremental/online navigation solution using the nonlinear least-squares optimisation with classification expectationmaximisation (EM). In this problem, weights are assigned to each measurement observation using the Cauchy function that are iteratively computed from the errors between predicted robot poses and the observed robot measurement. However, the computational cost is quite high in solving the full-batch estimation via Gauss-Newton. By implementing the sliding window filter (SWF), we introduce an incremental EM based robust navigation where the computational cost is shown a significant reduction compared to the full robust batch estimation. The impact of window size on the navigation performance is studied given the dataset is unknown to predict the optimum window gating. This allows a robust constant-time estimation of the robot pose. Such a capability is desirable in underwater navigation applications such as intervention missions. We verify this work using the experimental dataset collected by the UTS submersible pile inspection robot (SPIR).
Katuwandeniya, K, Kiss, SH, Shi, L & Miro, JV 1970, 'Exact-likelihood User Intention Estimation for Scene-compliant Shared-control Navigation', 2022 International Conference on Robotics and Automation (ICRA), 2022 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Khatkar, J, Clemon, LM, Fitch, R & Mettu, R 1970, 'A Reeb Graph Approach for Faster 3D Printing.', CASE, 2022 IEEE 18th International Conference on Automation Science and Engineering (CASE), IEEE, pp. 277-282.
View/Download from: Publisher's site
View description>>
Material extrusion additive manufacturing is an essential technology for rapid prototyping. The standard approach to planning the deposition toolpath for this technology builds each layer sequentially. Unfortunately this approach typically results in significant wasted motion, which is a barrier for use in industrial production. In this paper, we give a new method for toolpath planning that improves on the layer-based approach as well as our own previous methods that build toolpaths across layers. Our approach utilizes a Reeb decomposition on the input model, which is a geometric decomposition that allows toolpath planning over subcomponents of the model rather than over individual extrusion segments. This allows a top-down construction of toolpaths, and is highly effective. We test our new approach, which we call Reeb planning, over a benchmark of 50 models and achieve a reduction of 49.7% in wasted motion over standard layer-based methods. Our decomposition scheme also provides insight into model classification, which can be used for improved production planning.
Khatkar, J, Yoo, C, Fitch, R, Clemon, LM & Mettu, R 1970, 'Coordinated Toolpath Planning for Multi-Extruder Additive Manufacturing.', IROS, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 10230-10237.
View/Download from: Publisher's site
View description>>
We present a new algorithm for coordinating the motion of multiple extruders to increase throughput in fused filament fabrication (FFF)/fused deposition modeling (FDM) additive manufacturing. Platforms based on FFF are commonly available and advantageous to several industries, but are limited by slow fabrication time and could be could be significantly improved through efficient use of multiple extruders. We propose the coordinated toolpath planning problem for systems of extruders mounted as end-effectors on robot arms with the objective of maximizing utilization and avoiding collisions. Building on the idea of dependency graphs introduced in our earlier work, we develop a planning and control framework that precomputes a set of multi-layer toolpath segments from the input model and efficiently assigns them to individual extruders such that executed toolpaths are collision-free. Our method overcomes key limitations of existing methods, including utilization loss from workspace partitioning, precomputed toolpaths subject to collisions with the partially fabricated object, and wasted motion resulting from strict layer-by-layer fabrication. We report simulation results that show a major increase in utilization compared to single and multi-extruder methods, and favorable fabrication results using commodity hardware that demonstrate the feasibility of our method in practice.
Larpruenrudee, P, Bennett, NS, Hossain, J, Fitch, R & Islam, MS 1970, 'Hydrogen Energy Storage System: How does the semi-cylindrical helical coil heat exchanger affect metal hydride beds' thermal conductivity?', Australasian Fluid Mechanics Conference, Australasian Fluid Mechanics Conference, Sydney, Australia.
View description>>
Metal hydride (MH) is classified as one of the solid material storage technologies for hydrogen storage. This material has been recently used worldwide because of its ability to provide a large hydrogen storage capacity, low operating pressure and high safety. However, the disadvantage of this material is having low thermal conductivity, which leads to it having a slow hydrogen absorption time. For the absorption process, faster heat removal from the MH storage will result in faster absorption. Therefore, enhancing heat transfer performance is one of the most effective ways to improve storage performance. This paper aims to improve the heat transfer performance by employing a semi-cylindrical coil as a heat exchanger embedded inside the storage material. Air is used as the heat transfer fluid (HTF). A comparison of the hydrogen absorption duration and the bed temperature between the semi-cylindrical coil heat exchanger (SCHE) and the traditional helical coil heat exchanger (HCHE) has been made to investigate the effect of heat exchanger configuration designs. These two configurations are designed based on the constant volume of the heat exchanger tube and metal hydride. The numerical simulations are performed by using ANSYS Fluent 2020 R2. The results from this study indicate that the average bed temperature inside the storage by using SCHE is reduced faster than using HCHE, which leads to having a faster hydrogen absorption, approximately 59% time reduction. The key finding from this study could be an important enabler for industrial applications.
Mao, Z, Zhao, L, Huang, S, Fan, Y & Lee, APW 1970, 'DSR: Direct Simultaneous Registration for Multiple 3D Images', Springer Nature Switzerland, pp. 98-107.
View/Download from: Publisher's site
Mathur, S, Sankaran, S, MacAulay, S & Tsang, I 1970, 'MINIMUM VIABLE GOVERNANCE FOR DATA SCIENCE INITIATIVES A TRANSPORT FOR NSW CASE STUDY', Value co-creation in the project society, 10th IPMA Research conference: Value co-creation in the project society, International Project Management Association, Serbian Project Management Association, pp. 65-76.
View/Download from: Publisher's site
View description>>
Too much governance can stifle innovation in organizations. Too little governance can waste precious organizational resources. Business agility demands empowerment of people to take decisions on initiatives designed to deliver innovative products and services. Traditional monthly and quarterly governance forums such as steering committees and program boards for decision-making potentially impede the flow of work when the delivery of a program or project is done using agile methods in two-weekly sprints and decisions are required at a different and more frequent cadence. Data Science Initiatives (DSIs) which are exploratory and innovative in nature follow agile delivery methods. This paper is an exploratory study of implementing governance for DSIs based on a single case study. It investigates agile governance at project, program, and portfolio level for DSIs and suggests eight guiding principles focusing on product and portfolio governance. It is targeted at practitioners to guide them in setting minimum viable governance to ensure value is realized from their DSIs and for academics to advance research in governance of DSIs.
Okour, M, Falque, R, Vidal-Calleja, T & Alempijevic, A 1970, 'Sim2real Cattle Pose Prediction in 3D pointclouds', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia, pp. 1-8.
View description>>
Cattle's body shape and joint articulation carry significant information about their well-being. Building a large dataset of any animals' 3D scans is a challenging task. However, such a dataset is required for training deep learning algorithms for 3D body pose estimation. In this work, we investigate how such a dataset can be constructed for cattle from a single 3D model animated by a digital artist. Further, we reduce the sim2real gap between the virtual dataset and real scans of animals by augmenting the shape of the 3D model to cover the range of possible body shapes. The generated dataset is tested on semantic key points detection with an encoder-decoder architecture.
Paul, G, Tomidei, L, Sick, N, Guertler, M, Carmichael, M & Wambsganss, A 1970, 'Guidelines for Safe Collaborative Robot Design and Implementation', Guidelines for Safe Collaborative Robot Design and Implementation, Guidelines for Safe Collaborative Robot Design and Implementation, Sydney.
Pẽna, F, Mehami, J, Falque, R, Patten, T, Alempijevic, A & Vidal-Calleja, T 1970, 'Subcutaneous Fat Depth Regression Using Hyperspectral and Depth Imaging', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARAA, Brisbane, Australia, pp. 1-10.
View description>>
Robotic perception is becoming an important component for automation in the meat processing industry. Whether for contaminant detection or automatic cutting, multimodal perception systems, in particular, based on hyperspectral imaging have the ability to provide information that goes beyond the texture and colour of a surface. In this paper, we present a learning-based method to estimate subcutaneous fat depth in meat cuts by leveraging hyperspectral data models that rely on the knowledge of modelled light sources and surface shape information. Data from a fully calibrated hyperspectral and colour depth (RGB-D) camera system is used as input. Fat depth ground truth is recovered via a novel systematic approach that ray casts a computed tomography (CT) mesh of the meat cuts, which is nonrigidly aligned with a depth reconstruction captured by the RGB-D camera. We thus evaluate machine learning methods that can handle small datasets, by employing dimensionality reduction and data augmentation to address the limited amount of imbalanced data that is acquired. Our results show that leveraging shape and light models, coupled with machine learning methods that capture nonlinearities and spatial correlations produces the most accurate results.
Sankaran, S, Clegg, S, Killen, C, Smyth, H & Scales, J 1970, 'Visualization of findings on construction project portfolio management using Gioia methodology', EURAM, Zurich.
Smith, W, Qin, Y, Furukawa, T & Dissanayake, G 1970, 'Autonomous Robotic Map Refinement for Targeted Resolution and Local Accuracy', 2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), IEEE.
View/Download from: Publisher's site
Tomidei, L, Sick, N, Guertler, M, Frijat, L, Carmichael, M, Paul, G, Wambsganss, A, Moreno, VH & Hussain, S 1970, 'BEYOND TECHNOLOGY - THE COGNITIVE AND ORGANISATIONAL IMPACTS OF COBOTS', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Brisbane.
View description>>
Work environments are radically changing with the adoption of new technologies. As the trend for automation grows collaborative robots or 'cobots' are being increasingly adopted by organisations from various industries. As opposed to traditional industrial robots, collaborative robots are complex socio-technical systems that allow close interaction between robots and humans. As a result, these systems can have significant impact on the physical and mental well-being of individuals, and safety can be ensured only by addressing physical, cognitive, and organisational factors. This study aims to provide an understanding of the work practices and behaviours in relation to the cognitive and organisational impact of cobots in Australian industries. By raising awareness of the key challenges and possible solutions to address them, this study provides contributions to academia and industry practice.
Wakulicz, J, Brian Lee, KM, Yoo, C, Vidal-Calleja, T & Fitch, R 1970, 'Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression', 2022 International Conference on Robotics and Automation (ICRA), 2022 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Philadelphia, pp. 11066-11072.
View/Download from: Publisher's site
Webster, C, Kong, FH & Fitch, R 1970, 'Bio-inspired 2D Vertical Climbing with a Novel Tripedal Robot', 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 1239-1246.
View/Download from: Publisher's site
Wickramanayake, S, Thiyagarajan, K & Kodagoda, S 1970, 'Deep Learned Ground Penetrating Radar Subsurface Features for Robot Localization', 2022 IEEE Sensors, 2022 IEEE Sensors, IEEE, pp. 1-4.
View/Download from: Publisher's site
Woolfrey, J & Liu, D 1970, 'An Optimal Dynamic Control Method for Robots with Virtual Links', 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 12843-12848.
View/Download from: Publisher's site
View description>>
Virtual links and virtual joints can be appended to the kinematic chain of a robot arm to assist in modelling and control of certain tasks. Activities such as spray painting, sand blasting, or scanning with a laser or camera can be enhanced by modelling the fluid stream, light beam, or field of view using a virtual link. Virtual joints can be used to allow movement in semi-redundant degrees of freedom of the task space. This can can be exploited to optimize the control of the real robot. A prudent choice is to minimize the effort required by the manipulator to execute the task. This often requires the inversion of the inertia matrix. However, virtual links have no inertia so the inverse does not exist. This paper first explores methods of adding virtual mass or modifying the inertia matrix to allow inversion and the consequences. Then an optimal control problem is proposed that minimizes kinetic energy in the real manipulator and maximizes use of the virtual joints. In doing so, we only need the real inertia matrix which is always invertible. The method is validated in a case study for high pressure water blasting. It is shown to reduce the dynamic torque norm compared to a minimum velocity controller.
Xu, M, Zhao, L, Huang, S & Hao, Q 1970, 'Active SLAM in 3D deformable environments', 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 7952-7958.
View/Download from: Publisher's site
View description>>
This paper considers active SLAM problem for 3D deformable environments where the trajectory of the robot is planned to optimize the SLAM results. A planning strategy combining an efficient global planner with an accurate local planner is proposed to solve the problem. Simulation results under different scenarios have shown that the proposed active SLAM algorithm provides a good balance between accuracy and efficiency as compared to the local planner and the global planner. The MATLAB code of this first active SLAM algorithm for 3D deformable environments is made publicly available4.
Zhang, S, Zhao, L, Huang, S, Wang, H, Luo, Q & Hao, Q 1970, 'SLAM-TKA: Real-time Intra-operative Measurement of Tibial Resection Plane in Conventional Total Knee Arthroplasty', Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, Springer Nature Switzerland, pp. 126-135.
View/Download from: Publisher's site
View description>>
Total knee arthroplasty (TKA) is a common orthopaedic surgery to replace a damaged knee joint with artificial implants. The inaccuracy of achieving the planned implant position can result in the risk of implant component aseptic loosening, wear out, and even a joint revision, and those failures most of the time occur on the tibial side in the conventional jig-based TKA (CON-TKA). This study aims to precisely evaluate the accuracy of the proximal tibial resection plane intra-operatively in real-time such that the evaluation processing changes very little on the CON-TKA operative procedure. Two X-ray radiographs captured during the proximal tibial resection phase together with a pre-operative patient-specific tibia 3D mesh model segmented from computed tomography (CT) scans and a trocar pin 3D mesh model are used in the proposed simultaneous localisation and mapping (SLAM) system to estimate the proximal tibial resection plane. Validations using both simulation and in-vivo datasets are performed to demonstrate the robustness and the potential clinical value of the proposed algorithm.
Falque, R, Vidal-Calleja, T & Alempijevic, A 2022, 'Semantic keypoint extraction for scanned animals using multi-depth-camera systems'.
He, Y, Wang, J, Su, D, Nakadai, K, Wu, J, Huang, S, Li, Y & Kong, H 2022, 'Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization'.
Hernandez Moreno, V, Carmichael, MG & Deuse, J 2022, 'Towards Learning by Demonstration for Industrial Assembly Tasks', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Hernandez Moreno, V, Carmichael, MG & Deuse, J 2022, 'Towards Learning by Demonstration for Industrial Assembly Tasks', Institute of Electrical and Electronics Engineers (IEEE).
View/Download from: Publisher's site
Sukkar, F, Wakulicz, J, Lee, KMB, Zhi, W & Fitch, R 2022, 'Multi-query Robotic Manipulator Task Sequencing with Gromov-Hausdorff Approximations', arXiv.
View/Download from: Publisher's site
Usayiwevu, M, Sukkar, F, Yoo, C, Fitch, R & Vidal-Calleja, T 2022, 'Continuous Planning for Inertial-Aided Systems'.
Vu, TL, Nguyen, DDK, Sutjipto, S, Le, DT & Paul, G 2022, 'Investigation of Annotation-assisted User Performance in Virtual Reality-based Remote Robot Control'.
View description>>
This paper investigates the use of point cloud processing algorithms to provide annotations for robotic manipulation tasks completed remotely via Virtual Reality (VR). A VR-based system has been developed that receives and visualises processed data from real-time RGB-D camera feeds. A point cloud processing algorithm is introduced to annotate targets, and simulated experiments were conducted to validate the efficacy of the proposed algorithm. A real-world robot model has also been developed to provide realistic reactions and control feedback. The targets and the robot model are reconstructed in a VR environment and presented to users with different modalities. The modalities and available information are varied between experimental settings, and the associated task performance is recorded and analysed. The results accumulated from 288 experiments completed by 12 participants indicated that point cloud data is sufficient for task completion. Additional information, neither image stream nor preliminary processes presented as annotations, was found to have a signficant impact on the completion time. However, the combination of image stream and colored point cloud data visualisation modalities was found to greatly enhance a user's performance accuracy, with the number of target centres missed being reduced by 25%.
Vu, TL, Nguyen, DDK, Sutjipto, S, Le, DT & Paul, G 2022, 'Investigation of User Performance in Virtual Reality-based Annotation-assisted Remote Robot Control', ACM, pp. 1-2.
View/Download from: Publisher's site
View description>>
This poster investigates the use of point cloud processing algorithms to provide annotations for robotic manipulation tasks completed remotely via Virtual Reality (VR). A VR-based system has been developed that receives and visualizes the processed data from real-time RGB-D camera feeds. A real-world robot model has also been developed to provide realistic reactions and control feedback. The targets and the robot model are reconstructed in a VR environment and presented to users in different modalities. The modalities and available information are varied between experimental settings, and the associated task performance is recorded and analyzed. The results accumulated from 192 experiments completed by 8 participants showed that point cloud data is sufficient for completing the task. Additional information, either image stream or preliminary processes presented as annotations, was found to not have a significant impact on the completion time. However, the combination of image stream and colored point cloud data visualization modalities was found to greatly enhance a user's performance accuracy, with the number of target centers missed being reduced by 40%.
Wakulicz, J, Lee, KMB, Yoo, C, Vidal-Calleja, T & Fitch, R 2022, 'Informative Planning for Worst-Case Error Minimisation in Sparse Gaussian Process Regression', arXiv.
Wu, L, Lee, KMB, Gentil, CL & Vidal-Calleja, T 2022, 'Log-GPIS-MOP: A Unified Representation for Mapping, Odometry and Planning'.
Zhang, S, Zhao, L, Huang, S, Wang, H, Luo, Q & Hao, Q 2022, 'SLAM-TKA: Real-time Intra-operative Measurement of Tibial Resection Plane in Conventional Total Knee Arthroplasty'.
Zhang, Z, Jiao, Y, Huang, S, Wang, Y & Xiong, R 2022, 'Map-based Visual-Inertial Localization: Consistency and Complexity'.
Zhang, Z, Song, Y, Huang, S, Xiong, R & Wang, Y 2022, 'Toward Consistent and Efficient Map-based Visual-inertial Localization: Theory Framework and Filter Design'.
