Agarwal, UA, Jain, K, Anantatmula, V & Shankar, S 2023, Managing People in Projects for High Performance Behavioural Approach to Productive Project Teams, Springer.
View description>>
This book examines practically useful management and people skills, and looks at competencies from the micro, meso, and macro- lens.
Aldini, S & Liu, D 2023, 'Human-Robot Collaboration in Agriculture' in Encyclopedia of Smart Agriculture Technologies, Springer International Publishing, pp. 1-9.
View/Download from: Publisher's site
Aldini, S & Liu, D 2023, 'Human-Robot Collaboration in Agriculture' in Encyclopedia of Digital Agricultural Technologies, Springer International Publishing, pp. 622-629.
View/Download from: Publisher's site
Clegg, S, Loosemore, M, Walker, D, van Marrewijk, A & Sankaran, S 2023, 'Construction Cultures: Sources, Signs, and Solutions of Toxicity', Wiley, pp. 3-16.
View/Download from: Publisher's site
Devkar, G & Sankaran, S 2023, '12 Responsible Leadership in Megaprojects' in De Gruyter Handbook of Responsible Project Management, De Gruyter, pp. 245-266.
View/Download from: Publisher's site
Hernandez Moreno, V, Carmichael, MG & Deuse, J 2023, 'Towards learning by demonstration for industrial assembly tasks' in Annals of Scientific Society for Assembly, Handling and Industrial Robotics 2022, pp. 229-239.
View/Download from: Publisher's site
View description>>
In recent times, learning by demonstration has seen tremendous progress in robotic assembly operations. One of themost prominent trajectory-level taskmodels applied isDynamic Movement Primitives (DMP). However, it lacks the ability to tackle complex operations as often encountered in industrial assembly. Augmenting low-level models with a highlevel framework in which different movement segments are deliberately parameterised is considered promising for such scenarios. This paper investigates the combination of trajectory-level DMPs with Methods-Time Measurement (MTM). We demonstrate how theMTM-1 system is utilised to establish distinguished DMP models for five of its basic elements, paving the way to benefitting from the sophisticated MTM system. The evaluation of the framework is conducted on a generic pick and place operation. Compared to a one-model-fits-all DMP approach for the whole task, the proposed method shows the advantage of appropriate temporal scaling, accuracy levelling and force consideration at adequate times.
Hernandez Moreno, V, Carmichael, MG & Deuse, J 2023, 'Towards Learning by Demonstration for Industrial Assembly Tasks' in Annals of Scientific Society for Assembly, Handling and Industrial Robotics 2022, Springer International Publishing, pp. 229-239.
View/Download from: Publisher's site
View description>>
AbstractIn recent times, learning by demonstration has seen tremendous progress in robotic assembly operations. One of the most prominent trajectory-level task models applied is Dynamic Movement Primitives (DMP). However, it lacks the ability to tackle complex operations as often encountered in industrial assembly. Augmenting low-level models with a high-level framework in which different movement segments are deliberately parameterised is considered promising for such scenarios. This paper investigates the combination of trajectory-level DMPs with Methods-Time Measurement (MTM). We demonstrate how the MTM-1 system is utilised to establish distinguished DMP models for five of its basic elements, paving the way to benefitting from the sophisticated MTM system. The evaluation of the framework is conducted on a generic pick and place operation. Compared to a one-model-fits-all DMP approach for the whole task, the proposed method shows the advantage of appropriate temporal scaling, accuracy levelling and force consideration at adequate times.
Killen, C, Sankaran, S, Clegg, S & Smyth, H 2023, 'Aligning Construction Projects with Strategy' in Construction Project Organising, Wiley, pp. 119-134.
View/Download from: Publisher's site
Kim, J 2023, 'Swarm and Fleet for Agriculture: Scalable Information Fusion Framework' in Encyclopedia of Smart Agriculture Technologies, Springer International Publishing, pp. 1-10.
View/Download from: Publisher's site
Kim, J 2023, 'Swarm and Fleet for Agriculture: Scalable Information Fusion Framework' in Encyclopedia of Smart Agriculture Technologies, Springer International Publishing, pp. 1-9.
View/Download from: Publisher's site
Kim, J 2023, 'Swarm and Fleet for Agriculture: Scalable Information Fusion Framework' in Encyclopedia of Digital Agricultural Technologies, Springer International Publishing, pp. 1421-1429.
View/Download from: Publisher's site
Mathur, S, Sankaran, S, MacAulay, S & Tsang, I 2023, 'Minimum viable governance for data science initiatives' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, UK, pp. 445-456.
View/Download from: Publisher's site
View description>>
This cutting-edge Research Handbook provides a comprehensive overview of research on the governance of projects.
Müller, R, Sankaran, S & Drouin, N 2023, 'A look ahead' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, pp. 458-461.
View/Download from: Publisher's site
Müller, R, Sankaran, S & Drouin, N 2023, 'Introduction to the Research Handbook on the Governance of Projects' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, pp. 1-6.
View/Download from: Publisher's site
Sankaran, S 2023, 'Governance of organizational project management' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, UK, pp. 329-342.
View/Download from: Publisher's site
View description>>
This cutting-edge Research Handbook provides a comprehensive overview of research on the governance of projects.
Sankaran, S 2023, 'Governance of Sustainable Development Goal programs' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, pp. 318-328.
View/Download from: Publisher's site
View description>>
This cutting-edge Research Handbook provides a comprehensive overview of research on the governance of projects.
Sankaran, S 2023, 'Systems theories and systems praxis' in Research Handbook on the Governance of Projects, Edward Elgar Publishing, pp. 50-64.
View/Download from: Publisher's site
View description>>
This cutting-edge Research Handbook provides a comprehensive overview of research on the governance of projects.
Sankaran, S & Bentahar, O 2023, 'The application of mixed methods in project management research: recent trends in their use and reporting' in Handbook of Mixed Methods Research in Business and Management, Edward Elgar Publishing, pp. 141-162.
View/Download from: Publisher's site
Aldini, S, Singh, AK, Leong, D, Wang, Y-K, Carmichael, MG, Liu, D & Lin, C-T 2023, 'Detection and Estimation of Cognitive Conflict During Physical Human–Robot Collaboration', IEEE Transactions on Cognitive and Developmental Systems, vol. 15, no. 2, pp. 959-968.
View/Download from: Publisher's site
View description>>
Robots for physical Human-Robot Collaboration (pHRC) often need to adapt their admittance and how they operate due to several factors. As the admittance of the system becomes variable throughout the workspace, it is not always straightforward for the operator to predict the robot’s behaviour. Previous work demonstrated that cognitive conflicts can be detected during one-dimensional tasks. This work assesses whether cognitive conflicts can also be detected during 2D tasks in pHRC and a classification problem is formulated. Different robot admittance profiles anticipating the stimulus translated into different levels of cognitive conflict. Several commonly used classification algorithms for EEG signals were evaluated to classify different levels of cognitive conflict. Results demonstrate that cognitive conflict level is lower when the admittance smoothly decreases before unexpected events when compared to conditions in which the admittance abruptly decreases before the stimulus. Among the classification algorithms, Convolutional Neural Network has shown the best results to classify different levels of cognitive conflict. Results suggest the feasibility of adaptive approaches for future pHRC control systems that close the loop on users through EEG signals. The detected human cognitive state can also be used to assess and improve the predictability of Human-Robot teams in various pHRC applications.
Cao, C, Nogueira, L, Zhu, H, Keller, J, Best, G, Garg, R, Kohanbash, D, Maier, J, Zhao, S, Yang, F, Cujic, K, Darnley, R, DeBortoli, R, Drozd, B, Sun, P, Higgins, I, Willits, S, Armstrong, G, Zhang, J, Hollinger, G, Travers, M & Scherer, S 2023, 'Exploring the Most Sectors at the DARPA Subterranean Challenge Finals', Field Robotics, vol. 3, no. 1, pp. 801-836.
View/Download from: Publisher's site
View description>>
Autonomous robot navigation in austere environments is critical to missions like “search and rescue”, yet it remains difficult to achieve. The recent DARPA Subterranean Challenge (SubT) highlights prominent challenges including GPS-denied navigation through rough terrains, rapid exploration in large-scale three-dimensional (3D) space, and interrobot coordination over unreliable communication. Solving these challenges requires both mechanical resilience and algorithmic intelligence. Here, we present our approach that leverages a fleet of custom-built heterogeneous robots and an autonomy stack for robust navigation in challenging environments. Our approach has demonstrated superior navigation performance in the SubT Final Event, resulting in the fastest traversal and most thorough exploration of the environment, which won the “Most Sectors Explored Award.” This paper details our approach from two aspects: mechanical designs of a marsupial ground-and-aerial system to overcome mobility challenges and autonomy algorithms enabling collective rapid exploration. We also provide lessons learned in the design, development, and deployment of complex but resilient robotic systems to overcome real-world navigation challenges.
Daniel, C, Hülsheger, UR, Kudesia, RS, Sankaran, S & Wang, L 2023, 'Call for papers: Mindfulness in project management', International Journal of Project Management, vol. 41, no. 4, pp. 102480-102480.
View/Download from: Publisher's site
Daniel, C, Hülsheger, UR, Kudesia, RS, Sankaran, S & Wang, L 2023, 'Mindfulness in projects', Project Leadership and Society, vol. 4, pp. 100086-100086.
View/Download from: Publisher's site
Das, S, Bhattacharjee, M, Thiyagarajan, K & Kodagoda, S 2023, 'Conformable packaging of a soft pressure sensor for tactile perception', Flexible and Printed Electronics, vol. 8, no. 3, pp. 035006-035006.
View/Download from: Publisher's site
View description>>
Abstract Humans can perceive surface properties of an unfamiliar object without relying solely on vision. One way to achieve it is by physically touching the object. This human-inspired tactile perception is a complementary skill for robotic tactile perception. Robot perception depends on the informational quality of the tactile sensor; thus, packaging sensors and integrating them with robots plays a crucial role. In this work, we investigate the influence of conformable packaging designs on soft polydimethylsiloxane-based flexible pressure sensors that work in a variety of surface conditions and load levels. Four different 3D printed packaging designs capable of maintaining sensor trends have been developed. The low detection limits of 0.7 kPa and 0.1 kPa in the piezoresistive and piezocapacitive sensors, respectively, remain unaffected, and a performance variation as low as 30% is observed. Coefficient of variation and sensitivity studies have also been performed. Limit tests show that the designs can handle large forces ranging from 500 N to more than a 1000 N. Lastly, a qualitative study was performed, which covered prospective use-case scenarios as well as the advantages and downsides of each sensor casing design. Overall, the findings indicate that each sensor casing is distinct and best suited for tactile perception when interacting with objects, depending on surface properties.
Das, S, Bhattacharjee, M, Thiyagarajan, K & Kodagoda, S 2023, 'Nonlinear Response Analysis of a Polymer-Based Piezoresistive Flexible Tactile Sensor at Low Pressure', IEEE Sensors Letters, vol. 7, no. 11, pp. 1-4.
View/Download from: Publisher's site
Guertler, M, Tomidei, L, Sick, N, Carmichael, M, Paul, G, Wambsganss, A, Hernandez Moreno, V & Hussain, S 2023, 'WHEN IS A ROBOT A COBOT? MOVING BEYOND MANUFACTURING AND ARM-BASED COBOT MANIPULATORS', Proceedings of the Design Society, vol. 3, pp. 3889-3898.
View/Download from: Publisher's site
View description>>
AbstractCollaborative robots (“cobots”) have attracted growing attention in academia and industry over the last years. Due to in-built safety features and easy programming, they allow for close human-cobot collaboration and support e.g. flexible manufacturing. However, the lack of a common understanding what a cobot is along with its traditional focus on arm-based cobots complicates further research and industry adoption. Thus, this paper analyses the variety of definitions in literature incl. standards and practice examples to derive a consistent and holistic definition and taxonomy of what a collaborative robot is. Aside from contributing a structured overview of various forms of human-robot collaboration, this builds an important foundation for future research as it systematically differentiates different cobot types. Companies and other organisations will benefit by a better understanding of what type of cobot they need and how to ensure safe collaboration.
Jones, DR, Wall, T, Kenworthy, A, Hurd, F, Dyer, S, Hedges, P & Sankaran, S 2023, 'Hiding in plain sight: Exploring the complex pathways between tactical concealment and relational wellbeing', Organization, vol. 30, no. 3, pp. 473-489.
View/Download from: Publisher's site
View description>>
We argue that the current environment in higher education is one of the primary drivers for the widespread adoption of concealment tactics with the aim of enhancing wellbeing. To explore the relationship between concealment and wellbeing, we draw upon Scott’s conceptualization of “hidden transcripts” and Keyes’s five dimensions of social wellbeing. Using a collaborative ethnographic approach, we examine a 2-year period of individual and collective inquiry by an eclectic multidisciplinary, international group of academics. Our empirical and theoretical contributions expose a complex and, at times, seemingly contradictory relationship between tactical concealments and relational wellbeing, with variously generative and destructive pathways between them. Our research offers a lens through which we can critically explore and extend our understanding of alternative pathways to wellbeing in organizational life.
Killen, CP, Sankaran, S, Knapp, M & Stevens, C 2023, 'Embracing paradox and contingency: integration mechanisms for ambidextrous innovation portfolio management', International Journal of Managing Projects in Business, vol. 16, no. 6/7, pp. 743-766.
View/Download from: Publisher's site
View description>>
PurposeThe purpose of this paper is to explore how organizations manage and integrate exploration and exploitation across the innovation project portfolio. Such ambidextrous capabilities are required for organizations to innovate and succeed in today's rapidly changing competitive environment. Understanding how exploration and exploitation projects are integrated can illustrate ways to enhance ambidexterity and boost learning for the benefit of both approaches.Design/methodology/approachA multiple-case study approach was used to explore innovation portfolio management in six large organizations that emphasize innovation in their strategies.FindingsThe findings draw upon concepts of paradox and contingency to reveal that the inherent tension between formality and flexibility in managing innovation project portfolios is aligned with the need for organizational ambidexterity that maintains effective exploitative innovation while supporting explorative innovation capabilities. Four integration mechanisms are identified that enhance ambidexterity across the innovation portfolio by embedding processes for transition from exploration to exploitation and cross-fertilizing knowledge to build innovation capability across both exploration and exploitation.Practical implicationsManagers may find inspiration on ways to enhance learning by bridging exploration and exploitation projects from the four types of integration mechanisms. Recognizing the paradoxical nature of the tension between formality and flexibility in project and portfolio management may also help guide organizations to effectively deve...
Larpruenrudee, P, Bennett, NS, Luo, Z, Fitch, R, Sauret, E & Islam, MS 2023, 'A novel design for faster hydrogen storage: A combined semi-cylindrical and central return tube heat exchanger', Journal of Energy Storage, vol. 71, pp. 108018-108018.
View/Download from: Publisher's site
Le Gentil, C & Vidal-Calleja, T 2023, 'Continuous latent state preintegration for inertial-aided systems', The International Journal of Robotics Research, vol. 42, no. 10, pp. 874-900.
View/Download from: Publisher's site
View description>>
Traditionally, the pose and velocity prediction of a system at time t2 given inertial measurements from a 6-DoF IMU depends on the knowledge of the system’s state at time t1. It involves a series of integration and double integration that can be computationally expensive if performed regularly, in particular in the context of inertial-aided optimisation-based state estimation. The concept of preintegration consists of creating pseudo-measurements that are independent of the system’s initial conditions (pose and velocity at t1) in order to predict the system’s state at t2. These pseudo-measurements, so-called preintegrated measurements, were originally computed numerically using the integration rectangle rule. This article presents a novel method to perform continuous preintegration using Gaussian processes (GPs) to model the system’s dynamics focusing on high accuracy. It represents the preintegrated measurement’s derivatives in a continuous latent state that is learnt/optimised according to asynchronous IMU gyroscope and accelerometer measurements. The GP models allow for analytical integration and double integration of the latent state to generate accurate preintegrated measurements called unified Gaussian preintegrated measurements (UGPMs). We show through extensive quantitative experiments that the proposed UGPMs outperform the standard preintegration method by an order of magnitude. Additionally, we demonstrate that the UGPMs can be integrated into off-the-shelf multi-modal estimation frameworks with ease based on lidar-inertial, RGBD-inertial, and visual-inertial real-world experiments.
Mao, Z, Zhao, L, Huang, S, Jin, T, Fan, Y & Lee, AP 2023, 'Complete region of interest reconstruction by fusing multiview deformable three‐dimensional transesophageal echocardiography images', Medical Physics, vol. 50, no. 1, pp. 61-73.
View/Download from: Publisher's site
View description>>
AbstractBackgroundWhile three‐dimensional transesophageal echocardiography (3D TEE) has been increasingly used for assessing cardiac anatomy and function, it still suffers from a limited field of view (FoV) of the ultrasound transducer. Therefore, it is difficult to examine a complete region of interest without moving the transducer. Existing methods extend the FoV of 3D TEE images by mosaicing multiview static images, which requires synchronization between 3D TEE images and electrocardiogram (ECG) signal to avoid deformations in the images and can only get the widened image at a specific phase.PurposeThis work aims to develop a novel multiview nonrigid registration and fusion method to extend the FoV of 3D TEE images at different cardiac phases, avoiding the bias toward the specifically chosen phase.MethodsA multiview nonrigid registration and fusion method is proposed to enlarge the FoV of 3D TEE images by fusing dynamic images captured from different viewpoints sequentially. The deformation field for registering images is defined by a collection of affine transformations organized in a graph structure and is estimated by a direct (intensity‐based) method. The accuracy of the proposed method is evaluated by comparing it with two B‐spline–based methods, two Demons‐based methods, and one learning‐based method VoxelMorph. Twenty‐nine sequences of in vivo 3D TEE images captured from four patients are used for the comparative experiments. Four performance metrics including checkerboard volumes, signed distance, mean absolute distance (MAD), and Dice similarity coefficient (DSC) are used jointly to evaluate the accuracy of the results. Additionally, pairedt‐tests are performed to examine the significance of the results.<...
Marrewijk, AV, Sankaran, S, Drouin, N & Müller, R 2023, 'Climbing to the top: Personal life stories on becoming megaproject leaders', Project Leadership and Society, vol. 4, pp. 100085-100085.
View/Download from: Publisher's site
Munasinghe, N, Romeijn, T & Paul, G 2023, 'Voxel-based sensor placement for additive manufacturing applications', Journal of Intelligent Manufacturing, vol. 34, no. 2, pp. 739-751.
View/Download from: Publisher's site
Nie, X, Liu, L, He, L, Zhao, L, Lu, H, Lou, S, Xiong, R & Wang, Y 2023, 'Weakly-Interactive-Mixed Learning: Less Labelling Cost for Better Medical Image Segmentation', IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 7, pp. 3270-3281.
View/Download from: Publisher's site
Sankaran, S 2023, 'Review of Productive Pragmatism: Can industrial democracy be viable under neoliberalist capital conditions?', IJAR – International Journal of Action Research, vol. 19, no. 1, pp. 62-73.
View/Download from: Publisher's site
View description>>
I review the two cases of industrial democracy in Norway and Mondragon using multiple perspectives. From a system thinking perspective, I use a General Systems Theory (GST), Viable Systems Model and Soft Systems Methodology. From a management perspective, I examine how institutional entrepreneurship plays a role in creating new ways of coping with regulative, normative, and cultural-cognitive forces impacting the two cases. I then view the two economies from a governmentality perspective on how they deal with power and autonomy. My analysis demonstrates that the two democracies have coped well with internal and external forces. I also argue that industrial democracy would face challenges in dealing with new ways of working that have emerged due to the influence of technology.
Sankaran, S, Ang, K & Hase, S 2023, 'Delphi Method', Journal of Systems Thinking, vol. 3, pp. 1-15.
View/Download from: Publisher's site
View description>>
In this chapter the Delphi method, a dialectical and consensus seeking approach, is applied to management research in ambiguous and uncertain situations. The Delphi method is essentially a process in which responses from many rounds of questions are sent to a group of leaders or experts. This happens for several iterations, and the responses are anonymous and also aggregated prior to sharing in each round. Notably, the leaders/ experts alter their response to the same questions after each round - largely due to the responses they have seen from the larger group. In sum, this process is believed to eventually create consensus as to the correct response for each question.
Sankaran, S, Killen, CP & Pitsis, A 2023, 'How do project-oriented organizations enhance innovation? An institutional theory perspective', Frontiers of Engineering Management, vol. 10, no. 3, pp. 427-438.
View/Download from: Publisher's site
View description>>
AbstractA project-oriented organization is a hybrid form of organization where a functional hierarchy is augmented with structures to manage projects strategically across the organization. Six project-oriented organizations from diverse industries that emphasize innovation in their strategies were selected for this study. We use the three pillars of institutional theory — regulative, normative and cultural-cognitive — and institutional entrepreneurship to analyze interview data from executive and project, program and portfolio management personnel in the project-oriented organizations to investigate how innovation is facilitated through external influences and internal responses. Our findings indicate that processes and new structures provide effective ways for innovation and, while individuals are important, processes are more effective than individuals at enabling innovation. We put forward some lessons for practice that emerge directly from the findings, including suggestions on improving allocation of resources, a need to focus on processes, reconceptualization of “failure”, and dedicated investment in market knowledge, customer knowledge, performance metrics and flexible governance structures.
Shakor, P, Nejadi, S, Paul, G & Gowripalan, N 2023, 'Effects of Different Orientation Angle, Size, Surface Roughness, and Heat Curing on Mechanical Behavior of 3D Printed Cement Mortar With/Without Glass Fiber in Powder-Based 3DP', 3D Printing and Additive Manufacturing, vol. 10, no. 2, pp. 330-355.
View/Download from: Publisher's site
Shepherd, M, Sankaran, S, Shi, Q, Piccard, L & Toma, T 2023, 'Principles-Based Project Management: Where to Now?', Project Management Journal, vol. 54, no. 6, pp. 583-587.
View/Download from: Publisher's site
Singh, K, Saikia, M, Thiyagarajan, K, Thalakotuna, D, Esselle, K & Kodagoda, S 2023, 'Multi-Functional Reconfigurable Intelligent Surfaces for Enhanced Sensing and Communication', Sensors, vol. 23, no. 20, pp. 8561-8561.
View/Download from: Publisher's site
View description>>
In this paper, we propose a reconfigurable intelligent surface (RIS) that can dynamically switch the transmission and reflection phase of incident electromagnetic waves in real time to realize the dual-beam or quad-beam and convert the polarization of the transmitted beam. Such surfaces can redirect a wireless signal at will to establish robust connectivity when the designated line-of-sight channel is disturbed, thereby enhancing the performance of wireless communication systems by creating an intelligent radio environment. When integrated with a sensing element, they are integral to performing joint detection and communication functions in future wireless sensor networks. In this work, we first analyze the scattering performance of a reconfigurable unit element and then design a RIS. The dynamic field scattering manipulation capability of the RIS is validated by full-wave electromagnetic simulations to realize six different functions. The scattering characteristics of the proposed unit element, which incorporates two p-i-n diodes have been substantiated through practical implementation. This involved the construction of a simple prototype and the subsequent examination of its scattering properties via the free-space measurement method. The obtained transmission and reflection coefficients from the measurements are in agreement with the anticipated outcomes from simulations.
Svejvig, P, Sankaran, S & Lindhult, E 2023, 'Guest editorial: Second special issue on action research and variants in project studies and project management', International Journal of Managing Projects in Business, vol. 16, no. 1, pp. 1-8.
View/Download from: Publisher's site
Wang, K, Ke, Y & Sankaran, S 2023, 'Social sustainability of aged care public-private partnership projects in China: Critical practices and realisation paths', Journal of Cleaner Production, vol. 422, pp. 138644-138644.
View/Download from: Publisher's site
View description>>
The profound changes in China's population, economy and social structure have significantly impacted traditional home-based aged care and social welfare, leading to the emergence of Aged Care Public-Private Partnership (PPP) projects for institutional care. Social sustainability is crucial for these projects as it greatly improves stakeholders' quality of life and well-being. Adoption of social sustainability practices enhances elderly and employee satisfaction, offers competitive advantages, and fosters community development. This study aimed to establish a socially sustainable development process for aged care PPP projects. A multiple case study was conducted, and an improved critical incident technique was adopted. Forty-two first-level critical practices that should be adopted by government departments, private investors and Special Purpose Vehicles (SPVs) at different stages in the lifecycle were identified from three main cases and seventeen parallel reference cases. Twenty-one realisation paths and a consolidated realisation path were established based on analysing the enabling relationships between critical practices. The preparation phase is pivotal, with ten of the 21 more important critical practices (i.e., critical practices that appear in all realisation paths) adopted at this phase. The behaviours and decisions of government departments played a key and decisive role, with eighteen more important critical practices adopted by them alone. This study contributes to enhancing knowledge of social sustainability in aged care. The critical practices and the realisation paths provide a complete picture of realising social sustainability of aged care PPP projects. The public and private sectors can adopt corresponding behaviours and decisions at different project stages to deliver projects successfully. The empirical data shows the applicability of stakeholder theory in social sustainability research on aged care. In addition, the results provide insights i...
Wang, T, Lu, W, Yu, H & Liu, D 2023, 'Modular transfer learning with transition mismatch compensation for excessive disturbance rejection', International Journal of Machine Learning and Cybernetics, vol. 14, no. 1, pp. 295-311.
View/Download from: Publisher's site
View description>>
Underwater robots in shallow waters usually suffer from strong wave forces, which may frequently exceed robot’s control constraints. Learning-based controllers are suitable for disturbance rejection control, but the excessive disturbances heavily affect the state transition in Markov Decision Process (MDP) or Partially Observable Markov Decision Process (POMDP). This issue is amplified by training-test model mismatch. In this paper, we propose a transfer reinforcement learning algorithm using Transition Mismatch Compensation (TMC), that learns an additional compensatory policy through minimizing mismatch of transitions predicted by the two dynamics models of the source and target tasks. A modular network of learning policies is applied, composed of a Generalized Control Policy (GCP) and an Online Disturbance Identification Model (ODI). GCP is first trained over a wide array of disturbance waveforms. ODI then learns to use past states and actions of the system to predict the disturbance waveforms which are provided as input to GCP (along with the system state). We demonstrated on a pose regulation task in simulation that TMC is able to successfully reject the disturbances and stabilize the robot under an empirical model of the robot system, meanwhile improve sample efficiency.
Wang, X, Thiyagarajan, K, Kodagoda, S & Zhang, M 2023, 'PIPE-CovNet: Automatic In-Pipe Wastewater Infrastructure Surface Abnormality Detection Using Convolutional Neural Network', IEEE Sensors Letters, vol. 7, no. 4, pp. 1-4.
View/Download from: Publisher's site
Wu, L, Lee, KMB, Le Gentil, C & Vidal-Calleja, T 2023, 'Log-GPIS-MOP: A Unified Representation for Mapping, Odometry, and Planning', IEEE Transactions on Robotics, vol. 39, no. 5, pp. 4078-4094.
View/Download from: Publisher's site
View description>>
Whereas dedicated scene representations are required for each different task in conventional robotic systems, this article demonstrates that a unified representation can be used directly for multiple key tasks. We propose the log-Gaussian process implicit surface for mapping, odometry, and planning (Log-GPIS-MOP): a probabilistic framework for surface reconstruction, localization, and navigation based on a unified representation. Our framework applies a logarithmic transformation to a Gaussian process implicit surface (GPIS) formulation to recover a global representation that accurately captures the Euclidean distance field with gradients and, at the same time, the implicit surface. By directly estimating the distance field and its gradient through Log-GPIS inference, the proposed incremental odometry technique computes the optimal alignment of an incoming frame and fuses it globally to produce a map. Concurrently, an optimization-based planner computes a safe collision-free path using the same Log-GPIS surface representation. We validate the proposed framework on simulated and real datasets in 2-D and 3-D, and benchmark against the state-of-the-art approaches. Our experiments show that Log-GPIS-MOP produces competitive results in sequential odometry, surface mapping, and obstacle avoidance.
Xu, Y, Zheng, R, Zhang, S, Liu, M & Huang, S 2023, 'CARE: Confidence-Rich Autonomous Robot Exploration Using Bayesian Kernel Inference and Optimization', IEEE Robotics and Automation Letters, vol. 8, no. 10, pp. 6755-6762.
View/Download from: Publisher's site
View description>>
In this letter, we consider improving the efficiency of information-based autonomous robot exploration in unknown and complex environments. We first utilize Gaussian process (GP) regression to learn a surrogate model to infer the confidence-rich mutual information (CRMI) of querying control actions, then adopt an objective function consisting of predicted CRMI values and prediction uncertainties to conduct Bayesian optimization (BO), i.e., GP-based BO (GPBO). The trade-off between the best action with the highest CRMI value (exploitation) and the action with high prediction variance (exploration) can be realized. To further improve the efficiency of GPBO, we propose a novel lightweight information gain inference method based on Bayesian kernel inference and optimization (BKIO), achieving an approximate logarithmic complexity without the need for training. BKIO can also infer the CRMI and generate the best action using BO with bounded cumulative regret, which ensures its comparable accuracy to GPBO with much higher efficiency. Extensive numerical and real-world experiments show the desired efficiency of our proposed methods without losing exploration performance in different unstructured, cluttered environments.
Yang, T, Miro, JV, Nguyen, M, Wang, Y & Xiong, R 2023, 'Template-Free Nonrevisiting Uniform Coverage Path Planning on Curved Surfaces', IEEE/ASME Transactions on Mechatronics, vol. 28, no. 4, pp. 1853-1861.
View/Download from: Publisher's site
Ye, K, Ji, JC & Fitch, R 2023, 'Further investigation and experimental study of an origami structure-based quasi-zero-stiffness vibration isolator', International Journal of Non-Linear Mechanics, vol. 157, pp. 104554-104554.
View/Download from: Publisher's site
View description>>
A quasi-zero stiffness (QZS) vibration isolator formed from a truss-spring stacked Miura-ori (TS-SMO) origami structure can provide a desired ultra-low dynamic stiffness for vibration isolation while remaining a high-static stiffness for load supporting capacity. This paper further investigates the design parameters and experimentally studies the dynamic performance of the proposed TS-SMO vibration isolation system. The effects of the spring parameters and the initial setup conditions on its static response are analysed. With the proper parameter selection, the resultant supporting force generated by the origami structure can be expressed as a polynomial containing the static force and dynamic force components which does not have the linear term. The displacement transmissibility of the proposed system is calculated to evaluate its isolation performance. Analytical and numerical results are in good agreement and both demonstrate an ultra-low resonance frequency for vibration isolation. The dynamic behaviour of the proposed system is also investigated under different conditions to enhance the vibration isolation performance. A proof-of-concept prototype is designed, fabricated and tested to verify both static and dynamic performances of the TS-SMO QZS isolator. The comparative experimental results between the corresponding linear isolation system and the proposed nonlinear QZS system validate the design of origami-inspired structure for vibration isolation and further confirm the effectiveness of the QZS vibration isolator. It is hoped that this research would provide a solid foundation for designing and modelling the TS-SMO structure adopted for vibration isolation in practical engineering applications.
Zhang, Y, Falque, R, Zhao, L, Chen, Y, Huang, S & Li, H 2023, 'Structure-to-Shape Aortic 3-D Deformation Reconstruction for Endovascular Interventions', IEEE Transactions on Robotics, vol. 39, no. 4, pp. 2954-2972.
View/Download from: Publisher's site
View description>>
Fluoroscopy-guided endovascular interventions by using X-ray images are challenging. The catheter needs to be manipulated precisely inside the aorta, while only 2-D views from the X-ray fluoroscopy are currently used to help the surgeons. Because the catheter is operated in a 3-D space, a visualization of the deforming 3-D aorta will be useful as guidance for catheter manipulation. Existing 3-D reconstruction methods fall short in only focusing on the deformation reconstruction of the aortic 3-D centerline, or using additional prior knowledge of 3-D catheter position for estimating the aortic 3-D deformation. In this article, we propose a novel framework that reconstructs the aortic 3-D deformation by fusing a preoperative 3-D model and two intraoperative X-ray images. Different from existing methods, the proposed framework reconstructs aortic deformation using a coarse-to-fine pipeline by first reconstructing the aortic 3-D centerline and then reconstructing the 3-D shape. To obtain the accurate features for the fluoroscopic-based 3-D reconstruction, we extract semantic features from the X-ray images, and compute the distance field to efficiently calculate the 3-D-2-D nonrigid correspondence. Nonlinear least squares optimization is used to solve the deformation of both centerline and shape. The proposed framework is validated using phantom and patient datasets, whose results demonstrate improved efficiency and accuracy compared with the existing methods. This framework provides a valuable clinical tool for endovascular interventions.
Zhang, Z, Jiao, Y, Huang, S, Xiong, R & Wang, Y 2023, 'Map-Based Visual-Inertial Localization: Consistency and Complexity', IEEE Robotics and Automation Letters, vol. 8, no. 3, pp. 1407-1414.
View/Download from: Publisher's site
View description>>
Drift-free localization is essential for autonomous vehicles. In this letter, we address the problem by proposing a filter-based framework, which integrates the visual-inertial odometry and the measurements from the pre-built map. In this framework, the transformation between the odometry frame and the pre-built map frame is augmented into the system state vector and estimated on the fly. Besides, we maintain the map keyframe poses and employ the Schmidt extended Kalman filter to update the state partially so that the uncertainty of the map information can be consistently considered with low computational complexity. Moreover, we theoretically demonstrate that the ever-changing linearization points of the estimated augmented state make the original four-dimensional unobservable subspace vanish, leading to the inconsistent estimation in practice. To relieve this problem, we employ the first-estimate Jacobian (FEJ) technique to maintain the correct observability properties of the augmented system. Furthermore, we introduce an observability-constrained updating method to compensate for the significant accumulated error after the long-term absence of map-based measurements. Finally, by evaluating the system through both simulation and real-world experiments, we confirm that the system has good consistency and low computational complexity.
Zhang, Z, Song, Y, Huang, S, Xiong, R & Wang, Y 2023, 'Toward Consistent and Efficient Map-Based Visual-Inertial Localization: Theory Framework and Filter Design', IEEE Transactions on Robotics, vol. 39, no. 4, pp. 2892-2911.
View/Download from: Publisher's site
View description>>
This article focuses on designing a consistent and efficient filter for visual-inertial localization given a prebuilt map. First, we propose a new Lie group with its algebra based on which a novel invariant extended Kalman filter (invariant EKF) is designed. We theoretically prove that, when we do not consider the uncertainty of map information, the proposed invariant EKF is able to naturally preserve the correct observability properties of the system. To consider the uncertainty of map information, we introduce a Schmidt filter. With the Schmidt filter, the uncertainty of map information can be taken into consideration to avoid overconfident estimation while the computation cost only increases linearly with the size of the map keyframes. In addition, we introduce an easily implemented observability-constrained technique because directly combining the invariant EKF with the Schmidt filter cannot maintain the correct observability properties of the system that considers the uncertainty of map information. Finally, we validate our proposed system's high consistency, accuracy, and efficiency via extensive simulations and real-world experiments.
Ang, K, Sankaran, S, Liu, D & Shreshta, P 1970, 'From Lab to Field: A Sociotechnical Systems View of the Organisational Cycle for Intelligent Robotics Technologies Ideation, Planning, Design, Development and Deployment', Proceedings of the International Symposium on Automation and Robotics in Construction (IAARC), 40th International Symposium on Automation and Robotics in Construction, International Association for Automation and Robotics in Construction (IAARC).
View/Download from: Publisher's site
Banuelos, DP, Falque, R, Patten, T & Alempijevic, A 1970, 'Skirting Line Estimation Using Sparse to Dense Deformation', 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 4256-4262.
View/Download from: Publisher's site
Bourahmoune, K, Ishac, K & Carmichael, M 1970, 'A remote training platform for learning physical skills using an AI powered virtual coach and a novel IoT sensing mat', SIGGRAPH Asia 2023 Posters, SA '23: SIGGRAPH Asia 2023, ACM, pp. 1-2.
View/Download from: Publisher's site
Chaisumdet, D, Tung Le, D, Khoa Nguyen, DD, Sutjipto, S, Rizvi, D & Paul, G 1970, 'Enhancing the Intuitiveness of Remote Mobile Industrial Robots with Haptic Devices', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, ARRA, Sydney.
View description>>
This paper presents the potential integration of Haptic Devices to complement the current Virtual Reality interfaces used for a remote mobile industrial robot. The integration of haptic feedback devices provides proper kinaesthetic awareness to operators, facilitating a feeling of total immersion, as if physically present. The ability to touch and feel, provided by these devices, allows for greater dexterity when operating these robotic systems. It can also solve issues when working within fragile and precision-required environments where current forms of remote teleoperation are lacking. A summary of the teleoperated manipulator, controlled by a haptic device, is outlined in this paper. This system is tested, and the findings from a human user study using the examined control method are presented. The human user study explores the effect of varying environments and modes of visual feedback on the participants’ performance. These results demonstrate the most practical form of visualising an unknown environment when leveraging haptic force feedback.
D'urso, G, Sadeghi, A, Yoo, C, Smith, SL & Fitch, R 1970, 'Distributed Multi-Robot Equitable Partitioning Algorithm for Allocation in Warehouse Picking Scenarios', 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), IEEE, pp. 1-8.
View/Download from: Publisher's site
Falque, R, Le Gentil, C & Sukkar, F 1970, 'Dynamic Object Detection in Range data using Spatiotemporal Normals', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Sydney.
View description>>
On the journey to enable robots to interact with the real world where humans, animals, and unpredictable elements are acting as independent agents; it is crucial for robots to have the capability to detect dynamic objects. In this paper, we argue that the detection of dynamic objects can be solved by computing the spatiotemporal normals of a point cloud. In our experiments, we demonstrate that this simple method can be used robustly for LiDAR and depth cameras with performances similar to the state of the art while offering a significantly simpler method.
Falque, R, Vidal-Calleja, T & Alempijevic, A 1970, 'Semantic Keypoint Extraction for Scanned Animals using Multi-Depth-Camera Systems', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 11794-11801.
View/Download from: Publisher's site
Fan, Y & Liu, D 1970, 'An equivalent two section method for calculating the workspace of multi-segment continuum robots', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Fu, L, Qiao, X, Huang, S, Mao, G, Lin, Z, Li, Y & Kong, H 1970, 'SLAM-Based Joint Calibration of Differential RSS Sensor Array and Source Localization', IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023- 49th Annual Conference of the IEEE Industrial Electronics Society, IEEE, pp. 1-8.
View/Download from: Publisher's site
Gentil, CL, Alzugaray, I & Vidal-Calleja, T 1970, 'Continuous-Time Gaussian Process Motion-Compensation for Event-Vision Pattern Tracking with Distance Fields', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, London, United Kingdom, pp. 804-812.
View/Download from: Publisher's site
View description>>
This work addresses the issue of motion compensation and pattern tracking in event camera data An event camera generates asynchronous streams of events triggered independently by each of the pixels upon changes in the observed intensity Providing great advantages in low light and rapid motion scenarios such unconventional data present significant research challenges as traditional vision algorithms are not directly applicable to this sensing modality The proposed method decomposes the tracking problem into a local SE 2 motion compensation step followed by a homography registration of small motion compensated event batches The first component relies on Gaussian Process GP theory to model the continuous occupancy field of the events in the image plane and embed the camera trajectory in the covariance kernel function In doing so estimating the trajectory is done similarly to GP hyperparameter learning by maximising the log marginal likelihood of the data The continuous occupancy fields are turned into distance fields and used as templates for homography based registration By benchmarking the proposed method against other state of the art techniques we show that our open source implementation performs high accuracy motion compensation and produces high quality tracks in real world scenarios
He, Y, Wang, J, Su, D, Nakadai, K, Wu, J, Huang, S, Li, Y & Kong, H 1970, 'Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization', 2023 IEEE/SICE International Symposium on System Integration (SII), 2023 IEEE/SICE International Symposium on System Integration (SII), IEEE, Atlanta, GA, USA, pp. 1-8.
View/Download from: Publisher's site
View description>>
Multiple microphone arrays have many applications in robot audition including sound source localization audio scene perception and analysis etc However accurate calibration of multiple microphone arrays remains a challenge because there are many unknown parameters to be identified including the Euler angles geometry asynchronous factors between the microphone arrays This paper is concerned with joint calibration of multiple microphone arrays and sound source localization using graph simultaneous localization and mapping SLAM By using a Fisher information matrix FIM approach we focus on the observability analysis of the graph SLAM framework for the above mentioned calibration problem We thoroughly investigate the identifiability of the unknown parameters including the Euler angles geometry asynchronous effects between the microphone arrays and the sound source locations We establish necessary sufficient conditions under which the FIM and the Jacobian matrix have full column rank which implies the identifiability of the unknown parameters These conditions are closely related to the variation in the motion of the sound source and the configuration of microphone arrays and have intuitive and physical interpretations We also discover several scenarios where the unknown parameters are not uniquely identifiable All theoretical findings are demonstrated using simulation data
Heon Lee, JJ, Anstee, S & Fitch, R 1970, 'Automated Slocum Mission Pipeline using Slocum Fleet Mission Control', OCEANS 2023 - Limerick, OCEANS 2023 - Limerick, IEEE, pp. 1-6.
View/Download from: Publisher's site
Hu, G, Ang, K, Khoa Le, DD & Liu, D 1970, 'Enhancing Sustainable Maintenance Operations Through Intelligent Climbing Robots', 2023 International Conference on Sustainable Technology and Engineering (i-COSTE), 2023 International Conference on Sustainable Technology and Engineering (i-COSTE), IEEE, Fiji, pp. 1-6.
View/Download from: Publisher's site
View description>>
This paper focuses on improving the performanceof advanced technologies to address the challenges of sustainable maintenance operations in inaccessible spaces, particularly for historical structures such as bridges and tunnels.Specifically, the study centres on enhancing the performance of Waumbot, an inchworm climbing robot, with a specific focus on rectifying mechanical sag-related issues. Accurate sag correction is crucial for precise robot positioning and movement, particularly in confined spaces like the Sydney Harbour Bridge’s steel arches.The paper introduces a sensor-fusion-based approachstrengthened by closed-loop control to effectively correct sagrelated errors. This correction significantly improves Waumbot’s precision in odometry models, enabling multi-step planning without requiring re-localization. The integration of inchworm robots, exemplified by the accurate sag correction of Waumbot, aligns with the mission of sustainable maintenance by preventing deterioration, minimizing environmental and societal impacts, and enhancing energy and resource efficiency compared to traditional labour-intensive methods. Furthermore, these robots excel in accessing hazardous spaces, thereby enhancing worker safety, well-being, and overall operational sustainability. Real-world experiments validate the approach’s accuracy and applicability, highlighting its potential for broader use in bridge maintenance and similar contexts.
Hull, R, Brian Lee, KM, Wakulicz, J, Yoo, C, McMahon, J, Clarke, B, Anstee, S, Kim, J & Fitch, R 1970, 'Decentralised Active Perception in Continuous Action Spaces for the Coordinated Escort Problem', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 7649-7655.
View/Download from: Publisher's site
Khoa Le, DD, Hu, G, Liu, D, Khonasty, R, Zhao, L, Huang, S, Shrestha, P & Belperio, R 1970, 'The QUENDA-BOT: Autonomous Robot for Screw-Fixing Installation in Timber Building Construction', 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), IEEE.
View/Download from: Publisher's site
Le Gentil, C & Vidal-Calleja, T 1970, 'A Gaussian Process approach for IMU to Pose Spatiotemporal Calibration', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Sydney.
View description>>
This paper presents a method to perform Inertial Measurement Unit (IMU)-to-pose extrinsic calibration. Considering the pose information collected with a motion-capture system or from the pose of a robotic arm’s end effector, the goal is to estimate the geometric transformation between the reference frame of an IMU and the one of a marker tracked by the motion-capture system (with the marker being rigidly mounted with the IMU) or the arm gripper. The method models the pose data in a continuous manner using Gaussian Processes (GP). With the use of linear operators, the GP models are utilised to predict the dynamics of the system in terms of velocities and accelerations without relying on any explicit motion model. Accordingly, the extrinsic parameters as well as the inter-sensor time-shift are estimated with a non-linear optimisation, minimising the difference between the IMU data and the predicted dynamics. Note that the method is not tailored to a specific motion-capture system or robotic arm and can be used with any exteroceptive sensor from which data can be preprocessed into poses through time. We demonstrate the soundness of our approach with real-world data throughout multiple experiments testing the robustness and repeatability of the results. We will release our open-source implementation1
Lee, JJH, Yoo, C, Anstee, S & Fitch, R 1970, 'Efficient Optimal Planning in non-FIFO Time-Dependent Flow Fields', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 7844-7850.
View/Download from: Publisher's site
Li, T, Song, Y, Walker, P, Pan, K, van de Graaf, VA, Zhao, L & Huang, S 1970, 'A Closed-Form Solution to Electromagnetic Sensor Based Intraoperative Limb Length Measurement in Total Hip Arthroplasty', Springer Nature Switzerland, pp. 365-375.
View/Download from: Publisher's site
Manitta, M, Jayasuriya, M & Liu, D 1970, 'A Vector Field-Based Method for Human Action Representation and Recognition During Human-Robot Collaboration.', CASE, 2023 IEEE 19th International Conference on Automation Science and Engineering (CASE), IEEE, pp. 1-7.
View/Download from: Publisher's site
McDonald, W, Le Gentil, C & Vidal-Calleja, T 1970, 'Global Localisation in Continuous Magnetic Vector Fields Using Gaussian Processes', ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, pp. 1-5.
View/Download from: Publisher's site
Mitchell, C, Best, G & Hollinger, G 1970, 'Sequential Stochastic Multi-Task Assignment for Multi-Robot Deployment Planning', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE.
View/Download from: Publisher's site
Nuñez, A, Kong, FH, González-Cantos, A & Fitch, R 1970, 'Risk-Aware Stochastic Ship Routing Using Conditional Value-at-Risk', 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 10543-10550.
View/Download from: Publisher's site
Nuñez, A, Kong, FH, Seiler, KM, Cantos, AG & Fitch, R 1970, 'Optimal ship routing via Spherical Visibility Graphs', OCEANS 2023 - Limerick, OCEANS 2023 - Limerick, IEEE, pp. 1-6.
View/Download from: Publisher's site
Pan, K, Zhang, S, Zhao, L, Huang, S, Zhang, Y, Wang, H & Luo, Q 1970, '3D Reconstruction of Tibia and Fibula using One General Model and Two X-ray Images', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 4732-4738.
View/Download from: Publisher's site
View description>>
The 3D reconstruction of patient specific bone models plays a crucial role in orthopaedic surgery for clinical evaluation, surgical planning and precise implant design or selection. This paper considers the problem of reconstructing a patient-specific 3D tibia and fibula model from only two 2D X-ray images and one 3D general model segmented from the lower leg CT scans of one randomly selected patient. Currently, the bone 3D reconstruction mainly relies on computed tomography (CT) and magnetic resonance imaging (MRI) scanning-based mode segmentation which result in high radiation exposure or expensive costs. While, the proposed algorithm can accurately and efficiently deform a 3D general model to achieve a patient-specific 3D model that matches the patient's tibia and fibula projections in two 2D X-rays. The algorithm undergoes a preliminary deformation, 2D contour registration, and opti-misation based on the deformation graph that represents the shape deformation of models. Evaluations using simulations, cadaver and in-vivo experiments demonstrate that the proposed algorithm can effectively reconstruct the patient's 3D tibia and fibula surface model with high accuracy.
Powell, K, Kodagoda, S & Vidal-Calleja, T 1970, 'Towards Context Aware Emotion Recognition in HRI for Social Robots', Australasian Conference on Robotics and Automation, ACRA.
View description>>
Social robots are becoming more prevalent in our daily environments but continue to struggle communicating in human-robot interactions, often misunderstanding people and thus making the interaction uncomfortable. Many attempts have been made to improve their understanding of people and their emotions but they still lack the socio-emotional intelligence humans often use in human-human interactions. A new approach previously explored in computer science is using context emotion recognition to interpret a scene for clues to a person’s emotional state. In this paper, we state that context emotion recognition will benefit the fields of human-robot interaction and social robotics. Further, we extend upon the EMOTIC model successfully adding a graphical representation of the emotion probabilities over time to the model output and with the addition of a facial feature extractor module that obtains an encouraging improvement over the original model. The algorithm was validated through data coming from two robotic platforms, namely PR2 and Pepper. The results show a promising way towards context aware emotion recognition in human-robot interactions with social robots, with 88% accuracy when comparing with 66% accuracy of the base model.
Ranasinghe, U, Abeyrathne, S, Samaranayake, L, Weerakoon, T, Harischandra, N & Dissanayake, G 1970, 'Enhanced Frequency Domain Analysis for Detecting Wild Elephants in Asia using Acoustics', 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), 2023 IEEE 17th International Conference on Industrial and Information Systems (ICIIS), IEEE, pp. 140-145.
View/Download from: Publisher's site
View description>>
Human-elephant conflict in Asia and Africa calls for an early warning system to reduce risks and harm for both elephants and humans. Acoustic based warning systems offer a promising solution due to their non-invasive and cost-effective nature. In this paper, we propose a novel approach for detecting wild elephants using acoustic signals, targeting the Asian elephant population in Sri Lanka. The proposed method introduces a unique data preprocessing technique, followed by feature extraction using a deep convolutional neural network followed by fully connected layers for classification. Spectro-grams are used as input data, and transfer learning is employed with YAMNet model layers. Additionally, we have developed a hardware system capable of capturing infra sound signals, although a detailed description of the system is beyond the scope of this paper as it is crucial for detecting elephant activity. The proposed method is evaluated on a large data set recorded under natural field conditions in Sri Lanka, and it demonstrates 97.77% accuracy in detecting elephants and robustness to noise sources. Proposed approach has the potential to develop into a non-invasive early warning system for elephant detection in the wild, contributing to the mitigation of human-elephant conflict and wildlife preservation.
Sharma, S, Brian Lee, KM, Brown, M & Best, G 1970, 'Instructing Robots with Natural Language via Bi-RNNs for Temporal Logic Translation', Australasian Conference on Robotics and Automation, ACRA.
View description>>
We consider the problem of planning trajectories that satisfy natural language instruction. We explore translating natural language commands to temporal logic formulae to resolve ambiguities for planning. Our main contribution is a new bi-directional recurrent neural network (Bi-RNN) architecture for this translation task. We experimentally show that the proposed Bi-RNN architecture achieves 1.6% better accuracy, 20% faster inference time, and 98% faster training time compared to leading models owing to bidirectional processing. The overall system, including a planning algorithm, exhibits useful diverse behaviours that satisfy given instructions.
Stephen, B, Kacprzak, M, Li, B, Guo, T, Wang, Y, Viswanathan, V, Kodagoda, S, Thiyagarajan, K & Vitanage, D 1970, 'Use of Machine Learning and Robotics To Target Renewals in Concrete Gravity Sewers', OzWater'23, OzWater'23, Sydney.
Sukkar, F, Moreno, VH, Vidal-Calleja, T & Deuse, J 1970, 'Guided Learning from Demonstration for Robust Transferability'.
View description>>
Learning from demonstration (LfD) has the potential to greatly increase theapplicability of robotic manipulators in modern industrial applications. Recentprogress in LfD methods have put more emphasis in learning robustness than inguiding the demonstration itself in order to improve robustness. The latter isparticularly important to consider when the target system reproducing themotion is structurally different to the demonstration system, as somedemonstrated motions may not be reproducible. In light of this, this paperintroduces a new guided learning from demonstration paradigm where aninteractive graphical user interface (GUI) guides the user duringdemonstration, preventing them from demonstrating non-reproducible motions. Thekey aspect of our approach is determining the space of reproducible motionsbased on a motion planning framework which finds regions in the task spacewhere trajectories are guaranteed to be of bounded length. We evaluate ourmethod on two different setups with a six-degree-of-freedom (DOF) UR5 as thetarget system. First our method is validated using a seven-DOF Sawyer as thedemonstration system. Then an extensive user study is carried out where severalparticipants are asked to demonstrate, with and without guidance, a mock weldtask using a hand held tool tracked by a VICON system. With guidance users wereable to always carry out the task successfully in comparison to only 44% of thetime without guidance.
Sukkar, F, Savery, R, Haque, N, Le Gentil, C, Falque, R & Vidal-Calleja, T 1970, 'A Robotic System For Imitating Human Percussionists', Australasian Conference on Robotics and Automation, ACRA, Australasian Conference on Robotics and Automation, Sydney.
View description>>
Robot musicians have the potential to revolutionise the way humans perceive and create music. Recent breakthroughs in this field have tended to focus more on the digital generation of music. Instead, we address how a musician’s physical embodiment can be translated to a robotic arm. Robots endowed with human-like musical capability open the possibility for wider applications such as human-robot bands, musical education and musical art. Prior work in this area tends to rely on pre-programmed actuation which is limited to simple motion and sound. In this paper, we propose a robotic system capable of imitating a human musician, with a focus on percussion instruments. Our system consists of a method for recording the human demonstration, a compact continuous representation of the demonstrated motion and a motion reproduction method which considers the dynamic constraints of the robot. We present results of our system and show that it is capable of closely reproducing the motion of the human percussionist.
Trung Le, NT, Bray, E, Brian Lee, KM & Best, G 1970, 'Adaptive Trajectory Library Planner for Fast Outdoor Robots', Australasian Conference on Robotics and Automation, ACRA.
View description>>
High-speed autonomous operation in outdoor environments requires fast computation of dynamically feasible, collision-free paths. To this end, we propose a new local path planning algorithm called Adaptive Trajectory Library. This approach relies on the selection of a suitable trajectory from a precomputed library to reduce online computation. A subset of trajectories that are dynamically feasible are considered, from which one is chosen to best move the robot towards a goal location while avoiding obstacles. In simulated experiments, the proposed algorithm significantly outperforms the Dynamic Window Approach [Fox et al., 1997] with 84.2 % less travel time and 39.5 % shorter path length. Hardware experiments in outdoor environments show that the proposed planner is able to reliably compute paths for a robot to follow to reach goals at high speeds in off-road terrain while avoiding obstacles.
Tung Le, D, Sutjipto, S, Khoa Nguyen, DD, Long Vu, T, Thong Vu, PD, Munasinghe, N & Paul, G 1970, 'HALO: a Rock Scaling Mobile Manipulator with Interactive Virtual Reality Live Digital Twin', Australasian Conference on Robotics and Automation, ACRA, Sydney.
View description>>
The High Access Localised Operations (HALO) system is a mobile manipulator that amalgamates advancements in digital twins, and virtual reality (VR) to enable safer rock scaling operations in the mining industry. Currently, the essential geotechnical activity of rock scaling is performed by certified workers suspended on the side of the rock wall, who perform the physically demanding task of removing loose rock debris. The HALO system enables a remote operator immersed in a VR environment that visualises the digital twin of the robot and its sensor data in real-time to interact with the robot intuitively. This eliminates the need for people to be exposed to the hazards associated with performing manual rock scaling, while enabling them to apply their existing expertise when operating the robot in VR. In this work, we present a summary of the HALO hardware and its interaction architecture, encompassing a framework for real-time remote scene reconstruction and natural interaction. Findings from preliminary site trials are also be presented to provide preliminary evaluation of the system.
Usayiwevu, M, Sukkar, F & Vidal-Calleja, T 1970, 'Probabilistic Plane Extraction and Modeling for Active Visual-Inertial Mapping', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, London, United Kingdom, pp. 10601-10607.
View/Download from: Publisher's site
View description>>
This paper presents an active visual inertial mapping framework with points and planes The key aspect of the proposed framework is a novel probabilistic plane extraction with its associated model for estimation The approach allows the extraction of plane parameters and their uncertainties based on a modified version of PlaneRCNN 1 The extracted probabilistic plane features are fused with point features in order to increase the robustness of the estimation system in texture less environments where algorithms based on points alone would struggle A visual inertial framework based on Iterative Extended Kalman filter IEKF is used to demonstrate the approach The IEKF equations are customized through a measurement extrapolation method which enables the estimation to handle the delay introduced by the neural network inference time systematically The system is encompassed within an active mapping framework based on Informative Path Planning to find the most informative path for minimizing map uncertainty in visual inertial systems The results from the conducted experiments with a stereo IMU system mounted on a robotic arm show that introducing planar features to the map in order to complement the point features in the state estimation improves robustness in texture less environments
Wakulicz, J, Brian Lee, KM, Vidal-Calleja, T & Fitch, R 1970, 'Topological Trajectory Prediction with Homotopy Classes', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, pp. 6930-6936.
View/Download from: Publisher's site
View description>>
Trajectory prediction in a cluttered environment is key to many important robotics tasks such as autonomous navigation. However, there are an infinite number of possible trajectories to consider. To simplify the space of trajectories under consideration, we utilise homotopy classes to partition the space into countably many mathematically equivalent classes. All members within a class demonstrate identical high-level motion with respect to the environment, i.e., travelling above or below an obstacle. This allows high-level prediction of a trajectory in terms of a sparse label identifying its homotopy class. We therefore present a light-weight learning framework based on variable-order Markov processes to learn and predict homotopy classes and thus high-level agent motion. By informing a Gaussian mixture model (GMM) with our homotopy class predictions, we see great improvements in low-level trajectory prediction compared to a naive GMM on a real dataset.
Wang, Q, Liu, D, Carmichael, MG & Lin, C-T 1970, 'Robot Trust and Self-Confidence Based Role Arbitration Method for Physical Human-Robot Collaboration', 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023 IEEE International Conference on Robotics and Automation (ICRA), IEEE, ENGLAND, London, pp. 9896-9902.
View/Download from: Publisher's site
View description>>
Role arbitration in human-robot collaboration (HRC) is a dynamically changing process that is affected by many factors such as physical workload, environmental changes and trust. In order to address this dynamic process, a trust-based role arbitration method is studied in this research. A computational model of robot trust and self-confidence (TSC) in physical human-robot collaboration (pHRC) is proposed. The TSC model is defined as a function of objective robot and human co-worker performance. A role arbitration method is then proposed based on the TSC model presented. The human-in-the-loop experiments with a collaborative robot are conducted to verify the TSC-based role arbitration method. The results show that the proposed method could achieve superior human-robot combined performance, reduce human co-workers' workload, and improve subjective preference.
Wu, L, Gentil, CL & Vidal-Calleja, T 1970, 'Pseudo Inputs Optimisation for Efficient Gaussian Process Distance Fields', 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 7249-7255.
View/Download from: Publisher's site
Xing, V, Zhao, L & Best, G 1970, 'CoordLight-YOLOv5: A Lightweight Object Detection Algorithm for Autonomous Motorsport', Australasian Conference on Robotics and Automation, ACRA.
View description>>
Autonomous motorsport is a rapidly developing field, among which autonomous racing based on cone tracks is a challenging testing and racing environment. Object detection is one of its indispensable technologies. We propose an improved lightweight model, CoordLightYOLOv5, motivated by autonomous racing projects that require a high frame rate and detection accuracy by onboard embedded computing. In the proposed method, we deleted large object detection feature maps from the backbone and neck network in order to reduce model training and detection time and reduce model computational costs. Furthermore, we introduce CoordConv layer in the neck network to enhance object localisation ability in Cartesian coordinates without using spatial transformations. Our experiments with five autonomous racing datasets show that compared to YOLOv5s, the average number of model parameters is reduced by 91.5%, the average floating-point operation is reduced by 78%, the detection speed has been increased from the original 94 frames per second to 117 frames per second, and the average detection accuracy decreased by only 2.5%.
Zhang, Y, Cheng, C, Falque, R, Zhao, L, Huang, S & Chen, Y 1970, '3D Intra-articular Dense Reconstruction from Arthroscopic Images', 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), 2023 IEEE International Conference on Robotics and Biomimetics (ROBIO), IEEE, pp. 1-7.
View/Download from: Publisher's site
Granatosky, M, Young, M, Dickinson, E, Tanis, D, Ratkiewicz, A, Hanna, C, Currier, A, Kong, F & Webster, C 2023, 'The Onset of Beak and Tail Use are Triggered by Changes in Substrate Orientation in Parrots', OXFORD UNIV PRESS INC, pp. S171-S171.
Guivant, J, Kim, J, Narula, K, Li, X & Khan, S 2023, 'Compressed Gaussian Estimation under Low Precision Numerical Representation', MDPI AG.
View/Download from: Publisher's site
Hull, R, Lee, KMB, Wakulicz, J, Yoo, C, McMahon, J, Clarke, B, Anstee, S, Kim, J & Fitch, R 2023, 'Decentralised Active Perception in Continuous Action Spaces for the Coordinated Escort Problem'.
Kim, S, Corah, M, Keller, J, Best, G & Scherer, S 2023, 'Multi-Robot Multi-Room Exploration with Geometric Cue Extraction and Circular Decomposition'.
Singh, K, Saikia, M, Thiyagarajan, K, Thalakotuna, D, Esselle, K & Kodagoda, S 2023, 'Multi-Functional Reconfigurable Intelligent Surfaces For Enhanced Sensing and Communication', MDPI AG.
View/Download from: Publisher's site
Wakulicz, J, Lee, KMB, Vidal-Calleja, T & Fitch, R 2023, 'Topological Trajectory Prediction with Homotopy Classes'.
Xu, M, Chen, S, Huang, S, Zhao, L & Hao, Q 2023, 'Invariant EKF based 3D Active SLAM with Exploration Task', Springer Science and Business Media LLC.
View/Download from: Publisher's site
Xu, Y, Zheng, R, Zhang, S, Liu, M & Huang, S 2023, 'CARE: Confidence-rich Autonomous Robot Exploration using Bayesian Kernel Inference and Optimization'.
