Accurate modelling of object deformations is crucial for a wide range of robotic manipulation tasks, where interacting with soft or deformable objects is essential. Current methods struggle to generalise to unseen forces or adapt to new objects, limiting their utility in real-world applications. We propose Shape-Space Deformer, a unified representation for encoding a diverse range of object deformations using template augmentation to achieve robust, fine-grained reconstructions that are resilient to outliers and unwanted artefacts. Our method improves generalization to unseen forces and can rapidly adapt to novel objects, significantly outperforming existing approaches. We perform extensive experiments to test a range of force generalisation settings and evaluate our method's ability to reconstruct unseen deformations. Our results demonstrate significant improvements in reconstruction accuracy and robustness. Our approach is suitable for real-time performance, making it ready for downstream manipulation applications.

Lifelong imitation learning for manipulation tasks poses significant challenges due to distribution shifts that occur in incremental learning steps. Existing methods often rely on unsupervised skill discovery to construct an ever-growing skill library or distillation from multiple policies, which can lead to scalability issues as diverse manipulation tasks are continually introduced and may fail to ensure a consistent latent space throughout the learning process, leading to catastrophic forgetting of previously learned skills. In this paper, we introduce M2Distill, a multimodal distillation-based method for lifelong imitation learning focusing on preserving consistent latent space across vision, language, and action distributions throughout the learning process. By regulating the shifts in latent representations across different modalities from previous to current steps, and reducing discrepancies in Gaussian Mixture Model (GMM) policies between consecutive learning steps, we ensure that the learned policy retains its ability to perform previously learned tasks while seamlessly integrating new skills. Evaluations on the LIBERO lifelong imitation learning benchmark suites, including LIBERO-OBJECT, LIBERO-GOAL, and LIBERO-SPATIAL, demonstrate that our method consistently outperforms prior state-of-the-art methods across all evaluated metrics.

Human operators in human-robot teams are commonly perceived to be critical for mission success. To explore the direct and perceived impact of operator input on task success and team performance, 16 real-world missions (10 h) were conducted based on the DARPA Subterranean Challenge. Missions involved deploying a heterogeneous team of robots to locate and identify artefacts such as climbing rope, drills and a mannequin representing a human survivor. Two conditions were evaluated: human operators that could control the robot team with state-of-the-art autonomy (Human-Robot Team) compared to autonomous missions without human operator input (Robot-Autonomy). Human interventions included creating waypoints to prioritise high-yield areas, and to navigate through error-prone spaces. Human-Robot Teams were often in directed autonomy mode (70% of mission time), found more items ( \(+\) 10.52%), traversed more distance ( \(+\) 12.71%), covered more unique ground ( \(+\) 10.56%), and longer time between safety-related events (34%). In routine conditions, both condition scores were comparable for artefacts, distance and coverage. Human-Robot Teams were faster at finding the first artefact but slower to respond to information from the robot team. Overall, operators contribute to mission-based outcomes, help to overcome environmental situations that can impede progress, and can assist robots to recover faster from difficult events.

Robotic vision, otherwise known as computer vision for robots, is a critical process for robots to collect and interpret detailed information related to human actions, goals, and preferences, enabling robots to provide more useful services to people. This survey and systematic review presents a comprehensive analysis on robotic vision in human-robot interaction and collaboration (HRI/C) over the past 10 years. From a detailed search of 3,850 articles, systematic extraction and evaluation was used to identify and explore 310 papers in depth. These papers described robots with some level of autonomy using robotic vision for locomotion, manipulation, and/or visual communication to collaborate or interact with people. This article provides an in-depth analysis of current trends, common domains, methods and procedures, technical processes, datasets and models, experimental testing, sample populations, performance metrics, and future challenges. Robotic vision was often used in action and gesture recognition, robot movement in human spaces, object handover and collaborative actions, social communication, and learning from demonstration. Few high-impact and novel techniques from the computer vision field had been translated into HRI/C. Overall, notable advancements have been made on how to develop and deploy robots to assist people.

Leveraging both the autonomy of robots and the expert knowledge of humans can enable a multi-robot system to complete missions in challenging environments with a high degree of adaptivity and robustness. This paper proposes a multi-modal task-based graphical user interface for controlling a heterogeneous multi-robot team. The core of the interface is an integrated multi-robot task allocation system to allow the user to encode his/her intents to guide the heterogeneous multi-robot team. The design of the interface aims to provide the human operator continuous situational awareness and effective control for rapid decision-making in time-critical missions. Team CSIRO Data61 came in second place utilizing this interface for the DARPA Subterranean (SubT) Challenge. The ideas used for this user interface can apply to other multi-robot applications.

The DARPA subterranean challenge requires teams of robots to traverse difficult and diverse underground environments. Traversing small gaps is one of the challenging scenarios that robots encounter. Imperfect sensor information makes it difficult for classical navigation methods, where behaviours require significant manual fine tuning. In this paper we present a deep reinforcement learning method for autonomously navigating through small gaps, where contact between the robot and the gap may be required. We first learn a gap behaviour policy to get through small gaps (only centimeters wider than the robot). We then learn a goal-conditioned behaviour selection policy that determines when to activate the gap behaviour policy. We train our policies in simulation and demonstrate their effectiveness with a large tracked robot in simulation and on the real platform. In simulation experiments, our approach achieves 93% success rate when the gap behaviour is activated manually by an operator, and 63% with autonomous activation using the behaviour selection policy. In real robot experiments, our approach achieves a success rate of 73% with manual activation, and 40% with autonomous behaviour selection. While we show the feasibility of our approach in simulation, the difference in performance between simulated and real world scenarios highlight the difficulty of direct sim-to-real transfer for deep reinforcement learning policies. In both the simulated and real world environments alternative methods were unable to traverse the gap.

Legged robots often use separate control policies that are highly engineered for traversing difficult terrain such as stairs, gaps, and steps, where switching between policies is only possible when the robot is in a region that is common to adjacent controllers. Deep Reinforcement Learning (DRL) is a promising alternative to hand-crafted control design, though typically requires the full set of test conditions to be known before training. DRL policies can result in complex (often unrealistic) behaviours that have few or no overlapping regions between adjacent policies, making it difficult to switch behaviours. In this work we develop multiple DRL policies with Curriculum Learning (CL), each that can traverse a single respective terrain condition, while ensuring an overlap between policies. We then train a network for each destination policy that estimates the likelihood of successfully switching from any other policy. We evaluate our switching method on a previously unseen combination of terrain artifacts and show that it performs better than heuristic methods. While our method is trained on individual terrain types, it performs comparably to a Deep Q Network trained on the full set of terrain conditions. This approach allows the development of separate policies in constrained conditions with embedded prior knowledge about each behaviour, that is scalable to any number of behaviours, and prepares DRL methods for applications in the real world.