News & Research

arXiv:2603.01229v3 Announce Type: replace Abstract: Robotic manipulation policies have made rapid progress in recent years, yet most existing approaches give limited consideration to memory capabilities. Consequently, they struggle to solve tasks that require reasoning over historical observations and maintaining task-relevant information over time, which are common requirements in real-world manipulation scenarios. Although several memory-aware policies have been proposed, systematic evaluation of memory-dependent manipulation remains underexplored, and the relationship between architectural design choices and memory performance is still not well understood. To address this gap, we introduce RMBench, a simulation benchmark comprising 9 manipulation tasks that span multiple levels of memory complexity, enabling systematic evaluation of policy memory capabilities. We further propose Mem-0, a modular manipulation policy with explicit memory components designed to support controlled ablat

arXiv:2603.01110v2 Announce Type: replace Abstract: Robotic laboratory automation has traditionally relied on carefully engineered motion pipelines and task-specific hardware interfaces, resulting in high design cost and limited flexibility. While recent imitation learning techniques can generate general robot behaviors, their large model sizes often require high-performance computational resources, limiting applicability in practical laboratory environments. In this study, we propose a compact imitation learning framework for laboratory automation using small foundation models. The proposed method, TVF-DiT, aligns a self-supervised vision foundation model with a vision-language model through a compact adapter, and integrates them with a Diffusion Transformer-based action expert. The entire model consists of fewer than 500M parameters, enabling inference on low-VRAM GPUs. Experiments on three real-world laboratory tasks - test tube cleaning, test tube arrangement, and powder transfer -

arXiv:2602.04635v2 Announce Type: replace Abstract: Robots are finding wider adoption in human environments, increasing the need for natural human-robot interaction. However, understanding a natural language command requires the robot to infer the intended task and how to decompose it into executable actions, and to ground those actions in the robot's knowledge of the environment, including relevant objects, agents, and locations. This challenge can be addressed by combining the capabilities of large language models (LLMs) to understand natural language with 3D scene graphs (3DSGs) for grounding inferred actions in a semantic representation of the environment. However, many 3DSGs lack explicit spatial relations between objects, even though humans often rely on these relations to describe an environment. This paper investigates whether incorporating open- or closed-vocabulary spatial relations into 3DSGs can improve the ability of LLMs to interpret natural language commands. To address

arXiv:2601.13732v2 Announce Type: replace Abstract: The fact that robots are getting deployed more often in dynamic environments, together with the increasing complexity of their software systems, raises the need for self-adaptive approaches. In these environments robotic software systems increasingly encounter (1) failures whose symptoms are easy to observe but root causes might be ambiguous or (2) multiple failures appearing concurrently. We present SUNSET, a ROS2-based exemplar that enables rigorous, repeatable evaluation of architecture-based self-adaptation in such conditions. It implements a sensor fusion semantic-segmentation pipeline driven by a trained Machine Learning (ML) model whose input preprocessing can be perturbed to induce realistic performance degradations. The exemplar exposes five observable failures, each of which can be caused by different faults and supports concurrent failures spanning self-healing and self-optimisation. SUNSET includes the segmentation pipelin

arXiv:2511.11970v2 Announce Type: replace Abstract: Robotic exploration in extreme environments, such as caves, oceans, and extraplanetary surfaces, poses significant challenges, specifically locomotion across diverse terrains. Conventional wheeled or legged robots often struggle in such contexts due to variability in traction. This paper presents ARCSnake V2, an adaptation of ARCSnake V1 with additional amphibious capabilities for aquatic environments. ARCSnake V2 combines the high mobility of hyper-redundant snake robots with the terrain versatility of Archimedean screw propulsion. Key contributions include a water-sealed mechanical design with serially linked screw and joint actuation, and an integrated buoyancy control system. Extensive experiments validate its underwater capabilities for diving and surfacing, as well as force-regulated actuation. These capabilities position ARCSnake V2 as a versatile platform for exploration, search-and-rescue, and environmental monitoring in mult

arXiv:2510.14584v3 Announce Type: replace Abstract: Reliable manipulation of previously unseen objects remains a fundamental challenge for autonomous robotic systems operating in unstructured environments. In particular, robust pick-and-place planning directly from noisy and only partial real-world observations, where object surfaces are inherently incomplete due to occlusions (e.g., bottom faces on a tabletop), is difficult. As a result, many existing methods rely on strong object priors (e.g., CAD models) or to assume placement on continuous, flat support surfaces such as planar tabletops, without explicitly accounting for edge proximity or inclined supports. In this work, we introduce a robust probabilistic placeability metric that evaluates 6D object placement poses from partial observations by jointly scoring object stability and graspability from raw point cloud geometry. Using this metric, we generate diverse multi-orientation placement candidates and condition grasp scoring on

arXiv:2510.02941v2 Announce Type: replace Abstract: Social, also called human-aware, navigation is a key challenge for integrating mobile robots into human environments. The evaluation of such systems is complex, as factors such as comfort, safety, and legibility must be considered. Human-centered assessments, typically conducted through surveys, provide reliable insights but are costly, resource-intensive, and difficult to reproduce or compare across systems. Alternatively, numerical social navigation metrics are easy to compute and facilitate comparisons, yet the community lacks consensus on a standard set of metrics. This work explores the relationship between numerical metrics and human-centered evaluations to identify potential correlations. If specific quantitative measures align with human perceptions, they could serve as preliminary benchmarking tools, providing a human-aligned assessment when large-scale surveys are not feasible. Our results indicate that while current metrics

arXiv:2506.04680v3 Announce Type: replace Abstract: Evaluating lower limb exoskeletons directly with human subjects can expose users to risk when actuator faults, joint misalignment, or unsuitable assistance occur. Therefore, captured human motion must first be converted into commands that are executable by the robot hardware and repeatable across trials. This paper presents a three-stage offline command generation framework for reproducing lower limb motion and torque on a suspended bipedal robot platform used as a robotic bench system for exoskeleton evaluation. First, State-Dependent Riccati Equation control is applied to the robot dynamic model to obtain a reference torque trajectory associated with measured lower limb motion. Second, parameterized optimization converts this reference into trapezoidal joint velocity commands subject to motor speed and acceleration limits. Third, a proportional-integral-derivative linear quadratic regulator (PID-LQR) compensation refines the command

arXiv:2505.04999v2 Announce Type: replace Abstract: Learning robot control policies from demonstrations typically requires action-labeled expert data, which is expensive to collect through teleoperation. We study a more practical setting in which expert demonstrations are available only as observation sequences without action labels, and only task-agnostic play data contains actions. We introduce continuous latent action models (CLAM), a framework that infers continuous latent actions between consecutive observations using self-supervised dynamics prediction. To ground these latent actions into executable motor commands, CLAM jointly trains an action decoder using a small amount of task-agnostic play data. We show that continuous latent actions combined with this joint training are essential for high-dimensional continuous control. Across DMControl locomotion, MetaWorld manipulation, and real-world WidowX robot tasks, CLAM improves average task success rates by 2-3x over prior latent-a

arXiv:2503.12287v2 Announce Type: replace Abstract: High-precision, tight-clearance assembly demonstrations are indispensable for training tactile-aware robotic foundation models, yet their acquisition is heavily bottlenecked by the high operational barriers of conventional teleoperation. To bridge this gap, we propose SharedAssembly, a novel shared-autonomy bilateral teleoperation framework that embeds assembly-specific intelligence across both leader and follower sides to facilitate scalable data collection. Rigorous real-world user studies on challenging sub-millimeter tasks show that SharedAssembly achieves an exceptional 97% assembly success rate while significantly boosting completion efficiency. Notably, these performance gains become even more pronounced as the assembly clearance shrinks. Furthermore, our framework effectively eliminates the expertise gap, enabling novice operators to match or even outperform expert operators using conventional systems. By minimizing the skill

arXiv:2607.28293v1 Announce Type: cross Abstract: While depth sensors have the potential to complement RGB data for affordance segmentation in wearable robots, their usage seems to remain underexplored. The paper proposes two approaches: a reformulated version of hardware-aware neural architecture search, endowed with a newly designed search space to integrate depth (D) information into small-sized deep networks, and a dedicated fine-tuning approach, including a preprocessing layer to merge depth information with RGB data and make it compatible with conventional architectures. In both cases, those methods aim to generate solutions that benefit from modern (portable) hardware accelerators and overcome existing tiny-like approaches, which often fail to tackle critical scenarios due to the severe constraints set by the supporting hardware. Extensive experiments on a pair of real-world datasets demonstrate the effectiveness of the proposed method as compared with existing solutions. The ap

arXiv:2607.27599v1 Announce Type: cross Abstract: Building generalizable agents for diverse applications remains a fundamental challenge. While imitation learning-based policies succeed in specific training environments, they often fail to generalize to novel scenes and tasks. In this work, we propose World Action Planner, a robot planning system that leverages the reasoning capabilities of Vision-Language Models (VLMs) and the physical grounding of a multi-task pose-image conditioned world model. Our system enables an agent to propose initial action plans and iteratively refine them via optimization and search, reasoning over imagined world model rollouts. We demonstrate that our approach achieves superior performance across compositional tasks, new layouts, and zero-shot generalization scenarios, significantly outperforming state-of-the-art end-to-end policy models such as VLAs and WAMs. Project website at worldactionplanner.github.io

arXiv:2607.28623v1 Announce Type: new Abstract: We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance represents clearance to every body link, and an adversarial motion prior regularizes the resulting evasive reflexes. We evaluate on a controlled any-link contact benchmark with seeded throws in two regimes: single throws and a deployment loop in which the robot walks back to its station and recovers between throws. On this benchmark, the policy comes within a few points of a privileged state oracle: a fixed onboard camera alone is adequate for evasion. We find that usable barrier structure depends on perceptual observability: Joint-CBF gives the best performance with accurate ball states, degrades under fixed-camera observations when used only as

arXiv:2607.28596v1 Announce Type: new Abstract: In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories might be equally valid, making it important to preserve diverse action modes. After contact, geometric constraints and force limits narrow the solution space, while successful execution demands rapid responses to force feedback. However, standard diffusion policies use a fixed inference frequency and sampling steps throughout the episode, forcing a fundamental compromise: low-frequency, multi-step sampling better preserves pre-contact multimodality but responds slowly to force feedback, whereas high-frequency sampling improves reactivity but tends to collapse distinct pre-contact modes. To resolve this tradeoff, we present FA-RDP, a frequency-adaptive reactive diffusion policy. A shared multi-frequency visual-force Transformer predicts action chunks at both low and high frequencies, while a

arXiv:2607.28560v2 Announce Type: replace Abstract: Pretraining navigation diffusion policies rely on large-scale expert demonstrations. These data are typically generated by a fully-informed oracle planner suited to a single nominal robot. This limits the policy's generalization to diverse embodiments and challenging scenarios (e.g., escaping dead ends or detouring long obstacles) that demand diverse local reactive behaviors with only onboard local observations. Post-training the policy with reinforcement learning (RL) offers a principled remedy. However, previous RL for diffusion approaches lead to only marginal improvements. This is because the intractable likelihood of diffusion policies renders policy gradients unstable in addition to inefficient policy exploration. To address these challenges, we propose a data-efficient diffusion RL post-training framework - GQRM (Group Q-score Reweighted Matching). Our framework introduces two complementary designs: (i) a self-bootstrapped expl