News & Research

arXiv:2512.17992v2 Announce Type: replace Abstract: Long-horizon robotic tasks are hard due to continuous state-action spaces and sparse feedback. Symbolic world models help by decomposing tasks into discrete predicates that capture object properties and relations. Existing methods learn predicates either top-down, by prompting foundation models without data grounding, or bottom-up, from demonstrations without high-level priors. We introduce UniPred, a bilevel learning framework that unifies both. UniPred uses large language models (LLMs) to propose predicate effect distributions that supervise neural predicate learning from low-level data, while learned feedback iteratively refines the LLM hypotheses. Leveraging strong visual foundation model features, UniPred learns robust predicate classifiers in cluttered scenes. We further propose a predicate evaluation method that supports symbolic models beyond STRIPS assumptions. Across five simulated and two real-robot domains, UniPred achieve

arXiv:2512.11609v3 Announce Type: replace Abstract: In embodied intelligence, the embodiment gap between robotic and human hands brings significant challenges for learning from human demonstrations. Although some studies have attempted to bridge this gap using reinforcement learning, they remain confined to merely reproducing human manipulation, resulting in limited task performance. Moreover, current methods struggle to support diverse robotic hand configurations. In this paper, we propose UniBYD, a unified framework that uses a dynamic reinforcement learning algorithm to discover manipulation policies aligned with the robot's physical characteristics. To enable consistent modeling across diverse robotic hand morphologies, UniBYD incorporates a unified morphological representation (UMR). Building on UMR, we design a dynamic PPO with an annealed reward schedule, enabling reinforcement learning to transition from offline-informed imitation of human demonstrations to online-adaptive expl

arXiv:2511.09484v3 Announce Type: replace Abstract: Learning agile robotic policies requires large-scale demonstrations, but translating abundant human motion data to robots is bottlenecked by the embodiment gap and missing dynamic information. To bridge this gap, we propose Scalable Physics-Informed DExterous Retargeting (SPIDER), a physics-based retargeting framework to transform and augment kinematic-only human demonstrations into dynamically feasible robot trajectories at scale. Our key insight is that human demonstrations should provide global task structure and objective, while a sampling-based solver can be used to find the feasible solution given the physics constraints. As a general framework, SPIDER is an efficient physics-based retargeting method that can be applied to both humanoid whole-body loco-manipulation and dexterous manipulation across 9 humanoid/dexterous hand embodiments, 6 datasets and 3 simulators. By bypassing the need for policy optimization, it achieves state

arXiv:2510.05382v2 Announce Type: replace Abstract: Tactile sensing is critical for enhancing manipulation precision and versatility, but its adoption in robotic hands remains limited due to high sensor costs, manufacturing and integration challenges, and difficulties in extracting expressive and reliable contact information. In this work, we present a low-cost, easy-to-make, adaptable, and compact fingertip design for robotic hands that integrates multi-modal tactile sensors. We use strain gauge sensors to capture static forces and a contact microphone sensor to measure high-frequency vibrations during contact. These tactile sensors are integrated into a compact design with a minimal sensor footprint. From sensor characterization, we show that strain gauge sensors provide repeatable 3D force measurements in the 0-5~N range and the contact microphone sensor can captures distinct vibrotactile signatures associated with different material types. We evaluate our design with three types of

arXiv:2509.22828v2 Announce Type: replace Abstract: Rearranging objects in cluttered tabletop environments remains a long-standing challenge in robotics. Classical planners often generate inefficient, high-cost plans by moving objects individually and using fixed buffers, temporary spaces such as unoccupied tabletop regions or static stacks, to resolve conflicts. When only free tabletop locations are used as buffers, planning in dense scenes becomes difficult, since placing an object can prevent others from reaching their goals and complicate subsequent planning. Stacking provides additional buffer capacity, but conventional stacking is static: the base object cannot be relocated while holding another, which limits efficiency. To address these limitations, a novel planning primitive called the Dynamic Buffer is introduced. Inspired by human grouping strategies, it enables robots to form temporary, movable stacks that can be transported as a unit. Dynamic buffers improve feasibility and

arXiv:2509.15880v2 Announce Type: replace Abstract: Geometry-grounded vision models, such as VGGT, have emerged as robust visual encoders, providing essential geometric priors for robotic manipulation. However, the high computational cost of these models often leads to slow inference, limiting their practical applications in real-world robotics. This paper introduces eVGGT, a lightweight geometry-aware vision encoder distilled from the high-performing VGGT. Our findings demonstrate two primary advantages: i) integrating eVGGT into imitation learning frameworks (including ACT and Diffusion Policy) yields up to a 6.3% improvement in success rate over standard 2D encoders across bimanual and single-arm tasks in both simulation and real-world settings with variable viewpoints; ii) eVGGT achieves a nearly 5 times speedup and a 63% reduction in memory usage compared to state-of-the-art geometry-aware encoders while maintaining comparable task performance. These results suggest that eVGGT sub

arXiv:2509.14636v3 Announce Type: replace Abstract: Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the scale drift problem of monocular visual odometry (MVO) by providing a metric-scaled planar workspace, enabling the simplification of 6-DoF ego-motion to a more robust 3-DoF model. However, existing BEV-based methods suffer from two key limitations: sparse supervision signals from pose-only training, and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework in the BEV-ODOM line that addresses both limitations without supervision modalities beyond the pose ground truth. Our approach introduces (1) pose-derived dense rigid BEV flow supervision, which reparameterizes the 3-DoF pose ground truth into a pixel-level training signal, and (2) Perspective View (PV)-BEV fusion, which computes correlation volumes before projection to retain additional motion c

arXiv:2509.14025v2 Announce Type: replace Abstract: Modular Aerial Robot Systems (MARS) consist of multiple drone modules that are physically bound together to form a single structure for flight. Exploiting structural redundancy, MARS can be reconfigured into different formations to mitigate unit or rotor failures and maintain stable flight. Prior work on MARS self-reconfiguration has solely focused on maximizing controllability margins to tolerate a single rotor or unit fault for rectangular-shaped MARS. We propose TransforMARS, a general fault-tolerant reconfiguration framework that transforms arbitrarily shaped MARS under multiple rotor and unit faults while ensuring continuous in-air stability. Specifically, we develop algorithms to first identify and construct minimum controllable assemblies containing faulty units. We then plan feasible disassembly-assembly sequences to transport MARS units or subassemblies to form target configuration. Our approach enables more flexible and prac

arXiv:2508.02873v3 Announce Type: replace Abstract: We present the design and implementation of HASTA (Hopper with Adjustable Stiffness for Terrain Adaptation), a vertical hopping robot with real-time tunable leg stiffness, aimed at optimizing energy efficiency across various ground profiles (a pair of ground stiffness and damping conditions). By adjusting leg stiffness, we aim to maximize apex hopping height, a key metric for energy-efficient vertical hopping. We hypothesize that softer legs perform better on soft, damped ground by minimizing penetration and energy loss, while stiffer legs excel on hard, less damped ground by reducing limb deformation and energy dissipation. Through experimental tests and simulations, we find the best leg stiffness within our selection for each combination of ground stiffness and damping, enabling the robot to achieve maximum steady-state hopping height with a constant energy input. These results support our hypothesis that tunable stiffness improves

arXiv:2503.19225v4 Announce Type: replace Abstract: We introduce CoinFT, a capacitive 6-axis force/torque (F/T) sensor that is compact, light, low-cost, and robust with an average root-mean-squared error of 0.16 N for force and 1.08 mN m for moment when the input ranges from 0-14 N and 0-5 N in normal and shear directions, respectively. CoinFT is a stack of two rigid PCBs with comb-shaped electrodes connected by an array of silicone rubber pillars. A microcontroller interrogates the electrodes in different subsets in order to enhance sensitivity for measuring 6-axis F/T. The combination of features of CoinFT enables various contact-rich robot interactions across different embodiment domains including drones, robot end-effectors, and wearable haptic devices. We demonstrate the utility of CoinFT through two representative applications: a multi-axial contact-probing experiment in which a CoinFT mounted beneath a hemispherical fingertip measures 6-axis force and torque representative of ma

arXiv:2412.16633v4 Announce Type: replace Abstract: LLM-based robots use Large Language Models (LLMs) as planners to translate natural language instructions into policies such as grasp(), move_to(), and open_gripper(). Jailbreak attacks on these robots extend the threat from generating malicious content to executing harmful behaviors. However, we find that existing jailbreak attempts against LLM-based robots that produce malicious-looking policies (intent jailbreaks) often fail to induce harmful physical actions by robots (behavior jailbreaks), due to robot-specific constraints, such as logical errors and hallucinated control APIs. In this paper, we demystify the intent-behavior gap and investigate its root causes to inform effective defenses. Our measurement study finds that current LLM jailbreak methods overlook robot-specific syntax constraints (e.g., executable control APIs) and physical feasibility (e.g., ordering of policies and hardware/kinematic constraints). To bridge the gap,

arXiv:2408.14518v3 Announce Type: replace Abstract: Simultaneous localization and mapping (SLAM) allows a mobile robot or autonomous vehicle to build a map of an unknown environment while estimating its own pose within that map. Reinforcement learning (RL), in which an agent learns a decision policy from interaction and reward, has been applied to decide how such systems move, explore, and recognize places they have visited before. This survey reviews the applications of RL in SLAM. We first distinguish passive SLAM, in which the robot's motion is not chosen by the SLAM system, from active SLAM, in which it is, and summarize the sensors that provide the input to SLAM. We then introduce the RL methods used in this literature, from value-based and policy-based methods to actor-critic and deep RL. Next, we classify RL applications in SLAM into three categories: path planning, including environment exploration and obstacle avoidance; loop closure detection; and active SLAM. Thirteen repres

arXiv:2308.09456v2 Announce Type: replace Abstract: Overtaking on two-lane roads is a safety-critical decision-making problem for autonomous vehicles, since oncoming traffic may force the ego vehicle to abort and merge back to its original lane. Deep reinforcement learning (DRL) is promising for such continuous-control tasks, but it requires substantial interaction data and may produce unsafe exploratory actions during training. Model-based controllers provide structured behavior, but depend on model fidelity and hand-designed logic. This paper proposes a fading expert-guidance framework that uses a model-based controller to guide DRL training for autonomous overtaking. The expert combines a constrained iterative LQR (CiLQR) planner with PID-based auxiliary controllers, activated when the optimized plan becomes infeasible. The expert action enters the actor objective through a fading term, interpreted as a time-varying soft trust region around the expert policy. This term first biases

arXiv:2609.35715v1 Announce Type: cross Abstract: Reinforcement learning (RL) in simulation can train dexterous manipulation policies without robot demonstrations, but training a single generalist policy with task-agnostic rewards faces a severe exploration problem: approaching, grasping, and reorienting diverse objects with many degrees of freedom is difficult to discover from scratch. Prior works make exploration tractable with high-quality robot demonstrations, per-task reward shaping, or by restricting policies to narrow modes of behavior. We propose X-Reset, a framework that instead resolves exploration with human hand-object demonstrations. Rather than imitating or tracking retargeted human motion, X-Reset kinematically retargets hand-object states to noisy robot states, filters out states that are unstable in simulation, and samples the remainder as resets during RL training with general-purpose object-centric rewards. The resulting policy depends only on object state and goal,

arXiv:2609.35311v1 Announce Type: cross Abstract: Action-conditioned video world models predict future robot interactions from multiple cameras, yet their outputs remain disparate video collections rather than a shared metric scene queryable across viewpoints and time. While existing 4D reconstruction methods offer a path to spatialize these predictions, independently reconstructing and merging each camera stream fails to enforce cross-view consistency. This limitation is particularly detrimental when combining moving robot-mounted cameras with fixed external views. To address this, we introduce RoGSW4RLD, a feed-forward framework that lifts synchronized multi-camera rollouts into a unified, time-queryable metric 4D Gaussian field. Rather than learning a separate geometric transition model, RoGSW4RLD directly reconstructs the visual future generated by existing world models. Its core innovation is a two-stage architecture: Stage 1 jointly forms the metric 4D field by fusing cross-view