뉴스 및 연구

arXiv:2503.17589v3 Announce Type: replace Abstract: Kinematic motion planners are among the most widely used control approaches in robotic applications. By modeling the robot as a first-order system, they generate a feedback-based desired velocity field that guides the robot toward a target while avoiding obstacles. However, extending such feedback planners to systems with higher-order dynamics, while preserving safety and stability properties, is not a straightforward task. In the present work, we propose an approach that adapts existing feedback-based kinematic motion planners to second-order autonomous systems while retaining their safety and almost global asymptotic stability guarantees. We consider two general classes of kinematic motion planners: those derived from navigation functions and those defined directly through desired velocity fields without relying on an underlying navigation function. To validate the proposed methodology, two feedback-based kinematic motion planners a

arXiv:2502.06359v3 Announce Type: replace Abstract: Ensuring safe driving while maintaining travel efficiency for autonomous vehicles in dynamic and occluded environments is a critical challenge. This paper proposes an occlusion-aware contingency safety-critical planning approach for real-time autonomous driving. Leveraging reachability analysis for risk assessment, forward reachable sets of phantom vehicles are used to derive risk-aware dynamic velocity boundaries. These velocity boundaries are incorporated into a biconvex nonlinear programming (NLP) formulation that formally enforces safety using spatiotemporal barrier constraints, while simultaneously optimizing exploration and fallback trajectories within a receding horizon planning framework. To enable real-time computation and coordination between trajectories, we employ the consensus alternating direction method of multipliers (ADMM) to decompose the biconvex NLP problem into low-dimensional convex subproblems. The effectiveness

arXiv:2410.18275v2 Announce Type: replace Abstract: In this paper, we study the problem of methodically obtaining a sufficient set of kinesthetic demonstrations, one at a time, such that a robot can be confident of its ability to perform a complex manipulation task in a given region of its workspace. Although programming by demonstration has been an active area of research, the problems of checking whether a set of demonstrations is sufficient and systematically seeking additional demonstrations have remained open. We present an approach for the robot to incrementally and actively ask for new demonstration examples, one at a time, until the robot can assess with high confidence that it can perform the task successfully. Our approach uses: (i) a screw geometric representation of motion to generate manipulation plans from demonstrations, which makes the sufficiency of a set of demonstrations measurable; (ii) a sampling strategy based on PAC-learning from multi-armed bandit optimization t

arXiv:2610.06814v1 Announce Type: cross Abstract: World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models optimize against the victim's actions or predicted futures and therefore require access to target-model outputs. In this paper, we propose an attack, TAPDreamer, against world action models that instead uses a public encoder alone to construct a fixed local perturbation that transfers across tasks and action architectures. TAPDreamer requires no target-policy queries. Our key insight is that interactions between patch-induced changes in attention weights and value vectors broadcast a nearly identical representation shift far beyond the patch footprint, and this shift remains stable across task observations. Guided by this insi

arXiv:2610.06805v1 Announce Type: cross Abstract: Long-horizon planning with latent world models requires reasoning across timescales and levels of abstraction. Existing task-agnostic JEPA world models predict and plan at a single timescale or with multiple horizons in one shared latent space. We introduce H-JEPA, an end-to-end recipe for training a hierarchy of action-conditioned JEPAs in which each level predicts farther ahead in its own learned latent space. Planning proceeds top-down: the top level optimizes progress toward the goal, and each level's predictions become subgoals for the planner below it. When factors in the data evolve at separated timescales, higher levels discard fast, unpredictable detail and retain slower task-relevant state. Across four simulated navigation and manipulation environments, hierarchical planning improves over a flat JEPA; on Visual AntMaze, a three-level hierarchy raises success from 18% to 73% using less planner compute. Ablations attribute these

arXiv:2610.06349v1 Announce Type: cross Abstract: Embodied world models predict the visual consequences of candidate actions before execution. However, existing action-conditioned world models often adopt uniformly weighted visual generation objectives that can be misaligned with embodied prediction needs. Even with explicit motion conditioning, these objectives can underemphasize spatially sparse changes that are critical to interaction. We propose KineWorld, a transport-aware world-modeling framework that extends robot kinematics from motion conditioning to the spatial allocation of generative supervision. Kinematic Transport Lifting (KTL) constructs renderer-derived, camera-aligned transport fields from commanded robot motion. Transport-Aware World Diffusion (TAWD) calibrates their motion support on the video-latent grid and reweights future-RGB flow matching through a normalized mixture of uniform and transport-focused distributions. We train KineWorld using ALOHA-AgileX bimanual m

arXiv:2610.05273v1 Announce Type: cross Abstract: Visual token pruning is an effective way to accelerate vision-language models and is especially useful for vision-language-action (VLA) inference, where many visual tokens must be processed before predicting robot actions. Existing pruning methods usually estimate which tokens can be pruned based on attention scores or feature diversity, retaining tokens that are either highly attended or visually different from others. However, most of them use fixed pruning schedules, such as pruning once at a preset layer or pruning at uniformly spaced layers. Such schedules can be risky for VLA models, because the model may not know which visual regions matter for the action in early layers. Tokens that look unimportant at first may become useful after the model combines visual observations with the language instruction. In this work, we propose SAPrune, a training-free visual token pruning framework for efficient VLA inference. Instead of pruning a

arXiv:2610.05087v1 Announce Type: cross Abstract: Contrastive Reinforcement Learning (CRL) learns representations that estimate goal reachability, yet its policy remains conditioned on raw goals and therefore does not directly exploit the geometry encoded by its critic. We introduce Direction-Conditioned Policies (DCP), a method built around a small modification to CRL: DCP selects previously visited states as waypoints during online training and conditions the policy on their direction and distance in representation space. At deployment, DCP applies the same interface directly to the final goal, requiring neither waypoint selection nor planning. Across nine navigation and manipulation tasks, DCP attains higher final success rates than CRL on seven tasks and spends more time near the goal on seven. Controlled maze experiments further show that DCP captures shortest-path geometry more accurately and that the supplied direction causally influences the actor's behavior. We identify waypoi

arXiv:2610.05062v1 Announce Type: cross Abstract: Vision-language-action (VLA) models translate multimodal observations into low-level robot actions. During robot operation, each control period sets an inference deadline, and overruns leave the robot acting on stale observations, reducing task success. Meeting this deadline motivates on-device or nearby edge execution, where a single robot requires batch-1 inference outside the design point of LLM serving systems. Although VLA architectures combine familiar vision-language, autoregressive, and diffusion-style components, their runtime behavior in this batch-1 control setting remains uncharacterized. We characterize four representative VLA models on an edge GPU server and two onboard SoCs, using single-inference profiling and 43,200 closed-loop episodes. Action tensor dimensionality determines whether a stage is memory- or compute-bound, platform balance can shift that bottleneck, and GPU frequency scaling yields a platform-dependent en

arXiv:2610.05026v1 Announce Type: cross Abstract: Vision-language-action (VLA) models encode semantic information from vision-language pretraining, but manipulation also requires precise spatial reasoning. We present GeoBridge-VLA, a two-stage method for learning geometric features from a pretrained VLA's frozen visual encoder and using them for action prediction. Stage I trains a feature bridge and geometry decoder with depth supervision. Stage II freezes these modules and trains a gated residual interface together with the action-side projections and action expert. The residual augments the existing visual tokens without adding a second image encoder or increasing the token count. Deployment requires RGB, robot state, and language, but no depth observations. Under matched evaluation conditions, GeoBridge-VLA achieves 70.9% success on LIBERO, compared with 60.0% for SmolVLA. Disabling the residual in the same trained checkpoint reduces success from 70.90% to 69.85%, with mixed effects

arXiv:2610.04662v1 Announce Type: cross Abstract: Temporal logic provides designers a formal reasoning tool for specifying complex spatio-temporal behaviors and tasks for autonomous systems. Many techniques exist for control synthesis according to temporal logic specifications, spanning a large variety of systems, including robotics. However, the vast majority of implementations are limited to Boolean temporal logics. Boolean temporal logic does not have an innate mechanism for quantifying abstention, rather verdicts are either definitively \textit{True} or \textit{False}. Recent work demonstrates that ternary logic is a capable formalism for reasoning about robotic behaviors, with the natural ability to classify uncertainty with the \textit{Unknown} literal. Ternary temporal logic is still in its infancy, with work limited to synthesis for linear systems and monitoring. This work proposes a probabilistic relaxation of ternary temporal logic that allows for value and gradient computati

arXiv:2610.04438v1 Announce Type: cross Abstract: We present RAGrasp, a retrieval-augmented pipeline for planar parallel-jaw grasping from a compact set of locally collected, grasp-annotated RGB-D (color and depth) templates. Unlike task-specific predictors trained primarily on large public or synthetic grasp datasets, RAGrasp requires no end-to-end retraining for a new deployment.Its template memory is constructed from observations collected with the deployment camera, robot, and gripper in the target workspace, thereby aligning stored examples with the local sensing and embodiment conditions. The system uses self-supervised DINOv2 visual fea- tures together with appearance and depth cues to prompt the Segment Anything Model 2 (SAM2), which isolates the query object. A two-stage geometry-semantic retrieval cascade then selects a template, and a confidence gate chooses one of two grasp- transfer estimators. The transferred grasp is refined using mask- support and silhouette-contact con

arXiv:2610.04432v1 Announce Type: cross Abstract: Building interactive simulators from real-world observations is a promising way to scale embodied data, but current pipelines still rely heavily on manual environment construction and calibration. We study whether frontier foundation models and coding agents can automate this process end to end. We formulate \emph{autonomous video-to-simulation} as a software engineering task in which an agent observes an embodied video, constructs the corresponding simulated environment and robot behavior, and iteratively refines the result through execution feedback. To evaluate this capability, we introduce \textbf{Video2World}, a benchmark comprising 222 reconstruction instances derived from 189 robot and human demonstration videos. Video2World measures reconstructed worlds along geometric fidelity, dynamic fidelity, and functional correctness, capturing spatial perception, physical reasoning, and executable interaction. Evaluating 9 frontier coding

arXiv:2610.04402v1 Announce Type: cross Abstract: We investigate the mutual visibility problem for a swarm of $n\ge3$ autonomous mobile robots under the budget-constrained mobility fault model. The robots are opaque, so if three robots are collinear, the middle robot obstructs the visibility between the other two. Each robot is assigned a finite movement budget, reflecting its limited energy, that bounds the total distance it may traverse during the execution. Moreover, an arbitrary number of robots may become permanently immobile due to mobility faults. The objective is to design a distributed algorithm that enables the non-faulty robots to coordinate their movements so that, within a finite time, every non-faulty robot attains unobstructed visibility of all robots in the system, including the faulty ones, while respecting the prescribed movement budget. We consider luminous robots operating under the $\mathsf{SSYNC}$ model with non-rigid movements, without any agreement on their loca

arXiv:2610.04364v1 Announce Type: cross Abstract: Designing effective reward functions in RL typically requires substantial expertise and trial and error. Recent work automates this process with LLM-based systems that generate and iteratively improve reward code using policy feedback. However, these methods are often hard to compare because they differ in implementation details, feedback assumptions, and evaluation environments. To address this, we introduce a Benchmark for Iterative Reward Design (BIRD) that expresses existing methods in a unified configuration and evaluation space. This lets us compare algorithms directly, ablate individual design choices, and prototype new components under matched feedback conditions and policy-training budgets. Across MuJoCo, Meta-World, Assistax, and HumanoidBench, we identify a small set of simple design choices that consistently improve performance. Combining these choices yields significantly better performance than the evaluated methods from p