Robotics & Automation
Robotics & Automation news — Monday 26 October 2026
107 stories from 1 sources, every one in English. Each links to its publisher.
-
MAST-VLA: Skill-Conditioned Adaptation with Trajectory-Affordance Priors for Multi-Skill Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.32312v1 Announce Type: new Abstract: Generalist robot manipulation requires a single vision-language-action (VLA) policy to execute diverse skills across scenes and instructions. However, current multi-skill VLA policies often…
-
LocoManiLab: A Unified Testbed for Data, Policies, Controllers, and Deployment in Humanoid Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.30876v2 Announce Type: replace Abstract: Humanoid robots must coordinate locomotion and manipulation in everyday environments, yet progress is difficult to assess across differing policies, controllers, and task settings…
-
Design and Analysis of a Nonlinear Parallel Mechanism Coupling for Dynamic Humanoid Legs
arXiv cs.RO (Robotics)
arXiv:2610.16604v2 Announce Type: replace Abstract: Humanoids increasingly demand lightweight leg mechanisms for agile, dynamic, and energy-efficient locomotion. Reducing distal inertia through proximal actuation has thus become a common…
-
FLORA: An Open Model Suite for Scaling Robotics Data Engines
arXiv cs.RO (Robotics)
arXiv:2610.31779v1 Announce Type: new Abstract: The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments. Process reward labels are needed during…
-
Adaptive World-Models for Anomaly Recognition (AWARE): A Framework for Robot Dynamics Prediction and Introspection
arXiv cs.RO (Robotics)
arXiv:2610.32742v1 Announce Type: new Abstract: Unrecognized anomalies in critical infrastructure can rapidly cascade into catastrophic physical or operational failures. Current anomaly detection approaches often rely on direct access to…
-
GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association
arXiv cs.RO (Robotics)
arXiv:2608.09581v2 Announce Type: replace-cross Abstract: Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene. Deterministic approaches, such as tracking-by-detection…
-
Input Bias Correction in Gaussian Process Regression
arXiv cs.RO (Robotics)
arXiv:2610.31920v1 Announce Type: new Abstract: In traditional Gaussian process (GP) regression, the inputs are typically assumed to be known, and uncertainty enters only through the measurements. When scalar fields are mapped using GP…
-
The effect of limb kinematics on the speed of a legged robot on granular media
arXiv cs.RO (Robotics)
arXiv:1303.7276v1 Announce Type: cross Abstract: Achieving effective locomotion on diverse terrestrial substrates can require subtle changes of limb kinematics. Biologically inspired legged robots (physical models of organisms) have shown…
-
Do Robotic World Models Really Follow Actions? Diagnosing and Aligning Action-Conditioned Generation for Policy Learning
arXiv cs.RO (Robotics)
arXiv:2608.24885v2 Announce Type: replace Abstract: Action-conditioned world models increasingly serve as learned simulators for robotic policy improvement, yet their reliability rests on an unverified assumption: generated futures…
-
Do VLAs Know They Will Fail? Interpretable Success and Failure Patterns in Physical AI Systems
arXiv cs.RO (Robotics)
arXiv:2610.32208v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as powerful general-purpose robot policies, but their successes and failures remain difficult to diagnose and understand. In this work, we…
-
Robotic Spatiotemporal Editing: A Unified Interface for Controllable Action Generation via Masked Action Reconstruction
arXiv cs.RO (Robotics)
arXiv:2610.23002v2 Announce Type: replace Abstract: Generative policies can synthesize robot behaviors, yet controlling and editing them through diverse spatiotemporal references remains challenging. In the real world, human intent…
-
Localization and Neural Splatting on the Edge: An FPGA Scene Memory for Robots
arXiv cs.RO (Robotics)
arXiv:2610.25068v2 Announce Type: replace Abstract: Resource-constrained robots and autonomous vehicles need scene memories that localize a camera and render nearby views without a desktop GPU. Scene-coordinate regression (SCR) and 3D…
-
RobustRLlib: A Unified Library and Benchmark for Robust Reinforcement Learning Algorithms
arXiv cs.RO (Robotics)
arXiv:2610.32971v1 Announce Type: cross Abstract: Robust reinforcement learning (RL) is critical for reliable real-world deployment, where policies may fail under diverse shifts and disruptions. Existing robust RL algorithms offer a rich…
-
ArtifactArena: Evaluating Models by What They Build in the Physical World
arXiv cs.RO (Robotics)
arXiv:2610.06511v2 Announce Type: replace Abstract: To evaluate the frontier, we must measure models not by what they say, but by what they can engineer and build in grounded physical environments. We introduce ArtifactArena, an open-ended…
-
EgoForesight: Effectively Scaling Policy Learning with Noisy Egocentric Actions
arXiv cs.RO (Robotics)
arXiv:2610.31845v1 Announce Type: new Abstract: Scaling policy learning requires broad experience and reliable supervision. Robot demonstrations provide high-quality trajectory supervision but are costly to collect. Egocentric videos…
-
If at First You Don't Succeed, Backtrack: Lightweight Recovery for Frozen VLAs
arXiv cs.RO (Robotics)
arXiv:2610.32941v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models perform well on robotic manipulation, yet remain brittle once their own actions carry them into states their training data barely covers. Recovering from…
-
RMMBench: A Comprehensive Benchmark for Robotic Mobile Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.05414v2 Announce Type: replace Abstract: Although the advancement of vision-language models (VLMs) has endowed robots with enhanced environmental understanding and task reasoning, a comprehensive evaluation methodology is…
-
Factor Graph-Based Continuum Robot State Estimation with Magnus Expansion Priors
arXiv cs.RO (Robotics)
arXiv:2604.15619v2 Announce Type: replace Abstract: Reconstructing the shape of continuum manipulators from sparse, noisy sensor data is a challenging task, owing to the infinite-dimensional nature of such systems. Existing approaches…
-
From Acceptance and Avoidance to Affective Viscosity: Designing Social Agents Intermediating in Human Relationships
arXiv cs.RO (Robotics)
arXiv:2610.29674v2 Announce Type: replace Abstract: As social agents become embedded in human relationships, they are expected not only to provide smooth assistance but also to handle rejection, discomfort, jealousy, persistence, and other…
-
When Human Corrections Travel: Safety in Federated VLA Adaptation
arXiv cs.RO (Robotics)
arXiv:2610.32888v1 Announce Type: new Abstract: Vision-language-action (VLA) policies can adapt to local human intervention, while federated learning can combine distributed robot experience without pooling raw records. We examine their…
-
VORL-EXPLORE: A Hybrid Learning Planning Approach to Multi-Robot Exploration in Dynamic Environments
arXiv cs.RO (Robotics)
arXiv:2603.07973v2 Announce Type: replace Abstract: Hierarchical multi-robot exploration decouples frontier allocation from local navigation, making systems brittle in dynamic environments. Without awareness of execution difficulty…
-
Flow-ERD: Agent-type Aware Flow Matching With Entropy-Regularized Distillation for Diverse Traffic Simulation
arXiv cs.RO (Robotics)
arXiv:2607.06957v2 Announce Type: replace Abstract: Realistic and diverse traffic simulation is essential to autonomous driving development. Yet prevailing benchmarks predominantly reward realism, and recent methods have optimized…
-
Unified Condition-Action Modeling for Accurate One-Step Action Generation
arXiv cs.RO (Robotics)
arXiv:2608.16153v5 Announce Type: replace Abstract: Robot manipulation requires policies that are both accurate and efficient, as robot control must respond to changing observations under tight latency constraints. Recent diffusion and…
-
Probing Collision Grounding in Vision-Language Models for Safe Human-Robot Collaboration
arXiv cs.RO (Robotics)
arXiv:2605.31196v2 Announce Type: replace-cross Abstract: Safe human--robot collaboration requires more than visual description: a monitor must determine whether the robot body is safely separated, already colliding with the scene or a…
-
From Tabletop to Walking Bot: Deploying a VLA Model on a Legged Manipulator Robot
arXiv cs.RO (Robotics)
arXiv:2610.32271v1 Announce Type: new Abstract: Vision-language-action (VLA) models are typically pretrained on broad, diverse datasets and subsequently fine-tuned on a comparatively small dataset tailored to a specific target robot. Such…
-
Motion Generation With Environmental Constraints
arXiv cs.RO (Robotics)
arXiv:2607.25053v2 Announce Type: replace Abstract: Robot motion planning faces challenges in high-dimensional spaces and uncertain environments, often constrained by the need for collision-free motions. We advocate an alternative…
-
See What I Need, Dream What I Want: A Navigation Foundation Model on a Self-Constructed Representation Space
arXiv cs.RO (Robotics)
arXiv:2610.31762v1 Announce Type: new Abstract: What visual representation should a navigation policy act on? Navigation policies built on vision foundation models largely leave representation design to the encoders' pretraining…
-
GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
arXiv cs.RO (Robotics)
arXiv:2607.05369v2 Announce Type: replace Abstract: For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to combine interpretable robot programming with the…
-
OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction
arXiv cs.RO (Robotics)
arXiv:2608.16499v3 Announce Type: replace Abstract: Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints…
-
SMR: Learning streaming motion retargeting for humanoids from human semantic
arXiv cs.RO (Robotics)
arXiv:2610.29169v2 Announce Type: replace Abstract: Retargeting human motion to humanoids requires preserving motion semantics while accounting for the robot's physical constraints. Kinematic pipelines prescribe a robot trajectory through…
-
GenTrack2: An Improved Hybrid Approach for Multi-Object Tracking
arXiv cs.RO (Robotics)
arXiv:2510.24410v5 Announce Type: replace-cross Abstract: This paper proposes a visual multi-object tracking method that jointly employs stochastic and deterministic mechanisms to ensure identifier consistency for unknown and time-varying…
-
SEVI: Safe Evidential Real-World Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.31829v1 Announce Type: new Abstract: Real-world reinforcement learning has enabled contact-rich manipulation tasks to be trained directly on physical robots, but unsafe interactions during online learning remain a key barrier to…
-
StackGen3D: Stable 3D Block Stack Generation from Multiview Silhouettes
arXiv cs.RO (Robotics)
arXiv:2610.31803v1 Announce Type: cross Abstract: Generating physically stable 3D structures from visual specifications requires resolving geometric ambiguity while accounting for physical interactions among objects. We present StackGen3D…
-
No Eyes, No Problem: What Does Touch Contribute to Blind Baoding Ball Manipulation?
arXiv cs.RO (Robotics)
arXiv:2610.23438v2 Announce Type: replace Abstract: Humans manipulate objects within their hands through touch alone with remarkable ease, but for robots, achieving sustained real-world manipulation without vision remains an open…
-
Distributed Swarm Morphogenesis with Neural Cellular Automata
arXiv cs.RO (Robotics)
arXiv:2610.31900v1 Announce Type: new Abstract: Swarm morphogenesis requires robots to assemble desired shapes through local interactions. We present a modular framework integrating neural cellular automata (NCA) with existing site…
-
Robotic Budding: From Homogeneous Cells to Diverse Morphologies in Physical Self-Reproduction
arXiv cs.RO (Robotics)
arXiv:2610.31929v1 Announce Type: new Abstract: Physical self-reproduction in modular robots remains difficult because a robot must not only move, but also collect, align, dock, and separate modules reliably in hardware. Taking inspiration…
-
$R^2E:$ A Role-driven Reward Evolutionary Framework for Automated Reward Function Design
arXiv cs.RO (Robotics)
arXiv:2610.32439v1 Announce Type: new Abstract: Designing effective reward functions is a critical challenge in Reinforcement Learning (RL), which traditionally requires costly manual trial-and-error. While Large Language Model (LLM)-based…
-
Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language
arXiv cs.RO (Robotics)
arXiv:2606.08666v2 Announce Type: replace Abstract: Robots deployed in human-centric environments routinely receive natural-language descriptions of spatial information ("I left my backpack on the table") that reference parts of the world…
-
Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers
arXiv cs.RO (Robotics)
arXiv:2610.32277v1 Announce Type: new Abstract: Learned humanoid controllers are usually trained in one simulator and then checked in a second one before they go near hardware. We ask what that check says about command delay. We train…
-
Semantic Representation for Agentic Self-Play in Automated Laboratories
arXiv cs.RO (Robotics)
arXiv:2610.32755v1 Announce Type: new Abstract: Navigating complex, high-dimensional biological search spaces necessitates scalable physical and computational intelligence to explore beyond local optima through iterative self-play across…
-
3D Generation for Embodied AI and Robotic Simulation: A Survey
arXiv cs.RO (Robotics)
arXiv:2604.26509v4 Announce Type: replace Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for simulation-based training and real-world deployment. While 3D generative…
-
DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning
arXiv cs.RO (Robotics)
arXiv:2610.32093v1 Announce Type: new Abstract: Behavior cloning for robotic manipulation is highly sensitive to the coverage of its training data, yet collecting diverse successful demonstrations remains costly. We study reinforcement…
-
FORCA: A Force-Aware Coding Agent for Contact-Rich Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.31841v1 Announce Type: new Abstract: Coding agents can translate language instructions into robot programs. For contact-rich manipulation, a key challenge is to generate and refine control logic that responds to physical…
-
WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot Demonstrations
arXiv cs.RO (Robotics)
arXiv:2610.31834v1 Announce Type: new Abstract: Existing approaches for robot learning in simulation often require substantial manual effort to construct scenes and specify tasks, limiting training scalability and data diversity…
-
PartialBiGrasp: Inferring Hidden Local Geometry for Bimanual Grasping from Partial Views
arXiv cs.RO (Robotics)
arXiv:2608.19188v2 Announce Type: replace Abstract: Dual-arm robotic grasping is essential for manipulating large, heavy, and geometrically complex objects that cannot be reliably handled using a single manipulator. These large objects…
-
Does LeWorldModel Preserve Local Action Geometry?
arXiv cs.RO (Robotics)
arXiv:2610.31716v1 Announce Type: cross Abstract: We examine how closely pretrained LeWorldModel (LeWM) reproduces the effects of small action changes. Using matched simulator and model responses, we measure action sensitivity with Gram…
-
TTT in VLA Models: Exploring Training with Human Demonstrations
arXiv cs.RO (Robotics)
arXiv:2610.32094v1 Announce Type: new Abstract: Long-horizon robot tasks require retaining and using past information. We integrate Test-Time Training (TTT), which stores context in fast weights, into InternVLA-A1 and Pi0.5 to study action…
-
OWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover Navigation
arXiv cs.RO (Robotics)
arXiv:2610.32596v1 Announce Type: new Abstract: Semantics can provide a proxy for physical traversability. Terrain that looks like loose sand or a rock field is likely to have similar physical properties. Open-vocabulary vision-language…
-
PnP*: A certifiable solver for Perspective-n-Point
arXiv cs.RO (Robotics)
arXiv:2610.31797v1 Announce Type: cross Abstract: Estimating a camera pose from 3D-2D correspondences - Perspective-n-Point - is one of the most fundamental problems in computer vision. Existing methods either solve a minimal problem or…
-
PrefO2O: Zero-Shot Preference-Based Reinforcement Learning via Offline-to-Online Latent Preference Transfer
arXiv cs.RO (Robotics)
arXiv:2610.31812v1 Announce Type: new Abstract: Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for learning robot behaviors aligned with human intent. However, its scalability is fundamentally limited by…
-
Move, don't think: sample-efficient collision avoidance with lossy proximity sensors
arXiv cs.RO (Robotics)
arXiv:2610.31891v1 Announce Type: new Abstract: Data-driven robots must learn to avoid collisions with as few demonstrations as possible to avoid collecting large datasets of destructive collision examples. We explore whole-body proximity…
-
TravSUITE: Traversability via Self-Supervised, Uncertainty-Aware IRL and Terrain Estimation
arXiv cs.RO (Robotics)
arXiv:2610.32130v1 Announce Type: new Abstract: Traversability analysis in off-road settings remains a fundamental challenge for mobile robots. Key difficulties include constructing an accurate and expressive local map from multimodal…
-
Geometry-Aware Reinforcement Learning for Close-Fitting Wearable Insertion
arXiv cs.RO (Robotics)
arXiv:2610.32143v1 Announce Type: new Abstract: Robot-assisted dressing is particularly challenging due to narrow openings and articulated body parts. Even small errors in the relative pose between the body part and garment opening can…
-
RAISE-Vision: An Automated Contact Angle Measurement Platform for Contact Lens Wettability Characterization
arXiv cs.RO (Robotics)
arXiv:2610.32188v1 Announce Type: new Abstract: Contact angle (CA) is a common parameter measured in the development of novel contact lens materials and surface coating technologies. Existing literature on in vitro CA of contact lenses via…
-
Incremental-Smoothing-Based ARAIM Protection Levels for Tightly Coupled GNSS/IMU Integration in Urban Canyons
arXiv cs.RO (Robotics)
arXiv:2610.32259v1 Announce Type: new Abstract: Protection levels (PLs) bound position errors under specified fault hypotheses and risk budgets, but advanced re-ceiver autonomous integrity monitoring (ARAIM) is formulated for snapshot GNSS…
-
LogLook: Execution-Grounded Memory for Frontier-Model Robot Planners
arXiv cs.RO (Robotics)
arXiv:2610.32348v1 Announce Type: new Abstract: Many manipulation tasks require a robot to remember what it has done and what it has seen. Frontier vision-language models can plan such tasks without task-specific training, but how such a…
-
Graphs of Trajectory Bundles for Nonlinear Motion Planning
arXiv cs.RO (Robotics)
arXiv:2610.32365v1 Announce Type: new Abstract: We present the Graphs of Trajectory Bundles (GTB) method for motion planning of systems with nonlinear and black-box dynamics, combining sampling-based motion planning with trajectory…
-
From Freehand Demonstrations to Autonomous Robotic Ultrasound: An Anatomy-Anchored Learning Framework
arXiv cs.RO (Robotics)
arXiv:2610.32525v1 Announce Type: new Abstract: Ultrasound imaging is highly operator-dependent, motivating robotic systems that reproduce expert scanning skills consistently. These skills involve coordinated interpretation of anatomical…
-
Facultative Swarming: A Capability, Not a Category, for Multi-Robot Systems
arXiv cs.RO (Robotics)
arXiv:2610.32526v1 Announce Type: new Abstract: Collective robotics is split by a long-standing but increasingly artificial boundary between centralised multi-robot systems that prioritise optimality and decentralised swarms that…
-
Optimization, Optimal Control, and Reinforcement Learning for Robotics
arXiv cs.RO (Robotics)
arXiv:2610.32538v1 Announce Type: new Abstract: These lecture notes provide an introduction to optimization, optimal control, and reinforcement learning for robotics, emphasizing their mathematical connections and practical relevance. They…
-
Monte Carlo-Based Indoor UAV Localization in Dynamic Environments Using Only Four Onboard Range Sensors
arXiv cs.RO (Robotics)
arXiv:2610.32645v1 Announce Type: new Abstract: Indoor UAV localization with minimal onboard sensing remains challenging, particularly in dynamic environments. We propose augmented filtered Monte Carlo localization (AF-MCL) for 2D…
-
Predictive Long-Horizon Progress Modeling with Action-Aware Quantification
arXiv cs.RO (Robotics)
arXiv:2610.32776v1 Announce Type: new Abstract: Quantitative and dense task progress feedback is essential for robotic manipulation across data curation, policy evaluation, and reinforcement learning. Existing progress annotations often…
-
HoloBoxing: A Simple Recipe for Humanoid Boxing with 7 Minutes of Single-GPU Training
arXiv cs.RO (Robotics)
arXiv:2610.32909v1 Announce Type: new Abstract: HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact…
-
Robotic Optical Coherence Tomography-Guided Geometric Modeling of Soft Tissue: 3D Representations for Data-Driven Closed-Loop Shape Control
arXiv cs.RO (Robotics)
arXiv:2610.32961v1 Announce Type: new Abstract: In medical robotics, data-driven soft-tissue shape control requires deforming tissue toward desired morphologies through sequential physical interactions. This challenge is particularly…
-
ViT-H: Generative Video-To-Humanoid Control with Motion Tracking Feedback
arXiv cs.RO (Robotics)
arXiv:2610.32966v1 Announce Type: new Abstract: Learning humanoid control from monocular human videos offers a scalable way to acquire diverse whole-body behaviors. Yet, existing reconstruction-retargeting-tracking pipelines are limited in…
-
SAGE: A hybrid vision-language and geometry framework for work-zone pathway prediction under temporary traffic control
arXiv cs.RO (Robotics)
arXiv:2610.31835v1 Announce Type: cross Abstract: Temporary traffic control redirects vehicles through work zones, requiring automated vehicles to connect an interpretation of the visible devices to a continuous passing path. Geometric…
-
CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition
arXiv cs.RO (Robotics)
arXiv:2610.32022v1 Announce Type: cross Abstract: Intent recognition in human-robot interaction requires agents to resolve ambiguous natural language instructions by inferring the speaker's underlying goals. Research has increasingly…
-
Regularised RL improves sim-to-real transfer
arXiv cs.RO (Robotics)
arXiv:2610.32855v1 Announce Type: cross Abstract: Regularised reinforcement learning (RL) has provable robustness guarantees that should ease the transfer of policies from simulation to robots, known as sim-to-real. Yet, weakly regularised…
-
Haptic bilateral teleoperation system for free-hand dental procedures
arXiv cs.RO (Robotics)
arXiv:2503.21288v4 Announce Type: replace Abstract: Free-hand dental procedures are typically repetitive, time-consuming and require high precision and manual dexterity. Robots can play a key role in improving procedural accuracy and…
-
RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution
arXiv cs.RO (Robotics)
arXiv:2608.15924v2 Announce Type: replace Abstract: Cloud-side inference expands the computational resources available to imitation-learning policies, but communication and inference latencies create a mismatch between prediction and…
-
ContactBench 1.0: A Benchmark for Everyday Contact-Rich Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.24512v2 Announce Type: replace Abstract: Contact-rich manipulation underlies many everyday human activities, yet evaluating robots on such tasks remains difficult: the tasks involve diverse contact behaviors and are hard to…
-
RGraph-Eval: Task-Grounded Scene Graphs for Evaluating Robot Video Generation
arXiv cs.RO (Robotics)
arXiv:2610.31121v2 Announce Type: replace Abstract: Generated robot videos can look convincing while depicting the wrong interaction: a different object is moved, a grasp disappears, or a placement ends outside its destination. We…
-
DepTR-MOT: Unveiling the Potential of Depth-Informed Trajectory Refinement for Multi-Object Tracking
arXiv cs.RO (Robotics)
arXiv:2509.17323v2 Announce Type: replace-cross Abstract: Visual Multi-Object Tracking (MOT) is a crucial component of robotic perception, yet existing Tracking-By-Detection (TBD) methods often rely on 2D cues, such as bounding boxes and…
-
Metro-WM: Long-Horizon Latent Planning with Realisable Sub-Goals
arXiv cs.RO (Robotics)
arXiv:2609.31868v3 Announce Type: replace-cross Abstract: Model-predictive control with Joint-Embedding Predictive Architectures (JEPAs) provides a strong zero-shot goal-reaching planner, but it is only effective over short planning…
-
Semantic Anchoring for Robotic Action Representations
arXiv cs.RO (Robotics)
arXiv:2607.13597v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models inherit rich semantic representations from pretrained Vision-Language Models, yet fine-tuning on limited robot demonstrations degrades this structure…
-
Conditional Neural Processes for Self-Supervised Goal Discovery in Action Imitation
arXiv cs.RO (Robotics)
arXiv:2610.32688v1 Announce Type: new Abstract: Inspired by infants' ability to learn novel tasks by imitating others, in this work we evaluate to what extent Conditional Neural Processes can autonomously learn representations of actions…
-
CARE: Consistent Action-Response Execution for Human-Guided Robot Transport
arXiv cs.RO (Robotics)
arXiv:2601.16686v2 Announce Type: replace Abstract: Human-guided collaborative transport becomes interaction-critical when the operator can continue along a route segment that is not executable by the robot--payload system. In this regime…
-
KiRoSe: Using Kinematic Data for Efficient Segmentation of Robot Demonstrations
arXiv cs.RO (Robotics)
arXiv:2610.31801v1 Announce Type: new Abstract: Segmenting robot demonstration data into disjoint temporal and semantic subsegments is valuable for learning, cleaning, retrieval, and analysis. Segmentation is often performed manually in a…
-
HGWM: Hierarchical Graph-Guided World Model for Zero-Shot Object Navigation via Graph Matching
arXiv cs.RO (Robotics)
arXiv:2610.32554v1 Announce Type: new Abstract: Zero-shot object navigation requires an embodied agent to choose where to search while retaining evidence from previous observations. HGWM couples an LLM-generated room-anchor prior with…
-
Not an Accident: Exploiting Safety Filter Inadequacy in Humanoid Robots
arXiv cs.RO (Robotics)
arXiv:2610.31923v1 Announce Type: cross Abstract: As humanoid robots move from research laboratories toward deployment in human-centered environments such as homes, hospitals, and warehouses, safe operation around nearby people and objects…
-
SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning
arXiv cs.RO (Robotics)
arXiv:2610.32978v1 Announce Type: cross Abstract: Training generalizable embodied agents requires realistic, varied, and simulation-ready indoor environments. Language-guided methods support semantic planning and object-level reasoning…
-
WAM-TTT: Steering World-Action Models by Watching Human Play at Test Time
arXiv cs.RO (Robotics)
arXiv:2607.06988v3 Announce Type: replace Abstract: Steering robot foundation models (RFMs) toward new task variants or user-preferred behaviors remains challenging, often requiring additional robot demonstrations, task-specific…
-
Rethinking Densification in Gaussian SLAM: A Stationary Sampling Perspective
arXiv cs.RO (Robotics)
arXiv:2601.00705v4 Announce Type: replace-cross Abstract: Gaussian Splatting enables high-fidelity differentiable SLAM by representing scenes as anisotropic Gaussian primitives. Most systems rely on residual-driven densification, which…
-
Emergent Cooperative Thermoregulation in Lunar Swarm Robotics
arXiv cs.RO (Robotics)
arXiv:2610.31868v1 Announce Type: new Abstract: Swarms of small robots are an attractive way to survey lunar caves and lava tubes. Missions such as NASA's CADRE will fly cooperating rovers for distributed mapping, but only in daylight. The…
-
Full-Weight VLA Fine-Tuning Without an fp32 Master Copy Silently Erases Most Updates
arXiv cs.RO (Robotics)
arXiv:2610.31859v1 Announce Type: new Abstract: When a vision-language-action (VLA) model is fine-tuned with its trainable weights in bfloat16 (bf16) and no fp32 master copy, AdamW writes each update straight into bf16, silently rounding…
-
DepState-JEPA: Learning Depth-Grounded State Representation for Visual Perception and Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.29246v2 Announce Type: replace Abstract: Predictive representations for robot manipulation should connect scene geometry with the state changes induced by actions. Our intuition is that understanding what an action will change…
-
Revisiting Temporal Regularization for Smooth Control in Deep Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.07910v2 Announce Type: replace-cross Abstract: Deep Reinforcement Learning policies can produce nonsmooth action oscillations that hinder deployment on physical robots. Existing architectural and penalty-based approaches seek…
-
Emergent Neural Automaton Policies: Learning Symbolic Structure from Visuomotor Trajectories
arXiv cs.RO (Robotics)
arXiv:2603.25903v3 Announce Type: replace Abstract: Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning…
-
DASH: A da Vinci Adapter for Serial-link and Humanoid Robots as an Accessible Platform for Surgical Robotics Research
arXiv cs.RO (Robotics)
arXiv:2610.05792v2 Announce Type: replace Abstract: Robotic minimally invasive surgery offers well-documented clinical benefits, but the cost and infrastructure requirements of purpose-built platforms limit access in rural and…
-
RoboCode: Learning Reusable Action Primitives for Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.32225v1 Announce Type: new Abstract: Recent robot manipulation policies commonly predict continuous action chunks directly from observations, without explicitly modeling reusable structure in the action space. However…
-
Natural-Language to Nav2: Operational Policies for Costmap-Based Navigation
arXiv cs.RO (Robotics)
arXiv:2610.32633v1 Announce Type: new Abstract: Autonomous mobile robots support material transport in warehouses and industrial facilities, where navigation must adapt to changing operating conditions. Sensor observations reveal physical…
-
RynnUnify: Towards Unified Embodied Brain
arXiv cs.RO (Robotics)
arXiv:2610.32965v1 Announce Type: new Abstract: We introduce RynnUnify, a 16B unified embodied model that combines strong embodied understanding with long-horizon visual planning through interleaved video--language reasoning. With…
-
Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure
arXiv cs.RO (Robotics)
arXiv:2606.26588v3 Announce Type: replace Abstract: A central challenge in deploying robot policies is inference-time policy steering: redirecting a policy to satisfy natural-language preferences unseen in training, without retraining…
-
Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena
arXiv cs.RO (Robotics)
arXiv:2610.00854v3 Announce Type: replace Abstract: A robot generalist must interpret a scene, act on it, and satisfy every condition of a task. How far do frontier vision-language models (VLMs) meet these demands? We introduce Embodied…
-
DynaSlots: Slot-Centric 3D Dynamics Pretraining for Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.32330v1 Announce Type: new Abstract: Robot manipulation involves localized changes: picking up a cup moves the cup while leaving the surrounding scene largely unchanged. Yet existing 3D visual pretraining methods, including…
-
DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection
arXiv cs.RO (Robotics)
arXiv:2610.32969v1 Announce Type: new Abstract: Collecting high-quality demonstrations remains a central bottleneck for learning dexterous manipulation. Teleoperation records executable robot actions, but it requires a complete robot setup…
-
Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.29264v2 Announce Type: replace Abstract: Large pretrained robot foundation models provide strong priors for manipulation, yet adapting them to target tasks with offline teleoperated demonstrations often fails to cover the…
-
UAV-SwarmAgent: Scalable Multi-UAV Reconnaissance and Task Allocation via Code Generation and Vision-Language Reasoning
arXiv cs.RO (Robotics)
arXiv:2610.32559v1 Announce Type: new Abstract: Supervising a multi-UAV reconnaissance mission usually means plotting waypoints and watching every drone. We present UAV SwarmAgent, a hierarchical multi-agent system in which an operator…
-
Coupling Execution Horizon and Sampling Depth in Flow-Matching VLA Policies
arXiv cs.RO (Robotics)
arXiv:2610.32102v1 Announce Type: new Abstract: Flow-matching Vision-Language-Action (VLA) models generate expressive continuous trajectories for robotic manipulation, yet balancing real-time responsiveness with execution stability remains…
-
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
arXiv cs.RO (Robotics)
arXiv:2610.31670v2 Announce Type: replace-cross Abstract: Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis…
-
Retiming Robot Demonstrations with a Learned Speed Prior
arXiv cs.RO (Robotics)
arXiv:2610.32676v1 Announce Type: cross Abstract: The pace of a robot demonstration is often determined by the teleoperator rather than by the task itself. As a result, the same motion can appear at widely different speeds across…
-
Multimodal MPC via Bayesian Set Optimization for Dynamic Manipulation of Deformable Linear Objects
arXiv cs.RO (Robotics)
arXiv:2610.31852v1 Announce Type: new Abstract: Dynamic manipulation of deformable linear objects (DLOs) remains challenging due to underactuated, high-dimensional dynamics, delayed deformation responses, and the presence of multiple…
-
CoCarry: Contact-Support-Structured Retargeting for Dual-Humanoid Cooperative Carrying
arXiv cs.RO (Robotics)
arXiv:2610.32460v1 Announce Type: new Abstract: Recent advances in large-scale human motion data, motion retargeting, and motion imitation have enabled increasingly capable whole-body control for individual humanoids. Cooperative carrying…
-
Robust Offset-Free Lane-Keeping Control Framework for Vision-Only Automated Vehicles
arXiv cs.RO (Robotics)
arXiv:2610.32666v1 Announce Type: new Abstract: Achieving accurate, real-time lane-keeping control during high-speed cornering on large-curvature roads while ensuring robust vehicle stability is a critical challenge in autonomous driving…
-
Deep Learning Warm Starts for Trajectory Optimization on the International Space Station
arXiv cs.RO (Robotics)
arXiv:2505.05588v4 Announce Type: replace Abstract: Trajectory optimization is a cornerstone of modern robot autonomy, enabling systems to compute trajectories and controls in real-time while respecting safety and physical constraints…
-
Robot Motion Transition with a Human Motion Prior
arXiv cs.RO (Robotics)
arXiv:2610.30817v2 Announce Type: replace Abstract: Humanoid motion-tracking policies can reproduce diverse behaviors, yet connecting independently acquired motions into a continuous sequence remains challenging. Interpolation connects…
-
Silence Is Not Assurance: When Production Lane Keeping Assist Does Not Warn, and What It Costs
arXiv cs.RO (Robotics)
arXiv:2610.31899v1 Announce Type: new Abstract: Production lane keeping assist (LKA) systems tell the driver whether they detect the lane markings, but whether this displayed status reflects what the system perceives, and what happens when…