Robotics & Automation
Robotics & Automation news — Monday 05 October 2026
127 stories from 3 sources, every one in English. Each links to its publisher.
-
Teradyne invests in Bright Machines to bring robotics to AI infrastructure manufacturing
The Robot Report
Bright Factory is an intelligent manufacturing platform connecting design, automation, and data. | Source: Bright Machines Teradyne Inc. today announced a strategic investment in Bright Machines Inc., a builder of AI and data center…
-
Teradyne invests in Bright Machines to bring robotics to AI infrastructure manufacturing
Robotics Business Review
Bright Factory is an intelligent manufacturing platform connecting design, automation, and data. | Source: Bright Machines Teradyne Inc. today announced a strategic investment in Bright Machines Inc., a builder of AI and data center…
-
FCC robot restrictions could accelerate shift to local AI
Robotics Business Review
A Unitree humanoid robot at the China Humanoid Robot Conference in Seoul in March. Robots are back in the national spotlight, and this time, the conversation is about more than what they can do. It’s about who controls them and what data…
-
FCC robot restrictions could accelerate shift to local AI
The Robot Report
A Unitree humanoid robot at the China Humanoid Robot Conference in Seoul in March. Robots are back in the national spotlight, and this time, the conversation is about more than what they can do. It’s about who controls them and what data…
-
SocialVLA: A Social Perception Gateway for Human-Reaction-Based Failure Detection and Recovery in VLA Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02360v1 Announce Type: new Abstract: Vision-language-action (VLA) policies enable diverse robotic manipulation but can fail during execution without recognizing their own errors. Human observers provide complementary signals, as…
-
SceneFactory-3D: Lifting 2D Traffic Scenes into 3D Physical Counterfactuals for Scalable Physically Grounded Safety Evaluation
arXiv cs.RO (Robotics)
arXiv:2610.02874v1 Announce Type: new Abstract: Scalable driving simulators typically execute vehicle commands using prescribed behavioral or kinematic rules, overlooking the physics of tire-road interfaces, thereby limiting their ability…
-
World Action Modeling with Progressive Visual Planning
arXiv cs.RO (Robotics)
arXiv:2610.02508v1 Announce Type: cross Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an initial observation and instruction…
-
S2M-Trek: From Single to Multi-Sphere Transport via Per-Frame Deep Sets on a Wheel-Legged Robot
arXiv cs.RO (Robotics)
arXiv:2606.01332v2 Announce Type: replace Abstract: We study the problem of scaling dynamic loco-manipulation from a single free-rolling sphere to multiple spheres transported simultaneously on the back of a wheel-legged quadruped, without…
-
AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness
arXiv cs.RO (Robotics)
arXiv:2606.10577v3 Announce Type: replace Abstract: Zero-shot vision-and-language navigation in continuous environments (VLN-CE) has recently become feasible with large vision-language models (VLMs). Existing methods typically rely on…
-
Uncertainty Quantification for Flow-Based Generalist Robot Policies
arXiv cs.RO (Robotics)
arXiv:2606.18043v2 Announce Type: replace Abstract: Generalist robot policies, such as vision-language-action models (VLAs) and world-action models (WAMs), combine powerful pretrained backbones with expressive generative action heads…
-
AR-WAM: A Visual-Conditioned Agent-Ready World Action Model for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.23578v2 Announce Type: replace Abstract: As AI agents become increasingly capable, agent-driven robotic control is emerging as a compelling paradigm. However, prevailing vision-language-action (VLA) models and world action…
-
AGT-CV: An Aerial-Ground Team Cross-View Dataset for Heterogeneous Robot Teams in Unstructured Environments
arXiv cs.RO (Robotics)
arXiv:2605.06478v2 Announce Type: replace Abstract: Heterogeneous air-ground robot teams combine complementary sensing modalities, mobility characteristics, and spatial viewpoints that can significantly enhance perception in complex…
-
FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid
arXiv cs.RO (Robotics)
arXiv:2603.08961v3 Announce Type: replace Abstract: Maintaining balance under external hand forces is critical for humanoid bimanual manipulation, where interaction forces propagate through the kinematic chain and constrain the feasible…
-
FastOPD: On-Policy Distillation for Lightweight VLA Deployment
arXiv cs.RO (Robotics)
arXiv:2610.02832v1 Announce Type: new Abstract: Vision-Language-Action (VLA) foundation models have scaled rapidly to enhance manipulation performance and generalizability, but this scaling incurs high computational costs that render…
-
Equivariant Visual-Tactile Diffusion Policy for Contact-Rich Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.03333v1 Announce Type: new Abstract: Imitation learning for contact-rich manipulation requires high-quality expert data that is expensive to obtain. This makes learning a sample-efficient policy a key issue. To address this, we…
-
MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.03476v1 Announce Type: new Abstract: Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and arm control. While recent…
-
OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
arXiv cs.RO (Robotics)
arXiv:2610.03015v1 Announce Type: cross Abstract: Accurate 3D detection is essential for mobile embodied agents, while Vision Foundation Models (VFMs) offer transferable visual and geometric priors. Yet existing VFM-based 3D detectors rely…
-
A Learning-Free Characterization Framework for the Resilience and Sensitivity of Polyurethane Vision-Based Tactile Sensors
arXiv cs.RO (Robotics)
arXiv:2511.07797v3 Announce Type: replace Abstract: Vision-based tactile sensors (VBTSs) are a promising technology for robots, providing them with dense signals that can be translated into a multi-faceted understanding of contact…
-
TimelyDAgger: Timing-Aware Expert Querying for VLA Policy Improvement
arXiv cs.RO (Robotics)
arXiv:2609.33157v2 Announce Type: replace Abstract: DAgger improves robot policies by aggregating expert supervision from states visited during policy execution. Robot-gated DAgger automates expert queries, allowing the robot to decide…
-
Move-Then-Operate: Behavioral Phasing for Human-Like Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2604.23620v3 Announce Type: replace Abstract: We present Move-Then-Operate, a Vision language action framework that explicitly decouples robotic manipulation into two distinct behavioral phases: coarse relocation (move) and…
-
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
arXiv cs.RO (Robotics)
arXiv:2610.02697v1 Announce Type: new Abstract: Recent vision-and-language navigation (VLN) systems increasingly adopt streaming Video-LLM policies that map egocentric RGB observations and instructions directly to low-level actions. Yet…
-
LLA-MPC on Embedded Hardware: Rapid Adaptive Control with Thousands of Parallel Models
arXiv cs.RO (Robotics)
arXiv:2610.03616v1 Announce Type: new Abstract: We present a generalized implementation of Look-Back and Look-Ahead Adaptive Model Predictive Control (LLA-MPC), a learning-free framework for real-time, rapid adaptive system identification…
-
Novelty Adaptation Through Hybrid Large Language Model (LLM)-Symbolic Planning and LLM-guided Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2603.11351v3 Announce Type: replace Abstract: In dynamic open-world environments, autonomous agents often encounter novelties that hinder their ability to find plans to achieve their goals. Specifically, traditional symbolic planners…
-
CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor Environments
arXiv cs.RO (Robotics)
arXiv:2610.03031v1 Announce Type: cross Abstract: Monocular semantic scene completion (SSC) for quadruped robots remains underexplored in real crowded indoor environments, where human-scene occlusion disrupts static geometry and human…
-
Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions
arXiv cs.RO (Robotics)
arXiv:2610.02662v1 Announce Type: cross Abstract: Language-enabled robot systems increasingly combine semantic-graph planning with temporal-logic safety monitors. We investigate a trace-completeness assumption in these systems: whether the…
-
Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models
arXiv cs.RO (Robotics)
arXiv:2610.03498v1 Announce Type: new Abstract: Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains poorly understood which…
-
A Change of Frame Makes the Capture Point Proprioceptive: Distillation-Free Humanoid Single-Leg Balance
arXiv cs.RO (Robotics)
arXiv:2608.00500v3 Announce Type: replace Abstract: Unified humanoid policies track agile whole-body motion, yet few can hold a clean single-leg stance. On the single-leg balance benchmark introduced here, eight released state-of-the-art…
-
VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.02801v1 Announce Type: cross Abstract: Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades substantially under unseen visual…
-
UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.03620v1 Announce Type: cross Abstract: Online reinforcement learning (RL) enables robot policies to improve through physical interaction, but the assistance they require changes as their competence evolves. Existing intervention…
-
Awomo-SimDataEngine: Agentic Simulation-ReadyWorld Generation
arXiv cs.RO (Robotics)
arXiv:2610.02274v1 Announce Type: new Abstract: Generating useful robot-training data requires more than visually plausiblescenes: objects must support interaction, placements must remain physicallyvalid, and tasks must admit repeatable…
-
Autonomous Robotic Navigation for Endovascular Brain-Computer Interface Access
arXiv cs.RO (Robotics)
arXiv:2610.03537v1 Announce Type: new Abstract: Endovascular brain-computer interfaces (BCIs) avoid craniotomy but require precise device delivery through anatomically variable cerebral veins. This work presents the first demonstration of…
-
RATE: Risk-Aware Tactile Encoding for Contact-rich Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.03538v1 Announce Type: new Abstract: Tactile sensing is particularly valuable for contact-rich robotic manipulation. Recent work has made substantial progress in tactile representation learning for robotic manipulation. However…
-
A Unified Framework for Empowerment and Predictive Control
arXiv cs.RO (Robotics)
arXiv:2610.03563v1 Announce Type: new Abstract: Sampling-based model predictive control (MPC) is a powerful approach to trajectory optimization, but its performance depends on an informative cost function that often requires substantial…
-
Query-Conditioned Articulation Estimation from a Single Image
arXiv cs.RO (Robotics)
arXiv:2610.01726v2 Announce Type: replace Abstract: Enabling robots to estimate the kinematic parameters of articulated objects unlocks a wide range of capabilities for interaction and manipulation. The estimation has to happen from the…
-
WAM-OPD: Joint Video-Action Supervision for World Action Model Post-Training with On-Policy Distillation
arXiv cs.RO (Robotics)
arXiv:2608.22364v2 Announce Type: replace-cross Abstract: World Action Models (WAMs) generate both future video and robot actions, offering two connected outputs for post-training supervision. How can a pretrained WAM learn from a stronger…
-
Around the World: Unified Learned Locomotion on a 270 g Continuous-Rotation Quadruped
arXiv cs.RO (Robotics)
arXiv:2610.02728v1 Announce Type: new Abstract: Closed-loop learned locomotion is established on commercial quadrupeds but remains uncommon at the sub-kilogram scale. Continuous-rotation legs give MiNI-Q, a 270 g quadruped, access to…
-
MixVLA: Adaptive Mixing of Non-Invariant Information for Generalizable Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.02898v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have achieved remarkable advances in robotic manipulation, yet their zero-shot generalization under out-of-distribution (OOD) conditions remains limited…
-
Co-design Gym: A Unified Benchmark for Embodiment-Policy Co-optimization
arXiv cs.RO (Robotics)
arXiv:2610.02366v1 Announce Type: cross Abstract: Finding an optimal behaviour policy within a given environment is a widely studied problem in domains as diverse as games, robotics, energy infrastructure, communication networks, and…
-
Retrospective Open-Vocabulary Memory for Long-Term Object Search
arXiv cs.RO (Robotics)
arXiv:2610.00330v2 Announce Type: replace Abstract: Long-term object search requires learning where objects usually appear from repeated but uneven observations of a changing environment. We formulate retrospective open-vocabulary memory…
-
Coding Agents with Harness for Safe Robot Control
arXiv cs.RO (Robotics)
arXiv:2609.20822v2 Announce Type: replace Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots…
-
Screw Attention: Rigid-Body Algebra Inside a Transformer
arXiv cs.RO (Robotics)
arXiv:2610.00904v2 Announce Type: replace Abstract: Learned manipulation policies rediscover from data the spatial relations that rigid-body mechanics supplies in closed form, which leaves them fragile to geometric change. We present Screw…
-
DeltaWorld: Physically Consistent Interactive World Simulators via Action-Conditioned Latent Increment Learning
arXiv cs.RO (Robotics)
arXiv:2610.02691v1 Announce Type: new Abstract: Interactive world simulators can provide scalable environments for robot planning, policy training, and evaluation by predicting action consequences while reducing reliance on repeated…
-
Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2610.02765v1 Announce Type: new Abstract: Monitoring planned driving trajectories requires accurately estimating the collision likelihood with actors whose motion is itself impacted by the ego motion. Existing classical approaches…
-
Skill2Real: Agentic Skill Learning for Zero-Shot Sim-to-Real Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02788v1 Announce Type: new Abstract: Transferring robotic skills from simulation to reality requires task knowledge that remains usable across differences in perception, dynamics, and embodiment. We introduce Skill2Real, an…
-
From Language Priors to Field Adaptation: Preference Learning for Traversability Estimation
arXiv cs.RO (Robotics)
arXiv:2610.02974v1 Announce Type: new Abstract: Image-based traversability estimation is inherently dependent on the robot platform, deployment domain, and mission preferences, which limits the applicability of purpose-trained models. To…
-
KungfuAthleteBot: learning high-dynamic humanoid motion from video with unified robust recovery
arXiv cs.RO (Robotics)
arXiv:2610.03388v1 Announce Type: new Abstract: Video is an abundant, inexpensive source of human motion data that is rich in extreme athletic behaviors. Making it usable for humanoid robots, however, is not a matter of simply retargeting…
-
EgoAlign: Bridging the Human-Humanoid Gap for Long-Range Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.38046v3 Announce Type: replace Abstract: Egocentric human demonstrations offer an accessible source of task experience, but differences in body scale and controller response, together with missing robot states, limit their value…
-
Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.03395v1 Announce Type: cross Abstract: Long-horizon tasks with sparse rewards pose an exploration bottleneck for goal-conditioned reinforcement learning: a policy started from the initial state rarely reaches the goal and…
-
LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World Models
arXiv cs.RO (Robotics)
arXiv:2609.14073v2 Announce Type: replace-cross Abstract: Counterfactual world models (CWM) extract motion from pretrained video predictors by comparing factual and intervened predictions, but uniform aggregation weights responses equally…
-
Modelling and Model-Checking a ROS2 Multi-Robot System using Timed Rebeca
arXiv cs.RO (Robotics)
arXiv:2511.15227v3 Announce Type: replace Abstract: Model-based development accelerates prototyping, enables earlier experimentation, and ensures rigorous validation of system design intents. In multi-agent systems with complex…
-
Real-Time sEMG-Based Telecontrol of an Assistive Robotic Arm Using a 1D Convolutional Neural Network
arXiv cs.RO (Robotics)
arXiv:2607.16310v2 Announce Type: replace Abstract: Motor impairments affecting the upper limb significantly reduce autonomy in daily activities, particularly for tasks involving object manipulation. Assistive robotic arms offer a…
-
World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2608.05369v2 Announce Type: replace Abstract: Vision-language-action (VLA) models often treat main-view and wrist-view observations as parallel visual inputs, overlooking their distinct roles in robot manipulation. Fine-grained…
-
Learning Low-Frequency Motion Control for Robust and Dynamic Robot Locomotion
arXiv cs.RO (Robotics)
arXiv:2209.14887v3 Announce Type: replace Abstract: Robotic locomotion is often approached with the goal of maximizing robustness and reactivity by increasing motion control frequency. We challenge this intuitive notion by demonstrating…
-
Filter-Aware Fine-Tuning for Safe Humanoid Whole-Body Tracking
arXiv cs.RO (Robotics)
arXiv:2610.02341v1 Announce Type: new Abstract: Safe whole-body motion is essential for deploying humanoid robots in unstructured environments. Modern humanoid control commonly separates reference specification from execution, with a…
-
Rethinking World-Action Model for Compositional and In-Context Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02368v1 Announce Type: new Abstract: Long-horizon compositional manipulation has become increasingly important for real-world robot deployment, where a single task involves multiple coordinated subtasks. Existing world-action…
-
Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.02398v1 Announce Type: new Abstract: A robot demonstration records two things in the same frames: what happened to the objects, and how one particular arm made it happen. We condition on the first. A demonstration is compiled…
-
Who Went Where When on the Lunar Surface: Forensic Trajectory Analysis to Identify Byzantine Rovers
arXiv cs.RO (Robotics)
arXiv:2610.02694v1 Announce Type: new Abstract: Future planetary surface missions are likely to involve multiple independently operated rovers sharing the same deployment region, raising the need to verify compliance with operational…
-
RoboBridge: A Self-Evolving Embodied Agent Framework for Sim-to-Real Transfer
arXiv cs.RO (Robotics)
arXiv:2610.02717v1 Announce Type: new Abstract: A key challenge in bringing embodied intelligence into the real world is transferring capabilities from simulation to reality and enabling agents to continually adapt after deployment…
-
I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision Geometry
arXiv cs.RO (Robotics)
arXiv:2610.03453v1 Announce Type: new Abstract: Physics simulators and motion planners require convex collision geometry, yet image-to-3D generative models output dense, frequently non-manifold visual meshes. Bridging the two today takes a…
-
Native Action-Prior Learning from Videos for World Action Models
arXiv cs.RO (Robotics)
arXiv:2610.03391v1 Announce Type: cross Abstract: World action models integrate future visual dynamics with robot action prediction, but their scalability remains limited by the need for action-annotated robot trajectories…
-
GlowTact: Simple and Compact Vision-Based Tactile Sensing with High Sensitivity and Spatial Resolution
arXiv cs.RO (Robotics)
arXiv:2609.32471v2 Announce Type: replace Abstract: Vision-based tactile sensors (VBTS) provide rich contact information for robotic manipulation, but existing designs can be hard to simplify and adapt to the size and constraints of…
-
World Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models
arXiv cs.RO (Robotics)
arXiv:2607.27599v2 Announce Type: replace-cross Abstract: Building generalizable robot agents for diverse applications remains a fundamental challenge. While imitation learning-based policies can perform well in familiar training…
-
Multi-Fidelity Policy Gradients Stabilize Data-Scarce Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.02505v1 Announce Type: cross Abstract: Policy gradient methods for on-policy reinforcement learning (RL) can become unstable when expensive, scarce target-domain data yield noisy gradient estimates. We address this challenge by…
-
ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2606.17011v2 Announce Type: replace Abstract: Human interventions provide crucial corrective signals for post-training Vision-Language-Action (VLA) models. However, enabling seamless humanoid interventions is a formidable systems…
-
EmbPASS: Towards Cross-Embodiment Open Panoramic Segmentation
arXiv cs.RO (Robotics)
arXiv:2610.03248v1 Announce Type: cross Abstract: Panoramic images provide a complete 360-degree field of view, enabling comprehensive scene understanding for embodied perception. However, heterogeneous embodied platforms exhibit…
-
Self-Repairing Recurrent Ensembles for Real-Time Recovery from Distribution Shift
arXiv cs.RO (Robotics)
arXiv:2610.03249v1 Announce Type: cross Abstract: Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulating measurement noise all induce a…
-
Toward Controlling Biology with Language:Offline Learning of Prompt-Conditioned Interventions for Cells, Organoids, and Biobots
arXiv cs.RO (Robotics)
arXiv:2610.02247v1 Announce Type: cross Abstract: Artificial intelligence increasingly serves as a natural-language interface to complex technical systems, letting people accomplish sophisticated tasks by describing what they want rather…
-
How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement Learning
arXiv cs.RO (Robotics)
arXiv:2610.03119v1 Announce Type: cross Abstract: In lifelong reinforcement learning, retaining previously learned policies is not sufficient for effective transfer to a new task. Useful knowledge may be distributed across several prior…
-
Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis
arXiv cs.RO (Robotics)
arXiv:2610.03717v1 Announce Type: cross Abstract: This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene structure, thereby enabling transferable…
-
Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes
arXiv cs.RO (Robotics)
arXiv:2605.00121v2 Announce Type: replace Abstract: We have seen tremendous recent progress in our ability to build "spatio-semantic" representations that enable robots to perform complex reasoning across geometry and semantics. However…
-
SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2606.00773v3 Announce Type: replace Abstract: Vision-language-action (VLA) benchmarks measure whether a policy completes a requested manipulation task, but binary success can hide safety violations along the trajectory: a policy may…
-
A Biomimetic Myoelectric Tentacle Prosthesis with Sensorless Object Detection and Vibrotactile Feedback
arXiv cs.RO (Robotics)
arXiv:2607.09807v4 Announce Type: replace Abstract: This paper presents the design and evaluation of a myoelectric tentacle-shaped prosthesis integrating electromyographic (EMG) control, sensorless object detection, and vibrotactile…
-
SABER: Learning Attention-based Semantic Affordance for Legged Locomotion
arXiv cs.RO (Robotics)
arXiv:2609.21572v2 Announce Type: replace Abstract: Perceptive legged locomotion has advanced rapidly by integrating terrain geometry into learned policies, yet the integration of terrain meaning remains sparse: a pipe, a patch of grass…
-
A Passive AI System for Verifying Physical State on Automated Liquid Handlers
arXiv cs.RO (Robotics)
arXiv:2610.02668v1 Announce Type: new Abstract: Automated liquid handlers execute digital protocols, but operators must assemble the deck and confirm that the physical setup matches the intended experiment. We present the Labware Setup…
-
Beyond Reward Hacking: Proxy Divergence Across Four Layers of a Staged Humanoid Learning Pipeline
arXiv cs.RO (Robotics)
arXiv:2610.03196v1 Announce Type: new Abstract: A reinforcement-learning (RL) pipeline for a legged robot is assembled from proxies. A reward stands in for intended behaviour, a curriculum gate stands in for competence, an evaluation…
-
OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies
arXiv cs.RO (Robotics)
arXiv:2610.02459v1 Announce Type: new Abstract: Coding agents are extending their reach into the physical world by writing and executing robot control programs. One might expect the agents to use the existing mature software stack that…
-
DR-IPC: Disturbance-Resilient Integrated Planning and Control for LiDAR-Based Quadrotor Navigation
arXiv cs.RO (Robotics)
arXiv:2610.03530v1 Announce Type: new Abstract: LiDAR-based quadrotor navigation in cluttered environments remains challenging under external disturbances, particularly when obstacle-aware motion generation and disturbance-rejection…
-
RUL-Aware RRT*: Degradation-Balanced Motion Planning for Robotic Manipulators
arXiv cs.RO (Robotics)
arXiv:2610.02469v1 Announce Type: new Abstract: Robotic manipulators operating over long durations often experience uneven joint degradation, which causes the weakest actuator to fail prematurely, leads to unplanned downtime, and results…
-
Learning Reflexive Behavior for Contact-Rich Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02811v1 Announce Type: new Abstract: During contact-rich manipulation, interactions between a robot and its environment carry information about local geometry: a surface prevents penetration, a bore guides a peg. A controller…
-
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
arXiv cs.RO (Robotics)
arXiv:2610.03710v1 Announce Type: new Abstract: Inspired by human vision, we introduce a framework using active gaze to enable fine-grained bimanual manipulation with only a single stereo camera. EyeRobot 2.0 physically attends to a 3D…
-
Fewer Tokens, Better Action: GPT-6 Astra Robot Agents with 14% Higher Success Rate but 65% Fewer Tokens
arXiv cs.RO (Robotics)
arXiv:2610.01939v1 Announce Type: cross Abstract: Vision language model (VLM) agents can control robots through visual feedback and action primitives, but repeated model invocations and redundant observations incur substantial token…
-
SARI: Phase-Split Sim-Real Co-Training for Contact-Rich Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02804v1 Announce Type: new Abstract: Vision-language-action (VLA) models often require costly real-world demonstrations to adapt to contact-rich manipulation tasks, particularly when generalization across object placements is…
-
Network-in-the-Loop at Scale: GPU-Batched 5G Simulation for Massively Parallel Robot Learning
arXiv cs.RO (Robotics)
arXiv:2610.02370v1 Announce Type: cross Abstract: Massively parallel GPU simulators train multi-robot policies in thousands of environments, and many fleets use private Fifth-Generation (5G) networks, where each robot's delay depends on…
-
Safe and Robust Neural Policy Learning with Statistical Verification for Sim-to-Real Deployment in Robotics
arXiv cs.RO (Robotics)
arXiv:2608.06481v2 Announce Type: replace Abstract: Synthesizing safe and robust neural controllers in simulation for reliable sim-to-real deployment remains a critical challenge in robotics. Existing learning-based methods typically lack…
-
Find Something You Can't Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA Models
arXiv cs.RO (Robotics)
arXiv:2609.32069v2 Announce Type: replace Abstract: Vision--language--action (VLA) models provide strong priors for robotic manipulation but are typically deployed as frozen policies, unable to improve from their own failures. Real-world…
-
Tactile Curiosity Drives Robot Interaction
arXiv cs.RO (Robotics)
arXiv:2609.40134v2 Announce Type: replace Abstract: Mastering robot manipulation skills via reinforcement learning (RL) remains largely sample-inefficient. The most common RL algorithms rely on random action sampling to discover new…
-
WB-WAM: Heterogeneous Body-Hand Pre-training for Humanoid Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.34199v3 Announce Type: replace Abstract: Humanoid loco-manipulation demands coordinated body and hand behavior, while conventional robot pre-training data provide limited coverage of such whole-body motion. We present WB-WAM, a…
-
Closing the Train-Test Gap in World Models for Gradient-Based Planning
arXiv cs.RO (Robotics)
arXiv:2512.09929v2 Announce Type: replace-cross Abstract: World models paired with model predictive control (MPC) can be trained offline on large-scale datasets of expert trajectories and enable generalization to a wide range of planning…
-
Spectral Alignment in Forward-Backward Representations via Temporal Abstraction
arXiv cs.RO (Robotics)
arXiv:2603.20103v4 Announce Type: replace-cross Abstract: Forward-backward (FB) representations provide a powerful framework for learning the successor representation (SR) in continuous spaces by enforcing a low-rank factorization…
-
LOCUS: Landmark-Oriented Container Discrimination Using Spatial Graphs
arXiv cs.RO (Robotics)
arXiv:2610.02803v1 Announce Type: new Abstract: As robots are increasingly deployed in unstructured, real-world environments, the ability to reason about complex spatial and semantic relationships among objects remains a fundamental…
-
Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution Dynamics
arXiv cs.RO (Robotics)
arXiv:2610.03132v1 Announce Type: new Abstract: Generative planners based on diffusion/flow matching can learn to synthesize long-horizon trajectories from demonstrations. However, real-world deployment requires (i) enforcing safety…
-
AVL-JEPA: Preventing Causal Dynamics Information Collapse In Joint Embedding Predictive Architecture World Models
arXiv cs.RO (Robotics)
arXiv:2610.03587v1 Announce Type: new Abstract: Joint embedding predictive architectures (JEPAs) predict future latent representations without reconstructing observations, enabling world models to focus on high-level semantic dynamics…
-
GlanceWAM: Sparse Test-Time Imagination for World-Action Models
arXiv cs.RO (Robotics)
arXiv:2608.23927v2 Announce Type: cross Abstract: Video generative models provide rich physical priors for robot learning, yet existing world-action models (WAMs) face a fundamental trade-off: synchronous video generation at control rate…
-
Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
arXiv cs.RO (Robotics)
arXiv:2610.02554v1 Announce Type: cross Abstract: Offline multi-agent reinforcement learning (MARL) faces a persistent trade-off. Expressive generative policies can represent multi-modal coordination in the data, but cannot distinguish…
-
Accurate Open-Loop Control of a Soft Continuum Robot Using Visually Learned Latent Dynamics
arXiv cs.RO (Robotics)
arXiv:2603.19655v2 Announce Type: replace Abstract: This work addresses open-loop control of a soft continuum robot (SCR) from video-learned latent dynamics. Visual Oscillator Networks (VONs) from previous work are used, which provide…
-
APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
arXiv cs.RO (Robotics)
arXiv:2606.12366v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models that couple pretrained Vision-Language Models (VLMs) with continuous action experts have achieved strong manipulation performance, yet generalization…
-
TouchTherm: Building Multimodal Digital Twins of Objects for Tactile and Thermal Rendering
arXiv cs.RO (Robotics)
arXiv:2610.01943v2 Announce Type: replace Abstract: Robotic simulation and virtual reality increasingly require object assets that capture not only visual geometry but also the physical cues underlying tactile and thermal interaction…
-
Subject-Specific Predictive Musculoskeletal Simulations of Lower-Limb Exoskeleton Assistance: Metabolic and Biomechanical Effects of Joint Assistance Strategies
arXiv cs.RO (Robotics)
arXiv:2610.02991v1 Announce Type: new Abstract: Lower-limb exoskeletons have made considerable progress in reducing energy expenditure during walking. However, designing optimal assistance strategies remains challenging, particularly given…
-
DexJoCo-X: Benchmarking Action Representations for Multi-Hand Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.03278v1 Announce Type: new Abstract: As dexterous hands proliferate, collecting data and training policies separately for every morphology becomes increasingly impractical. Scalable cross-embodiment learning therefore requires a…
-
On Representational Alignment among Embodied Agents
arXiv cs.RO (Robotics)
arXiv:2610.02985v1 Announce Type: new Abstract: Embodied agents interacting with the same physical process may maintain heterogeneous, asynchronous, and observer-relative representations. Rather than assuming that such representations…
-
CORNAV: Construction-Aware Reasoning for Robot Navigation on Active Worksites
arXiv cs.RO (Robotics)
arXiv:2610.03622v1 Announce Type: new Abstract: The construction industry faces persistent labor shortages, low productivity that costs the global economy over $1.6 trillion annually, and one of the highest injury rates among major…
-
CSIR: Contextually and Socially Informed Robots for Efficient Person Goal Navigation
arXiv cs.RO (Robotics)
arXiv:2610.02750v1 Announce Type: new Abstract: We address the Person Goal Navigation (PersonNav) problem, enabling robots to search for people under realistic constraints on information accessibility and language uncertainty. This tackles…
-
RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real Time
arXiv cs.RO (Robotics)
arXiv:2610.03013v1 Announce Type: cross Abstract: Category-level object pose estimation predicts the rotation, translation, and metric size of unseen instances within known categories. Many accurate RGB-D methods rely on external instance…
-
Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation
arXiv cs.RO (Robotics)
arXiv:2605.02227v2 Announce Type: replace Abstract: Long-term semantic navigation requires a robot to reuse past observations after appearance and scene change, but semantic memories are only useful if the robot can relocalize into the…
-
Autonomous mobile robot operations logistics: a dataset of jobs, dispatch events and robot states
arXiv cs.RO (Robotics)
arXiv:2610.02428v1 Announce Type: new Abstract: Autonomous mobile robots (AMRs) increasingly perform material transport in production logistics, where their operation is governed by job generation, dispatching and robot control. We present…
-
SoTa: Soft Tactile Skins for Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02338v1 Announce Type: new Abstract: A growing body of work suggests that tactile sensing gives robot policies contact information that complements vision in dexterous manipulation. However, visuo-tactile robot data remains…
-
CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization
arXiv cs.RO (Robotics)
arXiv:2610.02527v1 Announce Type: new Abstract: Learned visual reward models are increasingly used to optimize robot policies, yet a reward model can score an execution that acts on the wrong object as highly as one that completes the…
-
Real-time Event-camera Stereo Visual Odometry via Keytime Gaussian Process Regression
arXiv cs.RO (Robotics)
arXiv:2610.02601v1 Announce Type: new Abstract: Event cameras have microsecond-level temporal resolution and high dynamic range which make them more resilient to motion blur and poor illumination than standard frame-based cameras…
-
Register-Routed Delayed Fusion: Rewiring Shortcut-Prone Observation Fusion in Visuomotor Imitation
arXiv cs.RO (Robotics)
arXiv:2610.02813v1 Announce Type: new Abstract: Visuomotor imitation policies combine high-dimensional visual observations with compact signals such as proprioception, and their fusion topology determines when and through which tokens…
-
HexVIO: Towards All-Day Stereo-Inertial Tracking Through Commodity DSPs
arXiv cs.RO (Robotics)
arXiv:2610.03283v1 Announce Type: new Abstract: The ability of a device to localize itself within its surroundings is a fundamental prerequisite for spatial computing. Visual-inertial odometry (VIO) has proven to be a cost-effective and…
-
RoboChemGym: A Protocol-Driven Generative Simulation Framework for Long-Horizon Chemical Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02708v1 Announce Type: new Abstract: Wet-lab experimentation serves as the gold standard for hypothesis verification in scientific discovery; yet it is inherently labor-intensive, costly, and safety-critical. Embodied agents…
-
AdaTempo: Learning Shared Relative Tempo from Demonstrations for Faster Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02706v1 Announce Type: new Abstract: Visuomotor policies trained via imitation learning often inherit the unnecessarily slow timing of teleoperated demonstrations. Yet uniform speedup is unreliable because different phases of a…
-
Proprioceptive Sketches as Long-Horizon Intent for Generative Action Policies
arXiv cs.RO (Robotics)
arXiv:2610.02759v1 Announce Type: new Abstract: Generative robot policies predict short action chunks but lack explicit long-horizon intent. Recent methods expose longer-horizon structure through language plans, subgoal images, or video…
-
Communication-Aware Robot Execution for Cloud Inference under Spatially Heterogeneous Connectivity
arXiv cs.RO (Robotics)
arXiv:2606.31497v2 Announce Type: replace Abstract: Cloud-hosted foundation models enable robots to use semantic reasoning beyond onboard computational limits. In this setting, the robot executes a currently available primitive generated…
-
DriftWorld: Fast World Modeling through Drifting
arXiv cs.RO (Robotics)
arXiv:2607.15065v3 Announce Type: replace Abstract: Predictive world models enable robots to simulate the visual outcomes of their actions, but state-of-the-art diffusion-based models remain costly because generating each rollout requires…
-
WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning
arXiv cs.RO (Robotics)
arXiv:2608.22591v3 Announce Type: replace Abstract: Vision-language-action policies inherit both capabilities and input representations from pretrained vision-language models, showing great potential for robotic manipulation across diverse…
-
ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models
arXiv cs.RO (Robotics)
arXiv:2608.25572v2 Announce Type: replace Abstract: Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors under new task and scene…
-
ManiPhysicsBench: Physics-Based Assessment of Object Preservation in VLA Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02802v1 Announce Type: new Abstract: Vision-language-action (VLA) models aim to perform diverse manipulation tasks, but task success in existing rigid-body benchmarks does not indicate whether they preserve objects. We introduce…
-
PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.02840v1 Announce Type: new Abstract: World action models jointly learn to forecast world dynamics and predict robot actions, such that the learned internal world dynamics guide accurate actions. Existing approaches typically…
-
XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation
arXiv cs.RO (Robotics)
arXiv:2610.03516v1 Announce Type: new Abstract: World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and action based future prediction does not…
-
NEEDLEWORK: Offline Rewriting of Robot Data with Verified Local Stitches
arXiv cs.RO (Robotics)
arXiv:2610.02339v1 Announce Type: new Abstract: Robot demonstrations may contain useful behavior even when individual episodes are inefficient or unsuccessful. Trajectory stitching offers a way to compose these behaviors into improved…
-
SimpleTouch: Can Vision-Language-Action Models Master Contact-Rich Manipulation Without Tactile Policy Pretraining?
arXiv cs.RO (Robotics)
arXiv:2610.02784v1 Announce Type: new Abstract: Tactile sensing provides essential contact information for robotic manipulation, yet incorporating it into pretrained vision-language-action (VLA) models remains challenging. A common concern…
-
World Action Learning via Interaction-Centric Spectral Latent Guidance
arXiv cs.RO (Robotics)
arXiv:2610.03607v1 Announce Type: new Abstract: Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstrations remains expensive and difficult to scale. Egocentric videos offer…
-
Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer Policies
arXiv cs.RO (Robotics)
arXiv:2610.02848v1 Announce Type: new Abstract: Transformer policies are attractive for multi-agent robot learning because self-attention can model interactions among agents. However, multi-agent teams are unordered, while transformers…
-
Bridging Frontier Reasoning and Robot Execution: From Autonomous Demonstration Generation to Dense Language Supervision
arXiv cs.RO (Robotics)
arXiv:2610.03615v1 Announce Type: new Abstract: Recent advances in frontier models enable robot manipulation from only a few demonstrations, but high inference latency limits their use for real-time robot control. To bridge this gap, we…
-
FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized Adapters
arXiv cs.RO (Robotics)
arXiv:2610.02799v1 Announce Type: cross Abstract: Fisheye cameras give mobile robots a single-sensor, low-cost view of their surroundings, yet the COCO-pretrained detectors that practitioners routinely reuse fail on them: strong radial…
-
World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.02323v1 Announce Type: new Abstract: Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As this source is conditioned on neither recent…