Robotics & Automation
Robotics & Automation news — Wednesday 21 October 2026
130 stories from 3 sources, every one in English. Each links to its publisher.
-
AGCO to deploy Agility Digit humanoid in Kansas factory
Robotics Business Review
The news comes as Agility inches closer to its IPO via SPAC and after it announced the latest version of Digit. | Source: Agility Robotics AGCO and Agility Robotics have signed a commercial agreement to deploy Agility’s Digit humanoid in…
-
AGCO to deploy Agility Digit humanoid in Kansas factory
The Robot Report
The news comes as Agility inches closer to its IPO via SPAC and after it announced the latest version of Digit. | Source: Agility Robotics AGCO and Agility Robotics have signed a commercial agreement to deploy Agility’s Digit humanoid in…
-
A guide to Day 2 of RoboBusiness 2026
The Robot Report
Deepu Talla, NVIDIA’s VP of robotics and edge AI, gave the opening talk at RoboBusiness 2025. RoboBusiness 2026 will come to an end today. After a packed first day of the 20th anniversary show, here is everything you need to know about Day…
-
A guide to Day 2 of RoboBusiness 2026
Robotics Business Review
Deepu Talla, NVIDIA’s VP of robotics and edge AI, gave the opening talk at RoboBusiness 2025. RoboBusiness 2026 will come to an end today. After a packed first day of the 20th anniversary show, here is everything you need to know about Day…
-
AgenticRoboRL: Bringing Coding-Agent Post-Training to Agentic Robotics
arXiv cs.RO (Robotics)
arXiv:2610.28589v1 Announce Type: new Abstract: Agentic robotics systems combine planners with robot harnesses to perform complex manipulation tasks. Recent work improves these systems through better harnesses and external memory, but…
-
Knowing When to Stop Thinking: A Dissection of Expected Free Energy as a Test-Time Compute Controller for Latent World-Model Planning
arXiv cs.RO (Robotics)
arXiv:2610.28011v1 Announce Type: new Abstract: A planner using a learned world model can improve its predicted outcome while choosing a worse action. We study when expected free energy (EFE) can help decide how much computation to spend…
-
Plausible Future, Wrong Choice: Steering World-Action Models toward Intended Future
arXiv cs.RO (Robotics)
arXiv:2610.28431v1 Announce Type: new Abstract: World-Action Models (WAMs) have emerged as a promising paradigm for embodied generalist policies by jointly modeling future world evolution and robot actions across diverse manipulation…
-
Physical Canvas: A Vision Tactile World Model For Robot Policy Evaluation And Learning
arXiv cs.RO (Robotics)
arXiv:2610.28613v1 Announce Type: new Abstract: Evaluating and post-training robot policies through physical interaction is costly and difficult to scale, motivating action-conditioned world models as interactive simulators. However…
-
High-Precision RCM Motion for Ophthalmic Robotics via Hierarchical QP Control and Authority-Guided Recovery Planning
arXiv cs.RO (Robotics)
arXiv:2610.27905v1 Announce Type: new Abstract: General-purpose manipulators can position ophthalmic instruments under a software Remote Centre of Motion (RCM). However, at some reachable configurations that are nonsingular for the tip…
-
Sensitivity-Orthogonal Residual Learning for Adaptive Sideslip and Cornering Stiffness Estimation
arXiv cs.RO (Robotics)
arXiv:2610.27586v1 Announce Type: new Abstract: Online adaptation of the cornering stiffness keeps a model-based sideslip estimator valid as tires change, but competes with learned model correction for the same filter innovation. A…
-
FIT-MAC: A Closed-Loop Multi-Agent Framework for Robust Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.28109v1 Announce Type: new Abstract: Vision-language-action (VLA) models have achieved strong performance on standard robotic manipulation benchmarks. However, their reliability can degrade substantially when task conditions…
-
Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
arXiv cs.RO (Robotics)
arXiv:2610.26914v1 Announce Type: cross Abstract: Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objectives, and to personalize their behavior to…
-
Gibson Env: Real-World Perception for Embodied Agents
arXiv cs.RO (Robotics)
arXiv:1808.10654v2 Announce Type: replace-cross Abstract: Developing visual perception models for active agents and sensorimotor control are cumbersome to be done in the physical world, as existing algorithms are too slow to efficiently…
-
Learning Tactile-Aware Hand Representations from Human Hand-Object Interaction Data
arXiv cs.RO (Robotics)
arXiv:2610.27995v1 Announce Type: new Abstract: Tactile representation learning for dexterous manipulation often requires substantial robot-side data collection, limiting its scalability across different hands and sensors. We explore…
-
FERPO: Forward Entropy-Regularized Policy Optimization
arXiv cs.RO (Robotics)
arXiv:2610.02198v2 Announce Type: replace-cross Abstract: Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using action gradients of a learned critic. However, critics are typically…
-
Embodied Task Agents Can Perform Fine Manipulation through Tactile In-Context Learning
arXiv cs.RO (Robotics)
arXiv:2610.27613v1 Announce Type: new Abstract: Can embodied task agents use tactile experience to perform fine manipulation without task-specific model training? We investigate this capability through Tactile-ETA, a system that…
-
Learning Adaptable Dexterous Skills via Hybrid Dexterous Mimicking
arXiv cs.RO (Robotics)
arXiv:2610.28628v1 Announce Type: new Abstract: Dexterous multi-finger hands hold promise to unlock diverse skills like functional grasps, in-hand reorientation, and dynamic handover that the human-designed world assumes, yet existing…
-
Robotic Physical Comparison of Biologically Motivated and Counterfactual Sensory Arrangements using Biomimetic Skin
arXiv cs.RO (Robotics)
arXiv:2610.26680v2 Announce Type: replace Abstract: Human skin contains diverse mechanoreceptors, including Merkel cells and Pacinian corpuscles, each localized in specific regions. Although their spatial organization is known to be shaped…
-
Visual Task Modeling and Automated Planning for Humanoid Robots in Education of Individuals with Autism Spectrum Disorder
arXiv cs.RO (Robotics)
arXiv:2610.27162v1 Announce Type: new Abstract: In robot-assisted education, a robot must understand how to complete a task in order to effectively guide a student through it. We present a novel method that enables a semi-autonomous…
-
Physical AI for Intralogistics: Benchmarking the NVIDIA Sim-to-Real Ecosystem for Cosmos-Enhanced COMPASS Navigation on Industrial Mobile Robots
arXiv cs.RO (Robotics)
arXiv:2610.28432v1 Announce Type: new Abstract: Classical robot navigation stacks are reliable but often require re-engineering for each new robot type and site. Learning-based navigation shifts this effort from hand-tuned parameters to…
-
Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates
arXiv cs.RO (Robotics)
arXiv:2610.27870v1 Announce Type: new Abstract: Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains difficult, particularly when unsafe regions…
-
Interruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary Overrides
arXiv cs.RO (Robotics)
arXiv:2610.28121v1 Announce Type: cross Abstract: Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability…
-
RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
arXiv cs.RO (Robotics)
arXiv:2610.27782v1 Announce Type: cross Abstract: Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal large…
-
EchoNav: Evidential BEV Completion from Historical Observations for Visual Navigation
arXiv cs.RO (Robotics)
arXiv:2610.27616v1 Announce Type: new Abstract: Visual navigation in cluttered environments requires robots to recover previously observed structure and infer obstacles and free space that remain occluded. We present a framework that…
-
DexGraspFlow: Topology-Aware SE(3) Flow Matching for Cross-Embodiment Dexterous Grasp Generation
arXiv cs.RO (Robotics)
arXiv:2610.26962v1 Announce Type: new Abstract: Differences in hand geometry, joint parameterization, and kinematic topology pose challenges for cross-embodiment dexterous grasp generation. However, spatial relations among links alone are…
-
Evaluating Social Reasoning in Embodied Vision-Language Models
arXiv cs.RO (Robotics)
arXiv:2610.27496v1 Announce Type: new Abstract: Foundation models now serve as reasoning layers for robot teams, but it remains unclear whether embodiment-specialized vision-language models (VLMs) preserve the social-reasoning capabilities…
-
Temporal Difference Learning of Probabilistic Reach-Avoid Value Functions
arXiv cs.RO (Robotics)
arXiv:2610.28106v1 Announce Type: new Abstract: Reach-avoid sets, defining the states from which a task can be completed while avoiding unsafe regions, are fundamental tools for deploying robots in environments subject to disturbances and…
-
Reasoning as a Distribution: Generative Plan Latents for Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.28166v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies increasingly reason before acting, but existing reasoning models compress this intermediate decision into a single representation. When several plans are…
-
Kamino: GPU-based Simulation of Rigid Multi-Body Physics with Kinematic Loops
arXiv cs.RO (Robotics)
arXiv:2603.16536v2 Announce Type: replace Abstract: We present Kamino, a GPU-based physics solver for massively parallel simulations of heterogeneous highly-coupled mechanical systems. Implemented in Python using NVIDIA Warp and integrated…
-
Replan for Error Recovery: Training Embodied VLMs through Verifiable Interaction with Action-Grouped Turn-GSPO
arXiv cs.RO (Robotics)
arXiv:2610.27003v1 Announce Type: new Abstract: Embodied VLMs can execute increasingly complex manipulation tasks, yet execution errors can leave the environment in states that require replanning for recovery. Existing recovery methods…
-
Embodied Playground: A Long-Horizon Agentic Robotics Benchmark for Physical, Strategic, and Spatial Reasoning
arXiv cs.RO (Robotics)
arXiv:2610.27039v1 Announce Type: new Abstract: Foundation models offer a promising basis for robotic agents, but long-horizon tasks require them to sustain coherent reasoning and reliable physical execution across interdependent stages…
-
ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models
arXiv cs.RO (Robotics)
arXiv:2610.27040v1 Announce Type: new Abstract: General-purpose multimodal models, including GPT-6 Astra and Claude Opus 5.5, demonstrate broad capabilities in embodied manipulation. Our analysis indicates that this generality is…
-
EmbodyHOI: Embodiment-Aware Generation of Hand-Object Interactions for Humanoid Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.27242v1 Announce Type: new Abstract: Humanoid dexterous manipulation needs reference motions that are both semantically rich and kinematically feasible for the target robot. Text-conditioned hand-object interaction (HOI)…
-
What Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.27277v1 Announce Type: new Abstract: Vision-language-action (VLA) models are sensitive to visual corruptions, but knowing that a corruption is typically harmful does not establish whether removing it would benefit the current…
-
RadGeoLoc: Radar Geolocalization via Particle Filtering
arXiv cs.RO (Robotics)
arXiv:2610.27310v1 Announce Type: new Abstract: In real-time autonomous field applications, GNSS is often unreliable and inaccurate. A possible solution is localizing against a prebuilt map like a satellite image, as it is georeferenced…
-
PLaCA: Learning Patch-Level Future Latent Change for Action Generation
arXiv cs.RO (Robotics)
arXiv:2610.27657v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models generate robot actions from visual observations and language instructions, but effective manipulation also requires anticipating how the environment will…
-
CovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal Navigation
arXiv cs.RO (Robotics)
arXiv:2610.27677v1 Announce Type: new Abstract: In object goal navigation (ObjectNav), an embodied agent must find a target object (e.g., "find a bed") in a previously unseen environment, relying on spatial commonsense such as object…
-
Adaptive Traversal Tubes for Posture-Aware Navigation of Bipedal Humanoids
arXiv cs.RO (Robotics)
arXiv:2610.27688v1 Announce Type: new Abstract: Bipedal humanoids can change their effective footprint by adjusting body yaw, enabling both narrow-passage traversal and socially aware yielding. This paper presents a posture-aware…
-
AWLS: Advantage-Weighted Latent Steering for One-Step Generative Robotic Manipulation Policies
arXiv cs.RO (Robotics)
arXiv:2610.27736v1 Announce Type: new Abstract: Human-collected real-world robotic manipulation demonstrations often contain mixed-quality trajectories, including hesitant, indirect, or inefficient action segments. While diffusion- and…
-
Multi-View Latent Action Pretraining for Cross-Embodiment Robot Learning from Videos
arXiv cs.RO (Robotics)
arXiv:2610.27794v1 Announce Type: new Abstract: Action-free videos are an appealing substitute for costly teleoperated data. Latent action models (LAMs) turn videos into a supervision signal by inferring abstract actions between frames…
-
RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.27861v1 Announce Type: new Abstract: Vision-language-action (VLA) robustness is commonly summarized by aggregate task success, which obscures how individual executions change under distribution shifts and where failures emerge…
-
Design and implementation of thermal control strategy for micro-size lunar exploration rover hakuto
arXiv cs.RO (Robotics)
arXiv:2610.28127v1 Announce Type: new Abstract: The research focuses on the thermal interface design of the HAKUTO Rover Flight Model (FM) and its evaluation using the final thermal vacuum experiment. Initially, an analytical thermal model…
-
Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot Fleets
arXiv cs.RO (Robotics)
arXiv:2610.28624v1 Announce Type: new Abstract: Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage…
-
Fast Motion Retargeting Pipeline for Scalable Humanoid Robot Learning
arXiv cs.RO (Robotics)
arXiv:2610.28470v1 Announce Type: new Abstract: While large-scale human motion capture datasets provide a rich source of demonstrations for humanoid robot learning, retargeting the diverse motions to different humanoid robots remains a…
-
SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model
arXiv cs.RO (Robotics)
arXiv:2610.28480v1 Announce Type: new Abstract: Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive. Current pipelines use…
-
VLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human Interaction
arXiv cs.RO (Robotics)
arXiv:2610.28523v1 Announce Type: new Abstract: Humanoid-human interaction requires robots to operate under severe partial observability: during close physical contact, the human partner is occluded, truncated, or outside the robot's field…
-
UniWALM: Unified World Action Language Model for Embodied Robot Control
arXiv cs.RO (Robotics)
arXiv:2610.28626v1 Announce Type: new Abstract: Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and…
-
Latent Projection for Latent Planning
arXiv cs.RO (Robotics)
arXiv:2610.26979v1 Announce Type: cross Abstract: Latent world models let an agent plan in latent space. The planner searches for an action sequence that minimizes a cost, and that cost is often the $\ell_2$ distance between the predicted…
-
OmniVLoc: Topo-metric Visual Localization for Omnidirectional Cameras
arXiv cs.RO (Robotics)
arXiv:2610.27522v1 Announce Type: cross Abstract: Omnidirectional cameras provide surround-view information, significantly overcoming the field-of-view constraints for traditional visual localization systems. However, existing localization…
-
PanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian Splatting
arXiv cs.RO (Robotics)
arXiv:2610.27696v1 Announce Type: cross Abstract: 3D scene graphs support language-guided navigation by organizing physical entities and their containment and spatial relations into hierarchical maps. Building such structured maps requires…
-
When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited Baselines
arXiv cs.RO (Robotics)
arXiv:2610.27714v1 Announce Type: cross Abstract: When does experience memory help a closed-loop LLM driving agent? Published gains cannot say, because the two factors we find to matter most, which warmup experiences the pool contains and…
-
Give the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language Models
arXiv cs.RO (Robotics)
arXiv:2610.27756v1 Announce Type: cross Abstract: Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cross the barrier…
-
Planning under Noise with Neural Operators
arXiv cs.RO (Robotics)
arXiv:2610.28623v1 Announce Type: cross Abstract: Planning under uncertain control execution noise requires reliable feedback policies across diverse environments. We introduce Planning Under Noise (PUN), a neural operator that learns…
-
Synergistic Action and Style Priors for Learning Legged Locomotion
arXiv cs.RO (Robotics)
arXiv:2410.03246v3 Announce Type: replace Abstract: Deep Reinforcement Learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms…
-
Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2603.19233v4 Announce Type: replace Abstract: A fine-tuned Vision-Language-Action (VLA) policy can easily place the alphabet soup in the basket on command, just as it saw during fine-tuning. However, if the basket is shifted five…
-
Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs
arXiv cs.RO (Robotics)
arXiv:2606.10180v2 Announce Type: replace Abstract: We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real time through generic inputs, such as a keyboard. This method can…
-
ZeroDex: Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
arXiv cs.RO (Robotics)
arXiv:2606.19340v3 Announce Type: replace Abstract: We present ZeroDex, a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans from calibrated multi-view RGB images…
-
Readiness Barrier Functions: Forward-Invariant Control Authority for Overactuated Multirotor Allocation
arXiv cs.RO (Robotics)
arXiv:2608.16335v2 Announce Type: replace Abstract: Allocation schemes that greedily maximize a readiness metric over the actuator fiber bundle of an overactuated multirotor produce commands that jump between disconnected optimal strata…
-
From Instrument-Mounted Demonstrations to In-Vivo Execution: Learning Bimanual Laparoscopic Appendectomy Without Robot-Collected Demonstrations
arXiv cs.RO (Robotics)
arXiv:2609.25625v2 Announce Type: replace Abstract: Most minimally invasive surgery is still performed with hand-held laparoscopic instruments, and the surgeon's instrument kinematics are lost when the operation ends; only the endoscope…
-
ForeTac: Predictive Contact Guidance for Generative Robot Policies
arXiv cs.RO (Robotics)
arXiv:2610.18118v2 Announce Type: replace Abstract: In contact-rich manipulation, actions that appear equally plausible from vision can produce different contact outcomes, while reactive control based on current tactile feedback may…
-
HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents
arXiv cs.RO (Robotics)
arXiv:2610.23479v2 Announce Type: replace Abstract: Agents built on vision language models (VLMs) now compete with learned policies on robot manipulation leaderboards. We ask how far a coding agent can go when it controls a robot instead…
-
Action-Aligned Latent Planning for Versatile Humanoid Loco-Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.24675v2 Announce Type: replace Abstract: Learning a single perceptive policy for diverse humanoid loco-manipulation requires unifying high-level task decisions without losing the state-dependent physical responses that make each…
-
Visual-Inertial Odometry for Ground Robots with Dynamic Camera-IMU Extrinsic Calibration
arXiv cs.RO (Robotics)
arXiv:2610.25397v2 Announce Type: replace Abstract: Visual-inertial odometry systems are often constrained by the assumption that sensors are rigidly mounted, which limits their adaptability in practical scenarios involving structural…
-
InteractAgent: Agentic Human Motion Interaction with Memory-Augmented Reflection
arXiv cs.RO (Robotics)
arXiv:2610.25649v2 Announce Type: replace Abstract: Long-horizon human-scene interaction requires coordinated spatial reasoning, physical feasibility, and the ability to recover from compounding execution errors. Text-driven motion models…
-
VLA-Rolling: Fewer Denoising Steps, Better Control via Adaptive Action Reuse
arXiv cs.RO (Robotics)
arXiv:2610.25043v2 Announce Type: replace-cross Abstract: Flow-matching vision-language-action (VLA) models generate an action chunk by iteratively denoising Gaussian noise, but typically execute only a short prefix before replanning with…
-
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
arXiv cs.RO (Robotics)
arXiv:2610.27732v1 Announce Type: new Abstract: Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of…
-
WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory and In-Context Learning
arXiv cs.RO (Robotics)
arXiv:2607.18840v3 Announce Type: replace Abstract: World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constrained by…
-
From Predictive Geometry to Action: Learning Complementary Predictive Representations for Embodied Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.28164v1 Announce Type: new Abstract: Effective manipulation requires a policy to capture not only about the current scene geometry, but also about how that geometry will evolve under interaction. Existing approaches either…
-
TAPDreamer: Transferable Adversarial Patches for World Action Models
arXiv cs.RO (Robotics)
arXiv:2610.06814v3 Announce Type: replace-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…
-
KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation
arXiv cs.RO (Robotics)
arXiv:2606.22113v2 Announce Type: replace Abstract: Generalizing manipulation policies across robot embodiments remains difficult because standard policies tie the interactions needed for a task to the actions of a particular robot. We…
-
CLOSER: Evidence-Aware Active Visual Verification for Embodied Object-Goal Navigation
arXiv cs.RO (Robotics)
arXiv:2610.28476v1 Announce Type: cross Abstract: Object-goal navigation (ObjectNav) requires an embodied agent to find an instance of a specified category in an unseen environment and stop near it. The agent typically relies on an object…
-
Velocity Optimization via Thermal Imaging Enhances Autonomous Tumor Resection
arXiv cs.RO (Robotics)
arXiv:2610.27562v1 Announce Type: new Abstract: Objective: To demonstrate and evaluate THERMO, a thermal-velocity optimization algorithm for autonomous electrosurgery, in ex vivo porcine tissue using the UR10e-based ASTR system. Methods…
-
Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing
arXiv cs.RO (Robotics)
arXiv:2610.27141v1 Announce Type: new Abstract: Reliable contact establishment remains a critical challenge for autonomous on-orbit servicing (OOS), particularly when interacting with non-cooperative targets. Gecko-inspired dry adhesives…
-
On Maximum Clique and Maximum Consensus Formulations in Point Cloud Registration
arXiv cs.RO (Robotics)
arXiv:2610.27275v1 Announce Type: new Abstract: Maximum clique and maximum consensus are widely used formulations for robust point cloud registration in robotics. Maximum consensus seeks one transformation that aligns as many matches as…
-
Design and Control of a Multimodal Legged-Aerial Robot Through Separate Control Contraction Metrics
arXiv cs.RO (Robotics)
arXiv:2610.27315v1 Announce Type: new Abstract: The integration of dynamic legged locomotion and aerial mobility offers versatility that is deterred by challenges in payload distribution, actuation, and the contrasting requirements of both…
-
Determination of the Human-Robot Interaction Workspace for Robot Assisted Head Stabilization Control
arXiv cs.RO (Robotics)
arXiv:2610.27336v1 Announce Type: new Abstract: Accurate head immobilization is critical for medical procedures such as neuroimaging and intracranial radiation therapy, where even minor motion can compromise precision. Traditional methods…
-
Refuses When Asked, Complies When Acting: A Runtime Safety Check for Robot Control Loops
arXiv cs.RO (Robotics)
arXiv:2610.27350v1 Announce Type: new Abstract: Frontier models can control robots through agent harnesses that loop on one question: what motion comes next toward the user's goal? We show that this default loop carries out harmful…
-
Towards Autonomous Bricklaying Using Boston Dynamics Spot
arXiv cs.RO (Robotics)
arXiv:2610.27472v1 Announce Type: new Abstract: Mobile legged robots offer unique advantages for on-site construction, including the ability to traverse unstructured terrain, climb stairs, and operate independently between spatially…
-
A Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving Camera
arXiv cs.RO (Robotics)
arXiv:2610.27622v1 Announce Type: new Abstract: Handheld demonstration devices decouple data collection from the robot, but conventional designs burden the hand with a wrist camera, cables and a pose tracker (SLAM, an IMU, a VR controller…
-
LocoPilot: Single-Operator Bilateral Teleoperation for Loco-Manipulation Policy Learning
arXiv cs.RO (Robotics)
arXiv:2610.27998v1 Announce Type: new Abstract: Learning loco-manipulation policies requires demonstrations that capture coordinated base and arm motion on the target embodiment. Robot-free interfaces allow demonstrations to be collected…
-
De-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot Control
arXiv cs.RO (Robotics)
arXiv:2610.28122v1 Announce Type: new Abstract: Cascade world-action models (WAMs) use predicted visual futures to condition robot actions, but inherit costly iterative inference from diffusion-pretrained experts. We ask what a single-step…
-
Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAs
arXiv cs.RO (Robotics)
arXiv:2610.28184v1 Announce Type: new Abstract: Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize…
-
Safe Multi-Robot Collaboration With Uniform Exclusion Using Trust
arXiv cs.RO (Robotics)
arXiv:2610.28251v1 Announce Type: new Abstract: Robot swarms coordinate through directed, time-varying local communication links, some of which may be compromised to allow the transmission of arbitrary malicious data. We provide an…
-
Reinforced Iterative Learning Control for elastic joint arms: Guaranteed cross-trajectory generalization under model uncertainties
arXiv cs.RO (Robotics)
arXiv:2610.28329v1 Announce Type: new Abstract: Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter…
-
CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied Agents
arXiv cs.RO (Robotics)
arXiv:2610.28381v1 Announce Type: new Abstract: Reasoning about safety is essential for embodied agents powered by large language models (LLMs). We introduce the Contextual Action and Plan Safety benchmark (CAPSafe), designed to evaluate…
-
Physical AI: Concepts, Techniques, and Challenges
arXiv cs.RO (Robotics)
arXiv:2610.27045v1 Announce Type: cross Abstract: In recent years, physical artificial intelligence (physical AI) has experienced rapid development, capturing significant attention in academia and industry. However, the field has yet to…
-
SynCalib: Breaking Dataset Shortcuts in LiDAR-Camera Calibration via Extrinsic-Controllable Synthesis
arXiv cs.RO (Robotics)
arXiv:2610.27547v1 Announce Type: cross Abstract: Online LiDAR-camera calibration remains a fundamental yet challenging task in the field of robotics. Recently, deep learning-based data-driven approaches have emerged, offering…
-
Distributed Platoon Control for Safe and Smooth Crossing at an Unsignalized Intersection-Part I: Stability Analysis
arXiv cs.RO (Robotics)
arXiv:2610.28290v1 Announce Type: cross Abstract: We propose a distributed platoon controller that guarantees safe and smooth crossing of multi-vehicle systems at an unsignalized intersection. To support the stability analysis, we consider…
-
CoGaussian: Open-Vocabulary Gaussian-based Collaborative 3D Scene Understanding
arXiv cs.RO (Robotics)
arXiv:2610.28530v1 Announce Type: cross Abstract: Collaborative perception enables agents to retrieve the scene semantics and geometry beyond the field of view of any individual agent. This broader scene understanding enhances…
-
Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary Rigs
arXiv cs.RO (Robotics)
arXiv:2610.28632v1 Announce Type: cross Abstract: Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D…
-
DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs
arXiv cs.RO (Robotics)
arXiv:2605.19294v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide model latency behind ongoing robot motion. During inference, the robot continues executing its…
-
Exploring Nonlinear Body Oscillations for Natural Quadruped Gaits
arXiv cs.RO (Robotics)
arXiv:2609.00539v4 Announce Type: replace Abstract: Animals' body morphology shapes the gait patterns they can perform, where mechanical resonance reduces the need for active control. By tuning posture and muscle stiffness, they leverage…
-
Comfortably Stuck: Evaluation Pitfalls in Bench2Drive's Closed-Loop Protocol
arXiv cs.RO (Robotics)
arXiv:2610.21741v2 Announce Type: replace Abstract: Closed-loop evaluation is widely regarded as a more faithful way to assess end-to-end (E2E) driving models than open-loop evaluation, and Bench2Drive, built on the CARLA simulator, has…
-
RoboFake: Are Deepfake Detectors Ready for Humanoid Face Robots?
arXiv cs.RO (Robotics)
arXiv:2610.14269v2 Announce Type: replace-cross Abstract: Humanoid face robots can now move their lips in sync with speech and show detailed facial expressions. Give such a robot the face of a real person and drive it with generated…
-
Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence
arXiv cs.RO (Robotics)
arXiv:2610.18447v3 Announce Type: replace-cross Abstract: World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In…
-
Large Multimodal Models for Direct Robot Control: GPT-6 as a Beginning
arXiv cs.RO (Robotics)
arXiv:2610.28259v1 Announce Type: new Abstract: Recent advances in visuospatial understanding and agentic reasoning enable direct robotic manipulation with general-purpose multimodal models, but their embodied capabilities remain poorly…
-
Robot-Task Suitability in Heterogeneous Multi-Robot Task Allocation
arXiv cs.RO (Robotics)
arXiv:2610.27504v1 Announce Type: new Abstract: Heterogeneous multi-robot task allocation depends on estimates of how suitable individual robots are for candidate tasks, yet suitability can be defined in substantially different ways. We…
-
Real-Time Disturbance-Aware Koopman Model Predictive Control for Quadrotors in Spatially Varying Winds
arXiv cs.RO (Robotics)
arXiv:2610.27414v1 Announce Type: new Abstract: Reliable quadrotor flight in disturbed environments requires predictive models that remain accurate as unmodeled aerodynamic effects change during deployment. We introduce a disturbance-aware…
-
PACT-VLA: Speculative Action-Chunk Verification with Pre-Commit Observations
arXiv cs.RO (Robotics)
arXiv:2610.28019v1 Announce Type: new Abstract: Vision-language-action (VLA) policies are commonly deployed with asynchronous inference in real-world settings, where the next action chunk is generated while the robot is still executing the…
-
Test-Time Trajectory Optimization for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2606.07170v2 Announce Type: replace Abstract: End-to-end planners for autonomous driving typically generate a set of candidate trajectories, score each one, and return the highest-scoring candidate. However, the scorer is applied…
-
DA-WAM: Decision-Aligned Future Latents for Driving World Models
arXiv cs.RO (Robotics)
arXiv:2608.19085v3 Announce Type: replace Abstract: World models for autonomous driving should anticipate the consequences that matter for driving decisions rather than reconstruct every detail of future scenes. However, predictive…
-
FastVLA: Task-Conditioned and Temporally Adaptive Visual Token Compression for Efficient Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.22146v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models present a promising paradigm for general-purpose robot manipulation, but closed-loop deployment is often limited by inference efficiency: at each…
-
Policy Search in Code Space for Multi-Agent Pathfinding
arXiv cs.RO (Robotics)
arXiv:2610.25946v2 Announce Type: replace Abstract: Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in…
-
OmniInteract: Towards Unified Whole-Body Interaction Control for Dual Humanoids
arXiv cs.RO (Robotics)
arXiv:2610.26043v2 Announce Type: replace Abstract: Physical interaction is a key capability for humanoid collaboration, requiring coordinated whole-body motion and precise contact. However, learning diverse dual-humanoid interactions…
-
EMMA: Enhancing Robotic Control Robustness through a Generative Visual Model
arXiv cs.RO (Robotics)
arXiv:2509.22407v3 Announce Type: replace-cross Abstract: The generalization of vision-language-action (VLA) models heavily relies on diverse training data. However, acquiring large-scale robot manipulation data across varied object…
-
CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLA
arXiv cs.RO (Robotics)
arXiv:2610.25927v2 Announce Type: replace-cross Abstract: Robot manipulation often depends on short-term cues - such as brief contacts, temporary occlusions, and intermediate object states - that are ambiguous in a single frame and can…
-
SPAR: Search-trained Push Action Ranker for Efficient Navigation Among Movable Obstacles
arXiv cs.RO (Robotics)
arXiv:2610.28362v1 Announce Type: new Abstract: Navigation Among Movable Obstacles (NAMO) requires a robot to rearrange objects that block access to its goal. For a pushing robot, progress may depend on a setup push that enables a later…
-
JARVIS: From Visual Manuals to Autonomous Robotic Assembly
arXiv cs.RO (Robotics)
arXiv:2610.27618v1 Announce Type: new Abstract: Visual manuals communicate procedural knowledge through stepwise diagrams, but translating these instructions into reliable long-horizon robotic execution remains challenging. We introduce…
-
XoNav: An Exoskeleton as a Personalized Haptic Interface for Assisted Navigation
arXiv cs.RO (Robotics)
arXiv:2610.27271v1 Announce Type: new Abstract: Walking without vision requires timely, unambiguous guidance, yet many wearable aids encode directions as audio or vibrotactile signals that users must translate into movement. We present…
-
PAKE: Learning Whole-Body Loco-Manipulation with Partial Kinematic Embeddings
arXiv cs.RO (Robotics)
arXiv:2607.11041v2 Announce Type: replace Abstract: Loco-manipulation has recently shown promising capabilities; however, achieving high-precision control, managing the high-dimensional action space induced by many degrees of freedom…
-
Learning Reachability-Based Safety Representations for Real-Time Robot Navigation in Unknown and Dynamic Environments
arXiv cs.RO (Robotics)
arXiv:2610.16522v2 Announce Type: replace Abstract: Safe robot navigation in unknown, dynamic environments requires more than geometric collision checking: a robot still far from an obstacle may be unable to avoid it because of its speed…
-
SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images
arXiv cs.RO (Robotics)
arXiv:2610.28585v1 Announce Type: new Abstract: Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but…
-
Minimum-Time Escape from the Conic Field of View of a Reeds-Shepp Pursuer: Classification and Game Value for a Slower or Equally Fast Evader
arXiv cs.RO (Robotics)
arXiv:2610.27629v1 Announce Type: new Abstract: We study minimum-time escape of an omnidirectional evader from the forward conic field of view of a Reeds-Shepp pursuer with minimum turning radius $r$. For speed ratio $\nu$ and cone…
-
Frontier LLMs Enter the World of Robotics: A Cross-Model Evaluation on RoboColiseum
arXiv cs.RO (Robotics)
arXiv:2610.27865v1 Announce Type: new Abstract: Recent studies have explored the potential of multimodal large language models for robot control, yet the models' embodied capabilities remain insufficiently characterized across models…
-
EventSync: Event-Driven Memory Updates for History-Dependent Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.27917v1 Announce Type: new Abstract: History-dependent robotic manipulation requires task context and interaction history, as the current observation alone is insufficient to determine the next action. Hierarchical frameworks…
-
FPTAS for Polygonal Multi-Robot Motion Planning
arXiv cs.RO (Robotics)
arXiv:2610.20244v2 Announce Type: replace-cross Abstract: We study multi-robot motion planning in a polygonal environment with polygonal robots. The setting of the problem consists of a polygonal domain $\mathcal{W}$ with $n$ vertices and…
-
Taskonomy: Disentangling Task Transfer Learning
arXiv cs.RO (Robotics)
arXiv:1804.08328v2 Announce Type: replace-cross Abstract: Do visual tasks have a relationship, or are they unrelated? For instance, could having surface normals simplify estimating the depth of an image? Intuition answers these questions…
-
Training Controllable World Models via Action Influence Maximization
arXiv cs.RO (Robotics)
arXiv:2610.27387v1 Announce Type: new Abstract: Action-conditioned video generative models trained on successful, goal-directed demonstrations tend to ignore the commanded action, rendering a plausible expert-like future regardless of what…
-
GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action Models
arXiv cs.RO (Robotics)
arXiv:2610.28457v1 Announce Type: new Abstract: General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to…
-
HATCH: Hardware-Attested Task Chains for Verifiable Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.27485v1 Announce Type: new Abstract: Capability claims in robot manipulation are unverifiable, and existing leaderboards are each closed, simulated, or gameable. We propose HATCH, a robot escape room: an openly specified…
-
What Novice Operators See Changes What the Policy Learns: A User Study of Keypoint Hand Visual Representation for Teleoperated Demonstration
arXiv cs.RO (Robotics)
arXiv:2610.27907v1 Announce Type: new Abstract: Imitation learning increasingly relies on novice operators, whose demonstrations fall short of experts' in number and inter-trial consistency. Operators act on what they are shown, yet how…
-
Learning to Be Different: Component Specialization for Compositional Diffusion Policies
arXiv cs.RO (Robotics)
arXiv:2610.27194v1 Announce Type: new Abstract: Diffusion policies with linearly composed scores have emerged as a promising approach to multitask robotic learning by combining separate factors to enable modular, task-wise adaptation…
-
Learning Where it Matters: Autonomous Data Collection and Offline Reinforcement Learning for Local Contact-Rich Manipulation
arXiv cs.RO (Robotics)
arXiv:2607.15982v2 Announce Type: replace Abstract: Learned policies trained end-to-end on large datasets often remain brittle in high-precision contact-rich tasks. Further, they typically require large amounts of manually collected data…
-
MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy
arXiv cs.RO (Robotics)
arXiv:2610.28465v1 Announce Type: new Abstract: Lunar surface exploration increasingly relies on autonomous rovers that must perceive and traverse unstructured terrain under extreme illumination conditions. Near the lunar poles, low sun…
-
Which Depth Estimator for Jetson AGX Orin? A 2026 Benchmark of Monocular and Stereo Methods
arXiv cs.RO (Robotics)
arXiv:2610.27199v1 Announce Type: new Abstract: The Jetson AGX Orin is a common computer for robots and vehicles, yet measured accuracy, speed and energy of current depth estimators on it are hard to find. We benchmark nine model families…
-
NestedVLA: Learning to Consolidate and Generate Skills for Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.23271v3 Announce Type: replace Abstract: Vision-language-action (VLA) models can learn a wide range of robotic skills, but combining separately trained skills remains challenging. The original training data may be unavailable…
-
Physical Words: A Vocabulary for Structuring Latent Reasoning in Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.26854v2 Announce Type: replace Abstract: Multimodal reasoning provides robotic foundation models with predictive context needed for reliable action generation. However, language-based reasoning captures task semantics but…
-
MAPLE: Mondrian-Anchored Prior for Learning-free Indoor Exploration
arXiv cs.RO (Robotics)
arXiv:2610.28566v1 Announce Type: new Abstract: Robots exploring unknown indoor environments must decide where to move while much of the environment remains unseen. Predicting the occupancy of unseen space beyond the current sensor range…
-
Agentic discovery of interpretable car-following laws from multi-source trajectory data
arXiv cs.RO (Robotics)
arXiv:2610.27836v1 Announce Type: new Abstract: Car-following (CF) models is a fundamental component of microscopic traffic simulation and underpin the analysis of collective traffic dynamics, while its modeling becomes more challenging…
-
Curvature as a Baseline: Monocular Pose Measurement of Cylindrical Objects with Dual Colour Stripe Markers
arXiv cs.RO (Robotics)
arXiv:2610.26003v1 Announce Type: cross Abstract: Thin cylindrical objects offer little space for planar markers. We propose a dual-colour-stripe marker that uses the known curvature of an object to improve pose measurement with a single…