Robotics & Automation
Robotics & Automation news — Friday 09 October 2026
150 stories from 4 sources, every one in English. Each links to its publisher.
-
Why humanoid robot demos still fail the generalization test
Robotics Business Review
The Robot Report Podcast · Why humanoid robot demos still fail the generalization test Jeanine Sinanan-Singh, director of GenAI research at Appen. In Episode 265 of The Robot Report Podcast, our guest is Jeanine Sinanan-Singh, director of…
-
Why humanoid robot demos still fail the generalization test
The Robot Report
The Robot Report Podcast · Why humanoid robot demos still fail the generalization test Jeanine Sinanan-Singh, director of GenAI research at Appen. In Episode 265 of The Robot Report Podcast, our guest is Jeanine Sinanan-Singh, director of…
-
Boston Dynamics gives more insight into its redesigned humanoid hand
Robotics Business Review
Boston Dynamics said its new hand is still capable of handling over 100 lb. | Source: Boston Dynamics Last week, Boston Dynamics Inc. gave a look at its new humanoid robot hand. The four-fingered hand has 13 degrees of freedom, or DoF, and…
-
Boston Dynamics gives more insight into its redesigned humanoid hand
The Robot Report
Boston Dynamics said its new hand is still capable of handling over 100 lb. | Source: Boston Dynamics Last week, Boston Dynamics Inc. gave a look at its new humanoid robot hand. The four-fingered hand has 13 degrees of freedom, or DoF, and…
-
Video Friday: Robot Decommissioning Takes a Fun Turn
IEEE Spectrum Robotics
Video Friday is your weekly selection of awesome robotics videos, collected by your friends at IEEE Spectrum robotics. We also post a weekly calendar of upcoming robotics events for the next few months. Please send us your events for…
-
Groceryshop 2026 shows that retail robots are ready to scale, use AI
The Robot Report
Groceryshop 2026 provided an opportunity to assess the state of retail robotics. Source: Georges Mirza It has been more than a decade since I first helped to bring robots to live retail center stores. Long gone are retailers’ concerns…
-
Groceryshop 2026 shows that retail robots are ready to scale, use AI
Robotics Business Review
Groceryshop 2026 provided an opportunity to assess the state of retail robotics. Source: Georges Mirza It has been more than a decade since I first helped to bring robots to live retail center stores. Long gone are retailers’ concerns…
-
2DGS-Planner: Rasterization-based Path Planning in 2D Gaussian Splatting Map
arXiv cs.RO (Robotics)
arXiv:2610.11752v1 Announce Type: new Abstract: Gaussian splatting provides an explicit and efficiently rasterizable scene representation for robot navigation. However, individual Gaussian primitives may not reliably represent obstacles as…
-
PACE: Persona Adaptation through Conversational Elicitation in Human-Robot Interaction
arXiv cs.RO (Robotics)
arXiv:2607.15579v5 Announce Type: replace Abstract: Equipping humanoid robots with coherent and adaptable personas is crucial for fostering natural, engaging, and trustworthy human-robot interaction (HRI). However, existing approaches…
-
VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.12451v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to…
-
Multi-Agent Coordination via Support-Preserving Distillation
arXiv cs.RO (Robotics)
arXiv:2610.10087v2 Announce Type: replace-cross Abstract: Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentralized one-step actors under…
-
Traceable World State: A Provenance-Aware State Representation and Deterministic Replay Framework for Robotic Systems
arXiv cs.RO (Robotics)
arXiv:2610.12033v1 Announce Type: new Abstract: Robotic systems operating over extended tasks must maintain a world state assembled from observations arriving at different times, with varying confidence and potential revisions…
-
Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning
arXiv cs.RO (Robotics)
arXiv:2608.13422v2 Announce Type: replace Abstract: Visual bottlenecks that focus policy inputs on regions of interest (ROIs) can improve data-efficient visuomotor learning by separating where to look from how to act. Many ROI interfaces…
-
Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer
arXiv cs.RO (Robotics)
arXiv:2610.11416v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a prominent framework for complex robotic manipulation, building on the strong semantic understanding of pretrained Vision-Language Models…
-
ExecVLA: Following Fine-Grained Execution Constraints in Vision-Language-Action Models with Bi-Level Action Representation
arXiv cs.RO (Robotics)
arXiv:2603.17524v2 Announce Type: replace Abstract: We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must follow instruction-specified execution…
-
AURA: Asymptotically Optimal Uncertainty-Robust Replanning Algorithm for Kinodynamic Systems
arXiv cs.RO (Robotics)
arXiv:2605.27699v3 Announce Type: replace Abstract: Sampling-based motion planners offer a practical and scalable approach to kinodynamic motion planning, notably for high-dimensional, underactuated, or non-holonomic systems. However…
-
HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface
arXiv cs.RO (Robotics)
arXiv:2609.20659v2 Announce Type: replace Abstract: Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting them to a specific deployment remains challenging. Supervised fine-tuning…
-
VLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.08133v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token sequences at every control step, limiting…
-
Neural Networks for Temporal Pattern Recognition and Dynamic Arm Gesture Speed Estimation for Robot Control
arXiv cs.RO (Robotics)
arXiv:2610.11631v1 Announce Type: new Abstract: Deploying intelligent robotic systems that interact with humans through gestures requires neural networks capable of recognizing diverse temporal patterns. We present a systematic benchmark…
-
PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
arXiv cs.RO (Robotics)
arXiv:2606.17924v2 Announce Type: replace Abstract: Current Vision-Language-Action (VLA) models face a trade-off between efficient action generation and explicit deliberation. Directly decoding actions from vision-language backbone…
-
TacHair: Tactile Contact-Distribution Guided Online Correction for Robotic Hair Stroking and Perception
arXiv cs.RO (Robotics)
arXiv:2610.10637v1 Announce Type: new Abstract: Hair stroking is common in daily grooming and personal care, and is also widely used in hair-product evaluation, motivating robots with similar physical interaction capabilities. Existing…
-
SimVLA: Zero-Shot Sim-to-Real VLA Learning for Mobile Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.11248v1 Announce Type: new Abstract: Large-scale, diverse datasets have driven the success of LLMs and VLMs. But VLAs for robotics remain limited by the cost and complexity of real-world data collection. While simulation offers…
-
Demonstrating Arena 5.0: A Photorealistic ROS2 Simulation Framework for Developing and Benchmarking Social Navigation
arXiv cs.RO (Robotics)
arXiv:2610.11220v1 Announce Type: new Abstract: Building upon the foundations laid by our previous work, this paper introduces Arena 5.0, the fifth iteration of our framework for robotics social navigation development and benchmarking…
-
WAM-Cache: Staleness-Bounded KV Reuse for Efficient World Action Models
arXiv cs.RO (Robotics)
arXiv:2610.11401v1 Announce Type: new Abstract: World Action Models (WAMs) enable generalist robot manipulation by conditioning an action expert on representations from a pretrained video Diffusion Transformer (DiT). In closed-loop…
-
TAPNAV: Humanoid Navigation through Tactile Active Perception
arXiv cs.RO (Robotics)
arXiv:2610.10748v1 Announce Type: new Abstract: Navigation in vision-denied environments is challenging for humanoid robots because proprioceptive odometry drifts and localization uncertainty accumulates rapidly. We present TAPNAV, a…
-
ImagiNav: Scalable Embodied Navigation via Generative Visual Prediction and Inverse Dynamics
arXiv cs.RO (Robotics)
arXiv:2603.13833v2 Announce Type: replace Abstract: Enabling robots to navigate open-world environments via natural language is critical for general-purpose autonomy. Yet, Vision-Language Navigation has relied on end-to-end policies…
-
Trust Region Q Adjoint Matching
arXiv cs.RO (Robotics)
arXiv:2605.27079v2 Announce Type: replace-cross Abstract: Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently…
-
ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perception
arXiv cs.RO (Robotics)
arXiv:2610.06955v2 Announce Type: replace Abstract: Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment…
-
USDCraft: Geometrically Grounded Programmatic Modeling of Articulated 3D Assets for Simulation
arXiv cs.RO (Robotics)
arXiv:2610.11322v1 Announce Type: new Abstract: Geometrically faithful and functional articulated 3D assets are essential for real-to-sim robot manipulation, where policies trained in simulation must transfer to physical objects. Recent…
-
REACT: Rolling Denoising and Dual Decoupling for Reactive Robot Control with VLA Models
arXiv cs.RO (Robotics)
arXiv:2610.12007v1 Announce Type: new Abstract: Flow-based vision-language-action (VLA) models generate action chunks for temporally coherent robot motion, but chunked control creates a fundamental closed-loop trade-off: long chunks…
-
iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains
arXiv cs.RO (Robotics)
arXiv:2610.10962v1 Announce Type: new Abstract: Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied agents based…
-
Toward Lunar Legged Robots: Field Deployment Lessons at LUNA
arXiv cs.RO (Robotics)
arXiv:2610.12276v1 Announce Type: new Abstract: Legged robots are promising candidates for future lunar surface missions because they can traverse steep, loose, and obstacle-rich terrain that challenges conventional wheeled rovers…
-
Scalable LEO Conjunction Screening using Adaptive Synthetic-Covariance Thresholds
arXiv cs.RO (Robotics)
arXiv:2610.11645v1 Announce Type: new Abstract: As orbital populations grow, conjunction screening must search more object pairs for potential collision risks. Existing pipelines use early-stage filters, such as an apsis filter, to…
-
Does Dynamic-Point Filtering Help When Texture Is Scarce? A Controlled Study of ORB-SLAM2 Front-Ends in Synthetic Indoor Scenes
arXiv cs.RO (Robotics)
arXiv:2610.10564v1 Announce Type: new Abstract: Dynamic-point filters are routinely added to feature-based visual SLAM, and several recent systems argue that removing dynamic features can leave too few static features in low-texture…
-
Diagnosing and Recovering from Observation-Space Shift at Long-Horizon Skill Seams
arXiv cs.RO (Robotics)
arXiv:2610.10810v1 Announce Type: new Abstract: Long-horizon robotic manipulation is often built by chaining independently trained skills. Although each skill can be reliable in isolation, performance degrades sharply when skills are…
-
OmniHOI: Dexterous Hand-Object Interaction from Monocular Human Video
arXiv cs.RO (Robotics)
arXiv:2610.10855v1 Announce Type: new Abstract: Monocular videos of human manipulation provide abundant dexterous demonstrations, yet reconstructing hand-object interaction from a single view and transferring it to robot hands remain…
-
Informationally Decoupled Trajectory Design for Sim-to-Real System Identification
arXiv cs.RO (Robotics)
arXiv:2610.10905v1 Announce Type: new Abstract: Sampling-based system identification estimates physically meaningful parameters by tuning a simulator to reproduce the target system dynamics, providing an interpretable approach to improving…
-
Towards Path-Creative Navigation: Robot Navigation through Embodied Interaction
arXiv cs.RO (Robotics)
arXiv:2610.11072v1 Announce Type: new Abstract: Autonomous navigation in cluttered and constrained environments typically assumes a fixed environment and searches only for paths within existing free space. However, a route can be blocked…
-
FOCUS: From Privileged States to RGB-D with Controlled Modality Switching and Representation Alignment
arXiv cs.RO (Robotics)
arXiv:2610.11119v1 Announce Type: new Abstract: Vision-based reinforcement learning for robotic manipulation is sample-inefficient because RGB-D observations are high-dimensional and noisy. Privileged state information available in…
-
How Firm Should a Grasp Be?
arXiv cs.RO (Robotics)
arXiv:2610.11221v1 Announce Type: new Abstract: An ideal robot grasp is firm enough to securely handle an object, yet gentle enough to avoid damaging it. Achieving this balance requires knowledge of the object's material properties, such…
-
SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2610.11583v1 Announce Type: new Abstract: End-to-end autonomous driving demands trajectory planners that are both highly accurate and cheap enough for edge deployment. State-of-the-art artificial neural network (ANN) planners meet…
-
TACROSS: An Efficient and Low-Cost Scalable Human Touch System Across Heterogeneous Tactile Sensors for Dexterous Robot Learning
arXiv cs.RO (Robotics)
arXiv:2610.11945v1 Announce Type: new Abstract: Collecting tactile demonstrations on robots is costly and slow, motivating the use of lower-cost human tactile gloves for scalable data collection. However, human capacitive/piezoresistive…
-
RAGNAROK: Radar-Aided Gravity-Normalized Alignment for Robust Open Keyframe-based Radar-Visual-Kinematic-Inertial SLAM
arXiv cs.RO (Robotics)
arXiv:2610.11531v1 Announce Type: new Abstract: Legged robots offer superior mobility in unstructured environments, but reliable operation in such conditions requires robust state estimation. To address the vulnerability of proprioceptive…
-
From Solo to Ensemble: A Hierarchical Framework for Composable Multi-Agent Human-Object Interaction
arXiv cs.RO (Robotics)
arXiv:2610.11722v1 Announce Type: new Abstract: Physics-based human-object interaction has achieved robust single-agent manipulation skills, yet extending them to multi-agent cooperative tasks remains challenging. Existing approaches…
-
A Minimal Optical-Flow Representation for Vision-Based Tactile Rotation Classification in Robotic Manipulation Across Gravity Domains
arXiv cs.RO (Robotics)
arXiv:2610.12073v1 Announce Type: new Abstract: Vision-based tactile sensors provide rich contact information, but processing high-resolution images can be costly for resource-constrained platforms such as space robots. This work…
-
Tell Robot What Not to Do: A Negation Understanding Perspective
arXiv cs.RO (Robotics)
arXiv:2610.11952v1 Announce Type: new Abstract: Instruction following enables robots to perform diverse tasks specified in natural language, making it a fundamental capability for human-robot interaction. Beyond communicating desired…
-
PIER: An Evidence-Gated Execution Interface for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.12123v1 Announce Type: new Abstract: Generating a plausible robot action does not establish that current observations justify its execution. Motivated by exploratory observations of high-confidence visual outputs under severe…
-
SuperNav: An Agentic Navigation System for Any Task in Any Scene
arXiv cs.RO (Robotics)
arXiv:2610.12126v1 Announce Type: new Abstract: General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing…
-
Instance-anchored interaction evidence: Grounding robot plans in human pointing and handling
arXiv cs.RO (Robotics)
arXiv:2610.12157v1 Announce Type: new Abstract: A robot that assists people must often act on what a person has shown rather than said: which of several identical cartons was pointed at, or which box was handled. The plan is executed from…
-
Unifying Policy Learning and State Prediction through Spatial Language Modeling
arXiv cs.RO (Robotics)
arXiv:2610.12172v1 Announce Type: new Abstract: Learning how actions change scene geometry can provide complementary supervision for goal-directed manipulation. We introduce Spatial Language Modeling, which represents scene contours…
-
RESETTLE: Robotic Recovery through Disagreement-Triggered Retrieval and Efficient Corrective Control
arXiv cs.RO (Robotics)
arXiv:2610.12185v1 Announce Type: new Abstract: Reliable robotic manipulation requires timely intervention to correct emerging deviations and restore progress after execution errors. However, recovery methods based on repeated…
-
MAP2: Model- and Acceleration-Based Pursuit with MPC and Gaussian Process Residual Learning for Autonomous Racing
arXiv cs.RO (Robotics)
arXiv:2610.12196v1 Announce Type: new Abstract: Autonomous racing requires accurate trajectory tracking near the handling limits of a vehicle while maintaining low computational latency. Geometric controllers are computationally efficient…
-
Sim-to-Real RL for ASVs using SysID
arXiv cs.RO (Robotics)
arXiv:2610.12202v1 Announce Type: new Abstract: Autonomous Surface Vehicles (ASVs) operating in dynamic marine environments require robust control policies for tasks such as path following and station keeping, making reinforcement learning…
-
Residual Modeling Closes the Regression and Generative Policy Gap in Robot Learning
arXiv cs.RO (Robotics)
arXiv:2610.12231v1 Announce Type: new Abstract: Learning from demonstration has enabled impressive robot behaviors. A common choice for policy learning is to use diffusion or flow matching (Flow-Policies), which often outperforms direct…
-
From Language to Motion: Task-Conditioned Focal-Stack Trajectory Integration for Microscopic Robots
arXiv cs.RO (Robotics)
arXiv:2610.12241v1 Announce Type: new Abstract: Microscopic robots require accurate task geometry despite changes in language, parts, and focus. We present a semantic-to-physical framework that maps instructions to constrained geometric…
-
Fixed-Reference Pose Residuals for Measuring Cross-Dataset Cue Transfer in Human-Robot Interaction Anticipation
arXiv cs.RO (Robotics)
arXiv:2610.12245v1 Announce Type: new Abstract: Social and service robots in public spaces need to anticipate which nearby person is about to approach and touch them, so that a response can be prepared before contact. It is largely unknown…
-
Real-Time Motion Planning with Dynamic Hazards: Classical vs. Learning-Based Methods
arXiv cs.RO (Robotics)
arXiv:2610.12249v1 Announce Type: new Abstract: We study real-time motion planning in dynamic hazard fields through a controlled comparison between classical planning and learning-based methods. Rather than introducing a new planner, we…
-
Walking on Roofs: Exploring the Potential of Walking Robots for Construction Work on Roofs
arXiv cs.RO (Robotics)
arXiv:2610.12272v1 Announce Type: new Abstract: This paper investigates the feasibility of deploying quadruped walking robots for the automation of work in roof environments. While quadrupeds have demonstrated versatility across various…
-
PLaW-VLA: Predictive Latent World Modeling for Vision-Language-Action Policies
arXiv cs.RO (Robotics)
arXiv:2610.12285v1 Announce Type: new Abstract: Learning to predict how the world evolves can provide vision-language-action (VLA) policies with predictive context for long-horizon control, but its effectiveness depends on what future…
-
Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement
arXiv cs.RO (Robotics)
arXiv:2610.12369v1 Announce Type: new Abstract: Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA queries a VLM for decision making at run…
-
GLIO2: A GPU-Parallelized Tightly-Coupled LiDAR-Inertial-GNSS System for Robust and Real-Time Global Localization and Mapping
arXiv cs.RO (Robotics)
arXiv:2610.12411v1 Announce Type: new Abstract: Globally consistent, real-time state estimation in large-scale, perceptually degraded environments is essential for autonomous vehicles and aerial robots, and requires fusing LiDAR, inertial…
-
Control-Ready Uncertainty for Trajectory Diffusion
arXiv cs.RO (Robotics)
arXiv:2610.12431v1 Announce Type: new Abstract: Diffusion models can represent complex, multimodal trajectory distributions, but extracting uncertainty from them typically requires costly Monte Carlo sampling. This limits their use in…
-
A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control
arXiv cs.RO (Robotics)
arXiv:2610.12465v1 Announce Type: new Abstract: General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for…
-
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training
arXiv cs.RO (Robotics)
arXiv:2610.12468v1 Announce Type: new Abstract: We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a model on existing robot datasets faces…
-
SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature Caching
arXiv cs.RO (Robotics)
arXiv:2610.02660v1 Announce Type: cross Abstract: Diffusion-based world models enable high-quality interactive environment generation but suffer from substantial inference overhead due to repeated Transformer evaluations during denoising…
-
Autonomous thermodynamic cycles via robotic mobility and sensing
arXiv cs.RO (Robotics)
arXiv:2610.11667v1 Announce Type: cross Abstract: Thermodynamic cycles are the foundation of energy conversion across natural and engineered systems, transforming heat into useful work. However, these cycles traditionally operate between…
-
Digital Twin for Pre-Deployment Validation of AI-Driven Safety-Critical Industrial Edge Control Loops
arXiv cs.RO (Robotics)
arXiv:2610.11934v1 Announce Type: cross Abstract: Industrial environments are increasingly characterized by the tight interaction among physical processes, communication infrastructures, and intelligent applications. In this context…
-
Learning Which Correspondences to Trust: Confidence-Weighted Event-Camera Localization in LiDAR Maps
arXiv cs.RO (Robotics)
arXiv:2610.11967v1 Announce Type: cross Abstract: Localizing an event camera against a pre-built LiDAR map can be cast as dense optical-flow estimation between a rendered depth view and an event image, followed by a Perspective-n-Point…
-
The Kinetics Observer: A Tightly Coupled Estimator for Legged Robots
arXiv cs.RO (Robotics)
arXiv:2406.13267v2 Announce Type: replace Abstract: This paper presents the Kinetics Observer, a novel proprioceptive state estimator for legged robots designed to provide the feedback required for versatile locomotion and physical…
-
A Sliding-Window Filter for Online Continuous-Time Continuum Robot State Estimation
arXiv cs.RO (Robotics)
arXiv:2510.26623v2 Announce Type: replace Abstract: Stochastic state estimation methods for continuum robots (CRs) often struggle to balance accuracy and computational efficiency. While several recent works have explored sliding-window…
-
Census-Based Population Autonomy For Distributed Robotic Teaming
arXiv cs.RO (Robotics)
arXiv:2511.02147v2 Announce Type: replace Abstract: Collaborating teams of robots show promise due to their ability to complete missions more efficiently and with improved robustness, attributes that are particularly useful for systems…
-
SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation
arXiv cs.RO (Robotics)
arXiv:2603.09163v2 Announce Type: replace Abstract: Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Navigation (VLN). However, reliable path…
-
RoboRacer Arena: Specification-Driven Track Construction for Autonomous Racing
arXiv cs.RO (Robotics)
arXiv:2608.23040v2 Announce Type: replace Abstract: Learning-based autonomous racing relies on diverse training environments, yet constructing a new track requires geometric design, validation, and simulation-asset generation. This…
-
Same Action, Different Outcome: Variability in Dynamic Cloth Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.10801v1 Announce Type: new Abstract: Although cloth is known to exhibit different outcomes under repeated fast dynamic motions, even when the same trajectory is applied, this variability has not yet been systematically…
-
LM-X: Explainable Vision--Language--Action Modeling via Progress, Event, and Uncertainty Prediction
arXiv cs.RO (Robotics)
arXiv:2608.25757v5 Announce Type: replace Abstract: Large-scale vision--language--action (VLA) policies have advanced generalist robot control, yet most remain stimulus-to-action black boxes: actions are exposed, but their explanatory…
-
3D Point World Models: Point Completion Enables More Accurate Dynamics Learning
arXiv cs.RO (Robotics)
arXiv:2607.00148v2 Announce Type: replace Abstract: Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynamics…
-
ACID: Action Consistency via Inverse Dynamics for Planning with World Models
arXiv cs.RO (Robotics)
arXiv:2607.02403v2 Announce Type: replace Abstract: Decision-time planning with action-conditioned world models has become a popular paradigm for embodied control. However, the standard planning cost judges a candidate solely by how close…
-
UniWAM: Unified World-Action Model
arXiv cs.RO (Robotics)
arXiv:2610.02054v3 Announce Type: replace Abstract: Vision-language-action models benefit from the understanding and reasoning capabilities of pretrained vision-language models, but action-only supervision provides limited grounding in…
-
SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation
arXiv cs.RO (Robotics)
arXiv:2610.09488v2 Announce Type: replace Abstract: The future of autonomous robots in human-oriented environments depends on their ability to leverage existing navigational aids embedded in these environments, such as navigational signs…
-
PointZero: 3D Point Track Completion for Learning Transferable 3D Dynamics
arXiv cs.RO (Robotics)
arXiv:2609.19142v3 Announce Type: replace-cross Abstract: World models endow perceptual systems with the ability to predict how scenes evolve under interaction. They are most beneficial when trained on diverse volumes of data, to instill a…
-
Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation
arXiv cs.RO (Robotics)
arXiv:2610.11622v1 Announce Type: new Abstract: Traversability is essential for visual navigation but varies with robot capabilities and user preferences. Conventional pipelines often rely on explicit costmaps or segmentation masks with…
-
NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
arXiv cs.RO (Robotics)
arXiv:2610.10787v1 Announce Type: new Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals over many steps, raising the…
-
Reliability-Aware Future Conditioning for Temporally Robust Robot Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.11956v1 Announce Type: new Abstract: A generated video of a task the robot is about to perform is useful guidance only if it depicts the phase the robot is actually in. We show that temporal misalignment can turn a…
-
SkillWeave: Weaving Heterogeneous Demonstrations into Long-Horizon Manipulation Skills
arXiv cs.RO (Robotics)
arXiv:2610.12046v1 Announce Type: new Abstract: Dexterous manipulation requires both large-scale task progression and precise contact-rich interaction, making it challenging to collect demonstrations that effectively support both regimes…
-
PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
arXiv cs.RO (Robotics)
arXiv:2603.13228v3 Announce Type: replace-cross Abstract: Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this progress, recent…
-
Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform
arXiv cs.RO (Robotics)
arXiv:2509.24001v3 Announce Type: replace-cross Abstract: This paper evaluates the current gaze estimation methods within a human-robot interaction (HRI) context of a shared workspace scenario. We introduce a new, annotated dataset…
-
LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild
arXiv cs.RO (Robotics)
arXiv:2610.12368v1 Announce Type: new Abstract: Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation world models provide this foresight through…
-
Simultaneous Computation with Multiple Prioritizations in Multi-Agent Motion Planning
arXiv cs.RO (Robotics)
arXiv:2501.10781v2 Announce Type: replace-cross Abstract: Multi-agent path finding (MAPF) in large networks is computationally challenging. An approach for MAPF is prioritized planning (PP), in which agents plan sequentially according to…
-
Masked Generative Motion Planning with Geometry-Guided Token Search
arXiv cs.RO (Robotics)
arXiv:2610.10646v1 Announce Type: new Abstract: Generative motion planners typically use learned trajectory priors for initial generation, while leaving test-time repair to local continuous refinement. We introduce Masked Generative Motion…
-
UltraLight Luma: A Novel Edge-Deployable Perception Network for Crop-Row Segmentation in Agricultural Robotics
arXiv cs.RO (Robotics)
arXiv:2610.11764v1 Announce Type: new Abstract: Reliable crop-row perception is essential for autonomous agricultural robots, but low-cost deployment is constrained by computation, memory, power, and inference time. This paper addresses…
-
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
arXiv cs.RO (Robotics)
arXiv:2608.19776v3 Announce Type: replace Abstract: Current dexterous grasp planners primarily optimize for physical stability, focusing on whether an object can be grasped rather than how it should be grasped to support downstream…
-
WARP-VLA: Wrist-Camera Adaptation for View-Robust Policy Execution in Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.11508v1 Announce Type: new Abstract: Despite recent advances in Vision-Language-Action models (VLAs) for robotic manipulation, their performance remains sensitive to changes in camera configuration. The problem becomes more…
-
Rendering-Free Lookahead for Question-Guided Active Vision
arXiv cs.RO (Robotics)
arXiv:2610.11039v1 Announce Type: cross Abstract: Active robot vision requires controlling the camera to reveal task-relevant information that is hidden from the current viewpoint. For example, determining what is inside a box may require…
-
Generalists Act, Specialists Intervene: Modular Stage-Selective Reinforcement Learning for Vision-Language-Action Manipulation
arXiv cs.RO (Robotics)
arXiv:2609.26467v2 Announce Type: replace Abstract: Vision-language-action (VLA) models often struggle in the precision-critical phases of multi-stage manipulation tasks. To mitigate this issue, VLA models can be used in conjunction with…
-
Diffusion-2BC: Hybrid Diffusion and Regression Training for Offline Behavior Cloning in Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.38472v2 Announce Type: replace Abstract: Behavior cloning provides an offline route to autonomous-driving policy learning, but mean-squared-error regression is poorly matched to demonstrations in which one observation admits…
-
When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs
arXiv cs.RO (Robotics)
arXiv:2610.10912v1 Announce Type: new Abstract: Shortcut learning is a prevalent issue in robot learning. The limited diversity of robot demonstration datasets can mislead policies into exploiting spurious correlations between tasks and…
-
PathTime-VLA: Path-Time Decoupling for Factorized Post-Training of Vision-Language-Action Policies
arXiv cs.RO (Robotics)
arXiv:2610.11771v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies typically predict actions at fixed time intervals, coupling the route a robot follows with its execution pace. This coupling complicates adaptation from…
-
Skill-SLM: Agent Skill-driven Small Language Models for Reliable Robot Operation
arXiv cs.RO (Robotics)
arXiv:2610.10812v1 Announce Type: new Abstract: Small language models (SLMs) have been increasingly adopted for onboard robot operation because they enable intelligent decision-making. However, existing approaches are mainly…
-
Distributed Relative Localization Based on Ultra-WideBand and LiDAR for Multi-robot with Limited Communication
arXiv cs.RO (Robotics)
arXiv:2610.11141v1 Announce Type: new Abstract: Relative localization is crucial for a multi-robot system to collaboratively perform tasks, such as exploration and formation. However, this is highly challenging for homogeneous robots with…
-
STAG: A Sparse Traversability-Aware Graph Representation from Grid-Based Costmaps for Robotic Navigation
arXiv cs.RO (Robotics)
arXiv:2610.11943v1 Announce Type: new Abstract: Autonomous rovers navigating large unstructured environments need efficient global planning that accounts for terrain traversability. However, searching dense grid-based costmaps becomes…
-
RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
arXiv cs.RO (Robotics)
arXiv:2608.25585v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models provide a versatile foundation for general robotic manipulation, yet they exhibit significant brittleness when confronted with novel task…
-
In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks
arXiv cs.RO (Robotics)
arXiv:2609.38173v2 Announce Type: replace Abstract: We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself…
-
A Reconfigurable Fabric Based Pneumatic Actuator with Button Fastened Constraint Modules for Multi Mode Actuation
arXiv cs.RO (Robotics)
arXiv:2610.11054v1 Announce Type: new Abstract: Soft pneumatic actuators are widely used in soft robotics. However, their actuation modes are typically fixed by internal chamber designs or reinforcements, making post fabrication…
-
SafeInferCom: Safe Inference-Time Compute via Verifier-Guided Mid-Generation Intervention for Robotic Task Planning
arXiv cs.RO (Robotics)
arXiv:2610.11223v1 Announce Type: new Abstract: Large Reasoning Language Models (LRLMs) enable multi-step reasoning for robotic task planning, but continued reasoning can overwrite valid intermediate plans or leave constraint violations…
-
ARC: A Reasoning Recipe for Robot Foundation Models
arXiv cs.RO (Robotics)
arXiv:2610.12386v1 Announce Type: new Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale. We show that there exists an effective…
-
CoCam4D: Geometry-Aware Cooperative 4D Perception for Camera-Only Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2610.11577v1 Announce Type: new Abstract: Autonomous vehicles often suffer from limited perception due to occlusions, blind spots, limited sensor range, and the complex nature of surrounding environments. Multi-agent collaborative…
-
A Physics-Informed Collision Learning Framework for Collaborative Robot Motion Generation
arXiv cs.RO (Robotics)
arXiv:2610.12404v1 Announce Type: new Abstract: Close-proximity multi-arm manipulation requires collision models that are both geometrically accurate and differentiable enough for real-time optimization. Classical geometry checkers provide…
-
VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2610.11161v1 Announce Type: cross Abstract: VGGT provides a strong foundation for geometry-centric world models by recovering unified 3D scene geometry from visual observations. Although recent extensions enable temporal 3D…
-
SpatialHarness: Test-Time Spatial Scaffolding for Fine Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.12457v1 Announce Type: new Abstract: Frontier multimodal foundation models (e.g., GPT-6 Astra) have recently shown strong potential for direct robotic control, yet their performance on fine manipulation remains limited. We argue…
-
RoboAug: One Annotation to Hundreds of Scenes via Region-Contrastive Data Augmentation for Robotic Manipulation
arXiv cs.RO (Robotics)
arXiv:2602.14032v2 Announce Type: replace Abstract: Enhancing the generalization of robotic learning in diverse unseen environments remains a fundamental challenge. Existing approaches often rely on large-scale pretraining, which is…
-
STEAM: Self-Supervised Temporal Ensemble Advantage Modeling for Real-World Robot Learning
arXiv cs.RO (Robotics)
arXiv:2606.29834v2 Announce Type: replace Abstract: Real-world robot learning increasingly relies on heterogeneous data, but demonstrations and rollouts often mix useful progress with stalls, corrections, and suboptimal behavior. Effective…
-
Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2609.25831v2 Announce Type: replace Abstract: Recent VLM-based autonomous driving planners adopt GRPO-style reinforcement learning to optimize driving performance. However, existing GRPO recipes either optimize driving efficiency…
-
RoboIRS: Inference-Time Internal Representation Steering for Generalist Robot Policies
arXiv cs.RO (Robotics)
arXiv:2610.04681v3 Announce Type: replace Abstract: Vision-language-action (VLA) and world-action models (WAMs) often degrade under out-of-distribution task variations despite retaining partial task capability. To recover such capability…
-
FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinement
arXiv cs.RO (Robotics)
arXiv:2610.05011v2 Announce Type: replace Abstract: Floorplans provide compact and widely available geometric maps for indoor localization, but existing high-performing floorplan-based methods still convert them into dense scene-specific…
-
LACE-CRAFT: Robot Co-Design with Actor Inheritance and Blackboard Collaboration
arXiv cs.RO (Robotics)
arXiv:2610.09283v2 Announce Type: replace Abstract: Robot co-design couples morphology search with policy learning, yet training every new design from scratch discards acquired control experience. We present LACE-CRAFT, which compares…
-
RoboAware: Learning to Coordinate Embodied Skills from Counterfactual Outcomes
arXiv cs.RO (Robotics)
arXiv:2610.11480v1 Announce Type: new Abstract: Embodied coding agents can combine modular robot skills with frozen end-to-end policies, yet effective composition requires anticipating which policy family will succeed in the current…
-
CAPABLE: Capability-Aware Policy Adaptation via Behavioral Latent Encoding
arXiv cs.RO (Robotics)
arXiv:2610.11971v1 Announce Type: new Abstract: Vision-language-action (VLA) policies assume the embodiment on which they were trained and can fail when a joint fault changes how commanded actions are physically executed. Existing…
-
WAND: Learning Robust Navigation under Complex Wind Disturbances and Dense Obstacles for Quadrotors
arXiv cs.RO (Robotics)
arXiv:2610.11809v1 Announce Type: new Abstract: Robust navigation in cluttered environments remains a fundamental challenge for quadrotors, particularly when strong wind disturbances arise, which perturb vehicle dynamics, limit control…
-
RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments
arXiv cs.RO (Robotics)
arXiv:2610.12424v1 Announce Type: new Abstract: A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot…
-
YOCO: You Only Calibrate Once! Fast Mocap Calibration for Dexterous Teleoperation
arXiv cs.RO (Robotics)
arXiv:2610.11657v1 Announce Type: new Abstract: Dexterous teleoperation requires reliable human-hand state estimations. However, common low-cost motion-capture gloves and markerless trackers often exhibit biases that vary across users…
-
ManiUnit: A Manipulation Skill Dataset and Benchmark for Long-Horizon Tasks
arXiv cs.RO (Robotics)
arXiv:2610.12089v1 Announce Type: new Abstract: Long-horizon mobile manipulation requires a robot to navigate multi-room environments and execute a sequence of manipulation skills under a single natural language instruction. Learning and…
-
PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving
arXiv cs.RO (Robotics)
arXiv:2610.11382v1 Announce Type: new Abstract: World models in end-to-end autonomous driving predict future scene evolution to provide foresight for trajectory planning. Existing methods mainly study how to predict the future and how to…
-
OmniDex: Scaling Dexterous Hand Grasping to Diverse Cluttered Scenes
arXiv cs.RO (Robotics)
arXiv:2610.11194v1 Announce Type: new Abstract: Dexterous grasping is the foundational primitive in embodied AI, demanding massive data to train robust models. As real-world data collection is expensive, simulation has become the…
-
CSF: Contextual Safety Filtering for Motion Generators
arXiv cs.RO (Robotics)
arXiv:2610.12467v1 Announce Type: new Abstract: Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existing…
-
Humanoid World Action Model With Joint State--Action Generation
arXiv cs.RO (Robotics)
arXiv:2610.12026v1 Announce Type: new Abstract: Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from multimodal observations, while World Action…
-
LeWAM: A JEPA World Action Model with Diffusion-Steering-Based MPC
arXiv cs.RO (Robotics)
arXiv:2610.12407v1 Announce Type: new Abstract: World action models (WAMs) predict actions and future observations, typically from a reconstruction-based representation that carries noisy, redundant information which can complicate…
-
Altered Thoughts, Altered Actions: Reasoning Chain as Control Surface for a Vision-Language-Action Policy
arXiv cs.RO (Robotics)
arXiv:2603.12717v3 Announce Type: replace Abstract: Vision-language-action policies map camera images and natural-language instructions to a robot's motor actions. Some of these policies are designed to reason in text before acting…
-
World-Ego Modeling for Embodied Video Generation in Long-Horizon Navigation-Manipulation Tasks
arXiv cs.RO (Robotics)
arXiv:2605.19957v2 Announce Type: replace-cross Abstract: Embodied video world models typically capture both scene evolution and the robot's behavior, which we refer to as the \emph{world} and the \emph{ego}, respectively. The world and…
-
Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
arXiv cs.RO (Robotics)
arXiv:2610.10857v1 Announce Type: cross Abstract: Behavior cloning (BC) in non-Markovian environments is a challenging problem because policies have to reason over contextual information over long horizons. Existing policy architectures…
-
Seed2Scale: A Self-Evolving Data Engine with Parallel Worlds Expansion for Scalable Robot Learning
arXiv cs.RO (Robotics)
arXiv:2603.08260v2 Announce Type: replace Abstract: Existing data generation methods for robot learning suffer from limited exploration, embodiment gaps, low signal-to-noise ratios, and domain shifts, leading to performance degradation…
-
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
arXiv cs.RO (Robotics)
arXiv:2610.12470v1 Announce Type: new Abstract: While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods predominantly imitate demonstrated motions…
-
Video Prediction Policy 2: Predict Better, Act Better
arXiv cs.RO (Robotics)
arXiv:2610.10270v2 Announce Type: replace-cross Abstract: World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that…
-
Being-M0.7: A Latent World-Action Model for Humanoid Robots
arXiv cs.RO (Robotics)
arXiv:2610.11283v1 Announce Type: new Abstract: Humanoid loco-manipulation requires coordinated locomotion and manipulation informed by future scene evolution and whole-body motion, yet learning these capabilities is constrained by scarce…
-
ActiveReg: Information-Driven Active Regional Probing for Partial-to-Full Bone Registration
arXiv cs.RO (Robotics)
arXiv:2610.11003v1 Announce Type: new Abstract: Accurate bone registration is essential for orthopedic surgical navigation and robotic assistance. In a common workflow, the surgeon needs to identify and probe a number of prescribed…
-
VioLA: Learning Generalist Humanoid Control Policies from Human Data
arXiv cs.RO (Robotics)
arXiv:2610.12435v1 Announce Type: new Abstract: Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the…
-
Noise-Induced Navigation in Non-convex Domains and Compact Manifolds
arXiv cs.RO (Robotics)
arXiv:2610.10949v1 Announce Type: cross Abstract: In this note, we study the problem of designing a feedback law that globally steers a system to a prescribed target configuration. Even if the system is fully actuated, topological…
-
Acting from Belief, Looking When Needed: A Bayesian Spatial World Model for Navigation under Intermittent Perception
arXiv cs.RO (Robotics)
arXiv:2610.11591v1 Announce Type: new Abstract: Robot navigation commonly uses wide-coverage, high-frequency sensing to reduce partial observability; this reliance becomes restrictive when another task temporarily redirects a shared sensor…
-
Real-time Estimator of Actuator Control and Health (REACH) on an Eel-Inspired Soft Robot
arXiv cs.RO (Robotics)
arXiv:2608.14865v2 Announce Type: replace Abstract: An actuator health estimation algorithm for a soft swimming robot that can perform anguilliform swimming is developed. Due to harsh operational environments of underwater robots, and the…
-
MiniWAM: Learning Compact Future Targets for Efficient World-Action Modeling
arXiv cs.RO (Robotics)
arXiv:2610.12194v1 Announce Type: new Abstract: World modeling has emerged as an effective co-training objective for robot policies, giving rise to World Action Models (WAMs) that jointly predict actions and future states. However, most…
-
RoboTalk: Learning Multi-Robot Communication and Coordination from Multimodal Demonstrations
arXiv cs.RO (Robotics)
arXiv:2609.23997v2 Announce Type: replace Abstract: Multi-robot collaboration could enable more efficient and scalable solutions to complex robotic tasks, but collaboration under partial observability remains challenging. Natural-language…
-
quARtet Marker: A 3D-Printable Multi-Tag Fiducial for Robust Near-Frontal Pose Estimation
arXiv cs.RO (Robotics)
arXiv:2610.01072v2 Announce Type: replace Abstract: Robotic manipulation of labware is difficult when transparent or reflective objects must be identified and localized. Coded planar fiducials are a practical retrofit: easy to print, they…
-
Cross-Embodiment Robot Foundation World Models with Latent Actions
arXiv cs.RO (Robotics)
arXiv:2610.10846v1 Announce Type: new Abstract: The diversity of robot embodiments and action spaces makes it challenging to build robot world models that generalize across different embodiments. We introduce the Latent Action-Conditioned…
-
PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning
arXiv cs.RO (Robotics)
arXiv:2610.11168v1 Announce Type: new Abstract: Robotic manipulation often contains repeated motions whose local observations look similar at different phases. When these phases require different actions, a policy that relies mainly on the…
-
Higher-Order Action Supervision Makes A Strong Policy Class
arXiv cs.RO (Robotics)
arXiv:2610.11175v1 Announce Type: new Abstract: Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving many complex tasks. However, these methods…
-
FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems
arXiv cs.RO (Robotics)
arXiv:2610.12432v1 Announce Type: new Abstract: Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates. Safety filters separate them at action…
-
IndustrialVLA-Bench: A Traceable Multi-Axis Evaluation of Open Robot Policy Models
arXiv cs.RO (Robotics)
arXiv:2609.25562v2 Announce Type: replace Abstract: Open robot policies increasingly follow two paradigms: vision-language-action models (VLAs) directly map observations and instructions to actions, whereas world-action models (WAMs)…
-
StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models
arXiv cs.RO (Robotics)
arXiv:2610.07756v2 Announce Type: replace Abstract: Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process the…
-
More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models
arXiv cs.RO (Robotics)
arXiv:2510.04532v2 Announce Type: replace-cross Abstract: Vision-Language Model (VLM) driving agents promise explainable end-to-end autonomy by first producing natural-language reasoning and then predicting trajectory planning. However…
-
Generative Neural Retargeting for Human-to-Robot Dexterous Manipulation
arXiv cs.RO (Robotics)
arXiv:2610.12440v1 Announce Type: new Abstract: Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed directly on robots. Inverse kinematics…
-
GATOR: Generative and Agentic 3D Object Reconstruction From Casual Images
arXiv cs.RO (Robotics)
arXiv:2610.11215v1 Announce Type: cross Abstract: Reconstructing complete, scene-aligned 3D objects from casual images requires integrating sparse, uncertain observations and inferring surfaces hidden by occlusions. We present GATOR, a…