Research
Frontier robotics research: arXiv cs.RO papers, embodied AI, VLA models, manipulation, navigation and learning systems.
Frontier robotics research: arXiv cs.RO papers, embodied AI, VLA models, manipulation, navigation and learning systems.
Latest in Research
3542 stories$\mu$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models
arXiv:2606.12497v1 Announce Type: cross Abstract: Vision-language-action (VLA) models predict chunks of future actions from the current observation, an assumpti…
Mana: Dexterous Manipulation of Articulated Tools
arXiv:2606.13677v1 Announce Type: new Abstract: Articulated tool manipulation remains a major challenge in dexterous robotics due to the need to coordinate inte…
Improving Robotic Generalist Policies via Flow Reversal Steering
arXiv:2606.13675v1 Announce Type: new Abstract: Generalist policies can learn a wide range of skills from diverse robot datasets. In order to solve or improve o…
SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale
arXiv:2606.13497v1 Announce Type: new Abstract: This work introduces Spatial Annotations from Robot Demonstrations with Reliability Calibration (SPARC), a risk-…
GIVE: Grounding Human Gestures in Vision-Language-Action Models
arXiv:2606.13435v1 Announce Type: new Abstract: Human communication is inherently multimodal, where language is often accompanied by non-verbal cues such as ges…
GeoHAT: Geometry-Adaptive Hybrid Action Transformer for Mobile Manipulation
arXiv:2606.13394v1 Announce Type: new Abstract: Whole-body mobile manipulation requires coordinating mobile base and manipulator under shifting viewpoints, posi…
Real-Time Execution with Autoregressive Policies
arXiv:2606.13355v1 Announce Type: new Abstract: Real-time execution, enabled by asynchronous inference that ensures both smooth action trajectories and fast rea…
Low cost, easily manufactured, highly flexible strain and touch sensitive fiber for robotics applications
arXiv:2606.13352v1 Announce Type: new Abstract: Existing stretch and touch sensors for robots are generally expensive with respect to at least one of material c…
EMG-Based Adaptation of Anisotropic Virtual Fixtures for Robot-Assisted Surgical Resection and Dissection
arXiv:2606.13340v1 Announce Type: new Abstract: In this paper, we address the development of an adaptive assistance system for robot-assisted laparoscopic surge…
See Selectively, Act Adaptively: Dual-Level Structural Decomposition for Bimanual Robot Manipulation
arXiv:2606.13279v1 Announce Type: new Abstract: In bimanual robotic manipulation, task-relevant visual information varies with the task stage and context, while…
Proprioceptive-visual correspondence enables self-other distinction in humanoid robots
arXiv:2606.13222v1 Announce Type: new Abstract: Distinguishing self from others is a prerequisite for social intelligence, yet humanoid robots that increasingly…
FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation
arXiv:2606.13102v1 Announce Type: new Abstract: Despite the success of vision-based generalist robotic policies, existing tactile-based policies remain tied to …
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
arXiv:2606.13040v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detect…
GenHOI: Contact-Aware Humanoid-Object Interaction by Imitating Generated Videos without Task-Specific Training
arXiv:2606.12995v1 Announce Type: new Abstract: Humanoid-Object Interaction (HOI) is a fundamental capability for humanoid robots, yet it remains challenging du…
Trajectory-Level Redirection Attacks on Vision-Language-Action Models
arXiv:2606.12978v1 Announce Type: new Abstract: Vision-language-action (VLA) policies bring natural language into closed-loop robot control, enabling robots to …
Towards Reliable Sequential Object Picking in Clutter: The Runner-up Solution to RGMC 2025
arXiv:2606.12954v1 Announce Type: new Abstract: As a long-standing challenge in robotic manipulation, stable and efficient grasping in cluttered environments is…
An Embodied Simulation Platform, Benchmark, and Data-Efficient Augmentation Framework for Wet-Lab Robotics
arXiv:2606.12936v1 Announce Type: new Abstract: Wet-lab robots can improve the reproducibility, throughput, and safety of biomedical experiments, but scaling th…
DARRMS -- An Efficient Algorithm for Dynamic Attention Radius in Resource-Constrained Multi-Agent Systems
arXiv:2606.12614v1 Announce Type: new Abstract: Multi-agent systems are integral tools for various domains such as robotics, cybersecurity, and autonomous vehic…
From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation
arXiv:2606.12603v1 Announce Type: new Abstract: Autonomous long-horizon sidewalk navigation is essential for micro-mobility applications such as robotic food de…
G-MAPP: GPU-accelerated Multi-Agent Planning and Perception for Reactive Motion Generation
arXiv:2606.12579v1 Announce Type: new Abstract: Reactive motion generation in unstructured environments remains an open challenge in robotics. Due to the comput…
Foresight: Iterative Reasoning About Clues that Matter for Navigation
arXiv:2606.12550v1 Announce Type: new Abstract: Open-world mapless navigation from sparse language instructions requires resolving underspecified goals and infe…
Trojan Attacks on Neural Network Controllers for Robotic Systems
arXiv:2602.05121v2 Announce Type: replace-cross Abstract: Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory t…
RGB-S: Image-Aligned Tactile Saliency for Robust Dexterous Manipulation
arXiv:2606.08765v2 Announce Type: replace Abstract: Effective visuo-tactile integration is critical for robotic dexterous manipulation, especially when visual o…
Lexicographic Minimum-Violation Motion Planning using Signal Temporal Logic
arXiv:2604.20428v2 Announce Type: replace Abstract: Motion planning for autonomous vehicles often requires satisfying multiple conditionally conflicting specifi…
Multi-Modal Multi-Agent Robotic Cognitive Alignment enabled by Non-Invasive Consumer Brain Computer Interfaces: A Proof of Concept Exploration
arXiv:2606.13190v1 Announce Type: new Abstract: While non-verbal behaviors and expressive movements are essential for natural human-robot interaction, existing …
Stubborn: A Streamlined and Unified Reinforcement Learning Framework for Robust Motion Tracking and Fall Recovery for Humanoids
arXiv:2606.12814v1 Announce Type: new Abstract: Recent reinforcement learning approaches have shown great promise in improving humanoid motion tracking performa…
Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration
arXiv:2606.12475v1 Announce Type: new Abstract: Human-robot collaboration (HRC) combines the complementary strengths of humans and robots to improve task effici…
QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
arXiv:2511.17221v2 Announce Type: replace-cross Abstract: Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key …
Hello Robot is recognized by World Economic Forum as a tech pioneer
The World Economic Forum has honored Hello Robot, whose Stretch system provides mobile manipulation to older adults and people with disabilities. The post Hello…
AI could uncover new physics faster but there’s a surprising catch
Scientists found that transfer learning can make the search for new physics in the universe much faster, slashing the need for expensive simulations. Yet the ap…