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 storiesAerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial Agents
arXiv:2606.12142v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are increasingly used in inspection, search and rescue, environmental monitoring…
Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning
arXiv:2606.12109v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulatio…
DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model
arXiv:2606.12105v1 Announce Type: new Abstract: Vision-language-action (VLA) models inherit a shared synchronous clock from vision-language pretraining, process…
KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility
arXiv:2606.12042v1 Announce Type: new Abstract: Deep Reinforcement Learning (DRL) has shown promise for social navigation, yet its real-world deployment remains…
VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network
arXiv:2606.12028v1 Announce Type: new Abstract: Generalizable robot manipulation requires not only task-level reasoning over unseen scenes, but also reliable gr…
MPPI-based Informative Trajectory Planning for Search and Capture of Drifting Targets with ASVs
arXiv:2606.12019v1 Announce Type: new Abstract: Autonomous surface vehicles offer an efficient solution for environmental cleanup as well as search and rescue o…
Modular Anthropomorphic Hand Design via Multi-Parameter Finger Benchmarking and Selection
arXiv:2606.11826v1 Announce Type: new Abstract: Designing anthropomorphic dexterous robotic hands remains challenging as the design space straddles morphology, …
TacCoRL: Integrating Tactile Feedback into VLA via Simulation
arXiv:2606.11743v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide strong visual, language, and action priors for robot manipulation, b…
Learning Object Manipulation from Scratch via Contrastive Interaction
arXiv:2606.11525v1 Announce Type: new Abstract: Contrastive Reinforcement Learning (CRL) has seen recent success in a wide variety of goal-conditioned robotics …
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
arXiv:2606.11324v1 Announce Type: new Abstract: We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied rea…
Model-based Optimization of Anguilliform Swimming Gaits for Soft Robotic Applications
arXiv:2606.11278v1 Announce Type: new Abstract: In this paper, we introduce the Soft Lamprey-Inspired Dual Environment Robot (SLIDER) and a proper modeling and …
APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
arXiv:2606.12366v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models that couple pretrained Vision-Language Models (VLMs) with continuous action …
Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends
arXiv:2606.12207v1 Announce Type: new Abstract: Embodied intelligence now spans navigation, household assistance, manipulation, autonomous driving, aerial agent…
Fibration Trees: A Unified Approach to Multi-Robot Motion Planning
arXiv:2606.12070v1 Announce Type: new Abstract: State space projections and decompositions have emerged as powerful tools to tackle the curse of dimensionality …
Learning Unions of Convex Sets via Invertible Latent Decomposition for Path Planning
arXiv:2606.12027v1 Announce Type: new Abstract: Collision-free path planning in cluttered, real-world environments relies on a representation of the collision-f…
Deformable In-Hand Slip-Aware Tactile Sensor with Integrated Velocity, Force/Torque, and Pressure Map Sensing
arXiv:2606.11952v1 Announce Type: new Abstract: This paper introduces a novel tactile sensor for in-hand manipulation with slip-aware control that integrates ve…
DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World
arXiv:2606.11901v1 Announce Type: new Abstract: Bimanual robot systems substantially expand manipulation capabilities, but coordinating two arms introduces addi…
Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation
arXiv:2606.11891v1 Announce Type: new Abstract: Multi-objective reinforcement learning for humanoid robots must coordinate locomotion and manipulation within a …
Human-Guided Co-Manipulation of Carbon Fiber Plies
arXiv:2606.11818v1 Announce Type: new Abstract: The handling of flexible materials is a difficult task to fully automate due to the challenges caused by the def…
Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
arXiv:2606.11767v1 Announce Type: new Abstract: Blind grasping with a dexterous hand is a crucial manipulation capability. Nevertheless, learning such tactile-o…
Explore From Sketch: Accelerating UAV Exploration in Large-scale Environments with Prior Maps
arXiv:2606.11708v1 Announce Type: new Abstract: Autonomous exploration with UAVs in large-scale, topologically complex environments often suffers from low effic…
SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning
arXiv:2606.11636v1 Announce Type: new Abstract: Vision-based navigation models, particularly foundation models, generate viable trajectories from RGB observatio…
UGV-Conditioned Multi-UAV Informative Planning on a Shared Exposure Belief
arXiv:2606.12306v1 Announce Type: new Abstract: Safe ground navigation in large, threat-augmented environments requires aerial support that actively reduces the…
NEURA Robotics to raise up to $1.4B in Series C funding for physical AI
NEURA Robotics plans to expand its platforms for robot learning and global production of humanoids and other systems. The post NEURA Robotics to raise up to $1.…
Robotics will not have a clean Llama moment
The Llama moment in robotics will not be the day a policy becomes downloadable. It will be the day another team can take that policy, adapt it to its robot, rel…
Learning robust controllers that work across many partially observable environments
In intelligent systems, applications range from autonomous robotics to predictive maintenance problems. To control these systems, the essential aspects are capt…
Teaching robot policies without new demonstrations: interview with Jiahui Zhang and Jesse Zhang
The ReWiND method, which consists of three phases: learning a reward function, pre-training, and using the reward function and pre-trained policy to learn a new…
Robot Talk Episode 136 – Making driverless vehicles smarter, with Shimon Whiteson
Claire chatted to Shimon Whiteson from Waymo about machine learning for autonomous vehicles. Shimon Whiteson is a Professor of Computer Science at the Universit…
Robot Talk Episode 137 – Getting two-legged robots moving, with Oluwami Dosunmu-Ogunbi
Claire chatted to Oluwami Dosunmu-Ogunbi from Ohio Northern University about bipedal robots that can walk and even climb stairs. Oluwami Dosunmu-Ogunbi (Wami) i…
AI detects cancer but it’s also reading who you are
AI tools designed to diagnose cancer from tissue samples are quietly learning more than just disease patterns. New research shows these systems can infer patien…