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
6171 storiesTowards AI-enhanced control: a numerical technique for trajectory smoothing of a parallel robot for pancreatic surgery
arXiv:2609.20499v1 Announce Type: new Abstract: The paper presents a numerical approach for the end-effector trajectory smoothing of a parallel robot designed f…
Integrated Guidance and Control of a Mother-Child UAV-UGV System for Cooperative Missions
arXiv:2609.20540v1 Announce Type: new Abstract: Autonomous recovery of a small multirotor onto a hovering multirotor carrier differs from recovery onto ground o…
Learning Slope-Adaptive Whole-Body Locomotion for Humanoid Robots in Roofing Construction
arXiv:2609.20558v1 Announce Type: new Abstract: Roofing requires workers to coordinate locomotion, balance, and work-related body motions on pitched surfaces, c…
OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion
arXiv:2609.20566v1 Announce Type: new Abstract: Animal demonstrations provide quadruped robots with natural and distinctive gait styles that are difficult to sp…
Walking on the Slope: Stable Bipedal Gaits with Genetic-Algorithm-Optimized Trajectories
arXiv:2609.20570v1 Announce Type: new Abstract: This paper presents the kinematic and dynamic modeling, trajectory generation, and stability analysis of an 8-de…
Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control
arXiv:2609.20575v1 Announce Type: new Abstract: Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and …
V2-STRep: VLM-Grounded Structured Task Representations for Reusable Robot Skills Acquired from Generated Videos
arXiv:2609.20582v1 Announce Type: new Abstract: Human manipulation videos provide rich motion and interaction cues for acquiring robot skills without robot demo…
CoRef-GS: Cooperative Referring Gaussian Splatting for Multi-Agent Scene Understanding
arXiv:2609.20586v1 Announce Type: new Abstract: Referring scene understanding for embodied robots requires grounding object- and relation-centric language queri…
Bayesian Continuum Robot Dynamics and State Estimation
arXiv:2609.20605v1 Announce Type: new Abstract: Recent factor graph approaches to continuum robot state estimation have been successful for quasi-static applica…
A Simulation Platform for AUV Fault Recovery: Exploring LLM-Based Diagnostic Strategies
arXiv:2609.20620v1 Announce Type: new Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures withou…
SmellDiffusion: Diffusion-Based Quadruped Navigation with Olfactory Scene Graphs
arXiv:2609.20624v1 Announce Type: new Abstract: A robot sent to a named gas leak must preserve gas identity, estimate the source, and navigate to the resulting …
RTK-Vision PPO for Autonomous Micro UAV Recovery on an Airborne Carrier
arXiv:2609.20629v1 Announce Type: new Abstract: Autonomous recovery of a micro unmanned aerial vehicle (UAV) onto a moving airborne carrier enables reusable dep…
TraceFlow: Guiding Frozen Flow-Matching Robot Policies with Success and Failure Traces
arXiv:2609.20646v1 Announce Type: new Abstract: A vision-language-action (VLA) policy with a flow-matching action expert generates each action chunk (a short co…
SkipVLA: Skipping VLA Steps with Classical Planning for Fast Robot Manipulation
arXiv:2609.20648v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models are a class of generalist robot policies that map camera images and language…
DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation
arXiv:2609.20649v1 Announce Type: new Abstract: Learning predictive models of contact-rich dexterous manipulation requires dense tactile interaction, but such d…
HIL-UMI: Bringing Human-in-the-Loop Post-Training of Vision-Language-Action Models to Universal Manipulation Interface
arXiv:2609.20659v1 Announce Type: new Abstract: Large-scale vision-language-action (VLA) models provide powerful priors for robot manipulation, yet adapting the…
Learning Foresight without Explicit Trajectories for 3D Diffusion Policies
arXiv:2609.20669v1 Announce Type: new Abstract: 3D diffusion policies are strong at generating geometrically grounded actions from current observations, but suc…
MAGNETAR: Multipath-Guided Spatial Posteriors for Transmitter Pose Inference in the Upper Mid-Band
arXiv:2609.20670v1 Announce Type: new Abstract: Robots that localize a radio transmitter need more than a point estimate: in cluttered rooms, one measurement is…
Towards Scaling Marine Perception with Synthetic Data
arXiv:2609.20680v1 Announce Type: new Abstract: Scalable machine learning in challenging underwater environments is strongly limited by the lack of labeled real…
Custom PX4 firmware for autonomous hybrid aerial-marine missions
arXiv:2609.20691v1 Announce Type: new Abstract: Mapping and monitoring aquatic environments can benefit from hybrid aerial-amphibious drones able to combine fli…
MILER: Semantic Mid-Level Representation for Sim-to-Real Reinforcement Learning in Unstructured Autonomous Driving
arXiv:2609.20747v1 Announce Type: new Abstract: Reinforcement learning constitutes a promising approach owing to its potential for superhuman performance and se…
OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher
arXiv:2609.20756v1 Announce Type: new Abstract: As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important …
Agile-WAM: An Agile Tactile World Action Model for Contact-Rich Robot Control
arXiv:2609.20761v1 Announce Type: new Abstract: World Action Models (WAMs) advance beyond conventional visuomotor policies by jointly predicting future world st…
GeoAAC: Geometry-Based Adaptive Action Chunking from Denoising Trajectories in VLA Policies
arXiv:2609.20776v1 Announce Type: new Abstract: Action chunking is widely used for action generation and execution in Vision-Language-Action (VLA) policies, yet…
Workspace Models: Lightweight Robotic Memory via Saliency-Driven Supervision
arXiv:2609.20820v1 Announce Type: new Abstract: Complex robotic manipulation tasks frequently require a long-term memory of past events and actions. As conditio…
Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
arXiv:2609.20822v1 Announce Type: new Abstract: Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot con…
"Your Robot Was Trained on a Lie": Collision Mesh Poisoning Attacks on Robotic Manipulation
arXiv:2609.18122v1 Announce Type: cross Abstract: Learning-enabled robotic manipulation increasingly relies on robot simulators for policy training and evaluati…
Feasibility and Singularity in High-Order Safety-Critical Control for Quadrotor UAVs
arXiv:2609.19362v1 Announce Type: cross Abstract: We study high-order safety-critical control of quadrotor teams under bounded inputs and pairwise collision-avo…
ParticleSplat: Self-supervised Object-centric Latent Particle Splatting
arXiv:2609.19463v1 Announce Type: cross Abstract: We present ParticleSplat, a self-supervised object-centric learning method that decomposes scenes into a set o…
AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend
arXiv:2609.19518v1 Announce Type: cross Abstract: We present AMB3R-SLAM, a real-time monocular SLAM system capable of reconstructing kilometer-scale trajectorie…