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 storiesFLINT: Fast Lightweight Inference for Traversability
arXiv:2609.26857v1 Announce Type: new Abstract: Navigation in off-road conditions is challenging due to the lack of structure. There is no fixed vocabulary for …
Backdoors in Learning-Based Industrial Robotic Arm Manipulation: An Empirical Security Study
arXiv:2609.26868v1 Announce Type: new Abstract: Learning-based models (e.g., visuomotor and Vision-Language-Action (VLA)) are increasingly explored for industri…
Intelligence Across Embodiments
arXiv:2609.27095v1 Announce Type: new Abstract: Robotic embodiment encompasses the sensing, kinematics, dynamics, geometry, actuation, and control through which…
BladeMaster: Real-Time Robotic Cutting Simulation with Online-Generated Persistent Discontinuities
arXiv:2609.27342v1 Announce Type: new Abstract: Cutting changes both the shape and topology of deformable objects, making accurate simulation challenging for ro…
Reflection-Aware Reasoning for Non-Line-of-Sight Pedestrian Localization
arXiv:2609.27346v1 Announce Type: new Abstract: Reliable localization of non-line-of-sight (NLOS) pedestrians is critical for safe urban autonomous driving, yet…
Omnidirectional Amphibious Locomotion via Internal Mass Actuation
arXiv:2609.27358v1 Announce Type: new Abstract: Field robots must traverse varied terrain and obstacles while remaining robust to water, debris, vegetation, and…
Automotive mmWave Spinning Radar Place Recognition with Spatially Gated Feature-Correlation Representation
arXiv:2609.27394v1 Announce Type: new Abstract: Automotive spinning FMCW radar provides dense, $360^\circ$ sensing and remains reliable under poor illumination …
Compressed delayed-information projection for six-degree-of-freedom underwater vehicle navigation under delayed acoustic positioning
arXiv:2609.27439v1 Announce Type: new Abstract: Delayed acoustic positioning packets constrain historical navigation states, but a current-time update evaluates…
CoRelNav: Collaborative Relational Navigation for Multi-Robot Spatially Constrained Semantic Navigation
arXiv:2609.27720v1 Announce Type: new Abstract: Spatially constrained semantic navigation requires robots to identify targets specified not only by semantic cat…
InfiNoVA: Infinite Novel View Augmentation for Viewpoint Invariant Robot Policies
arXiv:2609.27734v1 Announce Type: new Abstract: Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing…
BIDETA: Brain-Inspired Data-Efficient Tactile Adaptation for Unseen Sensors
arXiv:2609.08673v2 Announce Type: replace Abstract: Vision-based tactile sensors provide high-resolution contact information for robotic perception and contact-…
LLM-Powered Socially Assistive Robot-Delivered Cognitive Behavioral Therapy Exercises: an Exploratory Study with University Students
arXiv:2402.17937v2 Announce Type: replace Abstract: Mental health is a significant healthcare challenge, and cognitive behavioral therapy (CBT) is a widely used…
Latent evolving World Action Model
arXiv:2609.27455v1 Announce Type: cross Abstract: World Action Models (WAMs) jointly model action generation and environment dynamics and are mostly built on pr…
Impact-Time Guidance via Normal Contraction to a Time-to-Go Isochron
arXiv:2609.26906v1 Announce Type: cross Abstract: We develop a contraction-based perspective on impact-time guidance that augments a baseline homing command wit…
LiMA: Bridging Long-term Imagination to Real-time Dexterous Manipulation via Asynchronous Diffusion
arXiv:2609.28431v1 Announce Type: new Abstract: Dexterous manipulation demands long-term foresight and rapid reactive control. Vision-Language-Action (VLA) mode…
Watch, Recall, Act: Always-On Robots in Concurrent Embodied Streams
arXiv:2609.28429v1 Announce Type: new Abstract: An always-on robot faces an endless stream that never resets: instructions arrive and lapse, the scene changes, …
BrickCraft-Duo: Efficient Dual-Arm Skill Learning and Refinement for Compositional Long-Horizon Assembly
arXiv:2609.28281v1 Announce Type: new Abstract: Interlocking brick assembly provides a representative testbed for evaluating real-world robotic manipulation cap…
Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers
arXiv:2609.28247v1 Announce Type: new Abstract: Large Language Models (LLMs) introduce an exciting new paradigm for planning and navigation in robotics, but fai…
GLASS: Architecture-Tuned, Composable, Device-Side Linear Algebra for Edge Robotics and Beyond
arXiv:2609.28179v1 Announce Type: new Abstract: GPU robotics lacks the reusable numerical infrastructure of mature CPU stacks, instead relying on compiler frame…
Anchor-Free Hidden-Target Seeking via Certified Self-Calibration under Correlated Odometry
arXiv:2609.27905v1 Announce Type: new Abstract: We study hidden-target seeking in an anchor-free regime where neither the vehicle, the relay, nor the target has…
Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulation
arXiv:2609.27780v1 Announce Type: new Abstract: Vision-language robot manipulation policies can follow semantic instructions, but adapting them to a new procedu…
Less Language, More Latents: Annotation-Efficient VLAs for Driving
arXiv:2609.27747v1 Announce Type: new Abstract: Vision-language-action models (VLA) promise human-steerable autonomous driving, but their training is bottleneck…
Qualcomm to acquire PickNik Robotics and keep MoveIt open-source
Qualcomm plans to integrate the Dragonwing and Arduino platforms with the MoveIt open-source manipulation framework. The post Qualcomm to acquire PickNik Roboti…
LiDAS: Lighting-driven Dynamic Active Sensing for Nighttime Perception
arXiv:2512.08912v2 Announce Type: replace-cross Abstract: Nighttime environments pose significant challenges for camera-based perception, as existing methods pa…
AgenticDiffusion: Multi-View Reasoning with View-Conditioned Diffusion Planning for Vision-Based UAV Navigation
arXiv:2606.04111v2 Announce Type: replace Abstract: Vision-based UAV navigation becomes challenging when navigation targets are distributed across complementary…
Closed-Loop Object-Informed Control for Non-Prehensile Robot Manipulation
arXiv:2605.30778v2 Announce Type: replace Abstract: Non-prehensile robot manipulation is challenging due to discontinuous, long-horizon interactions between the…
Wheel-loader V-Cycle Automation with Deep Koopman MPC
arXiv:2609.26580v1 Announce Type: new Abstract: The repeated forward-reverse maneuvers performed by wheel loaders during earthmoving operations make them well s…
RoboTwin-Phys: Do WAMs and VLAs Understand the Physical World?
arXiv:2609.26292v1 Announce Type: new Abstract: Physical-condition diversity is largely missing from current benchmarks for robot manipulation. While large-scal…
High-Bandwidth Biomimetic Finger for Tactile-Transparent Remote Texture Sensing
arXiv:2609.26256v1 Announce Type: new Abstract: High-fidelity tactile feedback is essential for robotic teleoperation, enabling precise manipulation and critica…
StepTrigger: Contact-State-Triggered Backdoor Attacks on VLM-Powered Legged Robots
arXiv:2609.26131v1 Announce Type: new Abstract: Large language models and vision-language models are increasingly used as high-level planners in robotic systems…