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
4787 storiesRAMS: Resource-Adaptive and Detection-Conditioned Model Switching for Embedded Edge Perception
arXiv:2606.14716v1 Announce Type: cross Abstract: Edge object detection on embedded hardware requires balancing inference latency and detection quality under ch…
Geometric Action Model for Robot Policy Learning
arXiv:2606.17046v1 Announce Type: new Abstract: Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot ac…
R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies
arXiv:2606.17040v1 Announce Type: new Abstract: Spatial generalization is critical for imitation-learned manipulation policies, but achieving it typically requi…
ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning
arXiv:2606.17011v1 Announce Type: new Abstract: Human interventions provide crucial corrective signals for post-training Vision-Language-Action (VLA) models. Ho…
When Should a Robot Replan? Regret-Guided Update Scheduling in Time-Varying MDPs
arXiv:2606.16972v1 Announce Type: new Abstract: Robots operating in non-stationary environments must continually adapt their policies as the dynamics drift, but…
SidewalkBench: Benchmarking Visual Navigation on Urban Sidewalks
arXiv:2606.16953v1 Announce Type: new Abstract: Urban sidewalk navigation presents significant challenges due to complex structural layouts, dynamic pedestrian …
ExoTraj: A General Lower-limb Exoskeleton Assistance Policy for Complex Environments
arXiv:2606.16876v1 Announce Type: new Abstract: Adaptive torque prediction in dynamic exoskeleton scenarios requires expensive motion capture systems, which are…
Pride and Prejudice: Toward an Information-Theoretic Framework for Mutually Communicative Driver Behavior Modeling
arXiv:2606.16735v1 Announce Type: new Abstract: Mixed autonomy driving becomes unsafe and inefficient when autonomous vehicles (AVs) and human-driven vehicles (…
VENOM: Versatile Embodied Network for Omni-bodied Motion tracking
arXiv:2606.16696v1 Announce Type: new Abstract: Achieving expert-level expressive full-body motion tracking across multiple humanoids solely from demonstration …
WaveSync: Constrained Wavefront Optimization for Synchronized Co-Speech Gestures in Humanoid Robots
arXiv:2606.16600v1 Announce Type: new Abstract: Expressive co-speech gestures are crucial for natural human-robot interaction, but generating them on physical h…
Steering Generative Reinforcement Learning into Stable Robotic Controller
arXiv:2606.16572v1 Announce Type: new Abstract: Diffusion and flow-based generative policies provide a powerful policy class for reinforcement learning by induc…
ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion
arXiv:2606.16542v1 Announce Type: new Abstract: Humanoids deployed in human-centered environments must handle force-interactive tasks, where external contacts i…
APEX: Adaptive Policy Execution for Precise Manipulation
arXiv:2606.16504v1 Announce Type: new Abstract: Modern imitation learning methods, including visuomotor and Vision-Language-Action (VLA) policies, typically out…
ART-Glove: Articulated Tactile Glove for Contact-Grounded Dexterous Interaction Capture
arXiv:2606.16370v1 Announce Type: new Abstract: We present ART-Glove, an articulated tactile glove designed to capture contact-grounded dexterous demonstrations…
TopoRetarget: Interaction-Preserving Retargeting for Dexterous Manipulation
arXiv:2606.16272v1 Announce Type: new Abstract: Human hand-object demonstrations provide dense reference motions for training dexterous manipulation reinforceme…
Scaling Short-Term Memory of Visuomotor Policies for Long-Horizon Tasks
arXiv:2606.16178v1 Announce Type: new Abstract: Many robotic tasks require short-term memory, whether it's retrieving an object that's no longer visible or turn…
Leveraging Deep Learning for Object and Position Recognition of Load Carriers for Autonomous Logistics Vehicles
arXiv:2606.16042v1 Announce Type: new Abstract: This work explores the use of artificial intelligence in mobile robotics to achieve autonomous detection and pos…
$\lambda$-Reachability: Geometric-Horizon Safety Bellman Equations for Humanoid Safety
arXiv:2606.16022v1 Announce Type: new Abstract: We introduce $\lambda$-Reachability, a scalable approach to Hamilton--Jacobi safety analysis for high-dimensiona…
Friction Characterization of a Cable-Driven Differential Actuation System for Lower-Limb Exoskeletons
arXiv:2606.15997v1 Announce Type: new Abstract: Lower-limb exoskeletons require actuation systems that can provide accurate joint torque control while preservin…
Identification of a Physics-Based Electrical Power Consumption Model for the Unitree G1 Humanoid Arm
arXiv:2606.15915v1 Announce Type: new Abstract: Accurate prediction of electrical power consumption is essential for energy-aware motion planning, battery manag…
VL2Spike: Spike-driven Distillation from VLMs for Low-Power Visual Perception in Embodied AI
arXiv:2606.15898v1 Announce Type: new Abstract: Spiking neural networks (SNNs) are brain-inspired, event-driven models that compute with sparse spikes, which en…
FlashNav: Ultra-Fast Policy Training for Robot Navigation within 20 Seconds
arXiv:2606.15846v1 Announce Type: new Abstract: Deep reinforcement learning has shown strong potential for robot navigation, but its practical deployment is sti…
LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies
arXiv:2606.15768v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) leverage large-scale vision-language pretraining for semantic robot control…
Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning
arXiv:2606.15685v1 Announce Type: new Abstract: Embodied Continual Learning (ECL) aims to enable robots to continually acquire new manipulation tasks while reta…
TO-SoFiT: Topology Optimization of Hydraulic Soft Fish Tail Design for programmable undulating locomotion
arXiv:2606.15645v1 Announce Type: new Abstract: Soft robots leverage compliant materials to generate motion through controlled elastic deformation, making them …
Perfect Demo Makes Poor Teacher: Learning Robust Alignment from Critical Motion Segments
arXiv:2606.15587v1 Announce Type: new Abstract: Expert demonstrations are widely assumed to be the gold standard for robot imitation learning. Yet for fine-grai…
SAPS: Shared Autonomy for Policy Steering by Blending Teleoperation with a Pretrained VLA
arXiv:2606.15568v1 Announce Type: new Abstract: Recent advancements in Vision-Language-Action (VLA) models have demonstrated impressive generalist capabilities …
Transferring Contact, Not Just Motion: Compliant Grasping Across Dexterous Hands
arXiv:2606.15516v1 Announce Type: new Abstract: Dexterous grasping depends on contact regulation, not motion alone. Stable manipulation requires fingers to main…
A Bilateral Teleoperation Framework for Dexterous Manipulation
arXiv:2606.15434v1 Announce Type: new Abstract: Dexterous teleoperation requires precise arm-hand coordination, low-latency feedback, and robust interaction in …
MapDream: Task-Driven Map Learning for Vision-Language Navigation
arXiv:2602.00222v3 Announce Type: replace Abstract: Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observ…