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 storiesMMD-SLAM: Structure-Enhanced Multi-Meta Gaussian Distribution-Guided Visual SLAM
arXiv:2606.19874v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has significantly boosted novel view synthesis and high-fidelity scene reconstructi…
Periodic robust robotic rock chop via virtual model control
arXiv:2508.02604v3 Announce Type: replace Abstract: Robotic cutting is a challenging, contact-rich manipulation task where the robot must simultaneously negotia…
Bidirectional Tutoring for Developmental Motor Learning in Robots: Co-Developed Interaction Dynamics Support Stable Learning
arXiv:2606.19728v1 Announce Type: new Abstract: Infants are well known to develop their motor skills through dense interaction with caregivers. Although such so…
Comparative Study on Agility, Efficiency, and Impact Absorption of Bipedal Robots with Active Toes
arXiv:2606.19699v1 Announce Type: new Abstract: Human legs exhibit high efficiency, agility, and impact absorption, with toes playing a crucial role in these ca…
Reinforcement Twinning for Hybrid Control of Flapping-Wing Drones
arXiv:2505.18201v2 Announce Type: replace Abstract: Controlling flapping-wing drones requires controllers that handle time-varying, nonlinear, underactuated dyn…
3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning
arXiv:2606.19451v1 Announce Type: cross Abstract: We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-leve…
FlexLAM: Resolving the Bottleneck Trade-off in Latent Action Learning
arXiv:2606.19408v1 Announce Type: cross Abstract: Latent actions provide a compact interface between action-free video and downstream decision-making, yet exist…
CTS-MoE: Implicit Terrain Adaptation via Mixture-of-Experts for Perceptive Locomotion
arXiv:2606.19633v1 Announce Type: new Abstract: Perceptive legged locomotion over discontinuous terrain (e.g., stairs, gaps, and obstacles) requires adaptive be…
Fail-RAG : A Retrieval Augmented Generation Informed Framework for Robot Failure Identification
arXiv:2606.19598v1 Announce Type: new Abstract: Industry automation is witnessing an evolution in robotics driven by both technological breakthroughs and societ…
pdSTL: Probabilistic Differentiable Signal Temporal Logic for Stochastic Systems
arXiv:2606.19561v1 Announce Type: new Abstract: Autonomous robots operating in uncertain environments must satisfy complex temporal and safety specifications de…
Zero-Shot Long-Horizon Dexterous Manipulation via Multi-View 3D-Grounded VLM Reasoning
arXiv:2606.19340v1 Announce Type: new Abstract: We present a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into…
Spatially Stratified Distillation for Heterogeneous Radar Place Recognition
arXiv:2606.18687v1 Announce Type: cross Abstract: Scalable, all-weather place recognition increasingly relies on heterogeneous radar place recognition to bridge…
Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation
arXiv:2606.18960v1 Announce Type: cross Abstract: Action-conditioned world models have emerged as a promising paradigm for robot learning, offering a scalable a…
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
arXiv:2606.19253v1 Announce Type: cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-s…
Steering Flexible Linear Objects in Planar Environments by Two Robot Hands Using Euler's Elastica Solutions
arXiv:2501.02874v5 Announce Type: replace Abstract: The manipulation of flexible objects such as cables, wires and fresh food items by robot hands forms a speci…
R2BC: Multi-Agent Imitation Learning from Single-Agent Demonstrations
arXiv:2510.18085v2 Announce Type: replace Abstract: Imitation Learning (IL) is a natural way for humans to teach robots, particularly when high-quality demonstr…
TurboMap: GPU-Accelerated Local Mapping for Visual SLAM
arXiv:2511.02036v4 Announce Type: replace Abstract: In real-time Visual SLAM systems, local mapping must operate under strict latency constraints, as delays deg…
Bench-Push: Benchmarking Pushing-based Navigation and Manipulation Tasks for Mobile Robots
arXiv:2512.11736v2 Announce Type: replace Abstract: Mobile robots are increasingly deployed in cluttered environments with movable objects, posing challenges fo…
Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation
arXiv:2606.18594v1 Announce Type: new Abstract: In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoo…
Tilt-Ropter: A Fully Actuated Hybrid Aerial-Terrestrial Vehicle with Tilt Rotors and Passive Wheels
arXiv:2602.01700v2 Announce Type: replace Abstract: In this work, we present Tilt-Ropter, a fully actuated hybrid aerial-terrestrial vehicle (HATV) that integra…
Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition
arXiv:2602.04401v2 Announce Type: replace Abstract: Visual Place Recognition (VPR) is a key component for localisation in Global Navigation Satellite System (GN…
Embedding Semantic Risk into Distance Fields and CBFs for Online Monocular Safe Control
arXiv:2606.01605v2 Announce Type: replace Abstract: We propose an online monocular perception-to-control framework that embeds semantic risk into the distance f…
SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumping
arXiv:2606.18625v1 Announce Type: new Abstract: Robotic jumping is pivotal in applications such as search and rescue and logistics, where crossing obstacles and…
VEGA: Learning Navigation VLAs from In-the-Wild Egocentric Video with Geometric Trajectory Supervision
arXiv:2606.18426v1 Announce Type: new Abstract: We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocent…
High-Degree-of-Freedom Lightweight Bioinspired Leg for Enhanced Mobility in Small Robots
arXiv:2606.18680v1 Announce Type: new Abstract: In microrobotics, enhancing locomotion capabilities by increasing the degrees of freedom (DoF) of leg mechanisms…
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
arXiv:2606.18375v1 Announce Type: new Abstract: World foundation models (WFMs) are powerful simulators, yet they predominantly operate in a single-view setting …
Why Automate This? Exploring Correlations Between Desire for Robotic Automation, Invested Time and Well-Being
arXiv:2501.06348v4 Announce Type: replace-cross Abstract: Understanding the motivations underlying the human inclination to automate tasks is vital for developi…
Guava: An Effective and Universal Harness for Embodied Manipulation
arXiv:2606.18363v1 Announce Type: new Abstract: Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agen…
Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures
arXiv:2606.18328v1 Announce Type: new Abstract: Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoi…
Congestion-Aware Robot Tour Planning in Crowded Environments
arXiv:2606.19031v1 Announce Type: new Abstract: Autonomous mobile service robots are often required to complete tours that require navigating through a set of l…