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 storiesFrom Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
arXiv:2609.21788v1 Announce Type: new Abstract: A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critic…
PopNavShift: Stress-Testing Social Navigation under Behavioral Population Shift
arXiv:2609.21838v1 Announce Type: new Abstract: Social-navigation algorithms are often evaluated under a fixed pedestrian-behavior distribution, despite substan…
CARF: Contrastive Attraction-Repulsion of Failure-Guided Flow Matching
arXiv:2609.21982v1 Announce Type: new Abstract: Robot demonstration collection often produces imperfect or failed trajectories in addition to successful demonst…
SeeQ: Training Generalist Value Functions for Long-Horizon Robotic Manipulation
arXiv:2609.22085v1 Announce Type: new Abstract: Despite rapid progress, generalist robot policies remain brittle on complex, long-horizon tasks that comprise mu…
Signal-Centric Remote Sensing via Alternative Preprocessing and Acoustic Processing for ML-Driven Applications
arXiv:2609.21123v1 Announce Type: cross Abstract: The dominant method of processing sonar data is using image-based representations, requiring the preprocessing…
A Fully Differentiable Neuro-Soft-Symbolic Framework for Perceptual Task Planning
arXiv:2609.21221v1 Announce Type: cross Abstract: Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning va…
A Scene Language Model for Open-Vocabulary Scene Mapping
arXiv:2609.21400v1 Announce Type: cross Abstract: Open-vocabulary 3D scene mapping aims to build a persistent representation of the objects in an environment. E…
MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation
arXiv:2609.21474v1 Announce Type: cross Abstract: Fast-WAM shows that video-action co-training improves control without generating future video at inference, ma…
Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering
arXiv:2609.21502v1 Announce Type: cross Abstract: Recent 3D foundation models enable generalizable geometric reasoning from RGB images but remain limited in per…
SFVO: Decoupled Confidence-Guided Stereo-Flow Visual Odometry with Bidirectional PnP
arXiv:2609.21754v1 Announce Type: cross Abstract: Deep learning-based visual odometry (VO) has achieved significant progress, yet most existing methods focus on…
PRIME: Perception Feedback with Situational Memory Embeddings in VLA Models
arXiv:2609.22040v1 Announce Type: cross Abstract: Current Vision-Language-Action (VLA) models for autonomous driving operate primarily through feedforward infer…
Advancing Minimally Invasive Precision Surgery in Large Open Cavities with Robotic Flexible Endoscopy
arXiv:2511.14458v2 Announce Type: replace Abstract: Flexible robots hold great promise for enhancing minimally invasive surgery (MIS) by providing superior dext…
ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation
arXiv:2603.03279v2 Announce Type: replace Abstract: Achieving autonomous and versatile whole-body loco-manipulation remains a central barrier to making humanoid…
FastLoop: Parallel Loop Closing with GPU-Acceleration in Visual SLAM
arXiv:2603.17201v2 Announce Type: replace Abstract: Visual SLAM systems combine visual tracking with global loop closure to maintain a consistent map and accura…
Backup-Based Safety Filters: A Comparative Review of Backup CBF, Model Predictive Shielding, and gatekeeper
arXiv:2604.02401v2 Announce Type: replace Abstract: This paper revisits three backup-based safety filters -- Backup Control Barrier Functions (Backup CBF), Mode…
PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation
arXiv:2606.00515v2 Announce Type: replace Abstract: Contact-rich manipulation demands both high-level semantic reasoning and the safe regulation of high-frequen…
Rollout Total Correlation for Deep Reinforcement Learning
arXiv:2209.05333v2 Announce Type: replace-cross Abstract: Learning task-relevant representations is crucial for reinforcement learning. Recent approaches aim to…
Provably Optimal Reinforcement Learning under Safety Filtering
arXiv:2510.18082v3 Announce Type: replace-cross Abstract: Recent advances in reinforcement learning (RL) enable its use on increasingly complex tasks, but the l…
Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning
arXiv:2604.13192v2 Announce Type: replace-cross Abstract: Robust control barrier functions (CBFs) provide a principled mechanism for smooth safety enforcement u…
Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning
arXiv:2505.04193v2 Announce Type: replace-cross Abstract: Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustn…
Evolving Skill Modules under a Fixed Planner: Versioning, Rollback, and Runtime Governance for Long-Lived Robot Systems
arXiv:2604.07799v3 Announce Type: replace Abstract: Robots deployed for long periods keep improving their skills, and each update changes a released system. We …
CoAd: Constant-Time Planning for Continuous Goal Manipulation with Compressed Library and Online Adaptation
arXiv:2603.12488v2 Announce Type: replace Abstract: In many robotic manipulation tasks, the robot repeatedly solves motion-planning problems that differ mainly …
Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor Quadrotors
arXiv:2602.21583v2 Announce Type: replace Abstract: While reinforcement learning (RL) has been successfully applied to conventional quadrotors for agile and rob…
EgoPush: Egocentric Multi-Object Rearrangement for Mobile Robots via Constrained Teacher Observability
arXiv:2602.18071v2 Announce Type: replace Abstract: Humans rearrange objects in cluttered environments using egocentric perception, actively moving to keep task…
Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation
arXiv:2509.22754v2 Announce Type: replace Abstract: Autonomous driving remains a highly active research domain that seeks to enable vehicles to perceive dynamic…
Benchmarking World Models for Continual Learning on Compositional Tasks
arXiv:2609.22055v1 Announce Type: cross Abstract: A desirable property of a world model is the ability to learn continually across tasks, adapting to new enviro…
Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning
arXiv:2609.21909v1 Announce Type: cross Abstract: In this work, we conduct a systematic comparison of two state-of-the-art motion-imitation reinforcement learni…
2D GauSS-MI: Efficient Active Scene Reconstruction with Balanced Visual and Geometric Quality
arXiv:2609.21516v1 Announce Type: cross Abstract: Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within l…
AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention
arXiv:2609.20106v1 Announce Type: cross Abstract: Robotic reward models evaluate task execution from visual observations, but their predictions can change with …
Talk to Me, Jarvis: An Open-Source Edge-Deployable Voice Assistant Framework for Autonomous Racecars
arXiv:2609.21109v1 Announce Type: cross Abstract: Recent advances in large language models have improved their effectiveness as back-end components for voice as…