{"total":73,"rows":[{"id":"2406.08858","title":"OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning","created":"2024-06-13","cited_by_count":189,"area":null},{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2403.04436","title":"Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation","created":"2024-03-07","cited_by_count":130,"area":"deeprl"},{"id":"2502.10363","title":"BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds","created":"2025-02-14","cited_by_count":46,"area":null},{"id":"2502.00935","title":"Generalizing Safety Beyond Collision-Avoidance via Latent-Space Reachability Analysis","created":"2025-02-02","cited_by_count":45,"area":"wm"},{"id":"2409.06366","title":"One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion","created":"2024-09-10","cited_by_count":43,"area":"deeprl"},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33,"area":"wm"},{"id":"2409.15634","title":"NavRL: Learning Safe Flight in Dynamic Environments","created":"2024-09-24","cited_by_count":26,"area":"deeprl"},{"id":"2403.18765","title":"CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learning","created":"2024-03-27","cited_by_count":23,"area":"deeprl"},{"id":"2503.08564","title":"MoE-Loco: Mixture of Experts for Multitask Locomotion","created":"2025-03-11","cited_by_count":23,"area":"moe"},{"id":"2505.22974","title":"Learning coordinated badminton skills for legged manipulators","created":"2025-05-29","cited_by_count":19,"area":"deeprl"},{"id":"2405.00846","title":"Gameplay Filters: Robust Zero-Shot Safety through Adversarial Imagination","created":"2024-05-01","cited_by_count":16,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"id":"2407.02666","title":"Commonsense Reasoning for Legged Robot Adaptation with Vision-Language Models","created":"2024-07-02","cited_by_count":15,"area":"lr"},{"id":"2409.13678","title":"SoloParkour: Constrained Reinforcement Learning for Visual Locomotion from Privileged Experience","created":"2024-09-20","cited_by_count":14,"area":"deeprl"},{"id":"2410.03076","title":"Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulation","created":"2024-10-04","cited_by_count":13,"area":"deeprl"},{"id":"2505.06883","title":"FACET: Force-Adaptive Control via Impedance Reference Tracking for Legged Robots","created":"2025-05-11","cited_by_count":11,"area":"deeprl"},{"id":"2506.05997","title":"Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning","created":"2025-06-06","cited_by_count":11,"area":"deeprl"},{"id":"2509.02530","title":"Manipulation as in Simulation: Enabling Accurate Geometry Perception in Robots","created":"2025-09-02","cited_by_count":11,"area":null},{"id":"2601.07821","title":"Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation","created":"2026-01-12","cited_by_count":11,"area":"offlinerl"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2412.13238","title":"SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Models","created":"2024-12-17","cited_by_count":10,"area":"driving"},{"id":"2412.09989","title":"One Filter to Deploy Them All: Robust Safety for Quadrupedal Navigation in Unknown Environments","created":"2024-12-13","cited_by_count":9,"area":null},{"id":"2511.18606","title":"How to Train Your Latent Control Barrier Function: Smooth Safety Filtering Under Hard-to-Model Constraints","created":"2025-11-23","cited_by_count":9,"area":null},{"id":"2409.13867","title":"MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety","created":"2024-09-20","cited_by_count":7,"area":"deeprl"},{"id":"2509.19555","title":"AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space","created":"2025-09-23","cited_by_count":7,"area":"wm"},{"id":"2406.04835","title":"SLR: Learning Quadruped Locomotion without Privileged Information","created":"2024-06-07","cited_by_count":6,"area":"deeprl"},{"id":"2412.04153","title":"A Dynamic Safety Shield for Safe and Efficient Reinforcement Learning of Navigation Tasks","created":"2024-12-05","cited_by_count":5,"area":"deeprl"},{"id":"2502.08643","title":"A Real-to-Sim-to-Real Approach to Robotic Manipulation with VLM-Generated Iterative Keypoint Rewards","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2505.00908","title":"Learning Conservative Neural Control Barrier Functions from Offline Data","created":"2025-05-01","cited_by_count":5,"area":"offlinerl"},{"id":"2509.01728","title":"Constrained Decoding for Safe Robot Navigation Foundation Models","created":"2025-09-01","cited_by_count":5,"area":null},{"id":"2412.04323","title":"GRAM: Generalization in Deep RL with a Robust Adaptation Module","created":"2024-12-05","cited_by_count":3,"area":"deeprl"},{"id":"2503.21401","title":"AcL: Action Learner for Fault-Tolerant Quadruped Locomotion Control","created":"2025-03-27","cited_by_count":3,"area":null},{"id":"2505.13834","title":"Toward Real-World Cooperative and Competitive Soccer with Quadrupedal Robot Teams","created":"2025-05-20","cited_by_count":3,"area":"deeprl"},{"id":"2510.03142","title":"MM-Nav: Multi-View VLA Model for Robust Visual Navigation via Multi-Expert Learning","created":"2025-10-03","cited_by_count":3,"area":"vla"},{"id":"2603.01151","title":"D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2607.28623","title":"PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball","created":"2026-07-30","cited_by_count":3,"area":null},{"id":"2404.15256","title":"TOP-Nav: Legged Navigation Integrating Terrain, Obstacle and Proprioception Estimation","created":"2024-04-23","cited_by_count":2,"area":null},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2503.05035","title":"QuietPaw: Learning Quadrupedal Locomotion with Versatile Noise Preference Alignment","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2508.07611","title":"End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy","created":"2025-08-11","cited_by_count":2,"area":"deeprl"},{"id":"2411.06782","title":"QuadWBG: Generalizable Quadrupedal Whole-Body Grasping","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2411.19809","title":"Q-learning-based Model-free Safety Filter","created":"2024-11-29","cited_by_count":1,"area":"deeprl"},{"id":"2502.15006","title":"Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2509.17877","title":"Sight Over Site: Perception-Aware Reinforcement Learning for Efficient Robotic Inspection","created":"2025-09-22","cited_by_count":1,"area":"deeprl"},{"id":"2510.04234","title":"Flexible Locomotion Learning with Diffusion Model Predictive Control","created":"2025-10-05","cited_by_count":1,"area":"diffusion"},{"id":"2510.13727","title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","created":"2025-10-15","cited_by_count":1,"area":"safety"},{"id":"2605.15559","title":"NavRL++: A System-Level Framework for Improving Sim-to-Real Transfer in Reinforcement Learning-Based Robot Navigation","created":"2026-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2606.08253","title":"Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking","created":"2026-06-06","cited_by_count":1,"area":null},{"id":"2607.21867","title":"When Is a Learned Command Adapter Worth It? Closed-Loop Identification and Counterfactual Auditing of Frozen Locomotion Policies","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2608.16164","title":"Trajectory-Level Automatic Curriculum Learning for Legged Locomotion on Unstructured Terrain","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2410.23571","title":"Dual Agent Learning Based Aerial Trajectory Tracking","created":"2024-10-31","cited_by_count":0,"area":"deeprl"},{"id":"2502.14457","title":"Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control","created":"2025-02-20","cited_by_count":0,"area":null},{"id":"2503.02111","title":"NavG: Risk-Aware Navigation in Crowded Environments Based on Reinforcement Learning with Guidance Points","created":"2025-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2504.05629","title":"PTRL: Prior Transfer Deep Reinforcement Learning for Legged Robots Locomotion","created":"2025-04-08","cited_by_count":0,"area":"deeprl"},{"id":"2505.06561","title":"Quadrupedal Robot Skateboard Mounting via Reverse Curriculum Learning","created":"2025-05-10","cited_by_count":0,"area":null},{"id":"2506.05115","title":"Whole-Body Constrained Learning for Legged Locomotion via Hierarchical Optimization","created":"2025-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2511.17765","title":"LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2602.10514","title":"Co-jump: Cooperative Jumping with Quadrupedal Robots via Multi-Agent Reinforcement Learning","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.23719","title":"SAGE-LLM: Towards Safe and Generalizable LLM Controller with Fuzzy-CBF Verification and Graph-Structured Knowledge Retrieval for UAV Decision","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.13665","title":"Robot Squid Game: Quadrupedal Locomotion for Traversing Narrow Tunnels","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2606.07193","title":"Shield-Loco: Shielding Locomotion Policies with Predictive Safety Filtering","created":"2026-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2606.10832","title":"GUIDE: Goal-Initialized Directional Understanding for End-to-End Legged Navigation","created":"2026-06-09","cited_by_count":0,"area":"deeprl"},{"id":"2606.12042","title":"KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2608.06907","title":"Spatiotemporal Agility: Time-Constrained Reinforcement Learning for Vision-Guided Dynamic Quadrupedal Interception","created":"2026-08-07","cited_by_count":0,"area":"deeprl"},{"id":"2608.28300","title":"MaCoPlanner: LLM-Assisted Manual-Compiled Task Planning with Proactive Safety Verification for Robotic Industrial Panel Operation","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2609.02358","title":"Humanoid Safe Stop via Learned Stoppability Value","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.15988","title":"ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids","created":"2026-09-14","cited_by_count":0,"area":"deeprl"},{"id":"2609.37070","title":"Predictive Safety Curricula for Robust Legged Locomotion","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.17927","title":"GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19627","title":"E2DRL: End-to-End Differentiable Reinforcement Learning for 3D Obstacle Avoidance in Quadruped Robots","created":"2026-10-14","cited_by_count":0,"area":"deeprl"},{"id":"2610.20255","title":"Safe Reinforcement Learning with Receding-Horizon Safety Critic and Differentiable Action Shields","created":"2026-10-14","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}