{"total":118,"rows":[{"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":"2306.01874","title":"SACSoN: Scalable Autonomous Control for Social Navigation","created":"2023-06-02","cited_by_count":61,"area":null},{"id":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56,"area":null},{"id":"2203.01821","title":"Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph","created":"2022-03-03","cited_by_count":53,"area":null},{"id":"2111.14843","title":"Catch Me If You Hear Me: Audio-Visual Navigation in Complex Unmapped Environments with Moving Sounds","created":"2021-11-29","cited_by_count":41,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2108.10879","title":"Are socially-aware trajectory prediction models really socially-aware?","created":"2021-08-24","cited_by_count":32,"area":null},{"id":"2102.13073","title":"Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians","created":"2021-02-25","cited_by_count":28,"area":null},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2409.15634","title":"NavRL: Learning Safe Flight in Dynamic Environments","created":"2024-09-24","cited_by_count":26,"area":"deeprl"},{"id":"2203.15983","title":"VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2401.12275","title":"Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation","created":"2024-01-22","cited_by_count":20,"area":null},{"id":"2409.14972","title":"Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments","created":"2024-09-23","cited_by_count":17,"area":"deeprl"},{"id":"2106.12113","title":"Conflict Avoidance in Social Navigation -- a Survey","created":"2021-06-23","cited_by_count":14,"area":null},{"id":"2102.05382","title":"Learning Interaction-Aware Trajectory Predictions for Decentralized Multi-Robot Motion Planning in Dynamic Environments","created":"2021-02-10","cited_by_count":12,"area":null},{"id":"2206.08487","title":"High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization","created":"2022-06-16","cited_by_count":11,"area":null},{"id":"2403.06828","title":"NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learning","created":"2024-03-11","cited_by_count":11,"area":null},{"id":"2403.09190","title":"Intention-aware Denoising Diffusion Model for Trajectory Prediction","created":"2024-03-14","cited_by_count":11,"area":"diffusion"},{"id":"2210.00552","title":"Occlusion-Aware Crowd Navigation Using People as Sensors","created":"2022-10-02","cited_by_count":9,"area":null},{"id":"2407.17460","title":"SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning","created":"2024-07-24","cited_by_count":9,"area":"deeprl"},{"id":"2407.20164","title":"Language-Conditioned Offline RL for Multi-Robot Navigation","created":"2024-07-29","cited_by_count":9,"area":"offlinerl"},{"id":"2410.10646","title":"DR-MPC: Deep Residual Model Predictive Control for Real-world Social Navigation","created":"2024-10-14","cited_by_count":9,"area":null},{"id":"2411.12150","title":"HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments","created":"2024-11-19","cited_by_count":9,"area":null},{"id":"2309.13285","title":"Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning","created":"2023-09-23","cited_by_count":8,"area":null},{"id":"2403.00991","title":"SELFI: Autonomous Self-Improvement with Reinforcement Learning for Social Navigation","created":"2024-03-01","cited_by_count":8,"area":"deeprl"},{"id":"2502.03640","title":"Discrete GCBF Proximal Policy Optimization for Multi-agent Safe Optimal Control","created":"2025-02-05","cited_by_count":8,"area":null},{"id":"2103.10000","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","created":"2021-03-18","cited_by_count":7,"area":null},{"id":"2102.13265","title":"Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planning","created":"2021-02-26","cited_by_count":6,"area":null},{"id":"2104.03663","title":"Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2212.00767","title":"Exploiting Proximity-Aware Tasks for Embodied Social Navigation","created":"2022-12-01","cited_by_count":6,"area":null},{"id":"2405.13969","title":"Uncertainty-Aware DRL for Autonomous Vehicle Crowd Navigation in Shared Space","created":"2024-05-22","cited_by_count":6,"area":"driving"},{"id":"2504.15425","title":"Solving Multi-Agent Safe Optimal Control with Distributed Epigraph Form MARL","created":"2025-04-21","cited_by_count":6,"area":null},{"id":"2508.05634","title":"Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling","created":"2025-08-07","cited_by_count":6,"area":"deeprl"},{"id":"2112.06594","title":"Multi-agent Soft Actor-Critic Based Hybrid Motion Planner for Mobile Robots","created":"2021-12-13","cited_by_count":5,"area":null},{"id":"2212.07684","title":"Multi-Agent Reinforcement Learning with Shared Resources for Inventory Management","created":"2022-12-15","cited_by_count":5,"area":null},{"id":"2303.05584","title":"SOCIALGYM 2.0: Simulator for Multi-Agent Social Robot Navigation in Shared Human Spaces","created":"2023-03-09","cited_by_count":5,"area":null},{"id":"2403.09793","title":"Socially Integrated Navigation: A Social Acting Robot with Deep Reinforcement Learning","created":"2024-03-14","cited_by_count":5,"area":"deeprl"},{"id":"2206.10028","title":"Intention-Aware Navigation in Crowds with Extended-Space POMDP Planning","created":"2022-06-20","cited_by_count":4,"area":null},{"id":"2402.11799","title":"Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning","created":"2024-02-19","cited_by_count":4,"area":"deeprl"},{"id":"2404.11327","title":"Following the Human Thread in Social Navigation","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2102.00675","title":"Autonomous Navigation through intersections with Graph ConvolutionalNetworks and Conditional Imitation Learning for Self-driving Cars","created":"2021-02-01","cited_by_count":3,"area":"driving"},{"id":"2104.04477","title":"Jamming-Resilient Path Planning for Multiple UAVs via Deep Reinforcement Learning","created":"2021-04-09","cited_by_count":3,"area":null},{"id":"2104.14912","title":"Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning","created":"2021-04-30","cited_by_count":3,"area":null},{"id":"2107.09170","title":"DeepSocNav: Social Navigation by Imitating Human Behaviors","created":"2021-07-19","cited_by_count":3,"area":null},{"id":"2206.03211","title":"Variational Meta Reinforcement Learning for Social Robotics","created":"2022-06-07","cited_by_count":3,"area":null},{"id":"2403.10083","title":"HeR-DRL:Heterogeneous Relational Deep Reinforcement Learning for Decentralized Multi-Robot Crowd Navigation","created":"2024-03-15","cited_by_count":3,"area":"deeprl"},{"id":"2408.14183","title":"Robot Navigation with Entity-Based Collision Avoidance using Deep Reinforcement Learning","created":"2024-08-26","cited_by_count":3,"area":"deeprl"},{"id":"2501.06946","title":"Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning","created":"2025-01-12","cited_by_count":3,"area":"offlinerl"},{"id":"2503.13934","title":"COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning","created":"2025-03-18","cited_by_count":3,"area":"diffusion"},{"id":"2108.06161","title":"Reinforcement Learning for Robot Navigation with Adaptive Forward Simulation Time (AFST) in a Semi-Markov Model","created":"2021-08-13","cited_by_count":2,"area":null},{"id":"2111.07037","title":"Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning","created":"2021-11-13","cited_by_count":2,"area":null},{"id":"2209.07996","title":"SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":"offlinerl"},{"id":"2303.04320","title":"SG-LSTM: Social Group LSTM for Robot Navigation Through Dense Crowds","created":"2023-03-08","cited_by_count":2,"area":null},{"id":"2306.08815","title":"Decentralized Social Navigation with Non-Cooperative Robots via Bi-Level Optimization","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2404.03710","title":"Self-organized free-flight arrival for urban air mobility","created":"2024-04-04","cited_by_count":2,"area":"deeprl"},{"id":"2406.11495","title":"Online Context Learning for Socially Compliant Navigation","created":"2024-06-17","cited_by_count":2,"area":null},{"id":"2407.06056","title":"Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation","created":"2024-07-08","cited_by_count":2,"area":"deeprl"},{"id":"2407.10547","title":"Learning Social Cost Functions for Human-Aware Path Planning","created":"2024-07-15","cited_by_count":2,"area":null},{"id":"2408.02661","title":"Context-aware Mamba-based Reinforcement Learning for social robot navigation","created":"2024-08-05","cited_by_count":2,"area":"ssm"},{"id":"2409.10655","title":"Disentangling Uncertainty for Safe Social Navigation using Deep Reinforcement Learning","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2409.16950","title":"Dynamic Obstacle Avoidance through Uncertainty-Based Adaptive Planning with Diffusion","created":"2024-09-25","cited_by_count":2,"area":"diffusion"},{"id":"2508.20315","title":"Multi-Agent Reinforcement Learning in Intelligent Transportation Systems: A Comprehensive Survey","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2603.24366","title":"CoordLight: Learning Decentralized Coordination for Network-Wide Traffic Signal Control","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2606.08729","title":"IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarking","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2102.03138","title":"An advantage actor-critic algorithm for robotic motion planning in dense and dynamic scenarios","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2106.10318","title":"Sample Efficient Social Navigation Using Inverse Reinforcement Learning","created":"2021-06-18","cited_by_count":1,"area":"offlinerl"},{"id":"2109.08536","title":"Decentralized Global Connectivity Maintenance for Multi-Robot Navigation: A Reinforcement Learning Approach","created":"2021-09-17","cited_by_count":1,"area":null},{"id":"2110.04564","title":"Human-Aware Robot Navigation via Reinforcement Learning with Hindsight Experience Replay and Curriculum Learning","created":"2021-10-09","cited_by_count":1,"area":null},{"id":"2201.04766","title":"Collision Detection: An Improved Deep Learning Approach Using SENet and ResNext","created":"2022-01-13","cited_by_count":1,"area":null},{"id":"2205.02003","title":"Multi-subgoal Robot Navigation in Crowds with History Information and Interactions","created":"2022-05-04","cited_by_count":1,"area":null},{"id":"2206.00705","title":"Dense Crowd Flow-Informed Path Planning","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2306.08870","title":"Evolutionary Curriculum Training for DRL-Based Navigation Systems","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2308.14947","title":"Improving Generalization in Reinforcement Learning Training Regimes for Social Robot Navigation","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2309.03758","title":"Hybrid of representation learning and reinforcement learning for dynamic and complex robotic motion planning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2404.05203","title":"MeSA-DRL: Memory-Enhanced Deep Reinforcement Learning for Advanced Socially Aware Robot Navigation in Crowded Environments","created":"2024-04-08","cited_by_count":1,"area":"deeprl"},{"id":"2407.13567","title":"Hyp2Nav: Hyperbolic Planning and Curiosity for Crowd Navigation","created":"2024-07-18","cited_by_count":1,"area":null},{"id":"2408.06397","title":"Distributed Stackelberg Strategies in State-based Potential Games for Autonomous Decentralized Learning Manufacturing Systems","created":"2024-08-12","cited_by_count":1,"area":null},{"id":"2503.12538","title":"EmoBipedNav: Emotion-aware Social Navigation for Bipedal Robots with Deep Reinforcement Learning","created":"2025-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2512.24651","title":"Hybrid Motion Planning with Deep Reinforcement Learning for Mobile Robot Navigation","created":"2025-12-31","cited_by_count":1,"area":"deeprl"},{"id":"2602.12724","title":"TRANS: Terrain-aware Reinforcement Learning for Agile Navigation of Quadruped Robots under Social Interactions","created":"2026-02-13","cited_by_count":1,"area":"deeprl"},{"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":"2101.05640","title":"Continuous Deep Q-Learning with Simulator for Stabilization of Uncertain Discrete-Time Systems","created":"2021-01-13","cited_by_count":0,"area":null},{"id":"2102.02376","title":"A review of motion planning algorithms for intelligent robotics","created":"2021-02-04","cited_by_count":0,"area":null},{"id":"2104.06410","title":"Reward Shaping with Subgoals for Social Navigation","created":"2021-04-13","cited_by_count":0,"area":null},{"id":"2209.09079","title":"MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation","created":"2022-09-19","cited_by_count":0,"area":null},{"id":"2304.00367","title":"Conveying Autonomous Robot Capabilities through Contrasting Behaviour Summaries","created":"2023-04-01","cited_by_count":0,"area":null},{"id":"2304.01428","title":"Learned Tree Search for Long-Horizon Social Robot Navigation in Shared Airspace","created":"2023-04-04","cited_by_count":0,"area":null},{"id":"2304.03593","title":"Deep Reinforcement Learning-Based Mapless Crowd Navigation with Perceived Risk of the Moving Crowd for Mobile Robots","created":"2023-04-07","cited_by_count":0,"area":null},{"id":"2311.16841","title":"Two-step dynamic obstacle avoidance","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2312.11032","title":"Robot Crowd Navigation in Dynamic Environment with Offline Reinforcement Learning","created":"2023-12-18","cited_by_count":0,"area":"offlinerl"},{"id":"2402.06297","title":"Dynamic Q-planning for Online UAV Path Planning in Unknown and Complex Environments","created":"2024-02-09","cited_by_count":0,"area":"deeprl"},{"id":"2404.16672","title":"RUMOR: Reinforcement learning for Understanding a Model of the Real World for Navigation in Dynamic Environments","created":"2024-04-25","cited_by_count":0,"area":"deeprl"},{"id":"2405.16830","title":"Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation","created":"2024-05-27","cited_by_count":0,"area":"deeprl"},{"id":"2408.03807","title":"Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning","created":"2024-08-07","cited_by_count":0,"area":"offlinerl"},{"id":"2410.12232","title":"Improving the Generalization of Unseen Crowd Behaviors for Reinforcement Learning based Local Motion Planners","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2411.01963","title":"V-CAS: A Realtime Vehicle Anti Collision System Using Vision Transformer on Multi-Camera Streams","created":"2024-11-04","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":"2503.15127","title":"A Comparative Study of Human Motion Models in Reinforcement Learning Algorithms for Social Robot Navigation","created":"2025-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2508.07941","title":"Deep Reinforcement Learning with anticipatory reward in LSTM for Collision Avoidance of Mobile Robots","created":"2025-08-11","cited_by_count":0,"area":"deeprl"},{"id":"2509.02134","title":"Learning Social Heuristics for Human-Aware Path Planning","created":"2025-09-02","cited_by_count":0,"area":null}],"next_cursor":"100"}