{"total":111,"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":"2101.06894","title":"Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs","created":"2021-01-18","cited_by_count":144,"area":null},{"id":"2101.05436","title":"Learning Safe Multi-Agent Control with Decentralized Neural Barrier Certificates","created":"2021-01-14","cited_by_count":74,"area":null},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"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":"2110.00675","title":"Contraction Theory for Nonlinear Stability Analysis and Learning-based Control: A Tutorial Overview","created":"2021-10-01","cited_by_count":45,"area":null},{"id":"2103.04351","title":"Learning a State Representation and Navigation in Cluttered and Dynamic Environments","created":"2021-03-07","cited_by_count":41,"area":null},{"id":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32,"area":"offlinerl"},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2402.01968","title":"A Survey on Context-Aware Multi-Agent Systems: Techniques, Challenges and Future Directions","created":"2024-02-03","cited_by_count":27,"area":"agents"},{"id":"2409.15634","title":"NavRL: Learning Safe Flight in Dynamic Environments","created":"2024-09-24","cited_by_count":26,"area":"deeprl"},{"id":"2407.08725","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","created":"2024-07-11","cited_by_count":21,"area":"wm"},{"id":"2111.00993","title":"Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion","created":"2021-11-01","cited_by_count":17,"area":null},{"id":"2206.08737","title":"N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments","created":"2022-06-17","cited_by_count":16,"area":null},{"id":"2207.04361","title":"State Dropout-Based Curriculum Reinforcement Learning for Self-Driving at Unsignalized Intersections","created":"2022-07-10","cited_by_count":16,"area":"driving"},{"id":"2104.03616","title":"Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems","created":"2021-04-08","cited_by_count":15,"area":null},{"id":"2106.12113","title":"Conflict Avoidance in Social Navigation -- a Survey","created":"2021-06-23","cited_by_count":14,"area":null},{"id":"2102.12668","title":"Learning-based Robust Motion Planning with Guaranteed Stability: A Contraction Theory Approach","created":"2021-02-25","cited_by_count":13,"area":null},{"id":"2110.08607","title":"Physics-guided Deep Markov Models for Learning Nonlinear Dynamical Systems with Uncertainty","created":"2021-10-16","cited_by_count":11,"area":null},{"id":"2210.08487","title":"Survey of Deep Learning for Autonomous Surface Vehicles in the Marine Environment","created":"2022-10-16","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":"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":"2203.12299","title":"NavDreams: Towards Camera-Only RL Navigation Among Humans","created":"2022-03-23","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":"2106.09019","title":"Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate","created":"2021-06-16","cited_by_count":6,"area":null},{"id":"2308.05893","title":"Learning Team-Based Navigation: A Review of Deep Reinforcement Learning Techniques for Multi-Agent Pathfinding","created":"2023-08-11","cited_by_count":6,"area":null},{"id":"2309.17187","title":"TBD Pedestrian Data Collection: Towards Rich, Portable, and Large-Scale Natural Pedestrian Data","created":"2023-09-29","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":"2109.11288","title":"Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation","created":"2021-09-23","cited_by_count":5,"area":null},{"id":"2212.04123","title":"Enhanced method for reinforcement learning based dynamic obstacle avoidance by assessment of collision risk","created":"2022-12-08","cited_by_count":5,"area":null},{"id":"2311.00063","title":"Safe multi-agent motion planning under uncertainty for drones using filtered reinforcement learning","created":"2023-10-31","cited_by_count":5,"area":null},{"id":"2401.06604","title":"Identifying Policy Gradient Subspaces","created":"2024-01-12","cited_by_count":5,"area":"deeprl"},{"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":"2403.14583","title":"Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multi-Agent Navigation","created":"2024-03-21","cited_by_count":5,"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":"2409.12471","title":"Arena 4.0: A Comprehensive ROS2 Development and Benchmarking Platform for Human-centric Navigation Using Generative-Model-based Environment Generation","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2104.06256","title":"Learning-Based UAV Trajectory Optimization with Collision Avoidance and Connectivity Constraints","created":"2021-04-03","cited_by_count":3,"area":null},{"id":"2104.10818","title":"XAI-N: Sensor-based Robot Navigation using Expert Policies and Decision Trees","created":"2021-04-22","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":"2211.01004","title":"Spatial-temporal recurrent reinforcement learning for autonomous ships","created":"2022-11-02","cited_by_count":3,"area":null},{"id":"2302.10023","title":"Arena-Rosnav 2.0: A Development and Benchmarking Platform for Robot Navigation in Highly Dynamic Environments","created":"2023-02-20","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":"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":"2110.10255","title":"A Simple Approach to Continual Learning by Transferring Skill Parameters","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2206.05652","title":"Dealing with Sparse Rewards in Continuous Control Robotics via Heavy-Tailed Policies","created":"2022-06-12","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":"2210.07282","title":"Harfang3D Dog-Fight Sandbox: A Reinforcement Learning Research Platform for the Customized Control Tasks of Fighter Aircrafts","created":"2022-10-13","cited_by_count":2,"area":null},{"id":"2302.02921","title":"Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems","created":"2023-02-06","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":"2307.05832","title":"Bag of Views: An Appearance-based Approach to Next-Best-View Planning for 3D Reconstruction","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2406.11495","title":"Online Context Learning for Socially Compliant Navigation","created":"2024-06-17","cited_by_count":2,"area":null},{"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":"2512.00049","title":"Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches","created":"2025-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2605.11859","title":"EvoNav: Evolutionary Reward Function Design for Robot Navigation with Large Language Models","created":"2026-05-12","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":"2101.08074","title":"Flocking and Collision Avoidance for a Dynamic Squad of Fixed-Wing UAVs Using Deep Reinforcement Learning","created":"2021-01-20","cited_by_count":1,"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":"2102.10711","title":"Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player","created":"2021-02-21","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":"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":"2301.05980","title":"Deep-Reinforcement-Learning-based Path Planning for Industrial Robots using Distance Sensors as Observation","created":"2023-01-14","cited_by_count":1,"area":null},{"id":"2302.02898","title":"Arena-Web -- A Web-based Development and Benchmarking Platform for Autonomous Navigation Approaches","created":"2023-02-06","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":"2307.15931","title":"Robust Recurrent Reinforcement Learning under Evolving Hidden Disturbances with Application to Rover Wheel Slip","created":"2023-07-29","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":"2508.01192","title":"Unified Generation-Refinement Planning: Bridging Guided Flow Matching and Sampling-Based MPC for Social Navigation","created":"2025-08-02","cited_by_count":1,"area":"diffusion"},{"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":"2603.06729","title":"Don't Freeze, Don't Crash: Extending the Safe Operating Range of Neural Navigation in Dense Crowds","created":"2026-03-06","cited_by_count":1,"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":"2109.14957","title":"Augmented reality navigation system for visual prosthesis","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2112.13984","title":"Relative velocity-based reward functions for crowd navigation of robots","created":"2021-12-28","cited_by_count":0,"area":null},{"id":"2203.01974","title":"Towards Rich, Portable, and Large-Scale Pedestrian Data Collection","created":"2022-03-03","cited_by_count":0,"area":null},{"id":"2211.15901","title":"Multi-robot Social-aware Cooperative Planning in Pedestrian Environments Using Multi-agent Reinforcement Learning","created":"2022-11-29","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":"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":"2403.19060","title":"Towards Human-Centered Construction Robotics: A Reinforcement Learning-Driven Companion Robot for Contextually Assisting Carpentry Workers","created":"2024-03-27","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":"2404.17673","title":"Learning Manipulation Tasks in Dynamic and Shared 3D Spaces","created":"2024-04-26","cited_by_count":0,"area":"deeprl"},{"id":"2406.10060","title":"PRIMER: Perception-Aware Robust Learning-based Multiagent Trajectory Planner","created":"2024-06-14","cited_by_count":0,"area":null},{"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":"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":"2507.20850","title":"Free Energy-Inspired Cognitive Risk Integration for AV Navigation in Pedestrian-Rich Environments","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2509.01611","title":"A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle","created":"2025-09-01","cited_by_count":0,"area":"driving"}],"next_cursor":"100"}