{"total":136,"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":"2203.15041","title":"Socially Compliant Navigation Dataset (SCAND): A Large-Scale Dataset of Demonstrations for Social Navigation","created":"2022-03-28","cited_by_count":127,"area":"offlinerl"},{"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":"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":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54,"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":"2111.06740","title":"Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches","created":"2021-11-11","cited_by_count":30,"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":"2107.00200","title":"Social Coordination and Altruism in Autonomous Driving","created":"2021-07-01","cited_by_count":28,"area":"driving"},{"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":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2108.09003","title":"Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey","created":"2021-08-20","cited_by_count":24,"area":null},{"id":"2107.03178","title":"Levels of explainable artificial intelligence for human-aligned conversational explanations","created":"2021-07-07","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":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"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":"2209.03859","title":"A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning","created":"2022-09-08","cited_by_count":14,"area":null},{"id":"2309.05662","title":"ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion","created":"2023-09-11","cited_by_count":14,"area":null},{"id":"2511.21135","title":"SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation","created":"2025-11-26","cited_by_count":12,"area":null},{"id":"2101.02647","title":"From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation","created":"2021-01-07","cited_by_count":11,"area":null},{"id":"2206.14155","title":"Position-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learning","created":"2022-06-28","cited_by_count":11,"area":null},{"id":"2107.07056","title":"Learning Sparse Interaction Graphs of Partially Detected Pedestrians for Trajectory Prediction","created":"2021-07-15","cited_by_count":10,"area":null},{"id":"2112.14004","title":"Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations","created":"2021-12-28","cited_by_count":10,"area":"offlinerl"},{"id":"2409.13244","title":"From Cognition to Precognition: A Future-Aware Framework for Social Navigation","created":"2024-09-20","cited_by_count":10,"area":null},{"id":"2509.08757","title":"SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation","created":"2025-09-10","cited_by_count":10,"area":null},{"id":"2210.00552","title":"Occlusion-Aware Crowd Navigation Using People as Sensors","created":"2022-10-02","cited_by_count":9,"area":null},{"id":"2306.11377","title":"HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2307.03015","title":"Sequential Neural Barriers for Scalable Dynamic Obstacle Avoidance","created":"2023-07-06","cited_by_count":9,"area":null},{"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":"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":"2503.09758","title":"Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation","created":"2025-03-12","cited_by_count":8,"area":"agents"},{"id":"2103.10000","title":"Human-Inspired Multi-Agent Navigation using Knowledge Distillation","created":"2021-03-18","cited_by_count":7,"area":null},{"id":"2202.01141","title":"Federated Reinforcement Learning for Collective Navigation of Robotic Swarms","created":"2022-02-02","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":"2210.08390","title":"SOCIALMAPF: Optimal and Efficient Multi-Agent Path Finding with Strategic Agents for Social Navigation","created":"2022-10-15","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":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"area":"deeprl"},{"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":"2409.18084","title":"GSON: A Group-based Social Navigation Framework with Large Multimodal Model","created":"2024-09-26","cited_by_count":6,"area":null},{"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":"2109.10493","title":"Benchmarking Augmentation Methods for Learning Robust Navigation Agents: the Winning Entry of the 2021 iGibson Challenge","created":"2021-09-22","cited_by_count":5,"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":"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":"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":"2602.09002","title":"From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection","created":"2026-02-09","cited_by_count":5,"area":null},{"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":"2211.10714","title":"PIC4rl-gym: a ROS2 modular framework for Robots Autonomous Navigation with Deep Reinforcement Learning","created":"2022-11-19","cited_by_count":4,"area":null},{"id":"2306.07525","title":"Using Collision Momentum in Deep Reinforcement Learning Based Adversarial Pedestrian Modeling","created":"2023-06-13","cited_by_count":4,"area":null},{"id":"2309.12568","title":"A Study on Learning Social Robot Navigation with Multimodal Perception","created":"2023-09-22","cited_by_count":4,"area":null},{"id":"2401.17914","title":"Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement Learning","created":"2024-01-31","cited_by_count":4,"area":"deeprl"},{"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":"2403.15648","title":"Unifying Large Language Model and Deep Reinforcement Learning for Human-in-Loop Interactive Socially-aware Navigation","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2404.11327","title":"Following the Human Thread in Social Navigation","created":"2024-04-17","cited_by_count":4,"area":null},{"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":"2509.17941","title":"ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion","created":"2025-09-22","cited_by_count":4,"area":"diffusion"},{"id":"2102.08863","title":"A Graph Neural Network to Model Disruption in Human-Aware Robot Navigation","created":"2021-02-17","cited_by_count":3,"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":"2104.14912","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":"2210.03582","title":"Learning Social Navigation from Demonstrations with Conditional Neural Processes","created":"2022-10-07","cited_by_count":3,"area":null},{"id":"2211.14440","title":"Don't Watch Me: A Spatio-Temporal Trojan Attack on Deep-Reinforcement-Learning-Augment Autonomous Driving","created":"2022-11-22","cited_by_count":3,"area":"driving"},{"id":"2301.00650","title":"Hybrid Deep Reinforcement Learning and Planning for Safe and Comfortable Automated Driving","created":"2022-12-30","cited_by_count":3,"area":"driving"},{"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":"2304.14102","title":"SocNavGym: A Reinforcement Learning Gym for Social Navigation","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2311.10309","title":"Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments","created":"2023-11-17","cited_by_count":3,"area":"driving"},{"id":"2311.17059","title":"Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2403.01537","title":"Mixed Strategy Nash Equilibrium for Crowd Navigation","created":"2024-03-03","cited_by_count":3,"area":null},{"id":"2406.08404","title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","created":"2024-06-12","cited_by_count":3,"area":null},{"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":"2103.05142","title":"Formal Verification of Stochastic Systems with ReLU Neural Network Controllers","created":"2021-03-08","cited_by_count":2,"area":null},{"id":"2203.00156","title":"Preemptive Motion Planning for Human-to-Robot Indirect Placement Handovers","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2209.06328","title":"Deterministic and Stochastic Analysis of Deep Reinforcement Learning for Low Dimensional Sensing-based Navigation of Mobile Robots","created":"2022-09-13","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":"2302.02921","title":"Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems","created":"2023-02-06","cited_by_count":2,"area":null},{"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":"2310.07335","title":"Exploring Social Motion Latent Space and Human Awareness for Effective Robot Navigation in Crowded Environments","created":"2023-10-11","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":"2407.06056","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":"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":"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":"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":"2210.08672","title":"Decision-Making Among Bounded Rational Agents","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2212.03068","title":"Active Classification of Moving Targets with Learned Control Policies","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2301.11173","title":"Double Deep Reinforcement Learning Techniques for Low Dimensional Sensing Mapless Navigation of Terrestrial Mobile Robots","created":"2023-01-26","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}],"next_cursor":"100"}