{"total":83,"rows":[{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86,"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":"2403.15637","title":"CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments","created":"2024-03-22","cited_by_count":43,"area":"mllm"},{"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":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2408.15099","title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","created":"2024-08-27","cited_by_count":31,"area":"deeprl"},{"id":"2204.07417","title":"Safe Reinforcement Learning Using Black-Box Reachability Analysis","created":"2022-04-15","cited_by_count":26,"area":null},{"id":"2203.10603","title":"Model-based Multi-agent Reinforcement Learning: Recent Progress and Prospects","created":"2022-03-20","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":"2106.12113","title":"Conflict Avoidance in Social Navigation -- a Survey","created":"2021-06-23","cited_by_count":14,"area":null},{"id":"2112.09012","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","created":"2021-12-16","cited_by_count":13,"area":null},{"id":"2201.12231","title":"Overcoming Exploration: Deep Reinforcement Learning for Continuous Control in Cluttered Environments from Temporal Logic Specifications","created":"2022-01-28","cited_by_count":12,"area":null},{"id":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2204.06477","title":"Data-heterogeneity-aware Mixing for Decentralized Learning","created":"2022-04-13","cited_by_count":12,"area":null},{"id":"2209.12091","title":"Graph Neural Networks for Multi-Robot Active Information Acquisition","created":"2022-09-24","cited_by_count":12,"area":null},{"id":"2210.08872","title":"PTDE: Personalized Training with Distilled Execution for Multi-Agent Reinforcement Learning","created":"2022-10-17","cited_by_count":11,"area":null},{"id":"2103.06403","title":"A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance","created":"2021-03-11","cited_by_count":10,"area":null},{"id":"2410.02581","title":"Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2203.04700","title":"Multi-robot Cooperative Pursuit via Potential Field-Enhanced Reinforcement Learning","created":"2022-03-09","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":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","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":"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":"2112.12612","title":"Towards Disturbance-Free Visual Mobile Manipulation","created":"2021-12-17","cited_by_count":6,"area":null},{"id":"2210.01162","title":"Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications","created":"2022-10-03","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":"2406.06823","title":"Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies","created":"2024-06-10","cited_by_count":6,"area":null},{"id":"2409.16720","title":"Dashing for the Golden Snitch: Multi-Drone Time-Optimal Motion Planning with Multi-Agent Reinforcement Learning","created":"2024-09-25","cited_by_count":6,"area":null},{"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":"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":"2212.04123","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":"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":"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":"2410.07933","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","created":"2024-10-10","cited_by_count":4,"area":"offlinerl"},{"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":"2104.14912","title":"Nearest-Neighbor-based Collision Avoidance for Quadrotors via Reinforcement Learning","created":"2021-04-30","cited_by_count":3,"area":null},{"id":"2202.11512","title":"Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogistics","created":"2022-02-23","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":"2110.10255","title":"A Simple Approach to Continual Learning by Transferring Skill Parameters","created":"2021-10-19","cited_by_count":2,"area":null},{"id":"2207.02464","title":"A Learning System for Motion Planning of Free-Float Dual-Arm Space Manipulator towards Non-Cooperative Object","created":"2022-07-06","cited_by_count":2,"area":null},{"id":"2209.09344","title":"Understanding reinforcement learned crowds","created":"2022-09-19","cited_by_count":2,"area":null},{"id":"2210.10639","title":"Robot Navigation with Reinforcement Learned Path Generation and Fine-Tuned Motion Control","created":"2022-10-19","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":"2403.06397","title":"DeepSafeMPC: Deep Learning-Based Model Predictive Control for Safe Multi-Agent Reinforcement Learning","created":"2024-03-11","cited_by_count":2,"area":null},{"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":"2512.09920","title":"LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating","created":"2025-12-10","cited_by_count":2,"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":"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":"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":"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":"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":"2403.10996","title":"Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2505.15033","title":"Toward Task Capable Active Matter: Learning to Avoid Clogging in Confined Collectives via Collisions","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.17244","title":"Scalable Multi Agent Diffusion Policies for Coverage Control","created":"2025-09-21","cited_by_count":1,"area":"diffusion"},{"id":"2511.09792","title":"Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning","created":"2025-11-12","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":"2103.04511","title":"An Energy-Saving Snake Locomotion Gait Policy Obtained Using Deep Reinforcement Learning","created":"2021-03-08","cited_by_count":0,"area":null},{"id":"2108.12934","title":"Distributed Swarm Collision Avoidance Based on Angular Calculations","created":"2021-08-29","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":"2207.06847","title":"Covy: An AI-powered Robot with a Compound Vision System for Detecting Breaches in Social Distancing","created":"2022-07-14","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":"2303.09946","title":"An Adaptive Fuzzy Reinforcement Learning Cooperative Approach for the Autonomous Control of Flock Systems","created":"2023-03-17","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":"2307.10574","title":"Adaptive Control of Resource Flow to Optimize Construction Work and Cash Flow via Online Deep Reinforcement Learning","created":"2023-07-20","cited_by_count":0,"area":null},{"id":"2309.10007","title":"Multi-Agent Deep Reinforcement Learning for Cooperative and Competitive Autonomous Vehicles using AutoDRIVE Ecosystem","created":"2023-09-18","cited_by_count":0,"area":"driving"},{"id":"2309.12841","title":"Reward Function Design for Crowd Simulation via Reinforcement Learning","created":"2023-09-22","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":"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":"2411.08400","title":"BAMAX: Backtrack Assisted Multi-Agent Exploration using Reinforcement Learning","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2510.00466","title":"Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation","created":"2025-10-01","cited_by_count":0,"area":"offlinerl"},{"id":"2607.04972","title":"Multi-Robot Open Adaptive Teaming Across Unseen Environments, Partners, and Scales","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.00625","title":"Learning-Based Motion Planning for Dynamic Environments: From Foundational Algorithms to Emerging Paradigms","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.21175","title":"SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.09752","title":"HiRAD: A Flexible Large-Scale AGV Routing System","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}