mlsanityData to 7 Oct 2026

Robot Crowd Navigation in Dynamic Environment with Offline Reinforcement Learning

arXiv 2312.11032 ↗First posted 18 Dec 2023cs.ROcited by 0

On the map: Offline RL and imitation learning from data → Social robot navigation

Abstract (arXiv)

Robot crowd navigation has been gaining increasing attention and popularity in various practical applications. In existing research, deep reinforcement learning has been applied to robot crowd navigation by training policies in an online mode. However, this inevitably leads to unsafe exploration, and consequently causes low sampling efficiency during pedestrian-robot interaction. To this end, we propose an offline reinforcement learning based robot crowd navigation algorithm by utilizing pre-collected crowd navigation experience. Specifically, this algorithm integrates a spatial-temporal state into implicit Q-Learning to avoid querying out-of-distribution robot actions of the pre-collected experience, while capturing spatial-temporal features from the offline pedestrian-robot interactions. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art methods by means of qualitative and quantitative analysis.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Social robot navigation, one of 13 directions in Offline RL and imitation learning from data. Builds on 13 of its 25 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

13 of 25 references.

References · 13

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  2. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  3. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  4. 2019Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learningcited by 750
  5. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 104
  6. 2018Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learningcited by 101
  7. 2017Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learningcited by 81
  8. 2022Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graphcited by 46
  9. 2020Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learningcited by 36
  10. 2020DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviorscited by 25
  11. 2016Deep-Learned Collision Avoidance Policy for Distributed Multi-Agent Navigationcited by 14
  12. 2023NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learningcited by 12
1 more
  1. 2021Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Diffusion Policies for Short-Horizon Planning in Robot Crowd Navigation
  2. 2025Integrating Offline Pre-Training with Online Fine-Tuning: A Reinforcement Learning Approach for Robot Social Navigation
  3. 2026SPLC: Social Preference Learning for Crowd Robot Navigation
  4. 2024Multi-Agent Inverse Reinforcement Learning in Real World Unstructured Pedestrian Crowds
  5. 2025Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning
  6. 2024Learning Crowd Behaviors in Navigation with Attention-based Spatial-Temporal Graphs
  7. 2024Navigating the Human Maze: Real-Time Robot Pathfinding with Generative Imitation Learning
  8. 2026Trajectory Learning with Graph Representations for Social Robot Navigation