mlsanityData to 14 Oct 2026

A Comparative Study of Human Motion Models in Reinforcement Learning Algorithms for Social Robot Navigation

arXiv 2503.15127 ↗First posted 19 Mar 2025cs.HC cs.RO cs.SYcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Social robot navigation is an evolving research field that aims to find efficient strategies to safely navigate dynamic environments populated by humans. A critical challenge in this domain is the accurate modeling of human motion, which directly impacts the design and evaluation of navigation algorithms. This paper presents a comparative study of two popular categories of human motion models used in social robot navigation, namely velocity-based models and force-based models. A system-theoretic representation of both model types is presented, which highlights their common feedback structure, although with different state variables. Several navigation policies based on reinforcement learning are trained and tested in various simulated environments involving pedestrian crowds modeled with these approaches. A comparative study is conducted to assess performance across multiple factors, including human motion model, navigation policy, scenario complexity and crowd density. The results highlight advantages and challenges of different approaches to modeling human behavior, as well as their role during training and testing of learning-based navigation policies. The findings offer valuable insights and guidelines for selecting appropriate human motion models when designing socially-aware robot navigation systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 46 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

19 of 46 references.

References · 19

  1. 2018On Evaluation of Embodied Navigation Agentscited by 547
  2. 2019Human Motion Trajectory Prediction: A Surveycited by 232
  3. 2017Social Attention: Modeling Attention in Human Crowdscited by 186
  4. 2018Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learningcited by 175
  5. 2016Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learningcited by 118
  6. 2018Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learningcited by 111
  7. 2021Core Challenges of Social Robot Navigation: A Surveycited by 106
  8. 2023Principles and Guidelines for Evaluating Social Robot Navigation Algorithmscited by 56
  9. 2017Socially Compliant Navigation through Raw Depth Inputs with Generative Adversarial Imitation Learningcited by 52
  10. 2023A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challengescited by 39
  11. 2021A Survey on Human-aware Robot Navigationcited by 24
  12. 2020Model Predictive Contouring Control for Collision Avoidance in Unstructured Dynamic Environmentscited by 21
7 more
  1. 2023HuNavSim: A ROS 2 Human Navigation Simulator for Benchmarking Human-Aware Robot Navigationcited by 13
  2. 2020Leveraging Neural Network Gradients within Trajectory Optimization for Proactive Human-Robot Interactionscited by 9
  3. 2020Generating Reliable and Efficient Predictions of Human Motion: A Promising Encounter between Physics and Neural Networkscited by 7
  4. 2018MengeROS: a Crowd Simulation Tool for Autonomous Robot Navigationcited by 5
  5. 2021Crowd against the machine: A simulation-based benchmark tool to evaluate and compare robot capabilities to navigate a human crowdcited by 5
  6. 2022Proactive Opinion-Driven Robot Navigation around Human Moverscited by 4
  7. 2022Simulators for Mobile Social Robots:State-of-the-Art and Challengescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021SOCIALGYM: A Framework for Benchmarking Social Robot Navigation
  2. 2024Following the Human Thread in Social Navigation
  3. 2024Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation
  4. 2026Trajectory Learning with Graph Representations for Social Robot Navigation
  5. 2025SocialNav-Map: Dynamic Mapping with Human Trajectory Prediction for Zero-Shot Social Navigation
  6. 2025Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches
  7. 2026Optimal-Horizon Social Robot Navigation in Heterogeneous Crowds ↗
  8. 2024Adaptive Social Force Window Planner with Reinforcement Learning