SPLC: Social Preference Learning for Crowd Robot Navigation

2026-07-02

AI Summary

This work addresses the challenge of designing socially compliant navigation reward functions in dense crowd scenarios, where complex pedestrian dynamics hinder manual reward specification. To circumvent handcrafted reward design, the authors propose a social preference learning approach that automatically quantifies and generates preference data through a novel feedback mechanism grounded in pedestrian dynamic characteristics. Integrated within an offline reinforcement learning framework, this method combines principle-guided preference evaluation criteria with automated data generation to effectively mitigate reward bias. Experimental results demonstrate consistent superiority over state-of-the-art methods across standard simulation benchmarks, and real-world deployment on a TurtleBot4 platform validates its practical efficacy.

Abstract

Offline reinforcement learning (RL) holds significant potential for crowd robot navigation in human-robot coexistence applications. However, the inherent complexity of pedestrian motion renders the design of effective reward functions for promoting socially compliant robot behaviors a persistent challenge. This paper proposes a Social Preference Learning for Crowd Robot Navigation (SPLC) algorithm to eliminate the need for detailed reward design. Its core innovation lies in the introduction of a social preference feedback mechanism to automatically generate preference data through principled preference evaluation criteria. By explicitly accounting for the intricacies of pedestrian dynamics, the pipeline mitigates the reward bias and facilitates the systematic quantification of broad social norms, thereby fostering socially compliant behaviors. Extensive experiments integrating SPLC with offline RL methods demonstrate consistent improvements over state-of-the-art baselines across standard performance metrics. Furthermore, real-world experiments on the TurtleBot4 further validate the effectiveness of SPLC in practical human-robot coexistence settings. Our code and video demos are available at https://github.com/sklus949/SPLC.

Problem

• crowd robot navigation
• offline reinforcement learning
• reward function design
• social compliance
• pedestrian dynamics

Innovation

• social preference learning
• offline reinforcement learning
• crowd robot navigation
• reward-free learning
• human-robot coexistence