Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations

Read full text Summarise with VIRAT
Authors: Han Bao, Bingyi Xia, Hanjing Ye, Yu Zhan, Hao Cheng, Baozhi Jia, Wenjun Xu, Jiankun Wang
Cited by: 0
References: 35

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Robot crowd navigation requires the ability to infer human intentions while accounting for the structural constraints of the environment. Currently, deep reinforcement learning (DRL) provides a promising method for learning navigation policies that understand human intentions. However, most of them rely on limited scene representations, treating pedestrians as simple 2D points and ignoring rich visual cues from both humans and the environment. To address this issue, iCrowdNav, a novel visual crowd navigation method with intention-aware scene representations, is introduced to encode behavioral and structural context from egocentric visual observations. Our method employs two key components: a spatio-temporal encoder for extracting occupancy features of the scene, and Intent-Interact Former (I2Former), an attention-based module that encodes human poses to infer pedestrians' motion intentions. These features are integrated into a compact state embedding that supports effective DRL policy training. Extensive experiments show that our method achieves superior performance over baselines, and real world deployment demonstrates vision-based crowd navigation.

Fields of Study & Subjects

Reinforcement Learning in Robotics Evacuation and Crowd Dynamics Autonomous Vehicle Technology and Safety

Publication details

Journal / source
IEEE Robotics and Automation Letters
Volume
11
Issue
5
Pages
6186–6193
Publication date
25 March 2026
Language
EN