Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations
For robot navigation in crowded environments, this work addresses the limitation of treating pedestrians as simple 2D points by incorporating rich visual cues and human pose-based intention inference.
iCrowdNav introduces a visual crowd navigation method using intention-aware scene representations that encode behavioral and structural context from egocentric observations, achieving superior performance over baselines in simulation and real-world deployment.
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, we introduce iCrowdNav, a novel visual crowd navigation method with intention-aware scene representations, 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 (I$^2$ Former), 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.