通过意图感知场景表示学习机器人在人群中的视觉导航
Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations
AI总结：
提出iCrowdNav方法，利用时空编码器和Intent-Interact Former从视觉观测中提取场景占用特征和人体姿态意图，通过深度强化学习实现高效人群导航。
摘要：
机器人人群导航需要具备推断人类意图的能力，同时考虑环境的结构约束。目前，深度强化学习（DRL）为学习理解人类意图的导航策略提供了一种有前景的方法。然而，大多数方法依赖于有限的场景表示，将行人视为简单的二维点，忽略了来自人类和环境的丰富视觉线索。为了解决这个问题，我们引入了iCrowdNav，一种新颖的视觉人群导航方法，具有意图感知的场景表示，从自我中心的视觉观察中编码行为和环境上下文。我们的方法采用两个关键组件：一个用于提取场景占用特征的时空编码器，以及Intent-Interact Former（I$^2$ Former），一个基于注意力的模块，用于编码人体姿态以推断行人的运动意图。这些特征被整合到一个紧凑的状态嵌入中，支持有效的DRL策略训练。大量实验表明，我们的方法在基线上取得了优越的性能，并且实际部署展示了基于视觉的人群导航。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
