arXiv 2604.233602026-04-25cs.RO

基于失败意识的学习用于安全机器人导航

Learning from Demonstration with Failure Awareness for Safe Robot Navigation

Department of Mechanical Engineering, The Hong Kong Polytechnic University（香港理工大学机械工程系）；College of Information Science and Technology, Eastern Institute of Technology（东华理工大学信息科学学院）；School of Computer Science and Technology, University of Science and Technology of China（中国科学技术大学计算机科学与技术学院）；Department of Aeronautical and Aviation Engineering, The Hong Kong Polytechnic University（香港理工大学航空与航空工程系）

Xianghui Wang, Siwei Cheng, Shanze Wang, Xinming Zhang, Dan Zhang, Wei Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种失败意识学习框架，通过分离成功与失败数据提升机器人导航安全性，减少碰撞并保持任务成功率。

摘要：

学习从示范在机器人导航中被广泛使用，但存在根本限制：示范主要包含成功行为，对不安全状态覆盖有限。这种限制导致机器人遇到超出示范分布的场景时安全性下降。失败经验如碰撞包含关于不安全区域的重要信息，但未被充分利用。关键难点在于失败数据无法提供有效的动作模仿指导，其简单纳入策略学习往往会降低性能。本文通过提出一个失败意识学习框架，明确分离成功和失败数据的角色。在该框架中，失败经验用于塑造危险区域的价值估计，而策略学习被限制在成功示范上。这种分离使失败数据得到有效利用而不影响策略行为。我们在此设计中实现了离线强化学习（RL）设置，并在仿真和真实环境进行评估。结果表明，我们的框架在减少碰撞率的同时保持任务成功率，并在不同环境和机器人平台中表现出强大的泛化能力。

英文摘要：

Learning from demonstration is widely used for robot navigation, yet it suffers from a fundamental limitation: demonstrations consist predominantly of successful behaviors and provide limited coverage of unsafe states. This limitation leads to poor safety when the robot encounters scenarios beyond the demonstration distribution. Failure experiences, such as collisions, contain essential information about unsafe regions, but remain underutilized. The key difficulty lies in the fact that failure data do not provide valid guidance for action imitation, and their naive incorporation into policy learning often degrades performance. We address this challenge by proposing a failure-aware learning framework that explicitly decouples the roles of success and failure data. In this framework, failure experiences are used to shape value estimation in hazardous regions, while policy learning is restricted to successful demonstrations. This separation enables the effective use of failure data without corrupting policy behavior. We implement this design within an offline reinforcement learning (RL) setting and evaluate it in both simulation and real-world environments. The results show that our framework consistently reduces collision rates while preserving the task success rate, and demonstrate strong generalization across different environments and robot platforms.

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。