MAER-Nav：通过镜像增强经验回放进行机器人导航的双向运动学习
MAER-Nav: Bidirectional Motion Learning Through Mirror-Augmented Experience Replay for Robot Navigation
AI总结：
本文提出MAER-Nav框架，通过结合镜像增强经验回放机制与课程学习，从成功轨迹生成合成后退导航经验，实现无需修改奖励函数的双向运动学习，有效解决了传统DRL导航在狭小复杂环境中因缺乏后退灵活性而易受困的问题。
摘要：
基于深度强化学习（DRL）的导航方法在移动机器人上展现出良好的效果，但在狭小空间中动作灵活性有限。传统DRL方法主要学习前进运动策略，导致机器人在需要后退操作以进行恢复的复杂环境中受困。本文提出MAER-Nav（用于机器人导航的镜像增强经验回放），这是一种新型框架，无需显式的失败驱动事后经验回放或奖励函数修改即可实现双向运动学习。该方法将镜像增强经验回放机制与课程学习相结合，从成功轨迹中生成合成的后退导航经验。在仿真和真实环境中的实验结果表明，MAER-Nav在保持强大前进导航能力的同时，显著优于现有最先进方法。该框架有效弥合了传统规划方法全面动作空间利用与基于学习方法环境适应性之间的差距，在传统DRL方法持续失败的场景中实现了稳健导航。
英文摘要：
Deep Reinforcement Learning (DRL) based navigation methods have demonstrated promising results for mobile robots, but suffer from limited action flexibility in confined spaces. Conventional DRL approaches predominantly learn forward-motion policies, causing robots to become trapped in complex environments where backward maneuvers are necessary for recovery. This paper presents MAER-Nav (Mirror-Augmented Experience Replay for Robot Navigation), a novel framework that enables bidirectional motion learning without requiring explicit failure-driven hindsight experience replay or reward function modifications. Our approach integrates a mirror-augmented experience replay mechanism with curriculum learning to generate synthetic backward navigation experiences from successful trajectories. Experimental results in both simulation and real-world environments demonstrate that MAER-Nav significantly outperforms state-of-the-art methods while maintaining strong forward navigation capabilities. The framework effectively bridges the gap between the comprehensive action space utilization of traditional planning methods and the environmental adaptability of learning-based approaches, enabling robust navigation in scenarios where conventional DRL methods consistently fail.
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。
