Robots that autonomously navigate real-world 3D cluttered environments need to safely traverse terrain with abrupt changes in surface normals and elevations. In this letter, we present the development of a novel sim-to-real pipeline for a mobile robot to effectively learn how to navigate real-world 3D rough terrain environments. The pipeline uses a deep reinforcement learning architecture to learn a navigation policy from training data obtained from the simulated environment and a unique combination of strategies to directly address the reality gap for such environments. Experiments in the real-world 3D cluttered environment verified that the robot successfully performed point-to-point navigation from arbitrary start and goal locations while traversing rough terrain. A comparison study between our DRL method, classical, and deep learning-based approaches showed that our method performed better in terms of success rate, and cumulative travel distance and time in a 3D rough terrain environment.

中文翻译：

---

用于在杂乱崎岖地形中自主机器人导航的深度强化学习的模拟到真实管道


自主导航现实世界 3D 杂乱环境的机器人需要安全地穿越表面法线和高程突然变化的地形。在这封信中，我们介绍了一种新颖的模拟到真实管道的开发，该管道适用于移动机器人，以有效学习如何在现实世界的 3D 崎岖地形环境中导航。该管道使用深度强化学习架构，从模拟环境中获得的训练数据中学习导航策略，并使用独特的策略组合来直接解决此类环境的现实差距。在现实世界的 3D 杂乱环境中进行的实验验证了机器人在穿越崎岖地形时成功地从任意起始位置和目标位置执行点对点导航。我们的 DRL 方法、经典方法和基于深度学习的方法之间的比较研究表明，我们的方法在 3D 崎岖地形环境中的成功率、累积行进距离和时间方面表现更好。