期刊
IEEE ROBOTICS AND AUTOMATION LETTERS
卷 6, 期 4, 页码 6569-6576出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3093551
关键词
Autonomous agents; deep learning for robotics and automation; search and rescue robots
类别
资金
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- Canada Research Chairs program (CRC)
The study presented a novel sim-to-real pipeline for a mobile robot to effectively learn how to navigate real-world 3D rough terrain environments, with experiments showing that our method outperformed classical and deep learning-based approaches in terms of success rate, cumulative travel distance, and time in a 3D rough terrain environment.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据