Learning to Drive Anywhere with Model-Based Reannotation
基于模型的重新标注:学习在任何地方驾驶
机构 * Department of Electrical Engineering and Computer Sciences , University of California, Berkeley, CA USA(电气工程与计算机科学系,加州大学伯克利分校) ; Toyota Motor North America, Inc(丰田北美公司) ; Department of Electrical and Computer Engineering, Princeton University(电气与计算机工程系,普林斯顿大学)
AI总结 本文提出基于模型的重新标注框架,利用被动数据训练出高效导航策略,实现机器人在复杂环境中的长距离稳健导航。
Comments 9 pages, 8 figures, 6 tables
Journal ref IEEE Robotics and Automation Letters 2025