arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2011.15014cs.ROcs.LGcs.SYeess.SY
收藏

从人类定向校正中学习

Learning from Human Directional Corrections

University of Pennsylvania(宾夕法尼亚大学);Northwestern University(西北大学);Purdue University(普渡大学)

Wanxin Jin, Todd D. Murphey, Zehui Lu, Shaoshuai Mou

摘要:

本文提出了一种新的方法,使机器人学习的目标函数逐步从人类的方向校正。现有的方法从人类幅度校正中学习;由于人类需要仔细选择每个校正的幅度,这些方法很容易导致过度校正和学习效率低下。所提出的方法只需要人为的方向修正--修正只指示输入变化的方向,而不指示其大小。我们只假设每个校正,无论其大小,在一个方向,改善机器人的当前运动相对于一个未知的目标函数的点。满足这一假设的允许修正占输入空间的一半,而不是幅度修正必须位于一个收缩的水平集。对于每个方向校正,所提出的方法更新的目标函数的估计的基础上的切割平面的方法,它具有几何解释。我们已经建立了理论结果,以显示收敛的学习过程。所提出的方法已在数值示例、两款人机游戏的用户研究以及真实世界的四旋翼实验中进行了测试。结果证实了所提出的方法的收敛性,并进一步表明,该方法是显着更有效的(更高的成功率),高效/轻松(需要更少的人工校正),并可能更容易(更少的早期浪费的试验)比最先进的机器人学习框架。

英文摘要:

This paper proposes a novel approach that enables a robot to learn an objective function incrementally from human directional corrections. Existing methods learn from human magnitude corrections; since a human needs to carefully choose the magnitude of each correction, those methods can easily lead to over-corrections and learning inefficiency. The proposed method only requires human directional corrections -- corrections that only indicate the direction of an input change without indicating its magnitude. We only assume that each correction, regardless of its magnitude, points in a direction that improves the robot's current motion relative to an unknown objective function. The allowable corrections satisfying this assumption account for half of the input space, as opposed to the magnitude corrections which have to lie in a shrinking level set. For each directional correction, the proposed method updates the estimate of the objective function based on a cutting plane method, which has a geometric interpretation. We have established theoretical results to show the convergence of the learning process. The proposed method has been tested in numerical examples, a user study on two human-robot games, and a real-world quadrotor experiment. The results confirm the convergence of the proposed method and further show that the method is significantly more effective (higher success rate), efficient/effortless (less human corrections needed), and potentially more accessible (fewer early wasted trials) than the state-of-the-art robot learning frameworks.

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。

↑