Learning from Extrapolated Corrections
Learning from Extrapolated Corrections
复制标题
从外推修正中学习
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
A. Dragan
中科院分区：
文献类型：
--
作者：
Jason Y. Zhang;A. Dragan
我们的目标是使机器人能够从用户指导中学习成本函数。用户通常很难或不可能提供完整的演示，因此更正已成为一种更容易的指导渠道。然而，当机器人从修正而不是演示中学习成本函数时，它们必须将少量信息（沿途航路点的变化）外推到轨迹的其余部分。我们将这个外推问题转换为在线函数近似，这暴露了机器人可以根据用于近似的函数空间来解释人想要的轨迹的不同方式。我们的模拟结果和用户研究表明，使用非欧几里得规范的函数空间可以更好地捕捉用户的意图，特别是在环境整洁的情况下。反过来，这可以使机器人学习更准确的成本函数，并提高用户对机器人的主观感知。
Our goal is to enable robots to learn cost functions from user guidance. Often it is difficult or impossible for users to provide full demonstrations, so corrections have emerged as an easier guidance channel. However, when robots learn cost functions from corrections rather than demonstrations, they have to extrapolate a small amount of information - the change of a waypoint along the way – to the rest of the trajectory. We cast this extrapolation problem as online function approximation, which exposes different ways in which the robot can interpret what trajectory the person intended, depending on the function space used for the approximation. Our simulation results and user study suggest that using function spaces with non-Euclidean norms can better capture what users intend, particularly if environments are uncluttered. This, in turn, can lead to the robot learning a more accurate cost function and improves the user’s subjective perceptions of the robot.