期刊
IEEE TRANSACTIONS ON ROBOTICS
卷 39, 期 1, 页码 681-698出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TRO.2022.3192969
关键词
Robots; Task analysis; Behavioral sciences; Linear programming; Hidden Markov models; Reliability; Predictive models; Expertise inference; human factors; learning and adaptive systems; learning from demonstration
类别
This article discusses the issue of robots learning from nonexpert humans, advocating for the robot to understand not only the human's objectives but also their expertise level. The article proposes two inference approaches and demonstrates them in simulation and with real user data.
When a robot learns from human examples, most approaches assume that the human partner provides examples of optimal behavior. However, there are applications in which the robot learns from nonexpert humans. We argue that the robot should learn not only about the human's objectives, but also about their expertise level. The robot could then leverage this joint information to reduce or increase the frequency at which it provides assistance to its human's partner or be more cautious when learning new skills from novice users. Similarly, by taking into account the human's expertise, the robot would also be able to infer a human's true objectives even when the human fails to properly demonstrate these objectives due to a lack of expertise. In this article, we propose to jointly infer the expertise level and the objective function of a human given observations of their (possibly) nonoptimal demonstrations. Two inference approaches are proposed. In the first approach, inference is done over a finite discrete set of possible objective functions and expertise levels. In the second approach, the robot optimizes over the space of all possible hypotheses and finds the objective function and the expertise level that best explain the observed human behavior. We demonstrate our proposed approaches both in simulation and with real user data.
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