Rapid behavior adaptation for human-centered robots in a dynamic environment based on the integration of primitive confidences on multi-sensor elements |
| |
Authors: | Saifuddin Md Tareeq Tetsunari Inamura |
| |
Affiliation: | 1. Graduate University for Advanced Studies, National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo, Japan
|
| |
Abstract: | This article presents a method for tele-operated mobile robots to rapidly adapt to behavior policies. Since real-time adaptation
requires frequent observations of sensors and the behavior of users, rapid policy adaptation cannot be achieved when significant
data are not differentiated from insignificant data in every process cycle. Our method solves this problem by evaluating the
significance of data for learning based on changes in the degree of confidence. A small change in the degree of confidence
can be regarded as reflecting insignificant data for learning (that data can be discarded). Accordingly, the system can avoid
having to store experience data too frequently, and the robot can adapt more rapidly to changes in the user’s policy. In this
article, we confirm that by taking advantage of a significance evaluation not only of proposition of behavior, but also of
each proposition of each piece of sensor-level data, a robot can rapidly adapt to a user’s policy. We discuss the results
of two experiments in static and dynamic environments, in both of which the user switched policies between “avoid” and “approach.” |
| |
Keywords: | |
本文献已被 SpringerLink 等数据库收录! |
|