PEXIS: probabilistic experience representation based adaptive interaction system for personal robots

摘要

In this paper the authors focus on the interaction between users and personal robots that can move in a real environment. When the creation of robots that can perform in an ordinary home or office is considered, it is difficult to imagine beforehand what kind of environment will be used, and so the approach in which developers embed environmental knowledge and strategies for autonomous movement fails. Thus, the authors propose an approach in which knowledge of the environment and the knowledge needed to move are acquired after development by allowing the robot and the user who is using the robot to engage in dialogue, and representing experience statistically. The authors introduce PEXIS, an interaction system developed using this approach, and then describe the characteristics and utility of their system via examples such as learning to avoid objects in an office environment and adapting to the vocabulary expressions of a particular user.