Incremental Acquisition of Behavior Decision Model based on Interaction between Human and Robots
Incremental Acquisition of Behavior Decision Model based on Interaction between Human and Robots
复制标题
基于人机交互的行为决策模型增量获取
DOI：
10.7210/jrsj.19.983
复制
发表时间：
2001
期刊：
影响因子：
--
通讯作者：
H. Inoue
中科院分区：
文献类型：
--
作者：
T. Inamura;M. Inaba;H. Inoue
本文提出了一种新的基于用户与机器人交互的个人机器人自主行为获取方法。该方法具有两个优点：一是与用户教学相比，用户无需负担;二是与自主学习相比，机器人可以按照用户的意愿获取行为。该方法将感知信息和交互结果存储起来，并将传感器与行为之间的关系表示为随机行为决策模型机器人通过使用随机模型向用户提出建议和问题来推进学习我们研究了这种方法在移动的机器人避障任务中的可行性通过实验我们证实了移动的机器人仅通过几次示教就获得了对环境变化的回避行为我们还证实了所获得的模型反映了用户的经验因此，该模型反映了教学操作的个人偏好
In this paper we propose a novel method for personal robots to acquire autonomous behaviors based on interaction between users and robots This method have two advantages rst is loadless for users by comparison with users teaching second is that robots can acquire behaviors as users wish by comparison with autonomous learning In this method robots store sensory information and results of interaction and represent the relationship between sensor and behavior as stochastic behavior decision models The robot advances the learning through making suggestions and questions for the user using the stochastic model We investigate the feasibility of this method on obstacle avoid ance tasks for mobile robots Through experiments we have con rmed that the mobile robot acquires avoidance behavior against change of environment through only several teaching Also we have con rmed that the acquired models re ect the experience of interaction therefore the model re ects personal preferences of teaching operation