著者
伊藤 一之 松野 文俊
出版者
一般社団法人 人工知能学会
雑誌
人工知能学会論文誌 (ISSN:13460714)
巻号頁・発行日
vol.16, no.6, pp.510-520, 2001 (Released:2002-02-28)
参考文献数
19
被引用文献数
2 7

Reinforcement learning has recently received much attention as a learning method for complicated systems, e.g., robot systems. It does not need prior knowledge and has higher capability of reactive and adaptive behaviors. However increase in dimensionality of the action-state space makes it diffcult to accomplish learning. The applicability of the existing reinforcement learning algorithms are effective for simple tasks with relatively small action-state space. In this paper, we propose a new reinforcement learning algorithm: “Q-learning with Dynamic Structuring of Exploration Space Based on Genetic Algorithm ”. The algorithm is applicable to systems with high dimensional action and interior state spaces, for example a robot with many redundant degrees of freedom. To demonstrate the effectiveness of the proposed algorithm simulations of obstacle avoidance by a 50 links manipulator have been carried out. It is shown that effective behavior can be learned by using the proposed algorithm.
著者
五福 明夫 中谷 武平 横田 直人 伊藤 一之
出版者
一般社団法人 日本機械学会
雑誌
設計工学・システム部門講演会講演論文集
巻号頁・発行日
vol.2003, pp.285-288, 2003

This study develops a dialogue model and a command interpretation technique for service robots to obtain interactively the necessary information of actions for the tasks requested from users. A request from users sometimes misses some data necessary to complete the requested task because a voice command is usually requested depending on context and situation. The developed command interpretation technique first divides a command into words. Then, it analyzes the content of the command paying attention to the verb used and object included. If there are some missing data in the command, it sequentially generates queries to obtain them. The applicability of the dialogue model and the technique is demonstrated by dialogue experiments using a robot arm system.