Decision Making Under Multi Task Based on Priority for Each Task

Decision Making Under Multi Task Based on Priority for Each Task

Takuya Masaki (Muroran Institute of Technology, Japan) and Kentarou Kurashige (Muroran Institute of Technology, Japan)
Copyright: © 2019 |Pages: 12
DOI: 10.4018/978-1-5225-8060-7.ch044
OnDemand PDF Download:
No Current Special Offers


In recent years, autonomous robots become to be desired to treat multi-task. A robot must decide a concrete action for plural objectives. Major researches try to realize this by weighted rewards. Weighted rewards can represent a human's intention easily. But weight of each task must change dynamically by a change of surrounding situation or of a robot status. Authors consider an independent learning for each task and selection of one concrete action from candidates of each learning. Authors propose a priority function to calculate priority for each task corresponding to surrounding situation or a robot status and propose a system which do decision making by using the priority function. Authors confirmed the usefulness of proposed method with simulation.
Chapter Preview

3. Proposal Technique

3.1. Outline of Proposal Technique

In this paper, authors propose the action learning and the action selection method of a robot that has multi task. Proposal method is roughly divided into the action selection part and the action learning part. The system does action learning for each task in the action learning part. In the action learning part, the system does action learning and accumulate action value into learning space. Thereafter, action value that learned is passed to action selection part.

Complete Chapter List

Search this Book: