Trajectory Generation of A Human-Friendly Robot using An Interactive Genetic Algorithm

Kubota, Naoyuki and Sulistijono, Indra Adji and Kojima, Fumio (2002) Trajectory Generation of A Human-Friendly Robot using An Interactive Genetic Algorithm. In: Asia-Pasific Conference on Simulated Evolution and Learning (SEAL) 2002, Nov 18-22, 2002, Singapore.

PDF (SEAL2002) - Published Version Restricted to Registered users only until 02 June 2014. Available under License Creative Commons Public Domain Dedication. Download (348Kb) | Request a copy

Abstract

This paper deals with human-friendly trajectory generation of a robot manipulator. Various methods for the trajectory generation have been proposed so far, but robots must deal with environments including human operators. This paper applies an interactive genetic algorithm for the trajectory generation using human evaluation, but the detail of the human evaluation is not clear. Therefore, we must estimate human evaluation through the optimization process, and we use a state-value function used often in reinforcement learning. Furthermore, we discuss the effectiveness of the proposed method through some experiments of the robot manipulator.

Actions (login required)