Abstract
In order to make robots more intelligent, the analysis, acquisition, and application of the human control strategy are drawing more and more attention. In this paper, we develop an intelligent game robot on an omnidirectional mobile platform which is made up of three omniwheels. The game platform consists of a square flat board, a ball, and a camera used to record the position of the ball. There is a goal on the board and the task is to move the ball into the goal by operating the robot. We analyzed the human control strategy in the ball-into-goal game based on the relationship between the human operation and the position of the ball on the board. The human control strategy was described by the relationship. The effectiveness of knowledge acquisition is demonstrated by an experiment in which the robot automatically played the game with the knowledge.
