Autonomous Learning of Ball Trapping in the Four-Legged Robot League

摘要: This paper describes an autonomous learning method used with real robots in order to acquire ball trapping skills the four-legged robot league. These involve stopping and controlling oncoming are essential passing a each other. We first prepare some training equipment then experiment only one robot. The can use our these necessary on its own, much same way that human practicing against wall learn proper movements actions of soccer his/her own. also two robots, findings suggest communicating between other more rapidly than those without any communication.