This paper proposes a method to control distributed autonomous robots for task sharing by simple rewards of an operator. The operator observes a group of robots, and provides rewards depending on its task sharing. Each robot creates its own behavioral evaluation by using the reward, and learns an appropriate behavior selection depending on situations. As the result, robots may generate cooperative behaviors such as task sharing. This means that an operator can control a group of robots by simple rewards. We performed simulations to study the effectiveness of the proposed method. And we confirmed that an operator can control robots without modifying the method even if we change the number of robots in the middle of simulation experiments.
© 2001-2026 Fundación Dialnet · Todos los derechos reservados