This paper proposes a method for generating cooperative behaviors among distributed autonomous robots based on local communications. In general, each robot can not communicate with all of the other robots when there are many robots in the environment. In order to cope with its problem, each robot should use local communication. However, it is difficult to make cooperation such as task sharing because each robot can not obtain the information of a whole group. In this paper, we describe a method to solve the problem. By using the method, an operator can conduct a group of robots to desired task sharing even if they use local communication. We studied an appropriate area size of local communication for robots. If the area is too small, each robot may not be able to cooperate with the other robots, because each robot doesn't have enough information. In order to find an appropriate area size of local communication, we carried out simulations. And we confirmed that the area size is not changed even if the number of robots is changed. After that, we performed simulation experiments to study the effectiveness of proposed method. In the simulations, we confirmed that robots could share task depending on commands from an operator.

In this paper, we present a novel self-generating algorithm for behavioral evaluation, which is used to evaluate self-selected behaviour in a reinforcement learning system. This behavioral evaluation is composed of rewards and self-evaluated standards. Rewards are given by the operator as one of the methods for understanding the purpose of tasks; and self-evaluated standards are obtained as the result of executions. Each robot can generate the evaluation depending on its situations by using the proposed method, and therefore the robots can create cooperative behaviours even if the number of robots or tasks is changed dynamically. We performed simulation experiments to study the effectiveness of the proposed method. The experimental results confirm that each robot can generate evaluations for creating cooperative behaviours without changing the algorithm during the simulation experiments.

This paper deals with spontaneous behavior for cooperation among distributed autonomous robots. Though human gives the robots evaluation functions of the relation of cooperation among them, each robot determines its behavior depending on its experience and the behaviors of other robots. The robot acquires a model of behaviors of the other robots through teaming. Inspired from biological systems, the robot has emotions which play important roles of behavior selection. Each robot feels frustration when its determination does not suit to its environment. Then, it changes its behavior to change its situation actively. The results show a potential of emotional intelligence in robotics.