A Research On The Pursuit Strategy For The Multiple Robots With Emotion

The multiple robots system can not only replace humans to complete many tedious and complex work, but also help people to perform many difficult and dangerous tasks. Research on the multiple robots system can not only reduce labor intensity and improve the efficiency effectively, but also reduce the risk of certain tasks in a certain extent to ensure the safety. As an important research direction of the multiple robots system, the multiple robots pursuit-evader problem has always been an important method to study the problem of team cooperation and team coordination. Through the research on multiple robots pursuit-evader problem, we can simulate many actual problems to get the effective task strategy and improve the task execution efficiency. At the same time, along with the continuous improvement of the intelligent demand of the robot, the emotional robot gradually enters people’s vision. Humanity is no longer satisfied with the situation that the robot can replace people to perform certain tasks. They require more harmonious and more intelligent robots to execute the task. Therefore, this paper discusses the task allocation problem and the cooperative pursuit algorithm of the emotional robot based on the multiple robots pursuit-evader problem, which makes the strategy of team cooperation and team coordination more consistent with current social needs, and improves the system efficiency.The main contents of this paper include the following aspects:1、This paper researches the alliance generation algorithm with emotional factors on the basis of multiple robots pursuit-evader problem. Firstly, this paper constructs an emotional model for pursuit robots:we not only apply the basic emotion method to the emotional expression, but also simulate the process of emotional transfer with Hidden Markov Model (HMM). Secondly, we determine the cooperation intention according to the robots’emotional factors, so that we can prevent the robots with the negative emotions from involving in the mission in case of a negative impact on the alliance. Then, we introduce the subgroup size on the foundation of particle swarm optimization (PSO) to avoid the premature convergence problem, thus the algorithm can obtain the maximum profit in a relatively short period of time. Finally, we bring in the dynamic redistribution mechanism for a better pursuit efficiency.2、Through the improvement of the traditional method of artificial potential field, we discuss the cooperative pursuit algorithm of the emotional robot. Firstly, the introduction of waiting secretly thought and the use of the "active regions-pursuit range" method can determine the evaders’target points, which makes the pursuit alliance form a team from the real meaning. Then, through the optimization of the repulsion system, we can avoid the collision occurred during the mission, which makes the pursuers can complete the mission more harmoniously,and improves the efficiency of the system. Finally, the introduction of the mechanism of the external force can solve the dilemma of the local minimum that the system may fall into effectively, which improves the system’s task completion rate.