For real-time and distributed features of multi-robot system, the strategy of combining the improved artificial potential field method and the mles based on priority is proposed to study the collision avoidance planning in multi-robot systems. The improved artificial potential field based on simulated annealing algorithm satisfactorily overcomes the drawbacks of traditional artificial potential field method, so that robots can find a local collision-free path in the complex environment. According to the movement vector trail of robots, collisions between robots can be detected, thereby the collision avoidance rules can be obtained. Coordination between robots by the priority based rules improves the real-time property of multi-robot system. The combination of these two methods can help a robot to find a collision-free path from a starting point to the goal quickly in an environment with many obstacles. The feasibility of the proposed method is validated in the VC-basod simulated environment.