In order to meet the real-time and accurate requirements of multi-robot path planning in dynamic environment, this paper adopted wireless sensor network to locate robots and obstacles and used an improved artificial intelligent algorithm to plan path. In this paper, a jumping mechanism particle swarm optimization (JPSO) algorithm and a safety gap obstacle avoidance algorithm (SGOA) algorithm were proposed. Compared with canonical PSO algorithm, JPSO algorithm has three improvement strategies: Fitness value evaluation function, new learning sample and jumping strategy. The JPSO algorithm updates the particles with poor comprehensive quality by jumping and adjusts the inertia weight adaptively according to fitness value evaluation function. With the cooperation of new learning samples, the global searching ability and precision of the algorithm can be improved. SGOA algorithm is mainly aimed at the problem that robots with low priority are stuck in a long wait and cannot continue to walk when avoiding obstacles. By implementing the SGOA algorithm, a new collision-free safety path can be optimized for the robot with low priority. In order to verify JPSO and SGOA algorithm, a lot of experiments were done. JPSO algorithm was compared with two other improved PSO algorithms with 6 standard test functions. The path planning and obstacle avoidance experiments of six robots were realized using the JPSO and SGOA algorithm. The experimental results show that JPSO algorithm has higher accuracy and faster convergence speed than the other two improved PSO algorithms, and SGOA algorithm can solve the dynamic obstacle avoidance problem in the path planning of multiple robots well.

为了满足动态环境下多机器人路径规划的实时性和准确性要求，本文采用无线传感器网络对机器人和障碍物进行定位，并采用改进的人工智能算法进行路径规划。提出了一种跳跃机制粒子群算法（JPSO）和安全间隙避障算法（SGOA）。与标准PSO算法相比，JPSO算法具有三种改进策略：适应度值评估功能，新学习样本和跳跃策略。JPSO算法通过跳跃更新综合质量较差的粒子，并根据适应度评估功能自适应地调整惯性权重。与新的学习样本合作，可以提高算法的全局搜索能力和精度。SGOA算法主要针对低优先级的机器人被困在漫长的等待中并且在避开障碍物时不能继续行走的问题。通过实施SGOA算法，可以为低优先级的机器人优化一条新的无碰撞安全路径。为了验证JPSO和SGOA算法，进行了大量实验。将JPSO算法与其他两种具有6种标准测试功能的改进PSO算法进行了比较。利用JPSO和SGOA算法实现了6个机器人的路径规划和避障实验。实验结果表明，与其他两种改进的PSO算法相比，JPSO算法具有更高的精度和更快的收敛速度，