Adaptive Set-Based CLPSO for Path Planning of Multi-Target Surveillance with Moving Obstacles

Multi-target surveillance is an important application of path planning in the field of autonomous vehicles (AV). The existing researches are limited to either static or random obstacle environments. A model-based moving obstacle environment is proposed in this paper. By setting the start point of the AV, when evaluating the path, the moving process of AV is monitored. The positions of obstacles are updated according to the time, as well as the path threat. The cost of the route between any two targets depends not only on the distance, but also the path threat value weighted by a penalty factor. In this paper, a set-based comprehensive learning particle swarm optimization with local search (S-CLPSO+LS) is proposed to find the optimal path. The influence of the penalty factor on the obstacle avoidance ability of the algorithm is discussed. Four dynamic scenarios with different characteristics are designed and analyzed, and other path planning algorithms have been used for comparative experiments.