Collaborative Motion Planning Based on the Improved Ant Colony Algorithm for Multiple Autonomous Vehicles
Shengchao Su, Xiang Ju, Chaojie Xu, Yufeng Dai
Abstract
To improve the online collaboration and planning capabilities between autonomous vehicles, this paper proposes a novel collaborative motion planning method. In this method, the ant colony algorithm was introduced and improved to achieve collaborative motion planning for multiple autonomous vehicles. First, independent subpopulations of the same size were generated according to the number of autonomous vehicles. Then, a multi-objective optimization function was established to optimize spatial collaboration and trajectory costs, and to update the pheromone in the ant colony algorithm. Meanwhile, the evaporation coefficient in the algorithm was adaptively adjusted to enhance the global search ability and improve the convergence speed of the algorithm. Finally, a feasible path was planned for each autonomous vehicle based on the path of each subpopulation. Simulation results show that the proposed method is effective and it can achieve stronger adaptability than the artificial potential field motion planning algorithm.