Local Path Planning Algorithm for UGV Based on Improved Covariance Matrix Adaptive Evolution Strategy

Local path planning algorithm is one of the key technologies for unmanned ground vehicle(UGV). In order to reduce the computational complexity of the local path planning algorithm and ensure the real-time performance of the algorithm, a non-uniform column grid lines modeling method is introduced, and on this basis, a modeling method for planning paths is proposed. Aiming at the path planning problem in a multi -obstacle environment, the evaluation function of the path is constructed from four aspects, and the covariance matrix adaptive evolution strategy(CMA-ES) is used to solve the nonlinear optimization problem. In order to further reduce the amount of calculation, the CMA-ES algorithm is improved by the dynamic adjustment strategy of population size. Experiment results show that the path planning algorithm can effectively realize the local path planning in complex environment.