A Hybrid Optimization Algorithm for Automatic Parking Trajectory Planning in Complex Scenarios

With the continuous complexity of the current environment, it is becoming increasingly challenging to park quickly and safely. This paper proposes a hybrid optimization algorithm to solve the problem by planning an optimal parking path for automated vehicles in complex environments with static obstacles. Firstly, a multi-constraint trajectory optimization model by minimizing parking time is established. Secondly, the Gaussian pseudo-spectral method reconstructs the optimization model into a nonlinear programming problem. Then, the particle swarm optimization algorithm is utilized to solve the problem and generate an initial guess for the trajectory. Finally, the best optimal trajectory is generated iteratively by the sequential quadratic programming algorithm under all constraints. The simulation results demonstrate that the proposed hybrid optimization algorithm can effectively handle complex parking path planning problems by finding the optimal collision-free trajectory in a shorter time.