Obstacle avoidance path planning for intelligent vehicles based on improved RRT algorithm

Aiming at the problem of time inefficiency caused by blind search of traditional rapid exploring random tree (RRT) algorithm for obstacle avoidance path planning of intelligent vehicles, an improved RRT algorithm is proposed. Firstly, the search area of the RRT algorithm is restricted according to the equations of motion and steering constraints of the vehicle. Then, an artificial potential field (APF) method is introduced to guide the RRT expansion nodes, which accelerates the convergence speed of the algorithm. Finally, the generated path is pruned to make the path planning smoother and shorter. The comparison of the proposed algorithm with the traditional RRT algorithm in the MATLAB platform shows that the proposed algorithm in this paper has superior performance in terms of search nodes, the time required for path planning, and path security performance.