The paper focuses on the challenge of path planning in autonomous driving – finding the optimal path in complex, dynamic environments with many obstacles. The authors propose a two-stage path planning algorithm, Angle-based Directed Rapidly exploring Random Trees (AD-RRT*), which uses the A* algorithm for global path planning and modifies RRT* to bound the samples using angle. The efficiency of this algorithm is evaluated through experiments in different scenarios based on the location and number of obstacles. The results show that the proposed algorithm has a higher rate of convergence with reduced time and fewer nodes than the base RRT* algorithm.
Publication date: 20 Feb 2024
Project Page: Unknown
Paper: https://arxiv.org/pdf/2402.12129
