The Optimization and Application Research of the RRT-APF-Based Path Planning Algorithm

Abstract

To address the shortcomings of the original rapidly-exploring random tree (RRT) algorithm, such as long and non-smooth paths, slow convergence to the goal region, and limited adaptability in dynamic environments, this paper proposes a hybrid path planning method combining the artificial potential field (APF) approach with the RRT algorithm. This integrated approach leverages the strengths of both methods to achieve efficient, collision-free path planning in both two-dimensional and three-dimensional environments. The algorithm overcomes the local minima problem inherent in APF while maintaining the RRT’s efficiency in high-dimensional spaces and complex environments. A dynamic adjustment strategy is introduced to adapt to specific application scenarios and varying environmental complexity. Additionally, Bezier curve fitting is applied to smooth the resulting paths. Simulations conducted in various environments demonstrate the effectiveness of the proposed method, highlighting its efficiency and robustness in generating collision-free paths. Compared to the original RRT algorithm, the proposed method reduces path length by 13.4% to 24.9% and decreases search time by 9.8% to 56.5%, improving both path quality and planning efficiency.