Research on Low-Altitude UAV Path Planning by Integrating RRT and Artificial Potential Field

An integrated UAV path planning framework combining Rapidly-exploring Random Tree Star (RRT*) with Artificial Potential Field (APF) methodology is proposed to address limitations inherent in conventional RRT∗ implementations. The hybrid algorithm employs APF-guided random tree expansion, where systematic optimization of weight coefficients and step size parameters is implemented to enhance convergence rates and search efficiency. Through comprehensive simulation analyses, the RRT*-APF method is demonstrated to achieve a 60.31% - 64.35% reduction in average planning time compared with baseline RRT implementations, accompanied by 23.96% - 26.30% decreases in path length. When benchmarked against standard RRT*, the proposed technique exhibits 51.20% - 56.72% improvements in computational efficiency while simultaneously demonstrating superior path smoothness characteristics. These empirical results substantiate the effectiveness of the APF integration strategy in overcoming traditional RRT∗ limitations related to convergence speed and trajectory quality.