A Guided Hybrid A*-Based Path Planning Method for Autonomous Driving

The path planning, as an important component of autonomous driving technology and a popular research area in the automotive industry, is gradually improving alongside the development and application trends of autonomous driving. This paper focuses on the path planning problem and proposes a Pruned $\mathrm{A}^{*}$-based path planning method for autonomous driving systems. The entire path planning method is divided into two parts: guidance path planning and global path planning. First, the guidance path planning stage identifies a guidance path from the vehicle’s starting point to the parking spot, efficiently generating a global path guide line by skipping numerous redundant points. Then, the global path planning stage creates the global path based on the directional guidance from the initial guidance path. Compared to conventional Hybrid $A^{*}$ algorithms, the proposed path planning algorithm requires less processing time and also demonstrates potential for practical applications