Path planning for automatic parking based on improved Hybrid A* algorithm

In this paper, an automatic parking planning algorithm based on hybrid A* improvement is proposed for the unstructured environment of parking lots. In order to obtain an optimal trajectory under the conditions of safety and comfort, the algorithm makes the following adjustments: (1) Based on the kinematic and dynamical parameters of the experimental vehicle, the expansion search of the nodes is performed using clothoids to ensure the continuity of curvature. (2) The heuristic term of hybrid A* is improved by adding a penalty term of obstacle distance to the Reeds-shepp (RS) curve as the heuristic term, which improves the problem that the RS curve is too close to the obstacle. The effectiveness of the algorithm is evaluated based on simulation and real-world experimental results, and it is demonstrated that the algorithm can be widely used in automatic parking scenarios.