Abstract
Autonomous parking trajectory planning in unstructured environments with irregular obstacles must address the challenges posed by non-convex obstacle constraints. Due to the coupling between problem complexity and the number of surrounding obstacles, existing methods often suffer from increased computation time and failure rates in dense environments. To tackle this issue, this paper proposes an efficient parking trajectory planner with fast obstacle retrieval capability. The proposed planner follows a classical two-stage architecture consisting of front-end trajectory generation and back-end trajectory optimization. In the first stage, a multi-resolution sampling-based trajectory generation method is introduced. By using multi-resolution sampling strategy and a KD-Tree-based collision detection algorithm, the method achieves high-quality initial trajectory while maintaining computational efficiency. In the second stage, we present a novel iterative trajectory optimization method based on neighbor obstacle indexing, which restricts the scale of obstacle constraints during each optimization iteration, which improves computational efficiency of trajectory optimization. Extensive comparative studies and real-car experiments are conducted to validate the advantages of the proposed method, particularly in terms of computation time and robustness in complex, cluttered environments.
Funding Information
  • State Key Program of National Natural Science Foundation of China (52332010)

This publication has 44 references indexed in Scilit: