APTEN-Planner: Autonomous Parking of Semi-Trailer Train in Extremely Narrow Environments

Parking semi-trailer train in extremely narrow environments pose challenges due to high nonholonomic constraints, unstable reversing dynamics, and non-convex obstacle avoidance constraints. This paper presents the APTEN (Autonomous Parking of semi-Trailer train in Extremely Narrow environments) with a three-layer framework to address these challenges. In the first layer, we employ a linearized gain scheduling method to create a stable Cl-RRT planner tailored for simplifying unstable reverse dynamics. This planner is adept at promptly warm starting the following homotopy problems. In the second layer, we introduce a novel “dynamics–full dimensional obstacle avoidance” progressive constraint approach. Modifying the constraints of nonlinear programming in separate homotopy problems not only protects the solver from falling into unfeasible local optima but also significantly enhances computational efficiency. In the third layer, a differentiable approach based on convex set separation is employed to establish full-dimensional obstacle avoidance constraints for semi-trailer train. Leveraging the warm start solutions obtained from the previous two layers, the algorithm identifies the optimal solution that strictly adheres to the obstacle avoidance constraints in an extremely narrow environment. The simulation results demonstrate that APTEN excels in parking motion planning within extremely narrow environments, exhibiting the shortest solution time, the highest trajectory quality, and exceptional adaptability to diverse working conditions.