Abstract
This paper introduces an autonomous parking trajectory planning method in an unstructured environment with narrow passages. The proposed hierarchical trajectory planner consists of a graph search layer and a numerical optimal control layer. The contribution mainly lies in the graph search layer, wherein a multistage hybrid A* algorithm is proposed to handle narrow passages formed by obstacles in the cluttered environment. In the multistage hybrid A* algorithm, a 2-dim A* search is conducted to find a global route that connects the starting and goal points. Along the derived global route, subtle segments that traverse narrow passages are extracted. Thereafter, the hybrid A* algorithm is used to plan kinematically feasible subpaths that connect the boundary points of each subtle segment. The hybrid A* algorithm is also used to find linking paths that connect adjacent subpaths. Combining all the subpaths and linking paths in a sequence yields a coarse path, which is converted into a coarse trajectory by attaching a time-optimal velocity profile to it. The coarse trajectory is fed into the numerical optimization layer as the initial guess. Simulation results indicate that the hierarchical trajectory planner runs much faster than prevalent ones in dealing with unstructured environments with narrow passages.
Highlights
Autonomous driving techniques have been widely developed during recent years due to the potential to relieve jammed traffic, reduce air pollution and prevent traffic accidents caused by human errors [1]
We propose a trajectory planner that adopts the hierarchical planning framework, wherein the samplingbased layer is developed based on the conventional hybrid A* algorithm while the optimization-based layer is conducted with an improved safe travel corridor (STC)-based optimization approach
The benchmark cases presented in this paper demonstrates that the combination of multi-stage hybrid A* and improved STC-based optimization provides a huge advantage on cost efficiency over conventional optimization-based counterparts and has the potential to be used in practical real-time autonomous planning
Summary
Autonomous driving techniques have been widely developed during recent years due to the potential to relieve jammed traffic, reduce air pollution and prevent traffic accidents caused by human errors [1]. A samplingbased method, in most cases, runs fast to derive a resolution-feasible path/trajectory It may fail when the environment is maze-like or contains narrow passages wherein the incremental sample and search would get stuck there. A sampling-based method provides a resolutionfeasible coarse path/trajectory, which serves as the initial guess in solving an optimization problem via a local optimizer Such a hierarchical method still runs not fast because the concerned problem contains large-scale non-convex and non-differentiable collision-avoidance constraints [14]. The benchmark cases presented in this paper demonstrates that the combination of multi-stage hybrid A* and improved STC-based optimization provides a huge advantage on cost efficiency over conventional optimization-based counterparts and has the potential to be used in practical real-time autonomous planning
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
