Fast Trajectory Path Planning Inspired by Binary Searching Algorithm

A safe trajectory planning is a challenging problem due to the variety and complexity of driving environment. The sampling-based method of path-velocity decomposition method has the advantages of being intuitive and convenient, but it has a drawback that its real-time performance significantly declines as obstacle density increases. In this paper, we introduce a fast trajectory path planning method to address the issue. A sampling point selection approach based on the same-side method is proposed. This helps the planner to decrease the generation of collision paths. To increase the speed of collision checking, a fast collision checking method inspired by binary searching is designed. The effectiveness of the algorithm is verified by simulation experiments.