A Traffic Knowledge Aided Vehicle Motion Planning Engine Based on Space Exploration Guided Heuristic Search

Abstract

A real-time vehicle motion planning engine is presented in this paper, with the focus on exploiting the prior and online traffic knowledge, e.g., predefined roadmap, prior environment information, behaviour-based motion primitives, within the space exploration guided heuristic search (SEHS) framework. The SEHS algorithm plans a kinodynamic vehicle motion in two steps: a geometric investigation of the free space, followed by a grid-free heuristic search employing primitive motions. These two procedures are generic and possible to take advantage of traffic knowledge. In this paper, the space exploration is supported by a roadmap and the heuristic search benefits from the behaviour-based primitives. Based on this idea, a light weighted motion planning engine is built, with the purpose to handle the traffic knowledge and the planning time in real-time motion planning. The experiments demonstrate that this SEHS motion planning engine is flexible and scalable for practical traffic scenarios with better results than the baseline SEHS motion planner regarding the provided traffic knowledge.