A flow-field guided method of path planning for unmanned ground vehicles

摘要

This paper focuses on the path planning problem for unmanned ground vehicles in complex environments. Fluid flow is applied to the path planning method based on the natural ability of the fluid in finding its outlet. The proposed method consists of two layers: the flow-field layer and the optimization layer. The flow-field layer provides a velocity distribution which describes the fluid flowing from a starting point to a terminal point. The solution of the flow field is obtained by the method of computational fluid dynamics. The optimization layer generates a specific path and guarantees the feasibility of the path. The proposed method is verified in several scenarios, and the smoothness and the completeness of the generated path is well demonstrated.