Grid-Based Multi-Road-Course Estimation Using Motion Planning

Knowing the course of the road, together with the corresponding road boundaries is an essential component of many advanced driver-assistance systems and of autonomous vehicles. This work presents an indirect grid-based approach for road course estimation. Due to the grid representation, it is independent of specific features or particular sensors and is able to handle continuous as well as sparse road boundaries of arbitrary shape. Furthermore, the number of road courses in the scene is determined to detect road junctions and forks in the road, and the boundaries of each road course are individually estimated. The approach is based on local path planning and path clustering to find the principal moving directions through the environment. They separate the boundaries and are used for their extraction. The set of local paths and principal moving directions is reduced with approximate knowledge of the road velocity paired with system constraints, and validation and tracking assure the required robustness. Experimental results from autonomous navigation of a vehicle through an unmapped road construction site as well as quantitative evaluations demonstrate the performance of the method.