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

Abstract

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 estimated individually. 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.

Review of Decision-Making and Planning Approaches in Automated Driving

“…The A* graph-search method can also be applied to local planning. It was combined with RRT for the navigation of an automated vehicle through an unmapped road scenario in [38].…”

A Two-Stage Real-Time Path Planning: Application to the Overtaking Manuever

“…Fu et al [22] combined the circle navigation method with cubic splines to analyze the risk of collision and generate collision-free trajectories. A road course estimation on a grid-based representation of the environment is proposed in [23], this approach benefits from offline maps to generate collision-free paths combining A* and RRT graph-based algorithms. Hundelshaussen et al presented an ego-centered occupancy grid-based method for drivability [24], combining it with the tentacles that are used for evaluating it and to perform the motion, integrating the method on the finalist Team AnnieWAY's vehicle of the DARPA Urban Challenge [25].…”

“…Authors in the literature review target dynamic environments as specific scenarios: emergency scenarios in [11], overtaking as a singular scenario in [12,13] from a dynamics point of view, in [14][15] as a predictive point of view with other obstacles, overtaking as a geometric problem in [16][17][18][19][20][21][22][23][24][25], focusing on the occupancy of the space in [27], from a vehicle-modeling point of view [17,28] or from the use of data-driven data [29][30][31][32][33], among others.…”

Dynamic path planning based on improved boundary value problem for unmanned aerial vehicle

“…On the other hand, the data structure of terrain model has a great influence on algorithm. Besides rectangular grid, other modeling methods of terrain mainly include grid based on sensors [16], triangle grid [17], grid based on multiresolution [18] and so on. UAV mobility is affected by velocity and turning radius and it is an intense constraint on the feasibility of path.…”