In this paper, we introduce an algorithm for generating collision-free two-lane paths for unmanned vehicles used at mining sites by using quartic (degree 4) B-spline curves. Given the boundary geometry of the haul road area and the positions and orientations of the two-dimensional vehicle at the start and goal points, the algorithm automatically generates a collision-free two-lane path that satisfies the minimum turning radius constraint. Moreover, the resulting path shares the same third derivative at knots (joints), i.e., $C^3$ continuity, which guarantees a continuous rate of change of the curvature along the entire path. Examples are provided to demonstrate the effectiveness of the proposed algorithm.
Automatic Two-Lane Path Generation for Autonomous Vehicles Using Quartic B-Spline Curves
IEEE Transactions on Intelligent Vehicles ; 3 , 4 ; 547-558
2018-12-01
6428873 byte
Article (Journal)
Electronic Resource
English
Efficent Lane Change Path Planning based on Quintic Spline for Autonomous Vehicles
British Library Conference Proceedings | 2020
|Path optimization based on constrained smoothing spline for autonomous driving vehicles
European Patent Office | 2020
|