一种自动驾驶车辆在规划轨迹中的相对定位方法
By using cubic spline interpolation and zigzag projection to determine the nearest temporal and spatial reference points for autonomous vehicles, the problem of discontinuity and singularity in relative positioning in existing methods is solved, resulting in smoother vehicle motion control and improved overall vehicle response quality for autonomous driving.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 上海友道智途科技有限公司
- Filing Date
- 2022-12-16
- Publication Date
- 2026-07-17
AI Technical Summary
In existing autonomous driving trajectory planning relative positioning methods, the solution processes for the nearest time reference point and the nearest space reference point are independent of each other, which may lead to jumps and singularities. Furthermore, the connection of straight segments cannot reflect curvature information, resulting in unsmooth vehicle movement and affecting comfort.
A piecewise polynomial function of discrete points of spatiotemporal trajectory is constructed using a cubic spline interpolation algorithm. Combined with the bisection indexing method and the polygonal projection method, the nearest reference point in time and space is determined. Singularities and discontinuities are avoided by using cubic spline curves and the polygonal projection method, providing smooth relative positioning input.
It improves the motion response quality of autonomous vehicles in the planned trajectory, reduces vehicle motion vibration and unevenness, and enhances overall vehicle comfort and control precision.
Smart Images
Figure CN115900747B_ABST