一种基于分段贝塞尔曲线的自动驾驶车辆轨迹优化方法
By constructing a piecewise spatiotemporal three-dimensional convex space using piecewise Bézier curves and transforming it into a quasi-quadratic programming problem, the safety and feasibility issues of existing trajectory planning algorithms under complex configuration spatiotemporal obstacles and dynamic constraints are solved, achieving more efficient trajectory optimization.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
- Filing Date
- 2023-09-18
- Publication Date
- 2026-07-17
AI Technical Summary
Existing polynomial trajectory planning algorithms cannot effectively guarantee safety and feasibility under complex configurations, spatiotemporal obstacles, and dynamic constraints, and have high computational complexity.
Piecewise Bézier curves are used for trajectory optimization. By leveraging the convex hull and convex graph properties of Bézier curves, a piecewise spatiotemporal three-dimensional convex space is constructed. The trajectory optimization problem is then transformed into a quasi-quadratic programming problem for solution. The convex graph properties of Bézier curves are used to constrain and control the trajectory with higher-order quantities.
It improves the robustness and security of trajectory optimization, reduces computational complexity, generates trajectories that better meet actual needs, and enhances the computational efficiency and real-time performance of the algorithm.
Smart Images
Figure CN117093004B_ABST