Constrained Smoothing Spline Path Optimization for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in navigating smoothly and avoiding obstacles due to the lack of effective path and speed optimization techniques, leading to unstable vehicle control and potential collisions.
Innovation Solution
The implementation of a constrained smoothing spline method using quadratic programming to generate optimal reference lines and trajectories, which considers road boundaries, obstacles, and traffic information, ensuring smooth and safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Stability of the object's composition
If traditional path planning methods are used without smoothing optimization, then the path can be generated quickly, but the vehicle control becomes unstable and the reference line is not smooth
Solution Approach 1:
The patent applies smoothing spline optimization to transform the reference line from a discrete set of points into a continuous smooth curve by optimizing parameters such as curvature and curvature rate. This ensures that the path maintains stability and smoothness for autonomous vehicle control while navigating through defined waypoints.
2Stability of the object's composition
If a smooth reference line is generated using smoothing spline, then vehicle control stability improves, but the computational complexity and processing time increase
Solution Approach 1:
The patent performs smoothing spline optimization on the reference line in advance before the vehicle begins navigation. By pre-computing the smooth path that satisfies curvature constraints, the system eliminates real-time computational delays during actual vehicle operation, ensuring both smoothness and timely response.
3Reliability
If the path trajectory does not consider obstacles and road boundaries, then the path planning is simpler, but the vehicle may collide with obstacles or leave the road
Solution Approach 1:
The patent applies different constraint conditions to different segments of the path trajectory. Obstacle avoidance constraints are applied in regions where obstacles are detected, road boundary constraints are applied near road edges, and smoother transitions are applied in open areas. This localized constraint application ensures safety while maintaining computational efficiency.
4Adaptability or versatility
If speed trajectory optimization is not performed, then the control system is simpler, but the vehicle cannot adapt to traffic information and obstacles effectively
Solution Approach 1:
The patent implements speed trajectory optimization that incorporates feedback from obstacle detection and traffic information. The system continuously adjusts the speed profile based on the smoothed path and real-time environmental perception, enabling the vehicle to adapt its speed to traffic conditions and obstacle locations while maintaining smooth and safe operation.
Data Source
AI summary
According to some embodiments, a system segments a first path trajectory selected from an initial location of the ADV into a number of path segments, where each path segment is represented by a polynomial function. The system selects an objective function in view of the polynomial functions of the path segments for smoothing connections between the path segments. The system defines a set of constraints to the polynomial functions based on adjacent path segments in view of at least a road boundary and an obstacle perceived by the ADV. The system performs a quadratic programming (QP) optimization on the objective function in view of the added constraints, such that an output of the objective function reaches a minimum. The system generates a second path trajectory representing a path trajectory with an optimized objective function based on the QP optimization to control the ADV autonomously.