Autonomous Vehicle Path Re-Linearization in Curvilinear Coordinates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional autonomous vehicle path planning systems operate in high-dimensional Cartesian coordinate frames, making it difficult to decouple lateral and longitudinal components, which hinders efficient optimization and trajectory refinement.
Innovation Solution
Decompose path planning into lower-dimensional curvilinear coordinate frames to separate lateral and longitudinal components, allowing for convex optimization and iterative refinement of trajectories using curvilinear coordinate frames.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If path planning is performed in high-dimensional Cartesian coordinate frames, then the system can represent complex trajectories, but it becomes difficult to decouple lateral and longitudinal components for efficient optimization
Solution Approach 1:
The patent segments the path planning problem by decomposing the high-dimensional Cartesian coordinate system into lower-dimensional curvilinear coordinate frames. This segmentation separates lateral and longitudinal components into distinct optimization problems, making it easier to handle each component independently while reducing overall system complexity.
Solution Approach 2:
The patent transitions from high-dimensional Cartesian coordinates to lower-dimensional curvilinear coordinates by changing the dimensional representation. This dimensionality reduction transforms the complex multi-dimensional optimization problem into simpler lower-dimensional problems that can be solved more efficiently while maintaining trajectory accuracy.
2Productivity
If traditional Cartesian coordinate systems are used for path planning, then comprehensive trajectory representation is achieved, but computational complexity increases and optimization efficiency decreases
Solution Approach 1:
By segmenting the path planning optimization into separate lateral and longitudinal components in curvilinear coordinates, the patent reduces computational complexity. Each component can be optimized independently using appropriate convex optimization techniques, improving overall optimization efficiency compared to solving the full high-dimensional problem simultaneously.
Solution Approach 2:
The patent changes the parameterization of the trajectory by using curvilinear coordinate frames instead of Cartesian coordinates. This parameter change transforms the optimization variables into a form that enables convex optimization, significantly improving computational efficiency and productivity while maintaining the ability to represent complex trajectories.
3Productivity
If lower-dimensional curvilinear coordinate frames are used, then computational complexity is reduced and optimization is improved, but trajectory accuracy may be compromised
Solution Approach 1:
The patent uses curvilinear coordinate frames that are specifically designed to maintain trajectory accuracy while reducing dimensionality. The curvilinear coordinates are defined along the reference trajectory, allowing accurate representation of the vehicle's path and orientation in lower-dimensional space without sacrificing trajectory fidelity.
Solution Approach 2:
The patent performs preliminary trajectory generation to establish a reference path, then uses this reference to define the curvilinear coordinate system. This preliminary action enables subsequent optimization to maintain high trajectory accuracy by anchoring the lower-dimensional optimization to the pre-computed reference trajectory, ensuring precision is preserved.
Data Source
AI summary
Disclosed herein are systems, methods, and computer program products for generating a reference path for an autonomous vehicle. The methods comprising: receiving, by a computing device, a reference trajectory for the autonomous vehicle; generating, by the computing device, a first alternative trajectory for the autonomous vehicle based on an objective identified by the reference trajectory; comparing, by the computing device, the first alternative trajectory to the reference trajectory or a previously generated alternative trajectory; selecting, by the computing device, whether to generate a second alternative trajectory based on a result of said comparing; and generating, by the computing device, the second alternative trajectory for the autonomous vehicle in response to said selecting.