Autonomous Vehicle Speed Planning via Continuous Constraint Function
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining optimal speeds due to varying environmental conditions, such as speed limits, path curvatures, and obstacles, which existing technologies struggle to integrate effectively into a single, continuous, and differentiable speed constraint function.
Innovation Solution
A method for autonomous vehicles to generate a single, continuous, and differentiable speed constraint function by discretizing separate functions representing speed limits, path curvatures, and obstacles, forming polynomial functions for each segment, and optimizing these to determine a set of speeds efficiently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If multiple separate functions representing speed limits, path curvatures, and obstacles are integrated into a single speed constraint function, then the speed determination becomes unified and efficient, but the mathematical complexity increases requiring the function to be continuous and differentiable
Solution Approach 1:
The patent merges multiple separate constraint functions (speed limits, path curvatures, obstacles) into a single unified speed constraint function. This consolidation allows the autonomous vehicle to determine optimal speeds more efficiently by evaluating one function rather than multiple separate functions, while still accounting for all environmental constraints.
Solution Approach 2:
The patent transforms the mathematical properties of the speed constraint function to ensure it is continuous and differentiable. By changing the parameter requirements from simple separate functions to a unified continuous differentiable function, the system enables efficient optimization while maintaining mathematical tractability for speed determination.
2Loss of time
If the speed constraint function is made continuous and differentiable, then optimization becomes more efficient, but the integration of discrete environmental constraints becomes more difficult
Solution Approach 1:
The patent changes the mathematical parameters of the constraint functions by discretizing environmental data (speed limits, curvatures, obstacles) and then constructing a continuous differentiable function from these discrete points. This allows efficient optimization while accurately representing discrete environmental constraints.
Solution Approach 2:
The patent uses polynomial interpolation as an intermediary method to bridge discrete environmental constraints and the requirement for a continuous differentiable function. The polynomial functions serve as a mathematical mediator that transforms discrete constraint data into a smooth, differentiable speed constraint function suitable for optimization.
3Manufacturing precision
If polynomial functions are used for each segment of the path, then the speed determination becomes more accurate, but the computational complexity increases
Solution Approach 1:
The patent segments the path into discrete sections and applies polynomial functions to each segment individually. This segmentation allows accurate speed determination for each specific path section while keeping the computational complexity manageable by processing segments separately rather than solving one large complex problem.
Solution Approach 2:
The patent changes the polynomial degree parameters to balance accuracy and computational complexity. By selecting appropriate polynomial orders for each segment, the system achieves sufficient speed determination accuracy without excessive computational burden.
Data Source
AI summary
In one embodiment, a method is provided. The method includes determining a first reference line representing a path through an environment for an autonomous driving vehicle. The method also includes determining a speed constraint function based on a set of speed limits associated with the environment, a set of curvatures of the path, and a set of obstacles in the environment, wherein the speed constraint function comprises a continuous function. The method further includes determining a set of speeds for the path through the environment based on the speed constraint function. The method further includes controlling the autonomous driving vehicle based on the path and the set of speeds.