Distance Calculation for Curved Road Segments in Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face difficulties in determining the closest distance between a point and a road segment, especially when the road segment includes curves, as existing methods are slow, prone to errors, and inaccurate due to global sampling, derivative-based optimization, and approximation techniques.
Innovation Solution
The technique involves dividing the xy-plane into regions associated with a reference line, using lines normal to the endpoints and a perpendicular bisector to determine the closest point, and applying rules and equations to calculate the minimum distance between points and the reference line, employing algorithms like the Brent Minimization Algorithm.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If global sampling or derivative-based optimization methods are used to determine distance to curved road segments, then measurement coverage is improved, but computational speed deteriorates and accuracy is reduced
Solution Approach 1:
The patent segments the space around the curved road segment into multiple regions (first region, second region, third region, fourth region) based on perpendicular lines at endpoints and a perpendicular bisector. Each region has predetermined rules for determining the closest point, avoiding global optimization while ensuring accurate distance measurement for objects in any region.
2Productivity
If approximation techniques are used to calculate distance to curved road segments, then computational speed is improved, but measurement precision deteriorates
Solution Approach 1:
The patent performs preliminary actions by pre-defining regions and their associated rules before actual distance calculation. The perpendicular lines at endpoints and the perpendicular bisector are established in advance, creating a structured framework that enables rapid determination of the closest point without requiring approximation during runtime.
3Measurement precision
If complex optimization algorithms are used to find the closest point on curved road segments, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent changes the approach from continuous optimization parameters to discrete regional parameters. By defining four distinct regions with specific boundary conditions (perpendicular lines at endpoints, perpendicular bisector), the system transforms a complex continuous optimization problem into a simpler discrete classification problem where the closest point can be determined using predetermined rules for each region.
Data Source
AI summary
Techniques and methods for determining a distance between a point within an environment and a reference line are discussed herein. For instance, a vehicle may be navigating. While navigating, the vehicle may receive a reference line that represents a road segment and determine various regions relative to the reference line. Additionally, the vehicle may generate sensor data representing the environment and identify an object using the sensor data. The vehicle may then determine that a location of the object corresponds to a region from the regions. Based on the region, the vehicle may determine a rule for identifying the distance between the vehicle and the reference line. The vehicle may then determine the distance using the rule, the location of the object, and the reference line. Additionally, the vehicle may determine an action for the vehicle to perform that is based on the distance.