Road-Centered Coordinate Transformation for Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Transforming object coordinates from a Cartesian coordinate system to a road-centered coordinate system in autonomous vehicles becomes computationally expensive at scale, necessitating a more efficient method for navigation.
Innovation Solution
A method and system that determine a source point's coordinates in a road-based reference frame by sampling waypoints, using linear and circular arc approximations, and interpolating using Frenet-Serret formulas, allowing for efficient transformation and operation of autonomous vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If coordinate transformation from Cartesian to road-centered system is performed using traditional methods, then accuracy of navigation is improved, but computational complexity increases
Solution Approach 1:
The coordinate transformation process is divided into multiple discrete steps: (1) identifying candidate road segments containing the source point, (2) computing projection of the source point onto each candidate segment, (3) selecting the optimal segment based on projection validity, and (4) calculating final Frenet coordinates. This segmentation allows the system to handle complex transformations through manageable, computationally efficient stages.
Solution Approach 2:
The method computes projections onto multiple candidate road segments beyond what a single exact transformation would require, then selects the valid projection. This partial action approach (computing multiple potential solutions) ensures accuracy by considering all possible segment assignments, while the selection step prevents excessive computation by eliminating invalid candidates early.
2Quantity of substance
If coordinate transformation is applied at scale for multiple objects, then completeness of environmental mapping is improved, but processing time increases
Solution Approach 1:
The system pre-identifies candidate road segments that could contain source points before performing actual coordinate transformations. By pre-computing which segments are relevant to which objects, the system avoids unnecessary projection calculations for objects that clearly don't lie on certain segments, significantly reducing processing time when transforming coordinates for multiple objects in the environment.
Solution Approach 2:
The transformation method adapts its computational approach based on the local geometric relationship between each source point and candidate road segments. For each object, the system identifies only the locally relevant candidate segments rather than evaluating all segments globally, optimizing processing time based on the specific spatial context of each object being transformed.
Data Source
AI summary
A system and method operate an autonomous vehicle. A sensor senses a road and an object. A processor determines, in a Cartesian reference frame, a representation of the road and a source point representative of the object, samples a first waypoint and a second waypoint from the representation of the road, determines a linear projection of the source point to a line connecting the first waypoint and the second waypoint, determines a first estimate of a longitudinal component of the source point in a road-based reference frame based on the linear projection, the first estimate being on a curve representing the road between the first waypoint and the second waypoint, determines a second estimate of the longitudinal component from the first estimate, determines a coordinate of the source point in the road-based reference frame from the second estimate and operates the vehicle with respect to the object using the coordinate.