Vehicle Area Skeleton and Circle Decomposition for Collision Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for geometric representation of vehicle areas for collision detection result in large overflow errors, leading to incorrect occupancy map regions, which is disadvantageous in applications like parking assistants.
Innovation Solution
A method involving medial axis transformation to generate a vehicle area skeleton, followed by circle decomposition with adaptive radius adjustment to minimize area exceedance, ensuring accurate collision detection by covering the vehicle area with a minimal number of circles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed number of circles with fixed radii are used to cover the vehicle area, then the coverage is simple and fast, but the area exceedance is large leading to incorrect collision detection
Solution Approach 1:
The patent applies dynamics by making the circle radii adaptive rather than fixed. The decomposition dynamically adjusts circle radii based on the vehicle's geometric skeleton, allowing the coverage to adapt to the actual vehicle shape and minimize area exceedance while maintaining computational efficiency.
Solution Approach 2:
The patent changes the parameter of circle radii from fixed values to adaptive values determined by the vehicle's medial axis transformation. This parameter change allows the decomposition to optimize coverage accuracy by matching the vehicle's actual geometry rather than using predetermined fixed radii.
2Productivity
If the vehicle area is decomposed into circles to enable fast collision detection, then the computation is simplified, but the overflow error increases causing false occupancy detection
Solution Approach 1:
The patent segments the vehicle area into multiple circles along the medial axis, creating a decomposition that follows the vehicle's actual shape. This segmentation maintains computational simplicity for fast collision detection while improving accuracy by reducing the overflow error through shape-adaptive circle placement.
3Ease of manufacture
If a bounding box is used to enclose the vehicle area, then the geometric representation is simple, but the area exceedance is large causing unnecessary collision warnings
Solution Approach 1:
The patent replaces the rectangular bounding box with a curved medial axis transformation that follows the vehicle's actual contours. This curvature-based approach maintains geometric simplicity while dramatically improving coverage accuracy by adapting to the vehicle's shape rather than forcing it into a rectangular envelope.
Data Source
AI summary
A method for the geometric representation of a vehicle area (1) of a vehicle for the purpose of collision detection, wherein the vehicle area (1) has a boundary (2), comprising the method steps of performing a medial axis transformation of the vehicle area (1) to generate a vehicle area skeleton (4) and performing a point classification of points of the vehicle area skeleton (4) to determine front corner region points (5, 6) and rear corner region points (7, 8), and a front wheelbase point (9) and a rear wheelbase point (10), and also performing a circle decomposition of the vehicle area (1), wherein each circle of the circle decomposition has a maximum area exceedance value (17).