Vehicle Relevance Polygon Filtering for Low-Latency Collision Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional vehicle collision avoidance systems face latency issues due to high computing power requirements for calculating the speed and direction of travel for detected objects, potentially degrading safe vehicle operation.
Innovation Solution
A vehicle computing system generates a relevance polygon based on speed to determine relevant objects, withholding data from control planning for irrelevant objects, thus reducing processing load and enhancing safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system calculates the speed and direction of travel for each detected object, then collision avoidance accuracy is improved, but computing time increases causing latency
Solution Approach 1:
The system segments the environment into multiple regions (first region, second region, third region) with different processing priorities. Objects in different regions are processed differently - full processing for critical regions, filtered processing for less critical regions, reducing overall computational load while maintaining safety for high-priority areas
Solution Approach 2:
Different processing quality is applied to different spatial locations. The system applies high-accuracy speed and direction calculation only to objects in critical regions (first region), while using simpler filtering methods for objects in less critical regions (second and third regions), optimizing the balance between accuracy and processing speed
2Reliability
If the system processes data for all detected objects, then comprehensive safety monitoring is achieved, but processing load increases reducing operational efficiency
Solution Approach 1:
The system extracts and processes only the most critical object data for full analysis, while applying simplified filtering to other objects. By taking out only the essential processing requirements and applying them selectively to objects in different regions, the system maintains comprehensive safety monitoring while significantly improving processing efficiency
Solution Approach 2:
The system applies partial processing action to objects based on their regional classification. Instead of full processing for all objects, it applies appropriate levels of processing - full action for critical objects in the first region, partial action for objects in the second region, and minimal filtering for objects in the third region, optimizing resource allocation
Data Source
AI summary
A vehicle computing system may implement techniques to improve collision prediction and avoidance between a vehicle and objects in an environment. A vehicle computing system of the vehicle generates a relevance polygon associated with a planned path of the vehicle based at least in part on a speed associated with the vehicle traveling through the environment. The vehicle computing system identifies objects in the environment and determines whether the objects are located within a boundary of the relevance polygon. Based on a determination that an object is within the boundary, the vehicle computing system determines that the object is relevant to the vehicle and includes data associated therewith in vehicle control planning considerations.