Multi-Target Collision Avoidance via Threat Number Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current collision avoidance systems are inadequate for intersections with multiple targets, as they fail to effectively detect and mitigate collision probabilities involving multiple objects simultaneously.
Innovation Solution
A computing device in the host vehicle identifies and predicts the paths of multiple targets based on speed, direction, and position, calculates threat numbers to determine collision probabilities, and actuates vehicle subsystems to slow or stop the vehicle at specific points to avoid targets with high threat numbers, thereby preventing collisions in intersections with multiple targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If current collision avoidance systems are used to detect targets in intersections, then single target detection capability is achieved, but the system fails to effectively handle multiple targets simultaneously
Solution Approach 1:
The system segments the multiple targets in the intersection by assigning unique identifiers to each detected target. The computing device processes each target independently by calculating separate threat numbers for each target based on their respective predicted paths, allowing the system to handle multiple targets simultaneously without confusion or missed detections.
2Measurement precision
If the system calculates threat numbers for multiple targets, then collision probability assessment improves, but computational complexity increases
Solution Approach 1:
The system calculates threat numbers for all detected targets, but only acts on targets whose threat numbers exceed a predefined threshold. This partial action approach allows the system to maintain high measurement precision by assessing all targets while avoiding unnecessary computational overhead and actuation for low-risk targets, thus managing computational complexity effectively.
3Reliability
If the host vehicle stops to avoid all potential targets, then collision avoidance is maximized, but traffic flow efficiency decreases
Solution Approach 1:
The system dynamically changes the threat number parameter for each target based on real-time factors including predicted path, speed, direction, and distance to the host vehicle. By continuously updating these parameters and comparing them against a threshold, the system determines the optimal stopping decision, maximizing collision avoidance while minimizing unnecessary stops that would reduce traffic flow efficiency.
Data Source
AI summary
A plurality of targets are identified. A path for each target is predicted. A threat number for each target is determined based at least in part on the predicted paths. The threat number indicates a probability of a collision between the respective target and a host vehicle. One or more vehicle subsystems in the host vehicle is actuated based on the threat numbers.