Vehicle Behavior Planning Gate for False Positive Hazard Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated vehicle systems with a 1oo2 redundancy architecture are prone to sudden and potentially risky reactions due to false positive and false negative detections, leading to increased risk in complex traffic environments, as neither processing path is considered more reliable or trustworthy.
Innovation Solution
A computer-implemented method for vehicle behavior planning that utilizes a first and second environmental detection using different sensors, applying safety rules for perception and creating environmental models, with an intervention measure that filters and adjusts proposed operating parameters based on state detection and safety assessments to prevent safety-critical maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a 1oo2 redundancy architecture is used with two independent processing paths, then safety is improved by detecting potential hazards, but false positive detections cause sudden and risky vehicle reactions
Solution Approach 1:
A gating mechanism is introduced as an intermediary between the two processing paths and the actuation system. This gate evaluates the credibility of hazard detections from either processing path before allowing intervention, thereby filtering out false positives while maintaining safety responses to true hazards
Solution Approach 2:
The system implements feedback by continuously monitoring the outputs of both processing paths and using this information to dynamically adjust the gating decision. The gate learns from the correlation between parallel detections and adjusts its intervention threshold accordingly, reducing false positives while maintaining safety
2Adaptability or versatility
If both processing paths are treated equally in a 1oo2 architecture, then system symmetry is maintained, but the system cannot identify more trustworthy processing paths
Solution Approach 1:
The gating mechanism introduces asymmetry by allowing one processing path to override the other based on credibility assessment. When one path detects a hazard that the other does not, the gate can selectively trust the detecting path if its detection pattern matches learned true hazard characteristics, thereby identifying more trustworthy paths without complete architectural redesign
3Reliability
If the system reacts proactively to false positive detections, then potential hazards are minimized, but unnecessary braking maneuvers increase risk in complex traffic environments
Solution Approach 1:
The gating mechanism performs preliminary anti-action by preemptively blocking false positive interventions before they reach the actuation system. It anticipates which detections are likely false positives based on pattern recognition and prevents the harmful braking action, while still allowing true hazard responses to proceed
Data Source
AI summary
A computer-implemented method for behavior planning of a vehicle, a processing device, and a vehicle control device.