Vehicle Signal Hazard Measures from Relative Speed and Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing vehicle safety are limited by their reliance on collision data, which is retrospective, sparse, and lacks linkage to causes, making it inadequate for evaluating the safety of vehicle sensing and decision-making systems, especially in automated and human-assisted systems.
Innovation Solution
A method is developed to compute a behavioral hazard measure by combining relative speed and separation distance between a subject vehicle and traffic objects, allowing for the derivation of a safety score that reflects the riskiness or safeness of vehicle behavior nearly continuously.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If collision data is used to measure vehicle safety, then the measure is based on actual safety outcomes, but the data is retrospective, sparse, and lacks linkage to causes
Solution Approach 1:
The patent applies preliminary action by computing behavioral hazard measures from sensor data and vehicle behavior parameters before collisions occur. This allows safety assessment to be performed continuously in advance, capturing near-miss events and behavioral patterns that lead to collisions, rather than waiting for collision data to become available retrospectively.
Solution Approach 2:
The patent introduces behavioral hazard measures as an intermediary metric that bridges the gap between raw sensor data and collision outcomes. This intermediary measure combines multiple parameters (relative speed, separation distance, time-to-collision) to create a continuous safety indicator that links vehicle behavior to safety outcomes without requiring actual collisions to occur.
2Productivity
If time-to-collision is used as a safety measure, then the measure is computable, but it is dependent on road conditions and vehicle speed, making it not independent
Solution Approach 1:
The patent applies parameter changes by transforming the time-to-collision parameter into a behavioral hazard measure that normalizes for vehicle speed and road conditions. The measure uses dimensionless parameters and scaling factors to make the safety assessment independent of specific operating conditions, allowing comparison across different vehicles, speeds, and road surfaces.
3Reliability
If disengagements per mile are used to assess automated system safety, then the measure indicates system performance, but it is subjective and influenced by operational policy
Solution Approach 1:
The patent applies self-service by enabling the vehicle's sensor system and decision-making system to automatically generate behavioral hazard measures without human intervention or subjective judgment. The system continuously computes safety metrics from its own sensor data and vehicle control signals, eliminating the need for human operators to subjectively determine when disengagements occur.
4Ease of operation
If collision frequency is used to measure safety, then the measure is simple to obtain, but it occurs relatively infrequently and cannot provide nearly continuous measurement
Solution Approach 1:
The patent applies continuity of useful action by computing behavioral hazard measures continuously from sensor data at the same rate as the sensors operate (e.g., 10 Hz or higher). This continuous computation provides a nearly continuous safety measurement that captures all near-miss events and behavioral patterns, rather than relying on infrequent collision occurrences.
Data Source
AI summary
A non-transitory computer readable storage medium has instructions executed by a processor to obtain the relative speed between a first traffic object and a second traffic object. The separation distance between the first traffic object and the second traffic object is received. The relative speed and the separation distance are combined to form a quantitative measure of hazard encountered by the first traffic object. The obtain, receive and combine operations are repeated to form cumulative measures of hazard associated with the first traffic object. The cumulative measures of hazard are analyzed to derive a first traffic object safety score for the first traffic object.