Vehicle Collision Scoring Using High-Rate Acceleration Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional collision detection systems rely on accelerometer data alone, which is unreliable due to false positives and negatives, and fail to accurately characterize collisions by not considering additional telemetry data or the context around the collision event.
Innovation Solution
A method using a telematics monitor to capture high-rate acceleration data and combine it with GPS and speed data to compute an accident score, filtering out noise and harsh braking events, and triggering responses based on the score indicating a potential collision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional collision detection systems use only accelerometer data, then the system complexity is low, but the reliability of collision detection deteriorates due to false positives and negatives
Solution Approach 1:
The patent combines multiple data sources including high-rate accelerometer data, GPS data, and speed data into a unified collision scoring system. The collision detection facility integrates these diverse data streams to compute a comprehensive accident score, merging previously separate detection mechanisms into a single coordinated system that improves reliability while managing complexity through integration.
Solution Approach 2:
The telematics monitor is designed to perform multiple functions: capturing acceleration data, acquiring GPS data, determining speed data, and providing communication capabilities. This multi-functional device consolidates what would otherwise require separate systems, improving collision detection reliability while avoiding the complexity of multiple independent devices.
2Measurement precision
If the system captures high-rate acceleration data at 80-120 Hz, then the measurement precision of collision events improves, but the quantity of data to be processed increases
Solution Approach 1:
The system extracts only the essential features from high-rate acceleration data that are relevant to collision detection. The collision detection facility identifies specific collision indicators and characteristics from the continuous high-rate data stream, separating the useful collision information from the redundant data, thereby maintaining measurement precision while reducing the effective data volume that requires detailed processing.
Solution Approach 2:
The system performs preliminary processing and filtering of high-rate acceleration data before full analysis. By pre-identifying potential collision events and extracting key features in advance, the system prepares the data for more efficient subsequent processing, reducing the computational burden while preserving the precision needed for accurate collision characterization.
3Measurement precision
If the system computes multiple contexts (acceleration, pullover, speed, road) and an accident score, then the accuracy of collision characterization improves, but the computational complexity increases
Solution Approach 1:
The collision detection system segments the complex task of collision characterization into distinct contextual components: acceleration context, pullover context, speed context, and road context. Each context is computed separately based on specific data types, and then integrated into a final accident score. This segmentation allows the system to manage computational complexity by breaking down the overall task into smaller, more manageable sub-tasks while maintaining comprehensive collision characterization accuracy.
4Reliability
If the system filters out noise events and harsh braking events, then the false positive rate decreases, but the complexity of event classification increases
Solution Approach 1:
The system applies different classification criteria and filtering thresholds tailored to specific event types. Noise events, harsh braking events, and actual collisions each have distinct local characteristics that are evaluated using specialized detection rules. This localized approach to event classification allows the system to accurately distinguish between different types of events, reducing false positives while managing complexity through targeted rather than universal classification logic.
Data Source
AI summary
Described herein are various techniques, including a system that uses high-rate acceleration data for computing an accident score indicative of a potential collision and triggering an action in response to determining that the accident score indicates a potential collision. The system is configured to filter out undesired high-rate acceleration trigger events such as noise and harsh braking events prior to determining the accident score. The accident score is based on contexts or scores computed from high-rate acceleration data, speed, and GPS data captured by a telematics monitor deployed in a vehicle.