ADAS Usage Detection from Telematics for Driver Risk Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge is determining whether advanced driver assistance systems (ADAS) features are operational in a vehicle during a trip, as this information is not typically exposed to mobile devices or telematics applications, which affects driving risk assessment by insurance providers.
Innovation Solution
A computer-implemented method using telematics information processed by a hardware processor to identify vehicle movement information, determine the probability of ADAS feature operation, and calculate a risk score based on this probability, employing machine learning, neural networks, and benchmark comparisons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If telematics applications access vehicle data to assess driving risk, then risk assessment accuracy is improved, but system complexity and data access restrictions worsen
Solution Approach 1:
The patent introduces an intermediary system that sits between the telematics application and the vehicle's ADAS systems. This intermediary captures and processes ADAS operational data, then provides processed information to the telematics application. This mediator layer enables risk assessment without requiring direct access to proprietary ADAS systems, thus improving measurement precision while managing device complexity through controlled data interfaces.
2Measurement precision
If ADAS operational data is made accessible to telematics systems, then driving risk assessment is improved, but data security and system protection worsen
Solution Approach 1:
The patent extracts only the necessary ADAS operational parameters needed for risk assessment rather than providing full access to the ADAS system. By taking out and providing only specific data elements (such as operational status, intervention events, and performance metrics), the system improves driving risk assessment while minimizing data security risks through selective data exposure.
3Measurement precision
If machine learning models analyze vehicle movement information to determine ADAS operation, then detection accuracy is improved, but processing time and computational resources worsen
Solution Approach 1:
The patent implements preliminary action by pre-processing vehicle movement information and organizing it into relevant feature sets before applying machine learning models. The system pre-identifies key parameters such as acceleration patterns, speed variations, and positional changes that indicate ADAS operation. This preliminary organization reduces the computational burden during actual analysis, improving detection accuracy while reducing processing time through efficient data preparation.
Data Source
AI summary
A system can include a mobile device that includes one or more sensors for sensing information during a trip in a vehicle. A hardware processor can execute operations including receiving telematics information produced by one or more sensors during a trip in a vehicle; processing, by a hardware processor, the received telematics information to identify vehicle movement information for the vehicle during the trip; determining, by the hardware processor, a probability that an advanced driver assistance system (ADAS) feature of the vehicle was operational during the trip based, at least in part, on the vehicle movement information for the vehicle during the trip; and determining, by the hardware processor, a risk score for the vehicle or a driver of the vehicle based, at least in part, on the probability that the ADAS feature was operational.