Edge Driver Data Tracking With In-Vehicle Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fleet management systems rely heavily on manual processing and cloud-based out-of-band communications to associate drivers with vehicles, leading to inefficiencies and increased costs due to data transmission and storage requirements, while failing to accurately identify drivers in multi-user scenarios.
Innovation Solution
Implementing an in-vehicle sensor system that captures driver images and biometric data, coupled with a telematics unit, to securely store and retrieve driver data on the edge, minimizing cloud reliance and ensuring accurate driver identification through facial recognition and secure data access protocols.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cloud-based out-of-band communication is used to associate drivers with vehicles, then driver identification can be achieved, but data transmission costs and cloud storage requirements increase
Solution Approach 1:
The patent extracts the driver identification function from cloud-based out-of-band communication and implements it locally using in-vehicle sensors and edge computing. The system captures images with in-vehicle cameras, processes them locally to identify drivers, and stores identification data in vehicle memory, eliminating the need for continuous cloud communication for this function.
Solution Approach 2:
The patent transitions from a single cloud-dependent identification dimension to a multi-dimensional approach combining in-vehicle sensor data, edge processing, and selective cloud synchronization. This allows local operation for immediate identification while maintaining cloud connectivity only when necessary for data aggregation.
2Device complexity
If manual processing is used to update driver-vehicle associations, then system complexity is reduced, but productivity and efficiency decrease
Solution Approach 1:
The system implements self-service automation where in-vehicle sensors automatically capture driver images, edge computing processors automatically identify drivers using captured images, and the system automatically updates driver-vehicle associations in memory without requiring manual intervention for each update.
Solution Approach 2:
The patent replaces manual mechanical processing with automated electronic systems. Manual paperwork and physical updates are substituted with sensor-based image capture, computational photo processing, and electronic database updates, dramatically improving processing speed and accuracy.
3Loss of information
If driver data is stored in the cloud for analysis, then data analysis capability is improved, but data transmission requirements and latency increase
Solution Approach 1:
The patent segments data processing into two parts: immediate driver identification and association updates are processed locally at the vehicle edge, while aggregated fleet-wide analytics are performed in the cloud. This segmentation allows time-sensitive operations to occur locally without latency while still leveraging cloud computing for broader analysis.
Solution Approach 2:
The vehicle's edge computing system acts as an intermediary between in-vehicle sensors and the cloud. It pre-processes data locally, filtering and preparing information before transmission, reducing the volume of data sent to the cloud and enabling faster response times for critical functions.
Data Source
AI summary
Driver insurance and risk management scores are calculated per driver based on vehicle and driver behavior data collected during driving sessions. Often one vehicle is shared by multiple drivers and one driver can drive multiple vehicles. The present disclosure securely tracks the individual drivers, stores, and retrieves associated driver data for analysis on the edge (vehicle) in near real time. Data collected is analyzed at various time intervals (each trip, daily, monthly) to produce the scores. The goal of the proposed solution minimizes cost associated with data transmission and cloud storage, tracks long term driver driving history on the edge for near real time analysis of driver behavior, minimizes driver distraction due to user device while driving, securely stores and retrieves driver driving data on the edge device associated with the driver, restricts access to the driver driving data, and restricts user device access to servers and telematic units.