Driver Attention Verification Using Gaze Monitoring and HMI Prompts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver monitoring systems lack the ability to collect feedback from drivers to verify their attention status, leading to potential safety risks due to distracted or drowsy driving.
Innovation Solution
A system that monitors driver gaze behavior using a driver monitoring system, classifies attention status, and prompts drivers with questions via a human-machine interface (HMI) to verify their alertness, analyzing responses to initiate responsive actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If driver monitoring systems use camera and sensor data to classify attention status, then the system can identify distracted or drowsy driving conditions, but the system cannot verify the actual attention state without driver feedback
Solution Approach 1:
The system introduces feedback by prompting the driver with questions through HMI and analyzing their responses. This feedback loop allows the system to verify the driver's actual attention state by comparing sensor data with the driver's self-reported awareness and cognitive responses, thereby resolving the contradiction between detecting attention status and verifying actual alertness.
2Measurement precision
If the system prompts the driver with questions to verify alertness, then the verification accuracy improves, but the driver experience may deteriorate due to interruptions
Solution Approach 1:
The system applies partial action by selectively prompting only those drivers who are classified as potentially distracted or drowsy, rather than interrupting all drivers. This targeted approach maintains verification accuracy for at-risk drivers while minimizing disruptions to drivers who are already attentive, thus balancing verification needs with operational continuity.
3Measurement precision
If the system uses multiple data sources including historical data and machine learning, then the prediction accuracy of unsafe attention status improves, but the system complexity increases
Solution Approach 1:
The system performs preliminary action by pre-processing and storing historical driver data during normal driving conditions. This allows the machine learning model to be trained and ready in advance, enabling rapid and accurate prediction of unsafe attention status when needed without requiring complex real-time processing of all historical data, thus managing system complexity while maintaining high prediction accuracy.
Data Source
AI summary
A system for monitoring a driver in a vehicle includes a driver monitoring system adapted to monitor the driver of the vehicle, a system controller in communication with the driver monitoring system and adapted to collect data from the driver monitoring system related to gaze behavior of the driver, classify the driver as one of a plurality of driver attention statuses based on the data from the driver monitoring system, the driver attention statuses including safe, borderline and unsafe, and, when the driver status is unsafe, prompt the driver, via a human machine interface (HMI), with questions adapted to test the alertness of the driver, receive, via the HMI, from the driver, responses to the questions, analyze the responses, and initiate responsive actions based on the responses from the driver.