Driver Biometric Signal-Based Road Condition Response System and Method

Road Condition Assessment System for Driver Stress Response Using Wrist-Worn GSR Sensors and Deep Learning

This technology uses a watch-style GSR sensor worn on the driver's wrist to measure changes in skin electrical conductivity caused by perspiration. It generates driver biometric signals based on factors such as GSR peak count, maximum peak, and waveform duration. A neural network processor uses deep learning to analyze these signals and determine current road conditions, such as traffic congestion, traffic clearance, highway driving, or city driving.

Driver stress, drowsiness, and fatigue increase accident risks by impairing reaction times and judgment, yet traditional safety features like seatbelts and airbags cannot fundamentally prevent human error. Existing collision warning systems only consider external factors like vehicle speed and distance to the car ahead, failing to provide alerts tailored to the driver's focus level. Furthermore, frequent alerts in congested city traffic can often increase driver stress.

Based on the assessed road conditions and biometric signals, this technology performs responsive actions such as lowering the cabin temperature by 1–3 degrees, opening windows, playing white noise during city traffic congestion, and using external LED colors to signal the driver's status to others. This reduces driver stress and helps prevent collisions and safety incidents. It can be applied to driver monitoring systems, smartwatch-integrated infotainment, and commercial fleet safety management to enable active, emotion-aware cabin control.

‍

‍

Key Features:

• A biometric signal measurement unit that uses a watch-style GSR sensor on the driver's wrist to measure skin electrical conductivity and detect potential differences caused by perspiration.
• A control unit that generates driver biometric signals by calculating peak count, maximum peak, waveform duration, and GSR values from the GSR waveform signal.
• A neural network processor that uses driver biometric signals as deep learning training data to recognize signals corresponding to traffic congestion, traffic clearance, highway driving, and city driving.
• A control configuration that lowers cabin temperature via the AC based on temperature sensor data, opens windows, or plays white noise when road conditions are identified as congested.

‍