Occupant Emotion Monitoring for Autonomous Driving Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in detecting occupant emotions and driving patterns, leading to potential distractions and increased traffic congestion when occupants fail to activate self-driving modes due to emotional or health events, causing deviations from normal driving behaviors.
Innovation Solution
A vehicle system equipped with input devices such as cameras, wearable sensors, and torque sensors that collect data on occupant emotions and driving patterns, and a computer system that processes this data to generate notifications recommending autonomous driving, with thresholds for intervention and communication with remote servers to update occupant behavior profiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system monitors occupant emotions and driving patterns continuously, then the ability to detect deviations and recommend autonomous driving improves, but the device complexity and energy consumption increase
Solution Approach 1:
The system divides monitoring into multiple independent sensor modules (cameras for facial expressions, microphones for voice tone, torque sensors for steering pressure, accelerometers for braking patterns) that each capture specific aspects of occupant state. This segmentation allows the complex monitoring task to be distributed across simpler, specialized components while maintaining overall detection accuracy.
Solution Approach 2:
The processor is designed to perform multiple functions: it analyzes data from various sensor types, compares current behavior against historical patterns, determines emotional states, and generates appropriate notifications. This multi-functionality consolidates what would otherwise require separate systems into a single universal processing unit, improving reliability without proportionally increasing complexity.
2Ease of operation
If the system provides frequent notifications to occupants about driving patterns, then the feedback effectiveness improves, but the occupant may experience increased distraction
Solution Approach 1:
The notification system adapts its behavior based on the specific deviation detected. Different notification types (subtle alerts for minor deviations, urgent warnings for serious deviations, informational messages for pattern changes) are delivered through appropriate channels (visual, auditory, haptic). This localized adaptation ensures feedback is effective for the specific situation without causing unnecessary distraction.
Solution Approach 2:
The system implements a feedback loop where notifications are sent to occupants about their driving patterns, and the system continues to monitor whether the occupant responds or maintains the deviant behavior. This ongoing feedback allows the system to adjust notification intensity and frequency based on occupant response, improving effectiveness while minimizing distraction.
3Measurement precision
If the system uses multiple sensor types to collect occupant data, then the measurement precision of emotion and behavior detection improves, but the energy consumption increases
Solution Approach 1:
The system activates sensor data collection at different levels based on detected anomalies. During normal driving, minimal monitoring occurs. When initial indicators of deviation are detected, the system intensifies data collection from relevant sensors to confirm the anomaly. This partial action approach maintains measurement precision for critical detections while reducing overall energy consumption compared to continuous full-scale monitoring.
Data Source
AI summary
A vehicle system for recommending driving automation based on occupant behavior and emotion includes one or more input devices. The input devices generate an input signal associated with sensor data indicative of a current emotion and a current driving pattern of an occupant. The vehicle system further includes a computer having a processor and a non-transitory computer readable storage medium (CRM). The CRM stores multiple occupant behavior profiles, with each occupant behavior profile including a unique occupant identification and multiple historical driving patterns. Each driving pattern has an associated historical emotion for the unique occupant identification. The processor is programmed to determine a deviation of the current driving pattern from the historical driving patterns, compare the deviation to a threshold, and generate a notification signal. The notification device provides the notification to recommend that the occupant actuate the vehicle system.