Autonomous Vehicle Driving Profile Adjustment via Passenger Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles often fail to adapt their driving patterns to match the preferences and habits of their passengers, leading to a mismatch that can result in a stressful and uncomfortable riding experience, potentially exceeding psychological and physical thresholds.
Innovation Solution
A computer-implemented method that selects a driving profile based on passenger reactions, using machine learning to correlate driving patterns with passenger comfort and confidence, and dynamically adjusts the vehicle's driving settings in real-time through feedback collection and analysis, including data from wearable devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning techniques are used to establish AV driving patterns through extensive training and test data, then the AV can achieve autonomous driving capability and obey traffic patterns, but the AV driving patterns significantly differ from the driving patterns of passengers or non-active drivers, causing stress and discomfort
Solution Approach 1:
The system dynamically adjusts the AV driving pattern by transitioning from a static machine learning-established pattern to a dynamic pattern that adapts in real-time based on passenger reactions. The driving pattern is continuously modified during the trip based on monitored passenger stress indicators, transforming the rigid autonomous driving behavior into a flexible, adaptive system that responds to passenger needs.
Solution Approach 2:
The system implements a feedback loop where passenger reactions (stress indicators, heart rate, breathing patterns) are continuously monitored and fed back to adjust the driving pattern. This feedback mechanism allows the AV to learn from passenger responses and modify its driving behavior accordingly, resolving the mismatch between autonomous driving patterns and passenger comfort preferences.
2Reliability
If the AV uses a fixed driving pattern established through machine learning training, then the driving behavior is consistent and predictable for the system, but it cannot adapt to individual passenger preferences and habits, leading to stressful riding experiences
Solution Approach 1:
The system transforms the static, fixed driving pattern into a dynamic one that can adapt while maintaining operational reliability. The driving pattern evolves from a predetermined machine learning output to a flexible behavior that adjusts in real-time based on passenger feedback, preserving system reliability while improving passenger comfort.
Solution Approach 2:
The system changes driving parameters (acceleration, braking, steering) based on monitored passenger reactions. By dynamically adjusting these parameters in response to passenger stress indicators, the system maintains reliable autonomous operation while adapting to individual passenger comfort preferences and reducing stress.
3Adaptability or versatility
If the AV monitors passenger reactions in real-time to adjust driving patterns, then passenger comfort and confidence can be improved, but the system complexity and data processing requirements increase
Solution Approach 1:
The system uses the passenger's own physiological data (heart rate, breathing patterns) as self-indicators of comfort and stress levels. This self-service approach allows the AV to monitor passenger reactions without requiring complex external monitoring equipment, reducing system complexity while maintaining adaptability to passenger preferences.
Solution Approach 2:
The system uses physiological indicators (heart rate, breathing patterns) as intermediaries to measure passenger comfort and stress levels. These intermediaries provide an indirect but effective way to monitor passenger reactions without requiring direct complex interaction, simplifying the monitoring system while enabling real-time driving pattern adjustment.
Data Source
AI summary
An approach for adjusting driving parameters of an AV (autonomous vehicle) based on the driving style of the passenger is disclosed. The approach utilizes existing driving patterns of the passenger and perform a dynamic comparison and correlation with safe driving patterns of the passengers themselves. Based on that evaluation, the approach would suggest the parameters for adjusting the AV driving style in order to ensure AV riding experience meets the expected level of safe and stress-less riding. Furthermore, the approach can dynamically adjust the driving style during the trip based on the reaction and feedback from the passenger.