Vehicle Occupant Emotion Prediction for Adaptive Autonomous Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current driver monitoring systems (DMS) do not adaptively select signal processing algorithms based on an occupant's predispositions towards the vehicle or vehicle systems, leading to suboptimal occupant comfort.
Innovation Solution
A system and method that trains emotional state prediction machine learning models using occupant personality profiles to adjust vehicle autonomous driving systems, including low-trust, medium-trust, and high-trust models, to enhance occupant comfort by adjusting driving parameters based on the occupant's emotional state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single signal processing algorithm is used for all occupants, then the device complexity is reduced, but the occupant comfort and emotional state prediction accuracy deteriorates
Solution Approach 1:
The system segments the emotional state prediction task by creating separate machine learning models for different occupant personality types (e.g., anxious, confident, neutral). Each model is specialized for a specific personality category, allowing the system to adapt to individual occupant characteristics while maintaining manageable model complexity through division of labor
Solution Approach 2:
The system changes the parameter of model selection based on detected personality traits. By identifying the occupant's personality type and selecting or adjusting the appropriate emotional state prediction model accordingly, the system achieves adaptability without requiring all possible models to run simultaneously, thus managing complexity
2Measurement precision
If multiple emotional state prediction models are trained for different personality profiles, then the emotional state prediction accuracy is improved, but the training time and computational resources increase
Solution Approach 1:
The system performs preliminary classification of the occupant's personality type before deploying the emotional state prediction. By first identifying the personality category and then selecting the corresponding pre-trained model, the system avoids the need to train multiple models from scratch for each user and reduces real-time computational burden
3Ease of operation
If the system adjusts vehicle operations based on detailed emotional state analysis, then the occupant comfort is improved, but the processing time and computational load increase
Solution Approach 1:
The system applies partial action by adjusting only the most relevant vehicle parameters based on the detected emotional state and personality profile, rather than optimizing all vehicle systems simultaneously. This selective adjustment maintains occupant comfort while reducing computational load and processing time
Data Source
AI summary
A method for increasing comfort of an occupant in a vehicle includes training a plurality of emotional state prediction machine learning models. The method further may include recording a plurality of sensor data using at least one vehicle sensor. The method further may include determining an occupant personality profile of the occupant. The method further may include selecting a selected one of the plurality of emotional state prediction machine learning models based at least in part on the occupant personality profile. The method further may include determining an occupant emotional state of the occupant based at least in part on the plurality of sensor data using the selected one of the plurality of emotional state prediction machine learning models. The method further may include adjusting an operation of a vehicle autonomous driving system of the vehicle based at least in part on the occupant emotional state.