Driver Physiology-Based Vehicle Spacing Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately control the distance between a vehicle and a preceding vehicle based on the preferences of individual drivers, which can vary due to physiological and vehicle status variations.
Innovation Solution
A system that uses physiological data of the driver and vehicle status information to train a model for predicting a preferred distance, allowing the vehicle to adjust its distance based on current preferences and conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed distance control system is used, then the system complexity is low, but the adaptability to different driver preferences and conditions is poor
Solution Approach 1:
The patent implements dynamic adaptability by training a machine learning model with physiological data collected under various driving conditions and driver states. The model dynamically adjusts the preferred distance based on real-time physiological inputs, transforming a static control system into one that adapts to individual driver preferences and conditions without requiring complex manual configuration
Solution Approach 2:
The system performs self-learning by automatically collecting physiological data during driving, training the model offline, and storing learned preferences for future use. This self-service approach allows the system to improve its adaptability over time without external intervention, resolving the contradiction between adaptability and complexity through autonomous model training
2Measurement precision
If physiological data collection and model training are implemented, then the prediction accuracy of preferred distance is improved, but the loss of time for data processing increases
Solution Approach 1:
The patent applies preliminary action by collecting and storing physiological data during normal driving operations, then training the machine learning model offline before actual deployment. This pre-training approach ensures the model is ready for immediate use without requiring time-consuming processing during critical driving moments, thus improving prediction accuracy while minimizing real-time processing delays
Solution Approach 2:
The system continuously collects physiological data during driving and continuously refines the model through incremental learning. This continuous data collection and model refinement process ensures high prediction accuracy is maintained over time without requiring periodic lengthy retraining sessions, thereby reducing overall data processing time while preserving measurement precision
Data Source
AI summary
A system includes a controller configured to train a model for predicting a preferred distance between a vehicle and a preceding vehicle using a training data set including physiological data of a driver and information on a status of the vehicle, input current physiological data of the driver and information on a current status of the vehicle to the trained model to obtain a current preferred distance, and control the vehicle to adjust a distance between the vehicle and the preceding vehicle based on the current preferred distance.