Vehicle Dynamics Model Validation via Sensor Concordance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Vehicle dynamics models used in driver assistance and autonomous driving systems may become inaccurate over time due to wear or modifications, potentially leading to unsafe vehicle behavior, as they do not sufficiently represent the actual vehicle conditions.
Innovation Solution
A method to continuously check the validity of vehicle dynamics models by comparing model-based and actual output values, such as yaw rate, using sensors and calculating a concordance measure like Jensen-Shannon divergence to determine if the model accurately represents the vehicle's behavior, allowing for real-time validation and potential error responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a vehicle dynamics model is used for predictions in autonomous driving, then the productivity and automation of vehicle control is improved, but the reliability deteriorates over time due to wear and modifications making the model inaccurate
Solution Approach 1:
The patent implements a feedback mechanism where actual vehicle sensor data is continuously compared with model predictions. A validity indicator is generated based on this comparison, and when the model deviates from actual behavior, the system can request updated measurements or switch to alternative control strategies, ensuring reliability is maintained despite model aging
Solution Approach 2:
The system performs preliminary validation of the dynamics model by comparing predicted values with actual sensor measurements before relying on model-based predictions for control decisions. This preliminary check ensures the model is still accurate enough for use, preventing reliability issues from arising
2Measurement precision
If visual assessment by experts is used to verify vehicle dynamics models, then the measurement precision of model validation is improved, but the productivity and automation deteriorates due to manual verification processes
Solution Approach 1:
The system enables self-service validation where the vehicle dynamics model automatically validates itself by comparing its own predictions with actual sensor measurements from the vehicle. This eliminates the need for expert visual assessment while maintaining validation accuracy through objective quantitative comparison
Solution Approach 2:
The patent replaces the mechanical process of expert visual assessment with an automated computational system that uses sensor data and algorithms to objectively validate model accuracy. This substitution dramatically increases verification speed while maintaining or improving validation precision
3Reliability
If the vehicle dynamics model is continuously updated to maintain accuracy, then the reliability is improved, but the device complexity increases due to additional sensors and processing requirements
Solution Approach 1:
The system uses existing vehicle sensors to measure actual dynamics behavior, creating a digital copy or representation of the vehicle's real-world performance. This copy is then compared with the dynamics model predictions, allowing validation without adding complex hardware while maintaining reliability
Data Source
AI summary
A method for checking a vehicle dynamics model of a vehicle, with which a value of an output variable is ascertainable from a value of a variable input variable, for multiple values of the input variable respectively associated model-based values of the output variable being ascertained with the aid of vehicle dynamics model, for the multiple values of the input variable at the vehicle respectively associated vehicle-based values of the output variable being ascertained, difference values being ascertained from mutually corresponding model-based values and vehicle-based values, respectively, an updated dataset of the ascertained difference values being compared with a comparison dataset with the aid of a comparison method and a concordance measure being ascertained in the process, and the vehicle dynamics model being determined to be valid if the concordance measure meets a predefined concordance criterion.