Vehicle Center of Gravity Estimation Using Learning-Based Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating the center of gravity position of a moving motor vehicle are limited by requiring known vehicle parameters, often focusing on only one or two coordinates, resulting in low quality estimation of the vertical coordinate and high processing power demands, which are not feasible in real-time applications.
Innovation Solution
A method that uses a learning-based classification approach with input variables like longitudinal and lateral acceleration, yaw rate, and wheel rotational speeds to estimate the center of gravity position without requiring prior vehicle parameters, utilizing simulation data to learn a non-linear assignment between driving dynamics and center of gravity positions, and implementing this in a processing unit within an ESP control unit.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If learning-based approaches with large number of classifiers are used, then estimation accuracy is improved, but processing power requirements increase and become expensive
Solution Approach 1:
The patent extracts and uses only the essential input variables (longitudinal acceleration, lateral acceleration, yaw rate, and wheel rotational speeds) that are already available from standard ESP sensors, eliminating the need for numerous additional classifiers and model parameters while maintaining estimation accuracy
Solution Approach 2:
Instead of using complex classification models to estimate center of gravity coordinates, the patent inverts the approach by using a simplified model that directly processes standard sensor data to achieve accurate three-dimensional center of gravity estimation without requiring high processing power
2Ease of operation
If known vehicle parameters are used in estimation algorithms, then estimation process is simplified, but adaptability to different vehicles is reduced
Solution Approach 1:
The patent creates a universal estimation algorithm that works across different vehicle types without requiring vehicle-specific parameters. The method uses only standard sensor data (accelerations, yaw rate, wheel speeds) that are universally available, making the system adaptable to any vehicle equipped with basic ESP sensors
Solution Approach 2:
The patent changes the approach from using fixed vehicle parameters to using dynamically measured operational parameters. By relying on real-time sensor data rather than pre-defined vehicle characteristics, the system maintains simplicity while achieving broad adaptability across different vehicle models and configurations
3Power
If existing methods estimate only one or two coordinates, then processing requirements are reduced, but estimation quality of vertical coordinate suffers
Solution Approach 1:
The patent extends the estimation from traditional two-dimensional (longitudinal and lateral) to three-dimensional by incorporating the vertical center of gravity coordinate. This is achieved by adding the wheel rotational speed dimension to the input variables, enabling accurate estimation of all three coordinates simultaneously without proportionally increasing processing requirements
Data Source
AI summary
A method in which the position of the center of gravity of a moving motor vehicle is ascertained, wherein at least one set of related input variables is taken into consideration, and the set of input variables includes at least a longitudinal acceleration of the motor vehicle, a lateral acceleration of the motor vehicle, a yaw rate of the motor vehicle and at least one wheel rotational speed, in particular four wheel rotational speeds, wherein the set of input variables is ascertained during a steady-state driving maneuver, and a quantity of possible center of gravity positions is defined as classes and, by a learning-based classification method, on the basis of the set of input variables, a class is selected which indicates an estimated center of gravity position. A control unit for carrying out the method is also disclosed.