Vehicle Controller Selection Under Uncertain Simulation Inputs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems face inaccuracies and uncertainties in selecting controllers due to unreliable data, leading to inappropriate or unsafe controller selection.
Innovation Solution
A system that acquires input values representing uncertainties in input variables, simulates vehicle performance for multiple controllers, determines a total cost for each, and selects the most optimal controller based on these simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If controller selection is based on predicted performance using available data, then selection efficiency is improved, but reliability deteriorates due to uncertainties in the data
Solution Approach 1:
The system performs preliminary simulations before actual controller selection by evaluating multiple hypothetical scenarios with varied input values. These pre-calculated results are stored and used to guide the selection process, allowing the system to quickly identify suitable controllers without performing real-time simulations during operation.
Solution Approach 2:
The system varies input parameters within defined ranges to create multiple simulation scenarios. By changing parameters such as vehicle mass, road gradient, and weather conditions within realistic bounds, the system evaluates how controllers perform under different conditions, leading to more robust selection decisions that account for data uncertainties.
2Reliability
If multiple simulations are performed to account for uncertainties, then reliability of controller selection is improved, but computational complexity increases
Solution Approach 1:
The simulation process is divided into discrete steps: generating varied input values within defined ranges, running individual simulations for each controller candidate, evaluating results against selection criteria, and aggregating outcomes. This segmentation allows the complex multi-scenario evaluation to be managed systematically and efficiently.
Solution Approach 2:
Instead of performing exhaustive real-time simulations, the system creates simplified simulation models that replicate essential vehicle dynamics and controller behaviors. These copied models enable rapid evaluation of multiple controllers across various scenarios without requiring full-fidelity simulations for each case.
3Measurement precision
If uncertainties in input data are considered, then accuracy of controller selection is improved, but processing time increases
Solution Approach 1:
The system pre-generates a set of representative input values that capture the range of uncertainties before the selection process begins. These pre-computed scenarios are stored and reused during controller evaluation, eliminating the need to generate and process uncertainty variations in real-time during the actual selection moment.
Data Source
AI summary
A computer system select a vehicle controller for use in control of a vehicle. The computer system has processing circuitry to acquire a plurality of input values for each of one or more input variables for simulating performance of the vehicle, wherein the plurality of input values represent an uncertainty in the respective input variable, simulate performance of the vehicle for each of a plurality of vehicle controllers, wherein a respective simulation is performed for each vehicle controller for each of a plurality of combinations of input values, determine a total cost for each vehicle controller based on the plurality of simulations performed for the respective vehicle controller, and select a vehicle controller from the plurality of vehicle controllers based on the determined costs.