Virtual Driving Tests with Sensor and Actuator Fault Injection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing virtual test methods for autonomous vehicle control systems fail to prevent incorrect output data from actuators when sensors malfunction or have limited performance, leading to potential safety issues.
Innovation Solution
A computer-implemented method and system that simulate driving scenarios by monitoring and adjusting sensor and actuator parameters during virtual tests, allowing for the detection and simulation of sensor and actuator malfunctions, thereby reducing unnecessary tests and improving the efficiency and effectiveness of driver assistance function testing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional virtual test methods are used, then the testing process is simple, but incorrect output data is generated when sensors malfunction or have limited performance
Solution Approach 1:
The patent applies preliminary action by introducing malfunction scenarios and performance limitations of sensors and actuators before executing the virtual test. The testing system pre-configures faulty sensor data and limited actuator performance conditions, then runs the autonomous driving algorithm under these predetermined faulty conditions to verify its robustness and correctness.
Solution Approach 2:
The patent uses an intermediary approach by introducing a testing system that acts as a mediator between the autonomous driving algorithm and the virtual environment. This testing system injects faulty sensor data and simulates actuator limitations, thereby indirectly testing the algorithm's ability to handle real-world sensor malfunctions and performance constraints.
2Reliability
If all possible sensor malfunctions are tested, then the reliability of the control system is improved, but the number of tests increases significantly
Solution Approach 1:
The patent applies parameter changes by systematically varying sensor data parameters and actuator performance parameters to create different malfunction scenarios. Instead of testing every possible failure mode exhaustively, the system changes key parameters such as sensor accuracy, detection range, and actuator response characteristics to cover the most critical failure modes efficiently.
Solution Approach 2:
The patent applies local quality by focusing testing efforts on specific critical parameters and scenarios rather than uniformly testing all possible conditions. The testing system identifies and concentrates resources on testing the most safety-critical sensor malfunctions and actuator failures, thereby improving reliability where it matters most while maintaining testing efficiency.
Data Source
Figure 1~2
AI summary
The invention relates to a method and system (1) for performing a virtual test of a device (10) for at least partial autonomous driving of a motor vehicle, comprising performing (S2) the virtual test by an algorithm (A) using at least one parameter set (P) of driving situation parameters, wherein the virtual test performed by the algorithm (A) simulates the at least one parameter set (P) of driving situation parameters; and upon fulfillment of a predetermined and/or algorithm-determined condition (B), changing (S4) the at least one first parameter (P1) detected by the at least one vehicle sensor (12a) and/or a third parameter (P3) relating to a vehicle actuator (12b) during the runtime of the virtual test.