Driving Assistance Algorithm Testing With Sensor and Control Conversion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current simulator-based verification of driving assistance algorithms results in inaccuracies due to discrepancies between simulator instructions and actual vehicle control instructions, leading to potential safety risks if unqualified algorithms are installed in vehicles.
Innovation Solution
A method involving an electronic device that models a virtual scene, converts sensor data, and generates target vehicle control instructions using conversion algorithms to accurately test driving assistance algorithms, ensuring the simulator accurately reflects real-world vehicle behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the simulator directly executes instructions calculated by the driving assistance algorithm, then the verification process is simple and fast, but the verification accuracy deteriorates due to errors between simulator execution instructions and vehicle control instructions
Solution Approach 1:
The patent introduces an instruction conversion module as an intermediary between the driving assistance algorithm and the simulator. This module converts the algorithm's output instructions into a format that the simulator can execute, while maintaining instruction correspondence through conversion relationships. This intermediary layer resolves the contradiction by enabling accurate verification without requiring direct simulator execution of raw algorithm instructions.
2Measurement precision
If instruction conversion is introduced to improve verification accuracy, then the verification accuracy improves, but the system complexity increases due to additional conversion modules and processes
Solution Approach 1:
The patent applies parameter changes by establishing conversion relationships between different instruction parameters. The instruction conversion module transforms algorithm instructions into simulator-executable instructions by modifying parameters such as control signals and execution timing, while maintaining the essential control logic. This approach improves verification accuracy through systematic parameter transformation rather than complex structural additions.
3Measurement precision
If the simulator uses converted instructions to accurately reflect vehicle control effects, then the verification accuracy improves, but the conversion process requires more time and computational resources
Solution Approach 1:
The patent implements preliminary action by pre-establishing conversion relationships and instruction mapping rules between the driving assistance algorithm and the simulator. These conversion relationships are defined in advance, allowing the instruction conversion module to perform rapid transformations during verification without requiring complex real-time computations. This preliminary preparation reduces conversion time while maintaining high verification accuracy.
Data Source
AI summary
A driving assistance algorithm testing method applied to an electronic device is provided. In the method, the electronic device obtains a driving assistance algorithm to be tested of a vehicle and multiple specification parameters and models a virtual scene on a simulator according to the preset parameters and generates an initial image according to the virtual scene. The electronic device obtains a target image corresponding to the driving assistance algorithm by converting the initial image according to a preset sensor conversion algorithm and the specification parameters, and generates a target vehicle control instruction according to the driving assistance algorithm, the target image, a vehicle control conversion algorithm, and the specification parameters, and scores the driving assistance algorithm by executing the target vehicle control instruction in the virtual scene of the simulator. The method can improve a verification accuracy of the driving assistance algorithm.