Autonomous Driving Error Event Root Cause Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Analyzing error events in autonomous driving systems is time-consuming and labor-intensive due to the complexity of recorded sensor measurement data, which makes it difficult for humans to identify root causes.
Innovation Solution
A method that uses a prediction model trained on signal states from multiple autonomous driving systems to automatically trace back error events to their root cause by finding correlations or patterns in dynamic signal states.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual forensics evaluation is performed on autonomous driving systems, then analysis accuracy can be maintained, but time consumption and labor intensity increase significantly
Solution Approach 1:
A prediction model serves as an intermediary between the complex sensor data and human analysts. The model automatically processes signal states, identifies patterns, and generates analysis results, acting as a mediator that handles the time-consuming manual work while preserving analysis accuracy through verified predictive algorithms
Solution Approach 2:
The patent replaces manual mechanical analysis processes with an automated prediction model that uses machine learning algorithms to analyze signal states. This substitution eliminates human labor intensity and time consumption while maintaining or improving analysis accuracy through consistent, reproducible computational methods
2Measurement precision
If complex sensor measurement data is analyzed manually, then detailed examination is possible, but difficulty in parsing and identifying patterns increases
Solution Approach 1:
The prediction model creates computational representations (copies) of the complex sensor data in structured formats that are easier to analyze. By transforming raw signal states into model-compatible formats, the system preserves detailed information while making it accessible for pattern recognition through automated processing
Solution Approach 2:
The patent transforms complex sensor measurement data into standardized signal state parameters that the prediction model can process. By changing the representation parameters of the data from raw sensor formats to structured signal states with defined properties, the system enables automated pattern detection while maintaining the ability to perform detailed examinations
3Productivity
If automated prediction models are used for error event analysis, then time and effort are reduced, but system complexity increases
Solution Approach 1:
The prediction model is designed as a universal system that can handle multiple types of sensor data, various signal states, and different error event scenarios through a single automated framework. This multi-functionality reduces the need for multiple separate analysis tools, thereby reducing overall system complexity while maintaining high productivity across diverse analysis tasks
Data Source
AI summary
A method for error event analysis performed by an electronic device includes: in response to an error event of an autonomous driving system, feeding a sequence of signal states, collected from the autonomous driving system into a prediction model, where the prediction model is trained based on signal states collected from a plurality of autonomous driving systems for predicting, based on a first signal state, a second signal state, the first signal state representing signals collected at a first time, and the second signal state representing signals collected at a second time succeeding the first time; converting the error event into an event signal state having signal values at an event time; comparing the second signal state with the event signal state; and in response to the second signal state matching the event signal state, tracing the error event back to the first signal state as a root cause.