Surroundings Model Malfunction Detection for Automated Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for identifying malfunctions in automated driving functions require manual data logging and analysis, which is time-consuming and lacks clarity on the cause of abnormal vehicle behavior, diminishing driver confidence.
Innovation Solution
A method and device for automatically determining variances between target and actual trajectories or road profiles using sensor data, enabling automated identification of malfunctions in the surroundings model, reducing manual effort and enhancing data-driven development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual data logging and analysis is performed to identify malfunctions in automated driving functions, then the cause of abnormal vehicle behavior can be determined, but the process requires many manual steps and is time-consuming
Solution Approach 1:
The system performs self-diagnosis by automatically comparing the surroundings model with sensor data and actual vehicle behavior to identify malfunctions without requiring manual intervention. The automated driving function monitors itself and generates malfunction reports autonomously.
Solution Approach 2:
Manual mechanical processes of data logging and analysis are replaced by automated computational processes. The system uses algorithms to automatically compare trajectories, detect variances, and identify malfunctions, substituting human operators with automated software.
2Loss of information
If manual visual analysis of logged data is performed to determine the reason for abnormal behavior, then developers can identify the malfunction cause, but the process is complex and requires manual comparison of road geometry with reality
Solution Approach 1:
The system implements continuous feedback loops where sensor data is compared with the surroundings model in real-time, and deviations are automatically fed back to the control system. This closed-loop feedback mechanism automatically identifies and reports malfunctions without manual intervention.
Solution Approach 2:
An automated analysis module acts as an intermediary between the raw sensor data and the final malfunction identification. This intermediate processing layer automatically compares trajectories, calculates variances, and translates complex data into clear malfunction reports.
3Reliability
If frequent manual intervention is required when the automated driving function missteers, then the vehicle can follow the real road profile correctly, but driver confidence in the automated driving function diminishes
Solution Approach 1:
The system performs preliminary detection and correction of malfunctions before they result in actual missteering. By continuously monitoring the surroundings model against sensor data and identifying variances in advance, the system prevents abnormal behavior before it affects vehicle control.
Solution Approach 2:
Real-time feedback mechanisms continuously monitor vehicle behavior and automatically adjust the surroundings model to correct malfunctions. This continuous self-correction through feedback loops maintains reliable road following without requiring manual driver intervention.
Data Source
AI summary
Provided is a method for identifying a malfunction in a surroundings model that is used by an automated driving function of a motor vehicle. The method includes determining a first deviation between a target trajectory determined by the surroundings model and an actual trajectory travelled by the motor vehicle and/or a second deviation between a course of a road determined by the surroundings model and a course of a road determined by camera software; and identifying the malfunction based on the first and/or the second deviation.