Vehicle Perception Confidence Evaluation for ADS Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for methods and systems capable of monitoring the reliability of the perception functionalities of automated driving systems (ADS) to ensure safe and reliable vehicle operation.
Innovation Solution
A computer-implemented method for monitoring the performance of an object perception system in vehicles by comparing sensor data with reference data to assign confidence values, allowing control of the vehicle or downstream ADS functions based on these values.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the object perception system processes sensor data to provide scene understanding, then the vehicle's perception capability is improved, but the reliability and accuracy of the perception output cannot be guaranteed without performance monitoring
Solution Approach 1:
The patent implements a performance evaluation module that continuously monitors the object perception system by comparing detected objects against reference data, generating confidence values that feedback to control the vehicle operation. This feedback mechanism ensures reliability by dynamically adjusting system behavior based on real-time performance assessment without requiring fundamental changes to the perception system architecture.
2Reliability
If confidence values are assigned to object perception data to indicate reliability, then the safety of vehicle operation is improved, but additional processing steps are required
Solution Approach 1:
The patent introduces a performance evaluation module as an intermediary component that bridges the object perception system and downstream ADS functions. This module generates confidence values by comparing perception output with reference data, serving as a mediator that translates complex perception reliability assessment into simple confidence metrics that can be directly used by vehicle control systems.
Solution Approach 2:
The patent replaces complex mechanical or manual verification of perception reliability with an automated electronic evaluation system. The performance evaluation module uses computational methods to generate confidence values, substituting what would otherwise require complex manual assessment or additional physical verification mechanisms.
3Measurement precision
If the object perception system provides accurate scene understanding, then downstream ADS functions can operate effectively, but without performance monitoring the reliability of the perception data is uncertain
Solution Approach 1:
The performance evaluation module establishes a feedback loop that continuously assesses perception accuracy by comparing detected objects against reference data. This feedback mechanism provides real-time reliability information about the accuracy of scene understanding, enabling downstream ADS functions to operate with known confidence levels rather than uncertain reliability.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A a computer-implemented method for monitoring a performance of an object perception system of an automated driving system of a vehicle and related aspects are disclosed. The object perception system is configured to ingest sensor data samples generated by one or more vehicle-mounted sensors out of a plurality of vehicle-mounted sensors and to output object perception data indicative of one or more detected objects in a surrounding environment of the vehicle and of one or more attributes of the detected objects. The method comprises outputting reference data indicative of one or more detected objects in the surrounding environment of the vehicle and of one or more attributes of the detected objects based on sensor data samples generated by one or more vehicle-mounted sensors out of the plurality of vehicle-mounted sensors. The method further comprises comparing the object perception data with the reference data and assigning one or more confidence values to the object perception data based on the comparison. The method further comprises controlling the vehicle, the object perception system, and/or one or more downstream ADS functions configured to ingest the object perception data, based on the assigned one or more confidence values.