Vehicle Perception Cross-Checking for ADAS Failure Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Advanced driver-assistance systems (ADAS) and automated driving systems (ADS) face challenges in monitoring their perception performance effectively, as relying solely on their perception system outputs makes it difficult to detect sub-optimal performance before accidents occur, especially given the high integrity and safety requirements for vehicle users and other traffic participants.
Innovation Solution
A perception comparing system that communicates with a secondary vehicle within its detection range, derives and compares perception data to identify discrepancies, and communicates acknowledgement data when certain criteria are met, allowing for the evaluation of perception performance and potential failures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If perception performance is monitored using only the ADAS/ADS perception system output, then the monitoring system complexity is minimized, but the ability to detect sub-optimal performance deteriorates
Solution Approach 1:
The patent introduces a secondary vehicle as an intermediary entity to provide independent perception data for comparison. This mediator allows the monitoring system to detect perception failures without requiring complex ground truth generation, resolving the contradiction between simplicity and detection capability
Solution Approach 2:
The system creates a copy of the perception evaluation process using a secondary vehicle's perception system. By comparing the primary vehicle's perception output with the secondary vehicle's independent perception of the same environment, the system achieves reliable failure detection without significantly increasing complexity
2Reliability
If statistical proofs are conducted with sufficient data to ensure low risk, then the safety level is improved, but the time and resources required become intractable
Solution Approach 1:
The system performs preliminary perception comparisons continuously in the field before critical failures occur. By constantly evaluating perception performance against secondary vehicle data, the system ensures safety levels are maintained without requiring lengthy post-deployment statistical analysis
Solution Approach 2:
The patent implements continuous feedback loops where perception discrepancies are detected, analyzed, and used to adjust monitoring strategies in real-time. This ongoing feedback mechanism provides reliable safety assurance much faster than traditional statistical proofs that would require centuries of data collection
Data Source
AI summary
An apparatus and method performed by a perception comparing system of a vehicle for perception performance evaluation of an ADAS or ADS. The perception comparing system establishes communication with a secondary vehicle determined and/or estimated to be positioned within a potential range of surrounding detecting sensors on-board the vehicle. The system derives perception data from a perception system of the ADAS or ADS. The system receives secondary perception data from a secondary perception system of a secondary ADAS or ADS of the secondary vehicle and determines a discrepancy output based on comparison of at least a portion of the both of perception data and the secondary perception data. The system communicates acknowledgement data when at least a portion of the discrepancy output fulfils discrepancy exceedance criteria and/or when the vehicle is perceivable in the secondary perception data but the secondary vehicle not is locatable in the perception data.