ADS Verification via Blockchain for ODD-Based Fleet Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The verification process for Autonomous Driving Systems (ADS) is complex and costly, relying heavily on a centralized system that aggregates data from thousands or millions of vehicles over time, increasing infrastructure and GDPR compliance challenges.
Innovation Solution
A distributed verification system using a peer-to-peer blockchain network that identifies and collects verification data from ADS-equipped vehicles, generates verification result transactions, and adds them to a distributed ledger, eliminating the need for a centralized entity and enhancing traceability and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a centralized verification system is used to aggregate data from thousands or millions of vehicles, then verification results can be collected and processed, but infrastructure complexity and GDPR compliance challenges increase significantly
Solution Approach 1:
The patent segments the centralized verification system into a distributed network where each vehicle acts as an independent node. Verification data is segmented across multiple vehicles rather than aggregated at a single central point, with each vehicle maintaining its own verification records and contributing to the collective verification process through peer-to-peer communication.
Solution Approach 2:
The patent extracts the central verification entity from the system and replaces it with a distributed consensus mechanism. The centralized data aggregation function is taken out and redistributed across the vehicle network, allowing verification to occur through decentralized consensus rather than central collection.
2Reliability
If verification data is collected from thousands or millions of vehicles over many years, then comprehensive verification coverage is achieved, but storage and management costs increase
Solution Approach 1:
The patent uses cryptographic copying where each vehicle creates a cryptographic copy of verification data through hashing and digital signatures. Instead of storing redundant copies of actual verification data across the network, each node stores cryptographic representations that verify authenticity without duplicating the full data set, significantly reducing storage requirements while maintaining verification coverage.
3Ease of operation
If a centralized entity aggregates and processes all verification data, then verification results can be centralized and managed, but transaction costs and infrastructure requirements increase
Solution Approach 1:
The patent implements self-service verification where each vehicle independently verifies its own ADS feature operations and generates verification records. Vehicles autonomously participate in the verification process by monitoring their own system state, recording verification events, and contributing to the distributed ledger without requiring centralized processing, thereby simplifying infrastructure while maintaining ease of operation.
4Ease of operation
If verification documentation is stored centrally, then access and retrieval are simplified, but GDPR compliance and data security challenges increase
Solution Approach 1:
The patent applies local quality by storing verification data locally at each vehicle node rather than centrally. Each vehicle maintains its own verification records and cryptographic proofs locally, providing immediate local access to verification documentation. This distributed local storage approach maintains data accessibility while reducing GDPR compliance risks associated with centralized data aggregation and cross-border data transfers.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to a method performed by a distributed verification system (1) for supporting verification of ADS features within specific ODDs. The distributed verification system identifies (1001) at one or more ADS-equipped vehicles (2) connected via a peer-to-peer blockchain network (3), a respective at least first verification instruction (4) pertinent an at least first specified ODD of a specified ADS feature; collects (1002) at at least a first vehicle (20) of the one or more vehicles, verification data from execution by the at least first vehicle of the at least first ADS verification instruction while the specified ADS feature is active within and/or in association with the at least first specified ODD; generates (1003) at the at least first vehicle, a verification result transaction (5) to be added to a distributed ledger of the network, which verification result transaction comprises verification information derived from the verification data along with information of circumstances and/or configuration of the at least first vehicle associated with the verification data; and when consensus of the verification result transaction is reached on the network, adds (1004) the verification result transaction to the distributed ledger. The disclosure also relates to a distributed verification system in accordance with the foregoing, at least a first node ― for instance a network-connected ADS-equipped vehicle and/or a network-connected simulation node (6) ― comprising such a distributed verification system, and a respective corresponding computer program product and nonvolatile computer readable storage medium.