Autonomous Vehicle Control Verification at Route Recognition Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous control systems face difficulties in detecting abnormalities in autonomous traveling machines whose control is compromised by attackers, as redundancy and monitoring methods can be vulnerable to cyberattacks, and simple monitoring devices may not effectively identify disguised behaviors.
Innovation Solution
A safety management system that includes an extraction unit to set verification points and extract operation states from surrounding situation data, and a verification unit to compare reported operation states with extracted states, ensuring the soundness of control in autonomous traveling machines by using a second autonomous traveling machine to verify the operation state of the first, even when under potential cyberattack.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundancy of control devices is added to monitor soundness of autonomous traveling machines, then reliability of detection is improved, but device complexity increases and all control devices may have the same vulnerability to cyberattacks
Solution Approach 1:
The patent introduces a safety management system as an intermediary that coordinates verification between autonomous traveling machines. Instead of each machine having redundant monitoring devices, the system uses the surrounding situation data and operation state data from other machines as mediators to verify soundness, reducing device complexity while maintaining detection reliability.
Solution Approach 2:
The patent uses copying by having autonomous traveling machines copy and share their surrounding situation data and operation state data with each other. The verification process compares the reported operation state with the extracted operation state from surrounding situation data, creating a virtual copy for verification purposes without adding physical redundant devices.
2Difficulty of detecting and measuring
If fixed monitoring devices are used to observe operation states, then detection capability is improved, but autonomous traveling machines can disguise their behavior by behaving normally only in monitored regions
Solution Approach 1:
The patent inverts the monitoring approach by having autonomous traveling machines monitor each other rather than having centralized fixed monitoring devices. Each machine uses its own sensors to capture surrounding situation data that includes operation states of other machines, making it difficult for any single machine to disguise its behavior since multiple independent observers exist throughout the workspace.
Solution Approach 2:
The patent adds another dimension to monitoring by transitioning from fixed spatial monitoring points to multi-dimensional verification through shared data. The verification process operates in the data dimension by comparing operation state data with extracted information from surrounding situation data, creating verification capabilities across multiple operational dimensions rather than just spatial coverage.
3Productivity
If data transmission between autonomous traveling machines and operation management system is used for control, then system coordination is improved, but security is worsened when data is tampered or forged
Solution Approach 1:
The patent implements feedback by having autonomous traveling machines continuously transmit operation state data to the safety management system, which then verifies this data against surrounding situation data obtained from other machines. This feedback loop enables real-time detection of data tampering or forgery while maintaining efficient system coordination through continuous data exchange.
Data Source
AI summary
A safety management system for recognizing surrounding conditions and transmitting first surrounding condition data, and for respectively indicating safety actions to a first autonomous traveling machine that autonomously travels on a given first travel route on the basis of the first surrounding condition data and to a second autonomous traveling machine that autonomously travels on a given second travel route. An extraction unit sets, on the second travel route, a verification point where the second autonomous traveling machine can be recognized by the first autonomous traveling machine, and extracts an operation state of the second autonomous traveling machine at the verification point from the first surrounding condition data. A verification unit compares an operation state transmitted from the second autonomous traveling machine at the verification point and the operation state extracted by the extraction unit to verify the soundness of control in the second autonomous traveling machine.