V2V Misbehavior Detection Using RSU Fusion Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in distinguishing between legitimate and malicious vehicle-to-vehicle (V2V) messages, which can lead to navigation errors or accidents due to the potential presence of 'ghost vehicles' created by malicious entities.
Innovation Solution
An automated driving system (ADS) equipped with a communication module, misbehavior detection module, and processor that receives V2V messages and fusion data from a mobile edge computing system, including a roadside unit, to determine the plausibility of source vehicle data through checks such as speed, position, and message consistency, and classify messages as malicious if the source vehicle is not physically located, thereby managing vehicle performance and reporting malicious identifiers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the ADS relies on V2V messages from other vehicles to guide and navigate, then navigation efficiency is improved, but the system becomes vulnerable to malicious messages from ghost vehicles
Solution Approach 1:
The patent introduces a Mobile Edge Computing (MEC) system with roadside units (RSUs) as an intermediary to verify the authenticity of V2V messages. The MEC system acts as a trusted third party that cross-checks message data against sensor data collected from multiple sources, thereby mediating between the need for efficient navigation and the requirement for reliable message authentication.
Solution Approach 2:
The system implements a feedback mechanism where the MEC system continuously monitors V2V messages and sensor data, then provides verification feedback to the ADS. This feedback loop allows the system to identify and filter malicious messages while maintaining efficient navigation by only processing verified legitimate messages.
2Reliability
If the ADS implements multiple plausibility checks on V2V messages, then message authenticity is improved, but system complexity increases
Solution Approach 1:
The patent segments the verification system into two distinct components: the ADS in vehicles that sends and receives messages, and the MEC system with RSUs that performs the complex verification. This segmentation allows multiple plausibility checks to be implemented in the MEC system without significantly increasing the complexity of individual vehicle ADS units.
Solution Approach 2:
The MEC system serves as an intermediary that centralizes the complex verification logic. Instead of each vehicle implementing full verification capabilities, the MEC system handles the computationally intensive plausibility checks, thereby reducing the complexity burden on individual vehicles while maintaining high reliability.
3Measurement precision
If the system verifies each V2V message through fusion data comparison, then accuracy in identifying malicious messages is improved, but processing time increases
Solution Approach 1:
The MEC system performs preliminary actions by continuously collecting and pre-processing sensor data from multiple sources before verification is needed. This pre-computation of fusion data allows the system to quickly compare incoming V2V messages against pre-prepared verification data, reducing the actual verification time while maintaining high detection accuracy.
Solution Approach 2:
The system implements a tiered verification approach where not all messages require full fusion data comparison. The MEC system can perform quick initial checks on message plausibility and only conduct comprehensive fusion data comparison when anomalies are detected, thereby reducing average processing time while maintaining high accuracy for identifying malicious messages.
Data Source
AI summary
An automated driving system (ADS) of an autonomous vehicle includes a communication module, a misbehavior detection module, and a processor. The communication module is configured to receive a vehicle-to-vehicle (V2V) message including source vehicle data and receive a fusion data message including fusion data from a mobile edge computing (MEC) system including a roadside unit (RSU). The source vehicle data includes a source vehicle location. The fusion data is based on RSU sensed data and on vehicle sensed data received at the RSU from at least one vehicle. The misbehavior detection module is configured to determine whether a source vehicle is disposed at the source vehicle location based on the fusion data. The processor is configured to manage performance of the autonomous vehicle in accordance with the source vehicle data based at least in part on the determination. Other embodiments are described and claimed.