Autonomous Driving Module Abnormality Detection Using Map and Motion Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in reliable driving due to the risk of hacking of newly mounted autonomous driving systems or modules, which can lead to malfunctions.
Innovation Solution
An electronic device and method for identifying abnormalities in autonomous driving modules by analyzing command data, measurement data, and high-definition map data to determine errors and prevent malfunction, using encryption and random number verification to secure communication with the vehicle's gateway.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If an autonomous driving module is newly mounted in the vehicle, then the autonomous driving capability is improved, but the risk of being hacked from the outside increases
Solution Approach 1:
The system performs preliminary actions by acquiring command data from the autonomous driving module and verifying its authenticity against HD map data and sensor measurement data before allowing the module to control the vehicle. This pre-verification mechanism prevents unauthorized commands from executing, addressing the security risk while maintaining autonomous driving capability.
Solution Approach 2:
The system implements a feedback loop where command data from the autonomous driving module is continuously monitored and compared with expected values derived from HD map data and sensor data. When discrepancies are detected, the system identifies abnormality and prevents malicious commands from affecting vehicle operation, thus resolving the contradiction between capability and security.
2Reliability
If command data from the autonomous driving module is verified using HD map data and sensor measurement data, then the security against hacking is improved, but the system complexity increases
Solution Approach 1:
The system uses multi-functional data processing where HD map data and sensor measurement data serve multiple purposes: they are used for navigation, path planning, and simultaneously for verifying the authenticity of command data from the autonomous driving module. This multi-functionality reduces the need for separate verification systems, thereby limiting the increase in system complexity.
Solution Approach 2:
The system introduces an intermediary verification mechanism that acts as a mediator between the autonomous driving module and the vehicle control system. This intermediary layer compares command data with expected values without requiring complete system redesign, thus improving security while controlling complexity through a modular approach.
3Measurement precision
If the system acquires and analyzes multiple types of data (command data, measurement data, map data) to identify abnormalities, then the detection accuracy is improved, but the processing time increases
Solution Approach 1:
The system performs preliminary processing of HD map data and sensor measurement data to pre-calculate expected command values and their valid ranges before autonomous driving operations begin. This pre-computation reduces the real-time processing burden during actual driving, allowing accurate abnormality detection without excessive processing time delays.
Solution Approach 2:
The system implements a tiered verification approach where critical safety-related command data parameters are verified with high precision using all available data sources, while less critical parameters use simplified verification methods. This partial application of full verification maintains detection accuracy for essential functions while reducing overall processing time.
Data Source
AI summary
An electronic device includes a memory that stores computer-executable instructions and at least one processor that executes the instructions. The at least one processor receives command data related to autonomous driving of a vehicle from an autonomous driving module. The at least one processor identifies, based on reception of the command data, at least one of first measurement data corresponding to a lateral direction based on a movement direction of the vehicle and related to a movement of the vehicle and/or second measurement data corresponding to a longitudinal direction based on the movement direction of and related to the movement of the vehicle. The at least one processor identifies an indication of abnormality of the autonomous driving module based on at least one of map data including a high-definition map received from a map device, the command data, the first measurement data, and/or the second measurement data.