Traffic Light Signal Validation for Safe Automated Driving Modes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current camera-based systems for recognizing traffic light signal states in autonomous vehicles do not meet the high safety requirements for autonomous intersection entry, particularly in Level 4 and Level 5 automation, where reliable and accurate detection is crucial to prevent accidents.
Innovation Solution
A method and apparatus that determine a traffic light's signal state using data from vehicle sensors and SPaT messages from a communication infrastructure, validating the signal state through comparison with redundant information from ego-localization systems, detailed maps, and communication messages to set appropriate operation modes, ensuring safe vehicle operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera-based systems are used for recognizing traffic light signal states, then the system can detect traffic light states, but the reliability and safety requirements for autonomous intersection entry are not met
Solution Approach 1:
The patent combines multiple independent detection systems (camera-based traffic light recognition, SPaT message reception, ego-localization validation, map data verification) into a unified validation framework. This merging of redundant systems allows cross-verification of traffic light signal states, thereby improving reliability and safety while maintaining detection accuracy through mutual validation of the combined systems.
2Reliability
If multiple redundant systems are used to validate traffic light signal states, then the reliability and safety are enhanced, but the device complexity increases
Solution Approach 1:
The validation system is segmented into distinct functional modules: traffic light state detection module, SPaT message reception module, ego-localization validation module, map data verification module, and operation mode setting module. Each module performs a specific validation function independently, which reduces overall system complexity by allowing modular design, independent testing, and targeted troubleshooting of individual components.
Solution Approach 2:
The system implements feedback mechanisms where each validation module compares its results with other modules and provides feedback for validation. The traffic light state is validated by comparing camera detection results with SPaT messages, ego-localization data, and map information. This feedback loop ensures reliability through cross-verification while managing complexity through structured information flow and decision logic.
Data Source
AI summary
A method, a computer program, and an apparatus for controlling operation of a transportation vehicle equipped with an automated driving function and a transportation vehicle equipped with an automated driving function which uses the method or apparatus. A first signal state of a traffic light is determined from data of at least one vehicle sensor, the determined first signal state of the traffic light is then validated based on information available in the transportation vehicle, and an operation mode of the transportation vehicle is set as a function of a validation result.