Traffic Light State Validation for Automated Driving Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current camera-based systems for recognizing traffic light signal states in autonomous vehicles may not meet the high safety requirements for autonomous driving, particularly in intersections with traffic lights.
Innovation Solution
A method and apparatus that utilize a redundant system by determining a first signal state from vehicle sensors and a second signal state from a SPaT message, validating the first signal state through comparison with the second and other vehicle information, and setting an operation mode based on validation results to ensure safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera-based systems are used for recognizing traffic light signal states, then the device complexity is reduced, but the reliability is insufficient for high safety requirements
Solution Approach 1:
The patent combines multiple sensing systems (cameras, LIDAR, RADAR) to recognize traffic light signal states. By merging these different sensing modalities, the system achieves higher reliability through redundant validation while maintaining manageable device complexity through integrated processing.
Solution Approach 2:
The system implements feedback by validating sensor data through cross-comparison of multiple sensing systems. The control unit verifies traffic light signal states by comparing results from different sensors, and only proceeds when validation succeeds, creating a feedback loop that ensures safety before action.
2Reliability
If multiple sensing systems are integrated for validation, then the reliability is improved, but the device complexity increases
Solution Approach 1:
The patent segments the sensing function into specialized components (camera for visual recognition, LIDAR for spatial mapping, RADAR for motion detection). Each sensor type is optimized for specific aspects of traffic light recognition, and the control unit coordinates them through structured validation processes.
Solution Approach 2:
The control unit serves multiple functions: it processes data from various sensor types, validates their outputs, determines traffic light states, and controls vehicle operations. This multi-functionality reduces overall system complexity by consolidating control logic in a single coordinating unit.
3Reliability
If redundant validation methods are used, then the reliability is enhanced, but the loss of time increases
Solution Approach 1:
The system performs preliminary validation by continuously monitoring and pre-processing sensor data before critical decisions are required. Traffic light signal states are validated in advance through cross-sensor comparison, so that when validation is needed for control actions, the process can proceed more quickly.
Solution Approach 2:
When sensor validation succeeds, the system skips unnecessary re-validation steps and proceeds directly to control actions. The patent allows the automated driving function to execute without repeated validation cycles once safety is confirmed, reducing time loss during normal operation.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
The present invention is related to a method, a computer program, and an apparatus for controlling operation of a vehicle equipped with an automated driving function. The invention is further related to a vehicle equipped with an automated driving function, which makes use of such a method or apparatus. In a first step, a first signal state of a traffic light is determined (11) from data of at least one vehicle sensor. The determined first signal state of the traffic light is then validated (12) based on information available in the vehicle. Finally, an operation mode of the vehicle is set (13) as a function of a validation result.