Vehicle Lane Control Using One-Sided Road Marking Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated driving systems face instability due to errors in recognizing road markings from one side, leading to mismatches with map information, causing lateral errors and swaying of vehicles.
Innovation Solution
A vehicle control device and method that corrects one-sided road marking mismatches by calculating a first and second self-position based on travel state and map information, adjusting vehicle travel to ensure alignment with corrected map road markings, and implementing travel control to stabilize automated driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated driving continues based on mismatched road marking or map information, then automated driving can proceed without interruption, but lateral error occurs and vehicle stability is impaired
Solution Approach 1:
The system continuously monitors the match between recognized road markings and map information, and adjusts vehicle trajectory based on the comparison result. When a mismatch is detected, the system uses feedback from the odometry-based position calculation to correct the trajectory and maintain stability.
Solution Approach 2:
The system calculates the vehicle's self-position based on odometry information before final trajectory determination. This preliminary position calculation allows the system to prepare correction actions in advance when mismatches are detected, preventing lateral swaying before it occurs.
2Device complexity
If road marking recognition is performed only for one side, then processing complexity is reduced, but errors in recognition lead to mismatches with map information
Solution Approach 1:
The system introduces map information as an intermediary reference to verify the accuracy of one-sided road marking recognition. By comparing the recognized marking with the map data, the system can detect errors without requiring recognition from both sides, thus maintaining simplicity while improving accuracy.
Solution Approach 2:
The system adds a verification dimension by comparing one-sided recognition results with pre-stored map information. This additional dimensional check allows the system to ensure accuracy without increasing the complexity of the primary recognition process.
3Measurement precision
If map road marking is corrected based on recognized road marking, then accuracy is improved, but lateral error occurs when recognition contains errors
Solution Approach 1:
The system calculates the vehicle's self-position based on odometry information before final trajectory determination. This preliminary position calculation allows the system to prepare correction actions in advance when mismatches are detected, preventing lateral swaying before it occurs.
Solution Approach 2:
Instead of directly correcting the map road marking when a mismatch is detected, the system inverts the approach by calculating the correct position based on odometry information and then adjusting the trajectory accordingly. This prevents erroneous corrections from propagating lateral errors.
Data Source
AI summary
A vehicle control device includes a storage medium storing computer-readable instructions and a processor connected to the storage medium. The processor executes the computer-readable instructions to recognize a road marking located in a travel direction of a vehicle, determine whether or not the recognized road marking matches a map road marking based on map information stored in a storage unit and determine whether or not a one-sided road marking that has been recognized matches a one-sided map road marking when the road marking has been recognized only for one side, correct the one-sided map road marking on the basis of the recognized one-sided road marking when it is determined that the recognized one-sided road marking matches the one-sided map road marking, and perform travel control for the vehicle. The processor calculates a first self-position of the vehicle based on the one-sided map road marking before the correction on the basis of a travel state of the vehicle, calculates a second self-position of the vehicle based on the one-sided map road marking after the correction or the recognized one-sided road marking, and performs the travel control for the vehicle so that the vehicle travels to a position based on the map road marking before the correction or a position based on the one-sided map road marking after re-correction offset from the recognized one-sided road marking to the map road marking before the correction when an error between the first self-position and the second self-position is greater than or equal to a first threshold value.