Vehicle Lane Assignment Using Object Edges When Markings Are Missing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems struggle to accurately recognize the position of objects around the vehicle when part of the demarcation lines are not recognized, leading to potential safety issues in driving control.
Innovation Solution
A vehicle control device and method that determines the lane to which an object belongs based on the positional relationship between demarcation lines and object edges, even when one or both demarcation lines are not recognized, using a controller to correct the object's position and control the vehicle's speed and steering accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If demarcation lines are used to determine object lane position, then lane recognition accuracy is improved, but system reliability deteriorates when demarcation lines are not recognized
Solution Approach 1:
The system performs preliminary actions by first attempting to recognize demarcation lines before determining object lane positions. When demarcation lines are successfully recognized, they are used for accurate lane determination. This preliminary recognition step allows the system to prepare alternative methods in advance for when demarcation line recognition fails, ensuring continuous operation and reliability.
Solution Approach 2:
The system introduces an intermediary approach by using alternative lane determination methods when demarcation line recognition fails. Instead of directly relying on demarcation lines, the system employs intermediate methods such as using object detection algorithms and spatial relationship analysis to determine lane positions, thereby maintaining system reliability when primary recognition methods fail.
2Measurement precision
If multiple demarcation lines are required for accurate lane determination, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system applies partial action by requiring only one demarcation line to be recognized for successful lane determination, rather than requiring all multiple demarcation lines to be perfectly recognized. This partial recognition approach reduces the complexity burden while still achieving sufficient measurement precision for safe lane position determination.
Solution Approach 2:
The system changes the recognition parameters by adjusting the confidence thresholds and acceptance criteria for demarcation line recognition. Instead of requiring high precision recognition of all demarcation lines, the system modifies parameters to accept partial recognition results, thereby reducing device complexity while maintaining adequate measurement precision for operational safety.
3Measurement precision
If demarcation line recognition is performed in all conditions, then measurement precision is maintained, but loss of time occurs when recognition fails and corrections are needed
Solution Approach 1:
The system dynamically adjusts its recognition strategy based on real-time conditions. When demarcation lines are clearly visible and recognizable, the system uses them for accurate lane determination. When recognition fails or conditions deteriorate, the system dynamically switches to alternative methods, avoiding unnecessary time loss from repeated failed recognition attempts while maintaining measurement precision through adaptive method selection.
Data Source
AI summary
A vehicle control device according to an embodiment includes an imager configured to image surroundings of a host vehicle, a recognizer configured to recognize a surroundings situation of the host vehicle, a driving controller configured to control one or both of speed and steering of the host vehicle, and a controller configured to control the driving controller, wherein the controller determines a lane to which the object belongs, based on a positional relationship between left and right demarcation lines defining a host lane in which the host vehicle travels and left and right edges of an object present around the host vehicle, which are present on a two-dimensional image captured by the imager, and determines the lane to which the object belongs, based on the positional relationship between the recognized demarcation line and the edge of the object when one of the left and right demarcation lines is not recognized.