Vehicle Control System Target Selection via Lane Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle control systems face challenges in accurately selecting and maintaining targets on the driving route, often incorrectly identifying objects on adjacent roads as control targets due to deteriorating radar sensor performance in varying driving environments.
Innovation Solution
A vehicle control system comprising a camera sensor and non-image sensors that process image and sensing data to output driving route and lane information, allowing a controller to filter and track control targets based on preset conditions, ensuring accurate selection of preceding targets on the driving lane.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar sensor is used to detect objects and measure distance, then object detection capability is improved, but measurement precision deteriorates in varying driving environments
Solution Approach 1:
The patent combines radar sensor data with camera sensor data to compensate for the limitations of individual sensors. The radar provides distance and relative speed information while the camera provides visual context, together enabling more reliable and precise object detection across varying driving environments.
Solution Approach 2:
The patent introduces lane information and driving route information as intermediary data to filter and validate radar detection results. By using these intermediary references, the system can distinguish between actual control targets and false detections, improving measurement precision while maintaining reliability.
2Productivity
If controller selects control target based on lateral position alone, then selection speed is improved, but target selection accuracy deteriorates
Solution Approach 1:
The patent performs preliminary filtering of potential control targets using multiple criteria (lateral position, lane information, driving route) before final selection. This preliminary action reduces the number of candidates that require detailed processing, maintaining selection speed while improving accuracy through pre-validation.
Solution Approach 2:
The patent adds dimensional filters beyond simple lateral position comparison by incorporating lane information and driving route information. These additional dimensions allow the system to quickly eliminate impossible candidates while preserving the speed of the original lateral position-based selection method.
3Area of stationary object
If radar sensor detection area is expanded to cover adjacent roads, then object coverage is improved, but target recognition accuracy deteriorates
Solution Approach 1:
The patent segments the detection area into relevant zones (driving lane, adjacent roads) using lane information and driving route information. By segmenting the detection space, the system can apply different processing rules to different zones, maintaining broad coverage while improving recognition accuracy for targets in the driving lane.
Solution Approach 2:
The patent applies different quality standards to different spatial regions. Targets within the driving lane receive higher priority and more stringent verification, while targets in adjacent roads are filtered out unless they meet specific criteria. This local quality approach maintains comprehensive detection coverage while ensuring high recognition accuracy for relevant targets.
Data Source
AI summary
The present disclosure relates to a vehicle control system, a sensing device and a sensing data processing method. In particular, the sensing device according to the present disclosure may include an information receiver for receiving at least one of driving route information of a vehicle and lane information, a control target selector for presetting at least one of a filter condition and a tracking condition based on the received information, and selecting a control target among one or more objects existing in front of the vehicle based on at least one of the filter condition and the tracking condition, and an output for capturing and outputting a sensing data including a control target information for the control target.