Map-Information Obstacle Tracking for Curved Lane Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional driver assistance systems face inaccuracies in detecting obstacles on curved lanes due to limited viewing angles, radar interference from steel rods and guardrails, and distortion from lidar on uphill slopes, leading to unstable detection results.
Innovation Solution
A map-information obstacle-tracking system that integrates vehicular dynamic positioning and map-information routes to predict the position of obstacles, using a Kalman filter and environment sensing devices to improve accuracy and track obstacles beyond the sensor's preset region of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional filter mechanism is used to estimate obstacle position based on past information, then the system can maintain continuous tracking, but the prediction accuracy deteriorates on curved lanes due to inability to anticipate obstacle turning points
Solution Approach 1:
The system performs preliminary actions by pre-acquiring map information routes and candidate routes in advance, and using them to predict obstacle trajectories before the obstacle actually turns. This allows the system to anticipate turning points and maintain accurate tracking on curved lanes, resolving the contradiction between continuous tracking and position accuracy.
2Device complexity
If camera viewing angle and visible distance are limited, then the device complexity is reduced, but the identification capability of traffic lanes and obstacles deteriorates
Solution Approach 1:
The system introduces map information routes and candidate routes as intermediary elements that bridge the gap between limited sensor viewing angles and the need for comprehensive lane identification. These pre-acquired route data serve as a reference framework that enhances obstacle and lane identification accuracy without requiring additional complex sensors.
3Speed
If radar is used for obstacle detection, then the detection range is extended, but misjudgments occur due to interference from steel rods and guardrails
Solution Approach 1:
The system implements feedback by comparing radar detection results with map information routes and candidate routes. When radar detects potential obstacles, the system uses the pre-acquired route data to verify and filter false positives caused by steel rods and guardrails, thereby maintaining extended detection range while improving detection accuracy through iterative validation.
4Measurement precision
If lidar is used for obstacle detection on uphill curved lanes, then the detection capability is enhanced, but appearance distortion of obstacles increases
Solution Approach 1:
The system applies parameter changes by transforming the detected obstacle parameters (position, shape, orientation) using the map information routes and candidate routes as reference. This allows the system to compensate for appearance distortion caused by uphill curved lane geometry, maintaining enhanced detection capability while correcting shape parameters to reflect the obstacle's true appearance.
Data Source
AI summary
A map-information obstacle-tracking system and a method thereof are provided. The system is installed in a vehicle. The method includes: using a vehicular dynamic positioning module to acquire a position of a vehicle, and using a map-information module to acquire map-information routes of an area neighboring the position of the vehicle; comparing position of the vehicle with the map-information routes to find out candidate routes in the moving direction of the vehicle; determining one of the candidate routes where said obstacle appears, and predicting a moving trajectory of the obstacle; estimating and outputting a position of the obstacle. The present invention is characterized in using map-information and able to acquire the curvature and slope of the front curved lane. Therefore, the present invention can improve the precision of the obstacle position and stabilizes the accuracy of detecting an obstacle in a curved lane.