Highway Lane Tracking Using GPS in Conjunction With Onboard IMU and Vision-based Lane Tracking Measurements

摘要

When a vehicle's Lane Departure Warning (LDW) system fails to detect lane markers on the roadway ahead of the vehicle, it loses its ability to alert the driver of an unintended lane departure. Therefore, it has been a recent trend in LDW research to explore the use of use multiple sensors, such as GPS and inertial measurement units (IMU) to assist the LDW vision system in the event of a lane detection failure [5] [7]. These multi-sensor systems typically use differential GPS or even real-time kinematic (RTK) GPS combined with high accuracy maps to locate the vehicle to within a particular lane on a roadway. Although these advanced positioning systems are highly accurate, they are currently not deployed in the consumer automobile market, so therefore, are currently not cost effective solutions. The goal of this research is to use regular GPS, combined with inertial sensors and a high accuracy map to assist a vision-based lane departure warning system. In-car GPS navigation systems are available in many automobiles, as well as automotive grade inertial sensors. The low accuracy of a typical GPS receiver found in an automotive navigation system is largely attributed to a position error. This error is too large to allow the GPS receiver to locate a vehicle in a particular lane on a roadway. This work will present a method to measure this error using a vision-based lane departure warning system together with a high-accuracy map. With the error known, the accuracy of the GPS receiver is increased to a high-enough level to localize the vehicle on a particular lane. Next, this work will present a method fusing GPS/INS/Vision and a high accuracy map for highway lane tracking. The goal of this method is to provide a backup lateral offset measurement that can be used for lane departure warning, when the LDW vision system loses track of the lane markings.