Development and Demonstration of a Cost-Effective In-Vehicle Lane Departure and Advanced Curve Speed Warning System
Lane Departure Warning System (LDWS) and the Advance Curve Warning System (ACWS) are two critical elements among several other Advanced Driver-Assistance Systems (ADAS) functions that have significant potential to reduce crashes that involve crossing of an edge line, center line, or otherwise leaving the intended lane or trajectory. LDWS generally uses image processing or optical scanning techniques to detect a lane departure. ACWS, on the other hand, uses a standard GPS receiver, a speed sensor, and access to the digital maps of lane-level resolution to detect the curve ahead. The primary objectives of this study were to develop a lane departure detection algorithm and an advanced curve warning algorithm using a standard GPS receiver with only road-level information, which are available commonly in any navigation device. GPS was used to determine the lateral shift of a vehicle, estimate road curvature, and provide an advisory travel speed. The lane departure detection algorithm compared vehicle trajectory to the road-level information obtained from a digital mapping database, and audible warning messages informed drivers about unintentional lane drifting. The curve detection algorithm utilized the road direction and curvature from the database to determine a safe deceleration rate; warning messages informed drivers of both the curve and the advisory travel speed. Researchers performed tests on a 3-km-long road segment on Rice Land Road in Duluth, Minnesota and a 4-km-long segment on the I-35. Intentional lane changes were carried out to evaluate the effectiveness of both algorithms.
Below are the lessons that can be taken from this study:
- Relative accuracy of a standard GPS receiver can be leveraged for detecting lane departures. Although the error in absolute position accuracy of a standard GPS receiver is larger than a standard lane width, the fact that the error in its relative accuracy is much less than the lane width provides an opportunity to potentially detect a lateral drift.
- Accuracy could be improved on sharp curves. Lane departures on both straight and curved road segments were detected almost 100 percent of the time. False lane detections occurred about 10 percent of the time on sharp curves.
- Algorithms should be reconfigured to reduce the number of false lane departure detections. Utilize algorithms that calculate vehicle trajectories using road direction, road curvature, and vehicle speed to significantly reduce the frequency of false detections.
- Improve accuracy by improving the ability to determine road direction on sharp curves. Research suggests that algorithms should calculate lateral distances every 100 milliseconds to improve LDWS and ACWS accuracy and effectiveness.
- Calculate safe distances for deceleration using vehicle and advisory speeds. Alert drivers of upcoming curves based on this distance, and issue curve warnings at a safe distance if travel speed is greater than the advisory speed.