Neural Network Implementation for Lane Tracking in Self-Driving Cars

The process of detecting and tracking lane lines is very crucial to the development of self-driving cars. For a self-driving car to successfully drive from one location to another, it must be able to detect and track lanes with minimal to no errors. Lane tracking is a computationally intensive task that needs an efficient implementation to meet the real-time requirements in self-driving cars. A self-driving car relies on the lane markings present on the road to drive safely from one point to another, so the visibility of the lane markings is important to avoid accidents. In situations where we have faded lane lines, obstructed lane, or no lane, it will be very difficult for a self-driving car to navigate safely. Few available algorithms have been able to address these issues efficiently. This research paper is aimed at addressing these problems by developing an algorithm using trained neural networks model to track lanes in most road conditions and implementing it on the NVIDIA Jetson TX2 to meet the real-time requirements of self-driving cars.

Article file ID not found.

The authors declare no conflict of interest.

Not applicable

The datasets used in this study are openly available at [repository link] and the source code is available on GitHub at [GitHub link].

This work did not receive any external funding.