Autonomous Driving Implementation in an Experimental Environment
This work addresses autonomous driving challenges in a controlled experimental setting, but it is incremental as it applies existing methods to a specific test environment.
The study developed an autonomous driving system for a model vehicle to trace lanes and avoid obstacles in an experimental environment, using Convolutional Neural Networks for lane tracking and various computer vision techniques for obstacle avoidance.
Autonomous systems require identifying the environment and it has a long way to go before putting it safely into practice. In autonomous driving systems, the detection of obstacles and traffic lights are of importance as well as lane tracking. In this study, an autonomous driving system is developed and tested in the experimental environment designed for this purpose. In this system, a model vehicle having a camera is used to trace the lanes and avoid obstacles to experimentally study autonomous driving behavior. Convolutional Neural Network models were trained for Lane tracking. For the vehicle to avoid obstacles, corner detection, optical flow, focus of expansion, time to collision, balance calculation, and decision mechanism were created, respectively.