@article{M2D6477EA,
title = "Implementation of Digital Virtual Environment Model Considering Obstacles and Traffic Lights, and Research on Multi-Lane Autonomous Driving Based on Deep Reinforcement Learning",
journal = "The Journal of Korean Institute of Communications and Information Sciences",
year = "2024",
issn = "1226-4717",
doi = "10.7840/kics.2024.49.6.862",
author = "Jae-yeong Lee, Sang-Jo Yoo",
keywords = "deep reinforcement learning, autonomous driving, digital virtual environment, ML-unity, DQN, PER",
abstract = "In this paper, a self-driving system in a digital virtual road environment utilizing deep reinforcement learning is proposed. Using ML-Unity, a digital virtual environment is created to simulate a multi-lane road with various obstacles and traffic lights. Multiple sensors are deployed on the vehicle to observe the current road and driving environment, facilitating the development of the autonomous driving system. Information about obstacles, traffic lights, and surrounding vehicles is acquired through the digital virtual environment. This information is then mapped to the state space of the deep reinforcement learning model to dynamically determine actions, such as driving direction and speed, to maximize performance in terms of driving distance and time. The paper introduces a system design that combines priority experience replay-based Deep Q-Network (DQN) with exploration strategies and a novel reward function to achieve fast learning and stable driving. Through experiments in the digital virtual space, the proposed system is validated to successfully perform lane-keeping, obstacle avoidance, and compliant driving with traffic signals compared to vanilla DQN."
}