Board 448: Exploring the Use of Artificial Intelligence in Racing Games in Engineering Education: A Systematic Literature Review

Abstract Over the past couple of years, artificial intelligence (AI) has undergone numerous breakthroughs and advancements, developing and refining itself into a remarkable and versatile technological asset in various different fields and domains in automated machinery. As AI continues to evolve, it emerges as a pivotal tool in research development and in different fields of learning, including engineering education in racing games. This paper presents a systematic literature review (SLR) that delves into the subject of artificial intelligence and machine learning and how it can be used to optimize the performance of AI agents in online racing games and simulators such as Track Mania, Gran Turismo, and The Open Racing Simulator (TORCS). The usage of these racing simulators is crucial as they not only provide a platform for entertainment but also a safe and reliable simulator for researchers and developers to test different AI/ML algorithms such as reinforcement learning (RL), providing a cost-effective and risk-free learning environment for users. The SLR focuses on the development and optimization of AI agents and finds from research in online engineering education. Information for this SLR was gathered from six different online scholarly sources including Google Scholar, Web of Science, IEEE Explorer, Engineering Village, EBSCOhost, ScienceDirect, and Wiley Online Library. The search process to ensure the inclusion of only relevant articles included screening by title, screening by abstract, screening by full-text, and a full synthesis of each targeted article. This methodological approach involving the combination of multiple scholarly sources and the utilization of a systematic screening process ensures a set of robust and reliable articles in providing a comprehensive literature review of the current state of AI in online racing games and its implications in engineering education. A total of twenty articles published between 2013 to 2023 met inclusion criteria, and the synthesis of these articles highlighted four themes: agent performance optimization, AI technologies applications, machine learning paradigms, and the racing simulation environment. Using these identified themes, the SLR explores the integration of AI in online racing games and simulators, shedding light on the intricate interplay and dynamics between AI technologies and the virtual racing environment.