Abstraction and Decision-Making Phase in Autonomous Vehicles using Artificial Intelligence: A Review of Models, Strengths, and Limitations

Fasa Pengambilan dan Pengambilan Keputusan dalam Kenderaan Autonomi menggunakan Kecerdasan Buatan: Kajian Model, Kekuatan, dan Batasan

Abstract

Autonomous vehicles (AVs) can sense their surroundings and operate without the need for human intervention. At no point is a human passenger required to assume control of the car, nor is a human passenger required to be present in the vehicle at all. A self-driving automobile can go anywhere a traditional car can go and accomplish everything a skilled human driver can do. Because of its futuristic driving experiences, the autonomous car, as an emerging and quickly rising area, has gotten a lot of attention. To operate, the AVs have their architecture consists of 4 phases: abstraction phase, decision-making phase, control phase, and chassis phase. However, some issues arise involving accidents between autonomous vehicles and others (Yuan, Gao & Li, 2016), which did not yield to the car but was predicted by the self-driving technology to delay or stop. Hereby, this paper was focused on identifying the model or methods or approaches that can be used in the abstraction phase and decision-making phase. In addition, the advantages and limitations of each model have also been reviewed in this paper. While, at the end of this paper, some conclusions on the models used in this phase have been done.