Path Planning for an Autonomous Vehicle based on the Ant Colony Algorithm: A Review

Efficient path planning technology for autonomous vehicles not only yields significant time savings but also contributes to reducing fuel usage. Various methodologies have been introduced and documented in the literature concerning the path planning of autonomous vehicles. While these methodologies may not ensure an optimal solution, they have demonstrated successful applications in their respective contexts, especially the ant colony algorithm. Nevertheless, not many papers discuss the literature review from the viewpoint of ant colony-based path planning. This paper aims to provide a comprehensive review encompassing the modeling, optimization criteria, and solution algorithms related to the ant colony for path planning. In this study, the review of the ant colony algorithm is divided into global and local path planning. Based on the review results, the ant colony algorithm appears suitable for global path planning. To achieve better performance, it can be combined with other algorithms such as artificial potential field (APF), genetic algorithm, and particle swarm algorithm. These studies are conducted solely in simulations. Therefore, further research should be carried out to ensure the performance of combining the ant colony and APF for autonomous vehicles for both global and local path planning.

I. Introduction

In recent decades, the growing demand for eco-friendly and efficient mobility has fueled research in developing autonomous vehicles. Improving path planning systems for autonomous electric vehicles is crucial to optimize energy usage and minimize environmental impact [1]. The main challenge in designing autonomous vehicles in Indonesia lies in the irregular geographical [2] conditions and road infrastructure, especially in suburban areas. Path planning with global applications like Google Maps currently does not cover small roads in residential areas or specific regions.