A hybrid graph–grid improved ant colony optimization framework for accurate and low-latency path planning
Abstract
Efficient path planning is essential for safe autonomous vehicle navigation. However, conventional ant colony optimization (ACO) often suffers from premature convergence, local optima, and high computational costs. This study aims to improve path planning accuracy and computational efficiency by integrating graph- and grid-based representations into an enhanced ACO algorithm. The proposed method was evaluated on 30 navigation routes at Universitas Sriwijaya (UNSRI), Indralaya, under obstacle-free and obstacle scenarios. Experimental results showed that the proposed algorithm outperformed conventional ACO in route accuracy and computational efficiency. In obstacle-free scenarios, the mean absolute error (MAE) decreased from 70.7 m to 2.8 m. The average path generation time was 0.47 s for obstacle-free routes and 0.21 s for routes with obstacles. These findings demonstrate that integrating graph and grid based representations improves path planning accuracy and reduces computational time, offering an effective approach for real time autonomous vehicle navigation.
Keywords
Ant colony optimization; Autonomous vehicle; Graph base; Grid base; Path planning
Full Text:
PDFDOI: https://doi.org/10.11591/eei.v15i6.14056
Refbacks
- There are currently no refbacks.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191
,
e-ISSN: 2302-9285
This journal is published by the
Institute of Advanced Engineering and Science (IAES)
.