Available at: https://digitalcommons.calpoly.edu/theses/3315
Date of Award
6-2026
Degree Name
MS in Electrical Engineering
Department/Program
Electrical Engineering
College
College of Engineering
Advisor
Xiao-Hua (Helen) Yu
Advisor Department
Electrical Engineering
Advisor College
College of Engineering
Abstract
Autonomous vehicles (AV) are widely used in a variety of applications, such as warehouse logistics and search-and-rescue operations. They often operate as part of a Multi‑Agent System (MAS), in which each vehicle is considered as an individual “agent”. The environments associated with these applications are often challenging for multi-agent system navigation, especially when larger number of obstacles is present and multiple tasks must be completed. Many existing algorithms struggle to deal with such complex scenarios.
This thesis proposes an approach based on PRM (Probabilistic Roadmaps) and ACO (Ant Colony Optimization) for multi-AUV (Autonomous Underwater Vehicle) task allocation and path planning in a 3D environment with obstacles. Computer simulations show that the proposed approach outperforms other alternative algorithms such as GBNN (Glasius Bio-Inspired Neural Network) on both path length and computational time, with an average improvement of 8.10% on path length and 18.42% on computation time for a multi-agent system of 10 AUVs.