A master thesis from Aalborg University
Advancements in the 'Multi-Agent Exploration for Three-dimensional Space' Framework
Term
4. term
Education
Publication year
2023
Submitted on
2023-06-16
Pages
11 pages
Abstract
Multi-agent Exploration Simulator for 3D Space (MAES3D) is an open-source framework developed in Unity for testing and comparing exploration and coverage algorithms (Biegel et. al). This paper proposes to further expand upon the framework by addressing shortcomings and implementing new features missing from the prior iteration of the framework. These changes include an improvement of the sensing capabilities of agents allowing them a longer sensing range, a visualization of the explored areas, a more configurable map generator, and an improved camera and user interface. Furthermore, a novel exploration algorithm called Dual-Stage Viewpoint Planner (DSVP) is translated from 2D using a single robot to 3D with multiple robots. Experiments are conducted to compare the performance of DSVP and the already implemented algorithms named Random Ballistic Walk (RBW) and Local Voronoi Decomposition (LVD). The results of the experiments show that RBW is outperformed by both LVD and DSVP, with DSVP as the concise winner. Finally, a performance test shows that MAES3D is able to simulate at least 10 agents simultaneously.
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.