Dissertation/Thesis Abstract

Morphogenetic computing and reinforcement learning for multi-agent systems
by Guo, Hongliang, Ph.D., Stevens Institute of Technology, 2011, 161; 3557278
Abstract (Summary)

There are some major limitations to conventional rule-based approaches for multi-robot system applications. First, as the complexity and scale of swarm robots grow, most rule-based methods are not able to accomplish the tasks due to the extensive communication and computational loads. Second, in most of the rule-based control systems, certain properties of the systems are predefined by the designers, consequently, it is hard for these systems to automatically deal with various uncertainties. To solve these issues, in the first part of this dissertation, we aim at developing a morphogenetic framework for the self-organization of swarm robots in dynamic uncertain environments. Specifically, the framework concentrates on multi-robot pattern generation and formation. The proposed mechanisms are the first attempt to generate the desired patterns based on the local sensory information and adapt the constructed patterns dynamically in response to environmental changes. This new morphogenetic framework can provide advanced control features, such as robustness, reliability, self-adaptation, and evolvability. In the second part of this dissertation, we propose a novel multi-agent reinforcement learning algorithm, in which agents not only learn from their own experiences and the environment, they also share them with their immediate neighbors and learn from their neighbors' experiences. Various simulation and experimental results demonstrate the effectiveness of the proposed algorithm.

Indexing (document details)
Advisor: Meng, Yan
Commitee: Chandramouli, Rajarathnam, Guo, Yi, Pochiraju, Kishore
School: Stevens Institute of Technology
Department: Electrical Engineer
School Location: United States -- New Jersey
Source: DAI-B 74/07(E), Dissertation Abstracts International
Subjects: Electrical engineering, Robotics, Artificial intelligence
Keywords: Bio-inspired, Gene regulatory network, Morphogen, Reinforcement learning, Robustness, Self-organization
Publication Number: 3557278
ISBN: 978-1-303-00223-6
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy