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.
|Commitee:||Chandramouli, Rajarathnam, Guo, Yi, Pochiraju, Kishore|
|School:||Stevens Institute of Technology|
|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|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be