Title of Poster / Presentation
The Power of the Collective: a Multi Agent-Based Modeling Approach to Nuclear Radiation Localization
Presentation Type
Poster
Start Date
4-5-2022 11:00 AM
End Date
4-5-2022 1:00 PM
Subjects
Nuclear Radiation, Agent Based Modeling, Deep Reinforcement Learning, Particle Swarm Optimization, Memristor Applications
Advisor
Dr. Christof Teuscher
Student Level
Masters
Abstract
Gamma radiation is a very high frequency, very dangerous electromagnetic wave that has a chance of being emitted after radioactive decay. Radiation source localization, or locating the previously unknown source of nuclear radiation, in a rapid and efficient manner is critically important, but challenging. We aim to create an architecture for multiple, fully independent agents that cooperate to localize sources faster than existing single-agent architectures, without compromising accuracy. Using Agent-Based Modeling and Deep Reinforcement Learning, agents are enabled to make decisions based on other agents' behaviors while maintaining programmatic autonomy. We hypothesize that radiation sources can be localized faster using multiple agents rather than one.
Persistent Identifier
https://archives.pdx.edu/ds/psu/37473
Included in
The Power of the Collective: a Multi Agent-Based Modeling Approach to Nuclear Radiation Localization
Gamma radiation is a very high frequency, very dangerous electromagnetic wave that has a chance of being emitted after radioactive decay. Radiation source localization, or locating the previously unknown source of nuclear radiation, in a rapid and efficient manner is critically important, but challenging. We aim to create an architecture for multiple, fully independent agents that cooperate to localize sources faster than existing single-agent architectures, without compromising accuracy. Using Agent-Based Modeling and Deep Reinforcement Learning, agents are enabled to make decisions based on other agents' behaviors while maintaining programmatic autonomy. We hypothesize that radiation sources can be localized faster using multiple agents rather than one.