Javascript must be enabled for the correct page display

Agent Allocation in Fighting Forest Fires

Rotteveel, Roel (2019) Agent Allocation in Fighting Forest Fires. Bachelor's Thesis, Artificial Intelligence.


Download (820kB) | Preview
[img] Text
Restricted to Registered users only

Download (136kB)


Forest fires are an increasing problem with respect to human safety and most importantly the ever increasing climate change. In previous research an Evolutionary Neural Network (ENN) method called ESP was used to stop forest fires in a simulation. For this research the ENN CoSyNE is instead used to establish the smallest amount of forest being burnt. This is done by creating eight waypoints for agents to navigate through, cutting firelines as they go. The impact of the amount of agents and the method of agent allocation is mostly looked into, and the results show that a Multi Agent System with eight agents using General Intelligent Allocation turns out to produce significantly better outputs than a MAS using Nearest Goal Allocation or Nearest Goal Allocation And Direction-tuning.

Item Type: Thesis (Bachelor's Thesis)
Supervisor name: Wiering, M.A.
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: Dutch
Date Deposited: 15 Nov 2019
Last Modified: 18 Nov 2019 08:47

Actions (login required)

View Item View Item