Development of Virtual Robot Based on Autonomous Behavior Acquisition
Masahito Yamamoto, Kenji IWADATE, Ryosuke Ooe, Ikuo Suzuki, Masashi Furukawa · Transactions of the Society of Instrument and Control Engineers · 2010
In this paper, we demonstrate a design of autonomous virtual robots and develop a design tool for autonomous virtual robots. A virtual robot can behave autonomously by using its own sensors and controllers on three-dimensional physically modeled environment. An approximate fluid environment model based on the drag force modeling is presented. The developed tool can simulate a physical environment at any time during the modeling process. A combinatorial use of neural network implementation for controllers and optimization method (genetic algorithm or particle swarm optimization) enables us to create autonomous behaviors of virtual robots.