Experiencing Belugas: Action Selection for an Interactive Aquarium Exhibit

Abstract

In this article we present a case study of an action-selection system designed with adaptive techniques to create a virtual beluga aquarium exhibit. The beluga interactive exhibit uses a realistic three-dimensional simulation system, which allows the virtual belugas, in a natural pod context, to learn and alter their behavior based on contextual visitor interaction. Ethogram information on beluga behavior was incorporated into the simulation, which uses physically based systems for natural whale locomotion and water, artificial intelligence systems including modified neural networks and a reactive hierarchical action-selection mechanism to simulate real-time natural individual beluga and group behavior. The beluga’s behavioral system consists of two layers: a low-level navigation system and a high-level reaction hierarchical action-selection system. The system is designed to be run on consumer level hardware while maintaining real-time speeds.