AI Modeling Animals

See Related Papers and Related Projects:
## Semantic Meaning & Analysis ## AI Modeling Thought & Language
## AI Affective Virtual Human ## XR Avatars; Edu, Coaches, Health ## Sensing Humans (Bio/Brain/Face/Movement/VR)

Researchers: Steve DiPaola, Bill Kraus

The Research: Our AI work here is in simulating complex (human and) animal behavoir using both Action Selection AI and Neural Networks (see papers). Technology is becoming increasingly incorporated into exhibit design. Both on the floor and extended online. Our AI work focuses on the design of VR AI interactive exhibits for an aquarium gallery. The goal was to use technology to better immerse and engage the visitors in complicated educational concepts about the life of wild belugas. We were interested in encouraging deeper exploration of the content than what is typically possible via wall signage or a video display. The beluga simulation uses extremely realistic graphics and is based on an intelligent system that allows the virtual belugas to learn and alter their behaviour based on the visitor interaction. It was informed by research data from the live belugas, (e.g. voice recordings tied to mother/calf behavior) obtained from interviews with the marine mammal scientists and education staff. Observation and visitor studies determined that visitors rarely visit alone, so the interface was designed to encourage collaboration. It allows visitors and their companions to engage in “what-if” scenarios of wild beluga emergent behavior via a 3D interactive that uses artificial intelligence, physically based animation, and real-time graphics. The program could be linked to the aquarium web site to allow for an extension of the aquarium visitor experience.

See samples of the work below:
Figure 1: Aquarium visitors interacting with virtual belugas.

Figure 2: Diagram of the belugas’ AI “brain structure”.

Figure 3: Diagram of the belugas’ neural net.




—— PAPERS: AI Modeling Animals ——

Experiencing Belugas; Developing an Action Selection-Based Aquarium Interactive

by DiPaola S; Akai C; Kraus B – Journal – (Special Issue on Action Selection). Vol 15. No 1. pp. 99-113
Adaptive Behavior (2007)

Blending Science Knowledge and AI Gaming Techniques for Experiential Learning

by DiPaola S; Akai C – Conference – 8 pages. Toronto
Canadian Game Studies Association (CGSA) (2006)

Designing Adaptive Multimedia Interactives to Support Shared Learning Experiences

by DiPaola S; Akai C – Conference – 6 pages
ACM SIGGRAPH - 2006 Educators Program (2006)

Shifting Boundaries; The Ontological Implications of Simulating Marine Mammals

by DiPaola S; Akai C – Conference – 7 pages
New Forms Festival Conference - Museum of Anthropology (2005)