16 June 2016 in Interactive Learning Environments
In this paper, we investigate an application of virtual reality and artificial intelligence (AI) as a technological combination that has a potential to improve the learning experience and engage with the modern generation of students. To address this need, we have created a virtual reality replica of one of humanity's first cities, the city of Uruk and populated this city with AI-controlled 3D avatars, which re-enact everyday life of ancient Sumerians in the period around 3000 B.C. Our hypothesis is that by immersing students into this environment and allowing them to learn by browsing through it and interacting with its virtual citizens can be more engaging and motivating than simply reading the corresponding history text or watching an educational video. To confirm this assumption, we have designed a study with three groups of students. One group was given a historical text about Uruk and everyday life of its citizens (created by our subject matter experts), the second group was shown a documentary video on Uruk and the third group was immersed into virtual Uruk and engaged into interactions with its virtual inhabitants. The outcomes of the study suggest that not only did people in the third group provide much more positive qualitative feedback about the learning experience, but they also showed a better comprehension of the study material by performing (on average) 20% better than the first two groups on the mini-exam that was conducted as a part of this study.
2 January 2016 in Connection Science
In this paper we investigate the concept of believability and make an attempt to isolate individual characteristics (features) that contribute to making virtual characters believable. As the result of this investigation we have produced a formalisation of believability and based on this formalisation built a computational framework focused on simulation of believable virtual agents that possess the identified features. In order to test whether the identified features are, in fact, responsible for agents being perceived as more believable, we have conducted a user study. In this study we tested user reactions towards the virtual characters that were created for a simulation of aboriginal inhabitants of a particular area of Sydney, Australia in 1770 A.D. The participants of our user study were exposed to short simulated scenes, in which virtual agents performed some behaviour in two different ways (while possessing a certain aspect of believability vs. not possessing it). The results of the study indicate that virtual agents that appear resource bounded, are aware of their environment, own interaction capabilities and their state in the world, agents that can adapt to changes in the environment and exist in correct social context are those that are being perceived as more believable. Further in the paper we discuss these and other believability features and provide a quantitative analysis of the level of contribution for each such feature to the overall perceived believability of a virtual agent.
1 July 2012 in Computer-Aided Design
15 April 2010 in The Visual Computer