D. Friedman, P. Tuchman. Virtual clones: Data-driven social navigation. Paper to be presented in: proc. of the 11th International Conference on Intelligent Virtual Agents. pp-28-34, Iceland, 2011.

Millions of participants inhabit online virtual worlds such as SL1 and engage in a wide range of activities, some of which require the performance of tedious tasks. Our goal is to develop a virtual proxy that would replace human participants in online virtual worlds. The proxy should be able to perform sim- ple tasks on behalf of its owner, similar to the way the owner would have per- formed it. In this paper we focus on the challenge of social navigation. We use a data-driven approach based on recording human participants in the virtual envi- ronment; this training set, with a machine learning approach, is then used to control an agent in real time who is performing the same social task. We evaluate our method based on data collected from different participants.