I am a postdoctoral researcher at the University of Texas at Austin, in the lab of Peter Stone. I received my Ph.D. in Cognitive Science from UC San Diego in 2006, in the Machine Perception Laboratory under Javier Movellan. My research focuses on applying machine learning and probability theory to understanding and solving real-world problems in machine perception and robotics. I am particularly interested in cognitive development, and my dissertation was on probabilistic generative models for learning real-time object detectors with little or no external supervision. This led to a new machine learning technique called “Segmental Boltzmann Fields” (SBFs). We used an SBF to form the “visual cortex” of an interactive infant robot which, using simple auditory contingencies as the only cue to determine when the visual field probably contained or did not contain a caregiver,was able to autonomously learn an accurate “person” visual category from only a few minutes worth of experience interacting with caregivers. Here is a more detailed description of my research. Since then I have begun extending this work to learning objects though touch contingencies, learning self-versus-other touch sensations, learning audio concepts, interaction and activity recognition, and learning from instruction by a teacher. This last area is part of the new DARPA “Bootstrap Learning” project.
Ian R Fasel
The University of Texas at Austin
Department of Computer Sciences
1 University Station C0500
Taylor Hall 2.124
Austin, TX 78712-0233
Phone: 512.471.7316
Fax: 512.471.8885
Selected Publications (complete list here)
Ian R. Fasel and Javier R. Movellan, “Segmental Bolzmann Fields”, in prep.
Ian R. Fasel, Learning to Detect Objects in Real-Time: Probabilistic Generative Approaches, PhD thesis, UCSD, June 2006 (full thesis pdf) (Chapters 2 and 3 are covered in the above paper. Here is the intro and final chapter only).
Ian R. Fasel, Nicholas Butko and Javier R. Movellan, Modeling the Embodiment of Early Social Development and Social Interaction: Learning about Human Faces During the First Six Minutes of Life, in: Society for Research in Child Development Biennial Meeting, 2007 (pdf)
Javier R. Movellan, Fumihide Tanaka, Ian R. Fasel, Cynthia Taylor, Paul Ruvolo and Micah Eckhardt, The RUBI Project: A Progress Report, in: 2nd ACM/IEEE International Conference on Human-Robot Interaction, 2007 (pdf)
Kevin Gold, Ian Fasel, Nathan Freier and Cristen Torrey, Young Researchers’ Views on the Current and Future State of HRI, in: 2nd ACM/IEEE International Conference on Human-Robot Interaction, 2007 (pdf)
G. Littlewort, M.S. Bartlett, J. Chenu, I. Fasel, T. Kanda, H. Ishiguro and J.R. Movellan, Towards social robots: Automatic evaluation of human-robot interaction by face detection and expression classification, in: Advances in neural information processing systems, volume 16, pp. 1563–1570, Cambridge, MA, 2004. MIT Press (pdf)
Ian Fasel, Bret Fortenberry and J. R. Movellan, “A generative framework for real-time object detection and classification”, Computer Vision and Image Understanding, 98, 2005 (pdf)
Takayuki Kanda, Nicolas Miralles, Masayuki Shiomi, Takahiro Miyashita, Ian Fasel, J. R. Movellan and Hiroshi Ishiguro, “Face-to-face interactive humanoid robot”, IEEE 2004 International Conference on Robotics and Automation, 2004 (pdf)
G. Littlewort, M.S. Bartlett, I. Fasel, J. Susskind and J.R. Movellan, “An automatic system or measuring facial expression in video”, Image and Vision Computing, in press (pdf)
Ian R Fasel, Gedeon O Deak, Jochen Triesch and Javier Movellan, Combining Embodied Models and Empirical Research for Understanding the Development of Shared Attention, in: Proceedings of the 2nd International Conference on Development and Learning, 2002 (pdf)
