I am currently a PhD candidate in Computer Science and Cognitive Science at Indiana University Bloomington advised by Dr. Chen Yu. My research focuses on mining temporal patterns and causal inferences in high-density multimodal behavioral dataset, and developing new methods and algorithms to operationalize and understand the social mechanism in child-parent interaction that underlie language and other cognitive ability development. I am also interested in both the engineering and cognitive modeling aspects in designing social robotic agents towards realizing a future depicted in this article.
Here is a longer statement with more details of my research.
I obtained a M.S. degree in Computer Science at Indiana University Bloomington in 2012, a B.E. degree in Software Engineering at Nanjing University in 2009. I also spent half a year as a visiting student in Computer Science at National Tsing Hua University in 2008.
Xu, T.L., Abney, D.H. & Yu, C. (2017).
Discovering Multicausality in the Development of Coordinated Behavior.
Proceedings of the 39th Annual Meeting of the Cognitive Science Society
. Austin, TX: Cognitive Science Society.
Yuan, L., Xu, T.L., Yu, C. & Smith, L.B.(2017). Seeing Is Not Enough for Sustained Visual Attention. Proceedings of the 39th Annual Meeting of the Cognitive Science Society . Austin, TX: Cognitive Science Society.
Xu, T. & Yu, C. (2016).
Quantifying Joint Activities using Cross-Recurrance Block Representation.
Papafragou, A., Grodner, D., Mirman, D., & Trueswell, J.C. (Eds.)
Proceedings of the 38th Annual Meeting of the Cognitive Science Society, (pp. 1997-2002)
. Austin, TX: Cognitive Science Society.
Xu, T.L. Zhang, H., and Yu, C. (2016). See You See Me: the Role of Eye Contact in Multimodal Human-Robot Interaction. ACM Transactions on Interactive Intelligent Systems, 6(1), 2.
Yu, C., Xu, T., Zhong, Y., and Zhang, H. (2014). Learning to Interact and Interacting to Learn: Active Statistical Learning in Human-Robot Interaction. In Neural Networks (IJCNN), 2014 International Joint Conference on(pp. 684-691). IEEE.
Xu, T., Zhang, H. & Yu, C. (2013). Cooperative Gazing Behaviors in Human Multi-Robot Interaction. Interaction Studies, 14(3), 390-418.
Yu, C., Yurovsky, D., and Xu, T.L. (2012). Visual Data Mining: An Exploratory Approach to Analyzing Temporal Patterns of Eye Movements. Infancy, 17(1), 33-60.
Xu, T., Yu, C. & Smith, L.B. (2011). It's the Child's Body: The Role of Toddler and Parent in Selecting Toddler's Visual Experience. Proceedings of IEEE 10th International Conference in Development and Learning and Epigenetic Robotics (ICDL-EpiRob 2011).
All courses were provided at Indiana University Bloomington
My research focuses on studying interpersonal coordination and the social mechanism underlie language learning and development of a spectrum of cognitive abilities. Towards this goal, three main approaches were used:
First, the developmental approach: using a naturalistic toy play experimental paradigm, we invited children at different ages and their parents to our lab and collected a spectrum of behavioral signals from both participants, such as eye gaze, first-person visual input, speech, manual action and bodily movements. With this paradigm, we are able to study how the coordinated behaviors develop and mature incrementally in infants. Demo videos:  
Second, the data mining approach: to cope with the curse of dimensionality in high-density multimodal temporal data, we developed a new analysis method, Cross Recurrence Block Quantification Analysis, and used other advanced analysis methods such as Granger causality to extract diverse coordination structures and quantify causal influences among multiple behavioral modules in child-parent interaction.
Third, the robotic approach: by implementing a gaze contingent robotic platform, we were able to systematically manipulate the robot agent’s behaviors in real time and test specific hypotheses and social mechanism about interpersonal coordination within the context of human-robot interaction. Demo videos: