Dr. Prashant Doshi
Director, THINC Lab
THINC lab is located in the Boyd Graduate Studies Research Center in the southern part of the UGA campus. Currently, more than 10 graduate students including doctoral and masters students are conducting research in the lab. Research conducted in the lab has been funded by grants from the Air Force and Army Research Offices, National Science Foundation, National Institutes of Health and the industry.
We present a new framework, OntoNLQA, for querying RDF data annotated using ontologies that allows posing questions in natural language. It introduces a novel approach for discovering the sophisticated semantic associations that may exist between the important entities of a question, in order to build an intuitive query and retrieve precise answers. We apply this framework to the context of parasite immunology data, leading to a system called AskCuebee that allows parasitologists to pose genomic, proteomic and pathway questions in natural language related to the parasite, Trypanosoma cruzi.[Learn more..]
 Uthayasankar Thayasivam and Prashant Doshi, Speeding Up Iterative Ontology Alignment using Block-Coordinate Descent, in Journal of AI Research, accepted.
 Ekhlas Sonu and Prashant Doshi, Scalable Solutions of Interactive POMDPs using Generalized and Bounded Policy Iteration, in Journal of AAMAS, in press.
 Kenneth Bogart and Prashant Doshi, Multi-Robot Inverse Reinforcement Learning under Occlusion with Interactions, in AAMAS 2014.
 Muthukumaran Chandrasekaran, Prashant Doshi, Yifeng Zeng and Yingke Chen, Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams (Extended Abstract), in AAMAS 2014.
 Xia Qu and Prashant Doshi, Behavioral Modeling of Sequential Bargaining Games: Fairness and Limited Backward Induction, in ISAIM 2014. [paper]
 Prashant Doshi, Xia Qu and Adam Goodie, Decision-Theoretic Planning in Multiagent Settings with Application to Behavioral Modeling, in Sukthankar, et al. (Eds.), Plan, Activity, and Intent Recognition, Elsevier, 2014, ISBN 978-0-12-398532-3. [chapter]
 Tejas Chaudhary, Uthayasanker Thayasivam and Prashant Doshi, Canonical Forms and Similarity of Complex Concepts for Improved Ontology Alignment, in IEEE/ACM/WIC Web Intelligence (WI) 2013 [paper]
[4/4/14] Prof. Munindar Singh of NC State visits the THINC lab on 04/04 and delivers a keynote talk at CS Research Day.
[12/18/2013] Kim, Thai and Doshi win a UGA Learning Tech. Grant to create RoboTube - a video-sharing website in which UGA undergraduate and graduate students enrolled in College of Education learn from videos, lesson plans, and discussions on how to use robotics technology in K-12 classrooms.
[11/27/13] We are looking for a postdoctoral associate in the areas of agent modeling and multiagent decision making to start immediately. Please get in touch with Prof. Doshi (pdoshi [at] cs [dot] uga [dot] edu) for more details.
[09/27/13] Prof. Doshi visited the Institute for Creative Technologies at USC and gave a hosted talk on compressing agent model spaces and model human strategic behavior.
[08/22/13] Prof. Doshi receives a 3-year grant from the Office of Naval Research. The grant will facilitate investigations of compressing mental model spaces in multiagent systems, which has broad applications toward designing intelligent autonomous systems.