I work with Professor Stan Franklin on the Attantional and Causal learning parts of the LIDA model. LIDA is a cognitive architecture that aspires to model several facets of human and animal cognition. LIDA incorporates sophisticated action selection, a centrally important attention mechanism, and multimodal instructionalist and selectionist learning mechanisms. Empirically grounded in cognitive science and neuroscience, the architecture is strictly neither symbolic nor connectionist, but blends crucial features of each. LIDA is a successor of IDA, an agent that helps the Navy by assigning sailors to jobs. IDA is a very complex agent that perceives e-mails from sailors, deliberates on the right jobs for the sailor and negotiates with the sailor in the context of sailor's preferences and Navy's policies. [Read More]
I work with Professor  Xiangen Hu on the Virtual Civilian Aeromedical Evacuation Sustainment Training (V-CAEST) project. The goal is to leverage proven learning technologies to make training widely available via a low cost, easily updateable, internet-based virtual intelligent tutoring environment to communities across the nation and, eventually, around the world and in multiple languages. The virtual intelligent tutoring environment is built integrating an Internet based virtual 3d environment (i.e. DI-Guy (http://www.diguy.com/diguy/) with AutoTutor Lite (ATL), an internet-based intelligent tutoring system (ITS) developed at the University of Memphis. ATL includes features such as Natural Language Conversational Feedback, Point & Query, Artificial Intelligence Markup Language (AIML) powered dialog, and Learner's Characteristics Curves (LCC) assessment. These features are supported by a server-side semantic engine called semantic processing portal (SPP) and can be implemented in any Internet-based delivery platform. The interaction between the courseware and the learner is mediated by one or multiple avatars.
canadarm
 Conscious Emotional Learning Tutoring System (CELTS) is a general cognitive architecture designed to be put to work as a Tutor for astronauts learning to manipulate Canadarm2.Canadarm2 is a robotic arm installed on the International Space Station's (ISS). ISS has been designed and imple- mented to accommodate scientific experiments and life in the space. Thus, it needs to be supplied constantly with foods, fuel, inspections, etc. For instance, astronauts may use Canadarm2 to charge or discharge the received food from the space shuttles. Thus, manipulating Canadarm2 is a difficult task, which requires astronauts to undergo a serious amount of training. The seven degrees of freedom of the Canadarm2 is the first difficulty to overcome, as it considerably increases the number of possible operations. The second difficulty is sight limita- tion. It is impossible to have an overall view of the sta- tion; therefore, theastronaut can only see the arm through a steady climb camera installed on the station and on the Canadarm2. Furthermore, the astronaut must choose among these cameras because there are only three screens Canadarm Tutor helps astronauts learn how to manipulate Canadarm2 before going to space.