This page is for research-related stuff from 2012 forward. We will add things to this page as they become available (as promptly as possible). My research generally falls into two broad categories: 1) Robots and 2) Healthcare AI. This page is also for sharing various resources we've created to perform this work (programming code, 3D printing designs, surveys, etc.), but if there is something not posted here you are interested in, just email me.
I. Robot Stuff
Robotic Pets - Project Page
We are currently working on a research project combining socially assistive robots (SARs) with in-home sensor networks (i.e. smart homes, IOT). The goal is to see whether we can improve the mental and physical functioning of elderly people suffering from chronic depression and co-occuring physical illness who are still independently living in their own homes. In more recent times, we have expanded this research to broader groups, such as children and healthy young adults. PARO (robotic seal pictured) has been shown to be effective in assisted-living environments (e.g. nursing homes), but the aim here is to see whether we can utilize such socially assistive robots to help keep people living in their own homes longer and as a tool to monitor people's everyday health beyond the clinic walls.
We also work with a number of other robotic pets, in partnership with Hanyang University, Indiana University, and Mississippi State University. Some of the output of this research has been novel robotic sensor devices, techniques, and instruments for understanding people's everyday health.
- SoREMA Instrument - survey for conducting EMA research with social robots
Social AI & Robotic Personalities
We are currently working creating "Social AI" for robots and virtual avatars which can operate in social scenarios, such as cooperative game paradigms (e.g. video games). The idea is to use those cooperative game paradigms to try to reverse engineer social cognition by attempting to "break" normal social interactions. The research incorporate various modalities such as speech, gesture, and facial expression. This also relates to research we've done evaluating how we can create emergent robotic personalities from very basic building blocks without explicit programming, by combining data from real-world physical human-robot interactions with simulations. The simulation code (for a robotic face) is below for those interested in creating their own simulations.
RoboPers_Sim - this is the software for a Robot Personality Simulator, written in Python. Instructions for how to use our included in the ReadMe file, in the documentation folder in the downloadable Zip file.
MiRAE (Robot Face) - Project Page
The goal of this project is to explore minimalistic features necessary for a robotic face to engage in meaningful affective social interaction, as well to study questions related to the temporal dynamics of social cognition in humans and human-robot interaction. The broader aim is to create an inexpensive and replicable robotic face that can help further the "science" of robots, and/or just to make such robotic platforms more accessible to the public in general. We are making the following resources are available for research/scientific and academic use. We would appreciate if you would cite the following if you use any of these resources: Casey C. Bennett and Selma Sabanovic (2014) "Deriving Minimal Features for Human-Like Expressions Robotic Faces." International Journal of Social Robotics. 6(3): 367-381.
MiRAE Construction Manual - Construction manual for building a robotic face from scratch out of easily accessible components
RobotFace Library - Programming code (C++/Arduino Library) for controlling a robot face, making expressions, etc.
3D Printing Schematics - for printing out a fully 3D-printed robot face/head and (will be releasing Summer 2014)
Design notebooks - this is a sample of design sketchbooks/notes about the process (we have hundreds of these)
TestServoPos code - Arduino sketch for determining 90 degree position of any servo
II. Healthcare/AI Stuff
BiAffect Project - Project Page
This project focuses on using passive interaction data from smartphones (e.g. keyboard typing dynamics) to track and predict health status in patients with depression and Bipolar disorder. The idea is to monitor people's everyday health by taking advantage of technology they are already using anyway, rather than wait for them to show up at the doctor's office. This is a partnership with researchers at several major universities around the world. Our role in the project is mostly focused on the machine learning aspects of how to model the data in a way that is applicable to real-world clinical care.
Wrote a blog post for the journal Nature explaining the concept plainly, check it out: https://go.nature.com/3hCUqp0
AI Framework for Simulating Clinical Decision Making
This project aimed to develop a clinical AI that could "think like a doctor," in order to better assist clinicians and patients in challenging healthcare decisions. This research was originally associated with this paper: Bennett & Hauser (2013) "Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach.” Artificial Intelligence in Medicine. 57(1): 9-19. We may release a scaled-down open-source version of that code for academic and research use. If you have questions, please email me.
This project focused on utilizing and adapting RxNorm to develop smarter ways to collect patient medication history in real-world electronic health records. The main associated paper with this is Bennett (2012) “Utilizing RxNorm to support practical computing applications: Capturing medication history in live electronic health records.” Journal of Biomedical Informatics. 45(4): 634-641. We released code for adapting and implementing RxNorm into any electronic health record. You can find it below:
- RxNorm Transform Code - Code for extracting and reorganizing RxNorm data so it can be used to support dynamic medication history data entry and search