About me
Fall 2023, I started the Ph.D. in Robotics program at Oregon State University under the guidance of Prof Julie Adams. I was a graduate student in the School of Interactive Computing at Georgia Tech, pursuing an MS in Robotics. I currently do research in three spaces in STAR Lab with Prof Harish Ravichandar. First, I worked on a project that learns trait preferences from expert demonstrations for multi-agent team formation. Second, I worked on creating StarCraft II expert demonstrations for a project that learns Gaussian processes from sub-optimal demonstrations and tries to find the best possible coalition using a given set of robots. Third, worked on a project that focused on understanding the concept of the trainability of agents in a decentralized market-based coalition formation framework.
I graduated from the University of Illinois Urbana-Champaign with a Bachelor’s in Mathematics and Computer Science in May 2021. While there, I did research on developing robotic systems for a teleoperated nursing robot. I am interested in working on continuing my work with learning algorithms as well as in developing middleware for autonomous robotic systems.
Current projects
-
Adaptive Human-Machine Teaming
Description: Human teaming with machines requires systems that can understand and adapt to their human teammates. This project incorporates objective metrics to determine the performance patterns of the human teammates (i.e., workload) in real-time, predict near term human performance and use this information to adapt the machines’ interactions with the human teammates or (re-)allocate tasks among the team members in order to improve the individual teammate’s or overall team’s performance when completing tasks. The work relies on using objective metrics (i.e., heart rate variability, speech rate, noise level) to assess performance. The current state of the art algorithm requires known tasks, but future efforts will focus on incorporating real-time task identification. Sponsors: DARPA/NASA, AFOSR
Past projects
-
Learning Trait Preferences for Task allocation
I develop algorithms to extract the underlying preferences from expert demonstrations. I then use these inferred preferences to make multi-robot task allocation more effective. Please check out the
-
Decentralized MRTA accounting for Trainability of agents
I am improving the existing decentralized MRTA method by adding a feature to incorporate the feedback on agent trainability from the coalition level.
-
User Study setup
I am helping set up a StarCraft II user study to collect demonstrations for learning a gaussian process that will be used to improve the performance of task allocation. Sponsors: ARL
-
Personalized pose detection
I am extending existing algorithms to include a component that learns a personalized embedding for distinguishing heterogeneity from person-to-person differences for pose prediction.