Yue Yang
yygx cs.unc.edu
I am currently a Computer Science PhD student at The University of North Carolina at Chapel Hill (UNC-CH) , under the co-supervision of Prof. Daniel J. Szafir and Prof. Gedas Bertasius. Prior to embarking on this academic journey, I pursued my Master’s degree in Computer Science at the Georgia Institute of Technology (GaTech). During my time at GaTech, I worked closely with Prof. Matthew Gombolay. I was fortunate to collaborate with Prof. Greg Turk as well. It’s a true privilege to have worked with these outstanding academics.
My research interests lie in Robotics, Machine Learning (ML), and their application in Human-Robot Interaction (HRI). I am passionate about solving the following research questions:
- Data: Scalable Robot Data (e.g., Demonstrations) Collection.
- What are the more efficient or user-friendly way to collect demonstration?
- Can we generate demonstrations via motion planner / generative models?
- Can we solve the sim-to-real gap so that we could enable scalable data collection in the simulation environment?
- Controller: Scalable Robot Policy Learning from Videos.
- How to enable cross-embodiment learning? For example, learn robot policy from human videos.
- Can the policy generalize to different goals/objects/tasks?
- Can we learn policy for Long horizonal tasks?
- Deployment: Human-in-the-loop Robot Behaviors Correction.
- When the robot needs to ask human for help?
- How the human could best help the robot? i.e., what modalities (e.g., language, visual information) are the best fit for human to help robot?
I eagerly anticipate any forms of opportunities for collaboration within the realm of ML and Robotics :) Feel free to reach me most reliably through email!
I believe in Slow Science.