Robotics Ph.D. Candidate at the University of Delaware
My core drive is to solve the hardest problems in robotics: moving from sim-to-real and making things work reliably in the physical world. Utilizing my foundation in dynamics and control, I integrate necessary techniques (MPC, RL, etc.) to enable robots to perform complex, boundary-pushing tasks.
Efficient and Compliant Control Framework for Versatile Human-Humanoid Collaborative Transportation
In this work we developed an MPC-QP control framework for heavy co-transportation tasks between humans and humanoids. This framework enables the robot to exhibit compliant behavior with respect to the co-transported object leading to a proven quantitative improvement of the efficiency of the task. Read more here
The entire framework was tested through MuJoCo simulations and later deployed on Digit humanoid through ROS2 based C++ deploy code.