I am a Robotics Researcher at the Honda Research Institute, where I advance multi-fingered manipulation. I am currently leading and contributing to a project focused on online learning for dexterous manipulation in the real world, with the goal of advancing real-time planning, exploration, and data-efficient learning.

I received my Ph.D. from Northwestern University in 2024, where I was advised by Kevin Lynch and Jose Pons. I also hold a robotics-focused Master’s degree from ETH Zürich, where I completed my thesis at the Robotic Systems Lab. I have extensive research and hands-on experience with robots that physically interact with their environments.

Research

My current research interest is in multi-fingered dexterous manipulation. I am particularly interested in tasks for which teleoperation demonstrations are not possible and in settings where direct sim-to-real approaches fail. In particular, my current research focuses on online planning and real-world learning in a data-efficient manner, combining both model-based and reinforcement learning approaches.

During my PhD, I worked on interaction force controllers for lower-limb exoskeletons and introduced a novel gait rehabilitation paradigm in which a therapist and a patient were each equipped with a lower-limb exoskeleton virtually connected to one another, enabling bidirectional physical interaction.