My projects span from the micro-scale to the macro-scale. On the microrobotics side, I have microrobot swarms composed of 300-micron diameter magnetic disks in a fluid that can be actuated with an oscillating magnetic field. Our goal is to eventually use future versions of these microrobot swarms for biomedical applications, where groups of microrobots could reconfigure to move through complex environments like the human body to deliver drugs or perform small-scale operations in hard-to-operate regions. Depending on the magnetic field signal, we can tune how each microrobot rotates or oscillates about its individual center, which changes its fluid-based interactions with its surrounding neighbors. We can tune the magnetic field signal to switch between different collective behaviors so that a large number of microrobots can traverse through a maze-like environment, manipulate objects to rotate and translate them to desired orientations and positions, and to disperse throughout some environment. My group is developing methods to optimally control these microrobot swarms so that visual feedback can be used to automatically control the magnetic field signal to drive the collective to exhibit specific behaviors that will enable the group to execute a desired function.
On the macro-scale robotics side, I have developed self-reconfigurable modular robot swarms composed of groups of robots that can move about each other’s perimeters to reconfigure the collective’s shape. Robot swarms like these could be used in the future to create structures in hard-to-reach locations, like space or underwater, that could change shape depending on the surrounding environment’s conditions. My lab is working to develop self-reconfigurable robots that can reconfigure into complex, desired formations in a fully distributed manner while still communicating very little information between neighbors.
After finishing my undergrad in Mechanical Engineering at the University of Florida, I went to Cornell for my PhD to work with Prof. Kirstin Petersen in her Collective Embodied Intelligence lab. As a PhD student, I had the opportunity to work on several projects related to self-reconfigurable modular robots, soft robotics, microrobotics, and complex systems. I had the chance to make use of several external fellowships throughout graduate school, which allowed me to dive into research projects that I was very interested in and to learn diverse skills related to fabrication, design, optimization, and controls that I can apply to many different types of projects related to robot swarms at various length scales. After finishing my PhD, I did a postdoc at MIT in Prof. Daniela Rus’ lab, where I further developed some of the swarming models I had introduced as a graduate student and I started implementing those models on commercial and custom-built robots at the macro-scale. In January 2025, I started my Synergetic Adaptive Machinas lab in the Robotics department at the University of Michigan in Ann Arbor.
One of the most significant contributions that I would like to make is the development of swarming models that will find use in physical robotic systems at the micro-scale and the macro-scale. My objective is to use some of the abstract swarming models my lab is developing to inform us on how we need to design the physical bodies of robots (at various length scales) and their pairwise interactions with their neighbors to enable specific collective behaviors, whether that is for biomedical applications with our microrobot swarms or for structural reconfiguration purposes with our macro-scale robot swarms.
What excites me most is that this type of research gives me the opportunity to uncover simple rules that give rise to complex, intelligent behavior—especially in systems made up of many interacting parts. There’s something fascinating about how local decisions, constrained by limited information, can lead to strong and scalable collective intelligence. Data science gives us the tools to reverse-engineer these dynamics in nature and to engineer them in artificial systems like robot swarms. I especially like the challenge of working in settings where data is sparse, noisy, or decentralized, in essence, situations where traditional, centralized approaches break down. Using data-driven models to extract structure, infer hidden variables, or guide emergent behaviors under real-world constraints is both intellectually rich and practically meaningful; an area in which foundational questions meet impactful applications.