Aditya Penumarti

Google Scholar 19 citations 2 h-index 0 i10-index as of Nov 2026

I am a Ph.D. candidate at the University of Florida in the Mechanical and Aerospace Engineering Department, where I study how robots can make good decisions when they can’t be sure where they are or what’s around them. My research focuses on planning under uncertainty in GPS-denied environments, such as underwater or indoor environments. The overarching theme is active perception: my algorithms treat sensing as active, allowing them to choose to gather the information a robot needs to stay localized. This includes belief-space planning, uncertainty-aware representations of the environment, and information-constrained planning that decides how much sensing is enough. The algorithms I design have been tested on underwater and ground robots with support from the Air Force Research Laboratory (AFRL).

I am advised by Prof. Jane Shin. I received my M.Sc from the University of Florida, working with Prof. Carl Crane and Prof. Michael Griffis. I received my B.Sc. from North Carolina State University.

I am deeply interested in teaching and mentoring. I co-developed an autonomous ground vehicle class at the University of Florida, built on 1/10 vehicle platforms, and I have mentored five undergraduate and master’s students.

Research Vision

To build robots that can be trusted in these settings, I develop autonomy frameworks in which uncertainty is explicit at every stage: in how the robot models its world, assesses the value of information, and makes decisions. Because the uncertainty is explicit, each decision is interpretable, whether the planner is classical or learned: it can be broken down into what the robot believed, the risk it accepted, and the information it expected to gain.

Much of my work to date uses magnetic navigation as a model problem. Earth’s crustal field is passive and hard to jam, which makes it attractive when GPS is denied, but it is weak and sparsely mapped, so a robot relying on it cannot ignore uncertainty. I have also built and fielded the systems these ideas run on, including the software stack for an underwater vehicle, a gesture-driven diver-following controller, research drones, and an Isaac Sim digital twin.

See more on the Research page.