I am a robotics enthusiast with a deep interest in building systems that combine mathematical rigor with real-world robustness. I completed dual master’s degrees at the University of Michigan in Mechanical and Automotive Engineering, where I focused on statistics, control, and optimization.

Prior to graduate school, I worked as a C++ software developer at Dassault Systèmes and Altair Engineering for 2 years. I worked with various scripting languages, managed large codebases, and used build tools. These experiences continue to support my current focus on implementation-driven robotics research.

I am also deeply enthusiastic about mathematics. Much of my current work in control and robotics is influenced by foundational ideas from statistics, real analysis, and functional analysis. These are abstract and rigorous areas, and I actively study and solve problems in them to strengthen both my theoretical foundation and practical contributions to robotics.

I am interested in developing autonomous robotic systems that can operate reliably in uncertain, dynamic environments by tightly integrating probabilistic reasoning with control. My goal is to build systems that can infer, adapt, and act with confidence, even when models are imperfect or information is incomplete.

I am currently exploring the following directions, with the intent to implement and deepen my expertise over time:

• Joint Estimation of State and Dynamics: Using Bayesian filtering techniques (e.g., EKF, UKF, Particle Filters) to estimate both the internal state and unknown system parameters of robots. This enables real-time model adaptation and robust behavior under uncertainty.
• Optimization- and Learning-Based Control: Designing control strategies that combine model-based optimization (e.g., MPC, convex formulations) with data-driven learning to ensure safe, adaptive, and efficient control in complex robotic systems.
• Uncertainty Quantification and Decision-Making under Uncertainty: Applying Monte Carlo simulation and probabilistic modeling to assess risk, quantify uncertainty, and enable decision-making that is robust to noise, disturbances, and incomplete knowledge.

These interests are driven by a desire to build robotic systems that are safe, adaptive, and grounded in strong mathematical principles. I aim to design systems capable of estimating, learning, and acting under uncertainty.

• 
  University of Michigan, Ann Arbor
  M.S. Mechanical Engineering (Robotics), Jan 2023 – Apr 2024
• 
  University of Michigan, Ann Arbor
  M.S. Automotive Engineering, Aug 2021 – Dec 2022
• 
  National Institute of Technology, Rourkela, India
  B.Tech. Mechanical Engineering, Jul 2015 – May 2019

Focus Areas: Machine Learning · Bayesian Inference · Convex Optimization · Control Theory · Statistical Estimation · Stochastic Processes · Nonlinear Dynamics