Experience

Engineering Development Group Intern | MathWorks

June 2022 - August 2022
Manager : Dr. Keith Martin

  • Worked on creating and refactoring tests for the PID simulink block.
  • Achieved a significant reduction in overall testing time and number of libraries used while maintaining a code coverage of 91.5%
  • Tested the control systems tuner app and fixed bugs
  • Integrated several MATLAB control systems tools within the Robot Operating System (ROS) framework for a UAV

Research Assistant | University of Michigan

September 2021 - Present
Research Supervisor : Dr. Vasileios Tzoumas

  • Research Intern at the Intelligent Robotics and Autonomy Lab
  • Researched on the applications of koopman operator to speed up learning and combinatorial optimization algorithms.
  • Working on the design of a safe active learning controller based on Koopman theory

Robotics Intern | ARTPARK

June 2021 - July 2021
Research Supervisor : Dr. Mukunda Bharatheesha

  • Worked on Coverage Path Planning for a robot performing janitorial tasks in a confined area
  • Worked on ROS Service creation for the Coverage Path Planning module
  • Worked with the MoveIt! package for cartesian planning and manipulation tasks such as pick-and-place

Research Intern | Indian Institute of Science

Jan 2021 - May 2021
Research Supervisor : Dr. Radhakant Padhi

  • Research Intern at the Integrated Control Guidance & Estimation Lab
  • Designed an optimal controller for effective radiotherapy using Model Predictive Static Programming (MPSP) for impulsive systems.
  • Designed a new unscented optimal control technique to deal with uncertainty in system parameters.
  • Applied the new technique on the Lotka-Volterra model.

Research Intern | PES University

June 2019 - July 2020
Research Supervisor : Dr. Koshy George

  • Research Intern at the Centre for Intelligent Systems.
  • Designed neural network controllers for the identification and control of multiple nonlinear dynamical systems using BPA and OSLA algorithms on MATLAB.
  • Applied various Reinforcement Learning algorithms to control an Inverted Pendulum and compared their relative performances.