top of page
This site was designed with the
.com
website builder. Create your website today.Start Now

Experience

May 2022 - Current

Visiting Researcher

University of Zurich, Robotics and Perception Group

Zurich, Switzerland

Figure1.jpg

  • Investigating methods for multi-player drone racing at the limit using reinforcement learning

  • Demonstration of competitive multi-robot systems on real hardware

  • Extensive simulation and modeling development of highly nonlinear and partially observable systems

February 2021  - August 2021

Visiting Researcher

University of Zurich, Robotics and Perception Group

Zurich, Switzerland

DataDriveMPC.png

  • Exploring various adaptive control methods to improve tracking performance of quadrotors at the limits of their operating capacity

  • Implementation of real time adaptive control synthesized with model predictive control methods

  • Extensive use of the ACADOS optimization framework for nonlinear optimal control problems

  • Flight testing on various quadcopter platforms, as well as simulator environments such as Rotors

Aug 2018 -Feb 2020

Controls/Robotics Engineer

Pratt and Miller Engineering

Wixom, MI

  • Developed planning and control algorithms for DoD robotic systems

  • Led C/C++ development on a team of 5 engineers 

  • Created simulation environments for validation and verification of software behavior

  • Architected control interfaces for high and low voltage systems.

  • Designed and implemented a Qt based GUI for soldiers and technicians to plan and execute trajectories via interactive waypoints

  • Lead C++ developer of stochastic optimal control based driver models for controlling racing vehicles at the limit.

  • Reduced simulation time by 10x by creating new control strategies which solved in real-time.

  • Advanced vehicle dynamics modeling including kinematics, tire models, and aerodynamics using a
    combination of first principles and machine learning approaches.

  • Provided simulation results to guide the vehicle development process of the C8.R racecar.

  • Developed distributed simulation workflows on AWS for 100x reduction
    in results turnaround.

c8r.jpg
tire.png

May 2019 - Aug 2019

Visiting Researcher

Georgia Institute of Technology

Atlanta, GA

autorally.jpg

  • Conducted meta-analysis of state of the art deterministic and stochastic Model Predictive Control algorithms for controlling a racing vehicle

  • Designed optimization frameworks using CVXGEN, Gurobi, and MOSEK

  • Implemented vehicle dynamics models and control algorithms in C++

  • Deployed software within the ROS ecosystem

  • Led the hardware/software integration on the AutoRally platform

Aug 2015 - Aug 2018

Undergraduate Researcher

Michigan Technological University

Houghton, MI

ARPA-E NEXTCAR:

  • Led a team of 5 graduate students modeling various vehicle subsystems using first principles and machine learning approaches

  • Setup data acquisition systems in Vector CANoe

  • Conducted in-vehicle experiments to validate predictive models

  • Developed optimal control algorithms for HVAC control in Hybrid Electric Vehicles

​

Building-to-Grid MPC:

  • Designed predictive models for batteries and photovoltaic cells in MATLAB

  • Implemented Model Predictive Control algorithms using the YALMIP toolbox for a 26% reduction in HVAC energy consumption for commercial buildings

Aug 2016 - Dec 2016

Robotics Intern

NASA

Cape Canaveral, FL

  • Developed bulk heat transfer models in MATLAB for fluid commodity tanks

  •  Reduced development time of heat transfer models by 80% relative to FLUENT model creation

  • Created CFD models for high pressure pneumatic systems

  • Optimized Orion capsule tank fill procedure for fluid commodities using MATLAB fluid models

  •  Programmed UR-10 robot to interface between lunar lander and rover to exchange fuel commodities via
    way-point based navigation and inverse kinematics

swampworks.jpg

Intern -  Aero, Vehicle Performance

General Motors

Detroit, MI

zl1.jpg

  • Developed weighted statistical analysis tool to account for changes in aerodynamic performance due to
    variation in front and rear ride heights and yaw angles

  • Developed CFD simulations to correlate with wind tunnel performance metrics

  • Researched the effects of anti-squat on tire loading and lap times using Lap Time Simulation software

  • Generated over $2,500,000 in savings per year across the SUV and truck lineup

  • Created DOEs to prove feasibility of new materials and designs

Summer '15, '16, '17

Education

2020 - 2022

University of Michigan

Coursework in optimal control, machine learning, and estimation.

Thesis on adaptive control and nonlinear model predictive control 

MS, Robotics

Ann Arbor, MI

2014 - 2018

Michigan Technological University

BS, Mechanical Engineering, Magna Cum Laude

Houghton, MI

Coursework in hybrid electric vehicles, robotics, and control theory. 3 years of undergraduate research in optimal control theory

Publications

  • Autonomous Drone Racing: A Survey

    • D. Hanover, A. Loquercio, L. Bauersfeld, A. Romero, R. Penicka, Y. Song, G. Cioffi, E. Kaufmann, D. Scaramuzza, Under Review, Transactions on Robotics, 2023

 

  • Performance, Precision, and Payloads: Adaptive Optimal Control for Quadrotors Under Uncertainty

    • D. Hanover, P. Foehn, S. Sun, E. Kaufmann, D. Scaramuzza, IEEE Robotics and Automation Letters and the International Conference on Robotics and Automation, 2022

​

  • Integrated cabin heating and powertrain thermal energy management for a connected hybrid electric vehicle

    • ​S. Hemmati, N. Doshi, D. Hanover, C. Morgan, M. Shahbakhti, Journal of Applied Energy, Volume 283,2021

​

  • Modeling of Thermal Dynamics of a Connected Hybrid Electric Vehicle for Integrated HVAC and Powertrain Optimal Operation 

    • N. Doshi, D. Hanover, S. Hemmati, C. Morgan, M. Shahbakhti., Dynamic Systems and Control Conference, 11 pages, 2019, Park City, UT, USA.

​

  • Enabling Demand Response Programs via Predictive Control of Building-to-Grid Systems Integrated with PV Panels and Energy Storage Systems

    • ​M. Razmara, G. R. Bharati, D. Hanover, M. Shahbakhti, S. Paudya, and R. D. Robinett III. American Control Conference, 6 pages, 2017, Seattle, WA, USA.

​

  • Building-to-grid Predictive Power Flow Control for Demand Response and Demand Flexibility Programs

    • ​M. Razmara, G. R. Bharati, D. Hanover, M. Shahbakhti, S. Paudya, and R. D. Robinett III. 37 pages, Journal of Applied Energy, 2017

​

Professional skillset

C/C++

Optimal Control

Reinforcement Learning

Machine Learning (TF, PyTorch)

ROS

Python

bottom of page