Dong Ho Lee

Deep RL Researcher at Strategic Aerospace Intiative (SAI).


Work Experience

Strategic Aerospace Initiative (SAI), KAIST

Deep RL Researcher, 2022 to present

  • Project (ongoing): Routing Problems Considering Value System for Exploration Missions (NRF KR grant: 2020R1A2C1005037)
  • Project (ongoing): Data-driven Flow Modeling Research (DAPA grant: UD200046CD)

Strategic Aerospace Initiative (SAI), KAIST

MS Student, 2020 to 2022

  • Project (ongoing): Routing Problems Considering Value System for Exploration Missions (NRF KR grant: 2020R1A2C1005037)
    • development of a data-efficient on-policy learning algorithm to train a Transformer-based policy network for solving routing problems via deep reinforcement learning
  • Project (ongoing): Data-Driven Flow Modeling Research (DAPA grant: UD200046CD)
    • development of a deep-learning model for efficient prediction of aerodynamic coefficients under extreme flow conditions

Aerospace Technology Research Institute, ADD

Research Officer (First Lieutenant), 2017 to 2020

  • Project: Autonomous navigation and Mission Management Technology
    • development of mission planning algorithm for UAV operation in dynamic environment
    • formulation of UAV planning problem as MILP for Gurobi solver
    • design of a fast online planning using genetic algorithm

Unmanned Systems Research Group (USRG), KAIST

Undergraduate Research Intern, 2015 to 2016

  • Project: Development of Modular Drone with Self-Configuration
    • design of a 3D-printable modular drone that can configure itself before coordinated flight


Teaching Experience

  • AE201 Introductory Flight Project (Spring 2021)
  • HSS024 Advanced English Writing (2015-2016)
  • HSS025 Advanced English Reading (2015-2016)
  • LG-KAIST Science Camp (Summer 2015)
  • Academic English Camp (2014-2015)


  • ME460 Automatic Control
  • AE450 Flight Dynamics and Control
  • ME500 Mathematical Methods in Mechanical Engineering
  • CC511 Probability and Statistics
  • IE539 Convex Optimization
  • AE552 Advanced Linear Stability and Control
  • IE540 Dynamic Programming and Reinforcement Learning
  • AE551 Introduction to Optimal Control
  • AE501 Multidisciplinary Design Optimization for Aerospace Systems
  • AI504 Programming for AI