Daehyung Park is a Robotics Ph.D. student at the Robotics and Intelligent Machines Center in the Georgia Institute of Technology. He is working with Dr. Charlie Kemp in the HealthcareRobotics Laboratory. His research interests include control, motion planning, and machine learning for autonomous manipulation. He is currently researching a data-driven behavior decision methodology for manipulations in clutter.

He has studied and experienced in a broad range of robotics in both academic and industrial areas. He received his B.S. at Osaka University in Japan, where he researched a turning pattern generation for a humanoid robot, HRP-2, in Dr. Arai Tatsuo’s Arai laboratory. He received M.S. at University of Southern California, where he researched machine learning and obstacle avoidance methods with various manipulators in Dr. Stefan Schaal’s Computational Learning andMotor Control laboratory. After earning his master’s degree, he worked as a robot engineer at the Mechatronics Center of Samsung Electronics Inc. He researched and developed motion control methodologies for versatile industrial robots such as multi-DoF industrial manipulators, LCD transfer robots (LTR), and wafer transfer robots (WTR).

He is eager to achieve highly reliable and autonomous motion control methodology in near future, based on his past and current experience in robotics. This homepage serves to introduce and check what is my goal, what I have achieved, and what I am doing now for the goal !! 


Interests  -  Machine Learning, Planning, Control, haptic manipulation
E-mail  -

Education

2012.8~Present   Robotics Ph.D student, College of Computing

  Georgia Institute of Technology, GA, USA

  Advisor: Dr. Charles C Kemp

2006.9~2008.5   M.S., Computer Science Intelligent Robotics

  University of Southern California, CA, USA

  Advisor: Prof. Stefan Schaal

2006.4~2006.6   Master Course, Adaptive Robotics in Engineering

  Osaka University, Osaka, JAPAN

  Advisor: Prof. Minoru Asada

2002.4~2006.3   B.S., System Science in Engineering Science

  Osaka University, Osaka, JAPAN

  Advisor: Prof. Tatsuo Arai


Research & Work Experience

2012.8~Present   Graduate Research Assistant, HRL

  Georgia Institute of Technology, GA, USA

  Task: Machine learning, manipulation, and control
2008.8~2012.7   Robot Engineer, Mech Center

  Samsung Electronics Inc., Suwon, KOREA

  Task: Motion Planning, Servo Control w/ robot

2007.1~2008.5   Graduate Research Assistant, CLMC Lab

  University of Southern California, CA, USA

  Task: Motor Primitives, Obstacle Avoidance

2006.4~2006.6   Research Assistant, Asada & Hosoda Lab

  Osaka University, Osaka, JAPAN

  Task: Motion Planning, Controller Design
          w/ Pneumatic Muscle Control & Mini Soccer Robot

2005.4~2006.3   Research Assistant, Arai Lab

  Osaka University, Osaka, JAPAN

  Task: Motion planning, Humanoid

2004.4~2004.10   Research Student, Ushio Lab

  Osaka University, Osaka, JAPAN

  Performed Problem-Based Learning course (PBL)

  Task: Designed Free Ranging Mobile Robot


Publications

[Articles]

[1] H. Hoffmann, P. Pastor, D. Park, and S. Schaal. “Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance”, IEEE International Conference on Robotics and Automation, 2009. [PDF]

[2] D. Park, H. Hoffmann, P. Pastor, and S. Schaal. “Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields”, IEEE-RAS International Conference on Humanoid Robots (Humanoids 2008) [PDF]

[3] D. Park, H. Hoffmann, and S. Schaal. “Combining dynamic movement primitives and potential fields for online obstacle avoidance”, Adaptive Motion of Animals and Machines (AMAM08), Cleveland, Ohio, 2008 [PDF]

[4] D. Park, A. Kapusta, Y. Kim, and C. Kemp. “Learning to Reach into the Unknown: Selecting an Initial Condition When Reaching in Clutter”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS2014) [Accepted]

[Patents]

[1] D. Park, K. Lee, C. An, and Y. Hong. “Teaching and playback method based on control of redundancy resolution for robot and computer-readable medium controlling the same.” US Patent 12 923 650, Apr. 21, 2011. [PDF]

[2] K. Lee, Y. Hong, C. An, and D. Park. “Motor control apparatus and motor control method thereof.” US Patent 13 009 961, Jan. 20, 2011. [PDF]


Awards

2008.5   Academic Achievement Award, USC, USA
2008.1~2008.5   Teaching Assistantship, CS545 Robotics, USC, USA
2007.1~2008.12   Graduate Research Assistantship, CLMC Lab, USC, USA
2001.10~2006.3   National full scholarship of Japan & Korea Governments


Skills

  • Software
    • Linux, OS X, Windows
    • Visual C++, #NET
    • Python, MATLAB, C, C++, Java
  • Hardware
    • Micro processor (8051, PIC, H8), Circuit design, Motor control
  • Language
    • Korean (native), Japanese (semi-native), English (fluent)

Current Research & Project

Data-driven Behavior Decision

  • Learning Initial Condition (LIC)

Exploration with Touch

  • Cost-based Rapidly exploring Randomized Tree
  • Environment recognition with tactile sensing

Past Research & Project

At Samsung, he worked on a variety of industrial robot developments. he was charge of from basic design such as kinematics & dynamics to path planning. Followings briefly show project details.
  To avoid confidential company information, this section only includes general keywords and web found pictures.

Industrial 6 DoF Manipulator Development

  • Kinematics & Dynamics
  • Singularity Avoidance Control
  • Motor Overdrive Control
  • Multi Gain System

Auto Servo Gain Tuning

  • Iterative Learning Control (ILC) 
  • Online Gain Optimization

Auto Teaching & Apparatus

  • Teaching Automation 
  • Cost Effective Teaching Tool Development

Industrial Transfer Robot Development

  • Wafer & LCD Transfer Robot Development 
  • Torque Optimization
  • Vibration Analysis

Dual Manipulation with 7-DoF Redundant Arms [08'~09']

    • Kinematics & Inverse Kinematics Dev. w/ Analytical & Numerical Solutions
    • Redundancy Resolution Control with Modified Arm Angle
    • Impedance Control
    • Collaboration Control
    • Collision Detection
       
 

In master course, he had focused on supervised learning. he joined to Prof. Stefan Schaal's CLMC Lab. In there, he
researched 'Dynamic Movement Primitives (DMPs)' with several types of robots.

Dynamic Movement Primitives with Obstacle Avoidance [07'~08']

  • Supervised Learning (Dynamic Movement Primitives)
  • Obstacle Avoidance by Potential Field Approach
  • 7-DoF Redudant Manipulator
  • Null-Space Elbow Avoidance

Manipulation for Rover Robot  & DSC System [07'~08']

  • PhanTom 3-DoF Robot Arm
  • Dynamic Movement Primitives (DMPs)
  • DSC System

 In bachelor course, he did undergraduate thesis research with a humanoid robot HRP-2 in Arai Lab. 

 Turning Pattern Generation using Spin Momentum on HRP2 [05'~06']

    • Resolved Momentum Control
    • Running Pattern Generation (Squat) 
    • Slip Observer (Spin)  

 After bachelor course, he studied many kinds of robots:

Control System for Pneumatic Humanoid [06']

  • Mckibben (Artificial Muscle)
  • PWM Pneumatic Control
  • H4 Controller
     

Eco-Be! League for Robocup [06']

    • Mini Soccer-Robot 
    • Path Planning
    • Robocup Kitakyushu Japan 2006.5.3 ~2006.5.6