I have conducted fundamental research in many different areas including autonomous guidance, navigation, and control of air, land, and marine vehicles, as well as problems for humanoid robots manipulating object-cluttered environment. My research focuses on improving performance of robotic systems with supervised autonomy through the application of planning, feedback control, integrated sensing systems.

The language-based interaction of the human-robot team is the core focus of my recent work. I’m trying to develop techniques which enable human operators to interact with robots at a highly-intuitive task-level, where the human has full strategic control and commands tasks or objectives, and the robot autonomously performs lower-level tasks such as path/motion planning and precision task execution, while communicating with each other at task/object-level.

This tightly-coupled, supervised autonomy allows human-robot systems to take advantage of the relative strengths of each member of the team : humans in reasoning, interpretation, and perception, and robots in precise control, efficiency, and repeatability. At all times the human is capable of stepping down to a lower level of control, if the robot finds a task which it is not intelligent enough to complete, which makes systems very robust to unknown or unexpected situations.


Recent Projects

 

Object-Level Communication for Human-Robot Motion Generation

This research will enable human operators to command the DRC-Hubo robot to complete object directed tasks (debris clearing, valve turning, and navigation among obstacles) through a multi-layered teleoperation interface that allows them to provide input to both the high-level HTN action planner and the low-level CBiRRT motion planner.

[1] Michael Grey, Sungmoon Joo, and Matt Zucker, “Planning Heavy Lifts for Humanoid Robots,” 2014 IEEE/RAS International Conference on Humanoid Robots, Madrid, Spain, Nov. 2014.

[2] Sungmoon Joo, “A Unifying Linguistic Formalism for Teleoperation of Semi-Autonomous Robots,” 2014 IEEE/RAS International Conference on Intelligent Robots and Systems (IROS), Workshop on AI and Robotics, Chicago, USA, Sep. 2014.

DARPA Robotics Challenge (DRC)

The DRC is a competition of robot systems and software teams vying to develop robots capable of assisting humans in responding to natural and man-made disasters. Participating teams, representing some of the most advanced robotics research and development organizations in the world, are collaborating and innovating on a very short timeline to develop the hardware, software, sensors, and human-machine control interfaces that will enable their robots to complete a series of challenge tasks selected by DARPA for their relevance to disaster response.

[1] Matt Zucker, Sungmoon Joo, Michael Grey, Christopher Rasmussen, Michael Stilman, and Aaron Bobick, “A General-purpose System for Teleoperation of the DRC-HUBO Humanoid Robot,” Journal of Field Robotics, to appear(accepted).

DART-GRIP

GRIP(Graphical Robot Interface Platform) is a graphical user interface for DART (Dynamic Animation and Robotics Toolkit). DART is a collaborative, cross-platform, open source library created by the Georgia Tech Graphics Lab and Humanoid Robotics Lab. I'm one of active collaborators of GRIP development.


Past Projects

  1. Bullet Stochastic Optimal Control

    • Jinhwan Kim, Sungmoon Joo, “An Optimal Control Formulation for Dual Control Problems,” Proc. of 11th International Conference on Control, Automation and Systems (ICCAS), Gyeonggi-do, Korea, Nov. 2011.

    • Sungmoon Joo, “SLAM-based nonlinear optimal control approach to robot navigation with limited resources," Ph.D. Thesis, Stanford University, Mar. 2010.

    • Eric. W. Frew, Jack Langelan, and Sungmoon Joo, “Adaptive Receding Horizon Control for Vision-based Navigation of Small Unmanned Aircraft,” Proc. of American Control Conference (ACC), Minneapolis, USA, Jun. 2006.

    Bullet Vision-augmented INU & Polymorphic Control Reconfiguration

    • Sungmoon Joo, Corey Ippolito, Khalid Al-Ali, and Yoo Hsiu Yeh, “Vision Aided Inertial Navigation with Measurement Delay for Fixed-Wing Unmanned Aerial Vehicle Landing,” Proc. of IEEE Aerospace Conference, Big Sky, USA, Mar. 2008.

    • Corey Ippolito, Sungmoon Joo, Khalid Al-Ali, and Yoo Hsiu Yeh, “Fligh Testing Polymorphic Control Reconfiguration in an Autonomous UAV with UGV Collaboration,” Proc. of IEEE Aerospace Conference, Big Sky, USA, Mar. 2008.

    • Sungmoon Joo, Corey Ippolito, Khalid Al-Ali, and Yoo Hsiu Yeh, “Towards Autonomous Fixed-wing UAV Landing: A Vision Aided INS under Sensor Reconfiguration Scenario,” Proc. of 17th Annual IFAC World Congress, Seoul, Korea, Jul. 2008.

    BulletAutomated Highway System

    • Sungmoon Joo, X. Y. Lu, and J. K. Hedrick, “Longitudinal Maneuver Design in Coordination Layer for Automated Highway System,” Proc. of American Control Conference, Denver, USA, Jun. 2003.

    BulletNaval Architecture & Ocean Engineering

    • Dong-Hwan Lee, Sungmoon Joo, and Hang-Soon Choi, “Control Performance of a Turret-Moored Vessel Assisted by Dynamic Positioning System,” Proc. of IFAC Conference on Control Application in Marine Systems (CAMS), Kukuoka, Japan, Oct. 1998.

    • Dong-Yeon Lee, Sungmoon Joo, and Hang-Soon Choi, “An Experimental Study on Breaking Waves,” Journal of Korean Society of Coastal and Ocean Engineers, Vol. 8, No. 1, pp. 37~43, 1996.