My name is Mark (Moonyoung) Lee.
I am currently a first year PhD at Carnegie Mellon University's Robotics Institute. I am in Intelligent Autonomous Manipulation group, co-advised by Prof. Oliver Kroemer and Prof. George Kantor.
I previously worked at KAIST Hubo Lab, the winning team of DARPA Robotics Challenge, and at iRobot, pioneer in consumer robotics. I graduated at Cornell University (B.S & M.Eng).
My research focuses on closing the perception-action loop through robot learning. I believe improving robot's ability to self-reason about interacting with the world will transform how robots are integrated in our society today.
"Dynamic Humanoid Locomotion over Uneven Terrain with Streamlined Perception-Control Pipeline" IEEE Int. Conference on Robotics and Automation (ICRA), 2021 (under review)
M. Lee, Y. Kwon, S. Lee, J. Choe, J. Park, H. Jeong, Y. Heo, M. Kim, S. Jo, S.E. Yoon, J.H. Oh
Bipedal locomotion poses an integrated challenge for the robot to perceive, plan, and control its movements, especially with dynamic motions where the robot may have to adapt its swing-leg trajectory onthe-fly in order to safely place its foot on the uneven terrain. In this paper we present an efficient geometric footstep planner and the corresponding walking controller that enables a humanoid robot to dynamically walk across uneven terrain at speeds up to 0.3 m/s. As dynamic locomotion, we refer first to the continuous walking motion without stopping, and second to the on-the-fly replanning of the landing footstep position in middle of the swing phase during the robot gait cycle. This is mainly achieved through the streamlined integration between an efficient sampling-based planner and robust walking controller.
"Joint Space Position/Torque Hybrid Control of the Quadruped Robot for Locomotion and Push Reaction" IEEE Int. Conference on Robotics and Automation (ICRA), 2020
O. Sim, H. Jeong, J. Oh, M. Lee, K.K. Lee, H. Park, J.H Oh
This paper proposes a novel algorithm for joint space position/torque hybrid control of a mammal-type quadruped robot.With this control algorithm, the robot demonstrated both dynamic locomotion and push recovery abilities
without torque control in the ab/ad joints. Based on the tipping and slipping condition of the legged robot, we showed that reaction to a typical push in the horizontal direction does not require full contact-force-control in the frontal plane. Furthermore, the joint configuration of the quadruped robot makes position/ torque hybrid control in Cartesian space directly applicable to joint space hybrid control. We conducted experiments on our legged robot platform to verify the algorithm performance. With this approach, the robot displayed stability while walking and reacting to external push disturbances.
"Fast Perception, Planning, and Execution for a Robotic Butler:
Wheeled Humanoid M-Hubo” IEEE Int. Conf. on Intelligent Robots and Systems (IROS), 2019
M. Lee, Y. Heo, J. Park, H. Yang, P. Benz, H. Jang, H. Park, I. Kweon, J.H. Oh
In order to assist with daily tasks such as fetching a beverage, a service robot must be able to perceive its environment and generate corresponding motion trajectories. This becomes a challenging and computationally complex problem when the environment is unknown and thus the path planner must sample numerous trajectories that often are sub-optimal, extending the execution time. To address this issue, we propose a unique strategy of integrating a 3D object detection pipeline with a kinematically optimal manipulation planner to significantly increase speed performance at runtime. In addition, we develop a new robotic butler system for a wheeled humanoid that is capable of fetching requested objects at 24% of the speed a human needs to fulfill the same task. The proposed system was evaluated and demonstrated in a real-world environment setup as well as in public exhibition.
"Motion Generation Interface of ROS to PODO Software Framework
for Wheeled Humanoid Robot" IEEE Int. Conf. on Advanced Robotics (ICAR), 2019
M. Lee, Y. Heo, S. Cho, H. Park, J.H. Oh
This paper discusses the development of robot motion generation interface between a real-time software architecture and a non-real-time robot operating system. In order for robots to execute intelligent manipulation or navigation, close integration of high-level perception and low-level control is required. However, many available open-source perception modules are developed in ROS, which operates on Linux OS that don’t guarantee RT performance. This can lead to non-deterministic responses and stability problems that can adversely affect robot control. As a result, many robotic systems devote RTOS for low-level motion control. As such, we present a new motion generation interface between ROS and PODO that enables users to generate motion trajectories through standard ROS messages while leveraging a real-time motion controller.
“Building a Robotic Candy Sorter” Circuit Cellar Graphics & Vision, #329 Dec. 2017: 10-16
P. Slater, M. Lee
The purpose of the Robotic Candy Sorter project was to implement a 3 degree of freedom robotic arm and vision system that can detect and sort candy by color. This was accomplished by building an integrated system that leverages high-level (Raspberry Pi) and low-level (PIC32) processing to accomplish an ambitious task. The Raspberry Pi (RPi) handled the image processing and sorting algorithms, while the PIC32 microcontroller (uC) maintained control of the motors by solving the inverse kinematics (IK).
Hubo Lab (Lab: 2017-2020)
inTouch (startup: 2014-2015)
Projects (School: 2015)
inTouch (startup: 2014-2015)
Projects (School: 2015)