Home

My research interests span computer animation, robotics, reinforcement learning, physics simulation, optimal control, and computational biomechanics. The goal of our lab is to recreate coordinated voluntary animal movements in digital world and on robotic platforms. In particular, we will focus on holistic motor behaviors that involve fusing multiple modalities of perception to produce coordinated, balanced, and precise whole-body movements to interact with the world. We are interested in the functionality of motor skills, as well as how they are learned or acquired. My colleagues and I developed computational approaches to modeling realistic and natural human movements, learning complex control policies for humanoids and assistive robots, and advancing fundamental numerical simulation and optimal control algorithms. I received a National Science Foundation CAREER Award, an Alfred P. Sloan Fellowship, and was named Young Innovators Under 35 by Technology Review. In 2012, I received the ACM SIGGRAPH Significant New Researcher Award for my contribution in the field of computer graphics. I am the Technical Papers Chair for SIGGRAPH Asia 2019.

I am looking for PhD students interested in robotics and/or computer animation to join my lab. I am particular interested in students who have strong math background and programming experiences in optimal control or reinforcement learning.

You might be looking for...

•DART is an open-source multi-body physics simulator widely used for robotics and computer graphics applications. It is one of the supported physics engines by Gazebo.
•DartEnv is a fork from OpenAI Gym compatible with rllab and baselines libraries. It supports DART as one of the physics engines to simulate 3D dynamic learning tasks.
•Robotic Assistance with Dressing s a NSF-funded project for developing assistive robots to put clothes on people in need.
•A short tutorial on multibody dynamics.
•A short tutorial on formulating contact constraints for multibody systems.
•My PhD thesis.

Research

Learning a Control Policy for Fall Prevention on an Assistive Walking Device, Visak CV Kumar, Sehoon Ha, Gregory Sawicki, C. Karen Liu.

[arXiv] [Video] [Code]

Assistive Gym: A Physics Simulation Framework for Assistive Robotics, Zackory Erickson, Vamsee Gangaram, Ariel Kapusta, C. Karen Liu, and Charles C. Kemp.

[arXiv] [Video] [Code]

Synthesis of Biologically Realistic Human Motion Using Joint Torque Actuation, Yifeng Jiang, Tom Wouwe, Friedl De Groote and C. Karen Liu. in Transactions on Graphics (SIGGRAPH), 2019

[arXiv] [Video] [Code]

Personalized collaborative plans for robot-assisted dressing via optimization and simulation, Ariel Kapusta, Zackory Erickson, Henry M. Clever, Wenhao Yu, C. Karen Liu, Greg Turk, Charles C. Kemp, Autonomous Robots, 2019.

[Paper] [Video] [Code]

Sim-to-Real Transfer for Biped Locomotion, Wenhao Yu, Visak CV Kumar, Greg Turk and C. Karen Liu, in IEEE/RSJ International Conference on
Intelligent Robots and Systems (IROS), 2019

[arXiv] [Video] [Code]

Policy Transfer with Strategy Optimization, Wenhao Yu, C. Karen Liu, Greg Turk, International Conference on Learning Representations (ICLR), 2019.

[arXiv] [Video] [Code]

Multidimensional Capacitive Sensing for Robot-Assisted Dressing and Bathing, Zackory Erickson, Henry M. Clever, Vamsee Gangaram, Greg Turk, C. Karen Liu, and Charles C. Kemp, International Conference on Rehabilitation Robotics (ICORR), 2019.

[arXiv] [Video] [Code]

Data-Augmented Contact Model for Rigid Body Simulation, Yifeng Jiang, Jiazheng Sun, and C. Karen Liu

[arXiv] [Video] [Code]

Expanding Motor Skills through Relay Neural Networks, Visak C.V. Kumar, Sehoon Ha, and C. Karen Liu, in Conference on Robot Learning (CoRL), 2018

[PDF] [Video] [Code]

Learning to Dress: Synthesizing Human Dressing Motion via Deep Reinforcement Learning, Alex Clegg, Wenhao Yu, Jie Tan, C. Karen Liu and Greg Turk, in Transactions on Graphics (SIGGRAPH Asia), 2018

[PDF] [Video] [Code]

Learning Symmetric and Low-Energy Locomotion , Wenhao Yu, Greg Turk, and C. Karen Liu in Transactions on Graphics (SIGGRAPH), 2018

[PDF] [Video] [Code]

GRSI Approved

Data-Driven Approach to Simulating Realistic Human Joint Constraints, Yifeng Jiang and C. Karen Liu in IEEE International Conference on Robotics and Automation (ICRA), 2018

[arXiv] [Video] [Code]

Deep Haptic Model Predictive Control for Robot-Assisted Dressing, Zackory Erickson, Henry M. Clever, Greg Turk, C. Karen Liu, and Charles C. Kemp in IEEE International Conference on Robotics and Automation (ICRA), 2018

[arXiv] [Video]

Stair Negotiation Made Easier Using Novel Interactive Energy-Recycling Assistive Stairs, Yun Seong Song, Sehoon Ha, Hsiang Hsu, Lena H. Ting, and C. Karen Liu, in PLOS ONE, 2017