Sim-to-Real: From Skilled Virtual Agents to Real-World Robots

Yeuhi Abe is a Senior Roboticist at Boston Dynamics where he is primarily focused on developing exciting, new behaviors for the Atlas humanoid robot. Prior to that he received his PhD on physics-based methods for animating humanoid characters at MIT.

Jie joined the Brain team at Google in 2016, working on deep learning, reinforcement learning and robotics. Before that, he was a Member of Technical Staff at the Computational Imaging group at Lytro, working on computer vision, SLAM, light field technology and image processing. Jie got his PhD in computer science from Georgia Tech in 2015, under the supervision of Greg Turk and Karen Liu.

Konstantinos is a Senior Research Scientist at DeepMind, where he is working on computer vision, robotics and machine learning. Before DeepMind, he was at Google Brain and Robotics at Google. Konstantinos received his PhD in Computer Science from Imperial College London in 2014. His focus has since been on simulation-to-reality transfer for vision and robotic learning problems.

Gavriel State is a Senior Director for Simulation and AI at NVIDIA, based in Toronto, where he leads efforts involving applications of AI technology to simulation and vice versa. His current work includes physics based simulation of human motion, as well as research into minimizing the domain gap between synthetic and real data for perception with neural networks. Previously, Gavriel founded TransGaming Inc, and spent 15 years focused on games and rendering technologies.

Carmel is the Clarence H. Adamson Associate Professor of Mechanical Engineering at Carnegie Mellon, where he leads the Soft Machines Lab. His interest is in developing novel materials architectures, fabrication methods, and computational tools that enable robots and machines to behave like soft biological organisms and be safe for contact with humans. Carmel is also the co-founder of several start-ups that are commercializing lab inventions related to wearable health monitoring, robot actuation, and conductive elastomers.

Karen's research interests span computer animation, robotics, reinforcement learning, physics simulation, optimal control, and computational biomechanics. Together with her colleagues, she 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. Karen received a National Science Foundation CAREER Award, an Alfred P. Sloan Fellowship, and was named Young Innovators Under 35 by Technology Review. In 2012, she received the ACM SIGGRAPH Significant New Researcher Award for her contribution in the field of computer graphics.