Structured and Adaptive Real2Sim2Real RL for Humanoid Whole-Body Control and Loco-Manipulation - Robotics Institute Carnegie Mellon University

Faculty Events

May

16
Fri
Guanya Shi Assistant Professor Robotics Institute,
Carnegie Mellon University
Friday, May 16
12:00 pm to 1:00 pm
Newell-Simon Hall 4305
Zoom Link Button
Structured and Adaptive Real2Sim2Real RL for Humanoid Whole-Body Control and Loco-Manipulation

Abstract: Humanoid robots offer two unparalleled advantages in general-purpose embodied intelligence. First, humanoids are built as generalist robots that can potentially do all the tasks humans can do in complex environments. Second, the embodiment alignment between humans and humanoids allows for the seamless integration of human cognitive skills with versatile humanoid capabilities.
To fully unleash the capability of humanoids, we need to develop robust and precise whole-body control methods with agility. In this talk, I will present recent works to achieve this goal. Key methods include sim2real RL, structured RL, real2sim, and combining optimal control with model-free RL.
More details on the presented works are available on the CMU LeCAR Lab website: https://lecar-lab.github.io/

Bio: Guanya Shi is an Assistant Professor at the Robotics Institute at Carnegie Mellon University, leading the Learning and Control for Agile Robotics (LeCAR) Lab. He completed his Ph.D. in Control and Dynamical Systems in 2022 from Caltech. Before joining CMU, he was a postdoctoral scholar at the University of Washington. He is broadly interested in the intersection of machine learning and control, spanning the entire spectrum from theory and foundation, algorithm design, to real-world agile robotics. Guanya was the recipient of several awards, including the Outstanding Student Paper Award Finalist at RSS 2024 and the Best Paper Award Finalist at ICRA 2025. His research has been featured by major media outlets such as CNN, Reuters, and IEEE Spectrum. Guanya is an Associate Editor of IEEE Robotics and Automation Letters.