Title：Advancing Embodied Intelligence with Controllable Generative Models
Date：2024/12/11 14:20-15:30
Location：博理 201
Speakers: Prof. C. Karen Liu, Stanford University
Host: Prof. Yung-Yu Chuang
Abstract:
Embodied intelligence enables AI agents, such as humanoid robots and animated characters, to interact meaningfully with their environment. Recent advancements demonstrate the potential of learning embodied intelligence from human demonstrations or movements, enabling complex object manipulation and high-level command understanding. Generative models, particularly diffusion models, have emerged as a dominant choice due to their ability to manage the complexities of multi-modal embodied data comprising of corresponding observations and actions, despite ongoing challenges such as limited data availability, maintaining controllability, and adhering to physical constraints. This talk explores solutions to these challenges using diffusion models. I will introduce a number of different techniques to enhance controllability and enforce physical laws during training and inference, bridging gaps in achieving robust embodied intelligence.
Bio:
C. Karen Liu is a professor in the Computer Science Department at Stanford University. Liu's research interests are in computer graphics and robotics, including physics-based animation, character animation,optimal control, reinforcement learning, and computational biomechanics. 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. The algorithms and software developed in her lab have fostered interdisciplinary collaboration with researchers in robotics, computer graphics, mechanical engineering, biomechanics, neuroscience, and biology. Liu received a National Science Foundation CAREER Award, an Alfred P. Sloan Fellowship, and was named Young Innovators Under 35 by Technology Review. Liu also received the ACM SIGGRAPH Significant New Researcher Award for her contribution in the field of computer graphics. In 2021, Liu was inducted to ACM SIGGRAPH Academy.