AME Seminar

Speaker: Yue Wang, USC

Talk Title: Embodied Intelligence for Space Exploration with Foundation Models

Abstract: Robotics has made remarkable strides, driven by advances in machine learning, optimal control, and hardware innovation. However, their applications to the space domains still face unique challenges: it is neither straightforward nor inherently scalable to train large machine learning models to enable these applications. To address this gap, our research endeavors to tackle these challenges through three principal directions: Simulation. Constructing photorealistic simulations that replicate space environments and enabling foundation model learning from synthetic or hybrid data sources. Perception. Leveraging geometric, semantic, and motional cues to develop data-efficient algorithms for robust scene perception and understanding in both simulated and real-world settings. Decision making. Integrating knowledge from foundation models (such as LLMs) into intelligent agents to enhance autonomous decision-making capabilities in novel and unknown environments. My primary aim is to bridge the gap between the theoretical underpinnings of AI and tangible advancements in space robotics, overcoming data limitations to push the boundaries of intelligent exploration at an accessible cost.

Biography: Yue Wang is an assistant professor at the computer science department and a faculty scientist at Nvidia Research. His lab is focusing on three major directions: 1) neural scene representations for robotics; 2) real-to-simulation-to-real transfer for robotics; 3) and robotic manipulation. He worked on 3D geometric deep learning during his PhD. His paper "Dynamic Graph CNN" has been widely adopted in 3D visual computing and beyond. He received the Powell Faculty Research Award, Toyota Young Faculty Researcher award, Nvidia Fellowship, the best paper award in geometric computing and graphics at the inaugural international congress of basic science, and the best paper nomination at the CVPR 2021 workshop on autonomous driving. He was also named the first place recipient of the William A. Martin Master’s Thesis Award for 2021. Yue received his bachelor from Zhejiang University, master from UCSD, and PhD from MIT. He has spent time at Nvidia Research, Google Research and Salesforce Research.

Host: AME Department

More Info: https://ame.usc.edu/seminars/

Webcast: https://usc.zoom.us/j/96060458816?pwd=8LmoG2q6vBCQubqqWpcizd2F1bxqsH.1

Location: James H. Zumberge Hall Of Science (ZHS) - 252

WebCast Link: https://usc.zoom.us/j/96060458816?pwd=8LmoG2q6vBCQubqqWpcizd2F1bxqsH.1

Audiences: Everyone Is Invited

Contact: Tessa Yao

Event Link: https://ame.usc.edu/seminars/