Zoom: https://illinois.zoom.us/j/86238233298?pwd=Y29EWXRPOWtiZ09DczRYMXJZK3JRUT09
Title: Three Pillars for Generalizable and Interpretable Embodied AI
Abstract: Embodied AI as an emerging research topic has been studied in various visuomotor tasks such as indoor navigation and autonomous driving. Most embodied AI studies are conducted in fixed simulation environments, where the generalizability and safety of the autonomous agents in unseen complex scenes remain questionable. In this talk, I will introduce the research work in my lab for building three pillars to support generalizable embodied AI for machine autonomy: training data/environment, representation, and learning pipeline. First, I will introduce our effort in building the MetaDrive driving simulator by incorporating the capability of importing real-world scenarios and learning to generate novel ones. Then I will talk about learning generalizable representations for decision-making from hours of uncurated YouTube driving videos. Finally, I will discuss how our work on Human-in-the-loop learning brings safe training and inference for human-AI shared control.
Bio: Bolei Zhou is an Assistant Professor in the Computer Science Department at the University of California, Los Angeles (UCLA). He earned his Ph.D. from MIT in 2018. He has been a faculty member at The Chinese University of Hong Kong (CUHK) for the past 3 years. His research interest lies at the intersection of computer vision and machine autonomy, focusing on enabling interpretable and trustworthy human-AI interaction. He has developed many widely used interpretation methods such as CAM and Network Dissection, as well as computer vision benchmarks Places and ADE20K. He has been area chair for CVPR, ECCV, ICCV, and AAAI. He received MIT Tech Review's Innovators under 35 in Asia-Pacific Award. More about his research is at https://boleizhou.github.io/.
