静5前沿讲座 | Deploying Intelligent Autonomy at a Large Scale

Deploying Intelligent Autonomy at a Large Scale – Generalizability, Safety, Embodiment

报告人

Prof. Ding Zhao

Department of Mechanical Engineering

Carnegie Mellon University

时间

2023年12月6日  星期三 15:00

地点

静园五院204室

Host

董豪 助理教授

 Abstract

As AI becomes more integrated into physical autonomy, it presents a dual spectrum of opportunities and risks. In this talk, I will introduce our efforts in deploying trustworthy intelligent autonomy at a large scale for vital civil usage such as self-driving cars, assistant robots, and autonomous surgery. During the deployment and transition, training data often exhibit significant imbalance, multi-modal complexity, and nonstationarity. I will initiate the discussion by analyzing ‘long-tailed’ problems with rare events and their connection to safety evaluation and safe reinforcement learning. I will then discuss how modeling multi-modal uncertainties as ‘tasks’ may enhance generalizability by learning across domains. To facilitate task delineation with high-dimensional inputs in vision and language, we have developed prompt-transformer-based structures for efficient adaptation and mitigation of catastrophic forgetting. In cases involving unknown-unknown tasks with severely limited data, we explore the potential of leveraging external knowledge from legislative sources, causal reasoning, and large language models. Lastly, we will expand intelligence development into the realm of system-level design space with meta physical robot morphologies, which may achieve generalizability and safety more effectively than relying solely on software solutions.

Biography

Ding Zhao is the Dean’s Early Career Fellow Associate Professor of Mechanical Engineering at Carnegie Mellon University. He directs the CMU Safe AI Lab, where his research focuses on large scale deployment of intelligent autonomy, encompassing generalizability, safety, physical embodiment, as well as considerations of privacy, equity, and sustainability. His work spans self-driving cars, assistant robots, autonomous surgical robots, and co-designing smart cities/buildings/infrastructure with autonomy. Ding Zhao has received numerous awards, including IEEE George N. Saridis Best Transactions Paper Award, National Science Foundation CAREER Award, MIT Technology Review 35 under 35 Award in China, Struminger Teaching Award, George Tallman Ladd Research Award, Ford University Collaboration Award, Qualcomm Innovation Award, Carnegie-Bosch Research Award, and many other industrial awards.

往 期 讲 座

• 静5前沿讲座回顾 | Dr. Alan Szepieniec介绍区块链中可扩展且隐私保护的存储技术

• 静5前沿讲座回顾 | 周俊杰教授谈多层网络上的协作博弈

• 静5前沿讲座回顾 | 区文浩教授谈密码学前沿进展及在区块链中的应用

• 静5前沿讲座回顾 | 黄志毅教授谈数据驱动的拍卖机制设计问题

—   版权声明  —

本微信公众号所有内容，由北京大学前沿计算研究中心微信自身创作、收集的文字、图片和音视频资料，版权属北京大学前沿计算研究中心微信所有；从公开渠道收集、整理及授权转载的文字、图片和音视频资料，版权属原作者。本公众号内容原作者如不愿意在本号刊登内容，请及时通知本号，予以删除。

点“阅读原文”查看海报