【直播】【青年科学半月谈】Reliable Learning and Control in Dynamic...

直播信息

报告题目

Reliable Learning and Control in Dynamic Environments: Towards Unified Theory and Learned Robotic Agility

报告人（单位）

Guanya Shi | California Institute of Technology

报告时间

2022年3月17日（周四）10:00

主办方

蔻享学术

直播二维码

报告人介绍

Guanya Shi is a Ph.D. candidate in the Department of Computing and Mathematical Sciences at the California Institute of Technology. He received a B.E. in mechanical engineering with a dual degree in economics from Tsinghua University in 2017. He was a deep learning research intern at NVIDIA in 2020. His research interests are centered around the intersection of machine learning and control theory, spanning the entire spectrum from theory and foundation, algorithm design, to real-world agile robotic control. Guanya was the recipient of several awards, including the Simoudis Discovery Prize from Caltech and the Rising Star in Data Science from the University of Chicago.

报告摘要

Recent breathtaking advances in machine learning beckon to their applications in a wide range of real-world autonomous systems. However, for safety-critical settings such as agile robotic control in hazardous environments, we must confront several key challenges before widespread deployment. Most importantly, the learning system must interact with the rest of the autonomous system (e.g., highly nonlinear and non-stationary dynamics) in a way that safeguards against catastrophic failures with formal guarantees. In addition, from both computational and statistical standpoints, the learning system must incorporate prior knowledge for efficiency and generalizability. In this talk, I will present progress towards establishing a unified framework that fundamentally connects learning and control. First, I motivate the benefit and necessity of such a unified framework by the Neural-Control Family, a family of nonlinear deep-learning-based control methods with not only stability and robustness guarantees but also new capabilities in agile robotic control. Then I will discuss two unifying interfaces between learning and control: (1) meta-adaptive control, and (2) competitive predictive control. Both interfaces yield settings that jointly admit both learning-theoretic and control-theoretic guarantees.

扩展阅读

 

编辑、海报：黄琦

蔻享学术平台，国内领先的一站式科学资源共享平台，依托国内外一流科研院所、高等院校和企业的科研力量，聚焦前沿科学，以优化科研创新环境、传播和服务科学、促进学科交叉融合为宗旨，打造优质学术资源的共享数据平台。

版权说明：未经授权严禁任何形式的媒体转载和摘编，并且严禁转载至微信以外的平台！

---

原创文章首发于蔻享学术，仅代表作者观点，不代表蔻享学术立场。

转载请在『蔻享学术』公众号后台留言。

点击阅读原文～发现惊喜！