University of Cambridge > Talks.cam > CUED Control Group Seminars > Distributed Learning and Control for Networked Autonomy

Distributed Learning and Control for Networked Autonomy

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Fulvio Forni.

Systems that operate autonomously, with limited human involvement, are becoming ubiquitous and they facilitate applications such as Smart Cities, Connected Mobility, Resilient Energy Systems, and the Industrial Internet-of-Things. Modern autonomous systems exploit the accelerating convergence of the physical world with the digital world due to a) sensing available at scale, b) novel networking and computing capabilities, c) powerful algorithms for processing sensing data, and d) the ability to actuate on the physical world, e.g., by technologies such as autonomous robots or autonomous driving vehicles. In the main part of this seminar, I will study how these advances enable autonomous systems to learn and adapt to data collected in a distributed fashion. I will discuss approaches to address the fundamental challenge of communication efficiency in this distributed learning setup, combining the problem with tools from networked control systems. If time permits, I will also discuss recent work on how control systems can incorporate learning architectures, such as Neural Networks.

The seminar will be held in the JDB Seminar Room, Department of Engineering, and online (zoom): https://us06web.zoom.us/j/87986687566?pwd=MGJScmMwd2lwT0tVMHNmWmxSa05XZz09

This talk is part of the CUED Control Group Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity