Skip to main navigation Skip to search Skip to main content

Learning distributed controllers for V-formation

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

We show how a high-performing, fully distributed and symmetric neural V-formation controller can be synthesized from a Centralized MPC (Model Predictive Control) controller using Deep Learning. This result is significant as we also establish that under very reasonable conditions, it is impossible to achieve V-formation using a deterministic, distributed, and symmetric controller. The learning process we use for the neural V-formation controller is significantly enhanced by CEGkR, a CounterexampleGuided k-fold Retraining technique we introduce, which extends prior work in this direction in important ways. Our experimental results show that our neural V-formation controller generalizes to a significantly larger number of agents than for which it was trained (from 7 to 15), and exhibits substantial speedup over the MPC-based controller. We use a form of statistical model checking to compute confidence intervals for our neural Vformation controller's convergence rate and time to convergence.

Original languageEnglish
Title of host publicationProceedings - 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2020
EditorsEsam El-Araby, Sven Tomforde, Timothy Wood, Pradeep Kumar, Claudia Raibulet, Ioan Petri, Gabriele Valentini, Phyllis Nelson, Barry Porter
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages119-128
Number of pages10
ISBN (Electronic)9781728172774
DOIs
StatePublished - Aug 2020
Event1st IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2020 - Virtual, Washington, United States
Duration: Aug 17 2020Aug 21 2020

Publication series

NameProceedings - 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2020

Conference

Conference1st IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2020
Country/TerritoryUnited States
CityVirtual, Washington
Period08/17/2008/21/20

Keywords

  • Distributed Neural Controller
  • Model Predictive Control
  • Supervised Learning.
  • V-Formation

Fingerprint

Dive into the research topics of 'Learning distributed controllers for V-formation'. Together they form a unique fingerprint.

Cite this