Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbances

Shakiba Yaghoubi, Georgios Fainekos, Sriram Sankaranarayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Control Barrier Functions (CBF) have been recently utilized in the design of provably safe feedback control laws for nonlinear systems. These feedback control methods typically compute the next control input by solving an online Quadratic Program (QP). Solving QPs in real-time can be a computationally expensive process for resource-constrained systems. In the presence of disturbances, finding CBF-based safe control inputs can get even more time consuming as finding the worst-case of the disturbance requires solving a nonlinear program in general. In this work, we propose to use imitation learning to learn Neural Network based feedback controllers which will satisfy the CBF constraints. In the process, we also develop a new class of High Order CBF for systems under external disturbances. We demonstrate the framework on a unicycle model subject to external disturbances, e.g., wind or currents.

Original languageEnglish (US)
Title of host publication2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728141497
DOIs
StatePublished - Sep 20 2020
Externally publishedYes
Event23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020 - Rhodes, Greece
Duration: Sep 20 2020Sep 23 2020

Publication series

Name2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020

Conference

Conference23rd IEEE International Conference on Intelligent Transportation Systems, ITSC 2020
Country/TerritoryGreece
CityRhodes
Period9/20/209/23/20

Keywords

  • Barrier Function
  • Disturbance
  • Imitation Learning
  • Neural Network Controller

ASJC Scopus subject areas

  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Information Systems and Management
  • Modeling and Simulation
  • Education

Fingerprint

Dive into the research topics of 'Training Neural Network Controllers Using Control Barrier Functions in the Presence of Disturbances'. Together they form a unique fingerprint.

Cite this