Near Optimal Control with Reachability and Safety Guarantees

Research output: Contribution to journalConference articleScientificpeer-review

1 Citation (Scopus)
80 Downloads (Pure)

Abstract

Control systems designed via learning methods, aiming at quasi-optimal solutions, typically lack stability and performance guarantees. We propose a method to construct a near-optimal control law by means of model-based reinforcement learning and subsequently verifying the reachability and safety of the closed-loop control system through an automatically synthesized Lyapunov barrier function. We demonstrate the method on the control of an anti-lock braking system. Here the optimal control synthesis is used to minimize the braking distance, whereas we use verification to show guaranteed convergence to standstill and formally bound the braking distance.

Original languageEnglish
Pages (from-to)230-235
Number of pages6
JournalIFAC-PapersOnLine
Volume52
Issue number11
DOIs
Publication statusPublished - 2019
Event5th IFAC Conference on Intelligent Control and Automation Sciences, ICONS 2019 - Belfast, United Kingdom
Duration: 21 Aug 201923 Aug 2019

Keywords

  • nonlinear optimal control
  • reinforcement learning
  • value iteration
  • vehicle safety
  • verification

Fingerprint Dive into the research topics of 'Near Optimal Control with Reachability and Safety Guarantees'. Together they form a unique fingerprint.

Cite this