Automatic Tuning for Data-driven Model Predictive Control

William Edwards, Gao Tang, Giorgos Mamakoukas, Todd Murphey, Kris Hauser

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

Abstract

Model predictive control (MPC) is a powerful feedback technique that is often used in data-driven robotics. The performance of data-driven MPC depends on the accuracy of the model, which often requires careful tuning. Furthermore, specifying the task with an objective function and synthesizing a feedback policy are not straightforward and typically lead to suboptimal solutions driven by trial and error. To address these challenges, we present a method to jointly optimize the data-driven system identification, task specification, and control synthesis of unknown dynamical systems. We use our method to develop AutoMPC3, a software package designed to automate and optimize data-driven MPC. Empirical evaluation on the pendulum swing-up, cart-pole swing-up, and half-cheetah running demonstrates that our method finds data-driven control policies that outperform offline reinforcement learning, without any hand-tuning.

Original languageEnglish (US)
Title of host publication2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7379-7385
Number of pages7
ISBN (Electronic)9781728190778
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Robotics and Automation, ICRA 2021 - Xi'an, China
Duration: May 30 2021Jun 5 2021

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
Volume2021-May
ISSN (Print)1050-4729

Conference

Conference2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Country/TerritoryChina
CityXi'an
Period5/30/216/5/21

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Automatic Tuning for Data-driven Model Predictive Control'. Together they form a unique fingerprint.

Cite this