Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/153968
Title: Can deep models help a robot to tune its controller? : A step closer to self-tuning model predictive controllers
Authors: Mehndiratta, Mohit
Camci, Efe
Kayacan, Erdal
Keywords: Engineering::Mechanical engineering
Issue Date: 2021
Source: Mehndiratta, M., Camci, E. & Kayacan, E. (2021). Can deep models help a robot to tune its controller? : A step closer to self-tuning model predictive controllers. Electronics, 10(18), 2187-. https://dx.doi.org/10.3390/electronics10182187
Project: RG185/17
Journal: Electronics
Abstract: Motivated by the difficulty roboticists experience while tuning model predictive controllers (MPCs), we present an automated weight set tuning framework in this work. The enticing feature of the proposed methodology is the active exploration approach that adopts the exploration– exploitation concept at its core. Essentially, it extends the trial-and-error method by benefiting from the retrospective knowledge gained in previous trials, thereby resulting in a faster tuning procedure. Moreover, the tuning framework adopts a deep neural network (DNN)-based robot model to conduct the trials during the simulation tuning phase. Thanks to its high fidelity dynamics representation, a seamless sim-to-real transition is demonstrated. We compare the proposed approach with the customary manual tuning procedure through a user study wherein the users inadvertently apply various tuning methodologies based on their progressive experience with the robot. The results manifest that the proposed methodology provides a safe and time-saving framework over the manual tuning of MPC by resulting in flight-worthy weights in less than half the time. Moreover, this is the first work that presents a complete tuning framework extending from robot modeling to directly obtaining the flight-worthy weight sets to the best of the authors’ knowledge.
URI: https://hdl.handle.net/10356/153968
ISSN: 2079-9292
DOI: 10.3390/electronics10182187
Rights: © 2021 The Author(s). Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:MAE Journal Articles

Files in This Item:
File Description SizeFormat 
electronics-10-02187-v2.pdf1.17 MBAdobe PDFView/Open

Page view(s)

26
Updated on May 15, 2022

Download(s)

8
Updated on May 15, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.