Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain

Álvaro Javier Prado; Fernando Auat Cheein; Miguel Torres-Torriti

doi:10.1109/IROS.2016.7759479

Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain

Álvaro Javier Prado, Fernando Auat Cheein, Miguel Torres-Torriti

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Citations (Scopus)

Abstract

Nowadays, agricultural and mining industry applications require saving energy in mobile robotic tasks. This critical issue encouraged us to enhance the performance of path tracking controllers during manoeuvring over slippery and rough terrains. In this scenario, we propose probabilistic approaches under machine learning schemes in order to optimally self-tune the controller. The approaches are real time implemented and tested in a mining machinery skid steer loader Cat^® 262C under gravel and muddy terrains (and their transitions). Finally, experimental results presented in this work show that the performance of the controller enhances up to 20% (average) without compromising saturations in the actuators.

Original language	English
Title of host publication	2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
Publisher	IEEE
Pages	3095-3100
Number of pages	6
ISBN (Electronic)	9781509037629
DOIs	https://doi.org/10.1109/IROS.2016.7759479
Publication status	Published - 1 Dec 2016
Event	2016 IEEE/RSJ International Conference on Intelligent Robots and Systems - Daejeon, Korea, Republic of Duration: 9 Oct 2016 → 14 Oct 2016

Conference

Conference	2016 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated title	IROS 2016
Country/Territory	Korea, Republic of
City	Daejeon
Period	9/10/16 → 14/10/16

ASJC Scopus subject areas

Control and Systems Engineering
Software
Computer Vision and Pattern Recognition
Computer Science Applications

Access to Document

10.1109/IROS.2016.7759479

Cite this

@inproceedings{2da0eee730da4125b896772258779e40,

title = "Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain",

abstract = "Nowadays, agricultural and mining industry applications require saving energy in mobile robotic tasks. This critical issue encouraged us to enhance the performance of path tracking controllers during manoeuvring over slippery and rough terrains. In this scenario, we propose probabilistic approaches under machine learning schemes in order to optimally self-tune the controller. The approaches are real time implemented and tested in a mining machinery skid steer loader Cat{\textregistered} 262C under gravel and muddy terrains (and their transitions). Finally, experimental results presented in this work show that the performance of the controller enhances up to 20% (average) without compromising saturations in the actuators.",

author = "Prado, {{\'A}lvaro Javier} and {Auat Cheein}, Fernando and Miguel Torres-Torriti",

note = "Funding Information: This work is founded by the CONICYT-PCHA/Doctorado Nacional/2015-21151095, FONDECYT Grant 1140575, Basal Grant FB0008, DGIIP-UTFSM Chile and Pontificia Universidad Cat{\'o}lica de Chile, Chile. Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2016 ; Conference date: 09-10-2016 Through 14-10-2016",

year = "2016",

month = dec,

day = "1",

doi = "10.1109/IROS.2016.7759479",

language = "English",

pages = "3095--3100",

booktitle = "2016 IEEE/RSJ International Conference on Intelligent Robots and Systems",

publisher = "IEEE",

address = "United States",

}

Prado, ÁJ, Auat Cheein, F & Torres-Torriti, M 2016, Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain. in 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp. 3095-3100, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems, Daejeon, Korea, Republic of, 9/10/16. https://doi.org/10.1109/IROS.2016.7759479

TY - GEN

T1 - Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain

AU - Prado, Álvaro Javier

AU - Auat Cheein, Fernando

AU - Torres-Torriti, Miguel

N1 - Funding Information: This work is founded by the CONICYT-PCHA/Doctorado Nacional/2015-21151095, FONDECYT Grant 1140575, Basal Grant FB0008, DGIIP-UTFSM Chile and Pontificia Universidad Católica de Chile, Chile. Publisher Copyright: © 2016 IEEE.

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Nowadays, agricultural and mining industry applications require saving energy in mobile robotic tasks. This critical issue encouraged us to enhance the performance of path tracking controllers during manoeuvring over slippery and rough terrains. In this scenario, we propose probabilistic approaches under machine learning schemes in order to optimally self-tune the controller. The approaches are real time implemented and tested in a mining machinery skid steer loader Cat® 262C under gravel and muddy terrains (and their transitions). Finally, experimental results presented in this work show that the performance of the controller enhances up to 20% (average) without compromising saturations in the actuators.

AB - Nowadays, agricultural and mining industry applications require saving energy in mobile robotic tasks. This critical issue encouraged us to enhance the performance of path tracking controllers during manoeuvring over slippery and rough terrains. In this scenario, we propose probabilistic approaches under machine learning schemes in order to optimally self-tune the controller. The approaches are real time implemented and tested in a mining machinery skid steer loader Cat® 262C under gravel and muddy terrains (and their transitions). Finally, experimental results presented in this work show that the performance of the controller enhances up to 20% (average) without compromising saturations in the actuators.

UR - http://www.scopus.com/inward/record.url?scp=85006437113&partnerID=8YFLogxK

U2 - 10.1109/IROS.2016.7759479

DO - 10.1109/IROS.2016.7759479

M3 - Conference contribution

AN - SCOPUS:85006437113

SP - 3095

EP - 3100

BT - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - IEEE

T2 - 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems

Y2 - 9 October 2016 through 14 October 2016

ER -

Probabilistic approaches for self-tuning path tracking controllers using prior knowledge of the terrain

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this