Model predictive control based deep neural network for dynamic manipulation

Daichi Furuta; Kyo Kutsuzawa; Tetsugaku Okamoto; Sho Sakaino; Toshiaki Tsuji

doi:10.1109/IECON.2017.8216902

Model predictive control based deep neural network for dynamic manipulation

Daichi Furuta, Kyo Kutsuzawa, Tetsugaku Okamoto, Sho Sakaino, Toshiaki Tsuji

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

1 Citation (Scopus)

Abstract

This paper proposes a trajectory planning method with neural networks that learn model predictive control for dynamic manipulation. The novelty of this method is that target positions and model parameters are added to the input of the neural network. The proposed method solves the dynamic trajectory planning issues with low calculation cost. This paper shows the effectiveness of the proposed method through demonstrations of a robot turning a pancake over under various parameters. In addition, we verify a performance change with respect to the number of training data.

Original language	English
Title of host publication	Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5215-5220
Number of pages	6
ISBN (Electronic)	9781538611272
DOIs	https://doi.org/10.1109/IECON.2017.8216902
Publication status	Published - 2017 Dec 15
Externally published	Yes
Event	43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017 - Beijing, China Duration: 2017 Oct 29 → 2017 Nov 1

Publication series

Name	Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society
Volume	2017-January

Conference

Conference	43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017
Country	China
City	Beijing
Period	17/10/29 → 17/11/1

ASJC Scopus subject areas

Industrial and Manufacturing Engineering
Control and Optimization
Energy Engineering and Power Technology
Electrical and Electronic Engineering

Access to Document

10.1109/IECON.2017.8216902

Fingerprint Dive into the research topics of 'Model predictive control based deep neural network for dynamic manipulation'. Together they form a unique fingerprint.

Cite this

Furuta, D., Kutsuzawa, K., Okamoto, T., Sakaino, S., & Tsuji, T. (2017). Model predictive control based deep neural network for dynamic manipulation. In Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society (pp. 5215-5220). (Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society; Vol. 2017-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECON.2017.8216902

Model predictive control based deep neural network for dynamic manipulation. / Furuta, Daichi; Kutsuzawa, Kyo; Okamoto, Tetsugaku; Sakaino, Sho; Tsuji, Toshiaki.

Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc., 2017. p. 5215-5220 (Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society; Vol. 2017-January).

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

Furuta, D, Kutsuzawa, K, Okamoto, T, Sakaino, S & Tsuji, T 2017, Model predictive control based deep neural network for dynamic manipulation. in Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society. Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society, vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 5215-5220, 43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017, Beijing, China, 17/10/29. https://doi.org/10.1109/IECON.2017.8216902

Furuta D, Kutsuzawa K, Okamoto T, Sakaino S, Tsuji T. Model predictive control based deep neural network for dynamic manipulation. In Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc. 2017. p. 5215-5220. (Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society). https://doi.org/10.1109/IECON.2017.8216902

Furuta, Daichi ; Kutsuzawa, Kyo ; Okamoto, Tetsugaku ; Sakaino, Sho ; Tsuji, Toshiaki. / Model predictive control based deep neural network for dynamic manipulation. Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 5215-5220 (Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society).

@inproceedings{3281eee1060d4e81992272d90d99bc9d,

title = "Model predictive control based deep neural network for dynamic manipulation",

abstract = "This paper proposes a trajectory planning method with neural networks that learn model predictive control for dynamic manipulation. The novelty of this method is that target positions and model parameters are added to the input of the neural network. The proposed method solves the dynamic trajectory planning issues with low calculation cost. This paper shows the effectiveness of the proposed method through demonstrations of a robot turning a pancake over under various parameters. In addition, we verify a performance change with respect to the number of training data.",

author = "Daichi Furuta and Kyo Kutsuzawa and Tetsugaku Okamoto and Sho Sakaino and Toshiaki Tsuji",

year = "2017",

month = dec,

day = "15",

doi = "10.1109/IECON.2017.8216902",

language = "English",

series = "Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5215--5220",

booktitle = "Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society",

note = "43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017 ; Conference date: 29-10-2017 Through 01-11-2017",

}

TY - GEN

T1 - Model predictive control based deep neural network for dynamic manipulation

AU - Furuta, Daichi

AU - Kutsuzawa, Kyo

AU - Okamoto, Tetsugaku

AU - Sakaino, Sho

AU - Tsuji, Toshiaki

PY - 2017/12/15

Y1 - 2017/12/15

N2 - This paper proposes a trajectory planning method with neural networks that learn model predictive control for dynamic manipulation. The novelty of this method is that target positions and model parameters are added to the input of the neural network. The proposed method solves the dynamic trajectory planning issues with low calculation cost. This paper shows the effectiveness of the proposed method through demonstrations of a robot turning a pancake over under various parameters. In addition, we verify a performance change with respect to the number of training data.

AB - This paper proposes a trajectory planning method with neural networks that learn model predictive control for dynamic manipulation. The novelty of this method is that target positions and model parameters are added to the input of the neural network. The proposed method solves the dynamic trajectory planning issues with low calculation cost. This paper shows the effectiveness of the proposed method through demonstrations of a robot turning a pancake over under various parameters. In addition, we verify a performance change with respect to the number of training data.

UR - http://www.scopus.com/inward/record.url?scp=85046668391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046668391&partnerID=8YFLogxK

U2 - 10.1109/IECON.2017.8216902

DO - 10.1109/IECON.2017.8216902

M3 - Conference contribution

AN - SCOPUS:85046668391

T3 - Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society

SP - 5215

EP - 5220

BT - Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 43rd Annual Conference of the IEEE Industrial Electronics Society, IECON 2017

Y2 - 29 October 2017 through 1 November 2017

ER -