Title:
POSITION CONTROL DEVICE AND POSITION CONTROL METHOD
Document Type and Number:
WIPO Patent Application WO/2018/146769
Kind Code:
A1
Abstract:
The present invention includes: an imaging unit 201 that captures an image in which there are two objects; a control parameter generation unit 202 that inputs information regarding the captured image of two objects in an input layer of a neural network, and outputs a position control amount for controlling the positional relationship of the two objects as an output layer of the neural network; a control unit 203 that uses the outputted position control amount to control a current or voltage for controlling the positional relationship of the two objects; and a drive unit 204 that uses the current or voltage for controlling the positional relationship of the two objects to move one position among the positional relationship of the two objects. The control parameter generation unit 202 is configured to select one from a plurality of neural networks, and thus achieves an effect wherein alignment can be performed with higher accuracy even if there is a positional relationship error between the two objects or individual variation among the individual objects.
Inventors:
MARIYAMA TOSHISADA (JP)
MIURA MAMORU (JP)
MATSUMOTO WATARU (JP)
MIURA MAMORU (JP)
MATSUMOTO WATARU (JP)
Application Number:
PCT/JP2017/004732
Publication Date:
August 16, 2018
Filing Date:
February 09, 2017
Export Citation:
Assignee:
MITSUBISHI ELECTRIC CORP (JP)
International Classes:
G05D3/12; B25J13/08
Foreign References:
| JP2016000442A | 2016-01-07 | |||
| JP2013214136A | 2013-10-17 |
Other References:
YUKI MORIYAMA ET AL.: "View-Based Teaching/Playback for Manipulation by Industrial Robots", TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS SERIES C, vol. 79, no. 806, October 2013 (2013-10-01), pages 308 - 319, XP055534505
KAZUYOSHI YUKI ET AL.: "Effect of the number of hidden neurons in the learning of a layered neural network with a large number of inputs", DAI 23 KAI THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS KYUSHU SHIBU GAKUJUTSU KOENKAI YOKOSHU, 2004
MAKOTO KAWAMURA ET AL.: "Land cover classification of satellite images using cooperative learning neural networks", JOURNAL OF THE JAPAN SOCIETY OF PHOTOGRAMMETRY AND REMOTE SENSING, vol. 34, no. 1, 1995, pages 71 - 80, XP055534518
KAZUYOSHI YUKI ET AL.: "Effect of the number of hidden neurons in the learning of a layered neural network with a large number of inputs", DAI 23 KAI THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS KYUSHU SHIBU GAKUJUTSU KOENKAI YOKOSHU, 2004
MAKOTO KAWAMURA ET AL.: "Land cover classification of satellite images using cooperative learning neural networks", JOURNAL OF THE JAPAN SOCIETY OF PHOTOGRAMMETRY AND REMOTE SENSING, vol. 34, no. 1, 1995, pages 71 - 80, XP055534518
Attorney, Agent or Firm:
MURAKAMI, Kanako et al. (JP)
Download PDF:
Previous Patent: DEFECT FACTOR ESTIMATION DEVICE AND DEFECT FACTOR ESTIMATION METHOD
Next Patent: POSITION CONTROL DEVICE AND POSITION CONTROL METHOD
Next Patent: POSITION CONTROL DEVICE AND POSITION CONTROL METHOD