Title:
MODEL GENERATION DEVICE, MODEL GENERATION METHOD, CONTROL DEVICE, AND CONTROL METHOD
Document Type and Number:
WIPO Patent Application WO/2021/033486
Kind Code:
A1
Abstract:
A model generation device according to one aspect of this invention implements a machine learning model of a determination model by using a plurality of learning data sets, each configured from a combination of training data indicating a positional relationship between two objects, and correct answer data indicating whether the two objects contact each other in said positional relationship. The implementation of machine learning is configured by training the determination model such that, in response to an input of training data, an output value matching corresponding correct answer data is output.
Inventors:
OKAWA YOHEI (JP)
HAYASHI KENNOSUKE (JP)
SHIBATA YOSHIYA (JP)
HAYASHI KENNOSUKE (JP)
SHIBATA YOSHIYA (JP)
Application Number:
PCT/JP2020/028446
Publication Date:
February 25, 2021
Filing Date:
July 22, 2020
Export Citation:
Assignee:
OMRON TATEISI ELECTRONICS CO (JP)
International Classes:
B25J13/00
Domestic Patent References:
| WO2019097676A1 | 2019-05-23 |
Foreign References:
| JP2018149628A | 2018-09-27 | |||
| JP2019030941A | 2019-02-28 |
Other References:
DMITRY KALASHNIKOV ET AL.: "QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation", ARXIV: 1806.10293, 2018
S. HOCHREITERJ. SCHMIDHUBER: "Long Short-term Memory", NEURAL COMPUTATION, vol. 9, no. 8, 15 November 1997 (1997-11-15), pages 1735 - 1780
FELIX A. GERSJURGEN SCHMIDHUBERFRED CUMMINS: "Learning to Forget: Continual Prediction with LSTM", NEURAL COMPUTATION, October 2000 (2000-10-01), pages 2451 - 2471
JUSTIN FU ET AL.: "Learning Robust Rewards with Adversarial Inverse Reinforcement Learning", ARXIV:1710.11248, 2018
See also references of EP 4019207A4
S. HOCHREITERJ. SCHMIDHUBER: "Long Short-term Memory", NEURAL COMPUTATION, vol. 9, no. 8, 15 November 1997 (1997-11-15), pages 1735 - 1780
FELIX A. GERSJURGEN SCHMIDHUBERFRED CUMMINS: "Learning to Forget: Continual Prediction with LSTM", NEURAL COMPUTATION, October 2000 (2000-10-01), pages 2451 - 2471
JUSTIN FU ET AL.: "Learning Robust Rewards with Adversarial Inverse Reinforcement Learning", ARXIV:1710.11248, 2018
See also references of EP 4019207A4
Attorney, Agent or Firm:
TACHIBANA, Kenji et al. (JP)
Download PDF: