Title:
INFORMATION PROCESSING DEVICE AND INFORMATION PROCESSING METHOD
Document Type and Number:
WIPO Patent Application WO/2020/183877
Kind Code:
A1
Abstract:
The present invention provides an information processing device comprising a learning unit that uses a convolutional network to learn a heuristic function pertaining to a path search, the information processing device being such that: the learning unit has a first convolutional network that outputs a first feature amount based on an environment map, and a second convolutional network that outputs a second feature amount pertaining to the internal state of a search subject; the learning unit performs learning in which there is used a loss pertaining to a connection value of the first feature amount and the second feature amount, and outputs a heuristic map in which the heuristic function is represented as a two-dimensional or higher image; and the internal state of the search subject includes at least one element having a degree of freedom different from a position in the environment.
Inventors:
ARIKI YUKA (JP)
NARIHIRA TAKUYA (JP)
NARIHIRA TAKUYA (JP)
Application Number:
PCT/JP2020/000142
Publication Date:
September 17, 2020
Filing Date:
January 07, 2020
Export Citation:
Assignee:
SONY CORP (JP)
International Classes:
B60W30/10; B25J13/00; G05D1/02; G06N3/04
Foreign References:
| US20130253827A1 | 2013-09-26 | |||
| JP2008249536A | 2008-10-16 |
Other References:
LI, GUANGLI ET AL.: "ANN: A Heuristic Search Algorithm Based on Artificial Neural Networks", PROCEEDINGS OF THE 2016 INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION PROCESSING (ICIIP'16, 25 December 2016 (2016-12-25), pages 1 - 9, XP058317120, ISBN: 978-1-4503-4799-0
TANI, JUN: "Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective", IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS - PART B : CYBERNETICS, vol. 26, no. 3, June 1996 (1996-06-01), pages 421 - 436, XP000592745, ISSN: 1083-4419, DOI: 10.1109/3477.499793
KANEZAKI, ASAKO ET AL.: "GOSELO: Goal-Directed Obstacle and Self-Location Map for Robot Navigation Using Reactive Neural Networks", IEEE ROBOTICS AND AUTOMATION LETTERS, vol. 3, no. 2, 14 December 2017 (2017-12-14), pages 696 - 703, XP055739621, ISSN: 2377-3766
TANI, JUN: "Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective", IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS - PART B : CYBERNETICS, vol. 26, no. 3, June 1996 (1996-06-01), pages 421 - 436, XP000592745, ISSN: 1083-4419, DOI: 10.1109/3477.499793
KANEZAKI, ASAKO ET AL.: "GOSELO: Goal-Directed Obstacle and Self-Location Map for Robot Navigation Using Reactive Neural Networks", IEEE ROBOTICS AND AUTOMATION LETTERS, vol. 3, no. 2, 14 December 2017 (2017-12-14), pages 696 - 703, XP055739621, ISSN: 2377-3766
Attorney, Agent or Firm:
SAKAI INTERNATIONAL PATENT OFFICE (JP)
Download PDF: