Title:
SYSTEM AND METHOD FOR REAL-TIME SUPERVISED MACHINE LEARNING IN ON-SITE ENVIRONMENT
Document Type and Number:
WIPO Patent Application WO/2020/097837
Kind Code:
A1
Abstract:
An automatic guided vehicle (AGV)(100) comprising a mobile base(105) including a drive train(435) and configured to drive the AGV(100) in a self-navigation mode within a facility, a first camera(140A) configured to capture first image data of objects within the facility, a second camera(140B) configured to capture second image data of objects within the facility, the second camera(140B) including a content filter, and a main control module(170) configured to receive the first and second image data from the first and second cameras(140A,140B). The main control module(170) executes a recognition neural network program(413). The neural network program(413) recognizes targets in the first image data. The main control module(170) also executes a supervisor program(412) under user control. The supervisor program(412) receives the second image data and recognizes markers(511, 512, 513, 711, 712, 713, 714, 811, 812, 813, 911, 912) attached to targets in the second image data. The supervisor program(412) produces a supervised outcome in which targets to which markers(511, 512, 513, 711, 712, 713, 714, 811, 812, 813, 911, 912) are attached are associated with categories based on user commands. The supervised outcome adjusts weights of nodes in the recognition neural network program(413).
Inventors:
CHEN CHIUNG LIN (CN)
YAO MENG (CN)
YAO MENG (CN)
Application Number:
PCT/CN2018/115556
Publication Date:
May 22, 2020
Filing Date:
November 15, 2018
Export Citation:
Assignee:
LINGDONG TECH BEIJING CO LTD (CN)
International Classes:
G06V10/774; G06V10/82; G06V20/10
Foreign References:
| CN108399398A | 2018-08-14 | |||
| CN107330405A | 2017-11-07 | |||
| CN104754311A | 2015-07-01 | |||
| CN103473558A | 2013-12-25 | |||
| CN108230291A | 2018-06-29 | |||
| CN108009625A | 2018-05-08 | |||
| US9336483B1 | 2016-05-10 |
Attorney, Agent or Firm:
SHANGHAI TIANCHEN INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF: