Title:
UNMANNED DEVICE CONTROL AND MODEL TRAINING
Document Type and Number:
WIPO Patent Application WO/2020/177417
Kind Code:
A1
Abstract:
Methods and apparatuses for controlling an unmanned device and training a model, and an electronic device. The method comprises: obtaining the current control instruction data of a target device (101); obtaining a target hidden variable corresponding to a predetermined target device, wherein the target hidden variable is used for representing a conversion influencing factor between the control instruction data and a control parameter value for the target device (102); based on the current control instruction parameter and the target hidden variable, obtaining the current control parameter value (103); and according to the current control parameter value, controlling the target device (104).
Inventors:
MU RONGJUN (CN)
XIA HUAXIA (CN)
REN DONGCHUN (CN)
GUO XIAOYANG (CN)
FU SHENG (CN)
XIA HUAXIA (CN)
REN DONGCHUN (CN)
GUO XIAOYANG (CN)
FU SHENG (CN)
Application Number:
PCT/CN2019/123394
Publication Date:
September 10, 2020
Filing Date:
December 05, 2019
Export Citation:
Assignee:
BEIJING SANKUAI ONLINE TECH CO LTD (CN)
International Classes:
G05B13/04
Foreign References:
| CN109976153A | 2019-07-05 | |||
| CN109961509A | 2019-07-02 | |||
| CN108897313A | 2018-11-27 | |||
| CN109299732A | 2019-02-01 | |||
| CN109272108A | 2019-01-25 | |||
| CN107609502A | 2018-01-19 | |||
| CN106873566A | 2017-06-20 | |||
| CN106503393A | 2017-03-15 | |||
| US20190061771A1 | 2019-02-28 |
Other References:
JIN FAN: "Research on End-to-End Decision-Making of Intelligent Vehicle Based on Spatio-Temporal Recurrent Neural Network", CHINESE MASTER’S THESES FULL-TEXT DATABASE, no. 10, 15 October 2018 (2018-10-15), pages 1 - 91, XP055731824, ISSN: 1674-0246
Attorney, Agent or Firm:
BEIJING MAVAIP INTELLECTUAL PROPERTY LAW FIRM (CN)
Download PDF:
Previous Patent: FRONT MAINTENANCE TOOL FOR LED DISPLAY SCREEN
Next Patent: SMART AQUACULTURE CONTROL TERMINAL
Next Patent: SMART AQUACULTURE CONTROL TERMINAL