Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
VISION AND TOUCH COMBINED ROBOT PRECISION ASSEMBLY CONTROL METHOD AND SYSTEM
Document Type and Number:
WIPO Patent Application WO/2023/083034
Kind Code:
A1
Abstract:
A robot-based assembly control method, comprising providing a plurality of neural network models, the plurality of neural network models at least comprising a reinforcement learning network model and a tensor fusion network model, and training data comprising vision data from a vision device, touch data from a touch sensor, action feedback data of a robot, and torque feedback data. A computer-readable storage medium implementing the control method. A robot-based assembly control system, comprising: a clamping actuator arranged at the tail end of a moving part of a robot and a vision device matching the robot, a touch sensor and a soft rubber pad being sequentially arranged from inside to outside on the inner clamping side of the clamping actuator. External force information of other dimensions is indirectly obtained by using change of a touch signal, the external force information is combined with vision information, and representation vectors can be used for generating a proper robot action instruction and flexibly adjusting insertion force to complete assembly.

More Like This:
WO/2017/157402A ROBOT AND A METHOD OF CONTROLLING A ROBOT
JP7259269Data processing device, data processing method
WO/2022/088613ROBOT POSITIONING METHOD AND APPARATUS, DEVICE AND STORAGE MEDIUM
Inventors:
LOU YUNJIANG (CN)
LIU RUIKAI (CN)
YANG XIANSHENG (CN)
LI AJIAN (CN)
Application Number:
PCT/CN2022/128555
Publication Date:
May 19, 2023
Filing Date:
October 31, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HARBIN INST TECHNOLOGY SHENZHEN (CN)
International Classes:
B25J9/16
Foreign References:
CN113878588A2022-01-04
CN113927602A2022-01-14
CN113954076A2022-01-21
CN109940605A2019-06-28
CN112631128A2021-04-09
CN112388655A2021-02-23
CN113172629A2021-07-27
CN111444954A2020-07-24
JP2010017768A2010-01-28
US20210270605A12021-09-02
Other References:
"16th European Conference - Computer Vision – ECCV 2020", vol. 6, 19 October 2021, article LI AJIAN; LIU RUIKAI; YANG XIANSHENG; LOU YUNJIANG: "Reinforcement Learning Strategy Based on Multimodal Representations for High-Precision Assembly Tasks", pages: 56 - 66, XP047613894, DOI: 10.1007/978-3-030-89095-7_6
Attorney, Agent or Firm:
ZHUHAI DEQUAN IP LAW (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: METHOD FOR SENDING PRECODING MATRIX INDICATION INFORMATION, AND DEVICE

Next Patent: HYPERBRANCHED BORIC ACID MODIFIED PHTHALONITRILE MONOMER, PREPARATION METHOD THEREFOR, AND APPLICATI...