In-orbit autonomous filling control method and system based on multi-task learning
A multi-task learning and control method technology, applied in the field of on-orbit autonomous filling control, can solve the problems of system controllability and reliability reduction, and achieve the effect of improving convergence, reducing optimization burden, and weakening the intervention of artificial factors
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] Such as figure 1 As shown, the present invention provides an on-orbit autonomous filling control method based on multi-task learning, and the specific implementation control system mainly includes: supplementary satellite 1, mechanical arm 2, filling active end 3, filling passive end 4, Receptor satellite 5, sensor module 6, host computer 7; the filling active end 3 is located on the additional satellite 1, the filling passive end 4 is located on the acceptor satellite 5, and the mechanical arm 3 is used for clamping Hold the filling active end 3, and make the filling active end 3 follow it to move to the filling passive end 4; the end of the mechanical arm 2 is equipped with an RGB camera; the sensor module 6 is used to collect the environment of the mechanical arm 2 The interactive data is sent to the upper computer 7 after filtering the collected signals; the upper computer 7 reads the stored multi-task strategy network F=(G, H) parameters according to the input envi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com