Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IMPLEMENTATION METHOD FOR UNMANNED AERIAL VEHICLE REINFORCEMENT LEARNING TRAINING SYSTEM
Document Type and Number:
WIPO Patent Application WO/2023/184676
Kind Code:
A1
Abstract:
An implementation method for an unmanned aerial vehicle reinforcement learning training system. An unmanned aerial vehicle reinforcement learning training system comprises a system control module, an unmanned aerial vehicle simulation training module, an X-Plane Gym module, a reinforcement learning algorithm module and a data storage module, wherein the unmanned aerial vehicle simulation training module is used for providing a simulated training environment for an unmanned aerial vehicle; the unmanned aerial vehicle simulation training module performs interface communication with the system control module by means of the X-Plane Gym module; the reinforcement learning algorithm module is used for providing an algorithm required in the unmanned aerial vehicle simulation training module; and the data storage module is used for collecting and storing training data in the unmanned aerial vehicle simulation training module.

Inventors:
LI GUANG (CN)
LI YANBO (CN)
ZHANG JIANJUN (CN)
YU GUANGRI (CN)
Application Number:
PCT/CN2022/093871
Publication Date:
October 05, 2023
Filing Date:
May 19, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
TIANJIN 712 COMM & BROADCAST (CN)
International Classes:
G05D1/10
Foreign References:
CN114415737A2022-04-29
CN113759751A2021-12-07
CN114237267A2022-03-25
CN111142522A2020-05-12
CN111830848A2020-10-27
Other References:
RIZWAN MALIK MUHAMMAD, UL HAQ KHAN MUHAMMAD ONEEB, HUANG MARTIN, GUNDA KRISHNATEJA, ARAVINDAN RENGAPRIYA: "Reinforcement Learning Based Autopilot", ENGINEERING DESIGN DOCUMENT, VERSION 2.0, 8 December 2021 (2021-12-08), XP093097019, Retrieved from the Internet
Attorney, Agent or Firm:
TIANJIN JUNYAN INTELLECTUAL PROPERTY AGENCY CO., LTD (CN)
Download PDF: