Title:
FLIGHT DECISION GENERATION METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM
Document Type and Number:
WIPO Patent Application WO/2023/142316
Kind Code:
A1
Abstract:
Embodiments of the present disclosure relate to the technical field of unmanned aerial vehicles, and provide a flight decision generation method and apparatus, a computer device, and a storage medium. The method comprises: obtaining task demand data; constructing a flight decision model according to the data, wherein the flight decision model comprises a plurality of pieces of decision tuple data, the decision tuple data comprises original hyperparameter groups, and the original hyperparameter groups are gathered to form an original hyperparameter population; constructing a corresponding target learning function on the basis of the flight decision model; updating and optimizing the original hyperparameter population according to the target learning function to obtain a target hyperparameter population; and obtaining a target flight decision of an unmanned aerial vehicle according to the target hyperparameter population. According to the present application, on the basis of establishing the flight decision model, by defining the target learning function, the unmanned aerial vehicle is made to further update and optimize the original hyperparameter population by means of an optimization target of the target learning function on the basis of completing an autonomous navigation task, so as to obtain the target flight decision, such that the flexibility of the autonomous navigation task of the unmanned aerial vehicle is improved.
Inventors:
SHANG KE (CN)
ISHIBUCHI HISAO (CN)
ISHIBUCHI HISAO (CN)
Application Number:
PCT/CN2022/094033
Publication Date:
August 03, 2023
Filing Date:
May 20, 2022
Export Citation:
Assignee:
UNIV SOUTHERN SCI & TECH (CN)
International Classes:
G06N3/00
Foreign References:
| CN114492718A | 2022-05-13 | |||
| CN112507622A | 2021-03-16 | |||
| CN111708355A | 2020-09-25 | |||
| CN113281999A | 2021-08-20 | |||
| CN112327923A | 2021-02-05 | |||
| CN112198870A | 2021-01-08 | |||
| US20210343160A1 | 2021-11-04 |
Other References:
ZHENG, BAOJUAN: "Research on Improved NSGA-II Algorithm for UVA Path Planning", ENGINEERING SCIENCE AND TECHNOLOGY II, CHINA MASTER'S THESES FULL-TEXT DATABASE, no. 06, 15 June 2021 (2021-06-15), ISSN: 1674-0246
Attorney, Agent or Firm:
JIAQUAN IP LAW (CN)
Download PDF: