本文へ移動

サイトナビゲーションへ移動

検索ボックスへ移動

サイドバーへ移動

ここは、本文エリアの先頭です。

Evaluation of the Rocket’s Behavior based on Image Recognition Technology

JAXA Supercomputer System Annual Report February 2023-January 2024

Report Number: R23EEK20201

Subject Category: Space Technology

PDF available here

  • Responsible Representative: Space Transportation Technology Derectorate, Kagoshima Space Center, Range Technology Development Unit, Yoshinori Sunasaka
  • Contact Information: Space Transportation Technology Derectorate, Kagoshima Space Center, Range Technology Development Unit, Yukari Sakano(sakano.yukari@jaxa.jp)
  • Members: Yukari Sakano

Abstract

It is important to analyze the position and attitude of a rocket, immediately after the lift-off. This data is used for the evaluation of a rocket’s displacement caused by a surface wind, or a clearance between a rocket and a launcher. However, through the actual launch operation, this behavior can be measured only by ”Indirect” approaches, for example numerical analysis or on-board avionics. Therefore, we have developed the new system based on image recognition technology, which can evaluate the behavior”Directl”, and improve the designs and operations of both rockets and launchers. This research focuses on develop the fundamental technology of the new system.

Reference URL

N/A

Reasons and benefits of using JAXA Supercomputer System

For the calculation of the rocket’s position and attitude, by using image processing technology, following 3 processes are required: (1) take two images at the same time, (2) detect rockets and identify its key-points from each image, and (3) calculate triangulation for defining the rocket’s 3D position, as shown in Fig, 1. Deep learning models are applied for the process (2), and they consist of the model to detect rocket and the model to identify key-points. We utilized the JSS3 for train the deep learning models and succeed to complete the large-scale training calculation rapidly and efficiently.

Achievements of the Year

By utilizing JSS3, the deep learning models for the rocket detection and the key-point identification could be finally constructed, and the rocket position is calculated as shown in Fig. 2. In addition, rocket’s position data, which is more fluent and certain than the result of last year, can be obtained from the analysis. As a result of the research in this year, we can build the foundation of the technologies, and this can be applied to other rockets.

Annual Reoprt Figures for 2023

Fig.1: The process of detecting a rocket position

 

Annual Reoprt Figures for 2023

Fig.2: Evaluated roclet position

 

Publications

N/A

Usage of JSS

Computational Information

  • Process Parallelization Methods: N/A
  • Thread Parallelization Methods: N/A
  • Number of Processes: 1
  • Elapsed Time per Case: 4 Hour(s)

JSS3 Resources Used

 

Fraction of Usage in Total Resources*1(%): 0.00

 

Details

Please refer to System Configuration of JSS3 for the system configuration and major specifications of JSS3.

Computational Resources
System Name CPU Resources Used
(Core x Hours)
Fraction of Usage*2(%)
TOKI-SORA 0.00 0.00
TOKI-ST 284.14 0.00
TOKI-GP 0.00 0.00
TOKI-XM 0.00 0.00
TOKI-LM 0.00 0.00
TOKI-TST 0.00 0.00
TOKI-TGP 0.00 0.00
TOKI-TLM 0.00 0.00

 

File System Resources
File System Name Storage Assigned
(GiB)
Fraction of Usage*2(%)
/home 0.00 0.00
/data and /data2 2133.33 0.01
/ssd 0.00 0.00

 

Archiver Resources
Archiver Name Storage Used
(TiB)
Fraction of Usage*2(%)
J-SPACE 0.00 0.00

*1: Fraction of Usage in Total Resources: Weighted average of three resource types (Computing, File System, and Archiver).

*2: Fraction of Usage:Percentage of usage relative to each resource used in one year.

 

ISV Software Licenses Used

ISV Software Licenses Resources
ISV Software Licenses Used
(Hours)
Fraction of Usage*2(%)
ISV Software Licenses
(Total)
0.00 0.00

*2: Fraction of Usage:Percentage of usage relative to each resource used in one year.

JAXA Supercomputer System Annual Report February 2023-January 2024