Automatic process for 3D environment modeling from acquired image sequences

Matsumoto, Taku; Hanari, Toshihide; Kawabata, Kuniaki; Yashiro, Hiroshi*; Nakamura, Keita*

Proceedings of 28th International Symposium on Artificial Life and Robotics (AROB 28th 2023) (Internet), p.768 - 773, 2023/01

HAIROWorldPlugin operation manual (Revised edition)

Suzuki, Kenta; Yashiro, Hiroshi; Kawabata, Kuniaki

JAEA-Testing 2021-004, 125 Pages, 2022/03

JAEA-Testing-2021-004.pdf:6.1MB

This report is updated HAIROWorldPlugin Operation Manual (JAEA-Testing 2020-009). Our motivation is to develop a robot simulator based on Choreonoid for technological development to contribute the decommissioning work at the Fukushima Daiichi Nuclear Power Station of Tokyo Electric Power Company Holdings, Inc. Choreonoid is an open source simulator which calculates the behavior of robots. We are developing HAIROWorldPlugin which is an extended function of Choreonoid for providing a virtual decommissioning experience. In the latest HAIROWorldPlugin, the several functions were additionally implemented. In particular, we implemented new functionalities: logging a collision status between a robot and an object, showing and logging a status of the joystick input signals, generating an environmental object model (pipe, grating, and slope), bookmarking an often used simulation settings, and recording histories of a simulation settings. In addition, this report describes the installation of the plugin to Choreonoid on Ubuntu20.04-LTS and parameter settings of the plugin by presenting snapshots of operation windows.

Discrimination of the structures in nuclear facility station by deep learning based on 3D point cloud data

Imabuchi, Takashi; Tanifuji, Yuta; Kawabata, Kuniaki

Proceedings of 2022 IEEE/SICE International Symposium on System Integration (SII 2022) (Internet), p.1036 - 1040, 2022/01

This paper describes a method for discrimination of the structures in nuclear power station by deep learning based on 3D point cloud data. In order to promote safe and steady decommissioning work, it is important to estimate and assume the condition in nuclear power station based on the measured sensor data. Especially, the data of the dose rate in the workspace is useful to plan the decommissioning task and, the shape and the material property of the structures in the workspace are required for the dose rate simulation. Shape data can be obtained by such as 3D Scan, however, it is difficult to acquire the material property data of the objects. Therefore, we consider that it is possible that the major material property can be estimated from the category of the structures in nuclear power station. In this paper, we proposed a structure discrimination method by 3D semantic segmentation with 3D point cloud data that consists of labeled points by referring category labels of CAD data of existing nuclear facility. We reported discrimination performance of the proposed method by hold-out validation.

3D reconstruction considering calculation time reduction for linear trajectory shooting

Nakamura, Keita; Hanari, Toshihide; Kawabata, Kuniaki

Proceedings of 27th International Symposium on Artificial Life and Robotics (AROB 27th 2022) (Internet), p.771 - 775, 2022/01

In three-dimensional (3D) reconstruction from images, even if the number of images is small and each image captures the features of the target object for 3D reconstruction, highly accurate 3D reconstruction can be achieved in a short time. Therefore, to select effective images for 3D reconstruction, we consider that test data for image selection can be generated by constructing a virtual space using simulation and changing the shooting conditions. In this study, we focus on the case that a camera moves on a straight rail and obtains images, and investigate and verify the effective image selection conditions considering calculation time reduction for 3D reconstruction in this case by simulation.

Test methods for robots for nuclear emergency response and decommissioning; Tests for moving performances of robots (JAEA-TM-0004 and JAEA-TM-0005)

Kawabata, Kuniaki; Yamada, Taichi; Abe, Hiroyuki*

JAEA-Technology 2021-021, 30 Pages, 2021/11

JAEA-Technology-2021-021.pdf:2.55MB

This report describes the test procedures for performance evaluation of remotely operated robot utilized for nuclear emergency responses and decommissioning that provide to compare among the robot's performances quantitatively and relatively. After the accident at Fukushima Daiichi Nuclear Power Station of the Tokyo Electric Power Company Holdings Inc. (FDNPS) occurred, remotely operated robots have been deployed and utilized in the response tasks. Such post-accident work experiences and lessons learned are very valuable for developing the robots in the future. Therefore, we were motivated to develop the test methods for performance evaluation of the robot by referring with such experiences and lessons. In recent decommissioning tasks, reconnaissance on the distribution and status of nuclear fuel debris inside the Primary Containment Vessel (PCV) have been carried out. The insertion and deployment of robots into PCV were carried out through a penetration pipe with small diameter to prevent the scattering of radioactive materials. According to the authors' survey on such works have carried out in Units 1 and 2 of FDNPS, in order to carry out the reconnaissance work by the robot deployed into the PCV, it was clarified that the robots are required to run freely on the floor located below the exit of the penetration pipe and run freely on the inclined surface located below the exit of the pipe. This document describes two test procedures for performance evaluation of the robot connected with the cable such as running on the floor after being deployed through a penetration pipe and running on the inclined surface after being deployed through a penetration pipe. Typical course layout and the demonstration of test running are also illustrated for the references.

A Simulator-based system for testing skill to maneuver robot remotely; Implementations of data collection and presentation functions related to robot maneuver

Abe, Fumiaki; Kawabata, Kuniaki; Suzuki, Kenta; Yashiro, Hiroshi

2021 IEEE/SICE International Symposium on System Integration (SII 2021), Vol.2, p.835 - 836, 2021/07

https://doi.org/10.1109/IEEECONF49454.2021.9382608

HAIROWorldPlugin operation manual

Suzuki, Kenta; Abe, Fumiaki; Yashiro, Hiroshi; Kawabata, Kuniaki

JAEA-Testing 2020-009, 254 Pages, 2021/03

JAEA-Testing-2020-009.pdf:18.61MB

This report is the user manual of HAIROWorldPlugin for Choreonoid. Our motivation is to develop a robot simulator based on Choreonoid for technological development to contribute the decommissioning work at the Fukushima Daiichi Nuclear Power Station of Tokyo Electric Power Company Holdings, Inc. Choreonoid is an open source simulator which calculates the behavior of robots. The plugin is an extended function of Choreonoid which provides simulated behavior and phenomenon related to decommissioning tasks utilizing remotely operated robots. In particular, we developed additional functionalities for simulating the behavior of an underwater swimming robot, the behavior of an unmanned aerial vehicle robot, low visibility camera images, network communication failures, etc., and packaged these in the plugin. This report describes the installation of the plugin to Choreonoid on Ubuntu18.04-LTS and parameter settings of the plugin by presenting snapshots of operation windows.

Test methods for robots for nuclear emergency response and decommissioning; Tests for running performances of robots (JAEA-TM-0001, JAEA-TM-0002 and JAEA-TM-0003)

Kawabata, Kuniaki; Yamada, Taichi; Abe, Hiroyuki*

JAEA-Technology 2020-015, 37 Pages, 2020/11

JAEA-Technology-2020-015.pdf:3.81MB

This report describes the test procedures for evaluating running performances of remotely operated robot utilized for nuclear emergency responses and decommissioning. After the accident at Fukushima Daiichi Nuclear Power Station of the Tokyo Electric Power Company Holdings Inc. (FDNPS) occurred, remotely operated robots have been deployed and utilized in the response tasks. Such post-accident work experience and lessons learned are very valuable for developing the robots in the future. Therefore, we were motivated to develop the test methods for performance evaluation of the robot by referring with such experiences and lessons. Based on our examinations, in order to execute the response and decommissioning tasks, the robots are required to run through the space without enough margin and avoiding collisions, to move on stairs while avoiding tumbling or falling down and to drag a cable while avoiding problems caused by the cable entwining around objects. This report describes three test procedures for quantitatively evaluating the performances which are for running narrow passage, climbing up/down on the stairs and running with dragging the cable. Typical course layout and the demonstration of test running are also illustrated for the references.

An Image selection method from image sequence collected by remotely operated robot for efficient 3D reconstruction

Hanari, Toshihide; Kawabata, Kuniaki; Nakamura, Keita*; Naruse, Keitaro*

Proceedings of International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP 2020) (Internet), p.242 - 245, 2020/02

In this paper, we propose an image selection method to realize efficient three-dimensional (3D) reconstruction from image sequence collected by a remotely operated robot. The proposed method is to select adequate images for reconstruction computation based on optical flow measures. We confirmed that the proposed method can select adequate images for 3D reconstruction from the image sequence recorded by the remotely operated robot that is commanded stop-and-go motions. As a result, we demonstrated a 3D reconstruction could be performed efficiently with relatively few images that were selected by the proposed method.

Development of a simulator for underwater reconnaissance tasks by utilizing remotely operated robots

Suzuki, Kenta; Kawabata, Kuniaki

Proceedings of 2020 IEEE/SICE International Symposium on System Integration (SII 2020) (USB Flash Drive), p.1100 - 1106, 2020/01

https://doi.org/10.1109/SII46433.2020.9026281