|
Discussion of Teleoperation Support System Design Guideline for Working Robot in Radiation Narrow Environment |
|
Ryosuke Kobayashi, Takashi Yoshimi(Shibaura Institute of Technology, Japan) |
| In this work, we propose a design guideline of teleoperation support system for working robots in radiation narrow environments. The proposed guideline is discussed to configure the robot system with as few sensors as possible because of decreasing the sensor failure risk by high radiation. This paper describes discussion results of the guideline candidate, focusing on relationship between the required information for robot teleoperation and number of sensors that consists of the support system. Additionally, we present some support systems that were developed for an inspection or an investigation of nuclear power plants as development cases. |
|
|
Design of Algorithm for Dead Fish Recognition Based on Analysis of Fish Movement Patterns |
|
Jung-Ho Kang, Tatiana Keruzel, Kyung-Chang Lee(Pukyong National University, Korea) |
| This paper focuses on analyzing the difference in movement patterns of dead and live fish detected and tracked by moving underwater ROV’s camera. The YOLO object detection framework is utilized to detect fish, the tracking process is performed using StrongSORT algorithm, and VGG-16 network was applied to analyze the extracted paths images to effectively recognize dead fish on the bottom of sea cages before decomposition occurs |
|
|
Linearized Deviation Model of the Finite Screw for a Successive Manipulator |
|
Min Cheol Lee, Jaehyung Kim(Pusan National University, Korea) |
| This article proposes a novel method for calibrating serial manipulators using the linearized differential finite screw approach. Previous research has extensively explored calibration techniques utilizing end-effector tracking devices. However, the widespread application of these techniques is hindered by budget constraints and installation difficulties. Moreover, existing calibration methods often rely on continuous end-effector trajectories, which necessitate the use of tracking devices such as laser trackers. To overcome these limitations, a new linearized finite screw deviation model has been developed. |
|
|
Experimental report on digital twin system to assist in deep snow removal works |
|
Shunsuke Izutsu, Naoto Tanifuji, Tadahiro Hasegawa, Shin'ichi Yuta(Shibaura Institute of Technology, Japan), Tomoyuki Kato, Motoyuki Shiraishi, Naoki Kanoh, Shinsuke Sunaga(Seibu Construction Co., Ltd, Japan) |
| A digital twin system was developed to assist deep snow removal operations. By displaying multiple vehicle models in real time on a 3D environmental map in snow-free conditions, this assistance system can accurately identify the relationship between the position and posture of the vehicle and the terrain/ground objects that require attention during snow removal operations. In addition, the system estimates and displays the height of the snow cover to the road and the distance to the mountain slope as necessary information for snow removal operations. The experimental results showed the potential for application as an assistance system for deep snow removal operations. |
|
|
Accurate self-localization by time management fusion between 3D-NDT and odometry |
|
Naoto Tanifuji, Tadahiro Hasegawa, Hiroaki Fukuda, Shin’ichi Yuta(Shibaura Institute of Technology, Japan) |
| An accurate self-localization method was proposed based on time management fusion between 3D-NDT scan matching and odometry. The latency of NDT scan matching process is comparatively long and computationally expensive, which causes a problem of time discrepancy with the current position of the mobile robot driving autonomously. Therefore, an effective data sharing method between PCs, Distributed Streaming Data Sharing Manager (DSSM) with a cache mechanism, was also developed. resulting in a fusion with precise time management between each self-locations and improve accuracy of estimation, despite separating the NDT scan matching process from main PC. |
|
|
Obstacle Avoidance in Dynamic Environment using Particle Swarm Optimization and Kalman Filter |
|
Junmyeong Kim, Kwanho Kim, Kanghyun Jo(University of Ulsan, Korea) |
| This paper presents a novel approach to tackle obstacle avoidance using the Particle Swarm Optimization
(PSO) algorithm, a popular metaheuristic algorithm. One of among contributions is the introduction of the inertia rate
concept, which progressively increases the emphasis on local and global optima during exploration. By incorporating
this method, the performance of the PSO algorithm is significantly enhanced, resulting in improved obstacle avoidance
capabilities. Comparative analysis between scenarios with and without the proposed method demonstrates a noteworthy
decrease of 0.13 times in the Average collision count. |
|