Digital twin for autonomous collaborative robot by using synthetic data and reinforcement learning

被引:14
作者
Kim, Dongjun [1 ]
Choi, Minho [1 ]
Um, Jumyung [1 ]
机构
[1] Kyung Hee Univ, Dept Artificial Intelligence, 1732 Deogyeong daero, Yongin 17104, Gyeonggi Do, South Korea
关键词
Object detection; Synthetic data; Point cloud; Reinforcement learning; Digital twin; VIRTUAL-REALITY; MODEL;
D O I
10.1016/j.rcim.2023.102632
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Training robots in real-world environments can be challenging due to time and cost constraints. To overcome these limitations, robots can be trained in virtual environments using Reinforcement Learning (RL). However, this approach faces a significant challenge in obtaining suitable data. This paper proposes a novel method for training collaborative robots in virtual environments using synthetic data and the point cloud framework. The proposed method is divided into four stages: data generation, 3D object classification, robot training, and integration. The first stage of the proposed method is data generation, where synthetic data is generated to resemble real-world scenarios. This data is then used to train robots in virtual environments. The second stage is 3D object classification, where the generated data is used to classify objects in 3D space. In the third stage, robots are trained using RL algorithms, which are based on the generated data and the 3D object classifications. Finally, the effectiveness of the proposed method is integrated in the fourth stage. This proposed method has the potential to be a significant contribution to the field of robotics and 3D computer vision. By using synthetic data and the point cloud framework, the proposed method offers an efficient and cost-effective solution for training robots in virtual environments. The ability to reduce the time and cost required for training robots in real-world environments is a major advantage of this proposed method, and has the potential to revolutionize the field of robotics and 3D computer vision.
引用
收藏
页数:13
相关论文
共 50 条
[1]   Digital Twin System Framework for Gripping Deformable Objects with Synthetic Data and Reinforcement Learning [J].
Choi, Minho ;
Kim, Dongjun ;
Moon, Junhyuck ;
Kim, Minji ;
Um, Jumyung .
FLEXIBLE AUTOMATION AND INTELLIGENT MANUFACTURING: MANUFACTURING INNOVATION AND PREPAREDNESS FOR THE CHANGING WORLD ORDER, FAIM 2024, VOL 1, 2024, :98-106
[2]   Multi-dimensional digital twin for cable assembly by synthetic data and reinforcement learning [J].
Choi, Minho ;
Kim, Dongjun ;
Moon, Junhyuck ;
Kim, Minji ;
Um, Jumyung .
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2025,
[3]   Digital twin-based reinforcement learning framework: application to autonomous mobile robot dispatching [J].
Jaoua, Amel ;
Masmoudi, Samar ;
Negri, Elisa .
INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2024, 37 (10-11) :1335-1358
[4]   A robot arm digital twin utilising reinforcement learning [J].
Matulis, Marius ;
Harvey, Carlo .
COMPUTERS & GRAPHICS-UK, 2021, 95 :106-114
[5]   Reinforcement Learning of Robot Behavior based on a Digital Twin [J].
Hassel, Tobias ;
Hofmann, Oliver .
ICPRAM: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS, 2020, :381-386
[6]   Enhancing titanium spacer defect detection through reinforcement learning-optimized digital twin and synthetic data generation [J].
Mohanty, Sankarsan ;
Su, Eugene ;
Ho, Chao-Ching .
JOURNAL OF ELECTRONIC IMAGING, 2024, 33 (01)
[7]   Control framework for collaborative robot using imitation learning-based teleoperation from human digital twin to robot digital twin* [J].
Lee, Hyunsoo ;
Kim, Seong Dae ;
Amin, Mohammad Aman Ullah Al .
MECHATRONICS, 2022, 85
[8]   Reinforcement Learning from Simulation to Real World Autonomous Driving using Digital Twin [J].
Voogd, Kevin L. ;
Allamaa, Jean Pierre ;
Alonso-Mora, Javier ;
Son, Tong Duy .
IFAC PAPERSONLINE, 2023, 56 (02) :1510-1515
[9]   Digital Twin for a Collaborative Painting Robot [J].
Chancharoen, Ratchatin ;
Chaiprabha, Kantawatchr ;
Wuttisittikulkij, Lunchakorn ;
Asdornwised, Widhyakorn ;
Saadi, Muhammad ;
Phanomchoeng, Gridsada .
SENSORS, 2023, 23 (01)
[10]   Fruit Picking Robot Arm Training Solution Based on Reinforcement Learning in Digital Twin [J].
Tian X. ;
Pan B. ;
Bai L. ;
Wang G. ;
Mo D. .
Journal of ICT Standardization, 2023, 11 (03) :261-282