TY - GEN
T1 - Pick and Place Robot Using Visual Feedback Control and Transfer Learning-Based CNN
AU - Nagata, Fusaomi
AU - Miki, Kohei
AU - Otsuka, Akimasa
AU - Yoshida, Kazushi
AU - Watanabe, Keigo
AU - Habib, Maki K.
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/10/13
Y1 - 2020/10/13
N2 - Artificial neural network (ANN) which has four or more layers structure is called deep NN (DNN) and it is recognized as one of promising machine learning techniques. Convolutional neural network (CNN) is widely used and powerful structure for image recognition and/or defect inspection. It is also known that support vector machine (SVM) has a superior ability for binary classification in spite of only having two layers. The authors already have developed a CNN SVM design and training tool for defect detection of resin molded articles, while the effectiveness and the validity have been proved through several CNNs design, training and evaluation. The tool further enables to facilitate the design of a CNN model based on transfer learning concept. In this paper, a pick and place robot is introduced while implementing a visual feedback control and a transfer learning-based CNN. The visual feedback control enables to omit the complicated calibration between image and robot coordinate systems, also the transfer learning-based CNN allows the robot to estimate the orientation of target objects for dexterous picking operation. The usefulness and validity of the system is confirmed through pick and place experiments using a small articulated robot named DOBOT.
AB - Artificial neural network (ANN) which has four or more layers structure is called deep NN (DNN) and it is recognized as one of promising machine learning techniques. Convolutional neural network (CNN) is widely used and powerful structure for image recognition and/or defect inspection. It is also known that support vector machine (SVM) has a superior ability for binary classification in spite of only having two layers. The authors already have developed a CNN SVM design and training tool for defect detection of resin molded articles, while the effectiveness and the validity have been proved through several CNNs design, training and evaluation. The tool further enables to facilitate the design of a CNN model based on transfer learning concept. In this paper, a pick and place robot is introduced while implementing a visual feedback control and a transfer learning-based CNN. The visual feedback control enables to omit the complicated calibration between image and robot coordinate systems, also the transfer learning-based CNN allows the robot to estimate the orientation of target objects for dexterous picking operation. The usefulness and validity of the system is confirmed through pick and place experiments using a small articulated robot named DOBOT.
KW - convolutional neural network
KW - pick and place
KW - robot
KW - transfer learning
UR - http://www.scopus.com/inward/record.url?scp=85096542482&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85096542482&partnerID=8YFLogxK
U2 - 10.1109/ICMA49215.2020.9233829
DO - 10.1109/ICMA49215.2020.9233829
M3 - Conference contribution
AN - SCOPUS:85096542482
T3 - 2020 IEEE International Conference on Mechatronics and Automation, ICMA 2020
SP - 850
EP - 855
BT - 2020 IEEE International Conference on Mechatronics and Automation, ICMA 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th IEEE International Conference on Mechatronics and Automation, ICMA 2020
Y2 - 13 October 2020 through 16 October 2020
ER -