TY - GEN
T1 - Magnetic 3-Axis Soft and Sensitive Fingertip Sensors Integration for the iCub Humanoid Robot
AU - Holgado, Alexis C.
AU - Piga, Nicola
AU - Tomo, Tito Pradhono
AU - Vezzani, Giulia
AU - Schmitz, Alexander
AU - Natale, Lorenzo
AU - Sugano, Shigeki
N1 - Funding Information:
ACKNOWLEDGMENT The authors would like to thank M. Accame, who helped with MTB integration at Istituto Italiano di Tecnologia, and A. Geier, N. Yalta and S. Funabashi from Waseda University, who provided general advice and suggestions regarding machine learning techniques. This research was partially supported by the JSPS Grant-in-Aid for Young Scientists (B) No.17K18183 and (B) No. 19K14948 and the Grant-in-Aid for Scientific Research No. 19H02116 and 19H01130. Part of this research was conducted at IIT with the support of Top Global University, Waseda University. Additional financial support was provided by the Ministry of Education, Science, Sports and Culture of Japan (Monbukagakusho).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - The humanoid robot iCub is currently equipped with an array of capacitive sensors that provide pressure information throughout the body of the robot. Even though for some applications this type of data is sufficient, it is not always the case for the fingertips of the robot. In particular, the current sensors do not provide enough information for performing agile manipulation, where both intensity and direction of the exerted force on the fingertips are relevant for the proper execution of the task. In this paper, we present a single 3-Axis small magnetic sensor module and we show its effectiveness when integrated into the fingertips of the iCub. The sensor module is derived from uSkin, presented in previous works from our laboratory. Replaceable fingertips were designed, built and integrated via software into the low level communication network of the robot, providing fast 3D information about the contact between the fingertips and objects. Additionally, we present two experiments demonstrating tasks that would not be possible to perform with the current fingertip sensors.
AB - The humanoid robot iCub is currently equipped with an array of capacitive sensors that provide pressure information throughout the body of the robot. Even though for some applications this type of data is sufficient, it is not always the case for the fingertips of the robot. In particular, the current sensors do not provide enough information for performing agile manipulation, where both intensity and direction of the exerted force on the fingertips are relevant for the proper execution of the task. In this paper, we present a single 3-Axis small magnetic sensor module and we show its effectiveness when integrated into the fingertips of the iCub. The sensor module is derived from uSkin, presented in previous works from our laboratory. Replaceable fingertips were designed, built and integrated via software into the low level communication network of the robot, providing fast 3D information about the contact between the fingertips and objects. Additionally, we present two experiments demonstrating tasks that would not be possible to perform with the current fingertip sensors.
UR - http://www.scopus.com/inward/record.url?scp=85077319996&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077319996&partnerID=8YFLogxK
U2 - 10.1109/Humanoids43949.2019.9035062
DO - 10.1109/Humanoids43949.2019.9035062
M3 - Conference contribution
AN - SCOPUS:85077319996
T3 - IEEE-RAS International Conference on Humanoid Robots
SP - 328
EP - 335
BT - 2019 IEEE-RAS 19th International Conference on Humanoid Robots, Humanoids 2019
PB - IEEE Computer Society
T2 - 19th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2019
Y2 - 15 October 2019 through 17 October 2019
ER -