Contact Force Prediction for a Robotic Transesophageal Ultrasound Probe via Operating Torque Sensing

TY - CONF

T1 - Contact Force Prediction for a Robotic Transesophageal Ultrasound Probe via Operating Torque Sensing

AU - Xie, Yiping

AU - Hou, Xilong

AU - Liu, Hongbin

AU - Housden, James

AU - Rhode, Kawal

AU - Hou, Zeng Guang

AU - Wang, Shuangyi

N1 - Funding Information: Acknowledgments. This work was supported in part by the National Natural Science Foundation of China under Grant 62003339 and in part by the InnoHK program. Publisher Copyright: © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2022/10

Y1 - 2022/10

N2 - The advent of transesophageal ultrasound robots has provided a new idea to simplify relevant clinical procedures. However, the existing add-on robots often lack the ability to predict the contact force between the probe tip and the tissue. This makes the control of this robot under teleoperation lacking in tactile feedback and difficult to obtain effective safety. In this study, we propose a neural network-based internal resistance modeling method. Based on this, we experimentally calibrated the relationship between the tip contact force and handwheel torque through a self-learning idea. The experimental results show that a microcontroller-deployable lightweight neural network can achieve a good result on the fitting of the internal resistance, with its standard deviation being less than 3%. Moreover, a good linear correlation between the tip contact force and the handwheel torque was demonstrated in the case of passively applied forces. Independent experiments with actively applied forces further demonstrated the feasibility of the prediction method, especially in the forward bending process, with the prediction error mostly within 20% of the baseline force. Therefore, we believe that the proposed method has good potential to improve the safe use of transesophageal ultrasound robots.

AB - The advent of transesophageal ultrasound robots has provided a new idea to simplify relevant clinical procedures. However, the existing add-on robots often lack the ability to predict the contact force between the probe tip and the tissue. This makes the control of this robot under teleoperation lacking in tactile feedback and difficult to obtain effective safety. In this study, we propose a neural network-based internal resistance modeling method. Based on this, we experimentally calibrated the relationship between the tip contact force and handwheel torque through a self-learning idea. The experimental results show that a microcontroller-deployable lightweight neural network can achieve a good result on the fitting of the internal resistance, with its standard deviation being less than 3%. Moreover, a good linear correlation between the tip contact force and the handwheel torque was demonstrated in the case of passively applied forces. Independent experiments with actively applied forces further demonstrated the feasibility of the prediction method, especially in the forward bending process, with the prediction error mostly within 20% of the baseline force. Therefore, we believe that the proposed method has good potential to improve the safe use of transesophageal ultrasound robots.

KW - Contact force estimation

KW - Continuum robot

KW - Ultrasound robot

UR - http://www.scopus.com/inward/record.url?scp=85138766803&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-16902-1_15

DO - 10.1007/978-3-031-16902-1_15

M3 - Paper

AN - SCOPUS:85138766803

SP - 152

EP - 161

T2 - 3rd International Workshop of Advances in Simplifying Medical Ultrasound, ASMUS 2022, held in Conjunction with 25th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2022

Y2 - 18 September 2022 through 18 September 2022

ER -