We use perceptual methods, AI, and frugal robotics innovation to deliver transformative diagnostic and treatment solutions.
B415B Bessemer Building
South Kensington Campus
+44 (0)20 3312 5145
The HARMS lab leverages perceptually enabled methodologies, artificial intelligence, and frugal innovation in robotics (such as soft surgical robots) to deliver transformative solutions for diagnosis and treatment. Our research is driven by both problem-solving and curiosity, aiming to build a comprehensive understanding of the actions, interactions, and reactions occurring in the operating room. We focus on using robotic technologies to facilitate procedures that are not yet widely adopted, particularly in endoluminal surgery, such as advanced treatments for gastrointestinal cancer.
Mr Amirhosein Alian
Casual - Other work
Dr Said Alyacoubi
Clinical Research Fellows
Dr James P Avery
Honorary Lecturer
Mr Junhong Chen
Casual
Mr Kaizhong Deng
Research Postgraduate
Mr KAIZHE JIN
Research Postgraduate
Mr Hanqi LOU
Research Postgraduate
Dr George Mylonas BEng, MSc, DIC, PhD
Associate Professor in Robotics and Technology in Cancer
Dr Adrian Rubio Solis
Research Associate in Sensing and Machine Learning
Dr Jianlin Yang
Research Associate
Mr Zhangxi Zhou
Research Postgraduate
@inproceedings{Alian:2023:10.1109/RoboSoft55895.2023.10121967,
author = {Alian, A and Mylonas, G and Avery, J},
doi = {10.1109/RoboSoft55895.2023.10121967},
pages = {1--6},
publisher = {IEEE},
title = {Soft continuum actuator tip position and contact force prediction, using electrical impedance tomography and recurrent neural networks},
url = {http://dx.doi.org/10.1109/RoboSoft55895.2023.10121967},
year = {2023}
}
TY - CPAPER
AB - Enabling dexterous manipulation and safe human-robot interaction, soft robotsare widely used in numerous surgical applications. One of the complicationsassociated with using soft robots in surgical applications is reconstructingtheir shape and the external force exerted on them. Several sensor-based andmodel-based approaches have been proposed to address the issue. In this paper,a shape sensing technique based on Electrical Impedance Tomography (EIT) isproposed. The performance of this sensing technique in predicting the tipposition and contact force of a soft bending actuator is highlighted byconducting a series of empirical tests. The predictions were performed based ona data-driven approach using a Long Short-Term Memory (LSTM) recurrent neuralnetwork. The tip position predictions indicate the importance of using EIT dataalong with pressure inputs. Changing the number of EIT channels, we evaluatedthe effect of the number of EIT inputs on the accuracy of the predictions. Theleast RMSE values for the tip position are 3.6 and 4.6 mm in Y and Zcoordinates, respectively, which are 7.36% and 6.07% of the actuator's totalrange of motion. Contact force predictions were conducted in three differentbending angles and by varying the number of EIT channels. The results of thepredictions illustrated that increasing the number of channels contributes tohigher accuracy of the force estimation. The mean errors of using 8 channelsare 7.69%, 2.13%, and 2.96% of the total force range in three different bendingangles.
AU - Alian,A
AU - Mylonas,G
AU - Avery,J
DO - 10.1109/RoboSoft55895.2023.10121967
EP - 6
PB - IEEE
PY - 2023///
SN - 2769-4534
SP - 1
TI - Soft continuum actuator tip position and contact force prediction, using electrical impedance tomography and recurrent neural networks
UR - http://dx.doi.org/10.1109/RoboSoft55895.2023.10121967
UR - https://ieeexplore.ieee.org/abstract/document/10121967
ER -