Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Soft e-Textile Sensor for Enhanced Deep Learning-based Shape Sensing of Soft Continuum Robots

Eric Vincent Galeta, Ayman A. Nada, Sabah M. Ahmed, Victor Parque, Haitham El-Hussieny

TL;DR

The paper tackles the challenge of sensing shape in soft continuum robots, where rigid sensors are bulky and incompatible. It introduces a soft e-textile resistive sensor integrated into the robot surface and uses a CNN to regress curvature $\kappa$ and planar angle $\phi$, converting 16 sensor readings into a 1330×4×4 input representation. Experimental results show the sensor reliably captures deformation through resistance changes and the CNN achieves accurate shape estimates with robust validation, including 5-fold cross-validation. This approach enables real-time, flexible, and potentially safer navigation for soft robotics, reducing reliance on traditional stiff sensing modalities.

Abstract

The safety and accuracy of robotic navigation hold paramount importance, especially in the realm of soft continuum robotics, where the limitations of traditional rigid sensors become evident. Encoders, piezoresistive, and potentiometer sensors often fail to integrate well with the flexible nature of these robots, adding unwanted bulk and rigidity. To overcome these hurdles, our study presents a new approach to shape sensing in soft continuum robots through the use of soft e-textile resistive sensors. This sensor, designed to flawlessly integrate with the robot's structure, utilizes a resistive material that adjusts its resistance in response to the robot's movements and deformations. This adjustment facilitates the capture of multidimensional force measurements across the soft sensor layers. A deep Convolutional Neural Network (CNN) is employed to decode the sensor signals, enabling precise estimation of the robot's shape configuration based on the detailed data from the e-textile sensor. Our research investigates the efficacy of this e-textile sensor in determining the curvature parameters of soft continuum robots. The findings are encouraging, showing that the soft e-textile sensor not only matches but potentially exceeds the capabilities of traditional rigid sensors in terms of shape sensing and estimation. This advancement significantly boosts the safety and efficiency of robotic navigation systems.

A Soft e-Textile Sensor for Enhanced Deep Learning-based Shape Sensing of Soft Continuum Robots

TL;DR

The paper tackles the challenge of sensing shape in soft continuum robots, where rigid sensors are bulky and incompatible. It introduces a soft e-textile resistive sensor integrated into the robot surface and uses a CNN to regress curvature and planar angle , converting 16 sensor readings into a 1330×4×4 input representation. Experimental results show the sensor reliably captures deformation through resistance changes and the CNN achieves accurate shape estimates with robust validation, including 5-fold cross-validation. This approach enables real-time, flexible, and potentially safer navigation for soft robotics, reducing reliance on traditional stiff sensing modalities.

Abstract

The safety and accuracy of robotic navigation hold paramount importance, especially in the realm of soft continuum robotics, where the limitations of traditional rigid sensors become evident. Encoders, piezoresistive, and potentiometer sensors often fail to integrate well with the flexible nature of these robots, adding unwanted bulk and rigidity. To overcome these hurdles, our study presents a new approach to shape sensing in soft continuum robots through the use of soft e-textile resistive sensors. This sensor, designed to flawlessly integrate with the robot's structure, utilizes a resistive material that adjusts its resistance in response to the robot's movements and deformations. This adjustment facilitates the capture of multidimensional force measurements across the soft sensor layers. A deep Convolutional Neural Network (CNN) is employed to decode the sensor signals, enabling precise estimation of the robot's shape configuration based on the detailed data from the e-textile sensor. Our research investigates the efficacy of this e-textile sensor in determining the curvature parameters of soft continuum robots. The findings are encouraging, showing that the soft e-textile sensor not only matches but potentially exceeds the capabilities of traditional rigid sensors in terms of shape sensing and estimation. This advancement significantly boosts the safety and efficiency of robotic navigation systems.
Paper Structure (11 sections, 2 equations, 10 figures, 1 table)

This paper contains 11 sections, 2 equations, 10 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. E-textile Sensor Design
  3. Deep-CNN Shape Sensing
  4. Data Collection and Processing
  5. CNN Model Architectures
  6. Training of CNN model
  7. Results and Discussion
  8. e-Textile Sensor Responsiveness
  9. CNN Model Performance
  10. K-Fold Cross Validation
  11. Conclusion

Figures (10)

  • Figure 1: The sensor design, including the piezoresistive textile material and copper electrodes, is used to detect changes in pressure and strain.
  • Figure 2: Illustration of the design of our soft force sensor with stacked layers.
  • Figure 3: Illustration of the Soft E-Textile Sensor Interface: This diagram showcases the e-textile sensor at the core, flanked by copper electrodes, and encased within fabric insulation layers.
  • Figure 4: A one-section continuum robot is covered with the soft e-textile sensor comprising 16 sensing points arranged in 4 $\times$ 4 matrix.
  • Figure 5: The CNN architectures employed in estimating the curvature of the soft robot from the sensor readings.
  • ...and 5 more figures