Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Single and bi-layered 2-D acoustic soft tactile skin (AST2)

Vishnu Rajendran, Simon Parsons, Amir Ghalamzan E

TL;DR

This work tackles the challenge of accurate 2-D tactile feature estimation with a low-cost, easily customizable soft tactile skin. It introduces Acoustic Soft Tactile (AST) Skin, where acoustic channels beneath the sensing surface transduce deformations into modulated signals, decoded by data-driven models to predict contact forces, location, and geometry. A modular comparison of single-layer and bi-layer channel designs demonstrates that the bi-layer configuration yields superior geometry sensing while maintaining force accuracy, validated through calibration and real-time tests. The approach offers a scalable, reshapable tactile sensing solution with potential impact on robotic manipulation of soft and deformable objects.

Abstract

This paper aims to present an innovative and cost-effective design for Acoustic Soft Tactile (AST) Skin, with the primary goal of significantly enhancing the accuracy of 2-D tactile feature estimation. The existing challenge lies in achieving precise tactile feature estimation, especially concerning contact geometry characteristics, using cost-effective solutions. We hypothesise that by harnessing acoustic energy through dedicated acoustic channels in 2 layers beneath the sensing surface and analysing amplitude modulation, we can effectively decode interactions on the sensory surface, thereby improving tactile feature estimation. Our approach involves the distinct separation of hardware components responsible for emitting and receiving acoustic signals, resulting in a modular and highly customizable skin design. Practical tests demonstrate the effectiveness of this novel design, achieving remarkable precision in estimating contact normal forces (MAE < 0.8 N), 2D contact localisation (MAE < 0.7 mm), and contact surface diameter (MAE < 0.3 mm). In conclusion, the AST skin, with its innovative design and modular architecture, successfully addresses the challenge of tactile feature estimation. The presented results showcase its ability to precisely estimate various tactile features, making it a practical and cost-effective solution for robotic applications.

Single and bi-layered 2-D acoustic soft tactile skin (AST2)

TL;DR

This work tackles the challenge of accurate 2-D tactile feature estimation with a low-cost, easily customizable soft tactile skin. It introduces Acoustic Soft Tactile (AST) Skin, where acoustic channels beneath the sensing surface transduce deformations into modulated signals, decoded by data-driven models to predict contact forces, location, and geometry. A modular comparison of single-layer and bi-layer channel designs demonstrates that the bi-layer configuration yields superior geometry sensing while maintaining force accuracy, validated through calibration and real-time tests. The approach offers a scalable, reshapable tactile sensing solution with potential impact on robotic manipulation of soft and deformable objects.

Abstract

This paper aims to present an innovative and cost-effective design for Acoustic Soft Tactile (AST) Skin, with the primary goal of significantly enhancing the accuracy of 2-D tactile feature estimation. The existing challenge lies in achieving precise tactile feature estimation, especially concerning contact geometry characteristics, using cost-effective solutions. We hypothesise that by harnessing acoustic energy through dedicated acoustic channels in 2 layers beneath the sensing surface and analysing amplitude modulation, we can effectively decode interactions on the sensory surface, thereby improving tactile feature estimation. Our approach involves the distinct separation of hardware components responsible for emitting and receiving acoustic signals, resulting in a modular and highly customizable skin design. Practical tests demonstrate the effectiveness of this novel design, achieving remarkable precision in estimating contact normal forces (MAE < 0.8 N), 2D contact localisation (MAE < 0.7 mm), and contact surface diameter (MAE < 0.3 mm). In conclusion, the AST skin, with its innovative design and modular architecture, successfully addresses the challenge of tactile feature estimation. The presented results showcase its ability to precisely estimate various tactile features, making it a practical and cost-effective solution for robotic applications.
Paper Structure (5 sections, 7 figures, 3 tables)

This paper contains 5 sections, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. AST Sensing Technology
  3. Single and Bi-layered AST skin
  4. Results and discussion
  5. Conclusion

Figures (7)

  • Figure 1: Initial validation of the frame-based AST sensor with cylindrical channel with three sensing points at 20 mm spatial resolution (left), robot-based calibration setup (right) vishnu2023acoustic.
  • Figure 2: AST Skin Configuration: (a) Single-layered skin (b) Bi-layered skin (c) Tactile Feature Prediction Model; Both skin designs are calibrated with calibration points at a 3 mm spatial resolution, identified by the following coordinates: A={10,10}, B={13,10}, C={16,10}, D={16,13}, E={13,13}, F={10,13}, G={16,16}, H={13,16}, I={10,16}
  • Figure 3: Variation of FFT data at locations A, B, and C when force varies from 0 to 30$^{+1}$ N for (a) 300 Hz, (b) 500 Hz, (c) 700 Hz, and (d) 900 Hz.
  • Figure 4: Skin design: (a). Single-layer (left) skin and Bi-layer skin (right)
  • Figure 5: Prototyping process: (a) 3D printed moulds (b). Silicone gel mixed with the curing catalyst are poured into the mould (c). Cured skin is removed from the mould (d). Cured skin halves joined to make the single-layered skin (top), and two single-layered skin joined orthogonally to form the bi-layered skin (bottom) (e). Connecting flexible tube to extend the acoustic channels (f). Mounting the speaker and microphone on the holder and fastening to the flexible tubes
  • ...and 2 more figures