Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enabling Tactile Feedback for Robotic Strawberry Handling using AST Skin

Vishnu Rajendran, Kiyanoush Nazari, Simon Parsons, Amir Ghalamzan

TL;DR

This work addresses the need for flexible, real-time tactile feedback in robotic fruit handling by deploying Acoustic Soft Tactile (AST) skin on a custom end-effector finger. A data-driven calibration maps acoustic channel modulations to contact forces using a simple FFT-based feature and an Exponential Gaussian Process, enabling force-controlled gripping of strawberry peduncles. In experiments, the system achieved a target grip of $2$ N with a maximum MAE of $0.31$ N, and calibration RMSE of $0.27$ N with $91.1%$ of predictions within $±0.5$ N and $99%$ within $±1.0$ N. The results demonstrate AST skin as a modular, low-cost tactile sensing solution capable of providing real-time tactile feedback for manipulation tasks in precision agriculture, with potential field deployment on strawberry-harvesting robots.

Abstract

Acoustic Soft Tactile (AST) skin is a novel sensing technology which derives tactile information from the modulation of acoustic waves travelling through the skin's embedded acoustic channels. A generalisable data-driven calibration model maps the acoustic modulations to the corresponding tactile information in the form of contact forces with their contact locations and contact geometries. AST skin technology has been highlighted for its easy customisation. As a case study, this paper discusses the possibility of using AST skin on a custom-built robotic end effector finger for strawberry handling. The paper delves into the design, prototyping, and calibration method to sensorise the end effector finger with AST skin. A real-time force-controlled gripping experiment is conducted with the sensorised finger to handle strawberries by their peduncle. The finger could successfully grip the strawberry peduncle by maintaining a preset force of 2 N with a maximum Mean Absolute Error (MAE) of 0.31 N over multiple peduncle diameters and strawberry weight classes. Moreover, this study sets confidence in the usability of AST skin in generating real-time tactile feedback for robot manipulation tasks.

Enabling Tactile Feedback for Robotic Strawberry Handling using AST Skin

TL;DR

This work addresses the need for flexible, real-time tactile feedback in robotic fruit handling by deploying Acoustic Soft Tactile (AST) skin on a custom end-effector finger. A data-driven calibration maps acoustic channel modulations to contact forces using a simple FFT-based feature and an Exponential Gaussian Process, enabling force-controlled gripping of strawberry peduncles. In experiments, the system achieved a target grip of N with a maximum MAE of N, and calibration RMSE of N with of predictions within N and within N. The results demonstrate AST skin as a modular, low-cost tactile sensing solution capable of providing real-time tactile feedback for manipulation tasks in precision agriculture, with potential field deployment on strawberry-harvesting robots.

Abstract

Acoustic Soft Tactile (AST) skin is a novel sensing technology which derives tactile information from the modulation of acoustic waves travelling through the skin's embedded acoustic channels. A generalisable data-driven calibration model maps the acoustic modulations to the corresponding tactile information in the form of contact forces with their contact locations and contact geometries. AST skin technology has been highlighted for its easy customisation. As a case study, this paper discusses the possibility of using AST skin on a custom-built robotic end effector finger for strawberry handling. The paper delves into the design, prototyping, and calibration method to sensorise the end effector finger with AST skin. A real-time force-controlled gripping experiment is conducted with the sensorised finger to handle strawberries by their peduncle. The finger could successfully grip the strawberry peduncle by maintaining a preset force of 2 N with a maximum Mean Absolute Error (MAE) of 0.31 N over multiple peduncle diameters and strawberry weight classes. Moreover, this study sets confidence in the usability of AST skin in generating real-time tactile feedback for robot manipulation tasks.
Paper Structure (10 sections, 2 equations, 6 figures, 4 tables)

This paper contains 10 sections, 2 equations, 6 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. Study on Gripping Force
  4. AST Finger Design
  5. Skin Calibration
  6. Performance Evaluation of AST Finger
  7. Gripper Force Controller
  8. Experimental Trials
  9. Results and Discussions
  10. Conclusion

Figures (6)

  • Figure 1: Demonstration of AST sensing technology to generate tactile force feedback for a robot manipulation task: The AST Skin is attached to a custom end effector finger (the AST finger), and the force feedback from the AST finger is used in performing force-controlled handling of strawberries by gripping their peduncle. This finger assembly is mounted on an SMC gripper for validation purposes, but later, it will be attached to a custom-built strawberry harvesting end-effector
  • Figure 2: (a). AST finger with its mating dummy finger, (b). Skin mould: The two semi-cylindrical projections in each mould help to create the skin's cylindrical cavity while joining two halves of the cured silicone
  • Figure 3: AST finger calibration: The calibrated area of the AST finger (left), the calibration set up consisting of 6 DOF UFactory xArm, axial load cell with peg attached to the robot arm wrist (middle), the calibration peg with cylindrical profiled edge to simulate the shape of strawberry peduncle (right)
  • Figure 4: Strawberry samples selected for the gripping trials
  • Figure 5: (a). AST finger assembly connected to the SMC gripper for gripping trials, (b). Experimental setup for the gripping trials: Point A is the picking point, B is a via point between A and C, and C is the dropping point
  • ...and 1 more figures