Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

TacPalm: A Soft Gripper with a Biomimetic Optical Tactile Palm for Stable Precise Grasping

Xuyang Zhang, Tianqi Yang, Dandan Zhang, Nathan F. Lepora

Abstract

Manipulating fragile objects in environments such as homes and factories requires stable and gentle grasping along with precise and safe placement. Compared to traditional rigid grippers, the use of soft grippers reduces the control complexity and the risk of damaging objects. However, it is challenging to integrate camera-based optical tactile sensing into a soft gripper without compromising the flexibility and adaptability of the fingers, while also ensuring that the precision of tactile perception remains unaffected by passive deformations of the soft structure during object contact. In this paper, we demonstrate a modular soft two-fingered gripper with a 3D-printed optical tactile sensor (the TacTip) integrated in the palm. We propose a soft-grasping strategy that includes three functions: light contact detection, grasp pose adjustment and loss-of-contact detection, so that objects of different shapes and sizes can be grasped stably and placed precisely, which we test with both artificial and household objects. By sequentially implementing these three functions, the grasp success rate progressively improves from 45% without any functions, to 59% with light contact detection, 90% with grasp pose adjustment, and 97% with loss-of-contact detection, achieving a sub-millimeter placement precision. Overall, this work demonstrates the feasibility and utility of integrating optical tactile sensors into the palm of a soft gripper, of applicability to various types of soft manipulators. The proposed grasping strategy has potential applications in areas such as fragile product processing and home assistance.

TacPalm: A Soft Gripper with a Biomimetic Optical Tactile Palm for Stable Precise Grasping

Abstract

Manipulating fragile objects in environments such as homes and factories requires stable and gentle grasping along with precise and safe placement. Compared to traditional rigid grippers, the use of soft grippers reduces the control complexity and the risk of damaging objects. However, it is challenging to integrate camera-based optical tactile sensing into a soft gripper without compromising the flexibility and adaptability of the fingers, while also ensuring that the precision of tactile perception remains unaffected by passive deformations of the soft structure during object contact. In this paper, we demonstrate a modular soft two-fingered gripper with a 3D-printed optical tactile sensor (the TacTip) integrated in the palm. We propose a soft-grasping strategy that includes three functions: light contact detection, grasp pose adjustment and loss-of-contact detection, so that objects of different shapes and sizes can be grasped stably and placed precisely, which we test with both artificial and household objects. By sequentially implementing these three functions, the grasp success rate progressively improves from 45% without any functions, to 59% with light contact detection, 90% with grasp pose adjustment, and 97% with loss-of-contact detection, achieving a sub-millimeter placement precision. Overall, this work demonstrates the feasibility and utility of integrating optical tactile sensors into the palm of a soft gripper, of applicability to various types of soft manipulators. The proposed grasping strategy has potential applications in areas such as fragile product processing and home assistance.
Paper Structure (31 sections, 17 figures, 2 tables)

This paper contains 31 sections, 17 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Tactile sensing in soft grippers
  4. Tactile palms in robot hands
  5. Camera-based optical tactile sensing
  6. Hardware Methods
  7. Overall Design of the Soft Gripper with TacPalm
  8. Base Design and Robot Mount
  9. Finger Design
  10. Tactile Sensor Design
  11. Fabrication
  12. Simulation Modeling
  13. 3D-printed Object Set
  14. Algorithmic Methods
  15. Overall Grasping Strategy
  16. ...and 16 more sections

Figures (17)

  • Figure 1: (a) Overview of the structural design. (1-Mounting flange. 2-Gripper body and housing. 3-Camera. 4-Camera mount. 5-LED ring. 6-Acrylic window. 7-Tip mount. 8-Flat skin with pins (markers). 9-Finger base. 10-Air tube. 11-Soft finger. 12-Air passage. 13-Embedded slot. 14-Air cavity. 15-Connected air passage. 16-Fingertip.) (b) The working state of the proposed soft tactile gripper. (c) Contact modelling of the proposed gripper. (Stress analysis and grasping deformation when grasping an apple (up) and an egg (down).
  • Figure 2: The fabrication process of the soft gripper.
  • Figure 3: 3D-printed object set used for training and testing.
  • Figure 4: Control flow of the soft grasping strategy, which includes the light contact detection, grasp pose adjustment and loss-of-contact detection, ensuring a stable and robust object grasping.
  • Figure 5: Pose adjustment of objects with a curved surface. (a) Initial contact (overhead view). (b) Grasp pose adjustment to be central and aligned with the minor axis of the object.
  • ...and 12 more figures