DenseTact 2.0: Optical Tactile Sensor for Shape and Force Reconstruction
Open Access
- 29 May 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12549-12555
Abstract
Collaborative robots stand to have an immense impact on both human welfare in domestic service applications and industrial superiority in advanced manufacturing with dexterous assembly. The outstanding challenge is providing robotic fingertips with a physical design that makes them adept at performing dexterous tasks that require high-resolution, calibrated shape reconstruction and force sensing. In this work, we present DenseTact 2.0, an optical-tactile sensor capable of visualizing the deformed surface of a soft fingertip and using that image in a neural network to perform both calibrated shape reconstruction and 6-axis wrench estimation. We demon-strate the sensor accuracy of 0.3633mm per pixel for shape reconstruction, 0.410N for forces, 0.387N. mm for torques, and the ability to calibrate new fingers through transfer learning, which achieves comparable performance with only 12% of the non-transfer learning dataset size.Keywords
All Related Versions
Funding Information
- National Science Foundation (2142773)
This publication has 21 references indexed in Scilit:
- High-Resolution 3-Dimensional Contact Deformation Tracking for FingerVision Sensor With Dense Random Color PatternIEEE Robotics and Automation Letters, 2021
- Event-Driven Visual-Tactile Sensing and Learning for Robots2020
- OmniTact: A Multi-Directional High-Resolution Touch Sensor2020
- DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor With Application to In-Hand ManipulationIEEE Robotics and Automation Letters, 2020
- Dynamically Reconfigurable Tactile Sensor for Robotic ManipulationIEEE Robotics and Automation Letters, 2020
- Shear, Torsion and Pressure Tactile Sensor via Plastic Optofiber Guided ImagingIEEE Robotics and Automation Letters, 2020
- Dense Tactile Force Estimation using GelSlim and inverse FEM2019
- Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulation2019
- Densely Connected Convolutional Networks2017
- A flexible capacitive tactile sensing array with floating electrodesJournal of Micromechanics and Microengineering, 2009