Autoencoding a Soft Touch to Learn Grasping from On-Land to Underwater

Guo, Ning1; Han, Xudong1; Liu, Xiaobo1; Zhong, Shuqiao2; Zhou, Zhiyuan2; Lin, Jian2; Dai, Jiansheng3; Wan, Fang3,4; Song, Chaoyang5

2023-10-01

10.1002/aisy.202300382

ADVANCED INTELLIGENT SYSTEMS   Impact Factor & Quartile

2640-4567

["Robots play a critical role as the physical agent of human operators in exploring the ocean. However, it remains challenging to grasp objects reliably while fully submerging under a highly pressurized aquatic environment with little visible light, mainly due to the fluidic interference on the tactile mechanics between the finger and object surfaces. This study investigates the transferability of grasping knowledge from on-land to underwater via a vision-based soft robotic finger that learns 6D forces and torques (FT) using a supervised variational autoencoder (SVAE). A high-framerate camera captures the whole-body deformations while a soft robotic finger interacts with physical objects on-land and underwater. Results show that the trained SVAE model learns a series of latent representations of the soft mechanics transferable from land to water, presenting a superior adaptation to the changing environments against commercial FT sensors. Soft, delicate, and reactive grasping enabled by tactile intelligence enhances the gripper's underwater interaction with improved reliability and robustness at a much-reduced cost, paving the path for learning-based intelligent grasping to support fundamental scientific discoveries in environmental and ocean research.","A soft robotic finger with in-finger vision capable of transferring grasping knowledge from on-land to underwater by learning 6D forces and torques using a supervised variational autoencoder is presented, resulting in a learning-based approach to introduce tactile intelligence for soft, delicate, and reactive grasping underwater, making it a promising solution that supports scientific discoveries in interdisciplinary research.image (c) 2023 WILEY-VCH GmbH"]

soft robotics tactile learning underwater grasping

SCI

English

First ; Corresponding

This work was partly supported by the Ministry of Science and Technology of China (2022YFB4701200), the National Natural Science Foundation of China (62206119), the Science, Technology, and Innovation Commission of Shenzhen Municipality (ZDSYS2022052717140[2022YFB4701200] ; Ministry of Science and Technology of China[62206119] ; National Natural Science Foundation of China["ZDSYS20220527171403009","JCYJ20220818100417038"]

Automation & Control Systems ; Computer Science ; Robotics

Automation & Control Systems ; Computer Science, Artificial Intelligence ; Robotics

WOS:001087503800001

WILEY

Web of Science

1.Southern Univ Sci & Technol, Dept Mech & Energy Engn, Shenzhen 518055, Peoples R China
2.Southern Univ Sci & Technol, Dept Ocean Sci & Engn, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Shenzhen Key Lab Intelligent Robot & Flexible Mfg, Shenzhen 518055, Peoples R China
4.Southern Univ Sci & Technol, Sch Design, Shenzhen 518055, Guangdong, Peoples R China
5.Southern Univ Sci & Technol, Guangdong Prov Key Lab Human Augmentat & Rehabil R, Shenzhen 518055, Guangdong, Peoples R China

Guo, Ning,Han, Xudong,Liu, Xiaobo,et al. Autoencoding a Soft Touch to Learn Grasping from On-Land to Underwater[J]. ADVANCED INTELLIGENT SYSTEMS,2023.

Guo, Ning.,Han, Xudong.,Liu, Xiaobo.,Zhong, Shuqiao.,Zhou, Zhiyuan.,...&Song, Chaoyang.(2023).Autoencoding a Soft Touch to Learn Grasping from On-Land to Underwater.ADVANCED INTELLIGENT SYSTEMS.

Guo, Ning,et al."Autoencoding a Soft Touch to Learn Grasping from On-Land to Underwater".ADVANCED INTELLIGENT SYSTEMS (2023).