Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater
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 tactil...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Advanced Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/aisy.202300382 |
| _version_ | 1797348540613132288 |
|---|---|
| author | Ning Guo Xudong Han Xiaobo Liu Shuqiao Zhong Zhiyuan Zhou Jian Lin Jiansheng Dai Fang Wan Chaoyang Song |
| author_facet | Ning Guo Xudong Han Xiaobo Liu Shuqiao Zhong Zhiyuan Zhou Jian Lin Jiansheng Dai Fang Wan Chaoyang Song |
| author_sort | Ning Guo |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T12:07:27Z |
| format | Article |
| id | doaj.art-2a6f54a5c8fb4535a6a8ae271d9fa0b6 |
| institution | Directory Open Access Journal |
| issn | 2640-4567 |
| language | English |
| last_indexed | 2024-03-08T12:07:27Z |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advanced Intelligent Systems |
| spelling | doaj.art-2a6f54a5c8fb4535a6a8ae271d9fa0b62024-01-23T05:32:23ZengWileyAdvanced Intelligent Systems2640-45672024-01-0161n/an/a10.1002/aisy.202300382Autoencoding a Soft Touch to Learn Grasping from On‐Land to UnderwaterNing Guo0Xudong Han1Xiaobo Liu2Shuqiao Zhong3Zhiyuan Zhou4Jian Lin5Jiansheng Dai6Fang Wan7Chaoyang Song8Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen 518055 ChinaDepartment of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen 518055 ChinaDepartment of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen 518055 ChinaDepartment of Ocean Science and Engineering Southern University of Science and Technology Shenzhen 518055 ChinaDepartment of Ocean Science and Engineering Southern University of Science and Technology Shenzhen 518055 ChinaDepartment of Ocean Science and Engineering Southern University of Science and Technology Shenzhen 518055 ChinaShenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Southern University of Science and Technology Shenzhen 518055 ChinaShenzhen Key Laboratory of Intelligent Robotics and Flexible Manufacturing Southern University of Science and Technology Shenzhen 518055 ChinaGuangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen Guangdong 518055 ChinaRobots 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.https://doi.org/10.1002/aisy.202300382soft roboticstactile learningunderwater grasping |
| spellingShingle | Ning Guo Xudong Han Xiaobo Liu Shuqiao Zhong Zhiyuan Zhou Jian Lin Jiansheng Dai Fang Wan Chaoyang Song Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater Advanced Intelligent Systems soft robotics tactile learning underwater grasping |
| title | Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater |
| title_full | Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater |
| title_fullStr | Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater |
| title_full_unstemmed | Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater |
| title_short | Autoencoding a Soft Touch to Learn Grasping from On‐Land to Underwater |
| title_sort | autoencoding a soft touch to learn grasping from on land to underwater |
| topic | soft robotics tactile learning underwater grasping |
| url | https://doi.org/10.1002/aisy.202300382 |
| work_keys_str_mv | AT ningguo autoencodingasofttouchtolearngraspingfromonlandtounderwater AT xudonghan autoencodingasofttouchtolearngraspingfromonlandtounderwater AT xiaoboliu autoencodingasofttouchtolearngraspingfromonlandtounderwater AT shuqiaozhong autoencodingasofttouchtolearngraspingfromonlandtounderwater AT zhiyuanzhou autoencodingasofttouchtolearngraspingfromonlandtounderwater AT jianlin autoencodingasofttouchtolearngraspingfromonlandtounderwater AT jianshengdai autoencodingasofttouchtolearngraspingfromonlandtounderwater AT fangwan autoencodingasofttouchtolearngraspingfromonlandtounderwater AT chaoyangsong autoencodingasofttouchtolearngraspingfromonlandtounderwater |