A Motion‐Sensing Integrated Soft Robot with Triboelectric Nanogenerator for Pipeline Inspection

The challenging and unstructured environment within pipelines demands the robotic exploration platforms with high adaptability, maneuverability, and recognition ability. Current soft robots equipped with cutting‐edge actuators have demonstrated inherent benefits in navigating pipeline environments d...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Chen, Huigang Wang, Haoji Wang, Huijiang Wang, Li Bai, Xinpei Ai, Lifu Liu, Zhihao Hu, Zean Yuan
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400643
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The challenging and unstructured environment within pipelines demands the robotic exploration platforms with high adaptability, maneuverability, and recognition ability. Current soft robots equipped with cutting‐edge actuators have demonstrated inherent benefits in navigating pipeline environments due to their material compliance and morphological adaptability. However, achieving inner‐pipe detection for pipeline‐climbing robots challenges the integration of sensors without compromising the robot's flexibility and operational functionalities. Herein, a soft robot that locomotes within pipelines and performs exteroception is presented. The main body of the robot is fabricated based on origami designs, powered by pneumatic actuators for locomotion and incorporates triboelectric nanogenerators as tactile sensors (T‐TENGs). Physical experiments have demonstrated the soft robot's capacity in crawling in various pipeline conditions such as the horizontal, vertical, and curved configurations. The T‐TENG‐based sensory system outputs distinct voltage signals upon exposed to different material and structural conditions, for which a 1D‐convolutional neutral network algorithm is exposed to process with the sequential signals. The robot achieves an overall recognition accuracy of 99% for distinguishing between eight distinct pipe inner surface structures and four different types of materials.
ISSN:2640-4567