Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Depot-Specific White Adipose Tissue Remodeling Supports Non-Thermogenic Metabolic Homeostasis During Shallow Hibernation in Raccoon Dogs.

International journal of molecular sciences·2026

Same author

Injectable alginate hydrogels improve the effects of subretinal hiPSC-derived RPE cell therapy on retinal degeneration in rats.

Materials today. Bio·2026

Same author

Auxin-Induced Adventitious Rooting in Pepper Involves <i>CaLBD16</i>: Functional Evidence from Tomato Overexpression.

Plants (Basel, Switzerland)·2026

Same author

Pallidal alpha activity is an electrophysiological biomarker of symptom severity in obsessive-compulsive disorder.

Research square·2026

Same author

Enrichment of colon cancer stem cells via polymeric porous filters with different zeta potentials.

Regenerative biomaterials·2026

Same author

Predicting adverse outcomes in dilated cardiomyopathy using 3D echocardiography: penalised Cox regression versus machine learning.

BMC cardiovascular disorders·2026

Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026

Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026

Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026

Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026

Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026

Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026

See all related articles

Search research articles

Related Experiment Video

Updated: May 10, 2025

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

TinyML-Based In-Pipe Feature Detection for Miniature Robots.

Manman Yang¹, Andrew Blight¹, Hitesh Bhardwaj¹

¹School of Mechanical Engineering, University of Leeds, Leeds LS2 9JT, UK.

Sensors (Basel, Switzerland)

|April 28, 2025

Summary

This summary is machine-generated.

This study introduces a resource-efficient pipe feature recognition method using tiny machine learning (TinyML) for miniature robots. The TinyML model accurately identifies pipeline features, enabling autonomous navigation in small-diameter pipes.

Keywords:

convolutional neural network (CNN)in-pipe feature detection miniature robot resource-efficient tiny machine learning (TinyML)

More Related Videos

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

Related Experiment Videos

Last Updated: May 10, 2025

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Picometer-Precision Atomic Position Tracking through Electron Microscopy

Published on: July 3, 2021

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Automated Rat Single-Pellet Reaching with 3-Dimensional Reconstruction of Paw and Digit Trajectories

Published on: July 10, 2019

Area of Science:

Robotics
Artificial Intelligence
Computer Vision

Background:

Autonomous navigation in small-diameter pipelines is crucial for miniature robots.
Limited computational resources on miniature robots pose challenges for environmental perception.

Purpose of the Study:

To propose a resource-efficient pipe feature recognition method for miniature robots using tiny machine learning (TinyML).
To enable miniature robots to identify key pipeline features for autonomous navigation.

Main Methods:

Developed a custom five-layer convolutional neural network (CNN) optimized for resource-constrained devices.
Trained the CNN model on a custom dataset of 4629 diverse pipeline images.
Implemented a sliding window smoothing strategy for stable performance in challenging conditions.

Main Results:

Achieved a high accuracy of 97.1% in recognizing pipeline features.
Demonstrated low resource utilization: 195.1 kB peak RAM, 427.9 kB flash usage.
Inference time of 1693 ms, indicating computational efficiency.

Conclusions:

TinyML models can be effectively deployed on resource-constrained miniature robots for pipeline feature recognition.
The proposed method offers a cost-effective solution for autonomous in-pipe exploration and inspection.
Advanced machine learning is feasible for enhancing robot autonomy in challenging environments.