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

Fuzzy-based self organizing aggregation method for swarm robots.

Bio Systems·2020

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 5, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Drivable path detection for a mobile robot with differential drive using a deep Learning based segmentation method

Oğuz Mısır¹

¹Department of Mechatronics Engineering, Bursa Technical University, Bursa, Türkiye.

Peerj. Computer Science

|December 16, 2024

Summary

This study presents a deep learning method for mobile robots to detect safe paths indoors. The approach uses semantic segmentation and a grid-based RRT* strategy for efficient and optimal navigation, enhancing robot intelligence.

Keywords:

Cybernetics system Mobile robots Navigation Robotic

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 5, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Robotics
Artificial Intelligence
Computer Vision

Background:

Deep learning enhances robot intelligence and enables meaningful task performance.
Mobile robots require intelligent navigation systems for complex environments.
Pathfinding in cluttered indoor spaces remains a significant challenge for autonomous robots.

Purpose of the Study:

To develop a semantic-segmentation-based method for detecting drivable paths for indoor mobile robot navigation.
To improve the safety and optimality of mobile robot path planning in obstacle-rich environments.
To integrate deep learning with pathfinding algorithms for enhanced autonomous navigation.

Main Methods:

A novel semantic-segmentation approach using DeepLabv3+ with a ResNet50 backbone for accurate drivable path detection.
Perspective transformation to map segmented images into real-world grid-based motion spaces.
A grid-based Rapidly-exploring Random Tree star (RRT*) navigation strategy with path smoothing for optimal obstacle avoidance.

Main Results:

The proposed method accurately identifies drivable paths, enabling mobile robots to reach targets optimally.
DeepLabv3+ and ResNet50 demonstrated superior segmentation performance (0.21%-4.18% improvement) over other methods.
The integrated system successfully navigated diverse indoor scenarios, validating the drivable path determination method.

Conclusions:

Semantic segmentation combined with a grid-based RRT* strategy provides an effective solution for indoor mobile robot navigation.
The developed method enhances robot intelligence and autonomy by enabling safe and optimal pathfinding.
The study validates the practical applicability of the proposed approach through real-world mobile robot testing.