Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 9, 2026

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion
08:19

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Published on: January 15, 2016

9.2K

RGB-Based Staircase Detection for Quadrupedal Robots: Implementation and Analysis.

Piotr Wozniak1, Paweł Penar2, Damian Bielecki2

  • 1Department of Computer and Control Engineering, Rzeszow University of Technology, 35-959 Rzeszow, Poland.

Sensors (Basel, Switzerland)
|December 11, 2025
PubMed
Summary

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

Multi-Domain Indoor Dataset for Visual Place Recognition and Anomaly Detection by Mobile Robots.

Scientific data·2025
Same author

Cross-Domain Indoor Visual Place Recognition for Mobile Robot via Generalization Using Style Augmentation.

Sensors (Basel, Switzerland)·2023
See all related articles

This study introduces a real-time stair detection algorithm for quadruped robots, enhancing safety by identifying hazards. The deep learning approach adapts to various camera views, enabling safer robot navigation.

Area of Science:

  • Robotics
  • Computer Vision
  • Artificial Intelligence

Background:

  • Quadruped robots require advanced perception for safe navigation in complex environments.
  • Stair detection is crucial for preventing falls and damage during robot operation.
  • Existing methods often lack adaptability to diverse viewpoints and real-time constraints.

Purpose of the Study:

  • To develop and validate a robust stair detection algorithm for quadruped robots.
  • To enable real-time hazard detection, specifically stair proximity, for enhanced robot safety.
  • To create a versatile algorithm adaptable to different camera perspectives and platforms.

Main Methods:

  • Utilized a deep neural network (YOLO version 11n) with RGB inputs for object detection.
  • Trained the network on a dataset of over 26,000 images from a quadruped robot's dual cameras.
Keywords:
YOLOdeep learningmobile robotobject detectionquadrupedal robotstair detection

More Related Videos

3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

11.2K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.1K

Related Experiment Videos

Last Updated: Jan 9, 2026

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion
08:19

Asymmetric Walkway: A Novel Behavioral Assay for Studying Asymmetric Locomotion

Published on: January 15, 2016

9.2K
3D Kinematic Gait Analysis for Preclinical Studies in Rodents
10:19

3D Kinematic Gait Analysis for Preclinical Studies in Rodents

Published on: August 3, 2019

11.2K
The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy
11:53

The Modular Design and Production of an Intelligent Robot Based on a Closed-Loop Control Strategy

Published on: October 14, 2017

12.1K
  • Incorporated multi-camera image training (front and bottom views) and tested on various embedded platforms.

    • Main Results:

    • Achieved an average mAP@50 of 51.30 for stair-only images and 87.56 for all images across 17 unseen sequences.
    • Demonstrated the algorithm's adaptability from a single training sequence to multiple diverse sequences.
    • Verified performance on the Unitree Go1 robot and other embedded systems.

    Conclusions:

    • The proposed stair detection algorithm effectively enhances safety for quadruped robots navigating stairs.
    • The method offers real-time hazard identification and adaptability to varying environmental and camera conditions.
    • This research advances stair detection capabilities for legged robots, addressing real-world deployment challenges.