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

<b>Taxonomic revision of the genus <i>Casphalia</i> Walker, 1866 (Lepidoptera, Limacodidae: Limacodinae)</b>.

Zootaxa·2026

Same author

Dataset and tools for benchmarking multi-sensor multi-people tracking for ground robots.

Data in brief·2026

Same author

Radiomic Analysis as a Powerful Tool for Cytological Images of Benign Thyroid Nodules Treated by Thermal Radiofrequency Ablation.

Bioengineering (Basel, Switzerland)·2026

Same author

EU-funded research to advance agroecological weed management in Europe, Part I: vision.

Open research Europe·2026

Same author

A catalogue of Limacodidae (Lepidoptera: Zygaenoidea) from India.

Zootaxa·2025

Same author

A Förster Resonance Energy Transfer (FRET)-Based Immune Assay for the Detection of Microcystin-LR in Drinking Water.

Sensors (Basel, Switzerland)·2024

Search research articles

Related Experiment Video

Updated: Jul 25, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Hazards&Robots: A dataset for visual anomaly detection in robotics.

Dario Mantegazza¹, Alind Xhyra¹, Luca M Gambardella¹

¹IDSIA - Dalle Molle Institute for Artificial Intelligence USI-SUPSI, Polo universitario Lugano - Campus Est, Via la Santa 1, CH-6962 Lugano-Viganello.

|June 29, 2023

Summary

We introduce Hazards&Robots, a large dataset for visual anomaly detection in robotics. This dataset aids in training and testing deep learning models for identifying anomalies like unexpected objects or robot defects.

Keywords:

Computer vision Deep learning Intelligent robotics Out of distribution detection

More Related Videos

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 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

Related Experiment Videos

Last Updated: Jul 25, 2025

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery

Published on: August 12, 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

Area of Science:

Robotics
Computer Vision
Machine Learning

Background:

Visual anomaly detection is crucial for robot safety and reliability.
Existing datasets may not adequately represent real-world robotic operational hazards.

Purpose of the Study:

To introduce the Hazards&Robots dataset for visual anomaly detection in robotics.
To provide a comprehensive resource for training and evaluating anomaly detection models.

Main Methods:

The dataset comprises 324,408 RGB frames from a DJI Robomaster S1 robot.
It includes 145,470 normal frames and 178,938 anomalous frames across 20 categories.
Anomalies include human presence, floor obstacles, and robot defects.

Main Results:

The dataset facilitates the development of advanced visual anomaly detection algorithms.
It enables benchmarking of deep learning vision models for robotic applications.

Conclusions:

Hazards&Robots offers a valuable resource for advancing research in robotic safety and perception.
The dataset supports the creation of more robust and reliable autonomous systems.