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

Abstract

We propose Hazards&Robots, a dataset for Visual Anomaly Detection in Robotics. The dataset is composed of 324,408 RGB frames, and corresponding feature vectors; it contains 145,470 normal frames and 178,938 anomalous ones categorized in 20 different anomaly classes. The dataset can be used to train and test current and novel visual anomaly detection methods such as those based on deep learning vision models. The data is recorded with a DJI Robomaster S1 front facing camera. The ground robot, controlled by a human operator, traverses university corridors. Considered anomalies include presence of humans, unexpected objects on the floor, defects to the robot. Preliminary versions of the dataset are used in [1,3]. This version is available at [12]

Keywords

• Out of distribution detection
• Intelligent robotics
• Deep learning
• Computer vision