Sensing Anomalies as Potential Hazards: Datasets and Benchmarks
This work addresses safety concerns for autonomous robots by enabling hazard detection through anomaly identification, but it is incremental as it builds on existing autoencoder methods with new datasets.
The paper tackles the problem of detecting unusual semantic patterns in visual data streams of autonomous robots to identify potential hazards, and it introduces three new image-based datasets with over 200k labeled frames and evaluates an autoencoder-based anomaly detection method.
We consider the problem of detecting, in the visual sensing data stream of an autonomous mobile robot, semantic patterns that are unusual (i.e., anomalous) with respect to the robot's previous experience in similar environments. These anomalies might indicate unforeseen hazards and, in scenarios where failure is costly, can be used to trigger an avoidance behavior. We contribute three novel image-based datasets acquired in robot exploration scenarios, comprising a total of more than 200k labeled frames, spanning various types of anomalies. On these datasets, we study the performance of an anomaly detection approach based on autoencoders operating at different scales.