Autoencoder-Based Semantic Novelty Detection: Towards Dependable AI-Based Systems

Many autonomous systems, such as driverless taxis, perform safety-critical functions. Autonomous systems employ artificial intelligence (AI) techniques, specifically for environmental perception. Engineers cannot completely test or formally verify AI-based autonomous systems. The accuracy of AI-based systems depends on the quality of training data. Thus, novelty detection, that is, identifying data that differ in some respect from the data used for training, becomes a safety measure for system development and operation. In this study, we propose a new architecture for autoencoder-based semantic novelty detection with two innovations: architectural guidelines for a semantic autoencoder topology and a semantic error calculation as novelty criteria. We demonstrate that such a semantic novelty detection outperforms autoencoder-based novelty detection approaches known from the literature by minimizing false negatives.

Automated summary

Autonomous systems like driverless taxis play critical safety roles with the help of AI techniques, which rely heavily on the quality of training data. Novelty detection becomes a safety measure in system development and operation, ensuring accurate performance by identifying data that differ from the training set.