Kang, Taewook You, Bum-Jae Park, Juyoun Lee, Yisoo 2025-07-18T07:00:07Z 2025-07-18T07:00:07Z 2025-07-18 2025-10 0952-1976 https://pubs.kist.re.kr/handle/201004/152786 The growing demand for robots to operate effectively in diverse environments necessitates the need for robust real-time anomaly detection techniques during robotic operations. However, deep learning-based models in robotics face significant challenges due to limited training data and highly noisy signal features. In this paper, we present Sparse Masked Autoregressive Flow-based Adversarial AutoEncoder model to address these problems. This approach integrates Masked Autoregressive Flow model into Adversarial AutoEncoders to construct a flexible latent space and utilizes Sparse autoencoder to efficiently focus on important features, even in scenarios with limited feature space. Our experiments demonstrate that the proposed model achieves a 4.96% to 9.75% higher area under the receiver operating characteristic curve for pick-and-place robotic operations with randomly placed cans, compared to existing state-of-the-art methods. Notably, it showed up to 19.67% better performance in scenarios involving collisions with lightweight objects. Additionally, unlike the existing state-of-the-art model, our model performs inferences within 1 millisecond, ensuring real-time anomaly detection. These capabilities make our model highly applicable to machine learning-based robotic safety systems in dynamic environments. The code is available at https://github.com/twkang43/sparse-maf-aae. English Pergamon Press Ltd. A real-time anomaly detection method for robots based on a flexible and sparse latent space Article 10.1016/j.engappai.2025.111310 1 Engineering Applications of Artificial Intelligence, v.158 Engineering Applications of Artificial Intelligence 158 N scie scopus 001513815500012 Automation & Control Systems Computer Science, Artificial Intelligence Engineering, Multidisciplinary Engineering, Electrical & Electronic Automation & Control Systems Computer Science Engineering Article Robot anomaly detection Unsupervised learning Masked autoregressive flow Adversarial autoencoder Sparse autoencoder