A real-time anomaly detection method for robots based on a flexible and sparse latent space
This addresses the problem of robust safety in dynamic robotic environments for operators and systems, though it is incremental as it builds on existing deep learning methods.
The paper tackles real-time anomaly detection in robots by proposing a Sparse Masked Autoregressive Flow-based Adversarial AutoEncoder model, which achieves 4.96% to 9.75% higher AUC in pick-and-place tasks and up to 19.67% better performance in collision scenarios compared to state-of-the-art methods, with inference within 1 millisecond.
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 utilize 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.