Spatio-Temporal Anomaly Detection for Industrial Robots through Prediction in Unsupervised Feature Space

Abstract

Spatio-temporal anomaly detection by unsupervised learning have applications in a wide range of practical settings. In this paper we present a surveillance system for industrial robots using a monocular camera. We propose a new unsupervised learning method to train a deep feature extractor from unlabeled images. Without any data augmentation, the algorithm co-learns the network parameters on different pseudo-classes simultaneously to create unbiased feature representation. Combining the learned features with a prediction system, we can detect irregularities in high dimensional data feed (e.g. video of a robot performing pick and place task). The results show how the proposed approach can detect previously unseen anomalies in the robot surveillance video. Although the technique is not designed for classification, we show the use of the learned features in a more traditional classification application for CIFAR-10 dataset.

An Overview of Deep Learning Based Methods for Unsupervised and Semi-Supervised Anomaly Detection in Videos

“…Other Predictive models : A convolutional feature representation was fed into an LSTM model to predict the latent space representation and its prediction error was used to evaluate anomalies in a robotics application [68]. A recurrent autoencoder using an LSTM that models temporal dependence between patches from a sequence of input frames is used to detect video forgery [69].…”

“…The motivation for negative learning using anomalous examples is to consistently provide poor reconstruction of anomalous samples. During the training phase, authors [68] reconstruct positive samples by minimizing the reconstruction error between samples, while negative samples are forced to have a bad reconstruction by maximizing the error. This last step was termed as negative learning.…”

Towards Corner Case Detection for Autonomous Driving

“…A consequence of the so-far missing universally accepted definition of a corner case is that there is also no explicit metric existing. Motivated by [17], we will use a predictive approach for corner case detection. The idea is that if a novel or abnormal or critical suddenly occurring situation is A corner case is given, if there is a non-predictable 1 relevant object/class 2 in relevant location.…”

MaestROB: A Robotics Framework for Integrated Orchestration of Low-Level Control and High-Level Reasoning

“…T. Inoue et al [10] showed how the data from conventional sensors can be combined with the deep reinforcement learning to solve precision insertion task. A. Munawar et al [15] presented an anomaly detection system using vision. Such systems can be used to enable the systems to keep a check on themselves with little intervention from the humans.…”