Detecting anomalies in unmanned vehicles using the Mahalanobis distance

Abstract

Abstract-The use of unmanned autonomous vehicles is becoming more and more significant in recent years. The fact that the vehicles are unmanned (whether autonomous or not), can lead to greater difficulties in identifying failure and anomalous states, since the operator cannot rely on its own body perceptions to identify failures. Moreover, as the autonomy of unmanned vehicles increases, it becomes more difficult for operators to monitor them closely, and this further exacerbates the difficulty of identifying anomalous states, in a timely manner. Model-based diagnosis and fault-detection systems have been proposed to recognize failures. However, these rely on the capabilities of the underlying model, which necessarily abstracts away from the physical reality of the robot. In this paper we propose a novel, model-free, approach for detecting anomalies in unmanned autonomous vehicles, based on their sensor readings (internal and external). Experiments conducted on Unmanned Aerial Vehicles (UAVs) and Unmanned Ground Vehicles (UGVs) demonstrate the efficacy of the approach by detecting the vehicles deviations from nominal behavior.

Improving dependability of industrial transport robots using model-based techniques

“…A similar approach to learn the system behavior was proposed in [25]. The method learns dependent variables and their nominal values.…”

A data driven approach for detection and isolation of anomalies in a group of UAVs

“…;ĥ N g , for each constitute aircraft of the team can be estimated, then, the aircraft with abnormal behavior can be determined by finding the model parameters that deviate from the standard reference (ĥ 0 ) in terms of some distance metrics, such as Euclidian and Mahalanobis distance. 12 The proposed procedure for detection of the anomaly of the flight is shown in Fig. 1, where the abnormal aircraft are shown within the circles.…”

“…The optimization problem defined in Eq. (12), however, is impractical to solve. The reasons are twofolds.…”

“…Based on this assumption, we use L 1 norm to replace the L 0 norm operator in Eq. (12), leading to the following convex cost function:…”

“…This constraint, however, is too strict to be satisfied in practical applications. In order to loosen the observer matching condition, algebraically decomposed technique, 8 unscented transformation (UT), 9 population-based approaches, 10 optimization methods 11,12 and neural networks, 13 have been incorporated into the framework of UIO, which greatly improves the performance of the original method in applications. Stochastic filters 11,14,15 such as Kalman filter and particle filter, have been introduced to solve the fault detection and isolation problems in recent years.…”