This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Coverage control for mobile sensing networks

Distributed estimation over a low-cost sensor network: a review of state-of-the-art

Anomaly detection is an active area of research with numerous methods and applications. This survey reviews the state-of-the-art of data-driven anomaly detection techniques and their application to the aviation domain. After a brief introduction to the main traditional data-driven methods for anomaly detection, we review the recent advances in the area of neural networks, deep learning and temporal-logic based learning. In particular, we cover unsupervised techniques applicable to time series data because of their relevance to the aviation domain, where the lack of labeled data is the most usual case, and the nature of flight trajectories and sensor data is sequential, or temporal. The advantages and disadvantages of each method are presented in terms of computational efficiency and detection efficacy. The second part of the survey explores the application of anomaly detection techniques to aviation and their contributions to the improvement of the safety and performance of flight operations and aviation systems. As far as we know, some of the presented methods have not yet found an application in the aviation domain. We review applications ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

https://hal.archives-ouvertes.fr/hal-02470453/document

Recent Advances in Anomaly Detection Methods Applied to Aviation

This paper proposes a distributed robust Kalman filter for time-varying uncertain linear multisensor systems subjected to stochastic uncertainties. A consensus algorithm is utilized to compromise on a single data among information of all nodes in a multisensor system. Distributed filtering based on consensus remarkably stands out from other algorithms because each node not only estimates its local states correctly, but also reaches an agreement with other nodes over a sensor network as well. The distributed filtering problem is formulated here using consensus on estimation (CE) algorithm. The optimal parameters of the filter are computed by minimizing the covariance of the estimation error. Moreover, the stability of the touched upon algorithm is proved by the Lyapunov stability theorem. Simulation results for a multisensor system with 100 nodes are presented to show the effectiveness and performance of the proposed CE-based distributed robust filtering approach.

Consensus-Based Distributed Robust Filtering for Multisensor Systems With Stochastic Uncertainties

The aircraft trajectory clustering analysis in the terminal airspace is conducive to determining the representative route structure of the arrival and departure trajectory and extracting their typical patterns, which is important for air traffic management such as airspace structure optimization, trajectory planning, and trajectory prediction. However, the current clustering methods perform poorly due to the large flight traffic, high density, and complex airspace structure in the terminal airspace. In recent years, the continuous development of Deep Learning has demonstrated its powerful ability to extract internal potential features of large dataset. Therefore, this paper mainly tries a deep trajectory clustering method based on deep autoencoder (DAE). To this end, this paper proposes a trajectory clustering method based on deep autoencoder (DAE) and Gaussian mixture model (GMM) to mine the prevailing traffic flow patterns in the terminal airspace. The DAE is trained to extract feature representations from historical high-dimensional trajectory data. Subsequently, the output of DAE is input into GMM for clustering. This paper takes the terminal airspace of Guangzhou Baiyun International Airport in China as a case to verify the proposed method. Through the direct visualization and dimensionality reduction visualization of the clustering results, it is found that the traffic flow patterns identified by the clustering method in this paper are intuitive and separable.

Aircraft Trajectory Clustering in Terminal Airspace Based on Deep Autoencoder and Gaussian Mixture Model

Following recent advances in networked communication technologies, sensor networks have been employed in a broad range of applications at a lower cost than centrally supervised systems. Their major functionality is to track and monitor targets using various distributed estimation techniques. Specifically, the distributed Kalman Consensus Filter (KCF) fuses data from different sensor agents by achieving two objectives for each sensor: 1) locally estimating the state of the target; and 2) reaching a consensus of the state estimate between neighboring agents through communication. Although the KCF has been proven to have superior performance in terms of stability and scalability, it relies on approximated suboptimal consensus gain to avoid algorithmic complexity. Specifically, we seek to address this problem of suboptimality, and analytically derive the closed form solution to the globally optimal consensus gain, which is characterized by the minimum mean square error for the estimation process. Illustrative simulation results are presented to demonstrate that the optimal consensus gain outperforms the suboptimal solution.

Optimal discrete-time Kalman Consensus Filter

The terminal airspace system is one of the most complex human-made dynamical systems with a continuously evolving structure. Modern aviation technologies in the terminal airspace record detailed fl...

Incremental-Learning-Based Unsupervised Anomaly Detection Algorithm for Terminal Airspace Operations

Anomaly Detection Using Temporal Logic Based Learning for Terminal Airspace Operations

In this study, the authors consider the distributed state estimation problem of a stochastic linear hybrid system (SLHS) observed over a sensor network. The SLHS is a dynamical system with interacting continuous state dynamics described by stochastic linear difference equations and discrete state (or mode) transitions governed by a Markovian process with a constant transition matrix. Most existing hybrid estimation algorithms are based on a centralised architecture which is not suitable for distributed sensor network applications. Further, the existing distributed hybrid estimation algorithms are restrictive in sensor network topology, or approximate the consensus process among connected sensor agents. This study proposes a distributed hybrid state estimation algorithm based on the multiple model based approach augmented with the optimal consensus estimation algorithm which can locally process the state estimation and share the estimation information with the neighbourhood of each sensor agent. This shared information comprises local mode-conditioned state estimates and edge-error covariances, and is used to bring about an agreement or a consensus across the network. The proposed distributed hybrid state estimation algorithm is demonstrated with an illustrative aircraft tracking example.

Distributed state estimation for a stochastic linear hybrid system over a sensor network

The airspace system is a complex dynamical system with complicated controlled interactions between its constituent subsystems – terminal airspace, en-route airspace, and ground. Of these, air traffic management in the multi-airport (metroplex) terminal airspace is one of the most complicated subsystems to manage, especially due to the interactions between proximal airports. Analyzing anomalous behaviors in the metroplex is emerging as a key problem in understanding air traffic management complexity and safety. Although physics-based approaches have been studied in-depth for this application, newfound interest has been observed to use recorded time-series air traffic surveillance and airport operations datasets for this purpose. In this paper, we propose a machine learning-based anomaly detection algorithm that generates mathematical models to detect anomalies in metroplex operations. Several machine learning algorithms have been developed to detect anomalies using only air traffic surveillance data, but there is a significant scope of improvement by including airport operational characteristics as well, since integrating such closely-controlled metroplex operational datasets allows the developed models to effectively detect anomalies. The key contribution of this paper is in allowing anomaly detection models to recursively update so as to adapt to changes in metroplex operations. The proposed algorithm is demonstrated with real air traffic surveillance and airport operations datasets at LaGuardia, John F. Kennedy, and Newark airports, thereby detecting anomalies for operations in the New York metroplex.

Raj Deshmukh

Papers

Optimal discrete-time Kalman Consensus Filter

Incremental-Learning-Based Unsupervised Anomaly Detection Algorithm for Terminal Airspace Operations

Anomaly Detection Using Temporal Logic Based Learning for Terminal Airspace Operations

Distributed state estimation for a stochastic linear hybrid system over a sensor network

Temporal logic learning-based anomaly detection in metroplex terminal airspace operations