Srikanth Gururajan

Flight-Test Evaluation of Sensor Fusion Algorithms for Attitude Estimation

In this paper, several Global Positioning System/inertial navigation system (GPS/INS) algorithms are presented using both extended Kalman filter (EKF) and unscented Kalman filter (UKF), and evaluated with respect to performance and complexity. The contributions of this study are that attitude estimates are compared with independent measurements provided by a mechanical vertical gyroscope using 23 diverse sets of flight data, and that a fundamental difference between EKF and UKF with respect to linearization is evaluated.

Sensitivity Analysis of Extended and Unscented Kalman Filters for Attitude Estimation

The extended Kalman filter (EKF) and unscented Kalman filter (UKF) for nonlinear state estimation with both additive and nonadditive noise structures are presented and compared. Three different Global Positioning System (GPS)/inertial navigation system (INS) sensor fusion formulations for attitude estimation are used as case studies for the nonlinear state estimation problem. A diverse set of actual flight data collected from research unmanned aerial vehicles was used as empirical data for this study. Roll and pitch estimation results were comparedwith independent measurements from amechanical vertical gyroscope to evaluate the performance. The performance of the EKF and UKF is compared in terms of noise assumptions, covariance matrix tuning, sampling rate, initialization error, GPS outages, robustness to inertial measurement unit bias and scale factors, and linearization. Similar sensitivity for this GPS/INS attitude estimation problem was found between the EKF and UKF for most cases. Small differences were seen between EKF and UKF for initialization error and GPS outages: the UKF was found to be more robust to inertial measurement unit calibration errors, and the EKF was determined to be more computationally efficient.

Adaptive control software: can we guarantee safety?

The appeal of including adaptive components in complex computational systems, such as flight control, is in their ability to cope with a changing environment. Continual changes induce uncertainty that limits the applicability of conventional verification and validation (V&V) techniques. In safety-critical applications, the mechanisms of change must be observed, diagnosed, accommodated and well understood prior to deployment. We present a nonconventional V&V approach suitable for online adaptive systems. We applied this approach to an adaptive flight control system that employs neural network learning for online adaptation. Presented methodology consists of a Novelty Detection technique and Online Stability Monitoring tools. The Novelty Detection technique is based on support vector data description that detects novel (abnormal) data patterns. The Online Stability Monitoring tools based on Lyapunovs stability theory detect unstable learning behavior in neural networks.

Autonomous Formation Flight: Hardware Development

This paper describes the hardware development for an autonomous formation flight research project at West Virginia University. Each aircraft test bed was outfitted with an inertial navigation system (INS), GPS receiver and telemetry system tailored to perform the formation flight experiment. This paper provides a detailed summary about the aircraft test-bed, on-board electronic payload, and the various flight testing phases leading to the final 3-aircraft formation demonstration

Design and Flight Testing of Intelligent Flight Control Laws for the WVU YF-22 Model Aircraft

The purpose of this paper is to present the design and the testing in flight of a neurally augmented control scheme based on non-linear dynamic inversion for the WVU YF-22 model aircraft. The adaptive flight controller is designed and tested through simulation using Matlab and Simulink. A single flight condition is considered and a neural network is used to compensate for inversion errors and changes in aircraft dynamics, including actuator failures. A minimal Real Time Application Interface Linux distribution was created using BusyBox. The Simulink Real Time Workshop environment was used to generate C code to be run on the WVU-YF22 customized on-board computer. Flight testing results performed at nominal flight conditions show the potential of the control scheme to achieve adequate stability and performance characteristics.

Validating an online adaptive system using SVDD

One of the goals of verification and validation (V&V) activities for online adaptive control systems is providing assurance that they are able to detect novel system behaviors and provide adequate (safe) control actions. Novel (or abnormal) system behaviors cannot be enumerated or fully and explicitly described in requirements documentation. Therefore, they have to be observed and recognized during the operation. Novelty detection methods, therefore, provide an adequate approach for the V&V purposes. We propose a novelty detection method based on support sector data description (SVDD) as a candidate approach for validating adaptive control systems. As a one-class classifier, the support vector data description is able to form a decision boundary around the learned data domain with very little or no knowledge of data points outside the boundary (outliers). We apply the SVDD techniques for novelty detection as part of the validation on an intelligent flight control system (IFCS). Experimental results show that the SVDD can be adopted as an effective tool for finding indications of the safe region for the learned domain, whereby we are able to separate faulty behavior from normal events.

Validating neural network-based online adaptive systems: a case study

Biologically inspired soft computing paradigms such as neural networks are popular learning models adopted in online adaptive systems for their ability to cope with the demands of a changing environment. However, continual changes induce uncertainty that limits the applicability of conventional validation techniques to assure the reliable performance of such systems. In this paper, we discuss a dynamic approach to validate the adaptive system component. Our approach consists of two run-time techniques: (1) a statistical learning tool that detects unforeseen data; and (2) a reliability measure of the neural network output after it accommodates the environmental changes. A case study on NASA F-15 flight control system demonstrates that our techniques effectively detect unusual events and provide validation inferences in a real-time manner.

Parameter Identification for Application within a Fault-Tolerant Flight Control System

This paper presents the results of a parameter identification study for the mathematical model of the WVU YF-22 unmanned research aircraft under both nominal and failure conditions to simulate malfunctions on primary control surfaces. Specifically, nominal and failure conditions for both linear and non-linear mathematical models were developed using flight data acquired from pilot and automated computer-injected maneuvers. From analysis, the stability and control derivatives were extracted to determine the aerodynamic forces and moments. The aerodynamic derivatives were introduced into a simulation model implemented within a Simulink-based environment; studies were conducted to validate the accuracy of the identified models. Initial simulation results highlight the potential for the development of the nominal and failure non-linear mathematical models from flight data.

An approach to v&v of embedded adaptive systems

Rigorous Verification and Validation (V& V) techniques are essential for high assurance systems. Lately, the performance of some of these systems is enhanced by embedded adaptive components in order to cope with environmental changes. Although the ability of adapting is appealing, it actually poses a problem in terms of V&V. Since uncertainties induced by environmental changes have a significant impact on system behavior, the applicability of conventional V& V techniques is limited. In safety-critical applications such as flight control system, the mechanisms of change must be observed, diagnosed, accommodated and well understood prior to deployment. In this paper, we propose a non-conventional V&V approach suitable for online adaptive systems. We apply our approach to an intelligent flight control system that employs a particular type of Neural Networks (NN) as the adaptive learning paradigm. Presented methodology consists of a novelty detection technique and online stability monitoring tools. The novelty detection technique is based on Support Vector Data Description that detects novel (abnormal) data patterns. The Online Stability Monitoring tools based on Lyapunovs Stability Theory detect unstable learning behavior in neural networks. Cases studies based on a high fidelity simulator of NASAs Intelligent Flight Control System demonstrate a successful application of the presented V&V methodology.

Design of Intelligent Flight Control Laws for the WVU YF-22 Model Aircraft

The purpose of this paper is to present the design and the testing through numerical simulation of a neurally augmented control scheme based on non-linear dynamic inversion for the WVU YF-22 aircraft scale model. The adaptive flight controller is designed at a single flight condition and a neural network is used to compensate for inversion errors and changes in aircraft dynamics, including actuator failures. Numerical simulation results performed at nominal flight conditions and following stabilator and aileron failures show adequate stability and performance characteristics of the control scheme.