Mario G. Perhinschi

Machine Vision/GPS Integration Using EKF for the UAV Aerial Refueling Problem

The purpose of this paper is to propose the application of an extended Kalman filter (EKF) for the sensors fusion task within the problem of aerial refueling for unmanned aerial vehicles (UAVs). Specifically, the EKF is used to combine the position data from a global positioning system (GPS) and a machine vision (MV)-based system for providing a reliable estimation of the tanker-UAV relative position throughout the docking and the refueling phase. The performance of the scheme has been evaluated using a virtual environment specifically developed for the study of the UAV aerial refueling problem. Particularly, the EKF-based sensor fusion scheme integrates GPS data with MV-based estimates of the tanker-UAV position derived through a combination of feature extraction, feature classification, and pose estimation algorithms. The achieved results indicate that the accuracy of the relative position using GPS or MV estimates can be improved by at least one order of magnitude with the use of EKF in lieu of other sensor fusion techniques.

AUTONOMOUS AERIAL REFUELING FOR UAVS USING A COMBINED GPS-MACHINE VISION GUIDANCE

The most important factors affecting the performance of a control scheme for Autonomous Aerial Refueling (AAR) for UAVs are the magnitude of the wake effects from the Tanker and the accuracy of the measurements of the UAV-Tanker distance and attitude leading to the docking. The main objective of the effort described in this paper is the implementation of a detailed modeling and simulation environment for evaluating the AAR problem. In particular, a specific control scheme based on a sensor fusion between GPS- based and Machine Vision-based measurements is proposed. Furthermore, the iterative algorithm used for estimating the position of the optical markers has been modified to be robust to a loss of visibility by one or more optical markers during the docking sequence. The paper presents the results of a detailed analysis of the AAR under different scenarios.

Online Parameter Estimation Techniques Comparison Within a Fault Tolerant Flight Control System

The results of a study where two online parameter identie cation (PID) methods are compared for application within a fault tolerant e ight control system are described. One of the PID techniques is time-domain based, whereas the second is featured in the frequency domain. The time-domain method was directly suitable for the online estimates of the dimensionless aircraft stability derivatives. The frequency-domain method was modie ed fromitsoriginalformulationtoprovidedirectestimatesofthestabilityderivatives.Thiseffortwasconductedwithin the research activities of the NASA Intelligent Flight Control System F-15 program. The comparison is performed throughdynamicsimulationswithaspecie cproceduretomodeltheaircraftaerodynamicsfollowingtheoccurrence of a battle damage/failure on a primary control surface. The two PID methods show similar performance in terms of accuracy of the estimates, convergence time, and robustness to noise. However, the frequency-domain-based method outperforms the time-domain-based method in terms of computational requirements for online real-time applications. The study has also emphasized the advantages of using ad hoc short preprogrammed maneuvers to provideenoughexcitationfollowingtheoccurrenceoftheactuatorfailuretoallowtheparameterestimationprocess.

An adaptive threshold approach for the design of an actuator failure detection and identification scheme

Typical logic schemes associated with failure detection and identification algorithms rely on a set of constant thresholds. The selection of the values for these thresholds is generally a tradeoff between the goals of maximizing failure detectability while minimizing false alarm rates. The main purpose of this brief is to propose an alternative to this conventional approach for defining the thresholds of a specific aircraft actuator failure detection and identification scheme. A specific set of detection and identification criteria for failures of the decoupled stabilators, canards, ailerons, and rudders of the NASA Advanced Control Technology for Integrated Vehicle F-15 aircraft have been formulated in terms of neural network estimates and correlation functions of the angular rates. The proposed scheme is based on the use of adaptive thresholds through the floating limiter concept. This new approach eliminates the need for parameter scheduling and has shown to be able to reduce the delays associated with the constant threshold method. The functionality of the approach has been illustrated through numerical simulations on the West Virginia University NASA Intelligent Flight Control System F-15 simulator.

Integrated Framework for Artificial Immunity-Based Aircraft Failure Detection, Identification, and Evaluation

This paper presents a novel conceptual framework for an integrated set of methodologies for the detection, identification, and evaluation of a wide variety of failures of aircraft subsystems based on the artificial immune system paradigm. The detection represents the capability to declare that a failure within any of the aircraft subsystems has occurred. The identification process determines which element has failed. The evaluation of the failure addresses three aspects: the type of the failure, its magnitude, and the reassessment of the generalized flight envelope. Failure detection, identification, and evaluation schemes are included using the bioimmune system metaphor combined with other artificial intelligence techniques. The immunity-based fault detection operates in a similar manner as does the immune system when it distinguishes between entities that belong to the organism and entities that do not. The proposed approach directly addresses the complexity and multidimensionality of aircraft dynamic response in the context of abnormal conditions and provides the adequate tools to solve the failure detection problem in an integrated and comprehensive manner. A multiself failure detection and identification scheme is presented for actuator, sensor, engine, and structural failures/damages, which was developed and tested using a motion-based flight simulator. The scheme achieves excellent detection rates and a low number of false alarms and demonstrates the effectiveness of the proposed framework.

Artificial-Immune-System-Based Aircraft Failure Evaluation over Extended Flight Envelope

This paper describes the design, development, and flight-simulation testing of an artificial-immune-system-based approach for the evaluation of different aircraft subsystem failures/damages. The evaluation consists of the estimation of the magnitude/severity of the failure and the prediction of the achievable states, leading to an overall assessment of the effects of the failure on reducing the flight envelope. A supersonic fighter model is used, which includes model-following adaptive control laws based on nonlinear dynamic inversion and artificial neural network augmentation. Data collected from a motion-based flight simulator were used to define the self for a wide area of the flight envelope and to test and validate the proposed approach. Example results are presented for failure-magnitude evaluation and flight-envelope-reduction prediction for abnormal conditions affecting sensors, actuators, engine, and wing structure. Successful failure detection and identification are assumed before evaluation. The results show the capabilities of the artificial-immune-system-based scheme to evaluate the severity of the failure and to predict the reduction of the flight envelope in a general manner.

A SIMULATION TOOL FOR ON-LINE REAL TIME PARAMETER IDENTIFICATION

This paper describes a simulation tool developed at West Virginia University (WVU) for online aircraft parameter identification (PID) within a specific fault tolerant flight control scheme for the NASA IFCS F-15 program. The simulation package developed by WVU researchers is modular and flexible so that different methods and/or approaches can be used for each of the tasks of the general fault tolerant control system, such as aircraft model, controller, parameter identification method, and on-line data storage. Numerous simulation options are directly available to the user through specific graphical user interface. These options allow to select among different control loop configurations, different versions of the parameter identification method, and different failure scenarios.

A MODIFIED GENETIC ALGORITHM FOR THE DESIGN OF AUTONOMOUS HELICOPTER CONTROL SYSTEM

The use of genetic algorithms for solving aerospace control system design and optimization problems is investigated. A modified genetic algorithm based on floating point representation of the chromosome and appropriate genetic operators is developed and used to design controller gains for an autonomous airvehicle. The controller design problem is formulated along a classical pattern with requirements expressed both in time and frequency domain. Performance of the controlled system is compared with results obtained using a classical design procedure and with results obtained with a standard genetic algorithm using binary representation. Improvements of the algorithm performance are obtained using elitist selection strategy and selective weights in the evaluation function. Genetic algorithms show the potential of promising techniques for solving complex aerospace control system design problems.

Aircraft Failure Detection and Identification Using an Immunological Hierarchical Multiself Strategy

This paper presents the development and application of an integrated artificial-immune-system-based scheme for the detection and identification of a variety of aircraft sensor, actuator, propulsion, and structural failures/damages. The proposed approach is based on a hierarchical multiself strategy in which different self configurations are selected for detection and identification of specific abnormal conditions. Data collected using a motion-based flight simulator were used to define the self for a subregion of the flight envelope. The aircraft model represents a supersonic fighter, including model-followinig adaptive control laws based on nonlinear dynamic inversion and artificial neural network augmentation. The proposed detection scheme achieves low false alarm rates and high detection and identification rates for all four categories of failures considered.

Addressing corner detection issues for machine vision based UAV aerial refueling

This paper describes the results of the analysis of specific ‘corner detection’ algorithms within a Machine Vision approach for the problem of aerial refueling for unmanned aerial vehicles. Specifically, the performances of the SUSAN and the Harris corner detection algorithms have been compared. A critical goal of this study was to evaluate the interface of these feature extraction schemes with the successive detection and labeling, and pose estimation schemes in the overall scheme. Closed-loop simulations were performed using a Simulink®-based simulation environment to reproduce docking maneuvers using the US Air Force refueling boom.