scholarly journals Planning the behavior of an integrated unmanned aerial vehicle based on the division of complex tasks into subtasks in the state space

2020 ◽  
Author(s):  
В.Б. Мелехин ◽  
М.В. Хачумов
Keyword(s):  
Behavior Problems ◽  
State Space ◽  
Unmanned Aerial Vehicle ◽  
Semantic Network ◽  
A Priori ◽  
Semantic Networks ◽  
The State ◽  
Operating Conditions ◽  
Complex Behavior ◽  
Aerial Vehicle

В работе решается одна из актуальных проблем искусственного интеллекта связанная с разработкой модели представления и обработки знаний автономным интегральным беспилотным летательным аппаратом – роботом в процессе автоматического планирования целенаправленной деятельности в априори неописанных условиях проблемной среды. Предложенная модель базируется на применении различных сценариев в виде фрейм-микропрограмм поведения, фрейм-отношений и фрейм-действий, а также расплывчатых семантических сетей, обеспечивающих представление знаний безотносительно к конкретной предметной области. Это, в свою очередь, позволяет интегральному беспилотному летательному аппарату оснащенному манипулятором адаптироваться после посадки к априори неописанным условиям функционирования и решать на этой основе сложные задачи поведения. Использованы два способа шаблонного разбиения сложных задач поведения в пространстве состояний на более простые подзадачи, решение которых определяется на основе типовых элементов представления знаний и определения нечеткого вложенного изоморфизма и равенства одной расплывчатой семантической сети в другую. Разработаны процедуры планирования, которые позволяют интегральному беспилотному летательному аппарату эффективным образом выполнить преобразование текущей ситуации априори неописанной проблемной среды в ситуацию, определяемую заданной ему целью поведения, и на этой основе организовать целенаправленную деятельность в труднодоступных и агрессивных для человека средах. This work addresses one of the urgent problems of artificial intelligence related to the development of a model for the representation and processing of knowledge by an autonomous integrated unmanned aerial vehicle (robot) in the process of automatic planning of targeted activities in a priori undescribed conditions of a problem environment. The proposed model is based on the application of various scenarios in the form of frame-microprograms of behavior, frame-relations and frame-actions, as well as vague semantic networks that provide the representation of knowledge without reference to a specific subject area. This, in turn, allows an integrated unmanned aerial vehicle equipped with a manipulator to adapt after landing to a priori unknown operating conditions and to solve complex behavior problems on this basis. Two methods of template partitioning of complex behavior problems in the state space into simpler subtasks are used, the solution of which is determined on the basis of typical elements of knowledge representation and definition of fuzzy embedded isomorphism and equality of one vague semantic network to another. Planning procedures have been developed that allow the integrated unmanned aerial vehicle to efficiently transform the current situation of an a priori undescribed problem environment into a situation determined by the goal of behavior, and on this basis to organize goal-seeking activities in hard-to-reach and aggressive environments for humans.

scholarly journals Partitioning complex tasks into subtasks in the process of planning goal-seeking behavior of an integral unmanned aerial vehicle in the state space

2020 ◽  
Author(s):  
В.Б. Мелехин ◽  
М.В. Хачумов
Keyword(s):  
Knowledge Representation ◽  
State Space ◽  
Unmanned Aerial Vehicle ◽  
Vision System ◽  
A Priori ◽  
The State ◽  
Operating Conditions ◽  
Complex Tasks ◽  
Seeking Behavior ◽  
Aerial Vehicle

Обозначены основные проблемы, связанные с разработкой интеллектуального решателя задач автоматической системы управления целенаправленным поведением интегрального беспилотного летательного аппарата в наземной проблемной среде. Рассмотрена конструкция типовых элементов представления знаний безотносительно к конкретной предметной области, позволяющих автономному беспилотному летальному аппарату, оснащенному манипулятором и системой технического зрения, решать сложные задачи в априори неописанных проблемных средах. Разработаны инструментальные средства разбиения сложных задач на подзадачи, обеспечивающие эффективный поиск их решения в пространстве состояний на основе типовых элементов представления знаний. Сформулированы основные методические положения, позволяющие синтезировать процедуры планирования целенаправленного поведения интегрального беспилотного летательного аппарата в сложных априори неописанных условиях функционирования. The main problems associated with the development of an intelligent problem solver of an automatic control system for the goal-seeking behavior of an integral unmanned aerial vehicle in a terrestrial problem environment are identified. The design of the typical elements of knowledge representation irrelative to the specific subject area is considered, allowing an autonomous unmanned aerial vehicle equipped with a manipulator and a vision system to solve complex problems in a priori undescribed problem environments. Tools are developed for partitioning complex tasks into sub-tasks, which provide an effective search for their solutions in the state space based on typical elements of knowledge representation. The main methodological provisions are formulated that allow synthesizing the planning procedures for the goal-seeking behavior of an integral unmanned aerial vehicle in a priori undescribed complex operating conditions.

Optimal State-Space Control of a Gas Turbine Engine

1992 ◽  
Vol 114 (4) ◽  
pp. 763-767 ◽  
Author(s):  
J. W. Watts ◽  
T. E. Dwan ◽  
C. G. Brockus
Keyword(s):  
State Space ◽  
Gas Turbine ◽  
State Space Model ◽  
Gas Turbine Engine ◽  
The State ◽  
Operating Conditions ◽  
Turbine Engine ◽  
Analog Control ◽  
Linear State ◽  
High Level

An analog fuel control for a gas turbine engine was compared with several state-space derived fuel controls. A single-spool, simple cycle gas turbine engine was modeled using ACSL (high level simulation language based on FORTRAN). The model included an analog fuel control representative of existing commercial fuel controls. The ACSL model was stripped of nonessential states to produce an eight-state linear state-space model of the engine. The A, B, and C matrices, derived from rated operating conditions, were used to obtain feedback control gains by the following methods: (1) state feedback; (2) LQR theory; (3) Bellman method; and (4) polygonal search. An off-load transient followed by an on-load transient was run for each of these fuel controls. The transient curves obtained were used to compare the state-space fuel controls with the analog fuel control. The state-space fuel controls did better than the analog control.

scholarly journals PERANCANGAN AUTOPILOT LATERAL-DIREKSIONAL PESAWAT NIRAWAK LSU-05 (THE DESIGN OF THE LATERAL-DIRECTIONAL AUTOPILOT FOR THE LSU-05 UNMANNED AERIAL VEHICLE)

2018 ◽  
Vol 15 (2) ◽  
pp. 93 ◽  
Author(s):  
Muhammad Fajar ◽  
Ony Arifianto
Keyword(s):  
State Space ◽  
Linear Model ◽  
Unmanned Aerial Vehicle ◽  
Pid Controller ◽  
Settling Time ◽  
Proportional Integral Derivative ◽  
Proportional Integral ◽  
Directional Motion ◽  
Aerial Vehicle ◽  
Simulation Results

The autopilot on the aircraft is developed based on the mode of motion of the aircraft i.e. longitudinal and lateral-directional motion. In this paper, an autopilot is designed in lateral-directional mode for LSU-05 aircraft. The autopilot is designed at a range of aircraft operating speeds of 15 m/s, 20 m/s, 25 m/s, and 30 m/s at 1000 m altitude. Designed autopilots are Roll Attitude Hold, Heading Hold and Waypoint Following. Autopilot is designed based on linear model in the form of state-space. The controller used is a Proportional-Integral-Derivative (PID) controller. Simulation results show the value of overshoot / undershoot does not exceed 5% and settling time is less than 30 second if given step command. Abstrak Autopilot pada pesawat dikembangkan berdasarkan pada modus gerak pesawat yaitu modus gerak longitudinal dan lateral-directional. Pada makalah ini, dirancang autopilot pada modus gerak lateral-directional untuk pesawat LSU-05. Autopilot dirancang pada range kecepatan operasi pesawat yaitu 15 m/dtk, 20 m/dtk, 25 m/dtk, dan 30 m/dtk dengan ketinggian 1000 m. Autopilot yang dirancang adalah Roll Attitude Hold, Heading Hold dan Waypoint Following. Autopilot dirancang berdasarkan model linier dalam bentuk state-space. Pengendali yang digunakan adalah pengendali Proportional-Integral-Derivative (PID). Hasil simulasi menunjukan nilai overshoot/undershoot tidak melebihi 5% dan settling time kurang dari 30 detik jika diberikan perintah step.

Unmanned Aerial Systems Platform Research Prognosis

2012 ◽  
Vol 225 ◽  
pp. 555-560
Author(s):  
Javaan Chahl
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Systems Engineering ◽  
The State ◽  
Unmanned Aerial Systems ◽  
Research Opportunities ◽  
Engineering Approach ◽  
Current Trends ◽  
Research Investment ◽  
Aerial Vehicle ◽  
Aerial Systems

Much of aerospace academia is anticipating a boom in Unmanned Aerial Vehicle (UAV) funding and research opportunities. The expectation is built on the premise that UAVs will revolutionize aerospace, which is likely based on current trends. There is also an anticipation of an increasing number of new platforms and research investment, which is likely but must be analyzed carefully to determine where the opportunities might lie. This paper draws on the state of industry and a systems engineering approach. We explore what aspects of UAVs really are the results of aerospace science advances and what aspects will be rather more mundane works of engineering.

scholarly journals Particle Filtering: A Priori Estimation of Observational Errors of a State-Space Model with Linear Observation Equation

Mathematics ◽  
2021 ◽  
Vol 9 (12) ◽  
pp. 1445
Author(s):  
Rodi Lykou ◽  
George Tsaklidis
Keyword(s):  
State Space ◽  
Particle Filtering ◽  
A Priori ◽  
State Space Model ◽  
Computational Cost ◽  
The State ◽  
Observation Equation ◽  
Basic Algorithm ◽  
Space Model ◽  
Observational Errors

Observational errors of Particle Filtering are studied over the case of a state-space model with a linear observation equation. In this study, the observational errors are estimated prior to the upcoming observations. This action is added to the basic algorithm of the filter as a new step for the acquisition of the state estimations. This intervention is useful in the presence of missing data problems mainly, as well as sample tracking for impoverishment issues. It applies theory of Homogeneous and Non-Homogeneous closed Markov Systems to the study of particle distribution over the state domain and, thus, lays the foundations for the employment of stochastic control against impoverishment. A simulating example is quoted to demonstrate the effectiveness of the proposed method in comparison with existing ones, showing that the proposed method is able to combine satisfactory precision of results with a low computational cost and provide an example to achieve impoverishment prediction and tracking.

Energy conservation based fuzzy tracking for unmanned aerial vehicle missions under a priori known wind information

2011 ◽  
Vol 24 (2) ◽  
pp. 278-294 ◽  
Author(s):  
Georgios P. Kladis ◽  
John T. Economou ◽  
Kevin Knowles ◽  
Jimmy Lauber ◽  
Thierry-Marie Guerra
Keyword(s):  
Energy Conservation ◽  
Unmanned Aerial Vehicle ◽  
A Priori ◽  
Aerial Vehicle

Generic Modeling and Control of an Open-Circuit Piston Pump—Part II: Control Strategies and Designs

2016 ◽  
Vol 138 (4) ◽  
Author(s):  
Shu Wang
Keyword(s):  
State Space ◽  
Control Strategies ◽  
State Space Model ◽  
Control Valve ◽  
Open Circuit ◽  
The State ◽  
Operating Conditions ◽  
Torque Control ◽  
Space Representation ◽  
Load Pressure

Hydromechanical compensators are often integrated with piston-type pumps to produce various control behavior, for example, pressure, load-sensing, power, or torque control. Various hydromechanical mechanisms (e.g., spring forces and load pressure) are found in the industry to ensure the desired effect of the system outputs: swash angle, discharge pressure, and input torque following the reference inputs. In a companion paper (Part I of this paper), a generic linearized state-space model is derived to investigate the pump dynamics and determine the design criteria and parameters. In the study, the state-space equations are used to propose and define the generic compensating control pump to conduct the similar strategies as hydromechanical pumps do. The different control purposes (pressure/flow/power compensating) are accomplished by only manipulating the generic regulate inputs given by an electrical proportional control valve. In the open-circuit pump, the generic controllers are proposed to generate these inputs by using one unique mechanical and electronic architecture to establish various purposes of flow, pressure, torque desired control, and even more control objectives. The controller is developed in accordance with the state-space representation and by following the models of the hydromechanical compensators that can facilitate the correlation verification. The proposed controllers are able to offer more intelligent and cost-saving control strategies for open-circuit piston pumps. To achieve the similar performance as hydromechanical compensators do and implement the comparative study, control gains and settings in the controller can be determined from ones that hydromechanical compensators have. The difference is that electronic signals (swash plate position, pressure, etc.) work as feedbacks together with other control gains to regulate the input signals. For the different control purposes, control gains are able to be set conveniently for the various control operating conditions with combining the certain feedbacks on the same hardware platform that will be value efficient and capable of control intelligence. In the paper, results of predictions made by the model are presented and compared with some experimental data of hydromechanical designs. Further work on the advanced model-based control and estimation is anticipated to be addressed.

State Feedback Controller - An Alternative Approach Applied to Unmanned Aerial Vehicle

2014 ◽  
Vol 704 ◽  
pp. 270-276
Author(s):  
Renato A. Aguiar ◽  
Fabrizio Leonardi
Keyword(s):  
Control Systems ◽  
Unmanned Aerial Vehicle ◽  
State Feedback ◽  
The State ◽  
Feedback Controller ◽  
Feedback Gain ◽  
State Feedback Controller ◽  
Alternative Approach ◽  
Aerial Vehicle ◽  
Alternative Methodology

The primary goal of this work is to propose an alternative methodology as a first approach in the design of control systems by means of a feedback state gain. The proposed method is detailed and an application is presented. The results show relevant aspects regarding the state feedback gain, especially in regard to variation in the parameters of the plant.

scholarly journals Devising an image processing method for transport infrastructure monitoring systems

2021 ◽  
Vol 4 (2(112)) ◽  
pp. 18-25
Author(s):  
Oleksandr Volkov ◽  
Mykola Komar ◽  
Dmytro Volosheniuk
Keyword(s):  
Unmanned Aerial Vehicle ◽  
The State ◽  
Transport Infrastructure ◽  
Dynamic Monitoring ◽  
Contour Analysis ◽  
Binary Images ◽  
Infrastructure Monitoring ◽  
Sorting Data ◽  
Aerial Vehicle ◽  
Image Contour

Identifying and categorizing contours in images is important in many areas of computer vision. Examples include such operational tasks solved by using unmanned aerial vehicles as dynamic monitoring of the condition of transport infrastructure, in particular road markings. This study has established that current methods of image contour analysis do not produce clear and reliable results when solving the task of monitoring the state of road markings. Therefore, it is a relevant scientific and applied task to improve the methods and models of filtration, processing of binary images, and qualitative and meaningful separation of the boundaries of objects of interest. To solve the task of highlighting road marking contours on images acquired from an unmanned aerial vehicle, a method has been devised that includes an operational tool for image preprocessing – a combined filter. The method has several advantages and eliminates the limitations of known methods in determining the boundaries of the location of the object of interest, by highlighting the contours of a cluster of points using histograms. The method and procedures reported here make it possible to successfully solve problems that are largely similar to those that an expert person can face when solving intelligent tasks of processing and filtering information. The proposed method was verified at an enterprise producing the Ukrainian unmanned aerial vehicle "Spectator" during tests of information technology of dynamic monitoring of the state of transport infrastructure. The results could be implemented in promising intelligent control systems in the field of modeling human conscious behavior when sorting data required for the perception of environmental features

Lateral directional parameter estimation of a miniature unmanned aerial vehicle using maximum likelihood and Neural Gauss Newton methods

2018 ◽  
Vol 122 (1252) ◽  
pp. 889-912
Author(s):  
Subrahmanyam Saderla ◽  
Dhayalan Rajaram ◽  
A. K. Ghosh
Keyword(s):  
Parameter Estimation ◽  
Maximum Likelihood ◽  
Unmanned Aerial Vehicle ◽  
Rectangular Cross Section ◽  
A Priori ◽  
Flight Data ◽  
Aerodynamic Model ◽  
Estimated Parameters ◽  
Aerial Vehicle ◽  
Cramer Rao Bound

ABSTRACTThe current research paper describes the lateral-directional parameter estimation from flight data of a miniature Unmanned Aerial Vehicle (UAV) using Maximum Likelihood (ML), and Neural-Gauss-Newton (NGN) methods. An unmanned configuration with a cropped delta planform and thin rectangular cross-section has been designed, fabricated and instrumented. Exhaustive full-scale wind-tunnel tests were performed on the UAV to extract the form of aerodynamic model that has to be postulated a priori for parameter estimation. Rigorous flight tests have been performed to acquire the flight data for several prescribed manoeuvres. Four sets of compatible flight data have been used to carry out parameter estimation using classical ML and neural-network-based NGN methods. It is observed that the estimated parameters are consistent and the lower values of the Cramer-Rao bound for the corresponding estimates have shown significant confidence in the obtained parameters. Furthermore, to validate the aerodynamic model used and to enhance the confidence in the estimated parameters, a proof of match exercise has been carried out.

Sign in / Sign up

Export Citation Format

Share Document