Active Guidance for a Finless Rocket using Neuroevolution
|
|
- Jean Boyd
- 6 years ago
- Views:
Transcription
1 Active Guidance for a Finless Rocket using Neuroevolution Gomez, F.J. & Miikulainen, R. (2003). Genetic and Evolutionary Computation Gecco, 2724, Introduction Sounding rockets are used for making scientific measurements of the Earth s upper atmosphere. They serve an invaluable role in many areas of scientific research including high-g-force testing, meteorology, radio-astronomy, environmental sampling and micro-gravity experimentation and have been used for over 40 years. Today, they are the most cost-effective platform for upper atmosphere experiments. To maintain stability and to keep a relatively straight path, sounding rockets are equipped with fins. Fins however increase both mass and drag on the rocket which lowers the final altitude or apogee that can be reached with a given amount of fuel. A rocket with smaller or no fins could fly higher than a full-finned design, however it is unstable and thus needs active attitude control or guidance. Early guidance systems of finless rockets are based on classical feedback control such as Proportional Integral-Differential (PID) methods. PIDs control the thrust angle of the engines. To apply these linear methods engineers must make simplifying assumptions, because rocket flight dynamics are highly non-linear. These assumptions must not be violated during flight. This requires detailed knowledge of the rocket s dynamics which can be very costly to acquire. Non-linear approaches such as neural networks have been explored. Neural networks can implement arbitrary non-linear mappings that can make control greatly more accurate and robust, but, unfortunately, still require significant domain knowledge to train. A method is proposed to develop more economic finless sounding rockets by using Enforced SubPopulations (ESP) to evolve a neural network guidance system. Test case is a finless version of the RSX-2 sounding rocket. This rocket uses differential thrust of its four engines to control attitude. By evolving a neural network controller which maps the state of the rocket to thrust commands, the guidance problem can be solved without the need for analytical modelling of the rocket s dynamics or prior knowledge of the appropriate control strategy to employ. A sufficiently accurate simulator and a fitness function are required to test ESP. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 1
2 Enforced SubPopulations (ESP) ESP is a neuroevolution method that extends the Symbiotic, Adaptive Neuroevolution algorithm (SANE). Both ESP and SANE evolve partial solutions or neurons instead of complete networks, and a subset of these neurons are put together to form a complete network. In ESP, subpopulations are predefined and a neuron can only be recombined with members of its own subpopulation (explicit subtasks). This way the neurons in each subpopulation can evolve independently and specialize rapidly into good network sub-functions. Evolution in ESP proceeds as follows: 1. Initialization. A subpopulation of neuron chromosomes is created. Each chromosome encodes the input and output connection weights of a neuron with a random string of real numbers. 2. Evaluation. A random selection of neurons, one from each subpopulation, takes place to form the hidden layer of a complete network. This network is submitted to a trial and awarded a fitness score. This is added to the cumulative fitness score and the process is repeated until each neuron has participated in an average of e.g. 10 trials. 3. Recombination. Average fitness of each neuron is calculated by dividing its cumulative fitness by the number of trials in which it participated. Ranking by average fitness than takes place and the top quartile is recombined with a higher-ranking neuron. The offspring replaces the lowest-ranking half of the subpopulation. 4. Repeating the evaluation and recombination cycle until a well performing network is found. Evolving neural networks at the neuron level are efficient for solving reinforcement learning tasks. ESP is more efficient than SANE first, because the subpopulations are already present with ESP. This way, organization does not need to take place from one single large population, and their progressive specialization is not hindered by recombination across specializations. Second, because the network is formed out of a representative from each specialization, a context dependent role evaluation of neurons takes place. As with a normal GA, a diversity decline over the course of evolution takes place with ESP. To deal with this premature convergence, ESP is combined with burst mutation. When performance has stagnated for a predetermined number of generations, new subpopulations are created by adding noise to each of the neurons in the best solution. After noise is added, evolution resumes, searching the space in a neighbourhood around the previous best solution. This done by applying Cauchy distribution to ensure that most changes are small while allowing for larger change to a some weights: f(x) = 2 2 π(a + x ) This technique of recharging the subpopulations keeps diversity so that solutions can be found even in prolonged evolution. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 2
3 The Finless Rocket Guidance Task The motion of a rocket is defined by the translation of its center of gravity (CG), and the rotation of the body about the CG in the pitch, yaw and roll axes. Four forces act upon the rocket in flight: (1) The thrust of the engines, (2) the drag of the atmosphere exerted at the center of pressure (CP), (3) the lift force generated by the fins along the yaw axis, and (4) the side force generated by the fins along the pitch axis. The angle between the direction the rocket is flying and the longitudinal axis of the rocket in the yaw-roll plane is known as the angle of attack or α. The angle in the pitchroll plane is known as the sideslip angle or β. When α or β is greater than 0 degrees the rocket will start to tumble if it is not stable. With fins, a torque is generated by the lift or side force of the fins that counteract the drag torque and α and β are minimized. Without fins, the CP is ahead of the CG causing the rocket to be unstable and a nonzero α or β will tend to grow during flight. During flight, the interactions between the rocket and the atmosphere are highly non-linear and complex, and the behaviour continuously changes throughout flight. From 0 to about 22,000ft the drag rises sharply, causing an increase of torque on the rocket and making attitude control increasingly difficult. The distance between the CG and CP also increases during this period because the consumption of fuel causes the CG to move back. Both lead to an increasingly unstable rocket. After 22,000ft the air becomes less dense, drag thus decreases and the CP steadily migrates back towards the CG, so the rocket becomes easier to control. For ESP, this means that the task becomes progressively harder as the population improves and the rocket is controlled to higher altitudes. Even above 22,000ft, progress in evolution becomes increasingly difficult because the controller is constantly entering unfamiliar state space. The control task was found to be too hard; evolution stalls and converges to a local maxima. Therefore, an incremental evolution approach is applied. The initial task is made easier by using a more stable version of the rocket first. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 3
4 Rocket Control Experiments Simulation environment As an evolution environment a adapted version the JSBSim Flight Dynamics Model is used. Aerodynamic forces and moments on the rocket were calculated using a detailed geometric model of the RSX-2. Four fin configurations were used: full fins, half sized fins, quarter sized fins, and no fins. Control architecture The controller is a feedforward neural network with one hidden layer. The control timestep is 0.05 seconds. At this interval the controller receives a vector input about the current orientation, orientation change rate, α, β, current throttle of the four thrusters, altitude and velocity. This vector input is propagated through the network to produce a new throttle position for each engine determined by: u = 1.0 / δ, i = i o i where u i is the throttle position of thruster i, o i is the value of network output unit i, 0 u i,o i 1, and δ 1.0. δ controls how far the controller is permitted to throttle back an engine from 100% thrust. Experimental setup The objective was to let ESP evolve a controller which was able to control the thrust of the rockets engines to maintain α and β within ±5 degrees. Each network was therefore evaluated in a single trial that consisted of the following four phases: 1. At t 0, the rocket is on a 50ft rail and the engines are ignited. 2. At t 1 >t 0, the rockets ascending begins with engines at full thrust. 3. At t 2 >t 1, the rocket leaves the rail and the controller begins to modulate the thrust. 4. At t f >t 2, one of two events occur: a. α or β exceeds ±5 degrees; failure. b. Burnout is reached; success. The rockets altitude at t f becomes the fitness score. A large locally maximal region was found in the network weight space which was keeping all four engines at full throttle. In initial populations, this policy is likely, but does not solve the task. Therefore all controllers that exhibited this policy were penalized by setting their fitness score to zero. The simulation used 10 subpopulations (10 hidden units) of 200 neurons, and δ was set to 10, meaning that the thrust range lies between 90% and 100% for each engine. This range proved sufficient in early testing. The earlier discussed incremental evolution method used was the quarter sized finned rocket. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 4
5 Results ESP solved the quarter-finned controlling task in approximately 600,000 evaluations. Another 50,000 evaluations were required to transition to the finless rocket. The full-finned rocket without guidance reached burnout at approximately 70,000ft. The quarter-finned and finless rockets with guidance both exceed this altitude by 10,000ft and 15,000ft respectively. The final altitude of the finless rocket is about 20 miles higher than that of the finned rocket. During flight, the controller makes smooth changes to the thrust of the engines throughout the flight. With guidance, α and β are kept at very small values up to burnout, whereas the unguided quarter-finned and half-finned rockets start to tumble as soon as α and β diverge from 0 degrees. Compared to the quarter-finned controller, the finless controller not only solves a more difficult task, but does so with more optimal performance. Discussion/Conclusion The rocket control task is representative of complex non-linear tasks. The advantage of ESP over traditional engineering approaches is that it does not require formal knowledge of system behaviour or prior knowledge of correct control behaviour. Furthermore, the differential thrust approach is feasible and the simulation has provided valuable information about the behaviour of the rocket. In future research, the task will be made more realistic in two ways: (1) the controller will no longer receive α and β values as input, and (2) instead of a generating continuous control signal, the network will output a binary vector to throttle back. After this, work will focus on varying environmental parameters and incorporating noise and wind. The authors conclude that the through ESP evolved guidance system is able to stabilize the finless rocket and greatly improve its final altitude compared to the full-finned, stable version of the rocket. Neuroevolution is a promising approach for difficult non-linear control tasks in the real world. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 5
6 Own Discussion In general, superficial explanations of processes are given in the article. When explaining the ESP method; the authors do not go into detail about the underlying algorithm of which ESP consist. This not only hinders acquiring insight in the ESP algorithm, it also compromises the ability to repeat the current study. It is claimed by the authors that ESP can be generalised to other tasks, examples of other tasks given in the article are closed-loop tasks, such as pole-balancing. Although tasks are being mentioned that could be controlled in a more open-loop manner, such robot arm control, I doubt that ESP will be able to do these sorts of tasks in its current form, i.e. without having both formal knowledge about the behaviour of the system and prior knowledge of the correct control behaviour. Furthermore, tests are performed with quarter-finned and finless rockets only. I wonder why the authors did not use a gradually decreasing fin size when implementing an incremental evolution approach. This seems a more natural way of implementing neural evolution and prevents making arbitrary choices such as in this case- choosing the size of the fins (full, half, quarter, and no fins). The authors stop the simulations when reaching burnout and fitness scores are then awarded based on the time until burnout (in the case of success). However, after burnout, the finless rocket cannot be controlled anymore, but it is still unstable. The authors fail to mention this or to provide possible solutions to this problem, e.g. using retractable fins which unfold directly after burnout. In the conclusion, the authors state that neuroevolution is a promising approach for difficult nonlinear control tasks in the real world. Based on their simulation experiments only, I find this to be a quite preliminary conclusion. Cognitive Robotics\Applications Summary of: Gomez (2003) Esar van Hal 6
Principles of Rocketry
1-1 Principles of Rocketry 1-2 Water Rockets BASIC CONCEPTS 1-3 What is a Rocket? A chamber enclosing a gas under pressure. A balloon is a simple example of a rocket. Rubber walls compress the air inside.
More informationCHAPTER 1. Introduction
CHAPTER 1 Introduction Linear geometric control theory was initiated in the beginning of the 1970 s, see for example, [1, 7]. A good summary of the subject is the book by Wonham [17]. The term geometric
More informationCoevolution of Multiagent Systems using NEAT
Coevolution of Multiagent Systems using NEAT Matt Baer Abstract This experiment attempts to use NeuroEvolution of Augmenting Topologies (NEAT) create a Multiagent System that coevolves cooperative learning
More informationNeuroevolutionary Planning for Robotic Control
Neuroevolutionary Planning for Robotic Control Reza Mahjourian Department of Computer Science The University of Texas at Austin Austin, TX 78712 reza@cs.utexas.edu Doctoral Dissertation Proposal Supervising
More informationPerformance. 7. Aircraft Performance -Basics
Performance 7. Aircraft Performance -Basics In general we are interested in finding out certain performance characteristics of a vehicle. These typically include: how fast and how slow an aircraft can
More informationUsing NEAT to Stabilize an Inverted Pendulum
Using NEAT to Stabilize an Inverted Pendulum Awjin Ahn and Caleb Cochrane May 9, 2014 Abstract The inverted pendulum balancing problem is a classic benchmark problem on which many types of control implementations
More informationA Blade Element Approach to Modeling Aerodynamic Flight of an Insect-scale Robot
A Blade Element Approach to Modeling Aerodynamic Flight of an Insect-scale Robot Taylor S. Clawson, Sawyer B. Fuller Robert J. Wood, Silvia Ferrari American Control Conference Seattle, WA May 25, 2016
More informationPRINCIPLES OF FLIGHT
1 Considering a positive cambered aerofoil, the pitching moment when Cl=0 is: A infinite B positive (nose-up). C negative (nose-down). D equal to zero. 2 The angle between the aeroplane longitudinal axis
More informationA SIMPLIFIED ANALYSIS OF NONLINEAR LONGITUDINAL DYNAMICS AND CONCEPTUAL CONTROL SYSTEM DESIGN
A SIMPLIFIED ANALYSIS OF NONLINEAR LONGITUDINAL DYNAMICS AND CONCEPTUAL CONTROL SYSTEM DESIGN ROBBIE BUNGE 1. Introduction The longitudinal dynamics of fixed-wing aircraft are a case in which classical
More informationChapter 2 Review of Linear and Nonlinear Controller Designs
Chapter 2 Review of Linear and Nonlinear Controller Designs This Chapter reviews several flight controller designs for unmanned rotorcraft. 1 Flight control systems have been proposed and tested on a wide
More informationExtended longitudinal stability theory at low Re - Application to sailplane models
Extended longitudinal stability theory at low Re - Application to sailplane models matthieu.scherrer@free.fr November 26 C L C m C m W X α NP W X V NP W Lift coefficient Pitching moment coefficient Pitching
More informationIntroduction to Flight Dynamics
Chapter 1 Introduction to Flight Dynamics Flight dynamics deals principally with the response of aerospace vehicles to perturbations in their flight environments and to control inputs. In order to understand
More informationDesign and modelling of an airship station holding controller for low cost satellite operations
AIAA Guidance, Navigation, and Control Conference and Exhibit 15-18 August 25, San Francisco, California AIAA 25-62 Design and modelling of an airship station holding controller for low cost satellite
More informationChapter 1 Lecture 2. Introduction 2. Topics. Chapter-1
Chapter 1 Lecture 2 Introduction 2 Topics 1.4 Equilibrium of airplane 1.5 Number of equations of motion for airplane in flight 1.5.1 Degrees of freedom 1.5.2 Degrees of freedom for a rigid airplane 1.6
More informationApplication of Neural Networks for Control of Inverted Pendulum
Application of Neural Networks for Control of Inverted Pendulum VALERI MLADENOV Department of Theoretical Electrical Engineering Technical University of Sofia Sofia, Kliment Ohridski blvd. 8; BULARIA valerim@tu-sofia.bg
More informationFlight Dynamics and Control
Flight Dynamics and Control Lecture 1: Introduction G. Dimitriadis University of Liege Reference material Lecture Notes Flight Dynamics Principles, M.V. Cook, Arnold, 1997 Fundamentals of Airplane Flight
More informationPerformance. 5. More Aerodynamic Considerations
Performance 5. More Aerodynamic Considerations There is an alternative way of looking at aerodynamic flow problems that is useful for understanding certain phenomena. Rather than tracking a particle of
More informationLecture #AC 3. Aircraft Lateral Dynamics. Spiral, Roll, and Dutch Roll Modes
Lecture #AC 3 Aircraft Lateral Dynamics Spiral, Roll, and Dutch Roll Modes Copy right 2003 by Jon at h an H ow 1 Spring 2003 16.61 AC 3 2 Aircraft Lateral Dynamics Using a procedure similar to the longitudinal
More informationNeuroevolution for Reinforcement Learning Using Evolution Strategies
Neuroevolution for Reinforcement Learning Using Evolution Strategies Christian Igel Institut für Neuroinformatik Ruhr-Universität Bochum 44780 Bochum, Germany christian.igel@neuroinformatik.rub.de Abstract-
More informationQuadrotor Modeling and Control for DLO Transportation
Quadrotor Modeling and Control for DLO Transportation Thesis dissertation Advisor: Prof. Manuel Graña Computational Intelligence Group University of the Basque Country (UPV/EHU) Donostia Jun 24, 2016 Abstract
More informationFin design mission. Team Members
Fin design mission Team Members Mission: Your team will determine the best fin design for a model rocket. You will compare highest altitude, flight characteristics, and weathercocking. You will report
More informationTransfer of Neuroevolved Controllers in Unstable Domains
In Proceedings of the Genetic Evolutionary Computation Conference (GECCO 24) Transfer of Neuroevolved Controllers in Unstable Domains Faustino J. Gomez and Risto Miikkulainen Department of Computer Sciences,
More informationThe Role of Zero Dynamics in Aerospace Systems
The Role of Zero Dynamics in Aerospace Systems A Case Study in Control of Hypersonic Vehicles Andrea Serrani Department of Electrical and Computer Engineering The Ohio State University Outline q Issues
More informationAim. Unit abstract. Learning outcomes. QCF level: 6 Credit value: 15
Unit T23: Flight Dynamics Unit code: J/504/0132 QCF level: 6 Credit value: 15 Aim The aim of this unit is to develop learners understanding of aircraft flight dynamic principles by considering and analysing
More informationEvolving Neural Networks in Compressed Weight Space
Evolving Neural Networks in Compressed Weight Space Jan Koutník IDSIA University of Lugano Manno-Lugano, CH hkou@idsia.ch Faustino Gomez IDSIA University of Lugano Manno-Lugano, CH tino@idsia.ch Jürgen
More informationFlight and Orbital Mechanics
Flight and Orbital Mechanics Lecture slides Challenge the future 1 Flight and Orbital Mechanics Lecture 7 Equations of motion Mark Voskuijl Semester 1-2012 Delft University of Technology Challenge the
More informationNEUROEVOLUTION. Contents. Evolutionary Computation. Neuroevolution. Types of neuro-evolution algorithms
Contents Evolutionary Computation overview NEUROEVOLUTION Presenter: Vlad Chiriacescu Neuroevolution overview Issues in standard Evolutionary Computation NEAT method Complexification in competitive coevolution
More informationAE Stability and Control of Aerospace Vehicles
AE 430 - Stability and ontrol of Aerospace Vehicles Static/Dynamic Stability Longitudinal Static Stability Static Stability We begin ith the concept of Equilibrium (Trim). Equilibrium is a state of an
More informationForming Neural Networks Through Efficient and Adaptive Coevolution
Forming Neural Networks Through Efficient and Adaptive Coevolution David E. Moriarty Information Sciences Institute University of Southern California 4676 Admiralty Way Marina del Rey, CA 90292 moriarty@isi.edu
More informationFundamentals of Airplane Flight Mechanics
David G. Hull Fundamentals of Airplane Flight Mechanics With 125 Figures and 25 Tables y Springer Introduction to Airplane Flight Mechanics 1 1.1 Airframe Anatomy 2 1.2 Engine Anatomy 5 1.3 Equations of
More informationFlight Dynamics, Simulation, and Control
Flight Dynamics, Simulation, and Control For Rigid and Flexible Aircraft Ranjan Vepa CRC Press Taylor & Francis Group Boca Raton London New York CRC Press is an imprint of the Taylor & Francis Group, an
More informationWhat is flight dynamics? AE540: Flight Dynamics and Control I. What is flight control? Is the study of aircraft motion and its characteristics.
KING FAHD UNIVERSITY Department of Aerospace Engineering AE540: Flight Dynamics and Control I Instructor Dr. Ayman Hamdy Kassem What is flight dynamics? Is the study of aircraft motion and its characteristics.
More informationNeural Network Control of an Inverted Pendulum on a Cart
Neural Network Control of an Inverted Pendulum on a Cart VALERI MLADENOV, GEORGI TSENOV, LAMBROS EKONOMOU, NICHOLAS HARKIOLAKIS, PANAGIOTIS KARAMPELAS Department of Theoretical Electrical Engineering Technical
More informationFLIGHT DYNAMICS. Robert F. Stengel. Princeton University Press Princeton and Oxford
FLIGHT DYNAMICS Robert F. Stengel Princeton University Press Princeton and Oxford Preface XV Chapter One Introduction 1 1.1 ELEMENTS OF THE AIRPLANE 1 Airframe Components 1 Propulsion Systems 4 1.2 REPRESENTATIVE
More informationHierarchical Evolution of Neural Networks. The University of Texas at Austin. Austin, TX Technical Report AI January 1996.
Hierarchical Evolution of Neural Networks David E. Moriarty and Risto Miikkulainen Department of Computer Sciences The University of Texas at Austin Austin, TX 78712 moriarty,risto@cs.utexas.edu Technical
More informationHigh-Power Rocketry. Calculating the motion of a rocket for purely vertical flight.
High-Power Rocketry Calculating the motion of a rocket for purely vertical flight. Phase I Boost phase: motor firing (rocket losing mass), going upwards faster and faster (accelerating upwards) Phase II
More informationGenetic Algorithms and Genetic Programming Lecture 17
Genetic Algorithms and Genetic Programming Lecture 17 Gillian Hayes 28th November 2006 Selection Revisited 1 Selection and Selection Pressure The Killer Instinct Memetic Algorithms Selection and Schemas
More informationArtificial Neural Networks Examination, March 2004
Artificial Neural Networks Examination, March 2004 Instructions There are SIXTY questions (worth up to 60 marks). The exam mark (maximum 60) will be added to the mark obtained in the laborations (maximum
More informationNEURAL-NETWORK BASED AIRCRAFT CONTROL SYSTEM OPTIMISATION
УДК 621.337.1:004.032.26(045) А. І. Dovgan, V. A. Apostolyuk NEURAL-NETWORK BASED AIRCRAFT CONTROL SYSTEM OPTIMISATION Introduction The problem of automatic control systems development for complex dynamic
More informationEvolutionary Computation
Evolutionary Computation - Computational procedures patterned after biological evolution. - Search procedure that probabilistically applies search operators to set of points in the search space. - Lamarck
More informationMechatronics Assignment # 1
Problem # 1 Consider a closed-loop, rotary, speed-control system with a proportional controller K p, as shown below. The inertia of the rotor is J. The damping coefficient B in mechanical systems is usually
More informationPitch Control of Flight System using Dynamic Inversion and PID Controller
Pitch Control of Flight System using Dynamic Inversion and PID Controller Jisha Shaji Dept. of Electrical &Electronics Engineering Mar Baselios College of Engineering & Technology Thiruvananthapuram, India
More informationLocalizer Hold Autopilot
Localizer Hold Autopilot Prepared by A.Kaviyarasu Assistant Professor Department of Aerospace Engineering Madras Institute Of Technology Chromepet, Chennai Localizer hold autopilot is one of the important
More informationAEROSPACE ENGINEERING
AEROSPACE ENGINEERING Subject Code: AE Course Structure Sections/Units Topics Section A Engineering Mathematics Topics (Core) 1 Linear Algebra 2 Calculus 3 Differential Equations 1 Fourier Series Topics
More informationMechanics of Flight. Warren F. Phillips. John Wiley & Sons, Inc. Professor Mechanical and Aerospace Engineering Utah State University WILEY
Mechanics of Flight Warren F. Phillips Professor Mechanical and Aerospace Engineering Utah State University WILEY John Wiley & Sons, Inc. CONTENTS Preface Acknowledgments xi xiii 1. Overview of Aerodynamics
More information1. (a) Describe the difference between over-expanded, under-expanded and ideallyexpanded
Code No: R05322106 Set No. 1 1. (a) Describe the difference between over-expanded, under-expanded and ideallyexpanded rocket nozzles. (b) While on its way into orbit a space shuttle with an initial mass
More informationAutonomous Mobile Robot Design
Autonomous Mobile Robot Design Topic: Guidance and Control Introduction and PID Loops Dr. Kostas Alexis (CSE) Autonomous Robot Challenges How do I control where to go? Autonomous Mobile Robot Design Topic:
More informationCHAPTER 5 FUZZY LOGIC FOR ATTITUDE CONTROL
104 CHAPTER 5 FUZZY LOGIC FOR ATTITUDE CONTROL 5.1 INTRODUCTION Fuzzy control is one of the most active areas of research in the application of fuzzy set theory, especially in complex control tasks, which
More informationMODELING OF DUST DEVIL ON MARS AND FLIGHT SIMULATION OF MARS AIRPLANE
MODELING OF DUST DEVIL ON MARS AND FLIGHT SIMULATION OF MARS AIRPLANE Hirotaka Hiraguri*, Hiroshi Tokutake* *Kanazawa University, Japan hiraguri@stu.kanazawa-u.ac.jp;tokutake@se.kanazawa-u.ac.jp Keywords:
More informationIntroduction to Aerospace Engineering
Introduction to Aerospace Engineering 5. Aircraft Performance 5.1 Equilibrium Flight In order to discuss performance, stability, and control, we must first establish the concept of equilibrium flight.
More informationDomain Knowledge in Neuroevolution
170 Utilizing Domain Knowledge in Neuroevolution J altles Fan JFAN(~CS.UTEXAS.EDU Raymond Lau LAURK@CS.UTEXAS.EDU l~ sto Milkkulalnen RISTO@CS.UTEXAS.EDU Department of Computer Sciences, The University
More informationInteger weight training by differential evolution algorithms
Integer weight training by differential evolution algorithms V.P. Plagianakos, D.G. Sotiropoulos, and M.N. Vrahatis University of Patras, Department of Mathematics, GR-265 00, Patras, Greece. e-mail: vpp
More informationNonlinear and Neural Network-based Control of a Small Four-Rotor Aerial Robot
Nonlinear and Neural Network-based Control of a Small Four-Rotor Aerial Robot Holger Voos Abstract Small four-rotor aerial robots, so called quadrotor UAVs, have an enormous potential for all kind of neararea
More informationAFRL MACCCS Review. Adaptive Control of the Generic Hypersonic Vehicle
AFRL MACCCS Review of the Generic Hypersonic Vehicle PI: Active- Laboratory Department of Mechanical Engineering Massachusetts Institute of Technology September 19, 2012, MIT AACL 1/38 Our Team MIT Team
More informationNewton s 2 nd Law If an unbalanced (net) force acts on an object, that object will accelerate (or decelerate) in the direction of the force.
Bottle Rocket Lab Physics Concepts: Newton s 1 st Law - Every object in a state of uniform motion tends to remain in that state of motion unless an external force is applied to it. This we recognize as
More informationAutopilot design for small fixed wing aerial vehicles. Randy Beard Brigham Young University
Autopilot design for small fixed wing aerial vehicles Randy Beard Brigham Young University Outline Control architecture Low level autopilot loops Path following Dubins airplane paths and path management
More informationA WAVELET BASED FLIGHT DATA PREPROCESSING METHOD FOR FLIGHT CHARACTERISTICS ESTIMATION AND FAULT DETECTION
A WAVELET BASED FLIGHT DATA PREPROCESSING METHOD FOR FLIGHT CHARACTERISTICS ESTIMATION AND FAULT DETECTION Masaru Naruoka Japan Aerospace Exploration Agency Keywords: Flight analyses, Multiresolution Analysis,
More informationHover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller
Vol.13 No.1, 217 مجلد 13 العدد 217 1 Hover Control for Helicopter Using Neural Network-Based Model Reference Adaptive Controller Abdul-Basset A. Al-Hussein Electrical Engineering Department Basrah University
More informationAerodynamics SYST 460/560. George Mason University Fall 2008 CENTER FOR AIR TRANSPORTATION SYSTEMS RESEARCH. Copyright Lance Sherry (2008)
Aerodynamics SYST 460/560 George Mason University Fall 2008 1 CENTER FOR AIR TRANSPORTATION SYSTEMS RESEARCH Copyright Lance Sherry (2008) Ambient & Static Pressure Ambient Pressure Static Pressure 2 Ambient
More informationNear-Hover Dynamics and Attitude Stabilization of an Insect Model
21 American Control Conference Marriott Waterfront, Baltimore, MD, USA June 3-July 2, 21 WeA1.4 Near-Hover Dynamics and Attitude Stabilization of an Insect Model B. Cheng and X. Deng Abstract In this paper,
More informationScaling Up. So far, we have considered methods that systematically explore the full search space, possibly using principled pruning (A* etc.).
Local Search Scaling Up So far, we have considered methods that systematically explore the full search space, possibly using principled pruning (A* etc.). The current best such algorithms (RBFS / SMA*)
More informationRESEARCH ON AEROCRAFT ATTITUDE TESTING TECHNOLOGY BASED ON THE BP ANN
RESEARCH ON AEROCRAFT ATTITUDE TESTING TECHNOLOGY BASED ON THE BP ANN 1 LIANG ZHI-JIAN, 2 MA TIE-HUA 1 Assoc. Prof., Key Laboratory of Instrumentation Science & Dynamic Measurement, North University of
More informationCooperative Coevolution of Multi-Agent Systems
Cooperative Coevolution of Multi-Agent Systems Chern Han Yong and Risto Miikkulainen Department of Computer Sciences The University of Texas at Austin Austin, T 787 USA compute,risto@cs.utexas.edu Technical
More informationEvolving Keras Architectures for Sensor Data Analysis
Evolving Keras Architectures for Sensor Data Analysis Petra Vidnerová Roman Neruda Institute of Computer Science The Czech Academy of Sciences FedCSIS 2017 Outline Introduction Deep Neural Networks KERAS
More informationAn Effective Chromosome Representation for Evolving Flexible Job Shop Schedules
An Effective Chromosome Representation for Evolving Flexible Job Shop Schedules Joc Cing Tay and Djoko Wibowo Intelligent Systems Lab Nanyang Technological University asjctay@ntuedusg Abstract As the Flexible
More informationUniversity of Utah Electrical & Computer Engineering Department ECE 3510 Lab 9 Inverted Pendulum
University of Utah Electrical & Computer Engineering Department ECE 3510 Lab 9 Inverted Pendulum p1 ECE 3510 Lab 9, Inverted Pendulum M. Bodson, A. Stolp, 4/2/13 rev, 4/9/13 Objectives The objective of
More informationkiteplane s length, wingspan, and height are 6 mm, 9 mm, and 24 mm, respectively, and it weighs approximately 4.5 kg. The kiteplane has three control
Small Unmanned Aerial Vehicle with Variable Geometry Delta Wing Koji Nakashima, Kazuo Okabe, Yasutaka Ohsima 2, Shuichi Tajima 2 and Makoto Kumon 2 Abstract The kiteplane that is considered in this paper
More informationLearning Gaussian Process Models from Uncertain Data
Learning Gaussian Process Models from Uncertain Data Patrick Dallaire, Camille Besse, and Brahim Chaib-draa DAMAS Laboratory, Computer Science & Software Engineering Department, Laval University, Canada
More informationLecture AC-1. Aircraft Dynamics. Copy right 2003 by Jon at h an H ow
Lecture AC-1 Aircraft Dynamics Copy right 23 by Jon at h an H ow 1 Spring 23 16.61 AC 1 2 Aircraft Dynamics First note that it is possible to develop a very good approximation of a key motion of an aircraft
More informationTechnology of Rocket
Technology of Rocket Parts of Rocket There are four major parts of rocket Structural system Propulsion system Guidance system Payload system Structural system The structural system of a rocket includes
More informationDesign of a Missile Autopilot using Adaptive Nonlinear Dynamic Inversion
2005 American Control Conference June 8-10,2005. Portland, OR, USA WeA11.1 Design of a Missile Autopilot using Adaptive Nonlinear Dynamic Inversion Rick Hindman, Ph.D. Raytheon Missile Systems Tucson,
More informationCS491/691: Introduction to Aerial Robotics
CS491/691: Introduction to Aerial Robotics Topic: Midterm Preparation Dr. Kostas Alexis (CSE) Areas of Focus Coordinate system transformations (CST) MAV Dynamics (MAVD) Navigation Sensors (NS) State Estimation
More informationFullscale Windtunnel Investigation of Actuator Effectiveness during Stationary Flight within the Entire Flight Envelope of a Tiltwing MAV
Fullscale Windtunnel Investigation of Actuator Effectiveness during Stationary Flight within the Entire Flight Envelope of a Tiltwing MAV M. Schütt, P. Hartmann and D. Moormann Institute of Flight System
More informationThe Fundamentals of Classic Style Skydiving by Vladimir Milosavljevic, assisted by Tamara Koyn
The Fundamentals of Classic Style Skydiving by Vladimir Milosavljevic, assisted by Tamara Koyn Although very simple in maneuvering description, classic style skydiving has very interesting history and
More informationTurn Performance of an Air-Breathing Hypersonic Vehicle
Turn Performance of an Air-Breathing Hypersonic Vehicle AIAA Aircraft Flight Mechanics Conference Derek J. Dalle, Sean M. Torrez, James F. Driscoll University of Michigan, Ann Arbor, MI 4809 August 8,
More informationRobust Controller Design for Speed Control of an Indirect Field Oriented Induction Machine Drive
Leonardo Electronic Journal of Practices and Technologies ISSN 1583-1078 Issue 6, January-June 2005 p. 1-16 Robust Controller Design for Speed Control of an Indirect Field Oriented Induction Machine Drive
More informationAerodynamics and Flight Mechanics
Aerodynamics and Flight Mechanics Principal Investigator: Mike Bragg Eric Loth Post Doc s: Graduate Students: Undergraduate Students: Sam Lee Jason Merret Kishwar Hossain Edward Whalen Chris Lamarre Leia
More informationArtificial Neural Networks Examination, June 2005
Artificial Neural Networks Examination, June 2005 Instructions There are SIXTY questions. (The pass mark is 30 out of 60). For each question, please select a maximum of ONE of the given answers (either
More informationSimulation of Non-Linear Flight Control Using Backstepping Method
Proceedings of the 2 nd International Conference of Control, Dynamic Systems, and Robotics Ottawa, Ontario, Canada, May 7 8, 2015 Paper No. 182 Simulation of Non-Linear Flight Control Using Backstepping
More informationLONGITUDINAL STABILITY AND TRIM OF AN ARIANE 5 FLY-BACK BOOSTER
12th AIAA International Space Planes and Hypersonic Systems and Technologies 1-19 December 23, Norfolk, Virginia AIAA 23-7 LONGITUDINAL STABILITY AND TRIM OF AN ARIANE FLY-BACK BOOSTER Th. Eggers DLR,
More informationAdaptive Winglet Design, Analysis and Optimisation of the Cant Angle for Enhanced MAV Performance
Adaptive Winglet Design, Analysis and Optimisation of the Cant Angle for Enhanced MAV Performance Chen-Ming Kuo and Christian Boller University of Saarland, Materials Science & Technology Dept. Chair of
More informationAerospace Engineering undergraduate studies (course 2006)
Aerospace Engineering undergraduate studies (course 2006) The Bachelor of Science degree final exam problems and questions Specialization administrator: prof. Cezary Galiński Field of Study Aerospace Engineering
More information3rd International Conference on Machinery, Materials and Information Technology Applications (ICMMITA 2015)
rd International Conference on Machinery, Materials and Information Technology Applications (ICMMITA 5) The open loop response analysis of duck wing with trust resistance balance and constant elasticity
More informationLecture Module 5: Introduction to Attitude Stabilization and Control
1 Lecture Module 5: Introduction to Attitude Stabilization and Control Lectures 1-3 Stability is referred to as a system s behaviour to external/internal disturbances (small) in/from equilibrium states.
More informationAircraft Maneuver Regulation: a Receding Horizon Backstepping Approach
Aircraft Maneuver Regulation: a Receding Horizon Backstepping Approach Giuseppe Notarstefano and Ruggero Frezza Abstract Coordinated flight is a nonholonomic constraint that implies no sideslip of an aircraft.
More informationOn Computational Limitations of Neural Network Architectures
On Computational Limitations of Neural Network Architectures Achim Hoffmann + 1 In short A powerful method for analyzing the computational abilities of neural networks based on algorithmic information
More informationA model of an aircraft towing a cable-body system
ANZIAM J. 47 (EMAC2005) pp.c615 C632, 2007 C615 A model of an aircraft towing a cable-body system C. K. H. Chin R. L. May (Received 2 November 2005; revised 31 January 2007) Abstract We integrate together
More informationReinforcement Learning and Control
CS9 Lecture notes Andrew Ng Part XIII Reinforcement Learning and Control We now begin our study of reinforcement learning and adaptive control. In supervised learning, we saw algorithms that tried to make
More informationTHE METEOROLOGICAL ROCKET SYSTEM FOR ATMOSPHERIC RESEARCH
THE METEOROLOGICAL ROCKET SYSTEM FOR ATMOSPHERIC RESEARCH Komissarenko Alexander I. (1) Kuznetsov Vladimir M. (1) Filippov Valerii V. (1) Ryndina Elena C. (1) (1) State Unitary Enterprise KBP Instrument
More informationNonlinear Landing Control for Quadrotor UAVs
Nonlinear Landing Control for Quadrotor UAVs Holger Voos University of Applied Sciences Ravensburg-Weingarten, Mobile Robotics Lab, D-88241 Weingarten Abstract. Quadrotor UAVs are one of the most preferred
More informationLecture 7 Artificial neural networks: Supervised learning
Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in
More informationStability and Control Some Characteristics of Lifting Surfaces, and Pitch-Moments
Stability and Control Some Characteristics of Lifting Surfaces, and Pitch-Moments The lifting surfaces of a vehicle generally include the wings, the horizontal and vertical tail, and other surfaces such
More informationDevelopment of a Deep Recurrent Neural Network Controller for Flight Applications
Development of a Deep Recurrent Neural Network Controller for Flight Applications American Control Conference (ACC) May 26, 2017 Scott A. Nivison Pramod P. Khargonekar Department of Electrical and Computer
More informationChapter 5 Performance analysis I Steady level flight (Lectures 17 to 20) Keywords: Steady level flight equations of motion, minimum power required,
Chapter 5 Performance analysis I Steady level flight (Lectures 17 to 20) Keywords: Steady level flight equations of motion, minimum power required, minimum thrust required, minimum speed, maximum speed;
More informationSeveral ways to solve the MSO problem
Several ways to solve the MSO problem J. J. Steil - Bielefeld University - Neuroinformatics Group P.O.-Box 0 0 3, D-3350 Bielefeld - Germany Abstract. The so called MSO-problem, a simple superposition
More informationFAULT - TOLERANT PROCEDURES FOR AIR DATA ELABORATION
25 TH INTERNATIONAL CONGRESS OF THE AERONAUTICAL SCIENCES FAULT - TOLERANT PROCEDURES FOR AIR DATA ELABORATION Alberto Calia, Eugenio Denti, Roberto Galatolo, Francesco Schettini University of Pisa Department
More informationEvolutionary Functional Link Interval Type-2 Fuzzy Neural System for Exchange Rate Prediction
Evolutionary Functional Link Interval Type-2 Fuzzy Neural System for Exchange Rate Prediction 3. Introduction Currency exchange rate is an important element in international finance. It is one of the chaotic,
More informationSRV02-Series Rotary Experiment # 7. Rotary Inverted Pendulum. Student Handout
SRV02-Series Rotary Experiment # 7 Rotary Inverted Pendulum Student Handout SRV02-Series Rotary Experiment # 7 Rotary Inverted Pendulum Student Handout 1. Objectives The objective in this experiment is
More informationAttitude Control of a Bias Momentum Satellite Using Moment of Inertia
I. INTRODUCTION Attitude Control of a Bias Momentum Satellite Using Moment of Inertia HYOCHOONG BANG Korea Advanced Institute of Science and Technology HYUNG DON CHOI Korea Aerospace Research Institute
More informationLongitudinal Flight Control Systems
Longitudinal Flight Control Systems 9 Basic Longitudinal Autopilots (I) Attitude Control System First idea: A Displacement Autopilot Typical block diagram: Vertical e g e δ Elevator δ A/C θ ref Amplifier
More information