Sérgio Ronaldo Barros dos Santos Cairo Lúcio Nascimento Júnior

Slides:



Advertisements
Similar presentations
Solar Sail Attitude Control using a Combination of a Feedforward and a Feedback Controller D. Romagnoli, T. Oehlschlägel.
Advertisements

1 © 2011 The MathWorks, Inc. Designing Control Systems for Wind Turbines Steve Miller Technical Marketing, Physical Modeling MathWorks Root LocusBode Plot.
Nonlinear Control of Quadrotor
 (x) f(x,u) u x f(x,  (x) x. Example: Using feed-forward, what should be canceled?
Outline quad-copter Abstract Quad-Copter Movement Hand movement
2 nd SSS, July 2010, Christina Scholz Performance Analysis of an Attitude Control System for Solar Sails Using Sliding Masses Christina Scholz Daniele.
NONLINEAR BACKSTEPPING CONTROL WITH OBSERVER DESIGN FOR A 4 ROTORS HELICOPTER L. Mederreg, F. Diaz and N. K. M’sirdi LRV Laboratoire de Robotique de Versailles,
Learning Parameterized Maneuvers for Autonomous Helicopter Flight Jie Tang, Arjun Singh, Nimbus Goehausen, Pieter Abbeel UC Berkeley.
DARPA Mobile Autonomous Robot SoftwareMay Adaptive Intelligent Mobile Robotics William D. Smart, Presenter Leslie Pack Kaelbling, PI Artificial.
ATMOSPHERIC REENTRY TRAJECTORY MODELING AND SIMULATION: APPLICATION TO REUSABLE LAUNCH VEHICLE MISSION (Progress Seminar Presentation - 2) K. Sivan (Roll.
Robust and Efficient Control of an Induction Machine for an Electric Vehicle Arbin Ebrahim and Dr. Gregory Murphy University of Alabama.
Development of Guidance and Control System for Parafoil-Payload System VVR Subbarao, Sc ‘C’ Flight Mechanics & Control Engineering ADE.
Integrating a Short Range Laser Probe with a 6-DOF Vertical Robot Arm and a Rotary Table Theodor Borangiu Anamaria Dogar
Design of Attitude and Path Tracking Controllers for Quad-Rotor Robots using Reinforcement Learning Sérgio Ronaldo Barros dos Santos Cairo Lúcio Nascimento.
Active Calibration of Cameras: Theory and Implementation Anup Basu Sung Huh CPSC 643 Individual Presentation II March 4 th,
280 SYSTEM IDENTIFICATION The System Identification Problem is to estimate a model of a system based on input-output data. Basic Configuration continuous.
Vehicle dynamics simulation using bond graphs
February 24, Final Presentation AAE Final Presentation Backstepping Based Flight Control Asif Hossain.
Introduction What is this ? What is this ? This project is a part of a scientific research in machine learning, whose objective is to develop a system,
CL A Coordinated Flight of Uninhabited Air Vehicles Olivier Laplace Princeton University FAA/NASA Joint University Program Quarterly Review - April, 2001.
Computer graphics & visualization Rigid Body Simulation.
Balancing (平衡) 南台科技大學 機械工程系 王永鵬.
Definition of an Industrial Robot
Sérgio Ronaldo Barros dos Santos, Cairo Lúcio Nascimento Júnior,
MAE 242 Dynamics – Section I Dr. Kostas Sierros.
Sérgio Ronaldo Barros dos Santos (ITA-Brazil) Sidney Nascimento Givigi Júnior (RMC-Canada) Cairo Lúcio Nascimento Júnior (ITA-Brazil) Autonomous Construction.
IPPW-9, Toulouse 2012A. Sánchez Hernández, UPC D YNAMICAL STUDY OF THE AEROBRAKING TECHNIQUE IN THE ATMOSPHERE OF M ARS Alberto Sánchez Hernández ETSEIAT.
Adapting Simulated Behaviors For New Characters Jessica K. Hodgins and Nancy S. Pollard presentation by Barış Aksan.
1  (x) f(x,u) u x f(x,  (x) x Example: Using feed-forward, what should be canceled?
UC SANTA CRUZ, AUTONOMOUS SYSTEMS LAB, An Improved Line-of- Sight Guidance Law for UAVs R. Curry, M. Lizarraga, B. Mairs, and G.H. Elkaim University of.
Sérgio Ronaldo Barros dos Santos (ITA-Brazil)
UC SANTA CRUZ, AUTONOMOUS SYSTEMS LAB, An Improved Line-of- Sight Guidance Law for UAVs R. Curry, M. Lizarraga, B. Mairs, and G.H. Elkaim University of.
Modeling and Simulation of Nickel-Cadmium Batteries during Discharge Giuliano S. Sperandio Cairo L. Nascimento Jr. Geraldo J. Adabo Prof. Master Program.
UC SANTA CRUZ, AUTONOMOUS SYSTEMS LAB, An Improved Line-of- Sight Guidance Law for UAVs R. Curry, M. Lizarraga, B. Mairs, and G.H. Elkaim University of.
COBXXXX EXPERIMENTAL FRAMEWORK FOR EVALUATION OF GUIDANCE AND CONTROL ALGORITHMS FOR UAVS Sérgio Ronaldo Barros dos Santos,
Plane Motion of Rigid Bodies: Forces and Accelerations
Model Reference Adaptive Control (MRAC). MRAS The Model-Reference Adaptive system (MRAS) was originally proposed to solve a problem in which the performance.
Modelling and Open Loop Simulation of Reentry Trajectory for RLV Missions Ashok Joshi and K. Sivan Department of Aerospace Engineering Indian Institute.
Advanced Control of Marine Power System
ADCS Review – Attitude Determination Prof. Der-Ming Ma, Ph.D. Dept. of Aerospace Engineering Tamkang University.
Model of Reluctance Synchronous Motor
City College of New York 1 John (Jizhong) Xiao Department of Electrical Engineering City College of New York Mobile Robot Control G3300:
Quadcopters A CEV Talk. Agenda Flight PreliminariesWhy Quadcopters The Quadcopter SystemStability: The NotionSensors and FusionControl AlgorithmsThe Way.
Two-Dimensional Rotational Dynamics 8.01 W09D2 Young and Freedman: 1.10 (Vector Product), , 10.4, ;
By: Stuti Vyas( ) Drashti Sheth( ) Jay Vala( ) Internal Guide Mr. J. N. Patel.
Fuzzy Controller for Spacecraft Attitude Control CHIN-HSING CHENG SHENG-LI SHU Dept. of Electrical Engineering Feng-Chia University IEEE TRANSACTIONS ON.
Minor Project on Vertical Take-off Landing System SUBMITTED BY:- SHUBHAM SHARMA ( ) ABHISHEK ARORA ( ) VIBHANSHU JAIN ( )
Learning of Coordination of a Quad-Rotors Team for the Construction of Multiple Structures. Sérgio Ronaldo Barros dos Santos. Supervisor: Cairo Lúcio Nascimento.
Beard & McLain, “Small Unmanned Aircraft,” Princeton University Press, 2012, Chapter 2: Slide 1 Chapter 2 Coordinate Frames.
Beard & McLain, “Small Unmanned Aircraft,” Princeton University Press, 2012, Chapter 4: Slide 1 Chapter 4 Forces and Moments.
Robotics Chapter 3 – Forward Kinematics
ECE 383 / ME 442 Fall 2015 Kris Hauser
From: Influence of Road Camber on Motorcycle Stability
Generation and Testing of Gait Patterns for Walking Machines Using Multi-Objective Optimization and Learning Automata Jeeves Lopes dos Santos Cairo L.
Classical Design of Wind Turbine Controllers
Forces on an Aircraft Four forces on an aircraft in flight:
Four Forces of Flight Lift Weight Thrust Drag
CHAPTER 4: Systems of Particles
Arbin Ebrahim and Dr. Gregory Murphy University of Alabama
Zaid H. Rashid Supervisor Dr. Hassan M. Alwan
Dynamics and Control of Hexapod Systems
Dynamic Controllers for Wind Turbines
QUANSER Flight Control Systems Design 2DOF Helicopter 3DOF Helicopter 3DOF Hover 3DOF Gyroscope Quanser Education Solutions Powered by.
LESSON ld05 Rocket Stability
Angular Momentum; General Rotation
Rigid Body Dynamics ~ f = p h g
Synthesis of Motion from Simple Animations
VIRTUAL ENVIRONMENT.
Physics 319 Classical Mechanics
Simulations and experiments of robot swimming stability.
Presentation transcript:

Design of Attitude and Path Tracking Controllers for Quad-Rotor Robots using Reinforcement Learning Sérgio Ronaldo Barros dos Santos Cairo Lúcio Nascimento Júnior Instituto Tecnológico de Aeronáutica (ITA) Brazil Sidney Nascimento Givigi Júnior Royal Military College of Canada (RMCC) Canada

Introduction Quad-rotor robots have attracted the attention of many researchers in the past few years. Examples of applications: Military applications: surveillance, border patrolling, crowd control. Civilian applications: rescue missions during floods and earthquakes, monitoring pipelines and electric transmission liones.

Introduction A quad-rotor consists of four independent propellers attached to the corners of a cross-shaped frame, turning in opposite directions.

Quad-Rotor Dynamics All rotational and translational movements of a quad- rotor can be achieved by adjusting its rotor speeds.

Introduction Quad-rotor robots are affected by a number of physical effects such as: Aerodynamic effects, Gravity effect, Ground effect, Gyroscopic effect, Friction. Due to these nonlinear effects, it is difficult to design good controllers for a quad-rotor.

Introduction Typically quad-rotor applications use controllers derived using linearized models. These controllers exhibit poor performance for fast maneuvers or in the presence of disturbances such as wind and the ground effect. In order to perform path tracking in the presence of nonlinear disturbances, a machine learning technique (RL-LA) will be applied.

Objectives To present a solution for testing and evaluation of attitude stabilization and path tracking controllers for quad-rotors. To use a Reinforcement Learning algorithm (Learning Automata) to adjust the controllers parameters using a simulation environment that includes wind and ground effects.

Quad-Rotor Dynamics An inertial frame and a body fixed frame whose origin is in the center of mass of the quad-rotor are used.

Quad-Rotor Dynamics The dynamic model is derived under the following assumptions. the vehicle frame is rigid and symmetrical, the body fixed frame is located at the vehicle center of mass, the propellers are also rigid.

Quad-Rotor Dynamics The dynamic model of the quad-rotor can de derived using Newton-Euler formalism.

Robot Controllers The control architecture for the robot involves two loops: inner and outer. The roll, pitch, and yaw angles are represented by Φ, θ and ψ, respectively.

Robot Controllers Three nonlinear control strategies are used: - Nonlinear PID Control, - Backstepping technique - Sliding Model Control.

Robot Controllers The parameters of the 6 controllers are tuned using the RL algorithm. Technique Controllers Path Tracking Attitude Height x-position y-position Pitch Roll Yaw PID kp,ki,kd kp,ki, ,kd Backstepping α12, α11 α10, α9 α4, α3 α1, α2 α5, α6 α7, α8 Sliding Mode k5, λ5 k4, λ4 k2, λ2 k1, λ1 k3, λ3 k6, λ6

Simulation Environment A simulation setup is proposed to train and evaluate the quad-rotor controller under more realistic conditions.

Simulation Environment

Simulation Environment

Simulation Environment Using the Plane-Marker, a X-Plane model of the X3D-BL quad-rotor (manufactured by Ascending Technologies) was created.

Simulation Environment The responses of the X-Plane and SIMULINK models are compared for a hovering maneuver.

Reinforcement Learning Learning Automata (LA) is an alternative approach that can be used to adjust the parameters of the controllers.

Reinforcement Learning Steps of the learning process: Initialize the probability and parameters vectors of each controller; Select the parameters for each controller using its associated probability vector; Execute the desired task, obtain its response and use a cost function to measure its performance. Compute the reinforcement signal; Adjust the probability vectors; Check the probability vectors for convergence, otherwise return to step 2.

Reinforcement Learning Supervisory level: LA adjusts the parameters of the attitude and path tracking controllers.

Reinforcement Learning Learning the parameters of the controllers was executed using the X-Plane model in 3 stages with increasing levels of difficulty : without the presence of any external disturbances, considering only the presence of wind, considering the wind and ground effects.

Reinforcement Learning

Reinforcement Learning

Reinforcement Learning A cost function evaluates the response of each controller (i) for the selected task at the end of each trial (k) :

Reinforcement Learning The reinforcement signal is computed for each controller (i) at the end of each trial (k):

Reinforcement Learning The element of the probability vector associated with the selected controller parameter is adjusted: The probability vector is then normalized.

Reinforcement Learning Learning the desired trajectory using the PID controller during the first stage.

Results The nonlinear PID controllers results obtained during simulation. The trajectory is formed by the points (0,0) - (0,10) - (10,10) - (10,0) meters.

Results The quad-rotor robot during the execution of a pre-defined trajectory visualized in the X-Plane.

Results The backstepping controller results in the presence of wind and ground effects

Results The path tracking of quad-rotor obtained by the backstepping controllers in the presence of wind and ground effects, visualized in the X-Plane.

Results The sliding mode controller response using the in presence of wind and ground effects.

Results The quad-rotor trajectory obtained by the sliding controllers in presence of wind and ground effects, visualized in the X-Plane.

Results Evaluation of the controllers tracking of desired path after the learning process.

Conclusions The proposed method (Learning Automata) allows one to tune the parameters of different controllers for a quad-rotor aircraft, considering external disturbances such as wind and ground effects. It was shown that the proposed simulation framework can be useful to investigate the application of learning algorithms to adjust the control laws of quad-rotors for different flight maneuvers.

Future Research Evaluate the controllers (obtained using LA, the simulated model, the simulation environment) using real quad-rotors. On-line learning: useful to correct inaccuracies of the simulated (model + environment).

Future Research Comparison to other RL methods (e.g., Q- Learning) and other search procedures (e.g., genetic algorithms). Limitation of learning: generalization to other tasks Problem: selection of tasks to be executed during training (adaptive control: choice of excitation signal).

Thank You !