Effects of System Uncertainty on Adaptive-Critic Flight Control Silvia Ferrari Advisor: Prof. Robert F. Stengel Princeton University FAA/NASA Joint University.

Slides:

Advertisements

Similar presentations

Benoit Pigneur and Kartik Ariyur School of Mechanical Engineering Purdue University June 2013 Inexpensive Sensing For Full State Estimation of Spacecraft.

Advertisements

Neural Network Control of a Hypersonic Inlet Joint University Program Meeting April 05, 2001 Nilesh V. Kulkarni Advisors Prof. Minh Q. Phan Dartmouth College.

M I T I n t e r n a t i o n a l C e n t e r f o r A i r T r a n s p o r t a t i o n Influence of Structure on Complexity Management Strategies of Air Traffic.

Crown Princess Vessel Dynamics. Overview Ship dynamics under INS 2 nd officer’s manual inputs Two opposing heeling responses Lag between wheel input and.

THE PHOENIX PROJECT Coordinated Flight of Multiple Unmanned Vehicles Michael P. Anthony Lab for Control and Automation Princeton University Princeton,

Development of a Closed-Loop Testing Method for a Next-Generation Terminal Area Automation System JUP Quarterly Review April 4, 2002 John Robinson Doug.

Development of Guidance and Control System for Parafoil-Payload System VVR Subbarao, Sc ‘C’ Flight Mechanics & Control Engineering ADE.

Design of Attitude and Path Tracking Controllers for Quad-Rotor Robots using Reinforcement Learning Sérgio Ronaldo Barros dos Santos Cairo Lúcio Nascimento.

Training an Adaptive Critic Flight Controller

Feb 2005 P. 1 Adaptive Control of Robotic Landers: Simulation Requirements Nilesh Kulkarni Perot Systems, Inc., Adaptive Control & Evolvable Systems Group.

February 24, Final Presentation AAE Final Presentation Backstepping Based Flight Control Asif Hossain.

Empirical Virtual Sliding Target Guidance law Presented by: Jonathan Hexner Itay Kroul Supervisor: Dr. Mark Moulin.

Arizona State University DMML Kernel Methods – Gaussian Processes Presented by Shankar Bhargav.

August, School of Aeronautics & Astronautics Engineering Optical Navigation Systems Takayuki Hoshizaki Prof. Dominick Andrisani.

Autonomous Robotics Team Autonomous Robotics Lab: Cooperative Control of a Three-Robot Formation Texas A&M University, College Station, TX Fall Presentations.

Our acceleration prediction model Predict accelerations: f : learned from data. Obtain velocity, angular rates, position and orientation from numerical.

CH 1 Introduction Prof. Ming-Shaung Ju Dept. of Mechanical Engineering NCKU.

Aircraft Response to Control Input Data Collection System Presenter: Curtis Cutright Advisor: Dr. Michael Braasch Project Sponsor: JUP.

CL A Coordinated Flight of Uninhabited Air Vehicles Olivier Laplace Princeton University FAA/NASA Joint University Program Quarterly Review - April, 2001.

Silvia Ferrari Princeton University

Performance Optimization of the Magneto-hydrodynamic Generator at the Scramjet Inlet Nilesh V. Kulkarni Advisors: Prof. Minh Q. Phan Dartmouth College.

Adaptive Signal Processing Class Project Adaptive Interacting Multiple Model Technique for Tracking Maneuvering Targets Viji Paul, Sahay Shishir Brijendra,

IPPW- 9 Royal Observatory of Belgium 20 June Von Karman Institute for Fluid Dynamics Obtaining atmospheric profiles during Mars entry Bart Van Hove.

A Statistical Inverse Analysis For Model Calibration TFSA09, February 5, 2009.

West Virginia University

A FUZZY LOGIC BASED MULTIPLE REFERENCE MODEL ADAPTIVE CONTROL (MRMAC) By Sukumar Kamalasadan, Adel A Ghandakly Khalid S Al-Olimat Dept. of Electrical Eng.

Introduction to estimation theory Seoul Nat’l Univ.

1 S ystems Analysis Laboratory Helsinki University of Technology Kai Virtanen, Tuomas Raivio, and Raimo P. Hämäläinen Systems Analysis Laboratory (SAL)

Flight Simulation: A Case Study in an Architecture for Integrability.

Aircraft Characterization in Icing Using Flight Test Data Ed Whalen University of Illinois Urbana Champaign 42 nd Annual Aerospace Sciences Conference.

Results of NASA/DARPA Automatic Probe and Drogue Refueling Flight Test Keith Schweikhard NASA Dryden Flight Research Center

Adaptive Critic Design for Aircraft Control Silvia Ferrari Advisor: Prof. Robert F. Stengel Princeton University FAA/NASA Joint University Program on Air.

A Framework for Distributed Model Predictive Control

SIMULATION MODELLING OF THE RAILWAY VEHICLE GUIDANCE MECHANISM Priya Parthasarathy Supervisors- Dr.Christopher Ward Dr.Roger Dixon UKACC PhD Presentation.

Optimal Nonlinear Neural Network Controllers for Aircraft Joint University Program Meeting October 10, 2001 Nilesh V. Kulkarni Advisors Prof. Minh Q. Phan.

Neural Network Based Online Optimal Control of Unknown MIMO Nonaffine Systems with Application to HCCI Engines OBJECTIVES  Develop an optimal control.

1 Adaptive, Optimal and Reconfigurable Nonlinear Control Design for Futuristic Flight Vehicles Radhakant Padhi Assistant Professor Dept. of Aerospace Engineering.

Optimal Feedback Control of the Magneto-hydrodynamic Generator for a Hypersonic Vehicle Nilesh V. Kulkarni Advisors: Prof. Minh Q. Phan Dartmouth College.

Assessment of Alternate Methodologies for Establishing Equivalent Satisfaction of the Ec Criterion for Launch Licensing Terry Hardy AST-300/Systems Engineering.

Time-Varying Angular Rate Sensing for a MEMS Z-Axis Gyroscope Mohammad Salah †, Michael McIntyre †, Darren Dawson †, and John Wagner ‡ Mohammad Salah †,

Research Heaven, West Virginia Verification and Validation of Adaptive Systems Bojan Cukic, Eddie Fuller, Marcello Napolitano, Harshinder Singh, Tim Menzies,

Introduction to Control / Performance Flight.

Smart Icing Systems Review, June 19-20, Aircraft Autopilot Studies Petros Voulgaris Vikrant Sharma University of Illinois.

Accurate Robot Positioning using Corrective Learning Ram Subramanian ECE 539 Course Project Fall 2003.

Smart Icing System Review, September 30 – October 1, 2002 Autopilot Analysis and EP Scheme for the Twin Otter under Iced Conditions. Vikrant Sharma University.

CL A UAV Control and Simulation Princeton University FAA/NASA Joint University Program Quarterly Review - October, 2000.

Hybrid Systems Controller Synthesis Examples EE291E Tomlin/Sastry.

Stochastic Optimal Control of Unknown Linear Networked Control System in the Presence of Random Delays and Packet Losses OBJECTIVES Develop a Q-learning.

7/6/99 MITE1 Fully Parallel Learning Neural Network Chip for Real-time Control Students: (Dr. Jin Liu), Borte Terlemez Advisor: Dr. Martin Brooke.

LRV: Laboratoire de Robotique de Versailles VRIM: Vehicle Road Interaction Modelling for Estimation of Contact Forces N. K. M'SIRDI¹, A. RABHI¹, N. ZBIRI¹.

A Dissertation Proposal Presentation By Sukumar Kamalasadan

Reinforcement Learning for Intelligent Control Presented at Chinese Youth Automation Conference National Academy of Science, Beijing, 8/22/05 George G.

Melak Zebenay > EPOS- A Robotics-Based Hardware in-the-Loop Simulator for Simulating Satellite RvD Operations >Aug 30, 2010 Slide 1 Control Strategy of.

Adaptive Optimal Control of Nonlinear Parametric Strict Feedback Systems with application to Helicopter Attitude Control OBJECTIVES  Optimal adaptive.

1 Lu LIU and Jie HUANG Department of Mechanics & Automation Engineering The Chinese University of Hong Kong 9 December, Systems Workshop on Autonomous.

Towards Adaptive Optimal Control of the Scramjet Inlet Nilesh V. Kulkarni Advisors: Prof. Minh Q. Phan Dartmouth College Prof. Robert F. Stengel Princeton.

Silvia Ferrari and Mark Jensenius Department of Mechanical Engineering Duke University Crystal City, VA, September 28, 2005 Robust and.

© Crown copyright Met Office Wind and turbulence measurements on the BAe146 Phil Brown, OBR Conference, Dec 2012.

10/31/ Simulation of Tightly Coupled INS/GPS Navigator Ade Mulyana, Takayuki Hoshizaki October 31, 2001 Purdue University.

Beard & McLain, “Small Unmanned Aircraft,” Princeton University Press, 2012, Chapter 4: Slide 1 Chapter 4 Forces and Moments.

Terrain Reconstruction Method Based on Weighted Robust Linear Estimation Theory for Small Body Exploration Zhengshi Yu, Pingyuan Cui, and Shengying Zhu.

FBW – Introduction The FBW architecture was developed in 1970’s

Sérgio Ronaldo Barros dos Santos Cairo Lúcio Nascimento Júnior

2. Industry 4.0: novel sensors, control algorithms, and servo-presses

Accurate Robot Positioning using Corrective Learning

Lithography Diagnostics Based on Empirical Modeling

Realizing Closed-loop, Online Tuning and Control for Configurable-Cache Embedded Systems: Progress and Challenges Islam S. Badreldin*, Ann Gordon-Ross*,

Physics-guided machine learning for milling stability:

Motion Cueing Standards for Commercial Flight Simulation

Presentation transcript:

Effects of System Uncertainty on Adaptive-Critic Flight Control Silvia Ferrari Advisor: Prof. Robert F. Stengel Princeton University FAA/NASA Joint University Program on Air Transportation, Ohio University, Athens, OH June 13-14, 2002

Introduction Stringent operational requirements introduce Complexity Nonlinearity Uncertainty Classical/neural synthesis of control systems A-priori knowledge Adaptive neural networks Action network takes immediate control action Critic network estimates projected cost Dual heuristic programming adaptive critic architecture:

Motivation Full envelope control Multiphase learning Initialization: match linear controllers exactly off-line On-line learning: full-scale simulations, testing, or operation On-line learning improves performance w.r.t. linear controllers: Differences between actual and assumed models Nonlinear effects not captured in linearizations Potential applications: Incorporate pilot's knowledge into controller a priori Uninhabited air vehicles control Aerobatic flight control

Table of Contents Adaptive-critic design approach Initialization phase On-line learning phase Adaptive controller final results Large-angle maneuvers Parameter variations Control failures Summary and conclusions

Full Envelope Control! Modeling On-line Training Design Approach Initialization Linear Control Linearizations

Linear Control Design Linearizations: Altitude (m) Velocity (m/s) Linear control design: Longitudinal Lateral-directional Flight envelope and design points: (  =  =  = 0) k  ( )

Proportional-Integral Linear Controller yc(t)yc(t) x(t)x(t) ys(t)ys(t) CICI CFCF CBCB HuHu HxHx u(t)u(t) LINEARIZED AIRCRAFT (t)(t) Closed-loop stability:

CBCB P CICI C F, f[] = 0 : Algebraic Initialization, Proportional-Integral Neural Network Controller yc(t)yc(t) x(t)x(t) u(t)u(t) uc(t)uc(t) + - uB(t)uB(t) uI(t)uI(t) xc(t)xc(t) ys(t)ys(t) e(t)e(t) a(t)a(t) NN F SVG CSG (t)(t) : On-line Training. NN I NN C NN B

Aircraft Response Comparison During a Large-Bank Turn Velocity (m/s) Climb Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Time (sec) Aircraft Response, (H 0, V 0 ) = (7 Km, 160 m/s) Adaptive Critic Neural Control: Command Input: Initialized Neural Control:

Control History and Aircraft Trajectory Comparison During a Large-Bank Turn Adaptive Critic Neural Control Initialized Neural Control Time (sec)  T (%) Control History, (H 0, V 0 ) = (7 Km, 160 m/s)  S (deg)  A (deg)  R (deg) Trajectory Altitude (m) North (m) East (m)

Effect of Parameter Variations on Initialized Neural Control, at a Design Point Velocity (m/s) Clim b Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Time (sec) Aircraft Response, (H 0, V 0 ) = (11 Km, 200 m/s) Perfect Aircraft Modeling: Parameter Variations: Command Input: Parameter Variations: C m q, C m r : 50%  C m  : 20%  C n  : 30% 

Velocity (m/s) Climb Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Time (sec) Aircraft Response, (H 0, V 0 ) = (11 Km, 200 m/s) Aircraft Response Comparison in the Presence of Parameter Variations Initialized Control with Parameter ariations: Command Input: Initialized Control with Perfect Modeling: Adaptive Critic Neural Control (2 nd adaptation):

Adaptive Critic and Initialized Neural Control History Comparison in the Presence of Parameter Variations Time (sec) Velocity (m/s) Climb Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Initialized Neural Control: Adaptive Critic Neural Control (2 nd adaptation): Control History, (H 0, V 0 ) = (11 Km, 95 m/s)

Initialized Neural Controller Performance in the Presence of Control Failures Time (sec) Aircraft Response, (H 0, V 0 ) = (3 Km, 100 m/s) Initialized Neural Control Command Input Control History Time (sec)  T (%)  S (deg)  A (deg)  R (deg) Control Failures:  T = 0, 0  t  15 sec  S = 0, 5  t  10 sec  R = 0, 5  t  10 sec  R = –34 o, t  5 or t  10 sec V (m/s)  (deg)  (deg)  (deg)  (deg)

Aircraft Response Comparison in the Presence of Control Failures Velocity (m/s) Climb Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Time (sec) Aircraft Response after t = 10 sec, (H 0, V 0 ) = (3 Km, 100 m/s) Adaptive Critic Neural Control: Command Input: Initialized Neural Control: Yaw Angle (deg)

Adaptive Critic Neural Control During a Previously-Encountered Maneuver Velocity (m/s) Climb Angle (deg) Roll Angle (deg) Sideslip Angle (deg) Time (sec) Aircraft Response, (H 0, V 0 ) = (3 Km, 100 m/s) Adaptive Critic Neural Control (2 nd adaptation): Command Input: Adaptive Critic Neural Control (1 st adaptation):

Summary and Conclusions Learning control system:  Improves global performance  Preserves prior knowledge  Suspends and resumes adaptation, as appropriate Achievements:  Systematic approach for designing adaptive control systems  Framework for investigating neural approximation properties  Innovative (off-line and on-line) training techniques Other Potential Applications for Adaptive Neural Control: Air-traffic management, reconfiguring hardware (raw chips), process control, criminal profiling, image processing,...

THANK YOU! JUP