Deep Convolutional Identifier for Dynamic Modeling and Adaptive Control of Unmanned Helicopter

Helicopters are complex high-order and time-varying nonlinear systems, strongly coupling with aerodynamic forces, engine dynamics, and other phenomena. Therefore, it is a great challenge to investigate system identification for dynamic modeling and adaptive control for helicopters. In this paper, we address the system identification problem as dynamic regression and propose to represent the uncertainties and the hidden states in the system dynamic model with a deep convolutional neural network. Particularly, the parameters of the network are directly learned from the real flight data of aerobatic helicopter. Since the deep convolutional model has a good performance for describing the dynamic behavior of the hidden states and uncertainties in the flight process, the proposed identifier manifests strong robustness and high accuracy, even for untrained aerobatic maneuvers. The effectiveness of the proposed method is verified by various experiments with the real-world flight data from the Stanford Autonomous Helicopter Project. Consequently, an adaptive flight control scheme including a deep convolutional identifier and a backstepping-based controller is presented. The stability of the flight control scheme is rigorously proved by the Lyapunov theory. It reveals that the tracking errors for both the position and attitude of unmanned helicopter asymptotic converge to a small neighborhood of the origin.

[1]  Woonchul Ham,et al.  Sliding mode control for the hovering of helicopter by using quaternion dynamics , 2011, SICE Annual Conference 2011.

[2]  Geoffrey I. Webb,et al.  Dynamic Time Warping Averaging of Time Series Allows Faster and More Accurate Classification , 2014, 2014 IEEE International Conference on Data Mining.

[3]  Shimon Whiteson,et al.  Neuroevolutionary reinforcement learning for generalized helicopter control , 2009, GECCO.

[4]  Eamonn J. Keogh,et al.  Exact indexing of dynamic time warping , 2002, Knowledge and Information Systems.

[5]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[6]  Vladislav Gavrilets,et al.  Autonomous aerobatic maneuvering of miniature helicopters , 2003 .

[7]  Marco,et al.  Modeling of Small-Scale Helicopters with Integrated First-Principles and System-Identification Techniques , 2002 .

[8]  Sun Ning.  Backstepping-based adaptive attitude and height control of a small-scale unmanned helicopter , 2012 .

[9]  Mark B. Tischler,et al.  Frequency-Response Method for Rotorcraft System Identification: Flight Applications to BO 105 Coupled Rotor/Fuselage Dynamics , 1992 .

[10]  Pieter Abbeel,et al.  Deep learning helicopter dynamics models , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Emery N. Brown,et al.  Dynamic Analysis of Neural Encoding by Point Process Adaptive Filtering , 2004, Neural Computation.

[12]  Ho-Chan Kim,et al.  Parameter identification and design of a robust attitude controller using H∞ methodology for the raptor E620 small-scale helicopter , 2012 .

[13]  Raymond W. Prouty,et al.  Helicopter performance, stability, and control , 1986 .

[14]  Zhiqiang Zheng,et al.  Nonlinear system identification of a small-scale unmanned helicopter , 2014 .

[15]  Martin Barczyk.  Nonlinear State Estimation and Modeling of a Helicopter UAV , 2012 .

[16]  Boschitsch,et al.  First-Principles Free-Vortex Wake Analysis for Helicopters and Tiltrotors , 2003 .

[17]  Dennis S. Bernstein,et al.  Globally convergent adaptive tracking of angular velocity and inertia identification for a 3-DOF rigid body , 2006, IEEE Transactions on Control Systems Technology.

[18]  Sarangapani Jagannathan,et al.  Output Feedback Control of a Quadrotor UAV Using Neural Networks , 2010, IEEE Transactions on Neural Networks.

[19]  Maneesh Sahani,et al.  Regularization and nonlinearities for neural language models: when are they needed? , 2013, ArXiv.

[20]  J. Gordon Leishman,et al.  Principles of Helicopter Aerodynamics , 2000 .

[21]  Dennis S. Bernstein,et al.  Adaptive tracking of angular velocity for a planar rigid body with unknown models for inertia and input nonlinearity , 2006, IEEE Transactions on Control Systems Technology.

[22]  Pieter Abbeel,et al.  Autonomous Helicopter Aerobatics through Apprenticeship Learning , 2010, Int. J. Robotics Res..

[23]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[24]  Mario Innocenti,et al.  Helicopter Flight Dynamics: The Theory and Application of Flying Qualities and Simulation Modeling , 1999 .

[25]  C. L. Philip Chen,et al.  Adaptive Position/Attitude Tracking Control of Aerial Robot With Unknown Inertial Matrix Based on a New Robust Neural Identifier , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Bernard Mettler.  Modeling small-scale unmanned rotorcraft for advanced flight control design , 2001 .

[27]  Bernard Mettler,et al.  System identification modeling of a small-scale unmanned rotorcraft for flight control design , 2002 .

[28]  Ali Karimoddini,et al.  Multi-layer flight control synthesis and analysis of a small-scale UAV helicopter , 2010, 2010 IEEE Conference on Robotics, Automation and Mechatronics.

[29]  Marios M. Polycarpou,et al.  A Robust Adaptive Nonlinear Control Design , 1993, 1993 American Control Conference.

[30]  E.N. Sanchez,et al.  Combining fuzzy and PID control for an unmanned helicopter , 2005, NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society.

[31]  J. T. Staley,et al.  Application of modern aluminum alloys to aircraft , 1996 .

[32]  Reihaneh Kardehi Moghaddam,et al.  Adaptive Fuzzy Sliding Mode Control for a Model-Scaled Unmanned Helicopter , 2016 .

[33]  Darren M. Dawson,et al.  Adaptive tracking control of an underactuated aerial vehicle , 2011, Proceedings of the 2011 American Control Conference.

[34]  John T. Wen,et al.  Attitude control without angular velocity measurement: a passivity approach , 1995, Proceedings of 1995 IEEE International Conference on Robotics and Automation.

[35]  Pedro Simplício,et al.  An acceleration measurements-based approach for helicopter nonlinear flight control using Incremental Nonlinear Dynamic Inversion , 2013 .

[36]  Fan Yang,et al.  Nonlinear system modeling and identification of small helicopter based on genetic algorithm , 2013, Int. J. Intell. Comput. Cybern..

[37]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[38]  Ah Chung Tsoi,et al.  Face recognition: a convolutional neural-network approach , 1997, IEEE Trans. Neural Networks.

[39]  Haiyan Lu,et al.  A case study on a hybrid wind speed forecasting method using BP neural network , 2011, Knowl. Based Syst..