Design, Implementation, and Evaluation of a Neural-Network-Based Quadcopter UAV System

In this paper, a quadcopter unmanned aerial vehicle (UAV) system based on neural-network enhanced dynamic inversion control is proposed for multiple real-world application scenarios. A sigma-pi neural network (SPNN) is used as the compensator to reduce the model error and improve the system performance in the presence of the uncertainties of UAV dynamics, payload, and environment. Besides, we present a technical framework for fast and robust implementation of multipurpose UAV systems and develop a testbed for the evaluation of UAV control system by using a high-precision optical motion capture system. Both simulation results and experiment results demonstrate that the SPNN can reduce the inversion errors related to UAV parameter uncertainties as well as tracking errors related to unknown disturbances and unmodeled dynamics. With the help of an online neural network (NN) learning mechanism, the entire system can achieve much higher accuracy in attitude and trajectory control than that achieved by conventional proportional-integral derivative based control systems under varying flight conditions.

[1]  Jinguo Liu,et al.  Fuzzy adaptive PD control for quadrotor helicopter , 2015, 2015 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER).

[2]  Qiong Hu,et al.  The longitudinal attitude control of UAV based on GPFN neural network , 2012 .

[3]  Richard J. Adams,et al.  Robust flight control design using dynamic inversion and structured singular value synthesis , 1993, IEEE Trans. Control. Syst. Technol..

[4]  Gang Tao,et al.  Robust Backstepping Sliding-Mode Control and Observer-Based Fault Estimation for a Quadrotor UAV , 2016, IEEE Transactions on Industrial Electronics.

[5]  G. Campa,et al.  Comparison of Different Neural Augmentations for the Fault Tolerant Control Laws of the WVU YF-22 Model Aircraft , 2006, 2006 14th Mediterranean Conference on Control and Automation.

[6]  Cong Mengyuan,et al.  Controlling quadrotors based on linear quadratic regulator , 2011 .

[7]  G. Shi,et al.  Intelligent control of UAV with neuron-fuzzy approach under hierarchical architecture , 2008, 2008 7th World Congress on Intelligent Control and Automation.

[8]  Yunsheng Fan,et al.  Adaptive RBF neural network controller design for SRM drives , 2016, 2016 35th Chinese Control Conference (CCC).

[9]  Zhihao Cai,et al.  Reconfigurable flight control for UAV with multiple control effectors based on neural network and dynamic inversion , 2011, 2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC).

[10]  Luis Mejías Alvarez,et al.  A neural-network based flight controller for UASs , 2013 .

[11]  Anthony J. Calise,et al.  Nonlinear flight control using neural networks , 1994 .

[12]  Zhang Hua-min,et al.  Neural network based adaptive dynamic inversion flight control system design , 2011, 2011 2nd International Conference on Intelligent Control and Information Processing.

[13]  Byung-Yoon Lee,et al.  Analysis of adaptive control using on-line neural networks for a quadrotor UAV , 2013, 2013 13th International Conference on Control, Automation and Systems (ICCAS 2013).

[14]  Qi Hao,et al.  Adaptive flight control for quadrotor UAVs with dynamic inversion and neural networks , 2016, 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[15]  Anthony J. Calise,et al.  Adaptive nonlinear controller synthesis and flight test evaluation on an unmanned helicopter , 1999, Proceedings of the 1999 IEEE International Conference on Control Applications (Cat. No.99CH36328).

[16]  Roland Siegwart,et al.  Backstepping and Sliding-mode Techniques Applied to an Indoor Micro Quadrotor , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

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

[18]  Qing Lin,et al.  Adaptive Flight Control Design for Quadrotor UAV Based on Dynamic Inversion and Neural Networks , 2013, 2013 Third International Conference on Instrumentation, Measurement, Computer, Communication and Control.

[19]  Anthony J. Calise,et al.  Analysis of Adaptive Neural Networks for Helicopter Flight Control , 1997 .

[20]  Yaonan Wang,et al.  Fuzzy radial basis function neural network PID control system for a quadrotor UAV based on particle swarm optimization , 2015, 2015 IEEE International Conference on Information and Automation.

[21]  Yi Chen,et al.  2DOF manipulator tracking control based on fuzzy CMAC neural network dynamic inversion , 2010, 2010 International Conference on Intelligent Computing and Integrated Systems.

[22]  Frank L. Lewis,et al.  Aircraft Control and Simulation , 1992 .

[23]  Peter Xiaoping Liu,et al.  Robust Control of Four-Rotor Unmanned Aerial Vehicle With Disturbance Uncertainty , 2015, IEEE Transactions on Industrial Electronics.

[24]  Sreenatha Anavatti,et al.  Real-time validation of a dual neural network controller for a low-cost UAV , 2009, 2009 IEEE International Conference on Industrial Technology.

[25]  Liuping Wang,et al.  Automatic tuning of attitude control system for fixed-wing unmanned aerial vehicles , 2016 .

[26]  Kagan Tumer,et al.  Robust neuro-control for a micro quadrotor , 2010, GECCO '10.

[27]  Vijay Kumar,et al.  Quadrotor Kinematics and Dynamics , 2015 .

[28]  Ali Vatankhah Barenji,et al.  An adaptive neuro PID for controlling the altitude of quadcopter robot , 2013, 2013 18th International Conference on Methods & Models in Automation & Robotics (MMAR).