Trajectory generation for networked UAVs using online learning for delay compensation

This paper presents a trajectory generation mechanism based on machine learning for a network of unmanned aerial vehicles (UAVs). For delay compensation, we apply an online regression technique to learn a pattern of network-induced effects on UAV maneuvers. Due to online learning, the control system not only adapts to changes to the environment, but also maintains a fixed amount of training data. The proposed algorithm is evaluated on a collaborative trajectory tracking task for two UAVs. Improved tracking is achieved in comparison to a conventional linear compensation algorithm.

[1]  Tielong Shen,et al.  Adaptive feedback control of nonlinear time-delay systems: the LaSalle-Razumikhin-based approach , 2005, IEEE Transactions on Automatic Control.

[2]  Andreas Krause,et al.  Safe controller optimization for quadrotors with Gaussian processes , 2015, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Claire J. Tomlin,et al.  Learning quadrotor dynamics using neural network for flight control , 2016, 2016 IEEE 55th Conference on Decision and Control (CDC).

[4]  Roland Siegwart,et al.  Design and control of an indoor micro quadrotor , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[5]  Shuzhi Sam Ge,et al.  Robust adaptive control of nonlinear systems with unknown time delays , 2004, Proceedings of the 2004 IEEE International Symposium on Intelligent Control, 2004..

[6]  Jaehyun Yoo,et al.  Distributed estimation using online semi-supervised particle filter for mobile sensor networks , 2015 .

[7]  Gert Cauwenberghs,et al.  Incremental and Decremental Support Vector Machine Learning , 2000, NIPS.

[8]  Peter I. Corke,et al.  A robotics toolbox for MATLAB , 1996, IEEE Robotics Autom. Mag..

[9]  Tao Zhang,et al.  The self-tuning networked control system with online delay prediction , 2017 .

[10]  Miroslav Krstic,et al.  Input Delay Compensation for Forward Complete and Strict-Feedforward Nonlinear Systems , 2010, IEEE Transactions on Automatic Control.

[11]  Hui Zhang,et al.  H∞ Step Tracking Control for Networked Discrete-Time Nonlinear Systems With Integral and Predictive Actions , 2013, IEEE Transactions on Industrial Informatics.

[12]  Holger Voos,et al.  Controller design for quadrotor UAVs using reinforcement learning , 2010, 2010 IEEE International Conference on Control Applications.

[13]  H. Jin Kim,et al.  Target Localization in Wireless Sensor Networks Using Online Semi-Supervised Support Vector Regression , 2015, Sensors.

[14]  P. Pepe,et al.  A Lyapunov-Krasovskii methodology for ISS and iISS of time-delay systems , 2006, Syst. Control. Lett..

[15]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[16]  S. Shankar Sastry,et al.  Provably safe and robust learning-based model predictive control , 2011, Autom..