Learning-based Path Tracking Control of a Flapping-wing Micro Air Vehicle

Flapping-wing micro air vehicles (FWMAVs) become promising research platforms due to their advantages such as various maneuverability, and concealment. However, unsteady flow at low Reynolds number around the wings makes their dynamics time-varying and highly non-linear. It makes autonomous flight of FWMAV as a big challenge. In this paper, we suggest a model-based control strategy for FWMAV using learning architecture. For this task, we construct a ground station for logging flight data and control inputs, and train dynamics with a neural network. Then, we apply model predictive control (MPC) to the trained model. We validate our method by hardware experiments.

[1]  D. Mayne.  A Second-order Gradient Method for Determining Optimal Trajectories of Non-linear Discrete-time Systems , 1966 .

[2]  Mao Sun,et al.  Dynamic flight stability of a hovering bumblebee , 2005, Journal of Experimental Biology.

[3]  James Diebel,et al.  Representing Attitude : Euler Angles , Unit Quaternions , and Rotation Vectors , 2006 .

[4]  S. Shankar Sastry,et al.  Flapping flight for biomimetic robotic insects: part I-system modeling , 2006, IEEE Transactions on Robotics.

[5]  Mao Sun,et al.  Dynamic flight stability of hovering insects , 2007 .

[6]  Gordon J. Berman,et al.  Energy-minimizing kinematics in hovering insect flight , 2007, Journal of Fluid Mechanics.

[7]  Wei Shyy,et al.  Aerodynamics of Low Reynolds Number Flyers: Index , 2007 .

[8]  Ronald S. Fearing,et al.  Flight forces and altitude regulation of 12 gram I-Bird , 2010, 2010 3rd IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics.

[9]  Imraan A. Faruque,et al.  Dipteran insect flight dynamics. Part 1 Longitudinal motion about hover. , 2010, Journal of theoretical biology.

[10]  Ronald S. Fearing,et al.  Flight control for target seeking by 13 gram ornithopter , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Ronald S. Fearing,et al.  Cooperative control and modeling for narrow passage traversal with an ornithopter MAV and lightweight ground station , 2013, AAMAS.

[12]  Ronald S. Fearing,et al.  Comparison of ornithopter wind tunnel force measurements with free flight , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Guido C. H. E. de Croon,et al.  Attitude and altitude estimation and control on board a Flapping Wing Micro Air Vehicle , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Ronald S. Fearing,et al.  Coordinated launching of an ornithopter with a hexapedal robot , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Guido C. H. E. de Croon,et al.  Black-box LTI modelling of flapping-wing micro aerial vehicle dynamics , 2015 .

[17]  Seungwan Ryu,et al.  Autonomous flight and vision-based target tracking for a flapping-wing MAV , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Ronald S. Fearing,et al.  Modeling and control of an ornithopter for diving , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[19]  S. F. Armanini,et al.  Time-Varying Model Identification of Flapping-Wing Vehicle Dynamics Using Flight Data , 2016 .

[20]  Sergey Levine,et al.  Neural Network Dynamics Models for Control of Under-actuated Legged Millirobots , 2017, ArXiv.

[21]  Changyin Sun,et al.  Adaptive Neural Network Control of a Flapping Wing Micro Aerial Vehicle With Disturbance Observer , 2017, IEEE Transactions on Cybernetics.

[22]  Sergey Levine,et al.  Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Erik-Jan Van Kampen,et al.  Machine Learning for Flapping Wing Flight Control , 2018 .