Attitude Control Based on Neural Networks for Micro Aerial Vehicle with Flapping Wings
ZHOU Jian-hua1,2, WANG Shu-xin2, YAN Jing-ping2
1. College of Machanical Engineering, Yangzhou University, Yangzhou 225009, China; 2. Department of Mechanical Engineering, Southeast University, Nanjing 210096, China
周建华, 王姝歆, 颜景平. 基于神经网络的拍翅式微型飞行器姿态控制[J]. 机器人, 2005, 27(4): 306-308,324..
ZHOU Jian-hua, WANG Shu-xin, YAN Jing-ping. Attitude Control Based on Neural Networks for Micro Aerial Vehicle with Flapping Wings. ROBOT, 2005, 27(4): 306-308,324..
Abstract:For attitude control of micro aerial vehicle with flapping wings, a control method based on BP(backpropagation) neural networks and average moments is proposed. At the end of each wingbeat, the neural network controller determines the adjustment value of attack angle according to attitude errors. The micro vehicle obtains desired average moments which control attitude at next wingbeat. The proposed controller is simulated. The results show that the control system is robust.
[1] Deng X, Schenato L, Sastry S. Hovering flight control of a micromechanical flying insect [A]. Proceedings of the IEEE International Conference on Decision and Control[C] . New York, USA: IEEE,2001. 235-240. [2] Dickinson M H, Lehmann F-O, Sane S P. Wing rotation and the aerodynamic basis of insect flight [J]. Science, 1999, 284 (5422):1954-1960. [3] 周建华,颜景平,王姝歆,等.微型仿昆飞行机器人翅运动模型及气动力分析[J].扬州大学学报,2004,7(1):36-39. [4] 黄真.空间机构学[M].北京:机械工业出版社,1991.160-197. [5] Shakernia O, Ma Y, Koo T J, et al. Landing an unmanned air vehicle: vision based motion estimation and nonlinear control[J]. Asian Journal of Control, 1999,1 (3): 128-145. [6] 周建华,王姝歆,颜景平,等.微型仿昆飞行机器人驻飞时姿态控制的研究[J].测控技术,2004,23(6):32-33,36. [7] 徐丽娜.神经网络控制[M].哈尔滨:哈尔滨工业大学出版社,1999.