Adaptive Trajectory Tracking Algorithm of a Quadrotor with Sliding Mode Control and Multilayer Neural Network

Abstract

To improve the trajectory tracking accuracy, the anti-jamming performance, and the environment adaptability of a quadrotor, the paper proposes a new adaptive trajectory tracking algorithm with multilayer neural network and sliding mode control method. The major difference between other related approaches is that the paper uses the multilayer neural network in the system and the neural network is online computing in the whole process. Firstly, the paper establishes the quadrotor dynamic model and introduces the conception of Sigma-Pi neural network. Then, the paper adds the neural network to the attitude and trajectory tracking control loop. Moreover, the paper designs the adaptive neural network control law. At last, to illustrate the stability of the adaptive control law, the paper gives the Lyapunov stability analysis. Finally, to demonstrate the effectiveness of the method, the paper gives different types of simulation. Comparing with different cases, when increasing the layer of the neural network, the trajectory tracking performance becomes better. In addition, introducing multilayer neural network into the system could improve the anti-interference ability of the system and has a high-precision in tracking the desire trajectory.

Control System for Quadcopter UAV based SMC-RBFNN with External Disturbance

“…1 illustrates the quadcopter's physical structure. The frame body coordinate system (B) and the inertial coordinate system on the earth I are the two coordinate systems used to describe the movement of the quadcopter, as shown in the picture [18,19].…”

“…While the rotating motion on the X, Y, and Z axes that produces an angular position is denoted by ϕ(roll), θ( pitch ), and ψ( yaw )., the translational motion on the X, Y, and Z axes that produces a linear position for a quadcopter is represented by x, y, and z. The quadcopter dynamics equation is written in equations ( 1) -(6) as follows [18][19][20]:…”

“…The RBFNN's architecture is shown in Fig. The 𝑄 ̂ Quadcopter position control equation ( 13) -(15) becomes equation ( 17 𝑈 𝑥 = 𝑚 (𝑄 ̂1 − 𝜏 1 𝑠 1 − 𝜉 1 𝑠𝑖𝑔𝑛(𝑠 1 )) (17) 𝑈 𝑦 = 𝑚 (𝑄 ̂2 − 𝜏 2 𝑠 2 − 𝜉 2 𝑠𝑖𝑔𝑛(𝑠 2 )) (18) 𝑈 𝑍 = 𝑚 (𝑄 ̂3 − 𝜏 3 𝑠 3 − 𝜉 3 𝑠𝑖𝑔𝑛(𝑠 3 )) (19) The following mathematical equations ( 17) -( 19) can be used to determine the appropriate roll and pitch angles based on the position control equations ( 20 Where 𝜙 𝑑 , 𝜃 𝑑 , 𝜓 𝑑 are the intended roll, pitch, and yaw angles are obtained from the desired trajectory.…”