Neural Network Based Feedback Linearization Control of an Unmanned Aerial Vehicle

This paper presents a flight control design for an unmanned aerial vehicle （UAV） using a nonlinear autoregressive moving average （NARMA-L2） neural network based feedback linearization and output redefinition technique. The UAV investigated is non- minimum phase. The output redefinition technique is used in such a way that the resulting system to be inverted is a minimum phase system. The NARMA-L2 neural network is trained off-line for forward dynamics of the UAV model with redefined output and is then inverted to force the real output to approximately track a command input. Simulation results show that the proposed approaches have good performance.

Developing Dijik-Primbert Algorithm for Finding Unpredictable Paths over Time-Varying Networks

Cooperation among multiple unmanned vehicles is an intensely challenging topic from a theoretical and practical standpoint, with far reaching indications in scientific and commercial mission scenarios. The difficulty of time coordination for a rapid of multirotor UAVs includes predefined spatial paths according to mission necessities. With the solution proposed, cooperative control is accomplished in the presence of time-varying communication networks, as well as stringent temporal constraints, such as concurrent arrival at the desired final locations. The proposed explanation solves the time-coordination problem under the acceptance that the trajectory-genera- tion and the path-following algorithms meeting convinced cohesion conditions are given. Communication is processed in unpredictable paths by the use of path following and directed communication graph. Dijik-Primbert algorithm for finding the shortest collision free paths is used to avoid and detect collision/congestion in unpredictable paths. Without collision detection, it doesn’t seem agreeable to have collision avoidance because there wouldn’t be everything to avoid. Dijikloyd algorithm is used for finding shortest paths in a weighted directed graph with positive and negative edges. Primloyd algorithm is used for finding shortest paths in a weighted undirected graph for conquering the complexity in matrix coding. In case of conges- tion or collision then the whole network is learned about it to all the communica- tors. Hence, communication is taken place in an unpredictable path in a secured manner.

Vector Field Based Sliding Mode Control of Curved Path Following for Miniature Unmanned Aerial Vehicles in Winds

In this paper, a curved path following control algorithm for miniature unmanned aerial vehicles（UAVs） in winds with constant speed and altitude is developed. Different to the widely considered line or orbit following, the curved path to be followed is defined in terms of the arc-length parameter, which can be straight lines, orbits, B-splines or any other curves provided that they are smooth. The proposed path following control algorithm, named by VF-SMC, is combining the vector field（VF） strategy with the sliding mode control（SMC） method. It is proven that the designed algorithm guarantees the tracking errors to be a bounded ball in the presence of winds, with the aid of the Lyapunov method and the BIBO stability. The algorithm is validated both in Matlab-based simulations and high-fidelity semi-physical simulations. In Matlab-based simulations, the proposed algorithm is verified for straight lines, orbits and B-splines to show its wide usage in different curves.The high-fidelity semi-physical simulation system is composed of actual autopilot controller, ground station and X-Plane flight simulator in-loop. In semi-physical simulations, the proposed algorithm is verified for B-spline path following under various gain parameters and wind conditions thoroughly.All experiments show the accuracy in curved path following and the excellent robustness to wind disturbances of the proposed algorithm.