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.

Guest Editorial for Special Issue on Autonomous Control of Unmanned Aerial Vehicles

IN recent years,unmanned aerial vehicles(UAVs)have been widely employed in different applications,both military and civilian.Especially,a fast growing civil UAV market is predicted over the next decades.However,most currently developed UAVs depend on simple control strategy.They require exact modeling of the UAVs dynamics and are vulnerable to external disturbance.Therefore,there is great

Deworming of stray dogs and wild canines with praziquantel-laced baits delivered by an unmanned aerial vehicle in areas highly endemic for echinococcosis in China

Background:Canines,the definitive hosts for the parasites causing alveolar(AE)and cystic echinococcosis(CE),are the main source of this infections playing the key role in the transmission.The ten-year mortality rate of AE is extremely high(94%)if the patients are not given sustained treatment.The aim of this field study is to explore the possibility of delivery of praziquantel-laced baits using unmanned aerial vehicles(UAVs)aimed at deworming wild canines in the endemic areas.Methods:UAVs were compared to manual bait delivery in the 1-km^(2)test areas followed by testing of canine faeces using an Echinococcus coproantigen ELISA test in the ensuing year.The outcomes of the two approaches were compared with respect to time of delivery and overall cost.Findings:Compared to manual bait delivery,delivery by UAVs saved up to 67%of the overall cost.Three times more staff was needed for the former approach compared to the latter and,time wise,UAV bait delivery saved 350%compared to manual bait delivery on average.With regard to investment needed,the use of UAVs showed an efficiency 2.5 times better than manual bait delivery.Compared to the area served by UAVs,the average positive rate for the canine faecal samples was more than 38%higher in the area served manually.Conclusion:The technique of bait delivery with praziquantel using UAVs for canine deworming has a strong potential with regard to savings of manpower,time and overall cost in areas highly endemic for echinococcosis.

Real-time trajectory planning for UCAV air-to-surface attack using inverse dynamics optimization method and receding horizon control

This paper presents a computationally efficient real-time trajectory planning framework for typical unmanned combat aerial vehicle （UCAV） performing autonomous air-to-surface （A/S） attack. It combines the benefits of inverse dynamics optimization method and receding horizon optimal control technique. Firstly, the ground attack trajectory planning problem is mathematically formulated as a receding horizon optimal control problem （RHC-OCP）. In particular, an approximate elliptic launch acceptable region （LAR） model is proposed to model the critical weapon delivery constraints. Secondly, a planning algorithm based on inverse dynamics optimization, which has high computational efficiency and good convergence properties, is developed to solve the RHCOCP in real-time. Thirdly, in order to improve robustness and adaptivity in a dynamic and uncer- tain environment, a two-degree-of-freedom （2-DOF） receding horizon control architecture is introduced and a regular real-time update strategy is proposed as well, and the real-time feedback can be achieved and the not-converged situations can be handled. Finally, numerical simulations demon- strate the efficiency of this framework, and the results also show that the presented technique is well suited for real-time implementation in dynamic and uncertain environment.