Print Email Facebook Twitter Neural-adaptive constrained flight control for air ground recovery under terrain obstacles Title Neural-adaptive constrained flight control for air ground recovery under terrain obstacles Author Su, Zikang (Nanjing University of Aeronautics and Astronautics) Wang, X. (TU Delft Transport and Planning) Wang, Honglun (Beihang University) Date 2022 Abstract This article contrives a neural-adaptive constrained controller of the cable towed air-ground recovery system subject to terrain obstacles, unmeasurable cable tensions, trailing vortex, wind gust, and actuator saturation. In air-ground recovery system modeling, the towed vehicle's nominal 6 DOF affine nonlinear dynamics and the cable system's finite links-joints dynamics are formulated. To achieve accurate air-ground recovery under terrain obstacles, an asymmetric barrier Lyapunov function-based flight controller of the towed vehicle is proposed, by transforming the terrain obstacles into time-varying constraints on the vehicle's trajectory. Then, to approximate the towed vehicle's lumped unknown dynamics caused by the unmeasurable cable tensions and airflows, several echo state network (ESN) approximators are established for velocity and attitude subsystems. By using the state approximation errors-based neural weights learning strategy and minimal learning parameter technique, these ESNs possess better transient behaviors and lower online computational burden. Furthermore, the actuator saturation is automatically monitored and released, by incorporating a specially designed auxiliary compensating system into the angular rate control law for compensation. The stability of the closed-loop system is analyzed. Finally, numerical simulations under two air-ground recovery scenarios are performed to demonstrate the performance of the proposed controller. Subject actuator saturationActuatorsAerodynamicsAerospace controlair-ground recoveryAircraftconstrained flight controlneural approximationNonlinear dynamical systemstowed vehicleTrajectoryVehicle dynamics To reference this document use: http://resolver.tudelft.nl/uuid:305177f9-573a-4d3b-83c1-39b49ea06a3a DOI https://doi.org/10.1109/TAES.2021.3101592 ISSN 0018-9251 Source IEEE Transactions on Aerospace and Electronic Systems, 58 (1), 374-390 Part of collection Institutional Repository Document type journal article Rights © 2022 Zikang Su, X. Wang, Honglun Wang Files PDF Neural_adaptive_constrain ... tacles.pdf 2.26 MB Close viewer /islandora/object/uuid:305177f9-573a-4d3b-83c1-39b49ea06a3a/datastream/OBJ/view