A Composite Adaptive Fault-Tolerant Attitude Control for a Quadrotor UAV with Multiple Uncertainties

In this paper,a composite adaptive fault-tolerant control strategy is proposed for a quadrotor unmanned aerial vehicle(UAV)to simultaneously compensate actuator faults,model uncertainties and external disturbances.By assuming knowledge of the bounds on external disturbances,a baseline sliding mode control is first designed to achieve the desired system tracking performance and retain insensitive to disturbances.Then,regarding actuator faults and model uncertainties of the quadrotor UAV,neural adaptive control schemes are constructed and incorporated into the baseline sliding mode control to deal with them.Moreover,in terms of unknown external disturbances,a disturbance observer is designed and synthesized with the control law to further improve the robustness of the proposed control strategy.Finally,a series of comparative simulation tests are conducted to validate the effectiveness of the proposed control strategy where a quadrotor UAV is subject to inertial moment variations and different level of actuator faults.The capabilities and advantages of the proposed control strategy are confirmed and verified by simulation results.

Training Generative Adversarial Networks with Adaptive Composite Gradient

The wide applications of Generative adversarial networks benefit from the successful training methods,guaranteeing that an object function converges to the local minimum.Nevertheless,designing an efficient and competitive training method is still a challenging task due to the cyclic behaviors of some gradient-based ways and the expensive computational cost of acquiring the Hessian matrix.To address this problem,we proposed the Adaptive Composite Gradients(ACG)method,linearly convergent in bilinear games under suitable settings.Theory analysis and toy-function experiments both suggest that our approach alleviates the cyclic behaviors and converges faster than recently proposed SOTA algorithms.The convergence speed of the ACG is improved by 33%than other methods.Our ACG method is a novel Semi-Gradient-Free algorithm that can reduce the computational cost of gradient and Hessian by utilizing the predictive information in future iterations.The mixture of Gaussians experiments and real-world digital image generative experiments show that our ACG method outperforms several existing technologies,illustrating the superiority and efficacy of our method.

Disturbance observer based actor-critic learning control for uncertain nonlinear systems

This paper investigates the disturbance observer based actor-critic learning control for a class of uncertain nonlinear systems in the presence of unmodeled dynamics and time-varying disturbances.The proposed control algorithm integrates a filter-based design method with actor-critic learning architecture and disturbance observer to circumvent the unmodeled dynamic and the timevarying disturbance.To be specific,the actor network is employed to estimate the unknown system dynamic,the critic network is developed to evaluate the control performance,and the disturbance observer is leveraged to provide efficient estimation of the compounded disturbance which includes the time-varying disturbance and the actor-critic network approximation error.Consequently,highgain feedback is avoided and the improved tracking performance can be expected.Moreover,a composite weight adaptation law for actor network is constructed by utilizing two types of signals,the cost function and the modeling error.Eventually,theoretical analysis demonstrates that the developed controller can guarantee bounded stability.Extensive simulations and experiments on a robot manipulator are implemented to validate the performance of the resulted control strategy.