Three‐Dimensional Trajectory Tracking Control for Stratospheric Airship Based on Deep Reinforcement Learning

Aiming at the trajectory tracking control of AGV in aeronautical manufacturing and automated warehouse, a novel trajectory tracking control method was proposed. Firstly, the kinematic model and trajectory tracking control model of AGV were established. After analysing the reversing problem of AGV in practical situation and the limitations of classic trajectory tracking control method, and based on the similarity between the forward mode and reversing mode of AGV, a novel trajectory tracking control rule was designed and its stability was proved. The trajectory tracking control rule had simpler, less amount of calculation and improved the flexibility and handling efficiency of AGV. Finally, the trajectory tracking control experiments of sinusoid and path consisting of segments and arcs were done on experimental platform. The experiment results verified that the trajectory tracking control method were effective and feasible. The method could meet the requirements of autonomous handing for AGV in aeronautical manufacturing and automated warehouse.

The waypoint behavior is a method of trajectory tracking control for unmanned surface vehicle (USV). We take the waypoint behavior as the research object, choose speed, steering angle, capture radius, slip radius, lead distance, lead damper as features, and establish a prediction model for trajectory tracking control of USV based on deep neural network. The model effectively predicts the navigation effect and provides assistance and reference for the maneuvering decision of the USV. Test results show that the predicted results and the reference samples have same tendency. The proposed model can improve the performance of trajectory tracking control for the USV.

Trajectory tracking is a problem of emphasis for the mobile robot. In this study, a coordinate transformation method was used to build a kinematic model of the wheeled mobile robot. A traditional proportional-integral-derivative control method was researched and improved by combining it with a neural network. A neural network proportional-integral-derivative trajectory tracking control method was thus designed, and a simulation experiment was performed using Simulink. The results show that in circular trajectory tracking control, the maximum errors of the X axis, Y axis, and θ were approximately 2.1 m, 2.3 m, and 0.4 rad, respectively, and that the system remained stable after running for 10 s. In straight-line trajectory tracking control, the maximum errors of the X axis, Y axis, and θ were approximately −0.8 m, 1.3 m, and 0.3 rad, respectively, and the system remained stable after running for 8 s. The error was relatively small, and the effect of trajectory tracking control was good. The studied method had good performance in terms of wheeled mobile robot trajectory tracking control and is worthy of further promotion and application.

The cerebellar model articulation controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. In recent works, the kernel recursive least squares CMAC (KRLS---CMAC) was proposed as a superior alternative to the standard CMAC as it converges faster and does not require tuning of a learning rate parameter. One improvement to the standard CMAC that has been discussed in the literature is eligibility, and vector eligibility. With vector eligibility the CMAC is able to control online motion control problems that it could not previously, stabilize the system much faster, and converge to a more intelligent solution. This paper integrates vector eligibility with the KRLS---CMAC and shows how the combination is advantageous through two simulated control experiments.

The trajectory tracking control of the quadrotor unmanned aerial vehicle (QUAV) is investigated. The aim of this paper is to develop a novel trajectory tracking control method considering model uncertainties and external disturbances with finite-time stability and prescribed performance of the attitude. Firstly, the trajectory tracking control system of the QUAV is decoupled into two subsystems, i.e., position and attitude subsystems, wherein, backstepping technique is used to design the position tracking controller. Then, to guarantee the tracking performance of the attitude subsystem, a finite-time convergent performance function is developed, and a prescribed performance attitude controller is devised via using integral barrier Lyapunov function thereafter. In the design process of the above two controllers, ESO is used to estimate and compensate multiple uncertainties and disturbances simultaneously. Moreover, the fractional state feedback and discontinuous phenomenon of the control law are directly avoided to achieve the finite-time convergence rate. Finally, an illustrative example is organized to verify the effectiveness of the proposed approach.

The cerebellar model articulation controller (CMAC) neural network (NN) has advantages over fully connected NNs due to its increased structure. This paper attempts to provide a comprehensive treatment of CMAC NNs in closed-loop control applications. The function approximation capabilities of the CMAC NN are first rigorously established, and novel weight-update laws derived that guarantee the stability of the closed-loop system. The passivity properties of the CMAC under the specified tuning laws are examined and the relationship between passivity and closed-loop stability is derived. The utility of the CMAC NN in controlling a nonlinear system with unknown dynamics is demonstrated through numerical examples.

The Cerebellar Model Articulation Controller (CMAC) neural network is an associative memory that is biologically inspired by the cerebellum, which is found in the brains of animals. The standard CMAC uses the least mean squares algorithm to train the weights. Recently, the recursive least squares (RLS) algorithm was proposed as a superior algorithm for training the CMAC online as it can converge in just one epoch, and does not require tuning of a learning rate. However, the RLS algorithm was found to be very computationally demanding as its computational complexity is dependent on the square of the number of weights required which can be huge for the CMAC. Here, we show a more efficient RLS algorithm that uses inverse QR decomposition and additionally provides a regularized solution, improving generalization. However, while the inverse QR decomposition based RLS algorithm reduces computation time significantly; it is still not fast enough for use in CMACs greater than two dimensions. To further improve efficiency we show that by using kernel methods the CMAC computational complexity can be transformed to become dependent on the number of unique training data. Additionally, it is shown how modeling error can be improved through use of higher order basis functions.

Self-balancing two-wheel robot is a high order, multi-variable, nonlinear, strong-coupling and absolutely unstable system. A reinforcement leaming algorithm based on many parallel Cerebellar Model Articulation Controller (CMAC) neural networks is proposed for the balance-control problem of self-balancing two-wheel robot. In the method, the outputs of CMAC are used to approximate the Q-functions of the input state variables. The input state variables are divided to decrease the grades of quantization. Therefore, the storage spaces of CMAC are reduced effectively, and the learning rate and control precision of Q-algorithm are improved. At the same time, the generalization of continuous state variables is realized too. The method is applied to solve the balance control problem of self-balancing two-wheel robot, and the simulation results show its correctness and efficiency.

A control scheme of ANN-based PID controller is developed here to reach high precision tracking control for an electro-hydraulic servo system. The PID controller is used as a feedback controller to guarantee the system stability. The cerebellar model articulation controller (CMAC) neural network is used as a feed-forward compensator to identify the inverse system dynamics model. The CMAC and the PID controller are connected in parallel. The outputs of this paralleled controller are summed up as the total control action. A nonlinear tracking differentiator (NTD) is presented to yield high quality differential signals for the PID controller. The main task of this control algorithm is to make the error between the total control action and the output of the CMAC minimize by the CMAC learning algorithm. Thus the control action is formed by the CMAC. Numerical simulation results show comparing with conventional PID control strategy this proposed control scheme has an excellent system performance including high precision trajectory tracking ability and rejection of disturbance.

DC–DC converters are the devices which can convert a certain electrical voltage to another level of electrical voltage. They are very popularly used because of the high efficiency and small size. This paper proposes an intelligent power controller for the DC–DC converters via cerebella model articulation controller (CMAC) neural network approach. The proposed intelligent power controller is composed of a CMAC neural controller and a robust controller. The CMAC neural controller uses a CMAC neural network to online mimic an ideal controller, and the robust controller is designed to achieve L 2 tracking performance with desired attenuation level. Finally, a comparison among a PI control, adaptive neural control and the proposed intelligent power control is made. The experimental results are provided to demonstrate the proposed intelligent power controller can cope with the input voltage and load resistance variations to ensure the stability while providing fast transient response and simple computation.

This paper describes the application of cerebellar model articulation controller (CMAC) and B-spline neural networks to switched reluctance motor (SRM) torque estimation and control. Non-linear adaptive systems such as neural networks are well suited to learning the highly non-linear electromagnetic characteristics of the SRM for the purposes of linearisation and simplification of their control and a number of researchers have investigated their use in this context. CMAC and B-spline neural networks are particularly suited to this application area due to their potential for low-cost, high-speed implementation including the capability for real-time, on-line adaptation. CMAC and B-spline neural networks have successfully been applied both to torque ripple minimisation and to torque estimation in simulation and, implemented using FPGA technology, experimentally. This paper describes those applications with particular emphasis on the suitability of the CMAC and B-spline neural networks and gives details of their FPGA implementation.

This paper discusses adaptive control method used in high performance servo system based on Cerebellar Model Articulation Controller(CMAC). It analyzes the uncertain and nonlinear factors of the servo system, studies the modeling method using the frequency property of the system, and then uses an additional item to instead of the non-modeling factor. In the proposed control scheme, the CMAC controller is able to learn the unknown model dynamics, parameter variation and disturbance of the system on line. The model reference adaptive control (MRAC) scheme is used to give better solutions with online adaptation. It contemporarily improved the conception mapping algorithm of the Cerebellar Model Articulation Controller Neural Network(CMACNN), which gave a determined expression of the physical memory size and designed a physical memory address function. Experiment results verify that the proposed strategy can achieve high tracking precision for real-time position close-loop servo system.

This paper studies the trajectory tracking control of second-order uncertain nonlinear systems in the presence of internal uncertainty and external disturbances. Trajectory tracking control method is presented based on integral concurrent learning predictor. Specifically, an integral concurrent learning predictor is designed by using the historical data and real-time data information, which can estimate the unknown system parameters without persistency of excitation. Then, a trajectory tracking controller is developed by combining the estimated information. By using the Lyapunov stability analysis, the closed system is input-to-state stable. Simulation results verify the effectiveness of the proposed method.

Load forecasting is an issue that needs to be addressed to prevent overloading and catastrophic blackouts in power grids. This paper proposes a dual cerebellar model articulation controller (CMAC) neural network which is able to give an accurate very short term prediction of the required load curve. This is the first time a CMAC algorithm has been employed for load forecasting. The paper depicts that the proposed method has the advantage of reduced training time and reduced computational requirements as compared to the other load forecasting techniques. The data of the south west interconnected system was employed to give load predictions whilst using the proposed dual CMAC and back propagation neural network. The performance evolution has shown that the proposed dual CMAC neural network works efficiently and accurately for very short term load forecasting scenarios as compared to other conventional load forecasting techniques.

Autonomous underwater vehicles (AUVs) have been widely used to perform underwater tasks. Due to the environmental disturbances, underactuated problems, system constraints, and system coupling, AUV trajectory tracking control is challenging. Thus, further investigation of dynamic characteristics and trajectory tracking control methods of the AUV motion system will be of great importance to improve underwater task performance. An AUV controller must be able to cope with various challenges with the underwater vehicle, adaptively update the reference model, and overcome unexpected deviations. In order to identify modeling strategies and the best control practices, this paper presents an overview of the main factors of control-oriented models and control strategies for AUVs. In modeling, two fields are considered: (i) models that come from simplifications of Fossen’s equations; and (ii) system identification models. For each category, a brief description of the control-oriented modeling strategies is given. In the control field, three relevant aspects are considered: (i) significance of AUV trajectory tracking control, (ii) control strategies; and (iii) control performance. For each aspect, the most important features are explained. Furthermore, in the aspect of control strategies, mathematical modeling study and physical experiment study are introduced in detail. Finally, with the aim of establishing the acceptability of the reported modeling and control techniques, as well as challenges that remain open, a discussion and a case study are presented. The literature review shows the development of new control-oriented models, the research in the estimation of unknown inputs, and the development of more innovative control strategies for AUV trajectory tracking systems are still open problems that must be addressed in the short term.