This article investigates the problem of robust trajectory design for low-thrust spacecraft subject to state and observation uncertainties. An adaptive latent reinforcement learning (RL) scheme based on sequential latent variable models (SLVMs) is proposed to address this issue. First, an SLVM is employed for the representation learning of uncertain environments and for predicting future observations. Subsequently, by integrating representation learning based on the SLVM with proximal policy optimization (PPO), a stochastic latent PPO (SLPPO) scheme is introduced. Distinct from existing methods, the control policy is derived from learned stochastic latent variables rather than raw uncertain observations, which effectively mitigates the adverse impact of uncertainties on control performance. Furthermore, to enhance training efficiency, an improved dense reward shaping mechanism is designed based on the observation predictions from the SLVM and adaptive techniques. Finally, numerical simulations of two rendezvous missions validate the effectiveness of the proposed approach.

This paper explores the prescribed-time consensus control problem for a class of high-order strict-feedback nonlinear multi-agent systems with output state constraints. A distributed adaptive$\mathit {C^{1}}$smooth control scheme is developed such that the output-constrained consensus tracking is achieved within a prescribed time regardless of any initial conditions and other design parameters, although in the presence of completely unknown control gains and uncertainties. The prescribed-time control scheme is made possible for high-order systems by constructing a hybrid time-varying gain-based prescribed-time first-order filter and using the time transformation methods. Particularly, a novel uniformly switching mechanism is introduced into the time-varying gains, where the gain function is$\mathit {C^{1}}$smooth and the switching time is regardless of initial conditions, ensuring that the gains are uniformly bounded for all time and thus avoiding infinite time-varying gain problem. Finally, the benefits and effectiveness of the proposed control scheme are confirmed by a numerical simulation and its application to a 2 degree of freedom robotic manipulator. Note to Practitioners—This paper investigates the distributed adaptive$C^{1}$smooth control problem for nonlinear multi-agent systems with high-order strict-feedback dynamics, which can model various physical systems, such as flight systems, robotic systems, and autonomous aerial vehicles. Achieving distributed prescribed-time control for high-order MASs with completely unknown control gains, output constraint, and uncertainties poses significant challenges. By introducing a novel$C^{1}$smooth gain switching mechanism, a hybrid time-varying gain function is constructed to ensure uniform boundedness of the time-varying gain, which effectively avoids the high-gain implementation problem. Moreover, a prescribed-time distributed$C^{1}$smooth controller, operating smoothly for all time and everywhere is also forwarded, which is more desirable in practice. As a result, the proposed control scheme demonstrates high adaptability to practical engineering requirements and exhibits enhanced generalizability, as finally validated by the numerical simulations including a dual-degree-of-freedom robotic manipulator.

This paper investigates a distributed model predictive control (DMPC) for linear heterogeneous systems tracking arbitrary periodic references. The control objective consists of two parts: (i) driving the output of each subsystem consensus; (ii) steering the outputs as close as possible to an exogenous periodic reference. The artificial state reference and control input are considered as decision variables to track unreachable references. The optimal control problem (OCP) is then solved in a distributed manner using Alternating Direction Multiplier Method (ADMM). The proposed method does not need ADMM convergence at each time step, which greatly reduces the computation time. Under several mild assumptions, the feasibility of the OCP and the closed-loop asymptotic stability with respect to an optimal reachable cooperative trajectory are presented. The performance of the approach is demonstrated with some simulation results.Note to Practitioners—The paper is motivated by the problem of cooperative tracking unreachable references for heterogeneous systems. The generation of the reference signal often ignores the dynamics feature of systems, leading to such reference may not be fully tracked (unreachable reference). However, existing methods either lack optimality or cannot achieve cooperative tracking of unreachable references. Therefore, this study develops a novel DMPC approach to make up for the above lack. In addition, the proposed method greatly reduces the computation time while ensuring optimality, and has a wider initial feasibility. The proposed controller can be extended to cooperative track unreachable constant signal. The proposed method can be used for highly collaborative tasks, such as formation missions, collaborative transportation and spacecraft collaboration. In future research, we will address the problem of cooperative tracking unreachable references for nonlinear heterogeneous systems.

This work focuses on the issue of fixed-time tracking control for a class of nonlinear systems affected by unknown uncertainties and external disturbances. First, a fixed-time neuroadaptive approximator is proposed to estimate the lumped uncertainties in nonlinear systems. Unlike existing neural network based methods, the estimation solution presented here introduces an adaptive predictor based learning mechanism, which would improve the estimation performance by removing the effect of tracking errors on the estimation process. Then, based on the reconstructed information, a fixed-time command filtered backstepping controller is developed with a fixed-time compensation system. In the compensation system, a novel bounded function is skillfully utilized such that the order and complexity of the compensation system are effectively reduced. Moreover, it is demonstrated that the designed control scheme can drive the tracking error to a small set near zero in a fixed time. Finally, the validity of the proposed control scheme is illustrated by numerical simulationsNote to Practitioners—This paper is motivated by the tracking control problem for nonlinear systems such as robotic, spacecraft, and unmanned aerial vehicle system. Existing tracking control schemes often suffer from issues such as insufficient tracking speed, redundant design process and the explosion of complexity. A fixed time neuroadaptive backstepping control scheme is proposed in this paper to ensure convergence of the error within a fixed time. An adaptive predictor-based fixed-time neuroadaptive estimator is presented to enhance the speed and accuracy of uncertainty estimation. Furthermore, a novel fixed-time compensation system is presented, which effectively addresses the issue of complexity explosion while reducing coupling of the compensation system, making the controller more concise. The effectiveness of the proposed method is validated through a numerical simulation in an uncertain spacecraft pitch motion system. Future work will involve validation of the proposed method on a hardware-in-the-loop simulation system or experiment platform.

This paper investigates the fixed-time attitude tracking control problem for rigid spacecraft subject to external disturbance and output constraints. First, the state transformed function (STF) technique is employed to convert the constrained spacecraft error dynamics into an unconstrained one. Subsequently, a fixed-time disturbance observer (FXTDO) is designed to estimate and reconstruct the lumped disturbance of unconstrained system. Combined with the developed STF, FXTDO and fixed-time integral terminal sliding mode (FITSM) surface techniques, the proposed fixed-time control law provides zero-error attitude tracking with high control precision and chattering avoidance, while the output constraints are never transgressed. The fixed-time stability of the closed-loop system is conducted via the Lyapunov technique and bi-limit homogeneity theory, and the expression of convergence time is also presented. Simulations illustrate the efficiency of the investigated controller.

In this work, we investigate the measurement noise sensitivity and peaking problem of the extended state observer (ESO) under high-gain characteristics. For a class ofn-order nonlinear systems with measurement noise, a new variable-order filter and the corresponding filtered ESO (FESO) are constructed to achieve arbitrary suppression ability of measurement noise. Such a salient feature lies in the establishment of the variable-order filter with independent parameters such that the observer poles and the order of the proposed filter can be set arbitrarily by the designer, thereby allowing the user to predefine the suppression strength in prior by adjusting parameters. In addition, a peaking-free FESO is further proposed to eliminate the undesired peaking phenomenon during the transient state. Finally, a comprehensive numerical comparison is presented, and the proposed peaking-free FESO is applied to the drag-free spacecraft hardware in-loop platform. The simulation results reveal the advantages of the proposed scheme in measurement noise suppression and peaking elimination.

This work studies the attitude coordination tracking problem for multiple spacecraft with consideration of unintended faults (communication link faults and actuator faults), inertial uncertainties, and external disturbances under a directed communication graph. A resilient neuroadaptive distributed fixed-time control scheme is investigated to solve this challenging problem. First, an improved adaptive distributed observer is established for followers to estimate the states of the leader when considering communication link faults. The proposed observer improves the resilience against communication link faults. Subsequently, to further cope with the problem of actuator faults, inertial uncertainties, and external disturbances, based on the proposed observer and the technique of adding a power integrator, a neuroadaptive distributed fixed-time attitude coordination controller is developed. Unlike the existing controllers, the proposed one requires less information when dealing with faults and lumped uncertainties, and has a lower-computational cost. Moreover, the fixed-time stability of the closed-loop system is ensured under the designed resilient neuroadaptive distributed control scheme. Finally, comparative simulations are carried out to manifest the effectiveness of the investigated coordination control method.

This article addresses the finite-time attitude formation-containment control problem for networked uncertain rigid spacecraft under directed topology. A unified distributed finite-time attitude control framework, based on the sliding-mode control (SMC) principle, is developed. Different from the current state of the art, the proposed attitude control method is suitable for not only the leader spacecraft but also the follower spacecraft, and only the neighbor state information among spacecraft is required, allowing the resulting control scheme to be truly distributed. Furthermore, the proposed method is inherently continuous, which eliminates the undesired chattering problem. Such features are deemed favorable in practical spacecraft applications. In addition, upon using the proposed neuro-adaptive control technique, the attitude formation-containment deployment can be achieved in finite time with sufficient accuracy, despite the involvement of both the uncertain inertia matrices and external disturbances. The effectiveness of the developed control scheme is confirmed by numerical simulations.

This article addresses the distributed finite-time attitude tracking control problem for a group of uncertain rigid spacecraft in the presence of unavailable angular velocity under the directed topology condition. First, a finite-time adaptive neural network observer is proposed for each follower to estimate its own unavailable angular velocity. Unlike existing velocity-observer-based design methods, the proposed one does not need the exact knowledge of the system model, and works well for the systems with both vanishing and nonvanishing uncertainties. Further, another finite-time observer is provided to obtain the precise angular velocity information of the dynamic leader in a distributed manner. Based on these two observers and adding a power integrator technique, a continuous distributed finite-time control scheme with only attitude measurements is finally established. A rigorous theoretical proof shows that the entire finite-time stability of the combined observer-controller closed-loop system is ensured. Simulation results illustrate the benefits and effectiveness of the developed control scheme.

This article is concerned with the finite-time tracking control problem for a class of strict-feedback nonlinear systems involving state constraints, unknown nonlinearities, and nonvanishing disturbances. Unlike the literature that mainly focuses on a C0finite-time controller, in this article, a novel C1smooth finite-time adaptive neural network (NN) controller is proposed by employing a smooth switch between the fractional and cubic form state feedback. The proposed controller not only avoids the singularity but also makes it possible to implement the dynamic surface control (DSC) technique. By applying the adaptive NN control technique, together with barrier Lyapunov functions (BLFs) and a generalized first-order filter including both linear and fractional terms, the desired fast finite-time control performance of the closed-loop nonlinear systems can be guaranteed, and meanwhile, the state constraints are never violated. Under the proposed control scheme, the tracking control problems of nonlinear systems with output constraint and full-state constraints are, respectively, discussed. It is explicitly shown that all the internal error signals are driven to converge into small regions in a finite time. Finally, the effectiveness of the control scheme is also confirmed by the applications to the control of a second-order nonlinear system and an uncertain ship autopilot.

The concept of Web 2.0 becomes prevalent and popular in the past few years. People are able to share and manage their own resources in Web 2.0 Systems. The abundance of Web 2.0 resources in various media formats calls for better resource integration, intending to enrich user experience in both browsing and searching. Though the Web 2.0 resources are shown in various modalities, their tags act as an intuitive medium to connect resources together. However, tagging is by nature an ad hoc activity. They do often contain noises and are affected by the subjective inclination of taggers. Consequently, linking resources simply by tags will not be reliable. In this paper, we propose an effective approach for linking tagged resources to concepts extracted from Wikipedia, which has become a fairly reliable reference over the last few years. Compared to the tags, the concepts are therefore of higher quality. Empirical experiments were conducted, and the results validate the effectiveness of our framework.