The problem of reinforcement learning (RL)-based fuzzy control for nonlinear systems with unknown dynamics via parallel composite policy iteration (PCPI) scheme is studied in this article. The main objective of this article is to solve the fuzzy algebraic Riccati equation (FARE), which is inherently complex and cannot be easily solved by traditional mathematical formulas. Policy iteration (PI) and value iteration (VI) algorithms proposed have been widely used to address this problem. However, these algorithms have the disadvantages of an initial stabilizing control policy, the persistent excitation (PE) condition, and huge amounts of data. To effectively alleviate these drawbacks, a novel PCPI algorithm is proposed in this article. Specifically, for each fuzzy subsystem, an adaptive parameter is designed to eliminate the requirement of an initial stabilizing control policy. In addition, an online model-free PCPI algorithm is proposed for the situation where the dynamic information of the fuzzy system is difficult to obtain. By substituting the stored historical data with online data, the PE condition is relaxed to the initial excitation (IE) condition. Concurrently, the corresponding algorithm can be executed independently and concurrently under each fuzzy rule, thereby fully exploiting the available computational resources. Finally, the effectiveness of the algorithms set forth in this article is verified through a single-link robot arm and quarter-car active suspension (QCAS) experiment.

Nonlinear affine systems with relative degree two widely exist in the control field, and the unified output tracking control approach of these systems is still an open problem. This paper presents a formal framework for output tracking control design methodology for nonlinear affine systems with relative degree two. Specifically, a control barrier function is constructed to enforce the forward invariance or the stability of a set contained within a 0-sublevel set of the first-order derivative of pre-stablished Lyapunov function, thereby stabilizing the system output to the desired value. Additionally, by taking the first-order derivative of the elaborated control barrier function, control input terms with a nonzero coefficient are introduced into the stability condition, addressing the weakness of controller design using conventional control Lyapunov function approaches, which fails in states where the coefficient of the control input term is zero. Furthermore, the stability conditions are proposed in the form of linear inequality constraints involving control inputs, with which a collection of admissible controllers is provided. Then, by resorting to the pointwise minimum norm (PMN) technique, a numerical solution of an admissible controller can be derived in the context of a quadratic program. We finally demonstrate the effectiveness of the controller design method via two simulations, adaptive cruise control and vehicle lateral control.

In this paper, we introduce a novel hierarchical decision-making framework that integrates control barrier functions (CBFs) with reinforcement learning (RL) to enhance the safety and efficiency of autonomous vehicle merging at on-ramps. The proposed technique is comprised of three layers: a behavioral planning layer that employs proximal policy optimization (PPO) algorithm aims to learn its driving behaviors, which are not necessarily compliant with vehicle dynamics; a motion control layer that adopts model predictive control (MPC) framework to ensure the kinematic feasibility to follow the trajectories with heading angles and velocities provided by the upper layer; and lastly, a control barrier function-guided layer, which is the core innovation of this paper, is implemented. It leverages the forward invariance of control barrier functions to design a safety controller that refines the output of MPC to maintain continuous driving safety. The refined results are then used as objective function, guiding subsequent updates in the learning process. Simulation results demonstrate that the proposed CBF-guided architecture significantly improves training efficiency and performance, achieving a 60% reduction in training time and 6% increase in success rate compared to standard RL methods.

The issue of fuzzy-observer-based (FOB) fault-tolerant (FT) steering control for autonomous driving with persistent disturbances via model predictive control approach is studied in this article, where velocity variation, potential faults, nonlinearity, and unmeasurable states are considered simultaneously. Due to the variable longitudinal velocity during cruising on diverse road conditions and various vehicle maneuvers, the Takagi–Sugeno fuzzy method is employed to handle parameter variations in the steering control system. For the sake of obtaining information on fault behavior and unmeasurable system states, this article constructs a fuzzy observer to estimate the fault signal and faulty system states. Improved conditions for designing the observer gains are proposed, such that the estimation error converges to a minimal robust positively invariant set. Subsequently, this article introduces a FOB FT model predictive controller, which is designed through the resolution of a Min-Max optimization issue. In the end, the benefits of the approach developed in this article are validated by utilizing the Carsim/Matlab joint simulation.

This article introduces a sustainable human-guided reinforcement learning (RL) framework to address the challenge of learning performance degradation when the human guidance is suspended. First, a compensation reward based on the historical similarity between the RL agent and human guidance history is designed to ensure the continued influence of human guidance. To avoid cumulative errors in value function approximation caused by fitting the new reward, including the compensation reward, a novel RL paradigm is proposed, which bypasses value function fitting and directly optimizes the policy using historical similarity. This paradigm develops a new historical similarity-based learning objective for RL to leverage human guidance more efficiently and achieve alignment with human behavior. Furthermore, the proposed paradigm enables the fine-tuning of the RL agent to address the long-tail problem. Experimental results demonstrate the advantages of the proposed method in terms of sustainable guidance and optimal performance in the autonomous driving, achieving a 15% increase in optimal performance compared with existing state-of-the-art (SOTA) methods.

This article investigates the output consensus problem of heterogeneous linear multiagent systems under directed communication graphs. A novel adaptive dynamic event-triggered mechanism is proposed, intending to further save system resources consumed in communication between agents and controller update of agents themselves, and remove the assumption that the global information associated with the communication topology should be known in advance for the design of control parameters. Unlike the existing related adaptive event-triggered algorithms, the proposed algorithm could theoretically guarantee the existence of a strictly positive constant on the interevent time intervals for both communication between agents and controller update. Furthermore, it is shown by the simulation that the addition of a dynamic variable has the potential to further optimize the control cost when compared to the addition of exponential function signal or$L_{1}$signal usually adopted in existing adaptive event-triggered mechanisms. Then, the obtained results are extended from the strongly connected graph to the directed communication graph only containing a spanning tree. Finally, numerical simulation results are conducted to demonstrate the effectiveness of the proposed mechanism.

In this article, a model-free predictive control algorithm for the real-time system is presented. The algorithm is data driven and is able to improve system performance based on multistep policy gradient reinforcement learning. By learning from the offline dataset and real-time data, the knowledge of system dynamics is avoided in algorithm design and application. Cooperative games of the multiplayer in time horizon are presented to model the predictive control as optimization problems of multiagent and guarantee the optimality of the predictive control policy. In order to implement the algorithm, neural networks are used to approximate the action-state value function and predictive control policy, respectively. The weights are determined by using the methods of weighted residual. Numerical results show the effectiveness of the proposed algorithm.

For time-varying delayed nonlinear systems with parameter uncertainties and persistent disturbances, an online and an offline robust fuzzy model predictive control algorithms are proposed in this article. Both methods guarantee the input-to-state stability of the system. Furthermore, a novel alternative optimization (AOP) approach and a dual-mode optimal control (OP)/AOP strategy are proposed to prevent the performance deterioration of the online OP approach due to the challenges in addressing the bilinear matrix inequality (BMI) constraints. With the established AOP and dual-mode OP/AOP techniques, the optimization problem constrained by BMIs is transformed into convex, and a significantly more precise approximation of the ellipsoidal minimal robust positively invariant set can be calculated. Besides, the system can eventually converge into a more compact ellipsoidal set. These two alternative optimization methods can be easily extended to various nonlinear systems. A numerical example and a continuous-time stirring tank example are provided to validate the effectiveness and advantages of the established methodologies.

Real-time semantic segmentation aims to generate high-quality prediction in limited time. Recently, with the development of many related potential applications, such as autonomous driving, robot sensing and augmented reality devices, semantic segmentation is desirable to make a trade-off between accuracy and inference speed with limited computation resources. This paper introduces a novel effective and light-weighted network based on Separable Pyramid Module (SPM) to achieve competitive accuracy and inference speed with fewer parameters and computation. Our proposed SPM unit utilises factorised convolution and dilated convolution in the form of a feature pyramid to build a bottleneck structure, which extracts local and context information in a simple but effective way. Experiments on Cityscapes and Camvid datasets demonstrate our superior trade-off between speed and precision. Without pre-training or any additional processing, our SPMNet achieves 71.22% mIoU on Cityscapes test set at the speed of 94 FPS on a single GTX 1080Ti GPU card.

In this article, the problem of the distributed$H_\infty$filtering in finite-time horizon is investigated for a class of Takagi–Sugeno (T-S) fuzzy systems with sensor saturation and unknown bounded noise. Considering the network bandwidth limitation, a dynamic event-triggered mechanism (ETM) is proposed. Due to an asynchronous problem of premise variables induced by the dynamic ETM, the partition approach is applied. Under the partition region, a novel piecewise T-S fuzzy distributed$H_\infty$filtering is derived. By constructing the Lyapunov function, sufficient conditions for the finite-time$H_\infty$performance of the estimation error system are given. Furthermore, to minimize the interference from disturbance to distributed filtering, the optimal problem of disturbance attenuate parameter$\gamma$is solved. Finally, a simulation example is presented to verify the effectiveness of the proposed algorithm.

This article proposes a unified framework to investigate the leader-following and leaderless consensus problem of general linear multiagent systems under the directed communication topology only containing a spanning tree. To further reduce the use of resources for the control objective, an energy-saving control algorithm is introduced composed of double dynamic event-triggered mechanisms that work independently: one intends to control the communication of agents with their neighbors and the other to decide the update of controllers. It is shown that the control algorithm performs well compared to most existing control algorithms in terms of the communication cost between agents and the update cost of controllers. In addition, a new procedure to choose parameters is obtained by the developed Lyapunov stabilty method, with the potential of achieving less conservative parameters than related results. Finally, the effectiveness of the proposed control scheme is verified by numerical simulations.

In this article, the problem of a nonlinear system states estimation with multisensor stochastic scheduling is investigated. In order to solve the non-Gaussian property induced by the nonlinear transformation, the unscented transformation (UT) technique is applied. Since the sensor networks channel is limited, the stochastic event-triggered mechanisms (SETMs) are proposed to reduce the network transmission burden. Under the SETMs, the modified unscented Kalman filter is proposed. Additionally, the sufficient conditions are given to guarantee the stabilities of the error covariance and the estimation error. Finally, extensive examples are carried out. Performances evaluation and comparison with existing methods are given to demonstrate the superiority of the proposed methods.

This paper studies the fixed-time distributed localization problem for directed network based on bearing measurements. The orientation of the global coordinate system is not available to nodes whose local coordinate systems do not to be aligned. First, the barycentric coordinate representation is obtained relying only on the bearing information. Then, a fixed-time distributed network localization algorithm is proposed. By applying the proposed algorithm, the localization problem is converted to the consensus tracking problem for localization errors. When nodes distribution and communication topology meet the requirements, one can prove that the position estimates can convert to the truth after a fixed time. Finally, the simulation verifies the validity of the algorithm.

In this article, the problem of steering control based on Takagi-Sugeno (T-S) fuzzy vehicle lateral dynamics is investigated for autonomous driving with nonlinearities, system uncertainties, and actuator constraints. During normal vehicle cruising, the vehicle velocity always changes due to the different road conditions and/or steering wheel maneuvers, and moreover, the vehicle dynamics is also significantly influenced by the tire/road forces under different road surface conditions, which brings many difficulties in steering controller design. By adopting fuzzy modeling techniques and varying look-ahead control strategy, an approach to the T-S fuzzy antiwindup output feedback controller design is proposed for the steering control in path tracking within T-S fuzzy-model-based analysis framework, where the actuator amplitude saturation and rate limit are simultaneously taken into consideration. Finally, valuation results with Carsim/MATLAB joint simulation are shown to demonstrate the effectiveness of the developed methods, and some comparison results in path tracking performance with fixed look-ahead distance control rule and the driver model controller embedded in Carsim are provided, which illustrate the advantages of the developed controller design method.

This paper is concerned with the stability of the vehicular platoon consisting of a leader and multiple cooperative autonomous driving followers. The objective of the platoon control is to ensure all vehicles traveling at the same speed while maintaining a safety spacing. To achieve the objective, a novel control framework consisting of the distributed adaptive event-triggered observer and the car-following control protocol is proposed for the vehicular platoon control. The condition that only few following vehicles can access the information of the leader is considered. In order to design controllers while avoid using any global information, such as the system matrix and the state of the leader, a distributed event-triggered observer is proposed, such that each vehicle can observe the dynamics of the leader. Based on this observer, both collision avoidance and limited communication source of each vehicle are simultaneously considered in the design of the observer. It is shown that under the proposed control framework, the platoon can achieve asymptotical stable, meanwhile, the amount of transmission data and communication cost among vehicles can be reduced. Finally, numerical simulations are presented to show the applicability of the obtained results.

In this paper, an online foot position compensator (FPC) is proposed for improving the robustness of humanoid walking based on orbital energy conservation and discrete control Lyapunov function (DCLF), with which the asymptotic stability of the humanoid system can be maintained and, thus, the foot placement control is achieved. The online FPC is developed based on linear model predictive control (MPC) by replanning the trajectories of the center of mass (CoM) and properly placing the footsteps to resist external disturbances and recover the walking posture. To further improve the robustness of the humanoid robots to suppress strong external disturbance, a strategy of upper body posture control is proposed. The presented controller stabilizes the humanoid robot by utilizing hip joints to modulate the upper body posture online. Webots simulations and real experiments on a full-body NAO humanoid robot verify the effectiveness of the proposed methods.

This article investigates the polynomial fuzzy output feedback (PFOF) control synthesis problem for positive polynomial fuzzy systems. When the states of a positive system cannot be fully obtained, the output feedback control strategy is a good method to stabilize the control system. From fuzzy control point of view, we employ the polynomial fuzzy model rather than the Takagi–Sugeno fuzzy model, and this kind of models can express a wider range of nonlinear positive systems. However, the polynomials in the system matrices and the feedback control gain matrices will make the nonconvex stability conditions more difficult to deal with. Thereby, in order to crack the hard nut, a nonzero transformation vector is introduced in this article to deal with the nonconvex problem skillfully. Furthermore, the imperfect premise matching technique is taken into account so that the implement of the controller is more simple and money-saving. In addition, the augmented dynamic of the positive polynomial fuzzy-model-based (PPFMB) control system is investigated to facilitate the stability and positivity analysis, and the basic conditions in the light of sum of squares (SOSs) are derived. Besides, the advanced membership function dependent (MFD) technique is used so that a great of useful information of MFs is extracted to improve the relaxation of the results. Finally, the effectiveness of the theoretical findings is illustrated by a simulation example.

In this paper, the problem of steering control is investigated for vehicle path tracking in the presence of parametric uncertainties and nonlinearities. In practice, the vehicle mass varies due to the number of passengers or amount of payload, while the vehicle velocity also changes during normal cruising, which significantly influences vehicle dynamics. Moreover, the vehicle dynamics are strongly nonlinear caused by the tire/road forces under different road surface conditions. With fuzzy modeling method, the original nonlinear path tracking system with parameter variations is first formulated as a T-S fuzzy model with additive norm-bounded uncertainties, and then an approach to the fuzzy observer-based output feedback steering control for vehicle dynamics is proposed under a fuzzy Lyapunov function framework. By employing matrix inequality convexifying techniques, a sufficient condition is developed in the form of linear matrix inequalities such that the closed-loop path tracking error system is asymptotically stable with a guaranteed H∞level. Finally, the effectiveness of the proposed fuzzy observer-based output feedback controller is demonstrated in Carsim/Matlab joint simulation environment, via which the advantage of a T-S fuzzy observer-based output controller over the closed-loop driver model embedded in Carsim is also shown with parametric uncertainties and nonlinearities.

This paper examines the problem of membership-function-dependent controller design for a class of discrete-time T-S fuzzy systems. Based on the partition method of premise variable space, the original T-S fuzzy model is equivalently converted into a piecewise-fuzzy system. Then, by employing some staircase functions, the continuous membership functions are approximated by a series of discrete values via which the information of membership functions is brought into the stability analysis to reduce the design conservatism. With piecewise-Lyapunov functions, the approaches to the piecewise-fuzzy state feedback and observer-based output feedback controller design are proposed, respectively, in terms of linear matrix inequalities such that the closed-loop system is asymptotically stable with a prescribed H∞performance level. It is shown that the membership functions of the fuzzy model and fuzzy controllers are not necessarily the same, which allows more design flexibility. Finally, two illustrative examples are provided to show the effectiveness of the developed methods.

Monocular ORB-SLAM has been proved to be one of the best open-source SLAM method. However, it is still unsatisfying especially in low illumination indoor environment, which is caused by scale recovery and wrong feature matching. In this paper, we proposed a vehicle model based monocular ORBSLAM method supplemented by April-Tag to improve the performance of original algorithm. This approach is practical when autonomous driving in low-light and less-feature environment like garages and tunnels. We achieve this by proposing a vehicle model based initialization method fusing April-Tag measurement to recover scale. During tracking procedure, the outliers ORB feature points will be removed by checking reprojection error calculated from April-Tag. In addition, considering vehicle model can only obtain 2D motion, the vertical transition is estimated from camera model. Afterwards, a local Bundle Adjustment(BA) is applied to optimize camera pose both from frame to frame and frame to keyframe which will reduce accumulative error of the vehicle model. Finally, a convincing result is obtained from the testing drive in a garage.

Due to the unavailability of full state variables in many control systems, this paper is concerned with the design of reliable observer-based output feedback controller for a class of network-based Takagi-Sugeno fuzzy systems with actuator failures. In order to better allocate network resources under the case that the sensor nodes are physically distributed, the decentralized event triggering communication scheme is adopted such that each sensor node is capable to determine the transmission of its local measurement information independently. Considering that the implementation of the controller may not be synchronized with the plant trajectories due to asynchronous premise variables with such communication mechanism, a novel piecewise fuzzy observer-based output feedback controller is developed. By applying a piecewise Lyapunov function and some techniques on matrix convexification, an approach to the design of observer and controller gain is derived for the augmented closed-loop system to be asymptotically stable with a guaranteed H∞performance and reduced transmission frequency. Finally, two examples are given to show the effectiveness of the developed method.

This paper is concerned with the design of H∞event-triggered filter for a class of Takagi-Sugeno fuzzy systems. Based on the proposed communication strategy, only the measured outputs of the physical plant that violate a predefined triggering condition will win the right for transmission in the shared communication channel. Considering that the implementation of the filter may not be synchronized with the plant trajectories due to the asynchronous premise variables in network environment, a novel observer-based piecewise fuzzy filter is proposed. By adopting the idea of input delay method, the filtering error dynamics is reformulated as a new event-triggered piecewise fuzzy system. By applying a piecewise Lyapunov-Krasovskii functional and some techniques on matrix convexification, a method of event-triggered H∞piecewise filter design is developed for the filtering error system concerned to be asymptotically stable with a given disturbance attenuation level and reduced transmission rate. Moreover, a co-design algorithm to derive the filter gains and the event triggering parameters is proposed. Illustrative examples are finally given to show the effectiveness of the developed method.

In this paper, the problem of generalized H2filtering is concerned for a class of discrete-time T-S fuzzy systems with measurement quantization and packet loss. The quantized measurements are transmitted to the filter via an imperfect communication channel, where the phenomenon of packet loss can be encountered. A random binary process is utilized to describe the packet dropouts, while the quantization errors are treated as sector bound uncertainties. Attention is focused on the design of generalized H2piecewise filter such that the filtering error system is stochastically stable and preserves a guaranteed generalized H2performance. The developed filter gains can be obtained by solving a set of linear matrix inequalities. Finally, an illustrative example is provided to show the effectiveness of the proposed method.

This paper investigates the problem of H∞filtering for a class of nonlinear discrete-time systems with measurement quantization and packet dropouts. Each output is transmitted via an independent communication channel, and the phenomenon of packet dropouts in transmission is governed by an individual random binary distribution, while the quantization errors are treated as sector-bound uncertainties. Based on a piecewise-Lyapunov function, an approach to the design of H∞-piecewise filter is pro posed such that the filtering-error system is stochastically stable with a guaranteed H∞performance. Some slack matrices are introduced to facilitate the filter design procedure by eliminating the coupling between the Lyapunov matrices and the system matrices. The filter parameters can be obtained by solving a set of linear matrix inequalities (LMIs), which are numerically tractable with commercially available software. Finally, two illustrative examples are provided to show the effectiveness of the proposed method.

This paper investigates the problem of guaranteed cost control for Takagi-Sugeno fuzzy dynamic systems with interval parameter uncertainties. The parameter uncertainty is characterized by the matrix bound, which is quite natural in real applications. Attention is focused on the fuzzy state feedback controller design via the so-called parallel distributed compensation scheme, which guarantees the closed-loop system to be robustly stable with a prescribed upper bound of the cost function. By utilizing the instrumental idea of delay dividing, a new Lyapunov-Krasovskii functional is introduced, which leads the resultant conditions to be much less conservative than most existing results in the literature. Some other new ideas such as basis dependence are also employed, which help to reduce the conservatism. All the results are formulated in the form of linear matrix inequalities (LMIs), which can readily be solved via standard numerical software. Finally, illustrative examples are given to show the less conservatism and applicability of the obtained results.