Recent Progress in Reinforcement Learning and Adaptive Dynamic Programming for Advanced Control Applications

Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.

An Adaptive Program Recommendation System for Multi-User Sharing Environment

More and more accounts or devices are shared by multiple users in video applications,which makes it difficult to provide recommendation service.Existing recommendation schemes overlook multiuser sharing scenarios,and they cannot make effective use of the mixed information generated by multi-user when exploring users’potential interests.To solve these problems,this paper proposes an adaptive program recommendation system for multi-user sharing environment.Specifically,we first design an offline periodic identification module by building multi-user features and periodically predicting target user in future sessions,which can separate the profile of target user from mixed log records.Subsequently,an online recommendation module with adaptive timevarying exploration strategy is constructed by jointly using personal information and multi-user social information provided by identification module.On one hand,to learn the dynamic changes in user-interest,a time-varying linear upper confidence bound(LinUCB)based on personal information is designed.On the other hand,to reduce the risk of exploration,a timeinvariant LinUCB based on separated multi-user social information from one account/device is proposed to compute the quality scores of programs for each user,which is integrated into the time-varying LinUCB by cross-weighting strategy.Finally,experimental results validate the efficiency of the proposed scheme.

Solar adaptive optics systems for the New Vacuum Solar Telescope at the Fuxian Lake Solar Observatory

Adaptive optics(AO)is essential for high-quality ground-based observations with large telescopes because it counters the impact of wavefront aberrations caused by atmospheric turbulence.The new vacuum solar telescope(NVST)is one of the most important high-resolution solar observation instruments in the world.Three sets of solar adaptive optics systems have been developed and installed on this telescope:conventional adaptive optics,ground layer adaptive optics,and multi-conjugate adaptive optics.These have been in operation from 2018 to 2023.This paper details the development and application of solar adaptive optics on the NVST and discusses the newest instrumentation.

Quaternion-Based Adaptive Trajectory Tracking Control of a Rotor-Missile with Unknown Parameters Identification

This paper investigates the adaptive trajectory tracking control problem and the unknown parameter identification problem of a class of rotor-missiles with parametric system uncertainties.First,considering the uncertainty of structural and aerodynamic parameters,the six-degree-of-freedom(6Do F) nonlinear equations describing the position and attitude dynamics of the rotor-missile are established,respectively,in the inertial and body-fixed reference frames.Next,a hierarchical adaptive trajectory tracking controller that can guarantee closed-loop stability is proposed according to the cascade characteristics of the 6Do F dynamics.Then,a memory-augmented update rule of unknown parameters is proposed by integrating all historical data of the regression matrix.As long as the finitely excited condition is satisfied,the precise identification of unknown parameters can be achieved.Finally,the validity of the proposed trajectory tracking controller and the parameter identification method is proved through Lyapunov stability theory and numerical simulations.

Ground-layer Adaptive Optics for the 2.5 m Wide-field and High-resolution Solar Telescope

The 2.5 m wide-field and high-resolution solar telescope(WeHoST)is currently under developing for solar observations.WeHoST aims to achieve high-resolution observations over a super-wide field of view(FOV)of5′×5′,and a desired resolution of 0.3″.To meet the scientific requirements of WeHoST,the ground-layer adaptive optics(GLAO)with a specially designed wave front sensing system is as the primary consideration.We introduce the GLAO configuration,particularly the wave front sensing scheme.Utilizing analytic method,we simulate the performance of both classical AO and GLAO systems,optimize the wave front sensing system,and evaluate GLAO performance in terms of PSF uniformity and correction improvement across whole FOV.The results indicate that,the classical AO will achieve diffraction-limited resolution;the suggested GLAO configuration will uniformly improve the seeing across the full 5′×5′FOV,reducing the FWHM across the axis FOV to less than0.3″(λ≥705 nm,r0≥11 cm),which is more than two times improvement.The specially designed wave front sensor schedule offers new potential for WeHoST’s GLAO,particularly the multi-FOV GLAO and the flexibility to select the detected area.These capabilities will significantly enhance the scientific output of the telescope.

Adaptive admittance tracking control for interactive robot with prescribed performance

An adaptive control approach is presented in this paper for tracking desired trajectories in interactive manipulators. The controller design incorporates prescribed performance functions (PPFs) to improve dynamic performance. Notably, the performance of the output error is confined in an envelope characterized by exponential convergence, leading to convergence to zero. This feature ensures a prompt response from admittance control and establishes a reliable safety framework for interactions. Simulation results provide practical insights,demonstrating the viability of the control scheme proposed in this paper.

Fast compressed sensing spectral measurement with adaptive gradient multiscale resolution

We propose a fast,adaptive multiscale resolution spectral measurement method based on compressed sensing.The method can apply variable measurement resolution over the entire spectral range to reduce the measurement time by over 75%compared to a global high-resolution measurement.Mimicking the characteristics of the human retina system,the resolution distribution follows the principle of gradually decreasing.The system allows the spectral peaks of interest to be captured dynamically or to be specified a priori by a user.The system was tested by measuring single and dual spectral peaks,and the results of spectral peaks are consistent with those of global high-resolution measurements.

Noise-tolerate and adaptive coefficient zeroing neural network for solving dynamic matrix square root

The solving of dynamic matrix square root(DMSR)problems is frequently encountered in many scientific and engineering fields.Although the original zeroing neural network is powerful for solving the DMSR,it cannot vanish the influence of the noise perturbations,and its constant-coefficient design scheme cannot accelerate the convergence speed.Therefore,a noise-tolerate and adaptive coefficient zeroing neural network(NTACZNN)is raised to enhance the robust noise immunity performance and accelerate the conver-gence speed simultaneously.Then,the global convergence and robustness of the pro-posed NTACZNN are theoretically analysed under an ideal environment and noise-perturbed circumstances.Furthermore,some illustrative simulation examples are designed and performed in order to substantiate the efficacy and advantage of the NTACZNN for the DMSR problem solution.Compared with some existing ZNNs,the proposed NTACZNN possesses advanced performance in terms of noise tolerance,solution accuracy,and convergence rate.

A Novel Clutter Suppression Algorithm for Low-Slow-Small Targets Detecting Based on Sparse Adaptive Filtering

Passive detection of low-slow-small(LSS)targets is easily interfered by direct signal and multipath clutter,and the traditional clutter suppression method has the contradiction between step size and convergence rate.In this paper,a frequency domain clutter suppression algorithm based on sparse adaptive filtering is proposed.The pulse compression operation between the error signal and the input reference signal is added to the cost function as a sparsity constraint,and the criterion for filter weight updating is improved to obtain a purer echo signal.At the same time,the step size and penalty factor are brought into the adaptive iteration process,and the input data is used to drive the adaptive changes of parameters such as step size.The proposed algorithm has a small amount of calculation,which improves the robustness to parameters such as step size,reduces the weight error of the filter and has a good clutter suppression performance.

Reinforcement learning based adaptive control for uncertain mechanical systems with asymptotic tracking

This paper mainly focuses on the development of a learning-based controller for a class of uncertain mechanical systems modeled by the Euler-Lagrange formulation.The considered system can depict the behavior of a large class of engineering systems,such as vehicular systems,robot manipulators and satellites.All these systems are often characterized by highly nonlinear characteristics,heavy modeling uncertainties and unknown perturbations,therefore,accurate-model-based nonlinear control approaches become unavailable.Motivated by the challenge,a reinforcement learning(RL)adaptive control methodology based on the actor-critic framework is investigated to compensate the uncertain mechanical dynamics.The approximation inaccuracies caused by RL and the exogenous unknown disturbances are circumvented via a continuous robust integral of the sign of the error(RISE)control approach.Different from a classical RISE control law,a tanh(·)function is utilized instead of a sign(·)function to acquire a more smooth control signal.The developed controller requires very little prior knowledge of the dynamic model,is robust to unknown dynamics and exogenous disturbances,and can achieve asymptotic output tracking.Eventually,co-simulations through ADAMS and MATLAB/Simulink on a three degrees-of-freedom(3-DOF)manipulator and experiments on a real-time electromechanical servo system are performed to verify the performance of the proposed approach.

Nonlinear robust adaptive control for bidirectional stabilization system of all-electric tank with unknown actuator backlash compensation and disturbance estimation

Since backlash nonlinearity is inevitably existing in actuators for bidirectional stabilization system of allelectric tank,it behaves more drastically in high maneuvering environments.In this work,the accurate tracking control for bidirectional stabilization system of moving all-electric tank with actuator backlash and unmodeled disturbance is solved.By utilizing the smooth adaptive backlash inverse model,a nonlinear robust adaptive feedback control scheme is presented.The unknown parameters and unmodelled disturbance are addressed separately through the derived parametric adaptive function and the continuous nonlinear robust term.Because the unknown backlash parameters are updated via adaptive function and the backlash effect can be suppressed successfully by inverse operation,which ensures the system stability.Meanwhile,the system disturbance in the high maneuverable environment can be estimated with the constructed adaptive law online improving the engineering practicality.Finally,Lyapunov-based analysis proves that the developed controller can ensure the tracking error asymptotically converges to zero even with unmodeled disturbance and unknown actuator backlash.Contrast co-simulations and experiments illustrate the advantages of the proposed approach.

Adaptive H_(∞)Filtering Algorithm for Train Positioning Based on Prior Combination Constraints

To solve the problem of data fusion for prior information such as track information and train status in train positioning,an adaptive H∞filtering algorithm with combination constraint is proposed,which fuses prior information with other sensor information in the form of constraints.Firstly,the train precise track constraint method of the train is proposed,and the plane position constraint and train motion state constraints are analysed.A model for combining prior information with constraints is established.Then an adaptive H∞filter with combination constraints is derived based on the adaptive adjustment method of the robustness factor.Finally,the positioning effect of the proposed algorithm is simulated and analysed under the conditions of a straight track and a curved track.The results show that the positioning accuracy of the algorithm with constrained filtering is significantly better than that of the algorithm without constrained filtering and that the algorithm with constrained filtering can achieve better performance when combined with track and condition information,which can significantly reduce the train positioning error.The effectiveness of the proposed algorithm is verified.

Value Iteration-Based Cooperative Adaptive Optimal Control for Multi-Player Differential Games With Incomplete Information

This paper presents a novel cooperative value iteration(VI)-based adaptive dynamic programming method for multi-player differential game models with a convergence proof.The players are divided into two groups in the learning process and adapt their policies sequentially.Our method removes the dependence of admissible initial policies,which is one of the main drawbacks of the PI-based frameworks.Furthermore,this algorithm enables the players to adapt their control policies without full knowledge of others’ system parameters or control laws.The efficacy of our method is illustrated by three examples.

A Fractional-Order Ultra-Local Model-Based Adaptive Neural Network Sliding Mode Control of n-DOF Upper-Limb Exoskeleton With Input Deadzone

This paper proposes an adaptive neural network sliding mode control based on fractional-order ultra-local model for n-DOF upper-limb exoskeleton in presence of uncertainties,external disturbances and input deadzone.Considering the model complexity and input deadzone,a fractional-order ultra-local model is proposed to formulate the original dynamic system for simple controller design.Firstly,the control gain of ultra-local model is considered as a constant.The fractional-order sliding mode technique is designed to stabilize the closed-loop system,while fractional-order time-delay estimation is combined with neural network to estimate the lumped disturbance.Correspondingly,a fractional-order ultra-local model-based neural network sliding mode controller(FO-NNSMC) is proposed.Secondly,to avoid disadvantageous effect of improper gain selection on the control performance,the control gain of ultra-local model is considered as an unknown parameter.Then,the Nussbaum technique is introduced into the FO-NNSMC to deal with the stability problem with unknown gain.Correspondingly,a fractional-order ultra-local model-based adaptive neural network sliding mode controller(FO-ANNSMC) is proposed.Moreover,the stability analysis of the closed-loop system with the proposed method is presented by using the Lyapunov theory.Finally,with the co-simulations on virtual prototype of 7-DOF iReHave upper-limb exoskeleton and experiments on 2-DOF upper-limb exoskeleton,the obtained compared results illustrate the effectiveness and superiority of the proposed method.

Implementation of Fuzzy Logic Control into an Equivalent Minimization Strategy for Adaptive Energy Management of A Parallel Hybrid Electric Vehicle

As government agencies continue to tighten emissions regulations due to the continued increase in greenhouse gas production, automotive industries are seeking to produce increasingly efficient vehicle technology. Hybrid electric vehicles (HEVs) have been introduced to mitigate problems while improving fuel economy. HEVs have led to the demand of creating more advanced controls software to consider multiple components for propulsive power in a vehicle. A large section in the software development process is the implementation of an optimal energy management strategy meant to improve the overall fuel efficiency of the vehicle. Optimal strategies can be implemented when driving conditions are known a prior. The Equivalent Consumption Minimization Strategy (ECMS) is an optimal control strategy that uses an equivalence factor to equate electrical to mechanical power when performing torque split determination between the internal combustion engine and electric motor for propulsive and regenerative torque. This equivalence factor is determined from offline vehicle simulations using a sensitivity analysis to provide optimal fuel economy results while maintaining predetermined high voltage battery state of charge (SOC) constraints. When the control hierarchy is modified or different driving styles are applied, the analysis must be redone to update the equivalence factor. The goal of this work is to implement a fuzzy logic controller that dynamically updates the equivalence factor to improve fuel economy, maintain a strict charge sustaining window of operation for the high voltage battery, and reduce computational time required during algorithm development. The adaptive algorithm is validated against global optimum fuel economy and charge sustaining results from a sensitivity analysis performed for multiple drive cycles. Results show a maximum fuel economy improvement of 9.82% when using a mild driving style and a 95% success rate when maintaining an ending SOC within 5% of the desired SOC regardless of starting SOC.

Research on Anthropomorphic Obstacle Avoidance Trajectory Planning for Adaptive Driving Scenarios Based on Inverse Reinforcement Learning Theory

The forward design of trajectory planning strategies requires preset trajectory optimization functions,resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajectories that conform to real driver behavior habits.In addition,owing to the strong time-varying dynamic characteristics of obstacle avoidance scenarios,it is necessary to design numerous trajectory optimization functions and adjust the corresponding parameters.Therefore,an anthropomorphic obstacle-avoidance trajectory planning strategy for adaptive driving scenarios is proposed.First,numerous expert-demonstrated trajectories are extracted from the HighD natural driving dataset.Subsequently,a trajectory expectation feature-matching algorithm is proposed that uses maximum entropy inverse reinforcement learning theory to learn the extracted expert-demonstrated trajectories and achieve automatic acquisition of the optimization function of the expert-demonstrated trajectory.Furthermore,a mapping model is constructed by combining the key driving scenario information that affects vehicle obstacle avoidance with the weight of the optimization function,and an anthropomorphic obstacle avoidance trajectory planning strategy for adaptive driving scenarios is proposed.Finally,the proposed strategy is verified based on real driving scenarios.The results show that the strategy can adjust the weight distribution of the trajectory optimization function in real time according to the“emergency degree”of obstacle avoidance and the state of the vehicle.Moreover,this strategy can generate anthropomorphic trajectories that are similar to expert-demonstrated trajectories,effectively improving the adaptability and acceptability of trajectories in driving scenarios.

Adaptive Space Expansion for Fast Motion Planning

The sampling process is very inefficient for sam-pling-based motion planning algorithms that excess random sam-ples are generated in the planning space.In this paper,we pro-pose an adaptive space expansion(ASE)approach which belongs to the informed sampling category to improve the sampling effi-ciency for quickly finding a feasible path.The ASE method enlarges the search space gradually and restrains the sampling process in a sequence of small hyper-ellipsoid ring subsets to avoid exploring the unnecessary space.Specifically,for a con-structed small hyper-ellipsoid ring subset,if the algorithm cannot find a feasible path in it,then the subset is expanded.Thus,the ASE method successively does space exploring and space expan-sion until the final path has been found.Besides,we present a particular construction method of the hyper-ellipsoid ring that uniform random samples can be directly generated in it.At last,we present a feasible motion planner BiASE and an asymptoti-cally optimal motion planner BiASE*using the bidirectional exploring method and the ASE strategy.Simulations demon-strate that the computation speed is much faster than that of the state-of-the-art algorithms.The source codes are available at https://github.com/shshlei/ompl.

TCAS-PINN:Physics-informed neural networks with a novel temporal causality-based adaptive sampling method

Physics-informed neural networks(PINNs)have become an attractive machine learning framework for obtaining solutions to partial differential equations(PDEs).PINNs embed initial,boundary,and PDE constraints into the loss function.The performance of PINNs is generally affected by both training and sampling.Specifically,training methods focus on how to overcome the training difficulties caused by the special PDE residual loss of PINNs,and sampling methods are concerned with the location and distribution of the sampling points upon which evaluations of PDE residual loss are accomplished.However,a common problem among these original PINNs is that they omit special temporal information utilization during the training or sampling stages when dealing with an important PDE category,namely,time-dependent PDEs,where temporal information plays a key role in the algorithms used.There is one method,called Causal PINN,that considers temporal causality at the training level but not special temporal utilization at the sampling level.Incorporating temporal knowledge into sampling remains to be studied.To fill this gap,we propose a novel temporal causality-based adaptive sampling method that dynamically determines the sampling ratio according to both PDE residual and temporal causality.By designing a sampling ratio determined by both residual loss and temporal causality to control the number and location of sampled points in each temporal sub-domain,we provide a practical solution by incorporating temporal information into sampling.Numerical experiments of several nonlinear time-dependent PDEs,including the Cahn–Hilliard,Korteweg–de Vries,Allen–Cahn and wave equations,show that our proposed sampling method can improve the performance.We demonstrate that using such a relatively simple sampling method can improve prediction performance by up to two orders of magnitude compared with the results from other methods,especially when points are limited.

Robust adaptive radar beamforming based on iterative training sample selection using kurtosis of generalized inner product statistics

In engineering application,there is only one adaptive weights estimated by most of traditional early warning radars for adaptive interference suppression in a pulse reputation interval(PRI).Therefore,if the training samples used to calculate the weight vector does not contain the jamming,then the jamming cannot be removed by adaptive spatial filtering.If the weight vector is constantly updated in the range dimension,the training data may contain target echo signals,resulting in signal cancellation effect.To cope with the situation that the training samples are contaminated by target signal,an iterative training sample selection method based on non-homogeneous detector(NHD)is proposed in this paper for updating the weight vector in entire range dimension.The principle is presented,and the validity is proven by simulation results.

Adaptive Robust Servo Control for Vertical Electric Stabilization System of Tank and Experimental Validation

A tracking stability control problem for the vertical electric stabilization system of moving tank based on adaptive robust servo control is addressed.This paper mainly focuses on two types of possibly fast timevarying but bounded uncertainty within the vertical electric stabilization system:model parameter uncertainty and uncertain nonlinearity.First,the vertical electric stabilization system is constructed as an uncertain nonlinear dynamic system that can reflect the practical mechanics transfer process of the system.Second,the dynamical equation in the form of state space is established by designing the angular tracking error.Third,the comprehensive parameter of system uncertainty is designed to estimate the most conservative effects of uncertainty.Finally,an adaptive robust servo control which can effectively handle the combined effects of complex nonlinearity and uncertainty is proposed.The feasibility of the proposed control strategy under the practical physical condition is validated through the tests on the experimental platform.This paper pioneers the introduction of the internal nonlinearity and uncertainty of the vertical electric stabilization system into the settlement of the tracking stability control problem,and validates the advanced servo control strategy through experiment for the first time.