Search

A hierarchical learning control framework (HLF) has been validated on two affordable control laboratories: an active temperature control system (ATCS) and an electrical rheostatic braking system (EBS). The proposed HLF is data-driven and model-free, while being applicable on general control tracking tasks which are omnipresent. At the lowermost level, L1, virtual state-feedback control is learned from input–output data, using a recently proposed virtual state-feedback reference tuning (VSFRT) principle. L1 ensures a linear reference model tracking (or matching) and thus, indirect closed-loop control system (CLCS) linearization. On top of L1, an experiment-driven model-free iterative learning control (EDMFILC) is then applied for learning reference input–controlled outputs pairs, coined as primitives. The primitives' signals at the L2 level encode the CLCS dynamics, which are not explicitly used in the learning phase. Data reusability is applied to derive monotonic and safely guaranteed learning convergence. The learning primitives in the L2 level are finally used in the uppermost and final L3 level, where a decomposition/recomposition operation enables prediction of the optimal reference input assuring optimal tracking of a previously unseen trajectory, without relearning by repetitions, as it was in level L2. Hence, the HLF enables control systems to generalize their tracking behavior to new scenarios by extrapolating their current knowledge base. The proposed HLF framework endows the CLCSs with learning, memorization and generalization features which are specific to intelligent organisms. This may be considered as an advancement towards intelligent, generalizable and adaptive control systems. [ABSTRACT FROM AUTHOR]

This paper proposes the design and implementation of a model-free tire slip control for a fast and highly nonlinear Anti-lock Braking System (ABS). A reinforcement Q-learning optimal control approach is inserted in a batch neural fitted scheme using two neural networks to approximate the value function and the controller, respectively. The transition samples required for learning high performance control can be collected by interacting with the process either by online exploiting the current iteration controller (or policy) under an ε-greedy exploration strategy, or by using data collected under any other controller that is capable of ensuring efficient exploration of the action-state space. Both approaches are highlighted in the paper. Fortunately, the ABS process fits this type of learning-by-interaction because it does not need an initial stabilizing controller. The validation case studies conducted on a real laboratory setup reveal that high control system performance can be achieved using the proposed approaches. Insightful comments on the observed control behavior are offered along with performance comparisons with several types of model-based and model-free controllers including relay, model-based optimal PI, an original model-free neural network state-feedback VRFT controller and a model-free neural network adaptive actor-critic one. With the ability to improve control performance starting from different supervisory controllers or to learn high performance controllers from scratch, the proposed Q-learning optimal control approach proves its performance in a wide operating range and is therefore recommended to its industrial application on ABS. [ABSTRACT FROM AUTHOR]

This paper proposes the combination of two model-free controller tuning techniques, namely linear virtual reference feedback tuning (VRFT) and nonlinear state-feedback Q-learning, referred to as a new mixed VRFT-Q learning approach. VRFT is first used to find stabilising feedback controller using input-output experimental data from the process in a model reference tracking setting. Reinforcement Q-learning is next applied in the same setting using input-state experimental data collected under perturbed VRFT to ensure good exploration. The Q-learning controller learned with a batch fitted Q iteration algorithm uses two neural networks, one for the Q-function estimator and one for the controller, respectively. The VRFT-Q learning approach is validated on position control of a two-degrees-of-motion open-loop stable multi input-multi output (MIMO) aerodynamic system (AS). Extensive simulations for the two independent control channels of the MIMO AS show that the Q-learning controllers clearly improve performance over the VRFT controllers. [ABSTRACT FROM AUTHOR]

This paper suggests a novel three-level model-free hierarchical learning approach that solves the reference trajectory tracking problem for control systems (CSs). The new approach consists of the low level, the intermediate level and the high level, it relies on past memorized optimal input output execution patterns and adaptively merges them using a similarity measure. The low level feedback control is carried out in a novel model-free framework using a neural network (NN) controwller tuned by Virtual Reference Feedback Tuning (VRFT) in order to linearize the closed-loop CS and to match a linear reference model. The NN controller is tuned in two phases, an offline one and an online one. Nonlinear Model Predictive Control (NMPC) is first employed in the novel offline tuning phase. The online tuning phase makes next use only of the process sign in the dynamic back-propagation mechanism that updates the NN parameters. After the NN controller is trained and the feedback CS is fixed, the optimal execution patterns (input/output patterns) are defined in terms of optimal control problems, which balance control accuracy and control effort. The input/output patterns are formulated over a feedback CS and are solved in a model-free Iterative Learning Control (ILC) framework for linear time-invariant systems at the intermediate level. Once the optimal executions are learned at the intermediate level over the feedback CS, they are stored in a database (DB). Then each time a new trajectory is to be tracked as required by the high level planner, similar patterns of executions are looked-up in the DB and are merged by the weighted average sum of most similar patterns resulted from a sort algorithm using a distance metric. The proposed approach is tested on the position control of a Single Input-Single Output nonlinear aerodynamic control system and shows trajectory tracking performance improvement with respect to the case when no learnt experience is used. [ABSTRACT FROM AUTHOR]

This study proposes data‐driven model‐free adaptive control (MFAC), model‐free control (MFC) and virtual reference feedback tuning (VRFT) techniques applied to the control of a representative non‐linear multi‐input–multi‐output (MIMO) system represented by the twin rotor aerodynamic system (TRAS). These data‐driven techniques are implemented for both a single MIMO controller and two separately designed single‐input–single‐output controllers running in parallel for azimuth and pitch control. The three techniques are implemented as MFAC and MFC algorithms and as linear controllers tuned by VRFT. The performance of the three data‐driven MIMO control system structures is compared systematically on the basis of the experimental results in terms of the values of the sum of mean squared control errors measured on TRAS equipment. [ABSTRACT FROM AUTHOR]

This paper presents the design and experimental validation of a new model-free data-driven iterative reference input tuning (IRIT) algorithm that solves a reference trajectory tracking problem as an optimization problem with control signal saturation constraints and control signal rate constraints. The IRIT algorithm design employs an experiment-based stochastic search algorithm to use the advantages of iterative learning control. The experimental results validate the IRIT algorithm applied to a non-linear aerodynamic position control system. The results prove that the IRIT algorithm offers the significant control system performance improvement by few iterations and experiments conducted on the real-world process and model-free parameter tuning. [ABSTRACT FROM PUBLISHER]

This study proposes a data‐based model‐free approach to reference trajectory tracking in two‐degree‐of‐freedom non‐linear control system (CS) structures. This model‐free control approach tunes both the feedback controller parameters and the reference input sequence accounting for control saturation and control rate constraints. The controller is iteratively tuned in a non‐linear framework that employs a gradient descent search approach. The model‐free gradient estimates are obtained by a perturbation‐based approach. The reference input tuning is carried out in a linear framework using an iterative learning control‐based approach, and it also includes a model‐free gradient search algorithm where the gradient estimates are obtained by a similar perturbation‐based approach. The number of real‐world experiments is significantly reduced by the use of simulated models identified as neural networks. A digitally simulated case study concerning the angular position control of a non‐linear aerodynamic twin‐rotor system shows that the author's approach can effectively improve the CS performance. [ABSTRACT FROM AUTHOR]

This paper presents a new iterative data-driven algorithm (IDDA) for the experiment-based tuning of controllers for nonlinear systems. The proposed IDDA solves the optimization problems for nonlinear processes while using linear controllers accounting for operational constraints and employing a quadratic penalty function approach. The search algorithm employs first-order gradient information obtained from neural-network-based process models to reduce the number of experiments needed to run on real-world processes. A data-driven controller tuning for the angular position control of a nonlinear aerodynamic system is used as an experimental case study to validate the proposed IDDA. [ABSTRACT FROM PUBLISHER]

A general control system tracking learning framework is proposed, by which an optimal learned tracking behavior called 'primitive' is extrapolated to new unseen trajectories without requiring relearning. This is considered intelligent behavior and strongly related to the neuro-motor cognitive control of biological (human-like) systems that deliver suboptimal executions for tasks outside of their current knowledge base, by using previously memorized experience. However, biological systems do not solve explicit mathematical equations for solving learning and prediction tasks. This stimulates the proposed hierarchical cognitive-like learning framework, based on state-of-the-art model-free control: (1) at the low-level L1, an approximated iterative Value Iteration for linearizing the closed-loop system (CLS) behavior by a linear reference model output tracking is first employed; (2) an experiment-driven Iterative Learning Control (EDILC) applied to the CLS from the reference input to the controlled output learns simple tracking tasks called 'primitives' in the secondary L2 level, and (3) the tertiary level L3 extrapolates the primitives' optimal tracking behavior to new tracking tasks without trial-based relearning. The learning framework relies only on input-output system data to build a virtual state space representation of the underlying controlled system that is assumed to be observable. It has been shown to be effective by experimental validation on a representative, coupled, nonlinear, multivariable real-world system. Able to cope with new unseen scenarios in an optimal fashion, the hierarchical learning framework is an advance toward cognitive control systems. [ABSTRACT FROM AUTHOR]

In this paper, a novel Virtual State-feedback Reference Feedback Tuning (VSFRT) and Approximate Iterative Value Iteration Reinforcement Learning (AI-VIRL) are applied for learning linear reference model output (LRMO) tracking control of observable systems with unknown dynamics. For the observable system, a new state representation in terms of input/output (IO) data is derived. Consequently, the Virtual State Feedback Tuning (VRFT)-based solution is redefined to accommodate virtual state feedback control, leading to an original stability-certified Virtual State-Feedback Reference Tuning (VSFRT) concept. Both VSFRT and AI-VIRL use neural networks controllers. We find that AI-VIRL is significantly more computationally demanding and more sensitive to the exploration settings, while leading to inferior LRMO tracking performance when compared to VSFRT. It is not helped either by transfer learning the VSFRT control as initialization for AI-VIRL. State dimensionality reduction using machine learning techniques such as principal component analysis and autoencoders does not improve on the best learned tracking performance however it trades off the learning complexity. Surprisingly, unlike AI-VIRL, the VSFRT control is one-shot (non-iterative) and learns stabilizing controllers even in poorly, open-loop explored environments, proving to be superior in learning LRMO tracking control. Validation on two nonlinear coupled multivariable complex systems serves as a comprehensive case study. [ABSTRACT FROM AUTHOR]

This paper presents the performance of two sliding mode control algorithms, based on the Lyapunov-based sliding mode controller (LSMC) and reaching-law-based sliding mode controller (RSMC), with their novel variants designed and applied to the anti-lock braking system (ABS), which is known to be a strongly nonlinear system. The goal is to prove their superior performance over existing control approaches, in the sense that the LSMC and RSMC do not bring additional computational complexity, as they rely on a reduced number of tuning parameters. The performance of LSMC and RSMC solves the uncertainty in the process model which comes from unmodeled dynamics and a simplification of the actuator dynamics, leading to a reduced second order process. The contribution adds complete design details and stability analysis is provided. Additionally, performance comparisons with several adaptive, neural networks-based and model-free sliding mode control algorithms reveal the robustness of the proposed LSMC and RSMC controllers, in spite of the reduced number of tuning parameters. The robustness and reduced computational burden of the controllers validated on the real-world complex ABS make it an attractive solution for practical industrial implementations. [ABSTRACT FROM AUTHOR]

Learning Output Reference Model Tracking for Higher-order Nonlinear Systems with Unknown Dynamics. The Value Iteration (VI) algorithm ensures model-free nonlinear state feedback controller learning, without relying on the process dynamics. Herein, we find that, given a transition sample dataset and a general linear parameterization of the Q-function, the ORM tracking performance obtained with an approximate VI scheme can reach the performance level of a more general implementation using neural networks (NNs). [Extracted from the article]

Linearly and nonlinearly parameterized approximate dynamic programming approaches used for output reference model (ORM) tracking control are proposed. The ORM tracking problem is of significant interest in practice since, with a linear ORM, the closed-loop control system is indirectly feedback linearized and value iteration (VI) offers the means to achieve ORM tracking without using process dynamics. Ranging from linear to nonlinear parameterizations, a successful approximate VI implementation for continuous state-action spaces depends on several key parameters such as: problem dimension, exploration of the state-action space, the state-transitions dataset size, and suitable selection of the function approximators. We show that using the same transitions dataset and under a general linear parameterization of the Q-function, high performance ORM tracking can be achieved with an approximate VI scheme, on the same performance level as that of a neural-network (NN)-based implementation that is more complex and takes significantly more time to learn. However, the latter proves to be more robust to hyperparameters selection, dataset size, and to exploration strategies, recommending it as the de facto practical implementation. The case study is aimed at ORM tracking of a real-world nonlinear two inputs–two outputs aerodynamic process with ten internal states, as a representative high order system. [ABSTRACT FROM AUTHOR]

This paper focuses on validating a model-free Value Iteration Reinforcement Learning (MFVI-RL) control solution on a visual servo tracking system in a comprehensive manner starting from theoretical convergence analysis to detailed hardware and software implementation. Learning is based on a virtual state representation reconstructed from input-output (I/O) system samples under nonlinear observability and unknown dynamics assumptions, while the goal is to ensure linear output reference model (ORM) tracking. Secondary, a competitive model-free Virtual State-Feedback Reference Tuning (VSFRT) is learned from the same I/O data using the same virtual state representation, demonstrating the framework's learning capability. A model-based two degrees-of-freedom (2DOF) output feedback controller serving as a comparisons baseline is designed and tuned using an identified system model. With similar complexity and linear controller structure, MFVI-RL is shown to be superior, confirming that the model-based design issue of poor identified system model and control performance degradation can be solved in a direct data-driven style. Apart from establishing a formal connection between output feedback control, state feedback control and also between classical control and artificial intelligence methods, the results also point out several practical trade-offs, such as I/O data exploration quality and control performance leverage with data volume, control goal and controller complexity. [ABSTRACT FROM AUTHOR]

This paper discusses an experiment-based approach to teaching an advanced control engineering syllabus involving controlled plant analysis and modeling, control structures and algorithms, real-time laboratory experiments, and their assessment. These experiments are structured around the representative case of the longitudinal slip control of an antilock braking system (ABS). The basic and advanced control strategies that are experimentally studied include the proportional-integral (PI) control, gain scheduling, iterative feedback tuning (IFT) and fuzzy control. The final grades obtained by representative groups of students demonstrate the efficiency of a described hands-on laboratory experimental study of a complex antilock braking system as encountered in practice, which allowed students to gain a better understanding of the theoretical aspects learned during the lectures . [ABSTRACT FROM AUTHOR]

The problem of classification for imbalanced datasets is frequently encountered in practical applications. The data to be classified in this problem are skewed, i.e., the samples of one class (the minority class) are much less than those of other classes (the majority class). When dealing with imbalanced datasets, most classifiers encounter a common limitation, that is, they often obtain better classification performances on the majority classes than those on the minority class. To alleviate the limitation, in this study, a fuzzy rule-based modeling approach using information granules is proposed. Information granules, as some entities derived and abstracted from data, can be used to describe and capture the characteristics (distribution and structure) of data from both majority and minority classes. Since the geometric characteristics of information granules depend on the distance measures used in the granulation process, the main idea of this study is to construct information granules on each class of imbalanced data using Minkowski distance measures and then to establish the classification models by using "If-Then" rules. The experimental results involving synthetic and publicly available datasets reflect that the proposed Minkowski distance-based method can produce information granules with a series of geometric shapes and construct granular models with satisfying classification performance for imbalanced datasets. [ABSTRACT FROM AUTHOR]

This paper presents theoretical and application results concerning the development of evolving Takagi-Sugeno-Kang fuzzy models for two dynamic systems, which will be viewed as controlled processes, in the field of automotive applications. The two dynamic systems models are nonlinear dynamics of the longitudinal slip in the Antilock Braking Systems (ABS) and the vehicle speed in vehicles with the Continuously Variable Transmission (CVT) systems. The evolving Takagi-Sugeno-Kang fuzzy models are obtained as discrete-time fuzzy models by incremental online identification algorithms. The fuzzy models are validated against experimental results in the case of the ABS and the first principles simulation results in the case of the vehicle with the CVT. [ABSTRACT FROM AUTHOR]

This paper discusses the design of fuzzy control systems (FCSs) with a reduced parametric sensitivity using simulated-annealing (SA) algorithms. Four generic families of objective functions expressed as integral quadratic performance indexes, which depend on the control error and squared output sensitivity functions, are suggested. SA algorithms are employed to minimize the objective functions in the appropriately defined optimization problems. A design method for Takagi–Sugeno proportional–integral fuzzy controllers (PI-FCs) is proposed. The resulting PI-FCs are intended for a class of plants characterized by second-order linearized models with integral component. A case study dealing with the angular position control of a dc servo system is used as test bed to validate the proposed new controller design. Experimental results illustrate the FCS performance. [ABSTRACT FROM PUBLISHER]

In this paper, a proposed algorithm that dynamically changes the neural network structure is presented. The structure is changed based on some features in the cascade correlation algorithm. Cascade correlation is an important algorithm that is used to solve the actual problem by artificial neural networks as a new architecture and supervised learning algorithm. This process optimizes the architectures of the network which intends to accelerate the learning process and produce better performance in generalization. Many researchers have to date proposed several growing algorithms to optimize the feedforward neural network architectures. The proposed algorithm has been tested on various medical data sets. The results prove that the proposed algorithm is a better method to evaluate the accuracy and flexibility resulting from it. [ABSTRACT FROM AUTHOR]

Person re-Identification(Re-ID) based on deep convolutional neural networks (CNNs) achieves remarkable success with its fast speed. However, prevailing Re-ID models are usually built upon backbones that manually design for classification. In order to automatically design an effective Re-ID architecture, we propose a pedestrian re-identification algorithm based on knowledge distillation, called KDAS-ReID. When the knowledge of the teacher model is transferred to the student model, the importance of knowledge in the teacher model will gradually decrease with the improvement of the performance of the student model. Therefore, instead of applying the distillation loss function directly, we consider using dynamic temperatures during the search stage and training stage. Specifically, we start searching and training at a high temperature and gradually reduce the temperature to 1 so that the student model can better learn from the teacher model through soft targets. Extensive experiments demonstrate that KDAS-ReID performs not only better than other state-of-the-art Re-ID models on three benchmarks, but also better than the teacher model based on the ResNet-50 backbone. [ABSTRACT FROM AUTHOR]

This paper studies a novel intelligent motion control algorithm for Autonomous Underwater Vehicles (AUV) and develops a virtual reality system for a new interactive experimental platform. The paper designs a robust neuro-fuzzy controller to tackle system uncertainties and external disturbances. Fuzzy control can solve the uncertainty problem of control systems. The neural network model self-tunes the controller parameters to improve the anti-interference ability. The designed control algorithm is verified using a MATLAB implementation and a virtual reality system. The virtual reality system developed in this paper can be used to debug the control algorithm, simulate the marine environment, and establish an ocean current interference model. The paper uses the MATLAB engine to realize the data communication between the MATLAB and the AUV virtual reality system. This allows the output order of the controller in MATLAB to drive the AUV in a virtual simulation system to simulate the 3D space motion. [ABSTRACT FROM AUTHOR]

Autonomous vehicles require fleet-wide data collection for continuous algorithm development and validation. The smart black box (SBB) intelligent event data recorder has been proposed as a system for prioritized high-bandwidth data capture. This paper extends the SBB by applying anomaly detection and action detection methods for generalized event-of-interest (EOI) detection. An updated SBB pipeline is proposed for the real-time capture of driving video data. A video dataset is constructed to evaluate the SBB on real-world data for the first time. SBB performance is assessed by comparing the compression of normal and anomalous data and by comparing our prioritized data recording with an FIFO strategy. The results show that SBB data compression can increase the anomalous-to-normal memory ratio by ∼25%, while the prioritized recording strategy increases the anomalous-to-normal count ratio when compared to an FIFO strategy. We compare the real-world dataset SBB results to a baseline SBB given ground-truth anomaly labels and conclude that improved general EOI detection methods will greatly improve SBB performance. [ABSTRACT FROM AUTHOR]