Search

The task of patrolling,seed sowing and industrial production of wheeled robots is a strongly nonlinear intermittent process.In this paper,a data-driven high-order iterative learning control algorithm is proposed for the path tracking of wheeled mobile robots in repeated running scenes.First,the model of wheeled mobile robot is derived and designed,and the discrete-time model in state space is transformed into linear input/ output data model by using iterative dynamic linearization method based on state transition.Second,a high-order iterative optimization objective function is designed to obtain the control law,and the parameter update law is used to estimate the unknown parameters in the linear data model. By using high order learning control method,more control input information of previous iteration is used in the control law to improve the control performance.Finally,the simulation results verify the effectiveness of this method in the trajectory tracking control of wheeled robot. [ABSTRACT FROM AUTHOR]

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In this article, an adaptive robust iterative learning control is developed to solve the trajectory tracking problem of a parallel Delta robot performing repetitive tasks and subjected to external disturbances. The proposed control scheme is composed of an adaptive proportional–derivative controller to increase the convergence rate, a proportional–derivative-type iterative learning control to enhance the tracking performances through the repetitive trajectory as well as a robust term to compensate the repetitive and nonrepetitive disturbances. The practical assumption of alignment condition is introduced instead of the classical assumption of resetting conditions. The asymptotic convergence is proved using Lyaponuv analysis, and it is shown that the tracking error decreases through the iterations. Simulation and experiments are performed on a Delta robot to demonstrate the effectiveness and the superiority of the proposed controller over the traditional iterative learning control. [ABSTRACT FROM AUTHOR]

Background: The Lancet Global Health Commission (LGHC) has argued that quality of care (QoC) is an emergent property that requires an iterative process to learn and implement. Such iterations are required given that health systems are complex adaptive systems. Objective: This paper explores the multiple roles that evaluations need to play in order to help with iterative learning and implementation. We argue evaluation needs to shift from a summative focus toward an approach that promotes learning in complex systems. A framework is presented to help guide the iterative learning, and includes the dimensions of clinical care, person-centered care, continuum of care, and 'more than medicine. Multiple roles of evaluation corresponding to each of the dimensions are discussed. Methods: This paper is informed by reviews of the literature on QoC and the roles of evaluation in complex systems. The proposed framework synthesizes the multiple views of QoC. The recommendations of the roles of evaluation are informed both by review and experience in evaluating multiple QoC initiatives. Results: The specific roles of different evaluation approaches, including summative, realist, developmental, and participatory, are identified in relationship to the dimensions in our proposed framework. In order to achieve the potential of LGHC, there is a need to discuss how different evaluation approaches can be combined in a coherent way to promote iterative learning and implementation of QoC initiatives. Conclusion: One of the implications of the QoC framework discussed in the paper is that time needs to be spent upfront in recognizing areas in which knowledge of a specific intervention is not complete at the outset. This, of course, implies taking stock of areas of incompleteness in knowledge of context, theory of change, support structures needed in order for the program to succeed in specific settings. The role of evaluation should not be limited to only providing an external assessment, but an important goal in building evaluation capacity should be to promote adaptive management among planners and practitioners. Such iterative learning and adaptive management are needed to achieve the goals of sustainable development goals. [ABSTRACT FROM AUTHOR]

Gullies are landforms with specific patterns of shape, topography, hydrology, vegetation, and soil characteristics. Remote sensing products (TanDEM-X, Sentinel-1, and Sentinel-2) serve as inputs into an iterative algorithm, initialized using a micro-mapping simulation as training data, to map gullies in the northwestern of Namibia. A Random Forest Classifier examines pixels with similar characteristics in a pool of unlabeled data, and gully objects are detected where high densities of gully pixels are enclosed by an alpha shape. Gully objects are used in subsequent iterations following a mechanism where the algorithm uses the most reliable pixels as gully training samples. The gully class continuously grows until an optimal scenario in terms of accuracy is achieved. Results are benchmarked with manually tagged gullies (initial gully labeled area <0.3% of the total study area) in two different watersheds (408 and 302 km2, respectively) yielding total accuracies of >98%, with 60% in the gully class, Cohen Kappa >0.5, Matthews Correlation Coefficient >0.5, and receiver operating characteristic Area Under the Curve >0.89. Hence, our method outlines gullies keeping low false-positive rates while the classification quality has a good balance for the two classes (gully/no gully). Results show the most significant gully descriptors as the high temporal radar signal coherence (22.4%) and the low temporal variability in Normalized Difference Vegetation Index (21.8%). This research builds on previous studies to face the challenge of identifying and outlining gully-affected areas with a shortage of training data using global datasets, which are then transferable to other large (semi-) arid regions. [ABSTRACT FROM AUTHOR]

Recently, a method called Meta-SR has solved the problem of super-resolution of arbitrary scale factor with only one single model. However, it has a limited reconstruction accuracy compared with RDN + and EDSR +. Inspired by Meta-SR, we noticed that by combining the core idea of Meta-SR and D-DBPN, we might construct a network that has as good image reconstruction accuracy as D-DBPN's, at the same time, keeps arbitrary scaling function. According to Meta-SR's Meta-Upscale Module, we designed a different structure called Meta-Downscale Module. By using these two different modules and back-projection structure, we construct an arbitrary back-projection network, which has the ability to enlarge images with arbitrary scale factor by using only one single model, meanwhile, obtains state-of-the-art reconstruction results. Through extensive experiments, our proposed method performs better reconstruction effect than Meta-SR and more efficient than D-DBPN. Besides that, we also evaluated the proposed method on widely used benchmark dataset on single image super-resolution. The experimental results show the superiority of our model compared to RDN+ and EDSR+. [ABSTRACT FROM AUTHOR]

Nonlinearities, uncertainties and external disturbances commonly exist in a wastewater treatment process (WWTP). Those issues present great challenges to the control of the dissolved oxygen (DO) concentration in a WWTP. In this paper, an active disturbance rejection control (ADRC) is utilized to estimate the total disturbance and drive the DO concentration to track the set-value. Simultaneously, an iterative learning strategy is employed to adjust the parameters of an extended state observer (ESO) to improve the accuracy of the estimation and reduce the dependence on experience in determining parameters. By combining the advantages of the ADRC and the iterative learning strategy, an iterative learning based active disturbance rejection control (ILADRC) is constructed, and the close-loop stability is analyzed. The benchmark simulation model No.1 (BSM1) is utilized to confirm the ILADRC. Numerical results show that the ILADRC is more effective in the DO concentration control. [ABSTRACT FROM AUTHOR]

Summary: This article is concerned with the tracking of nonequilibrium motions with model predictive control (MPC). It proposes to parametrize input and state trajectories of a dynamic system with basis functions to alleviate the computational burden in MPC. As a result of the parametrization, an optimization problem with fewer variables is obtained, and the memory requirements for storing the reference trajectories are reduced. The article also discusses the generation of feasible reference trajectories that account for the system's dynamics, as well as input and state constraints. In order to cope with repeatable disturbances, which may stem from unmodeled dynamics for example, an iterative learning procedure is included. The approach relies on a Kalman filter that identifies the repeatable disturbances based on previous trials. These are then included in the system's model available to the model predictive controller, which compensates them in subsequent trials. The proposed approach is evaluated on a quadcopter, whose task is to balance a pole, while flying a predefined trajectory. [ABSTRACT FROM AUTHOR]

Non-holonomic path planning is to solve the two point boundary value problem under constraints. Since it is offline and open-loop, the path planning cannot compensate for the disturbances and eliminate the errors. To solve the problems, this paper puts forward an iterative learning control algorithm that adjusts the control parameters of the path planner online through the multiple iterative computations of the target configuration error equation, under the initial configuration error and model error, and thus enhancing the accuracy of non-holonomic system path planning. Then, a simulation experiment on path planning was carried out for a chainable three-joint, non-holonomic manipulator. The results show that the iterative learning controller can eliminate the interference of initial configuration error and model error, such that each joint can move to the target configuration. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

We respond to the consensus control algorithms for second-order non-linear MAS with unknown control gains in the finite time interval by adopting iterative learning control (ILC) methods in this paper. Compared to the current findings, the control gains in the proposed method are unknown functions with unknown and non-identical signs. The topology graph between the follower agents is an undirected connected graph. By referencing the Nussbaum-type function and the neural networks, the adaptive control algorithms are intended to cope with the consensus control between the agents on the limited time interval. Simulation results illustrate the efficacy of the raised algorithms. [ABSTRACT FROM AUTHOR]

Active learning algorithms attempt to overcome the labeling bottleneck by asking queries from large collection of unlabeled examples. Existing batch mode active learning algorithms suffer from three limitations: (1) The methods that are based on similarity function or optimizing certain diversity measurement, in which may lead to suboptimal performance and produce the selected set with redundant examples. (2) The models with assumption on data are hard in finding images that are both informative and representative. (3) The problem of noise labels has been an obstacle for algorithms. In this paper, we propose a novel active learning method that makes embeddings of labeled examples to those of unlabeled ones and back via deep neural networks. The active scheme makes correct association cycles that end up at the same class from that the association was started, which considers both the informativeness and representativeness of examples, as well as being robust to the noise labels. We apply our active learning method to semi-supervised classification and clustering. The submodular function is designed to reduce the redundancy of the selected examples. Specifically, we incorporate our batch mode active scheme into the classification approaches, in which the generalization ability is improved. For semi-supervised clustering, we try to use our active scheme for constraints to make fast convergence and perform better than unsupervised clustering. Finally, we apply our active learning method to data filtering. To validate the effectiveness of the proposed algorithms, extensive experiments are conducted on diversity benchmark datasets for different tasks, i.e., classification, clustering, and data filtering, and the experimental results demonstrate consistent and substantial improvements over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Information & Control is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Path tracking control cannot effectively satisfy the stability requirements of intelligent vehicles under large curvature conditions. To solve this problem, an adaptive preview distance path tracking controller with a hierarchical structure is proposed in this study. The vehicle centroid lateral acceleration and lateral error of the preview point are taken as the inputs of the upper controller, and the optimal preview distance is obtained based on fuzzy inference. To eliminate the subjective influence of the membership function and fuzzy rule selection in the fuzzy controller design, a genetic algorithm is used for optimization. The lower controller is a sliding mode controller that aims to achieve intelligent vehicle self-tracking. Moreover, a radial basis function neural network is adopted to combine with the sliding mode controller to eliminate output chattering. However, adaptive adjustment of the preview distance deteriorates the vehicle directional tracking error, which makes controlling the vehicle at the road curvature switching point difficult. Thus, a directional error compensation controller is designed based on the iterative learning theory to compensate the front wheel steering angle. Simulations under two standard conditions are carried out to verify the control effect. The results show that, in a double lane change test, the peak centroid acceleration and coaxial load transfer rates decreased by 26.91% and 19.83% at low velocity, respectively, and the improvements at high velocity were 42.71% and 39.22%, respectively. In the pylon course slalom test, all three performance indicators decreased by more than 30%, which indicates the modified adaptive preview distance path tracking controller with a hierarchical structure can effectively improve the vehicle handling performance and roll stability and can ensure the tracking accuracy. [ABSTRACT FROM AUTHOR]

In recent years, investments in cybersecurity capabilities (C C) have emerged as an essential practice in reducing cyberattacks and optimizing the usage of technologies. Therefore, optimal investments in capabilities must be determined according to the cybersecurity scenario of firms. This experiment pursues an understanding of the effectiveness of the iterative learning process in investments in C C. Through a simulator game, experienced and inexperienced participants overcome challenges related to uncertainties of cyber incidents to decision-making in cybersecurity capability investments. The collected data were empirically tested from 119 participants analyzing 3,808 simulation runs. The findings demonstrated that there is a slight difference in the learning curve between the two groups even if they learn proactively and iteratively. However, experienced, and inexperienced groups did not demonstrate enough capacity to analyze the cybersecurity ecosystems designed in the simulator game to mitigate cyber incidents. Both groups exhibited similar results regarding gaps to invest in C C to address uncertainties associated with cyber threats. In this sense, this experiment highlights the relevance of learning about C C investments in any context to avoid resource losses and time to uncover the complexities related to incident responses. • Simulator game demonstrated good acceptance among participants. • Cybersecurity capabilities investments might be learnt proactively and iteratively. • There is a slight difference in the learning curve between experience and inexperience groups. • Experience and inexperience groups did not demonstrate knowledge in cybersecurity capabilities to mitigate cyber incidents. • Participants did not demonstrate knowledge in the relationship between cybersecurity capabilities and technological ecosystem. [ABSTRACT FROM AUTHOR]

In this study, vibration control, a behavior which subordinates to stall-induced nonlinear vibration and amplitude control of a wind turbine’s blade section, based on unified pitch motion driven by slider-linkage mechanism, is investigated by using an iterative learning control (ILC) method. The nonlinear dynamical system is a nonlinear aeroelastic system. The aeroelastic system equations consist of three parts: the nonlinear structural equations derived by using Lagrange’s equations, the improved stall-induced nonlinear ONERA (ISNO) aerodynamic equations, and the pitch control equation. The ISNO model is not only suitable for the actual external pitch motion, but also suitable for the solution by using an ILC algorithm due to its fitted nonlinear aerodynamic coefficients. The ILC algorithm used here is an improved iterative learning algorithm (IILC) which considers the large-range, linearized, residual terms, and realizes gain adaptive tuning based on PID controller. On the one hand, it can control the amplitude of an unsteady flutter through trajectory tracking. On the other hand, when the preset value of the amplitude of the ideal trajectory is very small, it can make the system directly tend to convergence and stability of a nonlinear aeroelastic system. To simplify the extremely difficult iterative process, the pitch movement can track the elastic twist displacement in time, thus simplifying the aeroelastic equations and accelerating the IILC iteration process. Therefore, amplitude control for flap-wise/lead-lag displacements is realized by the unified pitch motion and the trajectory tracking controlled by using the IILC algorithm.

In this article, we propose a recent iterative learning algorithm for sensor data fusion to detect pitch actuator failures in wind turbines. The development of this proposed approach is based on iterative learning control and Lyapunov’s theories. Numerical experiments were carried out to support our main contribution. These experiments consist of using a well-known wind turbine hydraulic pitch actuator model with some common faults, such as high oil content in the air, hydraulic leaks, and pump wear.

In order to meet the rigorous motion accuracy requirement and efficiently utilize the repetitive-task characteristics in modern precision industry, this paper concentrates on the comprehensive research of model-based data-driven learning adaptive robust control (LARC) strategy for precision mechatronic motion systems. The proposed LARC can achieve not only excellent transient/steady-state tracking performance but also adaptation ability and disturbance robustness. Specifically, the LARC strategy contains robust feedback term, adaptive model compensation term, and iterative learning term. Herein, the former two terms are designed based on the system dynamic model under parametric uncertainty and uncertain nonlinearity, and the data-driven iterative learning term is synthesized to generate optimal input to adjust the optimal reference. The whole controller design procedure and stability is presented, while the reason for the practically achievable performance of LARC is analyzed. Comparative experiments, among proportional-integral-differential, adaptive robust control, iterative learning control, and the proposed LARC, are conducted on a developed linear motor stage. The experimental results consistently validate that the proposed LARC scheme simultaneously achieves excellent transient/steady-state tracking performance, parametric adaptation ability, and disturbance robustness. The LARC strategy essentially provides an effective control technology with good potential in industrial applications.

Conclusive evidence has demonstrated the critical importance of adaptive cruise control (ACC) in relieving traffic congestion. To improve the performance of the ACC system, this paper proposes a novel ACC strategy for electric vehicles based on a hierarchical framework. Three main efforts have been made to distinguish our work from the existing research. Firstly, a sliding acceleration identification model is established based on the recursive least squares algorithm with multiple forgetting factors (MFF-RLS). Secondly, with vehicle following, economy, and comfort as the optimization objectives, the upper-level controller is developed based on the model predictive control (MPC) algorithm. Benefit from the identification of the sliding acceleration, the MPC controller holds better capability in accommodating environmental changes. Thirdly, an iterative learning lower-level controller is designed to control the driving and braking systems. Considering the efficiency of regenerative braking, the braking force distribution strategy is also designed in the lower-level controller. Simulation results show that, compared with the conventional MPC-based ACC strategy, the proposed strategy has similar performance in vehicle following, but it makes great improvements in comfort and economy. The specific features are that the vehicle acceleration and speed fluctuation are significantly reduced, and the energy consumption is also reduced by 2.05%.

In this paper, an anthropomorphic arm is introduced and used to the upper-limb passive rehabilitation therapy. The anthropomorphic arm is constructed via pneumatic artificial muscles so that it may assist patients suffering upper-limb diseases to achieve mild therapeutic exercises. Due to the uncertain dynamic environment, external disturbances and model uncertainties, a combined control is proposed to stabilize and to enhance the adaptivity of the system. In the combined control, an iterative learning control is used to realize accurate position tracking. Meanwhile, an adaptive iterative learning based impedance control is proposed to execute the appropriate contact force during the therapy of the upper-limb. The advantage of the combined control is that it doesn't depend on the accurate model of systems and it may deal with highly nonlinear system which has strong coupling and redundancies. The convergence of the proposed control is analyzed in detail. Numerical simulations are performed to verify the proposed control method. In addition, real experiments are executed on the Southwest anthropomorphic arm.

This paper has dealt with a tracking control problem for a class of unstable reaction–diffusion system with time delay. Iterative learning algorithms are introduced to make the infinite-dimensional repetitive motion system track the desired trajectory. A new Lyapunov–Krasovskii functional is constructed to deal with the time-delay system. Picewise distribution functions are applied in this paper to perform piecewise control operations. By using Poincaré–Wirtinger inequality, Cauchy–Schwartz inequality for integrals and Young’s inequality, the convergence of the system with time delay using iterative learning schemes is proved. Numerical simulation results have verified the effectiveness of the proposed method.

Summary: In this paper, we explore how to get the information of input‐output coupling parameters (IOCPs) for a class of uncertain discrete‐time systems by using iterative learning technique. Firstly, by taking advantage of repetitiveness of control system and informative input and output data, we design an iterative learning scheme for unknown IOCPs. It is shown that we can get the exact values of IOCPs one by one through running the repetitive system T+1 times if the control system is with identical initial state and noise free. Secondly, we give the iterative learning scheme for unknown IOCPs in the presence of measurement noise, system noise, or initial state drift and analyze the influence factors on the performance of developed iterative learning scheme. Meanwhile, we introduce the maximum allowable control deviation into the iterative learning mechanism to minimize the negative impact of noise on the performance of learning scheme and to enhance the robust of iterative learning scheme. Thirdly, for a class of multiple‐input–multiple‐output systems, we also develop iterative learning mechanism for unknown input‐output coupling matrices. Finally, an illustrative example is given to demonstrate the effectiveness of proposed iterative learning scheme. [ABSTRACT FROM AUTHOR]

In order to leverage the information embedded in the background state and observations, covariance matrices modelling is a pivotal point in data assimilation algorithms. These matrices are often estimated from an ensemble of observations or forecast differences. Nevertheless, for many industrial applications the modelling still remains empirical based on some form of expertise and physical constraints enforcement in the absence of historical observations or predictions. We have developed two novel robust adaptive assimilation methods named Covariance Updating iTerativE and Partially Updating BLUE. These two non-parametric methods are based on different optimization objectives, both capable of sequentially adapting background error covariance matrices in order to improve assimilation results under the assumption of a good knowledge of the observation error covariances. We have compared these two methods with the standard approach using a misspecified background matrix in a shallow water twin experiments framework with a linear observation operator. Numerical experiments have shown that the proposed methods bear a real advantage both in terms of posterior error correlation identification and assimilation accuracy. [ABSTRACT FROM AUTHOR]

This paper presents the development and field validation of an iterative learning-based admittance control algorithm for autonomous excavation in fragmented rock using robotic wheel loaders. An admittance control strategy is augmented with iterative learning, which automatically updates control parameters based on the error between a target bucket fill weight and the measured fill weight at the end of each excavation pass. The algorithm was validated through full-scale autonomous excavation experiments with a 14-tonne capacity load-haul-dump (LHD) machine and two different types of excavation materials: fragmented rock and gravel. In both excavation scenarios, the iterative learning algorithm is able to update the admittance control parameters for a specified target bucket fill weight, eliminating the need to manually re-tune control parameters as material characteristics change. These results have practical significance for increasing the autonomy of robotic wheel loaders used in mining and construction. [ABSTRACT FROM AUTHOR]

In order to realize a high-precision end trajectory tracking control of lower limb rehabilitation robots in the process of rehabilitation training, we propose a robust adaptive control method based on iterative learning with advanced sampling time. The iterative algorithm with advanced sampling time uses the torque output of the hip and knee joint of the previous running batch at the sampling time t +Δ, and optimizes the adjustment of the joint torque at the next running time t. Simulation results show that with the help of the iterative control with advanced sampling time, the end trajectory error has faster convergence speed, higher tracking accuracy, and better anti-interference performance. [ABSTRACT FROM AUTHOR]

This paper describes the design, industrial application, and field testing of a technique for autonomous wheeled‐vehicle path following that uses iterative learning control (ILC) in a feedback linearized space. One advantage of this approach is that ILC is used without having to employ approximate linearization at every time step. The main contribution of this paper is the unique field experiments that used two large industrial‐scale center‐articulated underground mining vehicles. The described field work not only tested the underlying technique on commercial vehicles, but also presents a method for parallel speed learning, wherein the speed is adjusted over subsequent learning trials to improve cycle productivity. Finally, presented are field results for an approach to prelearning through simulation before deployment in the field to reduce the initial path‐following errors. [ABSTRACT FROM AUTHOR]

The challenge of high-performance maneuvers for a deep-ocean underwater vehicle is to design proper controllers and ensure the high accuracy of vehicle state measurements. Current underwater vehicle control solutions are considered to be a unique controller designed to reject the disturbance and noise. However, the controller is based on a precise hydrodynamic model. It requires multiple underwater experiments and complex theoretical analysis. In this article, a hybrid control strategy is presented for the work-class remote operated vehicle. It tries to compose several proportion-integral-differential controllers into one intelligent sequence in terms of task requirements. The proposed approach employs the iterative learning method to improve the performance of the depth holding and the way-point tracking. A remote operated vehicle system weighted about 1.5 tons is provided as a physical platform for scientific investigations using acoustic Doppler current profiler, inertial navigation system, depth sensor, and an altimeter. Results from the simulation and the experiment in the basin show that the proposed approach provides high accuracy at both conditions: tracking way-points with or without ocean currents and disturbances, which show the effectiveness of the proposed approach. In addition, the thrust vector defined for a propeller facilitates the control of underwater vehicle as the thruster configuration changes. [ABSTRACT FROM AUTHOR]

A bionic robotic fish has great potential application prospect. High maneuverability swimming control of a bionic robotic fish has been one of the research hotspots in the robotic fish field. In this paper, an iterative learning method has been proposed to solve the trajectory tracking control problem of robotic fish swimming. First, a dynamic model of the multi-joint bionic robotic fish is established. By considering a three-joint robotic fish as an example, the unified expression of the dynamic equation of the three-joint bionic robotic fish is obtained by Lagrange method. Second, the iterative learning controller for controlling the bionic robotic fish is designed. Then the convergence of the iterative learning controller is proved. Finally, the trajectory tracking control simulation experiment based on iterative learning is conducted. The simulation results show that the trajectory tracking control method based on iterative learning for a bionic robotic fish is effective. [ABSTRACT FROM AUTHOR]

With an increasing number of multirotor unmanned aerial vehicles (UAVs), solutions supporting the improvement in their precision of operation and safety of autonomous flights are gaining importance. They are particularly crucial in transportation tasks, where control systems are required to provide a stable and controllable flight in various environmental conditions, especially after changing the total mass of the UAV (by adding extra load). In the paper, the problem of using only available basic sensory information for fast, locally best, iterative real-time auto-tuning of parameters of fixed-gain altitude controllers is considered. The machine learning method proposed for this purpose is based on a modified zero-order optimization algorithm (golden-search algorithm) and bootstrapping technique. It has been validated in numerous simulations and real-world experiments in terms of its effectiveness in such aspects as: the impact of environmental disturbances (wind gusts); flight with change in mass; and change of sensory information sources in the auto-tuning procedure. The main advantage of the proposed method is that for the trajectory primitives repeatedly followed by an UAV (for programmed controller gains), the method effectively minimizes the selected performance index (cost function). Such a performance index might, e.g., express indirect requirements about tracking quality and energy expenditure. In the paper, a comprehensive description of the method, as well as a wide discussion of the results obtained from experiments conducted in the AeroLab for a low-cost UAV (Bebop 2), are included. The results have confirmed high efficiency of the method at the expected, low computational complexity. [ABSTRACT FROM AUTHOR]

Summary: Robust and adaptive control strategies are needed when robots or automated systems are introduced to unknown and dynamic environments where they are required to cope with disturbances, unmodeled dynamics, and parametric uncertainties. In this paper, we demonstrate the capabilities of a combined L1 adaptive control and iterative learning control (ILC) framework to achieve high‐precision trajectory tracking in the presence of unknown and changing disturbances. The L1 adaptive controller makes the system behave close to a reference model; however, it does not guarantee that perfect trajectory tracking is achieved, while ILC improves trajectory tracking performance based on previous iterations. The combined framework in this paper uses L1 adaptive control as an underlying controller that achieves a robust and repeatable behavior, while the ILC acts as a high‐level adaptation scheme that mainly compensates for systematic tracking errors. We illustrate that this framework enables transfer learning between dynamically different systems, where learned experience of one system can be shown to be beneficial for another different system. Experimental results with two different quadrotors show the superior performance of the combined L1‐ILC framework compared with approaches using ILC with an underlying proportional‐derivative controller or proportional‐integral‐derivative controller. Results highlight that our L1‐ILC framework can achieve high‐precision trajectory tracking when unknown and changing disturbances are present and can achieve transfer of learned experience between dynamically different systems. Moreover, our approach is able to achieve precise trajectory tracking in the first attempt when the initial input is generated based on the reference model of the adaptive controller. [ABSTRACT FROM AUTHOR]

Recently, weakly-supervised object detection has attracted much attention, since it does not require expensive bounding-box annotations while training the network. Although significant progress has also been made, there is still a large gap on the performance between weakly-supervised and fully-supervised object detection. To mitigate this gap, some works try to use the pseudo ground truths generated by a weakly-supervised detector to train a supervised detector. However, such approaches incline to find the most representative parts instead of the whole body of an object, and only seek one ground truth bounding-box per class even though many same-class instances exist in an image. To address these issues, we propose a weakly-supervised to fully-supervised framework (W2F), where a weakly-supervised detector is implemented using multiple instance learning. And then, we propose a pseudo ground-truth excavation (PGE) algorithm to find the accurate pseudo ground truth bounding-box for each instance. Moreover, the pseudo ground-truth adaptation (PGA) algorithm is designed to further refine those pseudo ground truths mined by PGE algorithm. Finally, the mined pseudo ground truths are used as supervision to train a fully-supervised detector. Additionally, we also propose an iterative ground-truth learning (IGL) approach, which enhances the quality of the pseudo ground truths by using the predictions of the fully-supervised detector iteratively. Extensive experiments on the challenging PASCAL VOC 2007 and 2012 benchmarks strongly demonstrate the effectiveness of our method. We obtain 53.1% and 49.4% mAP on VOC2007 and VOC2012 respectively, which is a significant improvement over previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The most common technique of protecting crops from diseases is by applying a chemical process whereby a mixture of chemicals and water are sprayed onto the crops via a sprayer. Nowadays, modern sprayers are generally implemented to suspension systems for reducing the unwanted vibration of the spray boom structure to improve the uniformity of spray distribution in the agricultural field environment. This paper serves to present a new alternative to address and resolve the vibration control problem of the moving sprayer structures. The application of an active torque control (ATC) method to cancel the undesired vibration of the sprayer boom is thus proposed. As a continuation from Part I that deals with the modeling and simulation aspect, Part II explains the practical facet of the study through the implementation of ATC and iterative learning (ATCAIL) control scheme to an experimental spray boom structure as a basis to validate the effectiveness and robustness of the scheme as simulated and described at length in Part I. A sprayer boom suspension system test rig was specifically designed and developed to verify this control scheme that was principally chosen due to its ease of implementation through the exploitation of simple proportional–integral–derivative (PID), ATC and iterative learning algorithms. The system performance was evaluated and compared to the PID and ATC–PID control schemes for benchmarking. The results demonstrate the capability of the practical ATCAIL scheme to improve the vibration suppression in both time and frequency domains, thereafter guaranteeing a more uniform spray distribution of chemicals on a bumpy terrain. The experimental outcomes are in good agreements with the simulation counterpart. [ABSTRACT FROM AUTHOR]

Since one of the influential factors that affects the spray distribution pattern is the spray boom movements which are mostly induced by soil unevenness, most of the recent sprayers are equipped with suspensions for improving the uniformity of spray application in the field. This paper investigates the suitability of improving the sprayer suspension dynamics performance by employing a robust intelligent control scheme, namely active torque control (ATC) based method in reducing the undesired vibration through a simulation study. The ATC scheme with a self-tuning fuzzy proportional-integral-derivative (PID) (ATC-STF-PID) controller was first designed and simulated. Then an artificial intelligence (AI) method using iterative learning (IL) was embedded and implemented into the ATC loop to compute the estimated inertial parameter of the system; this scheme is known as ATCAIL. Thereafter, the performance of the ATCAIL scheme is later compared to the ATC with artificial neural network (ATCANN), ATC-STF-PID and STF-PID controllers in time and frequency domains. The results of simulation work affirm that ATC-based schemes can improve the system performance of the active rolling suspension in relation to roll vibration suppression. In other words, both the ATCAIL and ATCANN schemes show better responses in comparison to the ATC-STF-PID controller scheme. The results also imply that the ATCAIL scheme is indeed effective in suppressing the vibration of a sprayer boom structure. [ABSTRACT FROM AUTHOR]

Highlights • A novel gait simulator is developed for in vitro studies of the human foot. • Electro-hydraulic loading system is designed for tibia loading. • An iterative learning based output feedback DSC scheme is proposed. • The effectiveness is validated by the cadaveric gait simulation. Abstract In this paper, a novel gait simulator is developed for in vitro studies of the normal kinematics and kinetics of the human foot during the stance phase of the gait. In order to make the ground reaction force of the gait simulation in a manner similar to in vivo, an electro-hydraulic loading system (EHLS) is utilized for tibia loading. Since only the position and loading force signals are available, a high-gain observer is designed to estimate the unmeasured states of the EHLS, and the dynamic surface control is implemented for position tracking of the EHLS. The desired position trajectory of the EHLS could be optimized by an iterative learning mechanism such that the tibia loading force could be as close as possible to the target curve in the complex gait simulation process. The experimental results have verified the effectiveness of the proposed control method, and the average tibia loading error can be maintained within 1.5% of the total loading range. [ABSTRACT FROM AUTHOR]