Abstract Indonesia is a maritime country that has vast coastal resources and biodiversity. To support the Indonesian maritime program, a topography mapping tool is needed. The ideal topography mapping tool is the Unmanned Surface Vehicle (USV). This paper proposes the design, manufacture,and development of an affordable autonomous USV. The USV which is composed of thruster and rudder is quite complicated to build. This study employs rudderless and double thrusters as the main actuators. PID compensator is utilized as the feedback control for the autonomous USV. Energy consumption is measured when the USV is in autonomous mode. The Dynamics model of USV was implemented to study the roll stability of the proposed USV. Open-source Mission Planner software was selected as the Ground Control Station (GCS) software. Performance tests were carried out by providing the USV with an autonomous mission to follow a specific trajectory. The results showed that the developed USV was able to complete autonomous mission with relatively small errors,making it suitable for underwater topography mapping.

Abstract This article presents the study of the stability of single-input and multiple-input systems with point or distributed state delay and input delay and input saturation. By a linear transformation applied to the initial system with delay, a system is obtained without delay, but which is equivalent rom the point of view of stability. Next, using sufficient conditions for the global asymptotic stability of linear systems with bounded control, new sufficient conditions are obtained for global asymptotic stability of the initial system with state delay and input delay and input saturation. In addition,the article presents the results on the instability and estimation of the stability region of the delay and input saturation system. The numerical simulations confirming the results obtained on stability were performed in the MATLAB/Simulink environment. A method is also presented for solving a transcendental matrix equation that results from the process of equating the stability of the systems with and without delay, a method which is based on the computational intelligence, namely, the Particle Swarm Optimization (PSO) method.

Abstract This paper presents a new passivity-preserving order reduction method for linear time invariant passive systems, which are also called positive real (PR) systems, with the aid of the balanced truncation (BT) method. The proposed method stems from the conic positive real balanced truncation (CPRBT) method, which is a modification of the BT method for PR systems. CPRBT presents an algorithm in which the reduced models are obtained from some Riccati equations in which the phase angle of the transfer function has been taken into consideration. Although CPRBT is a powerful algorithm for obtaining accurate PR reduced-order models, it cannot guarantee that the phase diagram of the reduced model remains inside the same interval as that of the original full-order system. We aim to address such a problem by modifying CPRBT in the way that the phase angle of the reduced transfer function always remains inside the conic and homolographic phase interval of the original system. This is proven through some matrix manipulations, which has added mathematical value to the paper. Finally, in order to assess the efficacy of the proposed method, two numerical examples are simulated.

Abstract The closed-loop optimal control systems using the receding horizon control (RHC) struc ture make predictions based on a process model (PM) to calculate the current control output. In many applications, the optimal prediction over the current prediction horizon is calculated using a metaheuristic algorithm, such as an evolutionary algorithm (EA). The EAs, as other population-based metaheuristics, have large computational complexity. When integrated into the controller, the EA is carried out at each sampling moment and subjected to a time constraint: the execution time should be smaller than the sampling period. This paper proposes a software module integrated into the controller, called at each sampling moment. The module estimates using the PM integration the future process states, over a short time horizon, for different control input values covering the given technological interval. Only a narrower interval is selected for a ‘good’ evolution of the process,based on the so-called ‘state quality criterion’. The controller will consider only a shrunk control output range for the current sampling period. EA will search for its best prediction inside a smaller domain that does not cause the convergence to be affected. Simulations prove that the computational complexity of the controller will decrease.

Abstract In recent years, there has been growing interest in automated tracking and detection of sports activities. Researchers have shown that providing activity information to individuals during their exercise routines can greatly help them in achieving their exercise goals. In particular, such information would help them to maximize workout efficiency and prevent overreaching and overtraining. This paper presents the development of a novel multipurpose wearable device for automatic weight detection, activity type recognition, and count repetition in sports activities such as weight training. The device monitors weights and activities by using an inertial measurement unit (IMU), an accelerometer, and three force sensors mounted in a glove, and classifies them by utilizing developed machine learning models. For weight detection purposes, different classifiers including Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Multi-layer Perceptron Neural Networks (MLP) were investigated. For activity recognition, the K nearest neighbor (KNN), Decision Tree (DT), Random Forest (RF), and SVM models were trained and examined. Experimental results indicate that the SVM classifier can achieve the highest accuracy for weight detection whereas RF can outperform other classifiers for activity recognition. The results indicate feasibility of developing a wearable device that can provide in-situ accurate information regarding the lifted weight and activity type with minimum physical intervention.

Abstract In the last few decades, there has been a growing necessity for systems that handle market changes and personalized customer needs with near mass production efficiency, defined as the new mass customization paradigm. The Industry 5.0 vision further enhances the human-centricity aspect, in the necessity for manufacturing systems to cooperate with workers, taking advantage of their problem-solving capabilities, creativity, and expertise of the manufacturing process. A solution is to develop a flexible manufacturing system capable of handling different customer requests and real-time decisions from operators. This paper tackles these aspects by proposing a digital twin of a robotic system for solution preparation capable of making real-time scheduling decisions and forecasts using a simulation model while allowing human interventions. A discrete event simulation model was used to forecast possible system improvements. The simulation handles real-time scheduling considering the possibility of adding identical parallel machines. Results show that processing multiple jobs simultaneously with more than one machine on critical processes, increasing the robot speed, and using heuristics that emphasize the shortest transportation time can reduce the overall completion time by 82%. The simulation model has an animated visualization window for a deeper understanding of the system.

Abstract Mapping soil fertility attributes at fine spatial resolution is crucial for site-specific management in precision agriculture. This paper evaluated the performance of mobile measurements using visible and near-infrared spectroscopy (vis–NIR) to predict and map key fertility attributes in tropical soils through local data modeling with partial least squares regression (PLS) and artificial neural network (ANN). Models were calibrated and tested in a calibration area (18-ha) with high spatial variability of soil attributes and then extrapolated in the entire field (138-ha). The models calibrated with ANN obtained superior performance for all attributes. Although ANN models obtained satisfactory predictions in the calibration area (ratio of performance to interquartile range (RPIQ) ≥ 1.7) for clay, organic matter (OM), cation exchange capacity (CEC), base saturation (V), and exchangeable (ex-) Ca, it was not repeated for some of them when extrapolated into the entire field. In conclusion, robust mappings (RPIQ = 2.49) were obtained for clay and OM, indicating that these attributes can be successfully mapped on tropical soils using mobile vis–NIR spectroscopy and local calibrations using ANN. This study highlights the need to implement an independent test to assess reliability and extrapolability of previously calibrated models, even when extrapolating the models to neighboring areas.

Abstract Complex networks make an enticing research topic that has been increasingly attracting researchers from control systems and various other domains over the last two decades. The aim of this paper was to survey the interest in control related to complex networks research over time since 2000 and to identify recent trends that may generate new research directions. The survey was performed for Web of Science, Scopus, and IEEEXplore publications related to complex networks.Based on our findings, we raised several questions and highlighted ongoing interests in the control of complex networks.

Abstract Digital Twins (DTs) are one of the disruptive technologies associated with the Industry 4.0 concept. A DT connects the physical manufacturing system with the digital cyberspace, via the synchronization of the simulation (i.e., physical configurations) and data models (i.e., product, process, and resource models) of the manufacturing system. This synchronization of both worlds— the physical and digital—allows one to address the issue of manufacturing customized products. This challenge of mass customization (1) puts forward the goal of achieving the highest level of customer satisfaction, and (2) creates the need for the optimization of the complete value creation process. Within an Industry 4.0 context, the latter is translated as the interlinking of production resources and systems, via a DT, as it is in the physical world where the actual value-creation process takes place. The success of an Industry 4.0 mass customization environment (or mass customization 4.0), depends on its degree/level of sustainability. For these reasons, the present paper presents a review of relevant concepts related to the role of DTs in the achievement of a mass customization 4.0 environment, plus some proposals of how to address the identified research challenges. A future research agenda is proposed at the end of the paper.

Abstract The number of applications in which industrial robots share their working environment with people is increasing. Robots appropriate for such applications are equipped with safety systems according to ISO/TS 15066:2016 and are often referred to as collaborative robots (cobots). Due to the nature of human-robot collaboration, the working environment of cobots is subjected to unforeseeable modifications caused by people. Vision systems are often used to increase the adaptability of cobots, but they usually require knowledge of the objects to be manipulated. The application of machine learning techniques can increase the flexibility by enabling the control system of a cobot to continuously learn and adapt to unexpected changes in the working environment. In this paper we address this issue by investigating the use of Reinforcement Learning (RL) to control a cobot to perform pick-and-place tasks. We present the implementation of a control system that can adapt to changes in position and enables a cobot to grasp objects which were not part of the training. Our proposed system uses deep Q-learning to process color and depth images and generates an e-greedy policy to define robot actions. The Q-values are estimated using Convolution Neural Networks (CNNs) based on pre-trained models for feature extraction. To reduce training time, we implement a simulation environment to first train the RL agent, then we apply the resulting system on a real cobot.System performance is compared when using the pre-trained CNN models ResNext, DenseNet, MobileNet, and MNASNet. Simulation and experimental results validate the proposed approach and show that our system reaches a grasping success rate of 89.9% when manipulating a never-seen object operating with the pre-trained CNN model MobileNet.