This paper proposes a one-step-ahead predictive controller for regulating the formation of a group of wheeled mobile robots. Although nonlinear model predictive control (NMPC) is commonly applied to multi-robot systems, it requires solving a nonconvex optimization problem online, which introduces significant computational overhead. As a result, processing delays and communication constraints negatively affect system performance in completing assigned tasks. In return, convex optimization problems are solved faster and more reliably than general nonconvex problems. To overcome this challenge, the proposed approach applies a one-step predictive control scheme formulated as a quadratic programming problem, which significantly reduces computation time compared to NMPC. Simulation results confirm the effectiveness of the method.

Over the coming years, the advancement of driverless transport systems for people and goods that are designed to be used on fixed routes will revolutionize the transportation system. Therefore, for a safe transportation system, detecting and recognizing traffic signals based on computer vision has become increasingly important. Deep learning approaches, particularly convolutional neural networks, have shown exceptional performance in various computer vision applications. The goal of this research is to precisely detect and recognize traffic signs that are present on the streets using computer vision and deep learning techniques. Previous work has focused on symbol-based traffic signals, where popular single-task learning models have been trained and tested. Therefore, several comparisons have been conducted to select accurate single-task learning models. For further improvement, these models are employed in a multi-task learning approach. Indeed, multi-task learning algorithms are built by sharing the convolutional layer parameters between the different tasks. Hence, for the multi-task learning approach, different experiments have been carried out using pre-trained architectures like, for instance, InceptionResNetV2 and DenseNet201. A range of traffic signs and traffic lights are employed to validate the designed model. An accuracy of 99.07% is achieved when the entire network has been trained. To further enhance the accuracy of the model for traffic signs obtained from the street, a region of interest module is added to the multi-task learning module to accurately extract the traffic signs available in the image. To check the effectiveness of the adopted methodology, the designed model has been successfully tested in real-time on a few Riyadh highways.

Thoracic diseases pose significant risks to an individual's chest health and are among the most perilous medical diseases. They can impact either one or both lungs, which leads to a severe impairment of a person's ability to breathe normally. Some notable examples of such diseases encompass pneumonia, lung cancer, coronavirus disease 2019 (COVID-19), tuberculosis, and chronic obstructive pulmonary disease (COPD). Consequently, early and precise detection of these diseases is paramount during the diagnostic process. Traditionally, the primary methods employed for the detection involve the use of X-ray imaging or computed tomography (CT) scans. Nevertheless, due to the scarcity of proficient radiologists and the inherent similarities between these diseases, the accuracy of detection can be compromised, leading to imprecise or erroneous results. To address this challenge, scientists have turned to computer-based solutions, aiming for swift and accurate diagnoses. The primary objective of this study is to develop two machine learning models, utilizing single-task and multi-task learning frameworks, to enhance classification accuracy. Within the multi-task learning architecture, two principal approaches exist soft parameter sharing and hard parameter sharing. Consequently, this research adopts a multi-task deep learning approach that leverages CNNs to achieve improved classification performance for the specified tasks. These tasks, focusing on pneumonia and COVID-19, are processed and learned simultaneously within a multi-task model. To assess the effectiveness of the trained model, it is rigorously validated using three different real-world datasets for training and testing.

In this paper, an adaptive distributed formation controller for wheeled nonholonomic mobile robots is developed. The dynamical model of the robots is first derived by employing the Euler-Lagrange equation while taking into consideration the presence of disturbances and uncertainties in practical applications. Then, by incorporating fractional calculus in conjunction with fast terminal sliding mode control and consensus protocol, a robust distributed formation controller is designed to assure a fast and finite-time convergence of the robots towards the required formation pattern. Additionally, an adaptive mechanism is integrated to effectively counteract the effects of disturbances and uncertain dynamics. Moreover, the suggested control scheme's stability is theoretically proven through the Lyapunov theorem. Finally, simulation outcomes are given in order to show the enhanced performance and efficiency of the suggested control technique.

In this paper, a nonlinear constrained predictive scheme is proposed to control a two-link rigid manipulator. The main novelty, of this work, lies in the inclusion of constraints on the control action and its dynamics. At first, they are imposed on torque amplitude to protect actuators from excessive values. Then, they are imposed on the controller dynamics to avoid the chattering phenomenon. The proposed approach is validated and its performances are evaluated based on multiple simulation results. They showed and confirmed the expected effect of imposing constraints on the control action; the torque amplitude is reduced within an acceptable range, and the chattering phenomenon is efficiently avoided.

Our work aims to estimate the camera motion mounted on the head of a mobile robot or a moving object from RGB-D images in a static scene. The problem of motion estimation is transformed into a nonlinear least squares function. Methods for solving such problems are iterative. Various classic methods gave an iterative solution by linearizing this function. We can also use the metaheuristic optimization method to solve this problem and improve results. In this paper, a new algorithm is developed for visual odometry using a sequence of RGB-D images. This algorithm is based on a genetic algorithm. The proposed iterative genetic algorithm searches using particles to estimate the optimal motion and then compares it to the traditional methods. To evaluate our method, we use the root mean square error to compare it with the based energy method and another metaheuristic method. We prove the efficiency of our innovative algorithm on a large set of images.

This paper presents a robust formation control scheme for a team of nonholonomic wheeled mobile robots. First, the formation kinematic controller is introduced according to the leader-following strategy, then by employing the dynamic model of the robots, a combination of fractional calculus theories and integral sliding mode control is adopted to provide a robust dynamic control laws for every follower robots to track the leader and accomplish the required formation pattern even in the presence of external disturbances and model uncertainties. Furthermore, the chattering phenomenon is mitigated using a fuzzy logic control. Then, by using the Lyapunov theory, the proposed control scheme's convergence and stability are demonstrated. Finally, a comparative study is conducted to evaluate the performance of the suggested control strategy.

This article applies the maximum entropy principle to determine the probability density function of the delayed busy period in an M/G/1 type queueing system with setup time, two phases of service, Bernoulli vacation, N-policy, and server breakdowns. Numerical illustrations show that the accuracy of the estimated probability density function depends on the type of information fed to the method.

In this paper, a predictive sliding mode control (PSMC) strategy for the quadrotors tracking trajectory problem is proposed. This strategy aims to combine the advantages of sliding mode control (SMC) and non-linear model predictive control (NMPC) to improve the tracking control performance for quadrotors in terms of optimality, inputs/states constraints satisfaction, and strong robustness against disturbances. A comparative study of three popular controllers: the SMC, NMPC, and the integral backstepping control (IBC) is performed with different criteria. Accordingly, IBC and SMC show less computational time and strong robustness, while NMPC has minimum control effort. The discrete Dryden turbulence model is used as a benchmark model to represent the wind effect on the trajectory tracking accuracy. The effectiveness of the proposed method PSMC has been proven and compared with discrete-time slidingmode control (DSMC) and NMPC in several scenarios. Simulation results show that under both wind turbulence and time-variant uncertainties, the PSMC outperforms the other controllers by providing simultaneously disturbance rejection and guarantee that the control inputs are within bounded constraints.

This work aims to study different architectures for the classification of thoracic diseases using pre-trained convolutional neural networks (PCNN) such as VGG-16, ResNet-50, EfficientNetB0, and InceptionV3 which are considered as state-of-the-art deep learning models. Indeed, they are used to detect various thoracic disorders. In this study, the main focus is on COVID-19 and pneumonia to make an optimal diagnosis for these two diseases. Although these diseases are prevalent, the process of detection and diagnosis is challenging. In this work, two unbalanced datasets (COVID-19 and Pneumonia) have been used. After the training phase where hyperparameters of the models have been tuned for best accuracy, a comparison study of these different models is conducted. The EfficientNetB0 model has achieved the highest test accuracy around 96.50% for Pneumonia X-ray images. The same work has been applied to the COVID-19 CT scans dataset, and the highest accuracy is achieved with the ResNet-50 network (99.5%). Therefore, these two models will be used for rapid diagnosis and assist radiologists in the detection process precisely.

Self-driving vehicles are considered one of the most significant advanced technologies in computer science and artificial intelligence. The primary objective of autonomous driving is the elimination of human supervision from the workflow of autonomous cars. The advantages of this technology are to improve people's lives by minimizing traffic, eliminating parking spaces in cities, boosting collective fuel efficiency, and lowering accidents. As autonomous driving becomes more incorporated into our daily lives, effective solutions are essential to its challenges. One of the most important tasks for autonomous driving is the automatic recognition of traffic signs. Artificial intelligence is broadly used in the object detection fields and especially in traffic sign detection tasks, while Convolutional Neural Networks (CNNs) are utilized in many computer vision tasks. In this paper, we conduct a comparison study of object recognition challenges for self-driving automobiles, in particular for traffic signs and traffic signals detection. Two standard datasets and six different deep CNNs architectures are utilized to carry out experiments. The data augmentation method is employed to solve the unbalanced datasets problem. Experiments show that for the GTSRB dataset, the DenseNet201 model with Adam optimizer achieved the top accuracy (98.66%). For the LISA TL dataset, the InceptionResNetV2 model with Adam optimizer achieved the highest accuracy among the other networks (98.84%).

In the last years, mobile robot localization has been developed significantly due to the need for accurate solutions to determine the position and orientation of the wheeled mobile robot (WMR) in a given environment. Many different sensors have been used to solve the problem. For instance, ultrasonic sensors, laser, or infrared sensors are also used to determine the pose of the WMR. However, sensors are sensitive to noise measurements and disturbances, which can distort the acquired information. For this reason, adequate algorithms should be used to reduce these uncertainties and determine the optimal pose of the WMR. In this research work, we focus on the comparative study of the most used algorithms, using landmarks as sensors, which are the extended Kalman filter and particle filter. Further, for an effective comparison, the simulation results were conducted and analyzed using different performance criteria. The simulations results showed better estimation performance achieved by the particle filter being compared to the extended Kalman filter when the sensors are subject to non-Gaussian noises.

Nonlinear model predictive control (NMPC) has proven its ability to control constrained nonlinear processes. Although NMPC can achieve exemplary tracking performance, the related computation effort as well as guaranteeing tracking convergence are its main drawbacks. Indeed, constrained NMPC is a nonlinear and nonconvex optimization problem where it is difficult to find a feasible solution within a reasonable time. Motivated by these difficulties, this study proposes a procedure, using the Euler approximation, to transform the nonlinear optimization problem of NMPC into a constrained quadratic optimization problem. The proposed tracking controller is applied to the autonomous navigation problem of a wheeled mobile robot (WMR) in a constrained space. Under certain assumptions, we prove the closed-loop system stability and boundedness of the tracking error. Furthermore, we demonstrate the recursive feasibility of the solution. Simulations are performed, first to determine the adequate control parameters, and second, to demonstrate the effectiveness of the proposed algorithm, while its real-time implementation is experimentally verified using a differential drive mobile robot.

Quadrotor applications have become increasingly complicated as they require faster and more accurate movements to improve efficiency in obstacle avoidance and reduce flight time. This paper proposes a nonlinear model predictive control (NMPC) for tracking the trajectory of the quadrotor with obstacle avoidance; This command was chosen for its features in handling inputs and states constraints. Besides, given the nonlinearities and computational cost usually associated with the Euler angles and rotation matrix, the article proposes a quaternion-based approach to represent the vehicle’s attitude; Finally, a numerical simulation was performed to evaluate the controller’s performance with time-variant uncertainty.

The quadrotor often flies in an environment where external disturbances can occur and decrease its tracking performances. Hence, the robustness and effectiveness of nonlinear controllers are required to reject the external disturbance. The aim of this article is to design and verify an integral backstepping and sliding mode control techniques to track the desired trajectory for the quadrotor. The performance and effectiveness of the nonlinear controllers are illustrated through representative simulations showing the tracking of several reference trajectories with disturbances, model uncertainties, and wind gusts effect. To this end, the Dryden turbulence model for wind velocity fluctuations was used as a benchmark wind model to better represent the impact of the accuracy of the wind field model on the trajectory tracking performance. The tracking performances of these approaches are discussed using the root mean square error (RMSE).

In this paper, a versatile Markovian queueing system is considered. Given a fixed threshold levelc, the server serves customers one a time when the queue length is less thanc, and in batches of fixed sizecwhen the queue length is greater than or equal toc. The server is subject to failure when serving either a single or a batch of customers. Service rates, failure rates, and repair rates, depend on whether the server is serving a single customer or a batch of customers. While the analytical method provides the initial probability vector, we use the entropy principle to obtain both the initial probability vector (for comparison) and the tail probability vector. The comparison shows the results obtained analytically and approximately are in good agreement, especially when the first two moments are used in the entropy approach.

Localizing the mobile robot in an indoor environment is one of the problems encountered repeatedly. Achieving the target precisely in any environment is not an easy task since there are noises and obstacles in the surrounding environment. Therefore, filtering the signals to reduce noises is essential for more accurate and precise motion. In this paper, we selected the extended Kalman filter, which is used for non-linear models’ signals to predict the coordinates of a wheeled mobile robot. We tested the efficiency of this filter under three noise cases: no noise, Gaussian noise and non-Gaussian noise using MATLAB software.

In recent years, unmanned surface vehicles have been widely used in various applications from military to civil domains. Seaports are crowded and ship accidents have increased. Thus, collision accidents occur frequently mainly due to human errors even though international regulations for preventing collisions at seas (COLREGs) have been established. In this paper, we propose a real-time obstacle avoidance algorithm for multiple autonomous surface vehicles based on constrained convex optimization. The proposed method is simple and fast in its implementation, and the solution converges to the optimal decision. The algorithm is combined with the PD-feedback linearization controller to track the generated path and to reach the target safely. Forces and azimuth angles are efficiently distributed using a control allocation technique. To show the effectiveness of the proposed collision-free path-planning algorithm, numerical simulations are performed.

In this paper, we investigate the problem of robust altitude stabilization for the vertical take-off and landing (VTOL) of an unmanned aerial vehicle in the presence of external disturbances (e.g. wind gusts), payload variations, and noisy measurements. The design of the controller is simple; it is based on the minimization of the one-step-ahead predicted position errors. The stability analysis of the closed loop in the presence of external disturbances is presented. The analysis results prove that the tracking errors of attitude, take-off, hovering, and landing are uniformly bounded. Since the proposed control algorithm will be employed for goods delivery by drones, the robustness of this algorithm against low-frequency disturbances and payload variations is a major objective. To this end, integral action is included in the altitude loop to eliminate the induced steady-state error and to drop off the payload in the desired position successfully. Furthermore, the controller is given in the closed form to facilitate its implementation onboard to increase the autonomy of the flight. The numerical simulations are provided to show the effectiveness of the proposed algorithm.

We propose a nonsmooth dynamic system integrating production and inventory where the items may deteriorate and the demand is stock-dependent. We aim to derive the optimal production rate. In our first model, backorders are not allowed, while in the second model they are. Using optimal control, necessary optimality conditions are obtained for general forms of the cost, demand, and deterioration rates and closed form solutions are derived for specific forms of these rates. Numerical simulations are presented and sensitivity of the solutions are examined.