Search

Abstract Potential uses for electromagnetic launchers in defense systems, space exploration, and transportation have recently emerged. In addition, this accelerator has many applications, such as deploying small satellites into low-earth orbit and accelerating high-speed trains (e.g., bullet trains and Hyperloop) with a low-cost propulsion system instead of expensive linear motors, particularly in space applications. Therefore, the full capability and optimization of these launchers’ efficiency are still required. Therefore, this paper focuses on presenting a new design to decrease the coil’s magnetic circuit reluctance and boost the magnetic flux lines by adding a laminated iron yoke surrounding the coil. This design makes the inductance value of the iron-yoked accelerator twice the inductance in case of the absence of the iron-yoke at its peak. Additionally, the initial inductance of the iron-yoked accelerator is approximately 65% higher than that of the coil without the iron yoke. Consequently, the modified design proposed an efficiency of 17.5%, which represents a 60% improvement over the efficiency of the regular accelerator. In addition, the introduced design eliminates the suck-back force using a fast-switching device (IGBT) to switch the coil off when the projectile reaches half of the coil. Moreover, a mathematical model for the iron-yoked accelerator is built on MATLAB Simulink and validated experimentally. An artificial intelligence optimization technique, the gravitational search algorithm (GSA), is used to optimize the accelerator parameters, such as the number of turns, capacitor value, and capacitor voltage. Finally, the experimental evaluation of the GSA-optimized system demonstrated an additional 15% enhancement in efficiency, bringing the total efficiency to 20%.

Abstract Our research utilized deep learning to enhance the control of a 3 Degrees of Freedom biped robot leg. We created a dynamic model based on a detailed joint angles and actuator torques dataset. This model was then integrated into a Model Predictive Control (MPC) framework, allowing for precise trajectory tracking without the need for traditional analytical dynamic models. By incorporating specific constraints within the MPC, we met operational and safety standards. The experimental results demonstrate the effectiveness of deep learning models in improving robotic control, leading to precise trajectory tracking and suggesting potential for further integration of deep learning into robotic system control. This approach not only outperforms traditional control methods in accuracy and efficiency but also opens the way for new research in robotics, highlighting the potential of utilizing deep learning models in predictive control techniques.

Soft growing robots, are a type of robots that are designed to move and adapt to their environment in a similar way to how plants grow and move with potential applications where they could be used to navigate through tight spaces, dangerous terrain, and hard-to-reach areas. This research explores the application of deep reinforcement Q-learning algorithm for facilitating the navigation of the soft growing robots in cluttered environments. The proposed algorithm utilizes the flexibility of the soft robot to adapt and incorporate the interaction between the robot and the environment into the decision-making process. Results from simulations show that the proposed algorithm improves the soft robot’s ability to navigate effectively and efficiently in confined spaces. This study presents a promising approach to addressing the challenges faced by growing robots in particular and soft robots general in planning obstacle-aware paths in real-world scenarios.

In this study, we applied deep learning to improve the control of a KUKA LBR4 7 Degrees of Freedom (DOF) robotic arm. We developed a dynamic model using a comprehensive dataset of joint angles and actuator torques obtained from pick-and-place operations. This model was incorporated into a Model Predictive Control (MPC) framework, enabling precise trajectory tracking without the need for traditional analytical dynamic models. By integrating specific constraints within the MPC, we ensured adherence to operational and safety standards. Experimental results demonstrate that deep learning models significantly enhance robotic control, achieving precise trajectory tracking. This approach not only surpasses traditional control methods in terms of accuracy and efficiency but also opens new avenues for research in robotics, showcasing the potential of deep learning models in predictive control techniques.

Transitioning from petrol or gas vehicles to electric vehicles (EVs) poses significant challenges in reducing emissions, lowering operational costs, and improving energy storage. Wireless charging EVs offer promising solutions to wired charging limitations such as restricted travel range and lengthy charging times. This paper presents a comprehensive approach to address the challenges of wireless power transfer (WPT) for EVs by optimizing coupling frequency and coil design to enhance efficiency while minimizing electromagnetic interference (EMI) and heat generation. A novel coil design and adaptive hardware are proposed to improve power transfer efficiency (PTE) by defining the optimal magnetic resonant coupling WPT and mitigating coil misalignment, which is considered a significant barrier to the widespread adoption of WPT for EVs. A new methodology for designing and arranging roadside lanes and facilities for dynamic wireless charging (DWC) of EVs is introduced. This includes the optimization of transmitter coils (TCs), receiving coils (RCs), compensation circuits, and high-frequency inverters/converters using the partial differential equation toolbox (pdetool). The integration of wireless charging systems with smart grid technology is explored to enhance energy distribution and reduce peak load issues. The paper proposes a DWC system with multiple segmented transmitters integrated with adaptive renewable photovoltaic (PV) units and a battery system using the utility main grid as a backup. The design process includes the determination of the required PV array capacity, station battery sizing, and inverters/converters to ensure maximum power point tracking (MPPT). To validate the proposed system, it was tested in two scenarios: charging a single EV at different speeds and simultaneously charging two EVs over a 1 km stretch with a 50 kW system, achieving a total range of 500 km. Experimental validation was performed through real-time simulation and hardware tests using an OPAL-RT platform, demonstrating a power transfer efficiency of 90.7%, thus confirming the scalability and feasibility of the system for future EV infrastructure.

Soft continuum robots, with their flexible and deformable structures, excel in tasks requiring delicate manipulation and navigation through complex environments. Accurate shape sensing is vital to enhance their performance, safety, and adaptability. Unlike rigid sensors, soft sensors conform to the robot’s flexible surfaces, ensuring consistent measurement of shape and motion. This paper introduces a new approach using soft e-textile resistive sensors, which integrate seamlessly with the robot’s structure. These sensors adjust their resistance in response to movements, capturing multidimensional force data. A deep Convolutional Neural Network (CNN) decodes the sensor signals, enabling precise shape estimation and control. Our findings indicate that soft e-textile sensors may surpass traditional rigid sensors in shape sensing and control, significantly improving the functionality of soft continuum robots in challenging applications.

In this study, a novel magnetic gear design is introduced. Unlike conventional magnetic gears that can only achieve a single gear ratio using permanent magnetic poles, the proposed design incorporates electromagnetic coils that can adapt to various control strategies, resulting in a multiple gear ratio for the same machine design. We selected a gear system with five gear ratios to validate the new design. The performance of the proposed design was compared with that of the conventional magnetic gear. While permanent magnet poles offer high torque transmission with a small volume, they cannot provide different gear ratios for the same configuration. Therefore, this work suggests using a single-gear machine based on a fixed number of electromagnetic coils to achieve different gear ratios. This research outlines the design steps, simulation process, and detailed analysis. The results demonstrate the effectiveness of the proposed design strategy, which can be potentially applied to wind turbines, transportation, and other scenarios with comparable success.

Soft continuum robots, inspired by the adaptability and agility of natural soft-bodied organisms like octopuses and elephant trunks, present a frontier in robotics research. However, exploiting their full potential necessitates precise modeling and control for specific motion and manipulation tasks. This study introduces an innovative approach using Deep Convolutional Neural Networks (CNN) for the inverse quasi-static modeling of these robots within the Absolute Nodal Coordinate Formulation (ANCF) framework. The ANCF effectively represents the complex non-linear behavior of soft continuum robots, while the CNN-based models are optimized for computational efficiency and precision. This combination is crucial for addressing the complex inverse statics problems associated with ANCF-modeled robots. Extensive numerical experiments were conducted to assess the performance of these Deep CNN-based models, demonstrating their suitability for real-time simulation and control in statics modeling. Additionally, this study includes a detailed cross-validation experiment to identify the most effective model architecture, taking into account factors such as the number of layers, activation functions, and unit configurations. The results highlight the significant benefits of integrating Deep CNN with ANCF models, paving the way for advanced statics modeling in soft continuum robotics.

Recent developments in electromagnetic launchers have created potential applications in transportation, space, and defense systems. However, the total efficiency of these launchers has yet to be fully realized and optimized. Therefore, this paper introduces a new design idea based on increasing the magnetic flux lines that facilitate high output velocity without adding any excess energy. This design facilitates obtaining a mathematical equation for the launcher inductance which is difficult to analytically represent. This modification raises the launcher efficiency to 36% higher than that of the ordinary launcher at low operating voltage. The proposed design has proven its superiority to traditional launchers, which are limited in their ability to accelerate microsatellites from the ground to low Earth orbit due to altitude and velocity constraints. Therefore, an aircraft is used as a flying launchpad to carry the launcher and bring it to the required height to launch. Meanwhile, it is demonstrated experimentally that magnetic dipoles in the projectile material allow the launcher coil’s magnetic field to accelerate the projectile. This system consists of the launcher coil that must be triggered with a high amplitude current from the high DC voltage capacitor bank. In addition, a microcontroller unit controls all processes, including the capacitor bank charging, triggering, and velocity measurement.

One type of vehicle suspension system is the air suspension system. One of the important functions of the suspension system is to reduce vibration transmitted to the vehicle body from road unevenness. Soft suspension results in better ride comfort and worst handling. While stiff suspension results in better handling and worse comfort. This paper investigates the performance of air suspension in terms of passenger ride comfort and vehicle handling. The performance is tested once with Fuzzy logic control and another with Fuzzy control augmented with Neuro-Fuzzy inference system. A mathematical model is developed to describe the air-spring stiffness behavior. The air-spring suspension is merged on two degrees of freedom model. The air pressure is controlled by a Fuzzy controller as done previously in the literature. On the other hand, our approach is to control the volume change by connecting the air-spring volume to two additional unequal volumes through ON-OFF solenoid valves. The solenoid valves are controlled by Adaptive Neuro-Fuzzy Inference System (ANFIS). A single-degree-of-freedom setup was built from which the required training data for the ANFIS controller was carried out. The experimental setup is developed with variable excitation input in terms of frequency and amplitudes. The acceleration of the sprung mass has been measured and stored at different operating conditions and including different air volumes. The stored data is used for training of volume controller. The controller is tested with Sinusoidal excitation then with ISO 8608 road profile. It is found that increasing the air volume reduces the sprung mass acceleration. Also, the results showed that implementing the Neuro-Fuzzy controller with Fuzzy logic control reduces the sprung mass acceleration significantly by an average value that reaches 5 cm/s2 at frequencies above 1 Hz while maintaining road holding.

Soft growing robots, which mimic the biological growth of plants, have demonstrated excellent performance in navigating tight and distant environments due to their flexibility and extendable lengths of several tens of meters. However, controlling the position of the tip of these robots can be challenging due to the lack of precise methods for measuring the robots’ Cartesian position in their working environments. Moreover, classical control techniques are not suitable for these robots because they involve the irreversible addition of materials, which introduces process constraints. In this paper, we propose two optimization-based approaches, combining Moving Horizon Estimation (MHE) with Nonlinear Model Predictive Control (NMPC), to achieve superior performance in point stabilization, trajectory tracking, and obstacle avoidance for these robots. MHE is used to estimate the entire state of the robot, including its unknown Cartesian position, based on available configuration measurements. The proposed NMPC approach considers process constraints by relying on the estimated state to ensure optimal performance. We perform numerical simulations using the nonlinear kinematic model of a vine-like robot, one of the newly introduced plant-inspired growing robots, and achieve satisfactory results in terms of reduced computation times and tracking error.

Robotic exploration of wide terrains, such as agricultural fields, could be challenging while considering the limited robot's capabilities in terms of sensing and power. Thus, in this article, we proposed OGPR*, an Obstacle Guided Path Refinement algorithm for quickly planning collision-free paths utilizing the obstacles existing in the environment. To tackle the issue of exploring wide terrains, a supervisory-based collaboration between the quadcopter and a mobile robot is proposed. The quadcopter is responsible for streaming subsequently live two-dimensional images for the environment under discussion while planning safe paths for the ground the mobile robot is planning safe paths to manoeuvre. Numerical simulations proved the significant performance of the proposed OGBR* algorithm when compared to the state of the art algorithms exist in the literature.

Recently, continuum flexible robots have been designed for the use in diverse applications; including the exploration of confined static and dynamic environments. One of the challenging tasks for those robots is planning optimal trajectories due to, not only the redundant Degrees of Freedom (DOF) they own but also their compliant behaviour. In this paper, an Imitation-based Pose Planning (IbPP) approach is proposed to teach a two-section continuum robot the motion primitives that will facilitate achieving and generalizing for spatial point-to-point motion which involves both position and orientation goals encoded in a dual quaternion form. Two novel approaches are proposed in this research to intuitively generate the motion demonstrations that will be used in the proposed IbPP. Namely, a flexible input interface, acting as a twin robot, is designed to allow a human to demonstrate different motions for the robot end-effector. Alternatively, as a second approach, the Microsoft Kinect sensor is used to provide motion demonstrations faster via human arm movements. Based on the kinematic model of the two-section continuum robot, a Model Reference Adaptive Control (MRAC) algorithm is developed to achieve tracking the generated trajectory from the IbPP and to guarantee the robustness against the model uncertainties and external disturbances. Moreover, controller stability analysis is developed based on Lyapunov criteria. Finally, simulations are conducted for the two-section continuum robot to prove the ability of the proposed IbPP with the two proposed inputs to learn and generalize for spatial motions, which in future could be easily accommodated for robots with multiple sections. In addition, the proposed MRAC shows a significant performance towards following the required trajectory and rejecting the external disturbance.

Recently, researchers have shown an increased interest in considering plants as a model of inspiration for designing new robot locomotions. Growing robots, that imitate the biological growth presented by plants, have proved irresistible in unpredictable and distal environments due to their morphological adaptation and tip-extension capabilities. However, as a result of the irreversible growing process exhibited by growing robots, classical control schemes could fail in obtaining feasible solutions that respect the permanent growth constraint. Thus, in this article, a Nonlinear Model Predictive Control (NMPC) scheme is proposed to guarantee the robot's performance towards point stabilization while respecting the constraints imposed by the growing process and the control limits. The proposed NMPC-based growth control has applied to the kinematic model of the recently proposed plant-inspired robots in the literature, namely, vine-like growing robots. Numerical simulations have been performed to show the effectiveness of the proposed NMPC-based growth control in terms of point stabilization, disturbance rejection, and obstacle avoidance and encouraging results were obtained. Finally, the robustness of the proposed NMPC-based growth control is analyzed against various input disturbances using Monte-Carlo simulations that could guide the tuning process of the NMPC.

Recently, there has been an increased interest in the deployment of continuum robots in unstructured and challenging environments. However, the application of the state-of-the-art motion planning strategies, that have been developed for rigid robots, could be challenging in continuum robots. This, in fact, is due to the compliance that continuum robots possess besides their increased number of degrees of freedom. In this paper, a Demonstration Guided Pose Planning (DGPP) technique is proposed to learn and subsequently plan for spatial point-to-point motions for multi-section continuum robots. Motion demonstrations, including position and orientation, are collected from a human via a flexible input interface that is developed to command the continuum robot intuitively via teleoperation. A dynamic model based on Euler-Lagrange formalism is derived for a two-section continuum robot to be considered while planning for the robot motions. Meanwhile, a Proportional-Derivative (PD) computed torque controller with a Model Reference Adaptive Kinematic Control (MRAKC) scheme are developed to ensure the tracking performance against system uncertainties and disturbances. Also, the system stability analysis based on Lyapunov quadratic equation is proven. Simulation results prove that the proposed DGPP approach, along with the developed control scheme, have the ability to learn, generalize and reproduce spatial motions for a two-section continuum robot while avoiding both static and dynamic obstacles that could exist in the environments.

Mobile robots have been used to explore novel environments and build useful maps for navigation. Although sensor-based random tree techniques have been used extensively for exploration, they are not efficient for time-critical applications since the robot may visit the same place more than once during backtracking. In this paper, a novel, simple yet effective heuristic backtracking algorithm is proposed to reduce the exploration time and distance travelled. The new algorithm is based on the selection of the most informative node to approach during backtracking. A new environmental complexity metric is developed to evaluate the exploration complexity of different structured environments and thus enable a fair comparison between exploration techniques. An evaluation index is also developed to encapsulate the total performance of an exploration technique in a single number for the comparison of techniques. The developed backtracking algorithm is tested through computer simulations for several structured environments to verify its effectiveness using the developed complexity metric and the evaluation index. The results confirmed significant performance improvement using the proposed algorithm. The new evaluation index is also shown to be representative of the performance and to facilitate comparisons.