International Journal of Intelligent Robotics and Applications最新文献

String insulators are components in high-voltage towers responsible for preventing energy dissipation through the tower structure; that is, they are responsible for isolating the high voltage in the electrical network cables. These string insulators must be clean for best performance and to avoid malfunctions. Verifying the necessity for cleaning/washing is most often performed by human visual observation, which can lead to interpretation errors, in addition to bringing risks to the physical integrity of humans in the vicinity of these electrical systems. Thus, this paper aims to develop an algorithm to detect and classify these insulators. The proposed algorithm uses artificial intelligence techniques and analyzes the image, inferring the state of cleanliness of the analyzed insulator. For the development of this algorithm, it was necessary to build a synthetic database using CAD software such as Inventor and Unity-3D due to image limitations available from dirty insulator strings. In this paper, two distinct neural networks are built using supervised learning techniques, where the first one is for detecting the chain of insulators, and the second is for detecting the type of dirt on the disk surface. In the first stage, techniques that use supervised learning are studied, more aimed explicitly at semantic segmentation networks, and in the second stage, classification deep neural networks were used to detect the type of impurities. In detecting insulator strings, an average dice coefficient of 0.95 was achieved for simulated images and 0.92 for natural images, with learning parameters based on a database with only simulated images. The average accuracy obtained in the dirt classification stage was 0.98.

The demand for developing lighter manipulators, particularly in various long-reach applications, has surged significantly. In many of these applications, inherent structural flexibilities are unavoidable and lead to vibrations. Consequently, these residual vibrations detrimentally affect working efficiency and positioning accuracy. The present work introduces a novel approach by formulating a nonlinear dynamical model of a spatial multi-link manipulator mounted on a mobile platform. This model incorporates both rigid and flexible links, as well as the payload, enabling a comprehensive study of end-point residual vibration characteristics. The dynamic modeling employed in this study accounts for the interplay of coupled geometric and inertial nonlinearities arising from motion interactions among joints, actuators, and elastic link deflections. The manipulator configuration comprises rigid components and two 3D-flexible links actuated by prismatic and revolute joints, respectively. The flexible links are modelled using Euler–Bernoulli beam elements, while time-dependent in-plane motion is imparted to the rigid link. Utilizing Hamilton’s variational principle, a set of nonlinear governing equations of motion is analytically derived. Subsequently, an independent generalized coordinates system is adopted to transform the equations of motion into a nonlinear reduced form. This is achieved through discretization of the spatio-temporal equations, facilitating the analysis of trajectory dynamics for the robotic manipulator. The residual vibration characteristics at the payload end were explored graphically by applying generalized sinusoidal and bang-bang torque profiles to their respective joints. Nonlinear structural flexibility and material properties emerge as pivotal factors influencing these residual end-point vibrations. It has been observed that the bang-bang torque profile extends the settling period in residual vibration due to its intricate transition characteristics, in contrast to the sinusoidal motion profile with a specific torque duty cycle. Numerical simulations highlight that variations in physical and geometric variables significantly impact end-point residual vibrations and joint deflections, potentially leading to positioning errors in the control of spatial flexible manipulators.

Industrial robots have been widely used in manufacturing automobiles and consumable electronics, logistics, biomedical engineering, and many other industrial sectors. However, the need to enhance their adaptability, accuracy, and autonomy remains high, enabling them to be competent in advanced application scenarios, such as human–robot collaboration, flexible manufacturing, precision engineering, and large-scale automation. This focused section competitively selects the 10 research papers to disseminate new design, planning, and control methodologies of industrial robots toward intelligent automation.

The end effector (gripper) is an important part of a robotic system that is used for industrial and domestic tasks like grasping, carrying, manipulating, assembling, painting, and so on. For handling different types of objects hard as well as soft, require different types of the gripper. The employment of compliant soft-robotic grasping systems, which are characterized by high flexibility in terms of workpiece shape, dimension, and anatomy, is a good method to incorporate greater flexibility into production. The study's major goal is to build and analyses the soft-robotic grippers in terms of repeatability with large payload capacities. End effector (soft gripper) control is crucial for precision work by applying different gripping forces according to the object going to pick. The selection of suitable gripping force for a particular object is done by the process of machine learning (ML). The soft gripper is designed, fabricated, and tested using Industrial Robot (IRB 360) flex picker robot. The virtual environment is created to move the linear path using Robot studio software with rapid programming language. The accuracy, precision, recall, and receiver operating characteristic curve (ROC) curve are analyzed and predict the gripper force accurately with 94% when compared with experimental value. The gripper is working effectively from 1.4 to 2.8 bars with a maximum payload of 500 g. The soft flexible gripper angle is measured based on the pressure using an image processing edge detection technique. The optimized best possible gripping force is predicted using different objects and control action is done to supply exact force to the gripper.

In this study, we propose a novel end-effector that combines the characteristics of winding and scooping fabrics to grasp and categorically place various cloth parts cut by a cutting machine. In addition, we introduce a method for folding the fabric front and back into smaller dimensions, thereby reducing the space required for categorizing, placing, and packaging various clothes, which, to the best of our knowledge, is unique. Subsequently, we develop a method that autonomously determines folding strategies based on the different dimensions of cloth parts, allowing targeted processing of various cloth parts. This approach reduces the height demands of the robot and improves its capability to simultaneously handle multiple types of clothes. Finally, we evaluate the proposed end-effector and folding method in a simulated factory environment using T-shirt parts made of different materials.

The evolution of medical technologies—such as surgical devices and imaging techniques—has transformed all aspects of surgery. A key area of development is robot-assisted minimally invasive surgery (MIS). This review paper provides an overview of the evolution of robotic MIS, from its infancy to our days, and envisioned future challenges. It provides an outlook of breakthrough surgical robotic platforms, their clinical applications, and their evolution over the years. It discusses how the integration of robotic, imaging, and sensing technologies has contributed to create novel surgical platforms that can provide the surgeons with enhanced dexterity, precision, and surgical navigation while reducing the invasiveness and efficacy of the intervention. Finally, this review provides an outlook on the future of robotic MIS discussing opportunities and challenges that the scientific community will have to address in the coming decade. We hope that this review serves to provide a quick and accessible way to introduce the readers to this exciting and fast-evolving area of research, and to inspire future research in this field.

Pipeline detection is a crucial step in ensuring industrial safety. With the rapid advancement of information and sensor technology, research and applications of wireless pipeline inspection robotics have shown an increasing trend, necessitating a comprehensive review of these studies. Broadly, the research on these devices can be divided into two categories: In-Line Inspection (ILI) robots and external-pipeline inspection robots. This survey primarily focuses on the research status of wireless ILI robots. By using some typical robots as examples, this survey introduces key parameters that reflect the performance of ILI robots in tabular formats. These parameters include vehicle-borne sensors, wireless communication methods, cruising time, and applicable pipeline diameters. Finally, this survey summarizes the aforementioned wireless ILI robots and provides the author’s suggestions for their improvement.

There is increasing interests in robotic and computer technologies to accurately perform endovascular intervention. One major limitation of current endovascular intervention—either manual or robot-assisted is the surgical navigation which still relies on 2D fluoroscopy. Recent research efforts are towards MRI-guided interventions to reduce ionizing radiation exposure, and to improve diagnosis, planning, navigation, and execution of endovascular interventions. We propose an MR-based navigation framework for robot-assisted endovascular procedures. The framework allows the acquisition of real-time MR images; segmentation of the vasculature and tracking of vascular instruments; and generation of MR-based guidance, both visual and haptic. The instrument tracking accuracy—a key aspect of the navigation framework—was assessed via 4 dedicated experiments with different acquisition settings, framerate, and time. The experiments showed clinically acceptable tracking accuracy in the range of 1.30–3.80 mm RMSE. We believe that this work represents a valuable first step towards MR-guided robot-assisted intervention.

This paper focuses on Coverage Path Planning (CPP) methodologies, particularly in the context of multi-robot missions, to efficiently cover user-defined Regions of Interest (ROIs) using groups of UAVs, while emphasizing on the reduction of energy consumption and mission duration. Optimizing the efficiency of multi-robot CPP missions involves addressing critical factors such as path length, the number of turns, re-visitations, and launch positions. Achieving these goals, particularly in complex and concave ROIs with No-Go Zones, is a challenging task. This work introduces a novel approach to address these challenges, emphasizing the selection of launch points for UAVs. By optimizing launch points, the mission’s energy and time efficiency are significantly enhanced, leading to more efficient coverage of the selected ROIs. To further support our research and foster further exploration on this topic, we provide the open-source implementation of our algorithm and our evaluation mechanisms.

In this paper, using time domain passivity approach and energy storage capability of the coupling controllers in a bilateral teleoperation system as a storage element, an innovative control method for position-position architecture is proposed which reduces unnecessary conservatism caused by the conventional direction dependent energy monitoring. An ideal value for the energy storage element is obtained and it is shown that the passivity can be guaranteed by restricting the system output energy to some desired values based on the obtained ideal one. Simulation results show the less energy dissipation and improved position tracking in comparison with the conventional approaches.