Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract The significant quality and productivity improvements realized through the adoption of robotic systems in the manufacturing industries have sparked the interest of construction researchers and practitioners to explore their potentials in the construction industry. However, the lack of technical and financial knowledge among construction practitioners concerning robotic applications, the unique nature of construction projects, and fluctuating demand limit the widespread implementation of robotic systems in construction projects. The research present in this paper conducts a narrative review of state-of-the-art and state-of-the-practice of the application of robotic systems in the construction and manufacturing industries to augment automation in industrialized construction by identifying the limitations and potential directions of robotics. The proposed mapping system connects the identified robotic systems to offsite assembly and onsite installation tasks of industrialized construction. The study results revealed that robotics in industrialized construction is considerably under-researched, leaving significant room for improvement. Indeed, only six out of the twenty-five identified industrialized construction tasks, namely panel framing, boxing station, drywall installation, inspection, excavation/site rough grading, and surveying, have been sufficiently explored in the literature. This research intends to educate and inform construction practitioners about the potential integration of existing robotic systems into industrialized construction. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Water current is an important factor in the operation of marine robotic vehicles (MRVs). When cruising in a confined area, the perception of the flow field of this area greatly helps MRVs in path planning and improves energy efficiency. Traditional current observations rely on information obtained through buoys and satellites. It is expensive and time-inefficient. Therefore, using the position and velocity information of the vehicle to predict the flow field can significantly improve the time-efficiency and reduce the cost. Motion tomography is a method that uses vehicle navigation information to estimate current-induced flow and generate a flow field map. This method provides a time-efficient and convenient way to monitor water currents. Bio-inspired robotic fish is an ideal agent for shallow water environmental sensing tasks due to its high maneuverability in grassy environments, low noise propulsion, and multi-functional capabilities. Using trajectory of robotic fish to estimate the flow field can significantly benefit transportation and environmental study. To improve the estimation accuracy, we add an active heading control (AHC) to moderate the passive heading change caused by the flow field. With the position and direction data collected from multiple trips, a vectorized flow map could accurately estimate the flow field. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract In order to protect people from nuclear radiation, nuclear emergency robots are widely used in radiation environment. Except for the obstacle avoidance, these robots should also consider the radiation quantity (or dose rate) and the complex land slope. However, current navigation methods are insufficient to cover all these factors for nuclear emergency robots. In this paper, an autonomous navigation method is proposed for nuclear emergency robots. Firstly, a multi-layer costmap, which includes the costmap of radiation and the costmap of traversability, is proposed as the input of the path planner. Then, an A* algorithm with heuristic function of distance, radiation and slope is employed to search the global path. Finally, a multisensor data fusion algorithm is implemented for the real-time localization and motion control of the robot. Both simulation and real-world experiments demonstrate that the proposed autonomous navigation method can plan a reasonable path and control the robot to reach the target safely in a complex radiation environment. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract The quick deployment of cloud with computing platforms has driven novel tendencies which shifted operations of networks. However, the cloud is facing several security issues and is susceptible because of suspicious tasks and attacks. This paper devises a new method to detect malicious activities in cloud. Here, first step is the simulation of cloud patterns, wherein the data outsourced by the users are utilized for detecting malicious behaviors. The data pre-processing is done to eradicate unnecessary data and noise contained in the data and is performed using a min–max normalization process. The selection of imperative features is done using distance measure, namely Hellinger distance for mining the essential features. The augmentation of data is performed to make the data appropriate for improved processing. The malicious behavior detection is performed by exploiting the Deep Q network wherein training is performed with Autoregressive chimp optimization algorithm (AChOA), which is developed by integrating chimp optimization algorithm (ChOA) and Conditional Autoregressive Value at risk (CAViaR). The proposed AChOA-based Deep Q network outperformed with the highest testing accuracy of 94%, sensitivity of 94.1%, and specificity of 91.4%. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract While robotics has caused leaps in productivity and safety enhancements in several industries, its adoption in construction has been slow due to its perceived complexity and the high cost of implementation. Recently, however, there has been a high level of R&D work in this domain. This paper presents a review of recent publications about new advances in construction robotics. The survey revealed that several technologies (e.g., additive manufacturing; automated installation systems) are being implemented in structural works, interior finishing, exterior finishing, site preparation, lifting, repairs, and drilling. The paper identifies the key efforts that used intelligent tools to allow robots to increase productivity, quality, and safety on construction sites. The paper examines the benefits, the effort it takes, and how intelligence was implemented in various research efforts, as well as identifies common and future trends in this domain. This can contribute to helping researchers and practitioners identify cost-effective means to increase construction productivity/safety through intelligent automation. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract In the agriculture industry, which is the backbone of our country, attaining healthy crops is a critical task. Unidentified crop diseases can cause significant losses in the agriculture sector, thus they must be recognized and detected quickly. Crop infections can be identified and detected correctly, potentially saving harvests from spoilage. Due to the appearance differences and crowded backdrop among crop illnesses, automatic crop disease detection in the wild is a difficult issue in current intelligent agriculture. The main intention of this work is to implement a novel deep learning model for crop disease classification. In the data collection phase, the benchmark dataset is used, which is pre-processed by median filtering, and contrast enhancement techniques. Once the image is pre-processed, the abnormality segmentation from the leaves is performed by the Optimized Fuzzy C-Means Clustering (FCM). The improvement of FCM is done based on hybrid meta-heuristic algorithm with Galactic Swarm Optimization (GSO), and Rider Optimization Algorithm (ROA) called Hybrid Galactic-Rider Optimization Algorithm (HG-ROA). From the segmented images, the TGC features and deep features are concatenated. The TCG features are Texture features, Geometrical features, and Color Features, and the features from the Convolutional Neural Network (CNN) are considered as the deep features. These two sets of features are dimensionally reduced by the Principle Component Analysis (PCA). With these features, the modified Long short-term memory (LSTM) with HG-ROA-based improvement optimally classified the types of diseases from different plants. When compared to traditional approaches, the suggested methodology obtains the best classification accuracy. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Operating a handwheel adopted in the offshore energy industry normally requires tremendous force with accurate motion. It would be a big challenge for mobile robots, especially those deployed on offshore oil platforms. Our work addresses this challenge by designing tools for a mobile robot to operator handwheels employed in two of the most common types of equipment in offshore oil platforms; a watertight door and a gate valve. The operating methodology and the tool design are examined in experiments using real industry equipment and commercially-available lightweight robotic arm. The study also indicates that embedding sensors and actuators leverages the role of the proposed handwheel operation tool being an integrity helper; the tool can collect data and use deep learning technology to monitor the sealing of a valve. Overall, this study demonstrates the feasibility of using the tool to operate handwheels to expand the robot’s operating range and functionality, as well as to provide a low-cost high-accuracy (96%) approach for robot-enabled inspections. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Many studies on the object detection emphasizes the accuracy of the algorithms themselves, while the requirement of real-time processing can be addressed by the usage of “you only look once” (YOLO) model. However, the reliably of machine vision is still a problem since some practical issues are not addressed properly, such as variation of light intensity, reflection of light on the surface and interference of shooting background. In this paper, we address above problems by developing a vision system with YOLO algorithm for object detection, segmentation and localization. A segmentation approach is adopted on the model outputs to extract the object to be detected from the background, under the premise of enhancing the adaptability of the YOLO model to environmental changes. Thus, the influence of background and light-sensitive factors on localization is removed even in extreme lighting conditions. An experimental platform is built based on a pair of low-cost cameras, which verifies the effectiveness of proposed method. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Underwater optical images are widely used in marine exploration. Due to the weak light problem caused by water depth, underwater images generally have the characteristics of background noise, dark brightness, strong blue‒green background color, and blurred images. These characteristics bring great inconvenience to marine exploration tasks. In this way, the study of underwater image enhancement has important application value. Most of the existing underwater image enhancement methods mainly solve the problem of the overall denoising and brightness enhancement of the underwater image while ignoring the partial denoising of the image. To solve these problems, this paper proposes an improved generation adversarial network (GAN) to achieve clear processing of underwater images. The main improvements include three aspects. First, a portion denoising module is added to the generator to weaken the image noise produced by the generator in a detailed manner. Second, the acceleration module is introduced into the discriminator to accelerate the training process of the GAN network. Third, the sum of squares of confrontation loss, contrast loss and color loss is used as a loss function to make the training of the GAN network stable. Extensive experimental results show that the proposed model is superior to the comparison method in both quantitative and qualitative experiments, and the visualization results of the results are natural. PubDate: 2023-09-01
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract This paper provides solutions and insights into a new set of problems of catching a mobile robot intruder using limited information about the intruder’s location. The information about the intruder’s location, which is termed a snapshot, is only available upon request. We formulate the problem of tracking and catching an intruder with limited number of snapshots, which we termed the Moving Target Search with Snapshots (MTSWS). In the MTSWS problem a mobile guard \(G\) is chasing a mobile intruder \(B\) in \(R^{2}\) . Here, \(G\) knows the location of \(B\) either from a requested snapshot or if \(G\) is sufficiently close to \(B\) by sensing it. Sensing is the ability of \(G\) to detect \(B\) directly (e.g., using a directional proximity sensor or a short range camera). The objectives are to determine the number of required snapshots in the worst case and to reduce the distance travelled by \(G\) as it attempts to catch \(B\) (i.e., getting close enough so that it can follow and catch \(B\) without additional information). In this paper we present (1) Solution for computing the number of snapshots that are necessary and sufficient to catch an intruder in the worst case. (2) Algorithmic solutions when \(G\) is limited to using k snapshots by determining the locations and the time that \(G\) should take the snapshots. (3) Algorithmic solution when taking a snapshot is associated with a time penalty. Namely, when \(G\) is taking a snapshot then \(G\) must wait for a period of time before it can move again. The time penalty is applied either before or after taking a snapshot. PubDate: 2023-08-22
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Soft actuators have emerged as a promising solution for applications that conventional actuators are unable to address. Soft pneumatic actuators (SPAs) are widely used among various types of soft actuators due to their good performance and ease of use. However, the control of SPA movement poses challenges due to limited knowledge regarding their behaviours and characteristics, which are significantly influenced by the design. Therefore, this study aims to investigate the impact of three design parameters commonly modified during SPA design: chamber length, number, and wall thickness. Specifically, we examine their effects on the curvature and tip force generated by 3D printed SPAs. In this experimental study, we printed 21 SPAs using fused deposition modelling (FDM) 3D printing technology, employing varying chamber lengths, numbers, and wall thicknesses. The SPAs were then inflated with pressurized air, and the resulting outcomes were measured and analysed. Our findings reveal that increasing the chamber length leads to a reduction in the generated tip force, while also having a minor effect on reducing the curvature. Conversely, the addition of chambers enhances the curvature of the SPA, and diminishes the generated tip force, likely due to the presence of buckling chambers in the mid-body of the SPA. Notably, modifying the wall thickness of the chamber significantly affects the curvature, exerting a larger impact compared to the number of chambers. However, wall thickness does not significantly influence the generated tip force. These findings provide valuable insights for engineers to better comprehend the parameters affecting SPA characteristics, thereby reducing prototyping time and cost. PubDate: 2023-08-19
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Indoor spraying is a crucial component of the construction industry. The future evolution of the spraying industry will inexorably involve the substitution of robot-assisted autonomous spraying for manual spraying. In this paper, a fully autonomous indoor spraying robot is designed to handle a variety of manual spraying issues. At the system level, the robot’s mechanical structure, hardware system, general control logic, and crucial technologies are meticulously constructed. The robot is equipped with a chassis that can travel in any direction, a detachable material carrier, a secondary upgrade mechanism, and a spraying system. The robot performs indoor mapping and navigation with the lidar sensor, identifies non-sprayable areas, such as windows, using the camera, and then evaluates the spraying result after spraying. After analysis of the robot’s working environment, the SLAM algorithm and the deep learning-based object detection algorithm are improved in conjunction with the actual scene to assure accuracy and meet the criteria for real-time operation on embedded devices. The robot’s ability to perform a succession of indoor spraying activities without human intervention and to automatically adapt and adjust to varied indoor conditions is an important reference for its practical application in the field of interior design. PubDate: 2023-08-18
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract The framework of this paper is to present a systematic review of the state-of-the-art development of cooperative dual-arm manipulators in the industrial and household fields. A PRISMA report is exploited to select the inclusion and exclusion criteria of the relevant research articles for the review process. Based on the design, mobility, and application aspects, a sustainable classification of these manipulators is addressed. Thereafter, modeling, planning, control, and visualization techniques are investigated in developing dual-arm manipulators. The classification of control strategy for cooperative dual-arm manipulators is systematically presented in tabulated form based on the control method, targeted force, control architecture, type of uncertainty, and environment of conducted study. The effectiveness of reviewed techniques is highlighted for different dual-arm robotic manipulators. In the end, this paper discusses some of the challenges and future research directions in the field of grasp learning, materials, network communications, sensors, and intelligent controllers. PubDate: 2023-07-14
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract In current trends, Unmanned Aerial vehicles adopt a wide range of services for several applications, such as logistics, rescue operations, and real-time monitoring. UAVs’ are proven be provide a safe and cost-effective solution. Efficient Path planning is crucial to the navigation of UAVs in different environments. However, finding an optimal path is challenging as it is about more than just finding the shortest path but also considering many factors, such as path generation time and path quality. The present work aims to design and develop an efficient algorithm for providing an obstacle-free path approach between two points. The present work proposed a novel path planning scheme (Rapid A*) using a bounded line-of-sight approach to provide a guaranteed solution and achieve motivating results concerning path length and path generation time. We also provide a detailed comparative analysis of the proposed RA* approach with trademark and the latest approaches A*, Beam Search, IDA*, DWA*, and Theta* algorithm. In terms of path generation time and while considering the realistic path, the proposed approach outperforms other approaches and achieves approx 18% less path generation time as compared to A*, Beam Search and Theta* algorithm and 4% less path length as compared to A*, Beam Search, IDA* and DWA* algorithm. PubDate: 2023-07-13
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract This paper takes the motor drive travelling system of vehicles as research object. Addressing the disturbance derived from complex pavement and nonlinearity of system during walking and combined the characteristics of the mathematical model of hydraulic travelling system, a disturbance observer based on exponential convergent is designed on the conditions of the vehicle drives at low speed. It can estimate disturbances online and feedforward compensate to the control system. Then a sliding mode control strategy is used to motor speed control system. The simulation model of valve controlled motor system is carried out through MATLAB/Simulink platform. Compared of the result between the proportion integral differential (PID), sliding mode control (SMC) and sliding mode control (SMC) + disturbance observer (DOB), the oscillation and overshoot of step response on SMC are decreased obviously. When the slow time-varying torque disturbance is added on to evaluate the effects of disturbance observer induced on the SMC, the disturbance value can estimate precisely and deduce influence of motor speed. It improves the SMC + DOB control accuracy and made the vehicle travel on the complex pavement more smoothly. PubDate: 2023-07-12
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract A novel flexible polyimide-based soft jellyfish robot actuated by shape memory alloy (SMA) was fabricated and the pulse and recovery process of the jellyfish has been mimicked. The existing SMA wire-embedded tentacle fabrication technique is a time-consuming and human-tiring process. The proposed structure is novel, cost-effective, and easy to fabricate with very less time consumption compared to conventional mold-based methods. The behavior of the proposed jellyfish structure has been investigated with varying SMA wire diameters and frequencies. The jellyfish tentacle displacement and velocity during mimicking were measured. The temperature modeling of SMA embedded structure and deflection modeling using beam bending theory has been performed. In addition, a preliminary simulation of the jellyfish mimicking has been carried out in Ansys Fluent and the thrust force has been evaluated. The results show that the proposed method can be successfully applied to mimic jellyfish locomotion and extended to underwater applications. The initial prototype has been developed with an onboard camera module and sonar sensor for object detection application with a watertight PDMS bell structure. PubDate: 2023-07-08
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract A collaborative scheme of multiple ground and aerial robots applying a heterogeneous coverage control approach is presented. It aims to provide a density map of a contaminated area from hazardous material. Compared to a homogeneous scheme, heterogeneity enhances the coverage level by minimizing error and variance due to the estimation process. In this scheme, a weighting formulation based on the different characteristics of ground and aerial robots is formalized. The contaminated area is partitioned unequally according to the number of deployed robots corresponding to the robot’s weight and type. It shows better estimation values of the estimated density distribution map than the homogeneous scheme. The operation time needed to provide an estimation map of density distribution over the region is also faster than the homogeneous scheme. PubDate: 2023-06-16 DOI: 10.1007/s41315-023-00288-w
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract Remote control has been the most promising yet challenging problem in robotic manipulation. In this paper, the stabilization control problem of a quadruped robot’s manipulator is described as Euler–Bernoulli beam model. Considering time-delay characteristic of remote-control input or networked motion control input, the target system is presented as delay-wave equations. By formulating the equation into beam-transport cascade system without delay, predictor feedback is estimated. Then, the stabilization controller, which achieve the exponential stability, is proposed based on the derived predictor feedback. Both the stability and well-posedeness are proofed through mathematical analysis. Finally, the simulations are conducted and discussed. Results show the efficiency stability of proposed method. PubDate: 2023-06-13 DOI: 10.1007/s41315-023-00287-x
Please help us test our new pre-print finding feature by giving the pre-print link a rating. A 5 star rating indicates the linked pre-print has the exact same content as the published article.
Abstract: Abstract The gait phase recognition has some broad application prospects, such as lower limb exoskeleton (LLE). To accurately identify the gait phase in different locomotion modes according to gait patterns and corresponding gait characteristics, we define sets of gait phases and propose a gait phase recognition model using plantar pressure sensing signals. The gait phase recognition algorithm based on the multi-layer perceptron (MLP) is used to study the gait phase recognition in walking and running modes. The experimental results show that the gait phase recognition model can recognize the gait phase in different motion modes based on the plantar pressure sensing information. The gait phase recognition of multi-mode locomotion can provide sufficient control logic reference for the powered exoskeleton robot. Through the data of 1052 gait cycles of 4 participants in the experiment, the accuracy of gait recognition for walking mode is 93.9%, and the accuracy of gait recognition for flying state is 76.5%. PubDate: 2023-06-02 DOI: 10.1007/s41315-023-00283-1
Hybrid journal (It can contain Open Access articles)
[2468 journals]
