Search

Simple Summary: In the process of large-scale cage chicken breeding, using inspection robots instead of manual detection can solve the problems of large workload and low detection efficiency. However, poor driving stability of an inspection robot will lead to low inspection accuracy. In order to ensure high efficiency, accuracy, and stability of detection, this study takes the stability of visual navigation for inspection robots as the optimization goal, and designs an efficient and accurate road extraction algorithm and a navigation line fitting algorithm with better robustness. The experimental results show that the algorithm proposed in this study can improve the stability of detection, achieve a faster running speed, and achieve a better detection effect and a higher detection efficiency while keeping the detection effect unchanged. The navigation algorithm can accelerate the automation process of large-scale cage chicken breeding and promote the realization of fast and accurate monitoring. The speed and accuracy of navigation road extraction and driving stability affect the inspection accuracy of cage chicken coop inspection robots. In this paper, a new grayscale factor (4B-3R-2G) was proposed to achieve fast and accurate road extraction, and a navigation line fitting algorithm based on the road boundary features was proposed to improve the stability of the algorithm. The proposed grayscale factor achieved 92.918% segmentation accuracy, and the speed was six times faster than the deep learning model. The experimental results showed that at the speed of 0.348 m/s, the maximum deviation of the visual navigation was 4 cm, the average deviation was 1.561 cm, the maximum acceleration was 1.122 m/s2, and the average acceleration was 0.292 m/s2, with the detection number and accuracy increased by 21.125% and 1.228%, respectively. Compared with inertial navigation, visual navigation can significantly improve the navigation accuracy and stability of the inspection robot and lead to better inspection effects. The visual navigation system proposed in this paper has better driving stability, higher inspection efficiency, better inspection effect, and lower operating costs, which is of great significance to promote the automation process of large-scale cage chicken breeding and realize rapid and accurate monitoring. [ABSTRACT FROM AUTHOR]

Computer vision technology has been widely applied in reading recognition of analog meters. However, it is still a challenge to quickly and accurately read various types of analog meters under different environmental conditions. We propose a fast-reading method for analog meters based on keypoint detection, which is applied to inspection robots. First, we use the YOLOv5s network to locate the analog meter. Second, the HRNet network is used to detect the keypoints of the pointer and scale on the dial. Third, an objective image quality assessment method that includes multiple indicators is established to select the optimal image for reading recognition. Finally, we calculate the reading of the analog meter based on the deflection angle of the pointer. The experiment shows that our method can accurately read the readings of analog meters, with an average reading error of 3.81%. It can be effectively applied to inspection robots to read analog meter readings. [ABSTRACT FROM AUTHOR]

The current research on obstacle avoidance path planning methods for power inspection robots has problems such as poor obstacle avoidance ability and poor inspection effectiveness. Therefore, a planning method for obstacle avoidance path of power inspection robots is proposed. By utilizing motion relationships and the potential field theorem of robot motion, a three-dimensional model of the power inspection robot's route is established to determine the direction of the robot's route when obtaining action tasks. The fuzzy support vector algorithm is used to plan obstacle avoidance paths for the initialized walking path, making the inspection robot intelligent. The experimental results show that the average success rates for avoiding static and dynamic obstacles are 98.37% and 96.12%, respectively. The average time for obstacle avoidance path planning is 1.56 seconds, and it has fast, efficient, and accurate obstacle avoidance and path planning capabilities, which can improve the robot's obstacle avoidance ability and path planning efficiency for dynamic and static obstacles. [ABSTRACT FROM AUTHOR]

In view of the lack of advanced and mature substation fault detection and facility detection technology, combined with the characteristics of the actual application environment of substation, a substation operating equipment autonomous monitoring and fault diagnosis detection system based on deep learning intelligent detection robot is proposed. That is, the deep learning algorithm, Big data analysis technology and patrol robot with HD camera are organically combined. The image information collected by the high-definition camera is fused with the data information collected by a variety of sensors, and then the fault tree and Big data analysis algorithm are used to carry out real-time intelligent detection and analysis of all equipment in the substation, and the early warning can be sent to the relevant equipment maintenance personnel in a timely manner. The experimental results indicate that, the number of input nodes in the fault tree is 7, the number of output nodes is 2, the number of center vectors is 14, the number of nodes in the basis function layer is 7, and the threshold of the basis function is set to 0.8257. In actual training, after 31 iterations, the training results can quickly converge to the target value, the training error meets the requirements, and the fault diagnosis accuracy reaches over 90%. It has been proven that the diagnostic performance of the system is good, achieving the expected design effect. [ABSTRACT FROM AUTHOR]

To ensure the operational safety of nuclear power plants, we present a Quadruped Inspection Robot that can be used for many types of steam generators. Since the Inspection Robot relies on the Holding Modules to grip the tube-sheet, it can be regarded as a hybrid robot with variable configurations, switching between 4-RRR-RR, 3-RRR-RR, and two types of 2-RRR-RR, and the variable configurations bring a great challenge to dimensional synthesis. In this paper, the kinematic model of the Inspection Robot in multiple configurations is established, and the analytical solution is given. The workspace mapping is analyzed by the solution-space, and the workspace of multiple configurations is decomposed into the workspace of 2-RRR to reduce the analysis complexity, and the workspace calculation is simplified by using the envelope rings. The optimization problem of the manipulator is transformed into the calculation of the shortest contraction length of the swing leg. The switching performance of the Inspection Robot is evaluated by stride-length, turning-angle, and workspace overlap-ratio. The performance indexes are classified and transformed based on the proportions and variation trends of dimensional parameters to reduce the number of optimization objective functions, and Pareto optimal solutions are obtained using an intelligent optimization algorithm.

In recent years, coal mine robots have become a research hotspot in the field of modern coal machine equipment, and the main coal flow transportation system of most coal mines has basically realized continuity, mechanization and automation, which also puts forward higher requirements for safety monitoring and inspection efficiency in the main transportation roadway, and accurate target detection is a necessary guarantee for intelligent safety monitoring in coal mines, but the existing object detection algorithm is applied to complex and harsh coal mine underground roadway environment, and there is a problem of low target detection accuracy. Aiming at the special working condition detection requirements of low lighting and chaotic environment in the downhole, the target data set in the underground roadway environment was produced, and the dataset annotation was completed and multi-dimensional analysis was carried out. A PT target detection algorithm based on the fusion of pyramid structure and attention mechanism is proposed, and the attention mechanism module is used to replace the convolution module in the pyramid structure, which improves the extraction ability of global features while controlling the amount of feature calculation, realizes the extraction effect of the fusion of local features and global features of the target, and improves the expression ability of the features of the target area of interest in the image. Finally, for the application scenario of underground inspection robot in coal mine, the proposed PT algorithm is compared with the traditional Faster R-CNN and YOLOv4 algorithms. Compared with the mainstream Faster R-CNN and YOLOv4 target detection networks, the PT algorithm has better comprehensive recognition capabilities, and the accuracy of identifying coal mine personnel is increased by 2.90% and 4.30%, the accuracy of identifying underground obstacles is increased by 0.20% and 4.80%, and the accuracy of identifying mine cracks is increased by 4.40% and 8.60%, respectively. The accuracy rate of identifying downhole equipment was improved by 3.00% and 8.70%, respectively. Therefore, the PT target detection algorithm can better adapt to the underground environment, and the target detection algorithm can obtain higher accuracy and detection speed than other algorithms, which can provide theoretical basis and technical support for the construction of underground roadway security control system.

Substation secondary equipment is monitored through inspection robots, providing an important means to enhance power equipment automation and intelligent management, thereby ensuring the safe operation of power engineering equipment. In this paper, a Mecanum wheeled omnidirectional mobile robot is developed for automatically inspecting secondary equipment in substations. It possesses autonomous navigation, positioning, and identification capabilities, significantly enhancing inspection efficiency and the accuracy of protection plate state identification. The Mecanum wheels enable the inspection robot to move flexibly and adjust its attitude within narrow working environments. Meanwhile, a multi-track lifting platform facilitates image acquisition and state identification of the secondary equipment pressure plate, covering a height range of 350-1 800 mm. The robot employs the lidar-based simultaneous localization and mapping (SLAM) method for autonomous positioning and navigation, supplemented by a vision-based path extraction and tracking algorithm for precise position correction at set points. Moreover, a color recognition-based image arrangement and state recognition method is proposed to accurately identify and assess the connection state of the secondary equipment protection plate. Experimental results demonstrate that the substation secondary equipment inspection robot, utilizing Mecanum wheels, achieves successful autonomous navigation and precise positioning, with maximum deflection angles and distances during path tracking processes being ±3° and ±8 mm, respectively. Additionally, the plate recognition method, combining machine vision and color recognition, achieves an outstanding recognition accuracy rate exceeding 95.80%, thereby elevating the level of robot automation in inspection operations.

The crawler-type maintenance robot designed for the steam generator in nuclear power plants faces challenges such as inadequate adaptability and low maintenance efficiency. In order to address the task of maintaining multiple specifications of heat transfer tubes in the steam generator, a novel quadruped crawling maintenance robot with a new mechanism was proposed and gait planning was conducted. Firstly, the configuration and overall design of the robot were determined based on the requirements to adapt to multiple specifications of tube plates, and the main motion mode of the crawling robot was identified, along with providing the workspace for tools. Subsequently, research on gait planning was conducted for different types of tube plates, including planning linear motion gaits and turning motion gaits on tube plates arranged in triangular and square patterns. Finally, the motion simulation experiments of the robot were conducted through a joint simulation of V-REP and Python. The results demonstrate that the crawling robot can execute linear and turning motions on tube plates of various specifications, showcasing the rationality of the mechanism and the feasibility of the motion. [ABSTRACT FROM AUTHOR]

Copyright of Journal of China University of Petroleum is the property of China University of Petroleum and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Visual simultaneous localization and mapping (VSLAM) is a foundational technology that enables robots to achieve fully autonomous locomotion, exploration, inspection, and more within complex environments. Its applicability also extends significantly to agricultural settings. While numerous impressive VSLAM systems have emerged, a majority of them rely on static world assumptions. This reliance constrains their use in real dynamic scenarios and leads to increased instability when applied to agricultural contexts. To address the problem of detecting and eliminating slow dynamic objects in outdoor forest and tea garden agricultural scenarios, this paper presents a dynamic VSLAM innovation called MOLO-SLAM (mask ORB label optimization SLAM). MOLO-SLAM merges the ORBSLAM2 framework with the Mask-RCNN instance segmentation network, utilizing masks and bounding boxes to enhance the accuracy and cleanliness of 3D point clouds. Additionally, we used the BundleFusion reconstruction algorithm for 3D mesh model reconstruction. By comparing our algorithm with various dynamic VSLAM algorithms on the TUM and KITTI datasets, the results demonstrate significant improvements, with enhancements of up to 97.72%, 98.51%, and 28.07% relative to the original ORBSLAM2 on the three datasets. This showcases the outstanding advantages of our algorithm. [ABSTRACT FROM AUTHOR]

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

High-precision positioning and multi-target detection have been proposed as key technologies for robotic path planning and obstacle avoidance. First, the Cartographer algorithm was used to generate high-quality maps. Then, the iterative nearest point (ICP) and the occupation probability algorithms were combined to scan and match the local point cloud, and the positions and attitudes of the robot were obtained. Furthermore, Sparse Matrix Pose Optimization was carried out to improve the positioning accuracy. The positioning accuracy of the robot in x and y directions was kept within 5 cm, the angle error was controlled within 2°, and the positioning time was reduced by 40%. An improved timing elastic band (TEB) algorithm was proposed to guide the robot to move safely and smoothly. A critical factor was introduced to adjust the distance between the waypoints and the obstacle, generating a safer trajectory, and increasing the constraint of acceleration and end speed; thus, smooth navigation of the robot to the target point was achieved. The experimental results showed that, in the case of multiple obstacles being present, the robot could choose the path with fewer obstacles, and the robot moved smoothly when facing turns and approaching the target point by reducing its overshoot. The proposed mapping, positioning, and improved TEB algorithms were effective for high-precision positioning and efficient multi-target detection. [ABSTRACT FROM AUTHOR]

With the continuous acceleration of urbanization, traffic congestion, traffic accidents, and urban environmental problems are becoming increasingly serious, which negatively impacts the lives of city residents. With today's urbanization trend, traffic management is a pressing issue, and the safety and smoothness of highways profoundly affect a city's economy and quality of life. As a result, the intelligent inspection robot has entered the public view. It has the advantages of stability and efficiency, can continue to work in a high-intensity state, and helps reduce a lot of human workloads. Firstly, an intelligent transport monitoring system based on the Internet of Things (IoT) is proposed. This system integrates deep learning and artificial intelligence technology, which can quickly query traffic parameters, environmental parameters, and violations that may cause traffic accidents. Secondly, an intelligent inspection robot is introduced to monitor road traffic flow and violation records in real-time, which provides technical support for further scientific management of road traffic. Finally, the intelligent monitoring system's sensitivity and improvement measures are analyzed using the Simultaneous Localization and Mapping (SLAM) algorithm results, making intelligent traffic monitoring more popular. A section of closed safety road is selected for the inspection robot test. The results reveal that (1) the urban transportation model based on the IoT can meet the architecture of intelligent urban transportation. (2) Considering the performance of the inspection robot, the SLAM algorithm is more suitable for road intelligent traffic monitoring. (3) When the number of particles in the improved SLAM algorithm is small, the accuracy and real-time performance of the algorithm can also be guaranteed. The calculation efficiency is improved to 80%, and the modeling accuracy is improved by 23.3%. Traditional traffic monitoring methods typically rely on static sensors and limited data sources. However, the proposed system leverages IoT technology's and inspection robots' real-time data collection capabilities, achieving a more comprehensive, accurate, and flexible acquisition of traffic data. Through this exploration, the overall ideas and objectives of the construction of intelligent highways are clarified, which will lay a solid foundation for the follow-up construction of intelligent highways and provide comprehensive design and practical ideas. The improved SLAM algorithm can more stably complete the positioning and mapping of the tunnel inspection robot in the road environment. In the SLAM algorithm, an Extended Kalman Filter is introduced to ensure the accuracy and real-time of the improved algorithm, which can be applied to the modeling and positioning of unknown environments. Consequently, using the SLAM algorithm in the road detection robot system can stably realize environment awareness and autonomous path planning. [ABSTRACT FROM AUTHOR]

Copyright of Electric Power Engineering Technology is the property of Editorial Department of Electric Power Engineering Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, the potential of robotic harvesting in greenhouse tomato production has garnered significant attention within the tomato industry. However, there is a lack of sufficient research on the complete replacement of manual harvesting with this technology. In this paper, we propose a tomato harvesting method that utilizes a nesting approach to simplify the process and minimize damage. The paper describes the tomato harvesting robot prototype, the visual system equipped with three vision‐based tomato detectors: YOLOv5_CBAM, which incorporates a convolutional block attention module; YOLOv5_SE, enhanced with a squeeze‐and‐excitation block; and a standard YOLOv5s model. Additionally, a novel shear gripping method for fruit bunches is presented, utilizing a bottom‐up snapping technique during harvesting. Point cloud data are utilized to determine the position of the tomato's main stem and bunch. The paper includes field tests and experimental findings, which indicate that the YOLOv5_CBAM model achieves the highest precision (82.62%) and recall (82.57%), outperforming YOLOv5_SE and standard YOLOv5s. Field experiments demonstrate that the improved end‐effector and vision system have significantly enhanced the robot's performance, achieving a 57.5% harvesting success rate in just 14.9 s. [ABSTRACT FROM AUTHOR]

Copyright of Chinese Medical Equipment Journal is the property of Chinese Medical Equipment Journal Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The speed and accuracy of navigation road extraction and driving stability affect the inspection accuracy of cage chicken coop inspection robots. In this paper, a new grayscale factor (4B-3R-2G) was proposed to achieve fast and accurate road extraction, and a navigation line fitting algorithm based on the road boundary features was proposed to improve the stability of the algorithm. The proposed grayscale factor achieved 92.918% segmentation accuracy, and the speed was six times faster than the deep learning model. The experimental results showed that at the speed of 0.348 m/s, the maximum deviation of the visual navigation was 4 cm, the average deviation was 1.561 cm, the maximum acceleration was 1.122 m/s2, and the average acceleration was 0.292 m/s2, with the detection number and accuracy increased by 21.125% and 1.228%, respectively. Compared with inertial navigation, visual navigation can significantly improve the navigation accuracy and stability of the inspection robot and lead to better inspection effects. The visual navigation system proposed in this paper has better driving stability, higher inspection efficiency, better inspection effect, and lower operating costs, which is of great significance to promote the automation process of large-scale cage chicken breeding and realize rapid and accurate monitoring.

This paper discusses the development and design of two wheeled-type In-Pipe Inspection Robots (IPIRs), Kuzhali I and Kuzhali II, which were created to address the limitations of traditional human inspection methods and earlier robot designs. Specifically, the robots aim to overcome the motion singularity experienced by IPIRs when navigating through curved pipes. Kuzhali I was developed with wheels mounted at an asymmetric angle, which enables the wheels to maintain contact with the pipe's surface, preventing motion singularity. However, Kuzhali I had limitations due to its prismatic mechanism, and thus Kuzhali II was developed with a telescopic mechanism to allow it to pass through vertical pipes with obstacles. Motion analysis was conducted on both robots to demonstrate how they overcome motion singularity and navigate through straight and curved pipelines. Simulation results showed that the forces acting on the robots' wheels fell within 5 N to 12 N, demonstrating stability while navigating pipeline junctions. Experimental tests were conducted on Kuzhali II, and the results were compared to simulation results, showing an error of less than 5%. The results of the experiments indicate that Kuzhali II is safe to use for pipeline inspection, can navigate through vertical pipelines with ease and can overcome motion singularity in curved pipes. These robots offer a faster, more accurate, and safer alternative to human inspection, which can reduce the risk of pipeline failures and associated environmental and safety hazards. [ABSTRACT FROM AUTHOR]

In view of the high cost of crack and seepage detection in the traditional artificial pumped storage station and the difficulty of ensuring the detection accuracy, a set of inspection robot system based on machine vision is designed in this study. A convolutional neural network which combines cross entropy and dice cost function is constructed, and an evaluation function based on total pixel accuracy, cross parallel ratio and F1 score is established to ensure the accurate detection of common cracks. In order to verify the effectiveness of the designed robot inspection system, convolutional neural network is tested in this study, and its performance is compared with common computer vision methods and manual detection methods. The comparison results show that the neural network constructed in this study has obvious progress in detection accuracy and detection efficiency. [ABSTRACT FROM AUTHOR]

This paper presents an anti-swing control method to prevent situations where inspection robots detach and fall off transmission lines during obstacle crossing due to excessive swing angles caused by the rotation of the robot around the transmission line. Firstly, an obstacle-crossing model for the inspection robot was constructed and the causes of robot swinging phenomena were analyzed, in addition to their impact on obstacle crossing stability. By combining this with the obstacle-crossing model, a moment balance equation was established for the inspection robot. This equation can be used to solve mapping relationships between body offset and the tilt angle of transmission line gripping arms. We propose an anti-swing control strategy by adjusting the angle of the transmission line gripping arm's pitching joint to make the body offset approach zero, and by utilizing the advantages of fuzzy logic in the fuzzy PID algorithm compared with the traditional PID algorithm, it can adaptively avoid the occurrence of robot swinging phenomena. The experimental results of obstacle-crossing experiments under no wind and wind turbulence conditions indicated that the proposed anti-swing control method in this study can effectively keep the body offset to within 3 mm. Compared with the methods of not using anti-swing control and using traditional PID anti-swing control, in the absence of wind effects, the peak values of body offset were reduced by 96.53% and 18.85%, respectively. Under the influence of wind turbulence, the peak values of body offset were reduced by 97.02% and 27.12%, respectively. The effectiveness of the anti-swing control method proposed in this paper has thus been verified. [ABSTRACT FROM AUTHOR]

With the development of intelligent substations, inspection robots are widely used to ensure the safe and stable operation of substations. Due to the prevalence of grass around the substation in the external environment, the inspection robot will be affected by grass when performing the inspection task, which can easily lead to the interruption of the inspection task. At present, inspection robots based on LiDAR sensors regard grass as hard obstacles such as stones, resulting in interruption of inspection tasks and decreased inspection efficiency. Moreover, there are inaccurate multiple object-detection boxes in grass recognition. To address these issues, this paper proposes a new assistance navigation method for substation inspection robots to cross grass areas safely. First, an assistant navigation algorithm is designed to enable the substation inspection robot to recognize grass and to cross the grass obstacles on the route of movement to continue the inspection work. Second, a three-layer convolutional structure of the Faster-RCNN network in the assistant navigation algorithm is improved instead of the original full connection structure for optimizing the object-detection boxes. Finally, compared with several Faster-RCNN networks with different convolutional kernel dimensions, the experimental results show that at the convolutional kernel dimension of 1024, the proposed method in this paper improves the mAP by 4.13% and the mAP is 91.25% at IoU threshold 0.5 in the range of IoU thresholds from 0.5 to 0.9 with respect to the basic network. In addition, the assistant navigation algorithm designed in this paper fuses the ultrasonic radar signals with the object recognition results and then performs the safety judgment to make the inspection robot safely cross the grass area, which improves the inspection efficiency. [ABSTRACT FROM AUTHOR]

Visual simultaneous localization and mapping (VSLAM) is a foundational technology that enables robots to achieve fully autonomous locomotion, exploration, inspection, and more within complex environments. Its applicability also extends significantly to agricultural settings. While numerous impressive VSLAM systems have emerged, a majority of them rely on static world assumptions. This reliance constrains their use in real dynamic scenarios and leads to increased instability when applied to agricultural contexts. To address the problem of detecting and eliminating slow dynamic objects in outdoor forest and tea garden agricultural scenarios, this paper presents a dynamic VSLAM innovation called MOLO-SLAM (mask ORB label optimization SLAM). MOLO-SLAM merges the ORBSLAM2 framework with the Mask-RCNN instance segmentation network, utilizing masks and bounding boxes to enhance the accuracy and cleanliness of 3D point clouds. Additionally, we used the BundleFusion reconstruction algorithm for 3D mesh model reconstruction. By comparing our algorithm with various dynamic VSLAM algorithms on the TUM and KITTI datasets, the results demonstrate significant improvements, with enhancements of up to 97.72%, 98.51%, and 28.07% relative to the original ORBSLAM2 on the three datasets. This showcases the outstanding advantages of our algorithm.

High-precision positioning and multi-target detection have been proposed as key technologies for robotic path planning and obstacle avoidance. First, the Cartographer algorithm was used to generate high-quality maps. Then, the iterative nearest point (ICP) and the occupation probability algorithms were combined to scan and match the local point cloud, and the positions and attitudes of the robot were obtained. Furthermore, Sparse Matrix Pose Optimization was carried out to improve the positioning accuracy. The positioning accuracy of the robot in x and y directions was kept within 5 cm, the angle error was controlled within 2°, and the positioning time was reduced by 40%. An improved timing elastic band (TEB) algorithm was proposed to guide the robot to move safely and smoothly. A critical factor was introduced to adjust the distance between the waypoints and the obstacle, generating a safer trajectory, and increasing the constraint of acceleration and end speed; thus, smooth navigation of the robot to the target point was achieved. The experimental results showed that, in the case of multiple obstacles being present, the robot could choose the path with fewer obstacles, and the robot moved smoothly when facing turns and approaching the target point by reducing its overshoot. The proposed mapping, positioning, and improved TEB algorithms were effective for high-precision positioning and efficient multi-target detection.

The reliability of the inspection robot in the fully mechanized working face is low due to the lack of scale information. In order to solve the above problem, virtual reality (VR) technology is introduced into the inspection of fully mechanized working face. A fully mechanized working face inspection system based on simultaneous localization and mapping (SLAM) and VR is designed. The system includes two parts: an inspection robot subsystem located underground and a VR real-time rendering subsystem located on the ground. The inspection robot subsystem utilizes laser SLAM technology to achieve real-time 3D scanning and establish a 3D map. At the same time, a panoramic camera is used to capture the scene of the fully mechanized working face in real-time. The real-time obtained laser point cloud and panoramic video are transmitted to the VR real-time rendering subsystem. The VR real-time rendering subsystem uses GPU acceleration technology to color laser point clouds. By customizing the rendering part of the Unreal 3D engine, real-time rendering of the laser point cloud is achieved, and the laser point cloud is projected onto the VR glasses. Remote operators obtain real-time 3D scenes through VR glasses, and remotely control the movements of the inspection robot through the operating handle. The fully mechanized working face inspection based on the first perspective is achieved. The underground industrial test results show that the system can achieve free switching of perspectives and zoom in on the scene. It enables better observation of details, with higher accuracy and reliability. By using GPU acceleration technology for point cloud coloring, the processing time is significantly shorter than CPU processing time. GPU has higher real-time performance, and the entire system's latency can meet the requirements of inspection tasks.

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Global path planning is one of the key technologies for airport energy station inspection robots to achieve autonomous navigation. Due to the complexity of airport energy station buildings with numerous mechanical and electrical equipment and narrow areas, planning an optimal global path remains a challenge. This paper aimed to study global path planning for airport energy station inspection robots using an improved version of the Grey Wolf Optimizer (IGWO) algorithm. Firstly, the initialization process of the Grey Wolf Optimizer algorithm selects several grey wolf individuals closer to the optimal solution as the initial population through the lens imaging reverse learning strategy. The algorithm introduces nonlinear convergence factors in the control parameters, and adds an adaptive adjustment strategy and an elite individual reselection strategy to the location update to improve the search capability and to avoid falling into local optima. Benchmark function and global path planning simulation experiments were carried out in MATLAB to test the proposed algorithm's effectiveness. The results showed that compared to other swarm intelligent optimization algorithms, the proposed algorithm outperforms them in terms of higher convergence speed and optimization accuracy. Friedman's test ranked this algorithm first overall. The algorithm outperforms others in terms of average path length, standard deviation of path length, and running time. [ABSTRACT FROM AUTHOR]

To ensure the safe operation of high-voltage transmission line inspection robots during downhill descents without power and extend their range after a single charge, this paper proposes an energy-saving speed control method for the inspection robot's walking wheel motor on downhill slopes by integrating feedback braking and fuzzy PID control. By combining the parameter equation of the overhead catenary line and the structural characteristics of the overhead transmission line, this paper analyzes the relationship between the driving torque of the inspection robot's wheels and the horizontal displacement along the transmission ground wire before and after descending. Based on this analysis, a speed control and energy recovery scheme is developed for the inspection robot, which combines front-wheel feedback braking with rear-wheel regenerative braking. The fuzzy PID method is utilized to adjust the PWM duty cycle to achieve energy-efficient speed control of the inspection robot's rear walking wheels. Additionally, to improve the energy density and specific power of the robot's energy storage unit, a composite power source consisting of lithium batteries and supercapacitors is employed to recover energy from the front walking wheels through feedback braking. The combined simulation results indicate that, compared to fuzzy control and PID control, fuzzy PID control better regulates the robot's speed under varying slopes, wind resistance, and cable roughness. A downhill speed control system for the inspection of the robot's walking wheel motor was designed, and its effectiveness was validated through simulated high-voltage line experiments. The fuzzy PID control was demonstrated to effectively maintain the rear walking wheel speed within the targeted range during downhill descents. When descending along a fixed 30° angle cable, the fuzzy PID control resulted in an increase of 5.28% and 14.26% in the state of charge (SOC) of the supercapacitor compared to PID control and fuzzy control, respectively. Moreover, when descending along fixed angle cables of 10°, 20°, and 30°, as well as a variable angle cable ranging from 30° to 0°, the SOC of the supercapacitor increased by 17.55%, 26.25%, 38.45%, and 31.29%, respectively. This demonstrates the effective absorption of regenerative braking energy during the robot's downhill movement. [ABSTRACT FROM AUTHOR]

Copyright of Nonferrous Metals (Mineral Processing Section) is the property of Beijing Research Institute of Mining & Metallurgy Technology Group and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The regular detection of weld seams in large-scale special equipment is crucial for improving safety and efficiency, and this can be achieved effectively through the use of weld seam tracking and detection robots. In this study, a wall-climbing robot with integrated seam tracking and detection was designed, and the wall climbing function was realized via a permanent magnet array and a Mecanum wheel. The function of weld seam tracking and detection was realized using a DeepLabv3+ semantic segmentation model. Several optimizations were implemented to enhance the deployment of the DeepLabv3+ semantic segmentation model on embedded devices. Mobilenetv2 was used to replace the feature extraction network of the original model, and the convolutional block attention module attention mechanism was introduced into the encoder module. All traditional 3×3 convolutions were substituted with depthwise separable dilated convolutions. Subsequently, the welding path was fitted using the least squares method based on the segmentation results. The experimental results showed that the volume of the improved model was reduced by 92.9%, only being 21.8 Mb. The average precision reached 98.5%, surpassing the original model by 1.4%. The reasoning speed was accelerated to 21 frames/s, satisfying the real-time requirements of industrial detection. The detection robot successfully realizes the autonomous identification and tracking of weld seams. This study remarkably contributes to the development of automatic and intelligent weld seam detection technologies. [ABSTRACT FROM AUTHOR]

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

At present, the track type robot is widely used in the inspection robot of the fully mechanized working face. When the robot passes through the track connection, it will produce jitter. It causes an increase in the positioning error of the inertial navigation/odometer combination. In order to solve this problem, based on the integrated navigation algorithm of inertial navigation/odometer, a piecewise filtering method based on jitter detection is adopted to achieve autonomous positioning of the inspection robot. Based on the gyroscope data of the inspection robot passing through the track connector, a sliding window method is used to dynamically analyze the pitch angular velocity of the robot. The local maximum rising edge and local maximum falling edge are determined by calculating the derivative sum. When the maximum rising edge and maximum falling edge alternately appear, it is considered that the track connector has been recognized. The jitter detection is achieved, thus dividing the robot's motion state into stable operation state and jitter state. When the robot is in a stable operation state, both the gyroscope and odometer data are relatively stable. At this time, the inertial navigation/odometer combination navigation method is used for filtering and solving. The gyroscope error is corrected based on the characteristic that the gyroscope data should be stable near zero. When the robot is in a jitter state, the odometer may generate errors due to wheel slip and bouncing in the air. At this time, a pure inertial navigation algorithm is used to eliminate the impact of odometer errors on the integrated navigation positioning. The experimental results show that the jitter detection algorithm can accurately determine the track connections. The segmented filtering method based on jitter detection can effectively improve the positioning precision of the inspection robot. The average positioning error is less than 5 mm, meeting the precise positioning requirements of the fully mechanized working face.

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Factory safety inspections are crucial for maintaining a secure production environment. Currently, inspections are predominantly performed manually on a regular basis, leading to low efficiency and a high workload. Utilizing inspection robots can significantly improve the reliability and efficiency of these tasks. The development of robot localization and path planning technologies ensures that factory inspection robots can autonomously complete their missions in complex environments. In response to the application requirements of factory inspections, this paper investigates mapping, localization, and path planning methods for robots. Considering the limitations of cameras and laser sensors due to their inherent characteristics, as well as their varying applicability in different environments, this paper proposes SLAM application systems based on multi-line laser radar and visual perception for diverse scenarios. To address the issue of low efficiency in inspection tasks, a hybrid path planning algorithm that combines the A-star algorithm and time elastic band method is introduced. This approach effectively resolves the problem of path planning becoming trapped in local optima in complex environments, subsequently enhancing the inspection efficiency of robots. Experimental results demonstrate that the designed SLAM and path planning methods can satisfy the inspection requirements of robots in complex scenarios, exhibiting excellent reliability and stability. [ABSTRACT FROM AUTHOR]

The coal mine wind shaft is an important ventilation channel in coal mines, and it is of great significance to ensure its long-term safety. At present, the inspection of wind shafts still depends on manual work, which has low reliability and high risk. There are two main problems in the shaft wall detection of ventilation shafts: (1) The humidity and dust concentration in ventilation shafts are high, which makes imaging difficult; (2) the cracks on the shaft wall are long and irregular, so it is impossible to acquire the information of the whole crack from a single photo. Firstly, the mapping analysis between the concentration of water vapor and dust in the wind shaft and the image definition is determined by experiments. Then, the inspection robot is designed to move along the axial and circumferential directions to get close to the shaft wall, and the rack-and-rail drive design is adopted to ensure the real-time position feedback of the robot. Then, through the crack parameter detection method based on depth learning, the movement direction of the robot is controlled according to the crack direction so as to ensure that the complete crack parameters are obtained. Finally, the crack detection algorithm is verified by experiments. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The problems of narrow space, frequent operation of equipment and complex positional relationship in coal mine fully-mechanized mining face make it difficult for the conventional inspection robot to run directly on the mining face and automated monitoring. According to the requirements of working conditions, combined with the environment and the action characteristics of equipment group, the design requirements of working face inspection track are proposed. A new type of flexible track for cross-seat inspection robot is designed by using modular design, simulation, and prototype test methods to realize the installation and adjustment of the working face environment and the adaptive compensation of the track itself when the installation equipment moves and deforms. Firstly, the mechanical structure of the flexible track of the inspection robot is designed and the installation operation mode is determined. Secondly, taking the track spanning on the side of the cable groove of the scraper conveyor as an example, the bending and pitching deformation of the scraper conveyor under three different working conditions of straightness, bending and fluctuation are analyzed and the kinematics simulation of the flexible track is carried out. Under three working conditions, the track can be completed with horizontal bending 0~5.4°, vertical inclination of 0~6° and telescopic deformation 0~120 mm with the working face equipment to meet the actual working conditions. When the inspection robot on board passes through the flexible track under three different working conditions, it can always maintain uniform linear motion in the main operating direction, and the horizontal or vertical direction fluctuates in the flexible transition section, and the amplitude of the fluctuation is within the safe allowable range. Finally, the physical prototype of the flexible track and the test platform of the working face are built to verify the performance of the flexible track of the working face inspection robot. The results show that the flexible track structure is designed reasonably and can be adapted to different working conditions of the mining face inspection. It is of great significance to realize the inspection of the robot in the fully mechanized working face under the coal mine.