Search

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.)

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.)

Copyright of Control Theory & Applications / Kongzhi Lilun Yu Yinyong is the property of Editorial Department of Control Theory & Applications 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 Journal of Xihua University (Natural Science Edition) is the property of Xihua University 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 path tracking control of electric mining articulated vehicles (EMAVs), critical equipment commonly used for mining and transportation in underground mines, is a research topic that has received much attention. The path tracking control of EMAVs is subject to several system constraints, including articulation angle and articulation angular velocity. In light of this, many researchers have initiated studies based on model predictive control (MPC). The principal design schemes for existing MPC methods encompass linear MPC (LMPC) utilizing a single reference point, so named the single reference point LMPC (SRP-LMPC), and nonlinear MPC (NMPC). However, NMPC exhibits suboptimal real-time performance, while SRP-LMPC demonstrates inferior accuracy. To simultaneously improve the accuracy and real-time performance of the path tracking control of EMAV, based on the SRP-LMPC, a path tracking control method for EMAV based on nonlinear compensated multiple reference points LMPC (MRP-LMPC) is proposed. The simulation results demonstrate that MRP-LMPC simultaneously exhibits a commendable degree of accuracy and real-time performance. In all simulation results, the displacement error amplitude and heading error amplitude of MRP-LMPC do not exceed 0.2675 m and 0.1108 rad, respectively. Additionally, the maximum solution time in each control period is 5.9580 ms. The accuracy of MRP-LMPC is comparable to that of NMPC. However, the maximum solution time of MRP-LMPC can be reduced by over 27.81% relative to that of NMPC. Furthermore, the accuracy of MRP-LMPC is significantly superior to that of SRP-LMPC. The maximum displacement and heading error amplitude can be reduced by 0.3075 m and 0.1003 rad, respectively, representing a reduction of 65.51% and 73.59% in the middle speed and above scenario. [ABSTRACT FROM AUTHOR]

Big data and artificial intelligence have promoted mining innovation and sustainable development, and the transportation used in open-pit mining has increasingly incorporated unmanned driving, real-time information sharing, and intelligent algorithm applications. However, the traditional manual scheduling used for mining transportation often prioritizes output over efficiency and quality, resulting in high operational expenses, traffic jams, and long lines. In this study, a novel scheduling model with multi-objective optimization was created to overcome these problems. Production, demand, ore grade, and vehicle count were the model's constraints. The optimization goals were to minimize the shipping cost, total waiting time, and ore grade deviation. An enhanced multi-objective beluga whale optimization (IMOBWO) algorithm was implemented in the model. The algorithm's superior performance was demonstrated in ten test functions, as well as the IEEE 30-bus system. It was enhanced by optimizing the population initialization, improving the adaptive factor, and adding dynamic domain perturbation. The case analysis showed that, in comparison to the other three conventional multi-objective algorithms, IMOBWO reduced the shipping cost from 7.65 to 0.84%, the total waiting time from 35.7 to 7.54%, and the ore grade deviation from 14.8 to 3.73%. The implementation of this algorithm for truck scheduling in open-pit mines increased operational efficiency, decreased operating costs, and advanced intelligent mine construction and transportation systems. These factors play a significant role in the safety, profitability, and sustainability of open-pit mines. [ABSTRACT FROM AUTHOR]

The key to driverless technology is that the decision-making level makes accurate instructions based on the input information of the perception link. Reinforcement learning and imitation learning are better suited for complex scenarios than traditional rules. However, the imitation learning represented by behavioral cloning has the problem of composite error, and this paper uses the priority empirical playback algorithm to improve the behavioral cloning to improve the fitting ability of the model to the demo dataset. The original DDPG (deep deterministic policy gradient) algorithm has the problem of low exploration efficiency, and the experience pool separation and random network distillation (RND) technology are used to improve the DDPG algorithm and improve the training efficiency of DDPG algorithm. The improved algorithm is used for joint training to reduce the useless exploration in the early stage of DDPG training. Verified by TORC (the open racing car simulator) simulation platform, the experimental results show that the proposed method can explore more stable road maintenance, speed maintenance and obstacle avoidance ability within the same number of training times. [ABSTRACT FROM AUTHOR]

AbstractThe intelligent monitoring of electric locomotive loading is crucial in unmanned underground systems. A CNN-based monitoring scheme with migration learning was proposed to address efficiency, abnormality, and data acquisition challenges. Locomotive loading datasets are transformed, augmented, and equalized. Our model improves performance and training by modifying the fully connected layer, using optimized learning rate decay and adaptive algorithms. Training in PyTorch, the optimized VGG19-EL migration network achieves 99.85% recognition for 2-classifications, while the optimized RESNET50-EL migration network achieves 97.3% for 10-classifications. Overall, this study proposes a reliable and efficient model for liberating workers and monitoring locomotive loading.

As one of the important forms of equipment for underground auxiliary transportation in coal mines, monorail cranes have the advantages of large carrying capacity and strong climbing ability, and unmanned driving is its inevitable development direction in the context of intelligent construction of coal mines. In order to ensure the safe driving of the unmanned monorail crane in the underground roadway, it is particularly important for the reliable detection of track joints and key targets. Firstly, the mine image dataset was enhanced to improve its diversity. A YOLOv5 algorithm with improved channel attention mechanism ECA_s and EIOU regression loss function was proposed, and the improved YOLOv5 algorithm was experimentally analyzed, and the results showed that the recognition accuracy was increased by 9.1% and mAP by 3.6% by using the improved YOLOv5 algorithm. Secondly, a machine vision-based single-track crane track seam detection method was established, and the track seam distance was calculated according to the calibration coefficient by using image preprocessing, histogram information statistics, morphological processing and other technologies, and the results showed that the detection error of a seam image processed by the track seam detection algorithm based on machine vision was only 0.3 mm. Finally, the unmanned target detection test of the monorail crane is carried out, and the results show that the average accuracy of the improved YOLOv5 target detection algorithm reaches 90.3%, which has a higher detection accuracy. The average detection error of the seam image processed by the monorail crane rail seam detection algorithm is 0.73 mm, and the maximum detection error is not more than 1.1 mm, which has higher detection accuracy. In order to ensure the safe passage and reliability of unmanned monorail cranes in coal mines, a pragmatic and feasible detection scheme and an accurate and reliable detection algorithm are provided.

Open-pit mines, characterized by complicated environmental conditions and unstructured roads, pose challenges for the path planning of mine trucks, marked by inefficiency due to long-distance search and the need to adhere to the left-hand traffic rules common in mining settings. This paper introduces an optimization algorithm for adaptive dual-layer search path planning based on the left-hand traffic rules in mining areas, aiming to improve the navigation performance of mine trucks within these areas while ensuring the path safety and the real-time planning. The upper-layer search, employing the rapidly-exploring random tree (RRT) algorithm and accommodating the environmental characteristics of mining areas, features adaptive adjustments of search step sizes, achieving efficient searches with larger step sizes in open areas, while detailed searches with smaller step sizes in narrow or winding areas. Moreover, the search process is further optimized by setting range constraints for left-hand driving, to prevent potential vehicle conflicts and facilitate rapid convergence of path search. The lower-layer search incorporates a hybrid A* algorithm, effectively narrowing search space and enhancing the real-time nature of path planning through a reward and penalty mechanism for path selection. Furthermore, Reeds-Shepp (RS) curve and an improved cubic spline curve are applied to smooth the resultant path, not only optimizing path curvature but also ensuring that the mine truck reaches the target location in an optimal posture. Further optimization through the gradient descent method enables the efficient generation of safe and smooth paths. Experimental results showed a 14.8% reduction in path generation time and a 0.011 m-1 decrease in path curvature, demonstrating a significant enhancement in the navigation efficiency and safety during autonomous truck driving in mining areas.

Localization and mapping of the underground ramps is one of the key technologies for achieving unmanned driving of underground mining trucks. The underground ramp is a typical unstructured environmental feature, and the road has a certain inclination angle. However, the traditional SLAM algorithm cannot obtain accurate odometer information, which makes the accuracy of positioning and mapping difficult to meet the driving requirements of unmanned mine trucks. To overcome above problems, this paper proposes a positioning and mapping method suitable for underground ramp environments in mines by studying the laser SLAM (Simultaneous Localization And Mapping) algorithm LeGO-LOAM. Firstly, in terms of the characteristics of smooth cement walls and sparse features on both sides of the underground ramp, a manual landmark-based auxiliary enhancement positioning method is designed, effectively increase the number of point cloud features, to optimize the pose estimation results and avoid the phenomenon of mapping drift. Then, in the feature preprocessing stage, a highly efficient algorithm for extracting ground points based on the fusion of laser point cloud height difference and slope information is proposed, by improving the selection strategy of ground points, which can effectively be identified for sloped potholes, to solve the problem of large inclination angle and error in underground ramps. Next, a slope point cloud surface voxel clustering algorithm based on the CVC (Curved-Voxel Clustering) clustering algorithm is designed, using the curvature voxels and hash-based data structures to segmentation of point clouds, which significantly improve the robustness of point cloud clustering in sparse and noisy environments underground. Finally, the Scan-To-Map is used for point cloud registration, while balancing the performance and speed of point cloud alignment. The on-site experiment in an underground ramp of Shandong, Sinosteel Group proved that the proposed method has improved the accuracy by 13.15% and reduced the Z-axis error by 22.3% compared with the original algorithm. The quality of the map has been significantly improved, which can effectively solve the problem of mapping and positioning in underground autonomous driving.

Featured Application: This work can be applied to unmanned driving in mining environments, with a specific focus on enabling low-latency transmission of high-definition video from underground vehicles to the surface operators. In the development of intelligent mines, unmanned driving transportation has emerged as a key technology to reduce human involvement and enable unmanned operations. The operation of unmanned vehicles in mining environments relies on remote operation, which necessitates the low-latency transmission of high-definition video data across multiple channels for comprehensive monitoring and precise remote control. To address the challenges associated with unmanned driving in mines, we propose a comprehensive scheme that leverages the capabilities of 5G super uplink, edge collaborative computing, and advanced video transmission strategies. This approach utilizes dual-frequency bands, specifically 3.5 GHz and 2.1 GHz, within the 5G super uplink framework to establish an infrastructure designed for high-bandwidth and low-latency information transmission, crucial for real-time autonomous operations. To overcome limitations due to computational resources at terminal devices, our scheme incorporates task offloading and edge computing methodologies to effectively reduce latency and enhance decision-making speed for real-time autonomous activities. Additionally, to consolidate the benefits of low latency, we implement several video transmission strategies, such as optimized network usage, service-specific wireless channel identification, and dynamic frame allocation. An experimental evaluation demonstrates that our approach achieves an uplink peak rate of 418.5 Mbps with an average latency of 18.3 ms during the parallel transmission of seven channels of 4K video, meeting the stringent requirements for remote control of unmanned mining vehicles. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Ordnance Equipment Engineering 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.)

High definition map not only supports the accurate positioning and fine path planning of autonomous vehicles, assists in improving the perception capability of the vehicle end, but also effectively makes up the performance boundary of sensors to deal with a variety of long-tail scenarios. Therefore, high definition map has become essential for achieving L4/L5 unmanned driving at this stage. However, high definition map belongs to the basic strategic information resources of the country, involving military and national defense security. Therefore, in terms of policy, China requires high definition map to undergo geographic information confidentiality processing before public application and to comply with map review procedures. This leads to many limitations in the expression of elements and attributes in high definition map, as well as a lack of dynamic updating ability, making it difficult to accurately reflect the driving environment information of vehicles, seriously affecting the safety and stability of autonomous driving, and making it difficult to break through the “last mile” of unmanned driving. We focus on the issues of geographic information security and timeliness in applying high definition maps for L4/L5 unmanned driving. We comprehensively discuss the current situation, practical needs, and challenges of high definition maps application. Based on this, from policy, technology, standards, pilot exploration, and other aspects, we study and analyze the safety and compliance application trend of high definition maps in the commercialization of unmanned driving in China, and provide prospects for map management innovation, large-scale implementation of crowdsource update models, multi-dimensional collaboration, and cross-departmental, interdisciplinary, and cross-industry cooperation that are urgently needed in the process of high definition maps promoting unmanned driving landing in China. [ABSTRACT FROM AUTHOR]

In an effort to enhance the efficiency and safety of open-pit mines, this study explores the optimization of end slope road parameters and slope structures, specifically focusing on unmanned driving lanes. A significant aspect of the study is the development of a truck trajectory offset model, which considers the different reaction times between automated sensors and human drivers in adapting to environmental changes. To test these concepts, the study uses numerical simulations to confirm the stability of the proposed end slope designs. Using Victory West Mine No. 1 as a case study, the research determines the optimized width for unmanned driving lanes and the maximum angle for the safe steepening of end slopes. The findings indicate that the optimized unmanned lane width for NTE240 mining dump trucks is 1743 mm, allowing for a 2-degree increase in the slope angle at the south end slope. This optimization leads to a steep mining stripping volume of 3.2735 million m3 and a coal output of 2.49628 million tons, maintaining a stripping ratio of 1.31 m3/t. These results demonstrate that unmanned driving road width optimization not only ensures slope safety but also significantly boosts the economic benefits of steep mining in open-pit mines. [ABSTRACT FROM AUTHOR]

Copyright of Electric Drive for Locomotives is the property of Electric Drive for Locomotives 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 path tracking control of electric mining articulated vehicles (EMAVs), critical equipment commonly used for mining and transportation in underground mines, is a research topic that has received much attention. The path tracking control of EMAVs is subject to several system constraints, including articulation angle and articulation angular velocity. In light of this, many researchers have initiated studies based on model predictive control (MPC). The principal design schemes for existing MPC methods encompass linear MPC (LMPC) utilizing a single reference point, so named the single reference point LMPC (SRP-LMPC), and nonlinear MPC (NMPC). However, NMPC exhibits suboptimal real-time performance, while SRP-LMPC demonstrates inferior accuracy. To simultaneously improve the accuracy and real-time performance of the path tracking control of EMAV, based on the SRP-LMPC, a path tracking control method for EMAV based on nonlinear compensated multiple reference points LMPC (MRP-LMPC) is proposed. The simulation results demonstrate that MRP-LMPC simultaneously exhibits a commendable degree of accuracy and real-time performance. In all simulation results, the displacement error amplitude and heading error amplitude of MRP-LMPC do not exceed 0.2675 m and 0.1108 rad, respectively. Additionally, the maximum solution time in each control period is 5.9580 ms. The accuracy of MRP-LMPC is comparable to that of NMPC. However, the maximum solution time of MRP-LMPC can be reduced by over 27.81% relative to that of NMPC. Furthermore, the accuracy of MRP-LMPC is significantly superior to that of SRP-LMPC. The maximum displacement and heading error amplitude can be reduced by 0.3075 m and 0.1003 rad, respectively, representing a reduction of 65.51% and 73.59% in the middle speed and above scenario.

A differential robot is a typical mobile robot widely used in storage, agriculture, and other industries. The motion control of differential robots, including longitudinal and lateral control, is a current research hotspot. To date, researchers have not paid much attention to the interaction between longitudinal and lateral control of differential robots. However, the conflict between the ability to track the reference path and maintain the longitudinal speed at its maximum value is a critical issue that limits the operational efficiency of the differential robot. To solve this problem, a mapping relationship between the longitudinal speed and the turning curvature is analyzed. The mapping relationship is established when the maximum value of the longitudinal speed is known, i.e., the feasible upper limit of the longitudinal speed that can guarantee the steering ability of the differential robot is inversely proportional to the curvature of the trajectory. From this mapping relationship, a speed-adjusting method is proposed based on the preview information. This speed-adjusting method consists of two steps. First, the smaller value between the upper limit of the feasible longitudinal speed in a certain preview distance and the set value of the longitudinal speed are taken as the desired longitudinal speed. Second, a control law is established based on the deviation between this desired and current longitudinal speed. Additionally, a path-tracking method that cooperates with the above-mentioned speed-adjusting method is proposed. The theoretical basis of this path-tracking method is a nonlinear model predictive control. The prediction model used in this control method is derived from a kinematic model with longitudinal speed as a time-dependent parameter. Finally, a differential robot motion control system is formed based on speed adjusting and path tracking. The simulation and experimental results show that the proposed motion control system can actively adjust the longitudinal speed when the set value of the longitudinal speed of the differential robot is high and ensure high accuracy of path tracking control. Furthermore, the absolute value of the displacement and heading errors does not exceed 0.0499 m and 0.0726 rad, which are reduced by 97.57% and 45.04% compared with the motion control system without speed adjusting, respectively.

The working environment and lighting conditions of mining intelligent vehicles are complex. When detecting underground personnel, infrared reflection information and detailed texture information can be fused into visible light images by fusing visible and infrared images to improve the target detection effect. Traditional visible and infrared image fusion methods can lead to blurring of image edges and textures as the number of decomposition layers increases, and the fusion time also increases. At present, deep learning based fusion methods for visible and infrared images are difficult to balance the features in visible and infrared images, resulting in blurred detail information in the fused images. In order to solve the above problems, the image fusion algorithm based on multiple attention modules (IFAM) is proposed. Firstly, convolutional neural networks are used to extract image features from visible and infrared images. Secondly, the extracted features are cross fused using spatial attention and channel attention modules. The fusion weights of the output features of the two attention modules are calculated using the gradient information in the features. The output features of the two attention modules are fused based on the weights. Finally, the image features are restored through deconvolution transformation to obtain the final fused image. The fusion results on the RoadScene dataset and TNO dataset indicate that the IFAM fused image contains both background texture information from visible light images and personnel contour feature information from infrared images. The fusion results on the underground dataset indicate that in low lighting environments, infrared images can compensate for the shortcomings of visible light and are not affected by other light sources in the environment. In low lighting conditions, the personnel contour in the fused image is still obvious. The comparative analysis results show that the information entropy (EN), standard deviation (SD), gradient fusion metric (QAB/F), visual information fidelity for fusion (VIFF), and the union structural similarity index measure (SSIMu) of the image after IFAM fusion are 4.901 3, 88.521 4, 0.169 3, 1.413 5, and 0.806 2, respectively. The overall performance is superior to similar algorithms such as LLF-IOI and NDM.

Intelligent agricultural machinery refers to machinery that can independently complete tasks in the field, which has great significance for the transformation of agricultural modernization. However, most of the existing research on intelligent agricultural machinery is limited to unilateral research on positioning, planning, and control, and has not organically combined the three to form a fully functional intelligent agricultural machinery system. Based on this, this article has developed an intelligent agricultural machinery system that integrates positioning, planning, and control. In response to the problem of large positioning errors in the large range of plane anchoring longitude and latitude, this article integrates geographic factors such as ellipsoid ratio, long and short axis radius, and altitude into coordinate transformation, and combines RTK/INS integrated inertial navigation to achieve precise positioning of the entire vehicle over a large range. In response to the problem that existing full-coverage path planning algorithms only focus on job coverage as the optimization objective and cannot achieve path optimization, this paper proposes a multi-objective function-coupled full-coverage path planning algorithm that integrates three optimization objectives: job coverage, job path length, and job path quantity. This algorithm achieves optimal path planning while ensuring job coverage. As the existing pure pursuit algorithm is not suitable for the motion control of tracked mobile machinery, this paper reconstructs the existing pure pursuit algorithm based on the Kinematics characteristics of tracked mobile machinery, and adds a linear interpolation module, so that the actual tracking path points of motion control are always ideal tracking path points, effectively improving the motion control accuracy and control stability. Finally, the feasibility of the intelligent agricultural machinery system was demonstrated through corresponding simulation and actual vehicle experiments. This intelligent agricultural machinery system can cooperate with various operating tools and independently complete the vast majority of agricultural production activities. [ABSTRACT FROM AUTHOR]

The development of unmanned vehicles has been extremely rapid in recent years. Unmanned vehicles require path tracking control. Based on mature mathematical modeling methods for unmanned vehicles, path tracking control research using model-based control methods, such as feedback linearization control, optimal control, and model predictive control, is very common. Currently, two types of model-based control methods are commonly used in the path tracking control of unmanned vehicles: based on global and local models. The path tracking control based on the global model has a coupling relationship between the longitudinal speed of the unmanned vehicle and the lateral displacement error and longitudinal displacement error in the global coordinate system. Furthermore, this coupling relationship varies with the heading angle, making the controller unable to take the longitudinal speed as a control input to improve the accuracy of path tracking control. Path tracking controllers based on local models usually use errors as reference models, making the controller less accurate when the curvature of the reference path greatly varies. To address the above issue, an unmanned vehicle path tracking control method based on a time-varying local model is proposed considering the principle of rolling optimization of nonlinear model predictive control. Specifically, a time-varying local coordinate system is first established based on the time-varying pose of the vehicle. Then, a reference path in front of the vehicle is entered into this local coordinate system. The model-based iterative prediction is completed in this local coordinate system, and finally, the control is achieved using the optimization solution. The proposed control method is verified by co-simulation using MATLAB and CarSim. The simulation conditions include low-speed and high-adhesion road conditions, low-speed and low-adhesion road conditions, and high-speed low-adhesion road conditions. The simulation results show that the path tracking controller based on the time-varying local model outperforms the path tracking controller based on the global model, the path tracking controller based on the local model, and the Stanley path tracking controller. The maximum absolute value of the displacement error of the proposed controller does not exceed 0.3342 m under all simulation conditions, and the maximum absolute value of the heading error does not exceed 0.0913 rad. Moreover, the proposed controller can still complete the path tracking in situations where other controllers fail, such as high-speed and low-adhesion road conditions.

In the development of intelligent mines, unmanned driving transportation has emerged as a key technology to reduce human involvement and enable unmanned operations. The operation of unmanned vehicles in mining environments relies on remote operation, which necessitates the low-latency transmission of high-definition video data across multiple channels for comprehensive monitoring and precise remote control. To address the challenges associated with unmanned driving in mines, we propose a comprehensive scheme that leverages the capabilities of 5G super uplink, edge collaborative computing, and advanced video transmission strategies. This approach utilizes dual-frequency bands, specifically 3.5 GHz and 2.1 GHz, within the 5G super uplink framework to establish an infrastructure designed for high-bandwidth and low-latency information transmission, crucial for real-time autonomous operations. To overcome limitations due to computational resources at terminal devices, our scheme incorporates task offloading and edge computing methodologies to effectively reduce latency and enhance decision-making speed for real-time autonomous activities. Additionally, to consolidate the benefits of low latency, we implement several video transmission strategies, such as optimized network usage, service-specific wireless channel identification, and dynamic frame allocation. An experimental evaluation demonstrates that our approach achieves an uplink peak rate of 418.5 Mbps with an average latency of 18.3 ms during the parallel transmission of seven channels of 4K video, meeting the stringent requirements for remote control of unmanned mining vehicles.

In an effort to enhance the efficiency and safety of open-pit mines, this study explores the optimization of end slope road parameters and slope structures, specifically focusing on unmanned driving lanes. A significant aspect of the study is the development of a truck trajectory offset model, which considers the different reaction times between automated sensors and human drivers in adapting to environmental changes. To test these concepts, the study uses numerical simulations to confirm the stability of the proposed end slope designs. Using Victory West Mine No. 1 as a case study, the research determines the optimized width for unmanned driving lanes and the maximum angle for the safe steepening of end slopes. The findings indicate that the optimized unmanned lane width for NTE240 mining dump trucks is 1743 mm, allowing for a 2-degree increase in the slope angle at the south end slope. This optimization leads to a steep mining stripping volume of 3.2735 million m3 and a coal output of 2.49628 million tons, maintaining a stripping ratio of 1.31 m3/t. These results demonstrate that unmanned driving road width optimization not only ensures slope safety but also significantly boosts the economic benefits of steep mining in open-pit mines.

Driverless technology refers to the technology that vehicles use to drive independently with the help of driverless system under the condition of unmanned intervention. The working environment of construction machinery is bad, and the working conditions are complex. The use of driverless technology can greatly reduce the risk of driver operation, reduce labor costs and improve economic benefits.Aiming at the problem of the GPS positioning signal in the working environment of construction machinery being weak and not able to achieve accurate positioning, this paper uses the fusion SLAM algorithm based on improved NDT to realize the real-time positioning of the whole vehicle through reconstruction of the scene. Considering that the motion characteristics of crawler construction machinery are different from those of ordinary passenger cars, this paper improves the existing pure pursuit algorithm. Simulations and real vehicle tests show that the algorithm combined with the fusion SLAM algorithm can realize the motion control of driverless crawler construction machinery well, complete the tracking of the set trajectory perfectly and have high robustness. Considering that there is no mature walking method of driverless crawler construction machinery for reference, the research of this paper will lay a foundation for the development of driverless crawler construction machinery. [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.)

Introduction: In urban road scenes, due to the small size of traffic signs and the large amount of surrounding interference information, current methods are difficult to achieve good detection results in the field of unmanned driving. Methods: To address the aforementioned challenges, this paper proposes an improved E-YOLOv4-tiny based on the YOLOv4-tiny. Firstly, this article constructs an efficient layer aggregation lightweight block with deep separable convolutions to enhance the feature extraction ability of the backbone. Secondly, this paper presents a feature fusion refinement module aimed at fully integrating multi-scale features. Moreover, this module incorporates our proposed efficient coordinate attention for refining interference information during feature transfer. Finally, this article proposes an improved S-RFB to add contextual feature information to the network, further enhancing the accuracy of traffic sign detection. Results and discussion: The method in this paper is tested on the CCTSDB dataset and the Tsinghua-Tencent 100K dataset. The experimental results show that the proposed method outperforms the original YOLOv4-tiny in traffic sign detection with 3.76% and 7.37% improvement in mAP, respectively, and 21% reduction in the number of parameters. Compared with other advancedmethods, the method proposed in this paper achieves a better balance between accuracy, real-time performance, and the number of model parameters, which has better application value. [ABSTRACT FROM AUTHOR]

The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology. Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis. Semantic segmentation is also a challenging technology for image understanding and scene parsing. We focused on the challenging task of real-time semantic segmentation in this paper. In this paper, we proposed a novel fast architecture for real-time semantic segmentation named DuFNet. Starting from the existing work of Bilateral Segmentation Network (BiSeNet), DuFNet proposes a novel Semantic Information Flow (SIF) structure for context information and a novel Fringe Information Flow (FIF) structure for spatial information. We also proposed two kinds of SIF with cascaded and paralleled structures, respectively. The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule. Features from previous stages usually contain rich low-level details but high-level semantics for later stages. Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost. The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer. The concise component provides more spatial details for the network. Compared with BiSeNet, our work achieved faster speed and comparable performance with 72.34% mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone. [ABSTRACT FROM AUTHOR]

Aiming at the transportation scheduling problem of unmanned trucks in open-pit mines, an optimization model for transportation scheduling of unmanned trucks in open-pit mines is established, taking the minimum sum of fuel cost, fixed start-up cost, fault maintenance cost and network base station construction and maintenance cost as the objective function, and taking mining amount, crushing amount in crushing field, truck number and truck transportation work as the bundle reduction conditions. By adjusting the position of the encapsulated individual and the optimal encapsulated individual through the parameter position adaptive updating mechanism, the search range of the solution space can be enlarged, so that the algorithm can jump out of the local optimum. This paper analyzes the influence of vehicle clearance on coordinated traffic at intersections under clearance theory, and puts forward the minimum vehicle clearance to meet coordinated traffic. Generate trajectories with behavioral semantics through hierarchical online selection of primitives; Based on the model predictive control algorithm, the motion control module fully considers the execution ability, tracking deviation and control stability of the platform drive motor, and updates the weight coefficient of the control objective function in real time with the help of the semantic attributes of the behavioral motion primitives given by the motion planning, so as to reduce the lateral error, heading error and speed error of the trajectory tracking. Finally, a real vehicle is verified by a medium-sized hybrid unmanned crawler platform, which proves that the proposed intersection coordinated traffic model is feasible in theory, reflecting that the traffic density is a factor that affects the transportation efficiency. Under the condition of meeting the production requirements, reduce the intersection conflict and improve the traffic capacity of the intersection by adopting large-load unmanned mine trucks as much as possible, reducing the number of unmanned mine trucks and the interference between equipment.

Based on the development status of subway train driving technology at home and abroad, the necessity of subway train intelligent driving development and research was expounded.In view of the poor interpretability of machine learning algorithms used in current unmanned driving, with an introduction of fuzzy system, a metro train unmanned driving system based on man-machine hybrid intelligence was proposed, which realized man-machine hybrid intelligence in two ways.The subway train driverless system combined with cognitive system was explored, which a future-oriented solution for the realization of strong artificial intelligence subway train driverless system in the real sense was provided.

At present, the research on unmanned mine truck system on-board decision system in mine scenarios at home and abroad is still in the initial stage, and its research focus is mainly on global planning and scheduling to improve overall safety and efficiency of the system, while ignoring the research on the mine truck independent decision method based on the global planning and scheduling. In order to further improve the safety and efficiency of the system, this paper focuses on the two core functions of behavior decision-making and motion planning under the mining truck independent decision-making method of the vehicle decision-making system. Behavior decision includes driving mode and task mode decision, collision warning and protection decision, fault classification and safety oriented decision, based on the double layer limited state machine method to realize mine truck autonomous decision protection judgment, to ensure that the vehicle in the "loading, transportation, unloading" whole process scenario of mine to improve the safety of vehicle operation. Motion planning includes speed planning and path planning. This paper adopts the quadratic programming algorithm based on the shortest time and the optimal energy consumption to solve the speed planning, and adopts the hybrid A-star and curve fitting algorithm based on special scenarios to solve the local path planning, so that the operation efficiency can be improved by 10%~20% in the loading and unloading parking scenario. The system has been production and operation in a mining area in northern China for half a year. The real vehicle production and operation results show that the system can effectively improve the vehicle operation efficiency and safety ability to avoid obstacles.

Full hydraulic steering system adopted by mine electric-wheel dump truck is powered by steering hydraulic accumulator and steering hydraulic pump. Its actual steering response ability affected by road surface condition, steering oil pressure and flow, thus, it is a typical large inertia and time-varying execution system. Time-varying characteristics of the steering speed put forward time-varying coordination requirements for the lateral and longitudinal motion which indirectly restricted lateral motion ability of the unmanned mine truck. Speed planning and control without considering steering speed characteristics will result in poor coordination of lateral and longitudinal motion, which will lead to ineffective vehicle tracking. Firstly, this paper analyzes the key factors of time-varying response characteristics of the full hydraulic steering system based on its system principle. Secondly, the constraint of steering speed on the coordination of lateral and longitudinal motion is determined based on the deformation derivation of the truck kinematics model. Finally, combined with the pressure information of the steering accumulator, evaluation model of steering response capability and speed adjustment method in accordance with lateral and longitudinal cooperative constraints are established. Actual test results show that the designed speed adjustment method can achieve good tracking of the mine truck on the continuous limit curve path, with an average lateral error of 0.2 m, and ensure the continuous tracking ability of the mine electric-wheel dump truck on the complex curvature path.

In the view that lateral tracking accuracy of mine trucks is not high under the condition of complex path and muddy road, in order to improve the adaptability of the control algorithm to the complex driving environment in the mining area, an adaptive preview tracking control algorithm considering multi-factor fusion is proposed in this paper. Firstly, according to the vehicle kinematics, a rear wheel feedback tracking model based on preview is established. Secondly, vehicle trajectory is predicted by the trajectory prediction method. Considering the cumulative tracking error between reference trajectory and predicted trajectory, vehicle steering response delay and other factors, a multi-objective optimization function of adaptive preview is constructed. Finally, the optimization function is solved by genetic algorithms (GA), and the optimal preview point is output to the rear wheel feedback controller to realize the optimal control of the vehicle in the global path tracking process. Simulation and real vehicle test results show that when a vehicle starts with an initial lateral error of less than 0.8 m and a yaw angle error of 5°, the adaptive preview tracking control algorithm can achieve a certain degree of deviation-correcting control; the vehicle stops with a lateral error of less than 0.2 m and a yaw angle error of less than 2°, which effectively improves the tracking ability of mine trucks and its adaptability to complex working conditions.

In order to improve the adaptability of hybrid A* algorithm to mining scene, this paper proposes a path optimization method for unmanned mine trucks. Firstly, applicability and curvature continuity of initial solution of hybrid A* algorithm are improved by curvature continuous Reeds-Shepp screening in combination with mining scenes, and then the segmented spline curve numerical optimization method based on quadratic programming is used to further smooth and interpolate the searched path. This method can be applied to the screening and smooth optimization of the initial solution of path planning, and provides a safe, smooth and drivable path for unmanned mine trucks that satisfies the kinematic constraints of the vehicle. The results of simulation comparison test and on site vehicle test show that the proposed method can significantly improve the applicability and smoothness of the search path by the traditional hybrid A* algorithm, and the optimization efficiency is better than the traditional discrete point optimization.

Existing mine truck unmanned driving systems operating in complex mining areas have many potential safety hazards, such as problems with the planning trajectory of the dispatching system, failure to update the mining area operation map in time, and the loss of trajectories data between the ground and on-board system. All of these may lead to major security incidents for unmanned mine trucks due to incorrect reference trajectories. To this end, this paper proposes an active collision avoidance method based on predicted trajectories to solve the above safety issues. First, a model-based method is used to predict running trajectory of unmanned mine truck based on on-board sensors. Then, collision prediction is made on the predicted trajectory, and the OBB (oriented bounding box) collision detection method is used to find the nearest vehicle according to the current position of the vehicle. Finally, the unmanned mine truck performs cascade braking (ie multi-stage partial braking and full braking) according to the AEBS (advanced emergency braking system) control algorithm. Simulation results show that when there is no expected trajectory, mine truck can realize active braking in time, which ensures the safe operation of the vehicle.

Unmanned driving & remote driving transportation business in Xiwan Coal Mine requires three-dimensional coverage of wireless network with large bandwidth and low latency in light-load test area, heavy-load test area and whole mining area. In view of the difficulties of site landing, high frequency of site relocation and complex wireless environment in coal mining area, this paper puts forward a scheme of "700 MHz + 2.6 GHz + 4.9 GHz" triple frequency networking, which effectively solves the problem of safe, stable and efficient 5G network coverage in the whole mining area, and meets the bandwidth and delay business needs of unmanned driving & remote driving. At the same time, in order to further enhance the bandwidth of coal mining area (coal roof, stone roof), a 4.9 GHz time slot flip 1D3U scheme is proposed, which changes three downward time slots to uphill time slots, making the proportion of downward timeslot to uphill time slot from 5:3 to 1:3. After the implementation of the triple-frequency networking scheme, the proportion 50 Mbit/s upstream edge rate in the whole coal mine business area is more than 99%, and the average time delay is less than 20 ms. After the implementation of the 4.9 GHz timeslot flip 1D3U scheme, the peak rate of ascending in the core mine area increased from 290 Mbit/s to around 600 Mbit/s, which expanded the upstream bandwidth.

Aiming at the problems of poor detection effect and low tracking stability of multi-type vehicles in complex mining environment due to the similarity of operating vehicles and background images, this paper proposes a multi-category and multi-target real-time detection and tracking algorithm for operating vehicles in complex mining environments. The model framework is constructed based on the lightweight backbone network YOLO combined with the multi-scale feature fusion module. The model uses DIoU as loss function, uses K-means clustering to regress the size of candidate frame, and learns image features through the lightweight backbone network. On this basis, the features of multi-category work vehicle targets are used as similarity metric, combined with Mahalanobis distance metric and cosine metric that characterize motion information for cascading matching, and IoU matching and Kalman filtering are connected in series to confirm the trajectory and the real-time tracking of multiple work vehicles. Experimental results show that the average vehicle detection accuracy of the algorithm mAP@ 0.5-0.95 is 58.40%, the multi-target tracking accuracy reaches 82.60%, and the image processing time per frame is 26.5 ms, which can effectively perform real-time detection and tracking of working vehicles.

Unmanned fully line-controlled distributed drive electric vehicles with four-wheel independent drive, dependent braking and dependent steering have significant advantages over conventional vehicles in terms of dynamic control, but at the same time multiple actuators with multiple degrees of freedom also pose the risk of failure in the steering system, which is studied in this paper for trajectory tracking control. Rational control of multiple systems such as drive, braking, steering and fault tolerance of the unmanned fully line-controlled distributed drive electric vehicles are carried out. For longitudinal control, a fuzzy PI algorithm is used to input velocity error and velocity error rate of change, and to solve the required drive torque of the vehicle based on fuzzy rules; for lateral control, according to model prediction control theory, the exact model is predicted and an optimized search is performed to reasonably allocate the forward and backward wheels turning corners ensuring the accuracy and roadholding of trajectory tracking; for fault-tolerant control, differential drive and other methods of control, when a fault is detected, the number and position information of the faulty steering motor is transmitted to the fault-tolerant decision module, which outputs control commands according to the decision. The outcomes demonstrate that the presented trajectory following the control policy enhances the precision, roadholding and safety of trajectory following in an effective way. [ABSTRACT FROM AUTHOR]

The working environment of construction machinery is harsh, and some operations are highly repetitive. The realization of intelligent construction machinery helps to improve economic efficiency and promote industrial development. Construction machinery is different from ordinary passenger vehicles. Aiming at the fact that the existing environmental perception data set cannot be directly applied to construction machinery, this paper establishes the corresponding data set in combination with the specific working conditions of construction machinery and carries out training based on the PointPillars network to realize the environmental perception function applicable to the working conditions of construction machinery. Most construction machinery runs on unstructured roads, and the existing passenger vehicle path planning algorithm is not applicable to construction machinery. Based on this, this paper uses a hybrid A* algorithm to achieve path planning that meets the kinematics of construction machinery and realizes real-time obstacle detection and avoidance. At the same time, this paper combines environmental perception with a path planning algorithm to provide a method of autonomous path finding and obstacle avoidance for construction machinery. Based on the improved pure pursuit algorithm, the high-precision motion control and established trajectory tracking of construction machinery are realized, which lays a certain foundation for the follow-up research and development of related intelligent technologies of construction machinery. [ABSTRACT FROM AUTHOR]

To realize the unmanned function of automatic washing and sweeping vehicles in closed parks, this paper designs a path planning and control algorithm based on a closed park scenario. The global path planning layer is constructed by using the improved A-Star algorithm combined with the third-order Bezier curve; The local path planning layer is designed based on the state space sampling, and the optimal local path is obtained by considering the constraints such as the steering constraints of the sweeper, the safe collision distance, and the road boundary distance; The Pure-Pursuit tracking algorithm is used to track the optimal path output by the local path planning layer. Then, to build the Simulink-ROS joint simulation platform, compile the planning control algorithm in Simulink, and embed it into the ROS platform for simulation verification; Finally, the MDC300 F vehicle-mounted computer is used to carry out the multi-condition real-vehicle experiment of the algorithm. The results show that the planning control algorithm can control the automatic sanitation washing and sweeping vehicle to complete unmanned functions such as following cars, avoiding obstacles, and meeting cars in multiple working conditions. [ABSTRACT FROM AUTHOR]

Based on the current development status of subway train driving technology in China and abroad, the four stages of subway train driving technology development were proposed and explained as manual driving, automatic driving, unmanned driving, and intelligent unmanned driving.After summarizing the construction situation of unmanned subway trains in China, the disadvantages of the current train control methods based on neural network-based machine learning methods were addressed.Then, the basic block diagram of metro intelligent unmanned driving based on man-machine hybrid intelligence was put forward and the deep fuzzy system was introduced.A promising solution for the combination of expert experience in dealing with emergency and interpretable AI algorithms for unmanned driving system to evolve into intelligent unmanned driving was provided.

Copyright of Nonferrous Metals (Mining 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.)

Unmanned driving is the direction of future development in the field of transportation. The development of unmanned driving will cause sensor monitoring and machine control to play a greater role. According to road roughness data collected by unmanned ground vehicles and vehicle dynamics, it is of great significance to establish a vehicle–pavement coupling model to analyze and guide driving comfort, cargo safety, and road friendliness. Pavement roughness is the main external excitation in the process of driving a vehicle. Therefore, a three-dimensional (3D) model of pavement roughness was constructed based on fractal theory and fractal interpolation. According to tire–pavement contact characteristics, a newly rerevised 3D flexible roller contact tire model was proposed. On this basis, vehicle vibration dynamics models for a car and a truck were established. The traditional point contact model was used to verify the model. Based on the comfort threshold of a passenger, the cargo vibration threshold, and the dynamic load coefficient (DLC) threshold of the truck, the conditions for ride comfort of an unmanned ground vehicle were expounded. The results showed that, compared with an ideal fully flat road surface, pavement roughness had a great impact on vehicle vibration. The 3D model of pavement roughness generated had high accuracy. The vehicle–pavement coupling model based on tire–pavement 3D contact under 3D pavement roughness excitation was correct. The proposed model can calculate vibration characteristics of passengers and cargo and the DLC of wheels in real time. For different types of vehicles and different roughness levels of pavement, different speed thresholds were given to ensure driving comfort, cargo safety, and road friendliness. Driving speed and each evaluation index met the Fourier function relationship. Partial correlation analysis showed that in order to ensure the comfort of passengers, more attention should be paid to pavement roughness, and for cargo safety and road friendliness, pavement roughness and vehicle speed should be considered at the same time. The results provide theoretical suggestions for the comfortable driving of future unmanned ground vehicles. [ABSTRACT FROM AUTHOR]

In the process of trajectory tracking using the linear quadratic regulator (LQR) for driverless wheeled tractors, a weighting matrix optimization method based on an improved quantum genetic algorithm (IQGA) is proposed to solve the problem of weight selection. Firstly, the kinematic model of the wheeled tractor is established according to the Ackermann steering model, and the established model is linearized and discretized. Then, the quantum gate rotation angle adaptive strategy is optimized to adjust the rotation angle required for individual evolution to ensure a timely jumping out of the local optimum. Secondly, the populations were perturbed by the chaotic perturbation strategy and Hadamard gate variation according to their dispersion degree in order to increase their diversity and search accuracy, respectively. Thirdly, the state weighting matrix Q and the control weighting matrix R in LQR were optimized using IQGA to obtain control increments for the trajectory tracking control of the driverless wheeled tractor with circular and double-shifted orbits. Finally, the tracking simulation of circular and double-shifted orbits based on the combination of Carsim and Matlab was carried out to compare the performance of LQR optimized by five algorithms, including traditional LQR, genetic algorithm (GA), particle swarm algorithm (PSO), quantum genetic algorithm (QGA), and IQGA. The simulation results show that the proposed IQGA speeds up the algorithm's convergence, increases the population's diversity, improves the global search ability, preserves the excellent information of the population, and has substantial advantages over other algorithms in terms of performance. When the tractor tracked the circular trajectory at 5 m/s, the root mean square error (RMSE) of four parameters, including speed, lateral displacement, longitudinal displacement, and heading angle, was reduced by about 30%, 1%, 55%, and 3%, respectively. When the tractor tracked the double-shifted trajectory at 5 m/s, the RMSE of the four parameters, such as speed, lateral displacement error, longitudinal displacement error, and heading angle, was reduced by about 32%, 25%, 37%, and 1%, respectively. [ABSTRACT FROM AUTHOR]