Search Documents

By Ebrahim Ghasemi, Mohammad Hossein Kadkhodaei, Mosareza Jalilian

Entry-type mining methods, such as cut and fill method, play a significant role in underground mining, and they are still suitable methods for extracting deposits with irregular shapes and with weak host rocks. In these mining methods, the stability of the open spans is important for improving worker safety and increasing ore recovery. This study focuses on the application of six data mining classification methods, namely multinomial logistic regression (MLR), classification and regression trees (CART), logistic model tree (LMT), decision tree (J48), multivariate adaptive regression spline (MARS), and gene expression programming (GEP), in order to develop predictive models for stability assessment of underground entry-type excavations. For this purpose, a database containing 399 case histories of entry-type excavations from seven Canada underground mines was used. These models predict the stability status of entry-type excavations based on two input parameters, dimensions of the span and rock mass rating (RMR). The performance of developed models was evaluated using six performance metrics namely accuracy (ACC), sensitivity (SE), precision (PR), Matthew’s correlation coefficient (MCC), area under the receiver operating characteristic (ROC) curve (AUC), and performance index (PI). The results showed that all developed models can be used to predict the excavation stability, but the comparison of models indicated that the J48 model provides the highest performance with ACC = 0.900, SE = 0.869, PR = 0.922, MCC = 0.835, AUC = 0.891, and PI = 4.417. Thus, the proposed J48 model can be applied to identify the susceptibility of span instability in the entry-type mining, and if instability has been predicted, the necessary measures, including the use of suitable support systems, can be considered to reduce the casualties resulting from span instability.

Feb 26, 2024

By Fouad Faraj

For every blast pattern, zones of unique material types need to be classified before mining. Most material types can be summarized into different kinds of ore and waste. Blocks generated from blasthole assays are too small to be selectively mined so areas with a single material classification meeting the mine’s selective mining unit must be defined. Current industry standard practices are to manually draw ore/waste dig limits but this process is subjective and results in quantities of dilution and ore loss which can be improved upon to enhance the profitability of mining operations. Two weeks production data from a homogeneous Cu porphyry and heterogeneous Manto-type Cu deposit are used to assess the variability in the hand-drawn dig limits for 20 geologists, mining engineers, or ore control specialists and are compared with the optimal ore/waste delineation. The profit for 20 distinct hand-drawn dig limits for the homogeneous mine ranged by 3.7% from $10.5 million to $10.9 million averaging at $10.8 million. The percent range nearly doubled for the more heterogeneous mine at 5.9% from $17.9 million to $19.0 million averaging at $18.6 million. Using the optimal ore waste delineation, the profit increased to $11.0 million (1.9% increase) and $19.3 million (7.0% increase) for the homogeneous and heterogeneous deposits respectively. The natural variability, diggability requirement, and selectivity are identified as the main drivers of ore loss and dilution. Recommendations are provided for reducing the subjectivity in manual hand-drawn dig limits by integrating dig limit optimization algorithms as a tool to assist practitioners.

Feb 23, 2024

By O. K. Olawale, G. O. Edaogbogun, B. N. Ben‑Festus, F. Ben, F. R. Amodu

The environmental and health implications of artisanal gold mining activities at mining sites across Nigeria have rekindled research interest. This study aimed to assess the scalability of naturally occurring radioactive materials in gold mining sites in Iperindo, Nigeria. Soil samples were collected from three different mining sites and control locations and analyzed for natural radionuclides, mainly 238U, 232Th, and 40K, using gamma spectrometry having a sodium iodide detector. The average activity concentration values of 61.55 ± 3.71, 72.65 ± 4.45, and 1134.99 ± 38.12 Bqkg− 1 obtained from within the mining sites for 238U, 232Th, and 40K, respectively, were above the world permissible values of 33.0 Bqkg− 1 for 238U, 45.0 Bqkg− 1 for 232Th, and 420.0 Bqkg− 1 for 40K. The average activity concentration values of 15.26 ± 3.19, 21.46 ± 4.27, 381.04 ± 23.36 Bqkg− 1 estimated for 238U, 232Th, and 40K, respectively, for the control location were, however, lower than the global permissible values. The study also evaluated other radiological parameters such as radium equivalent, dose rate, annual effective dose rate, internal and external hazard indices, and alpha and gamma indices. The obtained values were 252.83 Bqkg− 1, 119.98 nGyh− 1, 147.15 mSvy− 1, 0.85 Bqkg− 1, 0.68 Bqkg− 1, 0.31 Bqkg− 1, and 1.89 Bqkg− 1 respectively. Except for radium equivalent, external and internal hazard risks, and alpha index, which were significantly lower than the recommended threshold, all other radiological parameters were higher than the recommended global limits. Moderate data reproducibility and a p-value of 0.000574 further reinforced the robustness and reliability of the results obtained in this study.

Feb 22, 2024

By Chao Zhang, Wenhao Xia, Jianxin Fu, Ling Yu, Weidong Song, Yang Li

Sanshandao Gold Mine is the only undersea metal mine in China. To deal with the collapse and pumping of stopes and roadways caused by complex ore-rock occurrence conditions, the mine conducts filling and sealing of some areas, and the remaining ore reserves will be mined after treatment. Therefore, it is urgent to evaluate the stability of rock masses, fault fracture zones, and aquicludes during the secondary mining process. In this study, displacement and microseismic methods are employed to monitor rock deformation and fractures. Additionally, FLAC3D was used to simulate the process of secondary mining, reproducing the evolution of stress fields, displacement fields, seepage fields, and plastic zones at different mining stages. The combination of numerical simulation and on-site monitoring verification demonstrates that the deformation of surrounding rock presents a rapid growth at the initial stage of mining, followed by a gradual decrease in the growth rate, and finally tends to stabilize; the fracture zone area at the 151–159 exploration line on the − 320 m level (near the 7# and 8# stopes) exhibits poor stability, and monitoring measures should be strengthened; the deformation value of the aquiclude is less than the deformation value of I protection level in the Code for Design, the impact of secondary mining on the aquiclude is limited; fault and fracture zone deteriorate rock mass stability, and their impact is related to their spatial locations. Hanging wall fault has a more significant impact on the settlement of the aquiclude, while the footwall fracture zone has a greater impact on the development of the plastic zone.

Feb 21, 2024

By Edward Holloway

The basis for the selection of the ultimate pit for an open pit mining operation is generally opaque. Some form of value-based analysis will generally guide the final decision; however, the value will often gradually plateau whilst the ultimate pit size continues to increase. There is no established framework to guide specialists in the selection of the ultimate pit, with such decisions regularly made on a somewhat arbitrary basis. The key component that is missing from the analyses typically used to select the size of the ultimate pit is risk. Once risk is quantified within the analysis framework, the decision-making range is significantly reduced, and the process for selecting the ultimate pit becomes more consistent, replicable, and defensible. This paper provides an approach to including risk in the process used to select the ultimate pit.

Feb 21, 2024

By Zhibiao Guo, Jinglin You, Dongshan Yang, Yuanxin Zhao, Yuhui Li, Jingwei Gao

By utilizing collapsed gangue to create gob ribs, roof cutting and roadway maintenance (RCRM) technology enables coal pillar-free mining, presenting a novel approach. Due to their inherent structure, faults, which are common geological formations, can lead to various hazards, including fault sliding and significant deformation of roadways. In this study, a selfdesigned underground engineering simulation test device is utilized to imitate the cross-fault mining of the 11,101 working face in the Qipanjing Coal Mine (East). The objective is to examine the behavior of the surrounding rock and stress evolution. Generally, the experimental findings demonstrate that compared to the return air roadway, the RCRM roadway experiences a 3.3% decrease in maximum coal rib stress. This suggests that the implementation of this technique can effectively alleviate the stress on the surrounding rock of the roadway. The maximum coal rib stress, lateral pressure of the gob rib, and maximum deformation of the roof near the fault of the RCRM roadway are 11.3%, 25.6%, and 86.1% greater than those of the conventional geological conditions, respectively. The roadway deformation is negatively impacted by the fault structure. Based on experimental data and field measurements, a discrepancy in the maximum roof deformation between the test and field monitoring results under typical geological conditions is 8%. This indicates a favorable alignment between the test results and the real-life scenario. In conclusion, the proposed targeted control technique is implemented in the field by integrating the mining invariant equation and gangue volume expansion equation. This not only validates the effectiveness of the technology but also offers valuable insights for the future utilization of RCRM technology under comparable circumstances.

Feb 20, 2024

By Xinghai Lei, Yuqi Shang, Guiming Li, Lu He

There are many factors affecting the stability of open-pit mine slopes, among which slopes with soft interlayers have become an important factor inducing deformation and instability due to their poor mechanical properties. In this paper, for the destabilization of a slope with soft interlayer under rainfall infiltration in an open-pit mine in Zhejiang Province of China during the rainy season, a sudden change of displacement at the monitoring point and the formation of a continuous plastic deformation of the slope are proposed as the criteria for slope destabilization through the establishment of a rainwater seepage-stress coupling model combined with the strength reduction method, and by using COMSOL Multiphysics finite element numerical simulation software to establish a three-dimensional numerical model based on the actual mining slope conditions. The safety principle is introduced through the strength reduction method to analyze the stability of the slope with soft interlayer under the coupling effect of seepage and stress. The safety coefficients of the slope with soft interlayer are calculated by using Numerical methods under the coupling effect of seepage and stress. The influence of rainfall intensity and duration on the stability or safety factor of the slope with soft interlayers was studied through analysis of stress, saturation, displacement, and pore pressure evolution. The mechanism of rainfall affecting slope stability was investigated, and the findings were validated using an engineering case study of a slope with a soft interlayer. The findings show that rainfall intensity is the main factor affecting slope stability in the open-pit mine slope with soft interlayer. The higher the rainfall intensity, the faster the shallow soil forms a saturation zone, whereas soft interlayers speed up the process and endanger slope stability. The slope prevention and control technology of the prestressed anchor cable (rod) framework was proposed based on the slope management construction conditions of the mine, and the effectiveness of the measure was verified through on-site industrial tests. The research findings provide a reference for preventing and controlling slope with soft interlayers in open-pit mines under similar conditions.

Feb 20, 2024

By Yisa Liu, Lili Xu, Shina Li, Kang Li, Jiong Dong, Zichen Yin, Ruixin Ma

With the evolving landscape of gold mineral resource development and utilization, the easily treatable gold resources are continuously decreasing, while refractory gold minerals are becoming the most important resources in the field of gold extraction. In these original ores, most of the gold is encapsulated in the lattice of pyrite and arsenopyrite, resulting in difficulty of gold transfer into the solution during the leaching process. The most effective method to solve the problem of insufficient contact between gold particles and leaching reagent is oxidation pretreatment before leaching. Different from traditional high-temperature roasting, concentrated sulfuric acid was used as both an oxidant and leaching agent in a sulfideencapsulated refractory gold ore to decompose the pyrite in the curing environment to expose the gold and improve the leaching efficiency. The experimental results showed that under the conditions of liquid solid ratio 3:1, curing temperature 240 °C and the reaction time 1.5 h, the weight loss rate and iron removal rate of the ore sample reached the highest value of 60.01% and 99.68%, respectively. The main phase of curing residue was Fe2( SO4)3, and silica was nearly the only phase after washing. At the same time, by combining the sodium thiosulfate system gold leaching method, the gold leaching rate increased from 3.67% to 81.30% before and after pretreatment with concentrated sulfuric acid.

Feb 19, 2024

By Alfredo Valencia-Toledo

This study delves into the satisfaction levels of indigenous communities in Apurimac-Cusco, Peru, concerning mining activities in their region. Our primary objective is to elucidate the interrelationships among observable variables, which are conceived as linear combinations of multiple factors. Employing the statistical methodology of exploratory factor analysis, we aim to pinpoint the pivotal factors influencing the progress of mining activities in Apurimac-Cusco. Through our analysis, we have identified eight key factors that exert a significant impact on mining’s sustainable development in the area. These factors encompass diverse facets, ranging from the support offered by mining company to communities, environmental considerations, education, economic factors, provision of basic services, transportation and communication, support for social organizations, and social-health-related aspects. This research endeavors to provide a comprehensive understanding of the complex dynamics surrounding mining activity satisfaction among the indigenous population, offering a basis for further exploration and policy development.

Feb 17, 2024

By Richard A. Thomas, Liming Yuan, Wei Tang, JOHN SOLES

Lithium-ion battery applications are increasing for battery-powered vehicles because of their high energy density and expected long cycle life. With the development of battery-powered vehicles, fire and explosion hazards associated with lithium-ion batteries are a safety issue that needs to be addressed. Lithium-ion batteries can go through a thermal runaway under different abuse conditions including thermal abuse, mechanical abuse, and electrical abuse, leading to a fire or explosion. The NIOSH Mining program is conducting research to prevent and respond to lithium-ion battery fires for battery electric vehicles in the mining industry. In this study, experiments were conducted to investigate the effectiveness of different suppression systems including dry chemical, class D powder, and water mist for lithium iron phosphate battery pack fires. The effects of activation time and release time of the water mist system on the suppression of lithium-ion battery fires were studied. The results of this study may be helpful for developing strategic firefighting and response plans for battery-powered vehicles used in mining.

Feb 17, 2024

By Bernd Friedrich, Elif Emil‑Kaya, Merve Papakci

In the production of SmCo permanent magnets with excellent temperature stability, corrosion resistance, and oxidation resistance, samarium (Sm), one of the rare earth elements (REEs), and cobalt (Co) are employed. Cobalt (Co) is a crucial component in tool materials, nickel-based alloys, tablet and smartphone batteries, and electric car batteries. REEs and Co have been listed as critical raw materials by the European Union Commission for many years. Due to the ever-growing demand for Co and REEs in technological applications, the recovery of these elements from secondary sources has garnered significant interest. There are two types of SmCo magnets, one of which contains a high amount of iron, approximately 15.2%. This paper focuses on the recycling of Fe-bearing SmCo. In this study, an oxidative leaching process with nitric acid was developed to eliminate iron through in situ hydrolysis and to dissolve REEs and Co. The influence of experimental conditions on the formation of an amorphous iron compound through the hydrolysis of Fe3+ in a nitric acid environment was thoroughly examined based on a Taguchi orthogonal array. The optimal parameters for oxidative leaching were determined to be an acid concentration of 3 mol/L, a solid-to-liquid ratio of 1/10, and a process temperature of 60 °C.

Feb 15, 2024

By Zoheir Khademian, Morgan Sears

According to the 2010–2019 Mine Safety and Health Administration (MSHA) accident report database, 91% of reported ground control accidents in US longwall mines were caused by roof instability. Gateroads are subjected to significant changes in loading conditions from the development to the longwall abutment loading phases. When combined with thinly bedded shale roof, found in many US longwall coal mines, the design of efficient roof support becomes challenging. In previous work, the bonded block modeling (BBM) of roof by UDEC was validated against field extensometer measurements in a longwall entry roof at a 180-m depth of cover. The BBM was shown capable of capturing delamination and buckling of shale roof, one of the main roof instability mechanisms in longwall mines. This paper presents the recent findings on the roof-support interaction using BBM models of the same longwall entry. The effects of cable bolts, roof bolt density, and strap support on potential roof instability are studied. Results demonstrate the potential for BBM numerical models to help understand the complex roof and support system interactions and to assist with optimizing gateroad support systems.

Feb 13, 2024

By Zhongwei Wang, Dong Wang, Feng Ju

The coal seam in the southern coal field of the Ordos Basin serves as the main aquifer, while the region is known for its high-intensity coal mining activities. The coupling effect of mine water and the strong disturbance caused by high-intensity mining have brought serious challenges to the stability of coal pillars. To address this, a formula for determining the reasonable width of coal pillars under the aforementioned coupling effect and establish a criterion for coal pillar instability in this paper. A case study was on the 11,215 working face at the Xiaojihan coal mine in the area to investigate coal pillar stability. Results indicate that the strength and stability of the coal pillar are affected by the water content, with a small water content increasing its strength and large water content weakening it. In high-intensity exploration of watery coal seams, the best stability of the coal pillar is achieved at optimal water content and mining rates. For the Xiaojihan coal mine, the optimum water content and mining rate are 3.31% and 20 m/d, respectively, ensuring the efficient mining of watery coal seams. Furthermore, this study's findings can provide valuable references for the mining design of coal mines with similar geological conditions in the region.

Feb 13, 2024

By Wei Victor Liu, Omer Faruk Ugurlu, Chengkai Fan, Bei Jiang

The accurate prediction of truck productivity plays a pivotal role in improving the efficiency and profitability of open-pit mining operations. However, predicting truck productivity is challenging owing to the complex nature of the working conditions of the mine site. This paper proposes a deep neural network model to overcome the challenge of predicting truck productivity in open-pit mines. The prediction model was built using eight variables and was optimized by considering different train-test split ratios, numbers of hidden layers and neurons, and activation functions. The proposed model's performance was evaluated using various metrics and was compared with other commonly used machine learning algorithms. According to the results, the proposed model outperformed traditional machine learning algorithms by achieving higher accuracy and lower error rates, with the best-performing model having four hidden layers with 70 neurons per layer and a scaled exponential linear unit activation function, resulting in a coefficient of determination value of 0.89. This demonstrates the potential of deep neural network models for predicting truck productivity in open-pit mine sites. Moreover, a single variable sensitivity analysis was conducted to investigate the impact of input variables on truck productivity. The results show that haul distance is the most influential variable for the prediction of truck productivity.

Feb 12, 2024

By Manoj Khandelwal, Bright Akuinor Tsidi, Newton Amegbey, Daniel Mireku‑Gyimah

One of the ambient effects of production blasting is flyrock. To effectively manage flyrock throw distance in mining, there is the necessity to successfully envisage blasting output without sacrificing the hazardous impact of flyrock which may result in fatality and operational shutdown. For flyrock throw distance prediction, velocity of detonation (VOD) and charge per bank cubic meter (CPBCM) are not usually included. This paper focuses on the use of support vector machine (SVM) regression to ascertain the impact of VOD and CPBCM on flyrock throw predictions. The machine learning models were linear support vector machine (LSVM), quadratic Gaussian support vector machine (QGSVM), fine Gaussian support vector machine (FGSVM), medium Gaussian support vector machine (MGSVM), and cubic Gaussian support vector machine (CGSVM). The outcome indicates that FGSVM was the most sensitive with a 4% improvement when VOD and CPBCM were included. As a result, the LSVM model provides a suitable AI competitive alternative tool for flyrock throw prediction in mining operations by incorporating VOD and CPBCM.

Feb 10, 2024

By Kwadwo Osseo‑Asare, Isehaq Al‑Nafai

The hydrometallurgical processing of bastnasite is a well-known process that is used to extract rare earth metals. However, more accurate measures are required to enhance the efficiency of extracting and recycling rare earths. In this work, Pourbaix (Eh–pH) diagrams for La-, Nd-, and Pr-(F)-(CO3)-(SO4)-(Cl)-(NO3)-(C2O4)-H2O systems were theoretically derived to investigate the stability relations during the hydrometallurgical processing of bastnasite. The diagrams for RE-H2O systems show similar trends to the original ones drown by Pourbaix. The stability domains of RE carbonates were presented by RE-CO3-H2O systems with pH range of 4.5–11. In contrast, the diagrams for RE fluorides showed a large stability region of insoluble REF3 (pH ~ − 1.7–12). The decomposition behaviors of REFCO3 were studied by constructing Eh–pH diagrams for RE-F-CO3-H2O system. The stability regions of bastnasite species extend from nearly neutral to basic media (pH ~ 6.5–12). The acid treatment (using H2SO4, HCl, and HNO3) of bastnasite was investigated by constructing Eh–pH diagrams for REF- CO3-(SO4)-(Cl)-(NO3)-H2O systems. According to these systems, REFCO3 can be decomposed at pH ~ 6.5 when treated with H2SO4 and at pH ~ 1.7 when treated with HCl and HNO3 acids. On the other hand, the alkaline treatment of REFCO3 converts it to RE(OH)3 at pH ~ 11. The recovery of rare earths ions was studied with the aid of RE-C2O4-H2O systems which shows a wide stability region for RE oxalates in pH range of − 2–11. This theoretical approach explained the aqueous relations in the hydrometallurgical processing of bastnasite ore and it can improve the practical hydrometallurgical processing of such ores.

Feb 9, 2024

By Sara Swiokla Korsikas, Toren Olson, Amado Guzman, Yuri O. Zepeda P

Ore agglomeration has been used as part of the heap leaching process for the last 40 years. However, industrial experience shows that the lack of a universal agglomeration standard has limited the benefits of this, otherwise, valuable unit process. The more complex the ore, in terms of the nature and relative abundance of fines (<74 μm), the more important that the agglomeration product satisfies some minimal requirements. This paper presents an agglomeration scale that identifies the quality standards for agglomerates and documents the resulting mechanical, physical, and hydraulic (hydrodynamic) behavior associated with each level on the agglomeration scale. The hydrodynamic properties of an agglomeration product are critical for the proper design of a leaching operation and, as shown in this paper, can be used to select the optimal pretreatment method for a given ore sample. Agglomeration as a unit process not only allows better conditioning of the hydrodynamic behavior of the ore but also creates an opportunity for optimized delivery of reagents to kick-start the leaching process which may ultimately improve the economic performance of leaching. Industrial case data is used to demonstrate the shortfalls associated with low-quality agglomeration and the benefits of improved agglomeration which range from enhanced porous structure (better percolation and drainage characteristics) to better metallurgical response (faster kinetics and higher metal recovery). Proper agglomeration has been used to render otherwise untreatable ores into valuable leaching resources.

Feb 9, 2024

By Arash Nikvar‑Hassani, Timothy Batchler, Lianyang Zhang

Recently, a new hybrid geopolymer/biopolymer (GP/BP) cementitious material was developed for improving the performance of pumpable roof supports in underground mines. This study demonstrates the application of the hybrid GP/BP cementitious material and validates its effectiveness in full-scale. In this regard, eight (8) full-size (0.61 m diameter and 1.52 m height) cribs were produced in collaboration with Minova International Ltd and tested at the National Institute for Occupational Safety and Health (NIOSH) Mine Roof Simulator (MRS) Laboratory. These full-size cribs were produced with different material configurations to evaluate the effect of water to solid (W/S) ratio, Portland cement (PC) content, and BP dosage. The results demonstrated and validated the effectiveness of the hybrid GP/BP cementitious material in increasing the peak and residual bearing capacities of pumpable cribs and eliminating the issue of deterioration when exposed to air compared with the conventional Portland cement/fly ash (PC/FA) cementitious material currently used in practice. On average, the peak uniaxial compressive strength (UCS) and the highest residual UCS after peak of the full-size cribs produced from the hybrid GP/BP cementitious material are 1.90 and 1.33 times of those of the PC/FA-based full-size cribs by one company and 2.32 and 1.66 times of those of the PC/FA based full-size cribs by the other company, respectively.

Feb 6, 2024

By Rongjie Kong, Shiwei Wang, Guomin Wei

Owing to the selective oxidation and uneven combustion that occur on the surface of carbon anode, some carbon particles detach and form carbon residue, which is defined as spent anode slag (SAS). The highly graphitized and toxic impurities such as fluorite ( CaF2), corundum (α-Al2O3), and cryolite ( NaAl11O17) are crucial components of SAS resource but are difficult to separate from graphite. This study developed a method of using water-soluble (emulsified) kerosene to separate the carbon particles from the toxic impurities in the SAS resource. The flotation purification approach of utilizing conventional kerosene was experimentally investigated and compared with that of using water-soluble kerosene. The results showed that with the use of emulsified kerosene, the maximum combustible matter recovery of the carbon particles was 89.86% while that of using traditional kerosene was 80.30%. The emulsified kerosene was comprehensively examined by various instruments to clarify its adsorption mechanism on the carbon particle surfaces. Because of the superior dispersibility of emulsified kerosene, it effectively envelops carbon particles with a smooth surface, oxygen-containing functional groups, and hydrophilic C–F bonds, thereby increasing the surface hydrophobicity and flotation responses of targeted carbon particles.

Feb 6, 2024

By Min Chen, Qinghua Liang, Weishan Yan, Yuan Feng, Shigang Wang

Various coal mine robots (CMRs) and unmanned aerial vehicles (UAVs) are implemented to explore unknown mines for improving the safety and efficiency of mining. It is challenging for CMRs and UAVs to achieve accurate positioning due to the absence of the Global Positioning System (GPS), poor lighting conditions, and similar geometric features in complex mine scenes. LiDAR-based localization and mapping methods are more accurate than others, while long-time running in large-scale scenarios will introduce nonnegligible cumulative errors. This study presents a semantic-aided Li- DAR simultaneous localization and mapping (SLAM) with loop closure, which leverages the uniqueness of mine intersection structure to establish stable semantic loop closure. Specifically, we propose a semantic intersection descriptor of translation and rotation invariance, which encodes 3D point clouds of the same intersection from different positions and viewpoints into a unified image. By using the semantic descriptor, we can construct a constant loop constraint when the same intersection is revisited from different directions to reduce cumulative drift. We provide experimental validation using large data sets collected in two large underground mines, namely, a simulated Edgar mine deployed in ROS Gazebo and a public underground mine data set provided by ETH. Experimental results show that the proposed method has higher localization accuracy and outperforms the existing LiDAR-based SLAM strategies.

Feb 1, 2024