An open-pit mine autonomous driving method, electronic device and storage medium

Abstract

The present invention provides an open-pit mine automatic driving method, an electronic device, and a storage medium. The method includes: receiving an open-pit mine automatic driving instruction, where the open-pit mine automatic driving instruction at least includes an unmanned driving start instruction and an unmanned driving task; switching the driving mode of the mining truck to the unmanned driving mode according to the unmanned driving start instruction; obtaining the current coordinate position information of the corresponding mining truck in the mining area; enumerating all preselected unmanned driving routes based on the current coordinate position information, the unmanned driving task, and the road layout of the mining area; selecting the optimal route according to the distances, road conditions, and traffic flow information of each preselected unmanned driving route and through a preset screening algorithm; and enabling the corresponding mining truck to execute the unmanned driving task according to the optimal route. The present invention can achieve intelligent unmanned driving of mining trucks, replace traditional mining truck drivers, improve the transportation operation efficiency in the mining area, and save labor costs.

Description

Technical Field

[0001] The present invention relates to the field of driverless technologies, and particularly to an open-pit mine automatic driving method, an electronic device, and a storage medium. Background Art

[0002] As a major mineral resource country, China has a large number of coal, metal and other mineral production areas. In all mining areas, transportation is an extremely core issue. As is well known, if the transportation efficiency can be significantly improved, it will contribute to the overall improvement of the production efficiency in the mining area. In terms of transportation in the mining area, cost and safety issues are the main factors restricting mining area transportation.

[0003] In terms of cost, under the general trend of capacity reduction and cost reduction in the mining industry, the personnel cost remains high and increases year by year. Considering the relatively remote geographical location of the mining area and the relatively dangerous driving environment, fewer and fewer people want to be mining truck drivers in recent years. In order to ensure the normal operation of the mining area, companies and others have to spend high costs to hire relatively scarce mining truck drivers.

[0004] In terms of safety, the general natural environment in the mining area is harsh, the dust is serious, and the topography and landforms are changeable. For mining truck drivers, due to the large body of the vehicle and the poor visibility affected by the harsh environment, there are extremely many driving blind spots, which also pose terrible safety hazards.

[0005] Chinese Patent with Publication No. CN214474512U provides a control system for a driverless mining truck. In this system, the vehicle-end communication unit of the mining truck is used as the only communication medium for internal and external communication, so that the driverless control unit and the vehicle control unit of the mining truck can complete corresponding actions according to instructions. The mining truck of this patent is remotely controlled by a remote control platform, rather than achieving true autonomous driverless operation of the mining truck. Although no drivers are required, each mining truck still needs to be equipped with a remote control staff, and the labor cost has not been effectively reduced.

[0006] Chinese Patent with Publication No. CN111781601A provides a driverless system for mining trucks and a mining truck. The driverless system performs layered detection on the road environment where the mining truck is located by setting a lidar group, a long-range millimeter-wave radar group, a medium-range millimeter-wave radar group, and an ultrasonic radar group on the mining truck. It mainly detects road conditions through radar. In the complex environment of the mining area, many obstacles or organisms are easily blocked, and it is difficult for this patent to detect obstacles in complex terrains.

[0007] The Chinese patent with publication number CN112026620A provides an unmanned mining truck with sensing function. It is equipped with laser radar and ultrasonic radar to detect obstacles around the vehicle, so that the vehicle can bypass obstacles during forward movement, steering and reverse movement, ensuring that the vehicle can bypass obstacles and reverse smoothly when unmanned. However, this method is limited to flat and unobstructed terrain environments. Once in a complex mining area, too many obstructions will affect the accuracy of radar detection. Summary of the invention

[0008] In order to solve at least one of the above technical problems, the present invention proposes an open-pit mine automatic driving method, electronic equipment and storage medium, which can realize intelligent unmanned driving of mine trucks, replace traditional mine truck drivers, improve the efficiency of mine transportation operations, and save labor costs. At the same time, since the mine truck adopts an unmanned driving mode, the possibility of personnel activities in the mine area is reduced, effectively reducing the safety hazards of mine operations.

[0009] A first aspect of the present invention provides an open-pit mine automatic driving method, the method comprising:

[0010] receiving an open-pit mine automatic driving instruction, wherein the open-pit mine automatic driving instruction at least includes an unmanned driving start instruction and an unmanned driving task;

[0011] Switch the mining truck driving mode to unmanned driving mode according to the unmanned driving start command;

[0012] Get the current coordinate location information of the corresponding mining card in the mining area;

[0013] Based on the current coordinate location information, unmanned driving tasks and road layout of the mining area, all pre-selected unmanned driving routes are enumerated;

[0014] Based on the distance, road conditions and traffic flow information of each pre-selected unmanned driving route, the optimal route is selected through a preset screening algorithm;

[0015] The corresponding mining truck performs the unmanned driving task according to the optimal route.

[0016] In this solution, the current coordinate position information of the corresponding mining card in the mining area is obtained, including:

[0017] The rough coordinates of the mining truck are initially obtained through the mining truck's positioning module;

[0018] Taking the rough coordinate position as the center and the first preset threshold as the radius, a focus positioning area is defined;

[0019] Obtain multiple signal transmitters deployed around the mining truck and the geographical model of the mining area;

[0020] Based on each position point in the focused positioning area, directly determine whether there is an obstacle between each position point and each signal transmitter through a geographical model. If there is, mark the corresponding signal transmitter as a true blocker; if not, mark the corresponding signal transmitter as a true non-blocker.

[0021] Receive the signals of each signal transmitter through the signal receivers set on the mining card, and measure and calculate the signal-to-noise ratio of each signal.

[0022] Judge whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold. If it is less, mark the corresponding signal transmitter as a suspected blocker; if it is greater than or equal to, mark the corresponding signal transmitter as a suspected non-blocker.

[0023] Based on each position point in the focused positioning area, if a certain signal transmitter is judged as a true blocker and a suspected blocker respectively, add 1 to the score of the corresponding position point; if a certain signal transmitter is judged as a true non-blocker and a suspected blocker respectively, the score of the corresponding position point remains unchanged; if a certain signal transmitter is judged as a true non-blocker and a suspected non-blocker respectively, add 1 to the score of the corresponding position point; if a certain signal transmitter is judged as a true blocker and a suspected non-blocker respectively, the score of the corresponding position point remains unchanged.

[0024] Based on each position point in the focused positioning area, by comparing the true blocking and suspected blocking situations of all signal transmitters, count the total score of each position point.

[0025] Based on the total score of each position point and sort them from high to low to obtain the position point with the highest score.

[0026] If there is one position point with the highest score, directly use the position point with the highest score as the current coordinate position information. If there are multiple, perform clustering on the multiple position points with the highest score based on the density clustering algorithm to obtain the clustering center, and use the clustering center as the current coordinate position information.

[0027] In this solution, after obtaining the position point with the highest score, the method further includes:

[0028] If there are multiple position points with the highest score, calculate the difference K between the total number of signal transmitters and the highest score.

[0029] Based on all the position points with the highest score, obtain all signal transmitters whose true blocking or non-blocking does not match the suspected blocking or non-blocking.

[0030] Statistically count the frequencies of each mismatched signal transmitter in all the position points with the highest score, and screen out the top K mismatched signal transmitters according to the frequency.

[0031] Based on each selected signal transmitter, if the position point of the corresponding highest score is determined to be a real blockage, while the signal transmitter is determined to be a suspected non-blockage through the signal receiver, then the second preset threshold corresponding to the signal transmitter is updated and set to the signal-to-noise ratio of the corresponding signal plus the minimum variable; if the position point of the corresponding highest score is determined to be a real non-blockage, while the signal transmitter is determined to be a suspected blockage through the signal receiver, then the second preset threshold corresponding to the signal transmitter is updated and set to the signal-to-noise ratio of the corresponding signal minus the minimum variable;

[0032] Re-obtain the position point of the highest score according to the updated second preset thresholds of some signal transmitters, and determine the current coordinate position information based on the re-obtained position point of the highest score;

[0033] Use the updated second preset thresholds of some signal transmitters as the thresholds for judging the corresponding signal transmitters at the next positioning moment.

[0034] In this solution, enabling the corresponding mining truck to execute the driverless task according to the optimal route specifically includes:

[0035] Construct an emergency prediction model, and train the emergency prediction model through sample data to obtain an optimized emergency prediction model;

[0036] Real-time obtain the current environmental data around the mining truck through the sensors set on the mining truck;

[0037] Based on the current environmental data, and perform neural network processing through the optimized emergency prediction model to output an emergency plan;

[0038] Enable the mining truck to execute according to the emergency plan.

[0039] In this solution, based on the current environmental data, and perform neural network processing through the optimized emergency prediction model to output an emergency plan, specifically including:

[0040] The current environmental data includes the load of the mining truck and the ground road conditions, and perform neural network processing through the optimized emergency prediction model to output the predicted braking distance of the mining truck;

[0041] Obtain the historical braking data of the mining truck, and each historical braking data includes at least historical environmental data and historical real braking distance, and the historical environmental data includes at least historical load of the mining truck and historical ground road conditions;

[0042] Perform feature calculation on the current environmental data to obtain a first feature value;

[0043] Perform feature calculation on the historical environmental data of each historical braking data respectively to obtain a second feature value;

[0044] Compare the first eigenvalue with each second eigenvalue respectively and calculate the difference degree between them;

[0045] Add the historical braking data with the difference degree less than the third preset threshold to the candidate database;

[0046] Based on the historical environment data of each historical braking data in the candidate database and through processing by the emergency prediction model, output the corresponding historical predicted braking distance;

[0047] Based on each historical braking data in the candidate database, subtract the corresponding historical predicted braking distance from the historical actual braking distance to obtain a single error value;

[0048] Perform an averaging calculation on the error values of all historical braking data in the candidate database to obtain an average error value;

[0049] Add the average error value to the predicted braking distance to obtain a corrected predicted braking distance;

[0050] If an obstacle appears in front of the mining truck, an emergency braking plan needs to be output, and it is ensured that the braking measure is activated when the distance from the obstacle exceeds the corrected predicted braking distance.

[0051] In this solution, according to the distance, road conditions, and traffic flow information of each preselected driverless route, and through a preset screening algorithm, the optimal route is selected, specifically including:

[0052] Compare the distance of each preselected driverless route with the distances of the remaining preselected driverless routes one by one. If the former is shorter than the latter, add 1 to the distance score of the former; otherwise, the distance score of the former remains unchanged;

[0053] Compare the road conditions of each preselected driverless route with the road conditions of the remaining preselected driverless routes one by one. If the former is better than the latter, add 1 to the road condition score of the former; otherwise, the road condition score of the former remains unchanged;

[0054] Compare the traffic flow of each preselected driverless route with the traffic flows of the remaining preselected driverless routes one by one. If the former is less than the latter, add 1 to the traffic flow score of the former; otherwise, the traffic flow score of the former remains unchanged;

[0055] Statistically calculate the total distance score, total road condition score, and total traffic flow score of each preselected driverless route;

[0056] Obtain the influence weights of distance, road conditions, and traffic flow on route selection respectively;

[0057] Based on each preselected driverless route, multiply the total score of the route by the influence weight of the route, multiply the total score of the road condition by the influence weight of the road condition, multiply the total score of the traffic flow by the influence weight of the traffic flow, and accumulate each product to obtain the total score of the preselected driverless route;

[0058] Sort based on the total scores of each preselected driverless route, and use the preselected driverless route with the highest total score as the optimal route.

[0059] A second aspect of the present invention further proposes an electronic device for implementing open-pit mine autonomous driving, including a memory and a processor. The memory includes a program for an open-pit mine autonomous driving method. When the program for the open-pit mine autonomous driving method is executed by the processor, the following steps are implemented:

[0060] Receive an open-pit mine autonomous driving instruction, where the open-pit mine autonomous driving instruction at least includes a driverless start instruction and a driverless task;

[0061] According to the driverless start instruction, switch the driving mode of the mining truck to the driverless mode;

[0062] Obtain the current coordinate position information of the corresponding mining truck in the mining area;

[0063] Based on the current coordinate position information, the driverless task, and the road layout of the mining area, enumerate all preselected driverless routes;

[0064] According to the distance, road condition, and traffic flow information of each preselected driverless route, and select the optimal route through a preset screening algorithm;

[0065] Make the corresponding mining truck execute the driverless task according to the optimal route.

[0066] In this solution, obtaining the current coordinate position information of the corresponding mining truck in the mining area specifically includes:

[0067] Preliminarily obtain the rough coordinate position of the mining truck through the positioning module of the mining truck;

[0068] With the rough coordinate position as the center and a first preset threshold as the radius, delimit a focused positioning area;

[0069] Obtain multiple signal transmitters arranged around the mining truck and the geographical model of the mining area;

[0070] Based on each position point in the focused positioning area, directly judge through the geographical model whether there are obstacles between each position point and each signal transmitter. If there are, record the corresponding signal transmitter as a real obstruction. If not, record the corresponding signal transmitter as a real non-obstruction;

[0071] The signals of each signal transmitter are received by a signal receiver set on the mining card, and the signal-to-noise ratio of each signal is measured and calculated;

[0072] Determine whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold. If it is less, mark the corresponding signal transmitter as a suspected blocker. If it is greater than or equal to, mark the corresponding signal transmitter as a suspected non-blocker;

[0073] Based on each position point in the focusing and positioning area, if a signal transmitter is respectively judged as a real blocker and a suspected blocker, add 1 to the corresponding position point score. If a signal transmitter is respectively judged as a real non-blocker and a suspected blocker, the corresponding position point score remains unchanged. If a signal transmitter is respectively judged as a real non-blocker and a suspected non-blocker, add 1 to the corresponding position point score. If a signal transmitter is respectively judged as a real blocker and a suspected non-blocker, the corresponding position point score remains unchanged;

[0074] Based on each position point in the focusing and positioning area, by comparing the real blocking and suspected blocking situations of all signal transmitters, count the total score of each position point;

[0075] Based on the total score of each position point and sort them from high to low to obtain the position point with the highest score;

[0076] If there is one position point with the highest score, directly use the position point with the highest score as the current coordinate position information. If there are multiple, cluster the multiple position points with the highest score based on the density clustering algorithm to obtain the clustering center, and use the clustering center as the current coordinate position information.

[0077] In this solution, after obtaining the position point with the highest score, when the open-pit mine automatic driving method program is executed by the processor, the following steps are also implemented:

[0078] If there are multiple position points with the highest score, calculate the difference K between the total number of signal transmitters and the highest score;

[0079] Based on all the position points with the highest score, obtain all signal transmitters whose real blocking or non-blocking does not match the suspected blocking or non-blocking;

[0080] Count the frequencies of each non-matching signal transmitter appearing in all the position points with the highest score, and screen out the top K non-matching signal transmitters according to the frequency;

[0081] Based on each selected signal transmitter, if the position point of the corresponding highest score is determined to be a true block, and the signal transmitter is determined to be a suspected non-block by the signal receiver, then the second preset threshold corresponding to the signal transmitter is updated and set to the signal-to-noise ratio of the corresponding signal plus the minimum variable; if the position point of the corresponding highest score is determined to be a true non-block, and the signal transmitter is determined to be a suspected block by the signal receiver, then the second preset threshold corresponding to the signal transmitter is updated and set to the signal-to-noise ratio of the corresponding signal minus the minimum variable;

[0082] Re-obtain the position point of the highest score according to the updated second preset threshold of some signal transmitters, and determine the current coordinate position information based on the re-obtained position point of the highest score;

[0083] Use the updated second preset threshold of some signal transmitters as the threshold for judging the corresponding signal transmitter at the next positioning moment.

[0084] The third aspect of the present invention also proposes a computer-readable storage medium, which includes a program for an open-pit mine automatic driving method. When the program for the open-pit mine automatic driving method is executed by a processor, the steps of an open-pit mine automatic driving method as described above are implemented.

[0085] An open-pit mine automatic driving method, an electronic device and a storage medium proposed by the present invention can realize the intelligent driverless operation of mining trucks, replace traditional mining truck drivers, improve the efficiency of mining area transportation operations, save labor costs, and at the same time, since the mining trucks adopt a driverless mode, the possibility of personnel moving in the mining area is reduced, effectively reducing the potential safety hazards of mining area operations.

[0086] The additional aspects and advantages of the present invention will be given in the following description part, some will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] Figure 1 Shows a flowchart of an open-pit mine automatic driving method of the present invention;

[0088] Figure 2 Shows a block diagram of an electronic device of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0089] In order to be able to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention will be further described in detail below with reference to the drawings and specific embodiments. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0090] In the following description, many specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced in other ways than those described herein. Therefore, the scope of protection of the present invention is not limited by the specific embodiments disclosed below.

[0091] Figure 1 The flowchart of a method for automatic driving in an open-pit mine according to the present invention is shown.

[0092] As Figure 1 shown, a first aspect of the present invention proposes a method for automatic driving in an open-pit mine, the method comprising:

[0093] S102, receiving an automatic driving instruction for an open-pit mine, the automatic driving instruction for the open-pit mine including at least an unmanned driving start instruction and an unmanned driving task;

[0094] S104, switching the driving mode of the mining truck to the unmanned driving mode according to the unmanned driving start instruction;

[0095] S106, obtaining the current coordinate position information of the corresponding mining truck in the mining area;

[0096] S108, enumerating all preselected unmanned driving routes based on the current coordinate position information, the unmanned driving task, and the road layout of the mining area;

[0097] S110, selecting the optimal route according to the distance, road conditions, and traffic flow information of each preselected unmanned driving route and through a preset screening algorithm;

[0098] S112, causing the corresponding mining truck to execute the unmanned driving task according to the optimal route.

[0099] It should be noted that the unmanned driving start instruction is usually sent to the corresponding mining truck in the mining area through the background. Since the mining truck usually has two modes, one is the manual driving mode and the other is the unmanned driving mode. When the mining truck receives the automatic driving instruction for the open-pit mine, it obtains the unmanned driving start instruction and, according to the unmanned driving start instruction, in combination with the current driving mode of the mining truck, adjusts and switches to the unmanned driving mode.

[0100] It can be understood that the unmanned driving task of the present invention may include the destination of the unmanned driving, the mining machine for cooperation in loading, etc., but is not limited thereto.

[0101] First, the present invention adjusts the mining truck to the driverless mode and accurately obtains the current coordinate position information. Then, based on the current coordinate position information, the driverless task, and the road layout of the mining area, and through a screening algorithm, the optimal route is selected, and the corresponding mining truck is made to execute the driverless task according to the optimal route. The present invention can realize the intelligent driverless of the mining truck, replace the traditional mining truck driver, improve the transportation operation efficiency of the mining area, save labor costs, and at the same time, since the mining truck adopts the driverless mode, it reduces the possibility of personnel activities in the mining area and effectively reduces the safety hazards of mining area operations.

[0102] According to an embodiment of the present invention, obtaining the current coordinate position information of the corresponding mining truck in the mining area specifically includes:

[0103] Preliminarily obtain the rough coordinate position of the mining truck through the positioning module of the mining truck;

[0104] Taking the rough coordinate position as the center and a first preset threshold as the radius, demarcate a focused positioning area;

[0105] Obtain a plurality of signal transmitters arranged around the mining truck and the geographical model of the mining area;

[0106] Based on each position point in the focused positioning area, directly judge through the geographical model whether there is an obstacle between each position point and each signal transmitter. If there is, record the corresponding signal transmitter as a true block, and if not, record the corresponding signal transmitter as a true non-block;

[0107] Receive the signals of each signal transmitter through the signal receiver arranged on the mining truck, and measure and calculate the signal-to-noise ratio of each signal;

[0108] Judge whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold. If it is less, record the corresponding signal transmitter as a suspected block, and if it is greater than or equal to, record the corresponding signal transmitter as a suspected non-block;

[0109] Based on each position point in the focused positioning area, if a certain signal transmitter is respectively judged as a true block and a suspected block, add 1 to the score of the corresponding position point. If a certain signal transmitter is respectively judged as a true non-block and a suspected block, the score of the corresponding position point remains unchanged. If a certain signal transmitter is respectively judged as a true non-block and a suspected non-block, add 1 to the score of the corresponding position point. If a certain signal transmitter is respectively judged as a true block and a suspected non-block, the score of the corresponding position point remains unchanged;

[0110] Based on each position point in the focused positioning area, by comparing the true block and suspected block situations of all signal transmitters, count the total score of each position point;

[0111] Based on the total score of each position point and sorted from high to low, obtain the position point with the highest score;

[0112] If there is only one position point with the highest score, directly use the position point with the highest score as the current coordinate position information. If there are multiple such position points, perform clustering on the multiple position points with the highest score based on the density clustering algorithm to obtain the clustering center, and use the clustering center as the current coordinate position information.

[0113] It can be understood that the signal-to-noise ratio is the ratio of the signal to the noise in an electronic device. If there is no occlusion, the signal emitted by the signal transmitter can be directly received by the signal receiver, and the corresponding signal-to-noise ratio value is relatively large. If it is blocked, the signal may be reflected, refracted, etc., generating excessive noise, which will cause the corresponding signal-to-noise ratio value to become smaller.

[0114] It should be noted that in the mining area, due to the complex terrain restrictions in the mining area, the mining truck cannot complete precise position positioning. The present invention first performs rough positioning through the positioning module, and then based on the rough coordinate position, combines multiple signal transmitters in the mining area and the signal receiver on the mining truck to further adjust the rough coordinate position to obtain more accurate coordinate position information.

[0115] According to a specific embodiment of the present invention, after obtaining the clustering center, the method further includes;

[0116] Taking the clustering center as the reference point to create a two-dimensional coordinate system, perform secondary clustering on the multiple position points with the highest score in each sector of the two-dimensional coordinate system to obtain the sector clustering center;

[0117] Respectively create sub-vectors from the clustering center to each sector clustering center;

[0118] By querying the activity data of the mining truck at historical times, count the number of times the mining truck appears in each sector;

[0119] Perform normalization processing on the number of times the mining truck appears in each sector, and calculate the weight probability of each sector;

[0120] Multiply the sub-vectors of each sector by the corresponding weight probability to obtain the weighted sub-vectors;

[0121] Perform vector addition on multiple weighted sub-vectors to obtain the corrected clustering center.

[0122] It can be understood that affected by the terrain and landforms at various positions in the mining area, there are more ground obstacles in some areas (such as a certain sector), and the frequency of the mining truck appearing is not high. In some areas, the ground is relatively flat, and the frequency of the mining truck appearing is relatively high. The present invention corrects the clustering center based on the frequency of the mining truck appearing in different sectors, so as to obtain more accurate coordinate position information.

[0123] According to an embodiment of the present invention, after obtaining the position point with the highest score, the method further includes:

[0124] If there are multiple position points with the highest score, calculate the difference K between the total number of signal transmitters and the highest score;

[0125] Based on all the position points with the highest score, obtain all the signal transmitters whose actual blocked or not does not match the suspected blocked or not;

[0126] Count the frequencies of each mismatched signal transmitter at all the position points with the highest score, and screen out the top K mismatched signal transmitters according to the frequency;

[0127] Based on each screened signal transmitter, if the position point corresponding to the highest score is determined to be actually blocked, while the signal transmitter is determined to be suspected of not being blocked by the signal receiver, update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal plus the minimum variable. If the position point corresponding to the highest score is determined to be actually not blocked, while the signal transmitter is determined to be suspected of being blocked by the signal receiver, update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal minus the minimum variable;

[0128] Re-obtain the position point with the highest score according to the updated second preset thresholds of some signal transmitters, and determine the current coordinate position information based on the re-obtained position point with the highest score;

[0129] Use the updated second preset thresholds of some signal transmitters as the thresholds for judging the corresponding signal transmitters at the next positioning moment.

[0130] It can be understood that the minimum variable of the signal-to-noise ratio of the present invention is 1, but it is not limited thereto.

[0131] It should be noted that the environment in the mining area is relatively complex. For example, when there is dust flying, the dust will cause phenomena such as signal refraction and emission. If there is a large amount of dust floating in the air between a certain signal transmitter and the signal receiver, although there are no other blocking objects, the calculated signal-to-noise ratio is not high. If the second preset threshold is uniformly set as a fixed value and compared with the higher second preset threshold through the signal-to-noise ratio, misjudgment will occur. Therefore, the present invention first screens out the misjudged signal transmitters through the frequency, then updates the second preset threshold of the corresponding signal transmitter based on the signal-to-noise ratio, and at the same time introduces the updated second preset threshold into the next positioning moment, realizing the dynamic change of the second preset threshold in combination with the actual environment, and further improving the positioning accuracy of the current coordinate position.

[0132] According to an embodiment of the present invention, enabling the corresponding mining truck to execute the driverless task according to the optimal route specifically includes:

[0133] Construct an emergency prediction model, train the emergency prediction model with sample data to obtain an optimized emergency prediction model;

[0134] Obtain the current environmental data around the mining truck in real time through sensors set on the mining truck;

[0135] Based on the current environmental data, perform neural network processing through the optimized emergency prediction model, and output an emergency plan;

[0136] Make the mining truck execute according to the emergency plan.

[0137] It should be noted that during the automatic driving process of open-pit mines, various emergencies may occur, such as the sudden appearance of pedestrians, obstacles, etc. At this time, the mining truck needs to quickly make an emergency plan to avoid pedestrians or emergency braking to avoid unnecessary safety accidents.

[0138] According to the embodiments of the present invention, based on the current environmental data, perform neural network processing through the optimized emergency prediction model, and output an emergency plan, specifically including:

[0139] The current environmental data includes the load of the mining truck and the ground road conditions, and perform neural network processing through the optimized emergency prediction model to output the predicted braking distance of the mining truck;

[0140] Obtain the historical braking data of the mining truck. Each historical braking data includes at least historical environmental data and historical actual braking distance. The historical environmental data includes at least historical mining truck load and historical ground road conditions;

[0141] Perform feature calculation on the current environmental data to obtain a first eigenvalue;

[0142] Perform feature calculation on the historical environmental data of each historical braking data respectively to obtain a second eigenvalue;

[0143] Compare the first eigenvalue with each second eigenvalue respectively, and calculate the difference degree between the two;

[0144] Add the historical braking data with the difference degree less than the third preset threshold to the candidate database;

[0145] Based on the historical environmental data of each historical braking data in the candidate database, perform processing through the emergency prediction model, and output the corresponding historical predicted braking distance;

[0146] Based on each historical braking data in the candidate database, subtract the corresponding historical predicted braking distance from the historical actual braking distance to obtain a single error value;

[0147] The error values ​​of all historical braking data in the candidate database are averaged to obtain an average error value;

[0148] The predicted braking distance is added to the average error value to obtain a corrected predicted braking distance;

[0149] If an obstacle appears in front of the mining truck, an emergency braking plan needs to be output, and braking measures must be initiated when the distance to the obstacle exceeds the corrected predicted braking distance.

[0150] It should be noted that if a mining truck encounters an obstacle during normal driving, braking measures need to be taken. The present invention predicts the braking distance through a model, and further corrects the predicted braking distance in combination with historical braking data, thereby predicting a more accurate braking distance that is more in line with the actual value, and then making emergency plans based on the predicted braking distance, such as starting braking measures outside the range of the predicted braking distance. Therefore, the present invention can effectively improve the safety of autonomous driving in open-pit mines.

[0151] According to an embodiment of the present invention, based on the distance, road conditions and traffic flow information of each pre-selected unmanned driving route, the optimal route is selected through a preset screening algorithm, specifically including:

[0152] The distance of each pre-selected driverless route is compared with the distance of the remaining pre-selected driverless routes one by one. If the former is shorter than the latter, the distance score of the former is increased by 1, otherwise, the distance score of the former remains unchanged;

[0153] The road condition of each pre-selected unmanned driving route is compared with the road condition of the remaining pre-selected unmanned driving routes one by one. If the former is better than the latter, the road condition score of the former is increased by 1, otherwise, the road condition score of the former remains unchanged;

[0154] The traffic volume of each pre-selected unmanned driving route is compared with the traffic volume of the remaining pre-selected unmanned driving routes one by one. If the former is less than the latter, the traffic volume score of the former is increased by 1, otherwise, the traffic volume score of the former remains unchanged;

[0155] Calculate the total score of the distance, road condition and traffic flow of each pre-selected driverless route;

[0156] Obtain the influence weights of distance, road conditions and traffic volume on route selection respectively;

[0157] Based on each pre-selected driverless route, the total score of the distance is multiplied by the influence weight of the distance, the total score of the road condition is multiplied by the influence weight of the road condition, and the total score of the traffic flow is multiplied by the influence weight of the traffic flow, and each product is accumulated to obtain the total score of the pre-selected driverless route;

[0158] Sort based on the total scores of each preselected driverless route, and use the preselected driverless route with the highest total score as the optimal route.

[0159] It should be noted that there may be multiple routes in the mining area. When performing a driverless task, multiple routes can be adopted. By comparing the differences between multiple routes, the present invention selects the optimal route, thereby facilitating the improvement of the efficiency of the mining truck in performing driverless tasks and further enhancing the overall operation efficiency of the mining area operation.

[0160] Figure 2 The block diagram of an electronic device according to the present invention is shown.

[0161] As Figure 2 shown, the second aspect of the present invention also proposes an electronic device for realizing open-pit mine automatic driving, including a memory and a processor. The memory includes an open-pit mine automatic driving method program. When the open-pit mine automatic driving method program is executed by the processor, the following steps are realized:

[0162] Receive an open-pit mine automatic driving instruction, where the open-pit mine automatic driving instruction at least includes a driverless start instruction and a driverless task;

[0163] Switch the driving mode of the mining truck to the driverless mode according to the driverless start instruction;

[0164] Obtain the current coordinate position information of the corresponding mining truck in the mining area;

[0165] Enumerate all preselected driverless routes based on the current coordinate position information, the driverless task, and the road layout of the mining area;

[0166] According to the distance, road conditions, and traffic flow information of each preselected driverless route, and select the optimal route through a preset screening algorithm;

[0167] Make the corresponding mining truck execute the driverless task according to the optimal route.

[0168] According to an embodiment of the present invention, obtaining the current coordinate position information of the corresponding mining truck in the mining area specifically includes:

[0169] Preliminarily obtain the rough coordinate position of the mining truck through the positioning module of the mining truck;

[0170] Taking the rough coordinate position as the center, delineate a focused positioning area with a first preset threshold as the radius;

[0171] Obtain multiple signal transmitters arranged around the mining truck and the geographical model of the mining area;

[0172] Based on each position point in the focused positioning area, directly determine whether there is an obstacle between each position point and each signal transmitter through a geographical model. If there is, mark the corresponding signal transmitter as a true blocker; if not, mark the corresponding signal transmitter as a true non-blocker.

[0173] Receive the signals of each signal transmitter through the signal receivers set on the mining card, and measure and calculate the signal-to-noise ratio of each signal.

[0174] Judge whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold. If it is less, mark the corresponding signal transmitter as a suspected blocker; if it is greater than or equal to, mark the corresponding signal transmitter as a suspected non-blocker.

[0175] Based on each position point in the focused positioning area, if a certain signal transmitter is judged as a true blocker and a suspected blocker respectively, add 1 to the score of the corresponding position point; if a certain signal transmitter is judged as a true non-blocker and a suspected blocker respectively, the score of the corresponding position point remains unchanged; if a certain signal transmitter is judged as a true non-blocker and a suspected non-blocker respectively, add 1 to the score of the corresponding position point; if a certain signal transmitter is judged as a true blocker and a suspected non-blocker respectively, the score of the corresponding position point remains unchanged.

[0176] Based on each position point in the focused positioning area, by comparing the true blocking and suspected blocking situations of all signal transmitters, count the total score of each position point.

[0177] Based on the total score of each position point and sort them from high to low to obtain the position point with the highest score.

[0178] If there is one position point with the highest score, directly use the position point with the highest score as the current coordinate position information. If there are multiple, perform clustering on the multiple position points with the highest score based on the density clustering algorithm to obtain the clustering center, and use the clustering center as the current coordinate position information.

[0179] According to the embodiments of the present invention, after obtaining the position point with the highest score, when the open-pit mine automatic driving method program is executed by the processor, the following steps are further implemented:

[0180] If there are multiple position points with the highest score, calculate the difference K between the total number of signal transmitters and the highest score.

[0181] Based on all the position points with the highest score, obtain all the signal transmitters whose true blocking or non-blocking does not match the suspected blocking or non-blocking.

[0182] Statistically count the frequency of each non-matching signal transmitter appearing in all the position points with the highest score, and screen out the top K non-matching signal transmitters according to the frequency.

[0183] Based on each selected signal transmitter, if the position point of the corresponding highest score is determined to be a true block, and the signal transmitter is determined to be a suspected non-block by the signal receiver, then update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal plus the minimum variable; if the position point of the corresponding highest score is determined to be a true non-block, and the signal transmitter is determined to be a suspected block by the signal receiver, then update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal minus the minimum variable;

[0184] Re-obtain the position point of the highest score according to the updated second preset thresholds of some signal transmitters, and determine the current coordinate position information based on the re-obtained position point of the highest score;

[0185] Use the updated second preset thresholds of some signal transmitters as the thresholds for judging the corresponding signal transmitters at the next positioning moment.

[0186] The third aspect of the present invention also proposes a computer-readable storage medium, which includes a program for an open-pit mine automatic driving method. When the program for the open-pit mine automatic driving method is executed by a processor, the steps of an open-pit mine automatic driving method as described above are implemented.

[0187] An open-pit mine automatic driving method, an electronic device and a storage medium proposed by the present invention can realize the intelligent driverless operation of mining trucks, replace traditional mining truck drivers, improve the efficiency of mining area transportation operations, save labor costs, and at the same time, since the mining trucks adopt the driverless mode, the possibility of personnel moving in the mining area is reduced, effectively reducing the potential safety hazards of mining area operations.

[0188] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored, or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0189] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units; they can be located in one place or distributed to multiple network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0190] In addition, each functional unit in the embodiments of the present invention may be entirely integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the above-mentioned integrated unit may be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0191] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks and other various media that can store program codes.

[0192] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present invention essentially or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, ROM, RAM, magnetic disks, or optical disks and other various media that can store program codes.

[0193] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An open-pit mine autonomous driving method, characterized in that, The method includes: receiving an open-pit mine autonomous driving instruction, where the open-pit mine autonomous driving instruction at least includes an unmanned driving start instruction and an unmanned driving task; switching the driving mode of the mining truck to the unmanned driving mode according to the unmanned driving start instruction; obtaining the current coordinate position information of the corresponding mining truck in the mining area; enumerating all preselected unmanned driving routes based on the current coordinate position information, the unmanned driving task, and the road layout of the mining area; selecting the optimal route according to the distance, road conditions, and traffic flow information of each preselected unmanned driving route, and through a preset screening algorithm; and enabling the corresponding mining truck to execute the unmanned driving task according to the optimal route. Obtaining the current coordinate position information of the corresponding mining truck in the mining area specifically includes: preliminarily obtaining the rough coordinate position of the mining truck through the positioning module of the mining truck; delineating a focused positioning area with the rough coordinate position as the center and the first preset threshold as the radius; obtaining a plurality of signal transmitters arranged around the mining truck and the geographical model of the mining area; based on each position point in the focused positioning area, directly judging through the geographical model whether there is an obstacle between each position point and each signal transmitter. If there is, record the corresponding signal transmitter as a real obstruction. If not, record the corresponding signal transmitter as a real non-obstruction; receiving the signals of each signal transmitter through the signal receiver set on the mining truck, and measuring and calculating to obtain the signal-to-noise ratio of each signal; judging whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold. If it is less, record the corresponding signal transmitter as a suspected obstruction. If it is greater than or equal to, record the corresponding signal transmitter as a suspected non-obstruction; based on each position point in the focused positioning area, if a certain signal transmitter is respectively judged as a real obstruction and a suspected obstruction, add 1 to the score of the corresponding position point. If a certain signal transmitter is respectively judged as a real non-obstruction and a suspected obstruction, the score of the corresponding position point remains unchanged. If a certain signal transmitter is respectively judged as a real non-obstruction and a suspected non-obstruction, add 1 to the score of the corresponding position point. If a certain signal transmitter is respectively judged as a real obstruction and a suspected non-obstruction, the score of the corresponding position point remains unchanged; based on each position point in the focused positioning area, by comparing the real obstruction and suspected obstruction situations of all signal transmitters, statistically calculate the total score of each position point; based on the total score of each position point, and sorting according to high and low scores, obtain the position point with the highest score; if the position point with the highest score is one, directly use the position point with the highest score as the current coordinate position information. If there are multiple, perform clustering on the multiple position points with the highest score based on the density clustering algorithm to obtain the clustering center, and use the clustering center as the current coordinate position information.

2. The open-pit mine automatic driving method according to claim 1, wherein After obtaining the position point with the highest score, the method further includes: if there are multiple position points with the highest score, calculating the difference K between the total number of signal transmitters and the highest score; based on all the position points with the highest score, obtaining all the signal transmitters whose actual blocked or not status does not match the suspected blocked or not status; counting the frequencies of each unmatched signal transmitter at all the position points with the highest score, and screening out the top K unmatched signal transmitters according to the high and low frequencies; based on each screened signal transmitter, if the position point corresponding to the highest score is determined to be actually blocked, while the signal receiver determines that the signal transmitter is suspected to be unblocked, then updating and setting the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal plus the minimum variable, if the position point corresponding to the highest score is determined to be actually unblocked, while the signal receiver determines that the signal transmitter is suspected to be blocked, then updating and setting the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal minus the minimum variable; re-obtaining the position point with the highest score according to the updated second preset thresholds of some signal transmitters, and determining the current coordinate position information based on the re-obtained position point with the highest score; using the updated second preset thresholds of some signal transmitters as the thresholds for judging the corresponding signal transmitters at the next positioning moment.

3. The open-pit mine automatic driving method according to claim 1, wherein Making the corresponding mining truck execute the driverless task according to the optimal route specifically includes: constructing an emergency prediction model, training the emergency prediction model through sample data to obtain an optimized emergency prediction model; obtaining the current environmental data around the mining truck in real time through sensors arranged on the mining truck; based on the current environmental data, and performing neural network processing through the optimized emergency prediction model to output an emergency plan; making the mining truck execute according to the emergency plan.

4. The open-pit mine automatic driving method according to claim 3, wherein, Based on the current environmental data, neural network processing is performed through the optimized emergency prediction model to output an emergency plan, which specifically includes: the current environmental data includes the load weight of the mining truck and the ground road conditions, and the neural network processing is performed through the optimized emergency prediction model to output the predicted braking distance of the mining truck; the historical braking data of the mining truck is obtained, and each historical braking data at least includes historical environmental data and historical real braking distance, and the historical environmental data at least includes historical mining truck load weight and historical ground road conditions; feature calculation is performed on the current environmental data to obtain a first feature value; feature calculation is performed on the historical environmental data of each historical braking data to obtain a second feature value; the first feature value is compared with each second feature value, and the difference between the two is calculated; The historical braking data with a difference less than a third preset threshold value is added to the candidate database; based on the historical environmental data of each historical braking data in the candidate database, and processed through the emergency prediction model, the corresponding historical predicted braking distance is output; based on each historical braking data in the candidate database, the historical actual braking distance is subtracted from the corresponding historical predicted braking distance to obtain a single error value; the error values ​​of all historical braking data in the candidate database are averaged to obtain an average error value; the predicted braking distance is added to the average error value to obtain a corrected predicted braking distance; if an obstacle appears in front of the mining truck, it is necessary to output an emergency braking emergency plan, and ensure that braking measures are initiated when the distance to the obstacle exceeds the corrected predicted braking distance.

5. The automatic driving method for an open-pit mine according to claim 1, wherein According to the distance, road condition and traffic flow information of each pre-selected unmanned driving route, the optimal route is selected through a preset screening algorithm, specifically including: comparing the distance of each pre-selected unmanned driving route with the distance of the remaining pre-selected unmanned driving routes one by one, if the former is shorter than the latter, the distance score of the former is increased by 1, otherwise, the distance score of the former remains unchanged; comparing the road condition of each pre-selected unmanned driving route with the road condition of the remaining pre-selected unmanned driving routes one by one, if the former is better than the latter, the road condition score of the former is increased by 1, otherwise, the road condition score of the former remains unchanged; comparing the traffic flow of each pre-selected unmanned driving route with the traffic flow of the remaining pre-selected unmanned driving routes one by one Compare, if the former is less than the latter, then add 1 to the traffic flow score of the former, otherwise, the traffic flow score of the former remains unchanged; count the total distance score, total road condition score and total traffic flow score of each pre-selected unmanned driving route; obtain the influence weights of the distance, road condition and traffic flow on route selection respectively; based on each pre-selected unmanned driving route, multiply the total distance score by the influence weight of the distance, the total road condition score by the influence weight of the road condition, and the total traffic flow score by the influence weight of the traffic flow, and accumulate each product to obtain the total score of the pre-selected unmanned driving route; sort the pre-selected unmanned driving routes based on their total scores, and take the pre-selected unmanned driving route with the highest total score as the optimal route.

6. An electronic device for implementing open-pit mine autonomous driving, characterized in that, The invention comprises a memory and a processor, wherein the memory comprises an open-pit mine automatic driving method program, and the open-pit mine automatic driving method program implements the following steps when executed by the processor: receiving an open-pit mine automatic driving instruction, wherein the open-pit mine automatic driving instruction comprises at least an unmanned driving start instruction and an unmanned driving task; switching the mining truck driving mode to the unmanned driving mode according to the unmanned driving start instruction; obtaining the current coordinate position information of the corresponding mining truck in the mining area; enumerating all pre-selected unmanned driving routes based on the current coordinate position information, the unmanned driving task and the road layout of the mining area; selecting the optimal route according to the distance, road condition and traffic flow information of each pre-selected unmanned driving route and through a preset screening algorithm; enabling the corresponding mining truck to perform the unmanned driving task according to the optimal route; The method of obtaining the current coordinate position information of the corresponding mining card in the mining area specifically includes: preliminarily obtaining the rough coordinate position of the mining card through the positioning module of the mining card; defining a focus positioning area with the rough coordinate position as the center and the first preset threshold as the radius; obtaining multiple signal transmitters arranged around the mining card, and the geographical model of the mining area; based on each position point in the focus positioning area, directly judging whether there is an obstacle between each position point and each signal transmitter through the geographical model, if so, the corresponding signal transmitter is recorded as a real barrier, if not, the corresponding signal transmitter is recorded as a real non-barrier; receiving the signal of each signal transmitter through the signal receiver arranged on the mining card, and measuring and calculating the signal-to-noise ratio of each signal; judging whether the signal-to-noise ratio of each signal is less than the corresponding second preset threshold, if less than, the corresponding signal transmitter is recorded as a suspected barrier, if greater than or equal to, the corresponding signal transmitter is recorded as a suspected non-barrier; based on each position point in the focus positioning area, if If a signal transmitter is judged as a real blockage and a suspected blockage respectively, the score of the corresponding position point is increased by 1; if a signal transmitter is judged as a real non-blockage and a suspected non-blockage respectively, the score of the corresponding position point remains unchanged; if a signal transmitter is judged as a real non-blockage and a suspected non-blockage respectively, the score of the corresponding position point is increased by 1; if a signal transmitter is judged as a real blockage and a suspected non-blocking respectively, the score of the corresponding position point remains unchanged; based on each position point in the focus positioning area, the total score of each position point is calculated by comparing the real blockage and the suspected blockage of all signal transmitters; based on the total score of each position point, the positions are sorted by high and low scores to obtain the position point with the highest score; if there is only one position point with the highest score, the position point with the highest score is directly used as the current coordinate position information; if there are multiple position points with the highest scores, the multiple position points with the highest scores are clustered based on the density clustering algorithm to obtain the cluster center, and the cluster center is used as the current coordinate position information.

7. An electronic device according to claim 6, characterized in that, After obtaining the position point with the highest score, when the open-pit mine automatic driving method program is executed by the processor, the following steps are further implemented: If there are multiple position points with the highest score, calculate the difference K between the total number of signal transmitters and the highest score; Based on all the position points with the highest score, obtain all the signal transmitters whose actual blocked or not status does not match the suspected blocked or not status; Count the frequencies of each non-matching signal transmitter at all the position points with the highest score, and screen out the top K non-matching signal transmitters according to the high and low frequencies; Based on each screened signal transmitter, if the corresponding position point with the highest score is judged to be actually blocked, and the signal receiver judges that the signal transmitter is suspected of not being blocked, then update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal plus the minimum variable. If the corresponding position point with the highest score is judged to be actually not blocked, and the signal receiver judges that the signal transmitter is suspected of being blocked, then update and set the second preset threshold corresponding to the signal transmitter to the signal-to-noise ratio of the corresponding signal minus the minimum variable; Re-obtain the position point with the highest score according to the updated second preset thresholds of some signal transmitters, and determine the current coordinate position information based on the re-obtained position point with the highest score; Use the updated second preset thresholds of some signal transmitters as the thresholds for judging the corresponding signal transmitters at the next positioning moment.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes an open-pit mine automatic driving method program. When the open-pit mine automatic driving method program is executed by a processor, the steps of an open-pit mine automatic driving method as described in any one of claims 1 to 5 are implemented.

Images