CN115649158A - A mine vehicle anti-collision method, device and storage medium - Google Patents

Abstract

The application discloses a mine vehicle anti-collision method which is used for solving the technical problems that an existing mine vehicle anti-collision scheme is low in precision and inaccurate in obstacle identification. The method comprises the following steps: acquiring data measured by a plurality of sensors; data preprocessing is carried out on the data measured by the sensors; determining a tracking target based on the preprocessed data, and associating and fusing the tracking target; screening the tracking target according to the driving path of the mine vehicle, and determining the tracking target with the closest distance as a dangerous target; and calculating early warning time and braking time of the collision of the dangerous target and the mine vehicle, and controlling the early warning or braking of the mine vehicle according to the early warning time and the braking time. According to the method, the target motion track is predicted in a short time, so that collision can be avoided in time, forward collision and backward collision are considered, the safety is higher, and safe operation of underground mine vehicles is guaranteed.

Description

A mine vehicle anti-collision method, device and storage medium

technical field

The present application relates to the technical field of unmanned vehicles, in particular to a mine vehicle anti-collision method, equipment and storage medium.

Background technique

The production environment of underground mines is harsh, and mine trucks are mainly used to carry out transportation tasks. Mine transportation is related to safety production. According to statistics, about 1/4 of mine safety accidents occur in the transportation link. Therefore, safe transportation has become an increasingly important part of current mine production.

Generally speaking, mine vehicles are equipped with corresponding anti-collision systems or equipment to avoid collisions between vehicles and obstacles in an underground dark environment. Some strategies use the signal strength of the wireless network transmitter to judge the distance of the opposite mine car, and implement the corresponding anti-collision strategy. There are also combinations of lora wireless communication technology, RFID technology and laser radar, or visual technology to identify whether there are obstacles ahead. However, these solutions more or less have problems such as high cost, low precision, false triggering, and inaccurate obstacle recognition.

Contents of the invention

The embodiment of the present application provides a mine vehicle anti-collision method, equipment and storage medium, which are used to solve the technical problems of low precision and inaccurate obstacle identification in existing mine vehicle anti-collision schemes.

On the one hand, the embodiment of the present application provides a mine vehicle anti-collision method, the method comprising:

Obtain data measured by multiple sensors;

performing data preprocessing on data measured by the plurality of sensors;

Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target;

Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target;

Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

In an implementation manner of the present application, the performing data preprocessing on the data measured by the multiple sensors specifically includes:

Obtain the image data captured by the camera and the radar data detected by the radar;

performing data filtering on the image data and the radar data to remove invalid data;

Space synchronization is performed on the image data and the radar data after data filtering.

In an implementation manner of the present application, the determining the tracking target specifically includes:

Based on the preset constant velocity model, the future state of the target corresponding to the image data and radar data is predicted. The prediction formula is as follows:

x _k+1 =Ax _k +v

v是模型的过程噪声；Among them, x _k+1 represents the state of the target at time k+1;

v is the process noise of the model;

Plan the error covariance and calculate the Kalman filter gain;

The optimal value of the state quantity of the update target is measured by the following formula;

x _k ＝x _k (z _k -Hx _k )

Among them, z _k represents the measured value of the target at time k, H is the observation matrix; x _k is the state quantity of the target at time k;

The state quantity of the target at time k is matched with the measured value to determine the tracking target.

In an implementation manner of the present application, the associating the tracking target specifically includes:

Based on the global nearest neighbor algorithm, the radar data is associated with the image data, and the formula is as follows:

Among them, ρ represents the similarity between radar data and image data; x _ra represents the longitudinal distance of radar data; y _ra represents the lateral distance of radar data; x _ca represents the longitudinal distance of image data; y _ca represents the lateral distance of image data.

In one implementation of the present application, the tracking target is fused, specifically including:

The associated radar data and image data are fused using a weighted algorithm, the formula is as follows:

Among them, X _{F_obj} represents the fused target state quantity, V _ra represents the target state quantity of the associated radar data; V _ca represents the target state quantity of the correlated image data; P _ca represents the error generated by the image data during target tracking Covariance; P _ra represents the error covariance generated by radar data during target tracking.

In an implementation manner of the present application, the screening of the tracking target according to the driving path of the mine vehicle, and determining the tracking target with the closest distance as the dangerous target specifically includes:

generating a travel path of the mine vehicle based on the current driving state of the mine vehicle;

judging whether multiple tracking targets are located on the driving path, and removing tracking targets located outside the driving path;

The distance between multiple tracking targets located on the driving path and the mine vehicle is calculated, and the tracking target with the closest distance is determined as a dangerous target.

In an implementation manner of the present application, the controlling the early warning or braking of the mine vehicle according to the early warning time and the braking time specifically includes:

Based on the preset collision time algorithm, determine the warning threshold time, braking threshold time and collision time;

Judging the size between the collision time and the warning threshold time and the braking threshold time;

When the collision time is greater than the warning threshold time, the mine vehicle will not give warning and brake;

When the collision time is less than the warning threshold time and greater than the braking threshold time, the mine vehicle only gives a warning and does not brake;

When the collision time is less than the braking threshold time, the mine vehicle is controlled to give an early warning and brake.

In an implementation manner of the present application, the method further includes:

receiving ultrasonic data, determining a distance between an obstacle and the mine vehicle based on the ultrasonic data;

When the distance is less than a preset distance threshold, the warning and braking of the mine vehicle are controlled.

The embodiment of the present application also provides a mine vehicle anti-collision equipment, the equipment includes:

at least one processor; and,

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:

Obtain data measured by multiple sensors;

performing data preprocessing on data measured by the plurality of sensors;

Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target;

Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target;

Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

The embodiment of the present application also provides a non-volatile computer storage medium for anti-collision of mine vehicles, which stores computer-executable instructions, and the computer-executable instructions are configured to: acquire data measured by multiple sensors;

performing data preprocessing on data measured by the plurality of sensors;

Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target;

Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target;

Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

The mine vehicle anti-collision method, equipment and storage medium provided by the embodiment of the present application can determine whether there is an obstacle on the driving track of the mine vehicle by performing data correlation and fusion on multiple measurement targets and tracking them, and timely Carry out early warning or braking to prevent vehicle collisions and reduce accidents in underground mines. By spatially synchronizing the received data, more accurate data can be obtained. Based on various algorithms to process data, the system can obtain more accurate obstacle tracking information when tracking obstacle targets.

Description of drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The schematic embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation to the application. In the attached picture:

Fig. 1 is a kind of flow chart of mine vehicle anti-collision method provided by the embodiment of the present application;

Fig. 2 is a schematic diagram of the installation of the radar sensor and the camera provided by the embodiment of the present application;

Fig. 3 is a schematic diagram of the radar coordinate system and the vehicle body coordinate system provided by the embodiment of the present application;

Fig. 4 is a schematic diagram of the camera coordinate system and the vehicle body coordinate system provided by the embodiment of the present application;

Fig. 5 is a schematic diagram of an anti-collision device for a mine vehicle provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

The production environment of underground mines is harsh, and mine trucks are mainly used to carry out transportation tasks. Mine transportation is related to safety production. According to statistics, about 1/4 of mine safety accidents occur in the transportation link. Therefore, safe transportation has become an increasingly important part of current mine production.

Generally speaking, mine vehicles are equipped with corresponding anti-collision systems or equipment to avoid collisions between vehicles and obstacles in an underground dark environment. Some strategies use the signal strength of the wireless network transmitter to judge the distance of the opposite mine car, and implement the corresponding anti-collision strategy. There are also combinations of lora wireless communication technology, RFID technology and laser radar, or visual technology to identify whether there are obstacles ahead. However, these solutions more or less have problems such as high cost, low precision, false triggering, and inaccurate obstacle recognition.

The embodiment of the present application provides a mine vehicle anti-collision method, equipment and storage medium to solve the technical problems of low accuracy and inaccurate obstacle identification in existing mine environment vehicle anti-collision schemes.

The technical solutions proposed in the embodiments of the present application will be described in detail below with reference to the accompanying drawings.

Fig. 1 is a flowchart of a mine vehicle anti-collision method provided by an embodiment of the present application. As shown in Figure 1, the method mainly includes the following steps:

Step 101, acquiring data measured by multiple sensors.

In the embodiment of the present application, the anti-collision prediction of the mine vehicle is mainly obtained by analyzing and calculating the data based on the data measured by the sensor. Specifically, multiple millimeter-wave radars and ultrasonic radars are installed on mine vehicles to obtain radar data and ultrasonic data respectively. At the same time, ADAS cameras are installed on the mine vehicles to obtain image data in the mine environment. In addition, the mine vehicle is also equipped with a camera to obtain real-time video data captured in the mine environment.

Step 102, performing data preprocessing on data measured by multiple sensors.

In the embodiment of the present application, the system receives the image data captured by the camera and the radar data detected by the millimeter-wave radar, and uses these data as target data. Then target data filtering is performed on these data to remove empty target and invalid target data.

Further, after filtering target data such as image data and radar data, it is necessary to spatially synchronize the filtered image data and radar data. Because when the engineer installs the sensor, the coordinates of the sensor will not completely coincide with the coordinates of the car body. Therefore, it is necessary to use a level measuring instrument and a ruler to measure the deflection angle and displacement of the sensor coordinate system relative to the vehicle body coordinate system, and then convert the target data measured by the sensor to the vehicle body coordinate system through coordinate rotation.

The installation position of the sensor and ASDS camera on the car body is shown in Figure 2. It can be seen that the coordinates of the sensor do not completely coincide with the coordinates of the car body, so the radar coordinates are rotated relative to the car body coordinate system during installation. Displacement, radar coordinate system and car body coordinate system are shown in Fig. 3. Therefore, it is necessary to rotate and translate the radar target data to synchronize the radar target data to the car body coordinate system. The calculation formula is as follows:

x=y'sinθ+x'cosθ+Δx

y=y'cosθ-x'sinθ+Δy

Similarly, the ASDS camera has been rotated and displaced relative to the vehicle body coordinate system during installation, so the target data of the camera needs to be rotated and translated to synchronize the target data of the camera to the vehicle body coordinate system. The ASDS camera coordinate system is as follows: As shown in Figure 4, the calculation formula for camera coordinate space synchronization is as follows:

x=x'cosθ+y'sinθ

y=y'cosθ-x'sinθ

Step 103: Determine the tracking target based on the preprocessed data, and perform association and fusion on the tracking target.

In the embodiment of this application, it is considered that the motion model of the object obeys the Gaussian distribution, and then the Kalman filter algorithm is used to predict the state of the target, and then by comparing with the observation model, the motion state of the target is updated according to the error.

Specifically, based on the preset constant velocity model, the future state of the target corresponding to the image data and radar data is predicted, and the prediction formula is as follows:

x _k+1 =Ax _k +v

v是模型的过程噪声。Among them, x _k+1 represents the state of the target at time k+1;

v is the process noise of the model.

Further, the planning error covariance value, the formula is as follows:

P _k+1 =AP _k A ^T +Q,

Among them, P _k+1 represents the error covariance at time k+1, and Q represents the covariance matrix of the process noise. Further, calculate the Kalman filter gain, the formula is as follows:

K _k ＝P _k H ^T (HP _k H ^T +R)

Among them, K _k in the formula represents the Kalman filter gain at time k; H represents the observation matrix; R represents the measurement noise covariance matrix.

Update the best estimate by measurement, the formula is:

x _k ＝x _k (z _k -Hx _k )

Among them, _zk in the formula represents the measured value of the target at time k, H is the observation matrix; x _k is the state quantity of the target at time k.

Then, update the covariance error, the formula is as follows:

P _k ＝(IK _k H)P _k

Among them, I represents the identity matrix.

Then, P _k and x _k are calculated cyclically, and the state quantity of the target at time k is matched with the measured value to determine the tracking target.

In the embodiment of the present application, in the embodiment of the present application, the radar data is associated with the image data according to the global nearest neighbor algorithm, and the formula is as follows:

Among them, ρ represents the similarity between radar data and image data; x _ra represents the longitudinal distance of radar data; y _ra represents the lateral distance of radar data; x _ca represents the longitudinal distance of image data; y _ca represents the lateral distance of image data.

Further, the associated radar data and image data are fused using a weighted algorithm, the formula is as follows:

Among them, X _{F_obj} represents the fused target state quantity, V _ra represents the target state quantity of the associated radar data; V _ca represents the target state quantity of the correlated image data; P _ca represents the error generated by the image data during target tracking Covariance; P _ra represents the error covariance generated by radar data during target tracking.

In the embodiment of the present application, the aforementioned radar targets and camera targets associated together are fused respectively; the algorithm adopted for the fusion is a weighting algorithm, and the weighting formula is as follows:

Among them, X _{F_obj} represents the fused target state quantity, V _ra represents the target state quantity of the associated radar data; V _ca represents the target state quantity of the correlated image data; P _ca represents the error generated by the image data during target tracking Covariance; P _ra represents the error covariance generated by radar data during target tracking.

Step 104 , screening the tracking targets, and determining the tracking target with the closest distance as a dangerous target.

In the embodiment of the present application, based on the current driving state of the mine vehicle, the driving path of the mine vehicle is generated, and it is judged whether multiple tracking targets are located on the driving path, and the tracking objects located outside the driving path Target elimination, calculating the distance between multiple tracking targets on the driving path and the mine vehicle, and determining the closest tracking target as a dangerous target.

Step 105. Control the mine vehicle for early warning or braking according to the early warning time and the braking time.

In the embodiment of the present application, the anti-collision system includes a forward collision decision module, which determines the warning threshold time TTC _W , the braking threshold time TTC _b and the collision time TTC according to the preset collision time algorithm.

Judging the time between the collision time TTC and the warning threshold time TTC _W and the braking threshold time TTC _b .

When the collision time is greater than the warning threshold time, it means that the target ahead is not dangerous, so the mine vehicle will not give warning and brake.

When the collision time is less than the warning threshold time and greater than the braking threshold time, the braking threshold has not been reached at this time, so the mine vehicle only warns and does not brake.

When the collision time is less than the braking threshold time, danger is very likely to occur at this time, so it is necessary to control the mine vehicle to warn and brake.

In the embodiment of the present application, a backward collision decision-making module is also designed, and a backward ultrasonic radar is installed on the mine vehicle. Then set the distance threshold. When the distance between the mine vehicle and the target obstacle measured by the ultrasonic data is less than the preset distance threshold, the rear collision module decides to perform early warning or braking.

In addition, the method proposed in the embodiment of the present application also includes a decision-making arbitration module. According to the current vehicle speed, gear, the input of the forward collision decision-making module and the input of the rear collision decision-making module, it is judged whether it is early warning or braking. The decision-making arbitration module mainly realizes the decision-making arbitration through the following process:

When the vehicle speed (V) is equal to 0 or the gear (G) is in neutral (GN), the car will not issue an alarm and will not brake;

When the vehicle speed is greater than 0 and there is a gear, enter the following judgment:

The gear position is a forward gear (GD), which means that the car is moving forward, and the decision-making arbitration module outputs the result of the forward collision decision-making module;

The gear position is the reverse gear (GR), which means that the car is running backwards. At this time, the decision-making arbitration module outputs the result of the backward collision decision-making module.

The mine vehicle anti-collision method, equipment and storage medium provided by the embodiment of the present application can determine whether there is an obstacle on the driving track of the mine vehicle by performing data correlation and fusion on multiple measurement targets and tracking them, and timely Carry out early warning or braking to prevent vehicle collisions and reduce accidents in underground mines. By spatially synchronizing the received data, more accurate data can be obtained. Based on various algorithms to process data, the system can obtain more accurate obstacle tracking information when tracking obstacle targets.

The above is a mine vehicle anti-collision method provided by the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides a mine vehicle anti-collision device. Figure 5 is a schematic diagram of a device provided by the embodiment of the present application , as shown in FIG. 5 , the device mainly includes: at least one processor 501; and a memory 502 communicatively connected to the at least one processor; wherein, the memory 502 stores instructions executable by the at least one processor 501, and the instructions are At least one processor 501 executes, so that at least one processor 501 can complete: acquiring data measured by multiple sensors;

performing data preprocessing on data measured by the plurality of sensors;

Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target;

Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target;

Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

In addition, the embodiment of the present application also provides a non-volatile computer storage medium for anti-collision of mine vehicles, which stores computer-executable instructions, and the computer-executable instructions are set to: acquire data measured by multiple sensors ;

performing data preprocessing on data measured by the plurality of sensors;

Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target;

Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target;

Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

Each embodiment in the present application is described in a progressive manner, the same and similar parts of each embodiment can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, as for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and for relevant parts, please refer to part of the description of the method embodiment.

It should also be noted that the term "comprises", "comprises" or any other variation thereof is intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus comprising a set of elements includes not only those elements, but also includes Other elements not expressly listed, or elements inherent in the process, method, commodity, or apparatus are also included. Without further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising said element.

The above descriptions are only examples of the present application, and are not intended to limit the present application. For those skilled in the art, various modifications and changes may occur in this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims (10)

1. A mine vehicle anti-collision method is characterized in that, the method comprises: Obtain data measured by multiple sensors; performing data preprocessing on data measured by the plurality of sensors; Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target; Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target; Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time. 2. A kind of anti-collision method for mine vehicles according to claim 1, wherein said data preprocessing is carried out to the data measured by said plurality of sensors, specifically comprising: Obtain the image data captured by the camera and the radar data detected by the radar; performing data filtering on the image data and the radar data to remove invalid data; Space synchronization is performed on the image data and the radar data after data filtering. 3. A kind of anti-collision method for mine vehicles according to claim 1, wherein said determining the tracking target specifically comprises: Based on the preset constant velocity model, the future state of the target corresponding to the image data and radar data is predicted. The prediction formula is as follows: x _k+1 =Ax _k +v Among them, x _k+1 represents the state of the target at time k+1;

v is the process noise of the model; Plan the error covariance and calculate the Kalman filter gain; The optimal value of the state quantity of the update target is measured by the following formula; x _k ＝x _k (z _k -Hx _k ) Among them, z _k represents the measured value of the target at time k, H is the observation matrix; x _k is the state quantity of the target at time k; The state quantity of the target at time k is matched with the measured value to determine the tracking target. 4. A mine vehicle anti-collision method according to claim 1, wherein said associating said tracking target specifically comprises: Based on the global nearest neighbor algorithm, the radar data is associated with the image data, and the formula is as follows:

Among them, ρ represents the similarity between radar data and image data; x _ra represents the longitudinal distance of radar data; y _ra represents the lateral distance of radar data; x _ca represents the longitudinal distance of image data; y _ca represents the lateral distance of image data. 5. A kind of anti-collision method for mine vehicles according to claim 1, characterized in that merging the tracking target specifically includes: The associated radar data and image data are fused using a weighted algorithm, the formula is as follows:

Among them, X _{F_obj} represents the fused target state quantity, V _ra represents the target state quantity of the associated radar data; V _ca represents the target state quantity of the correlated image data; P _ca represents the error generated by the image data during target tracking Covariance; P _ra represents the error covariance generated by radar data during target tracking. 6. A kind of anti-collision method for mine vehicles according to claim 1, characterized in that, the said tracking target is screened according to the driving path of said mine vehicle, and the tracking target with the closest distance is determined as a dangerous target, specifically comprising: generating a travel path of the mine vehicle based on the current driving state of the mine vehicle; judging whether multiple tracking targets are located on the driving path, and removing tracking targets located outside the driving path; The distance between multiple tracking targets located on the driving path and the mine vehicle is calculated, and the tracking target with the closest distance is determined as a dangerous target. 7. A mine vehicle anti-collision method according to claim 1, characterized in that, said controlling said mine vehicle early warning or braking according to said early warning time and braking time specifically comprises: Based on the preset collision time algorithm, determine the warning threshold time, braking threshold time and collision time; Judging the size between the collision time and the warning threshold time and the braking threshold time; When the collision time is greater than the warning threshold time, the mine vehicle will not give warning and brake; When the collision time is less than the warning threshold time and greater than the braking threshold time, the mine vehicle only gives a warning and does not brake; When the collision time is less than the braking threshold time, the mine vehicle is controlled to give an early warning and brake. 8. A kind of mine vehicle anti-collision method according to claim 1, is characterized in that, described method also comprises: receiving ultrasonic data, determining a distance between an obstacle and the mine vehicle based on the ultrasonic data; When the distance is less than a preset distance threshold, the warning and braking of the mine vehicle are controlled. 9. A mine vehicle anti-collision equipment, characterized in that the equipment comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to: Obtain data measured by multiple sensors; performing data preprocessing on data measured by the plurality of sensors; Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target; Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target; Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time. 10. A non-volatile computer storage medium for anti-collision of mine vehicles, which stores computer-executable instructions, wherein the computer-executable instructions are set to: acquire data measured by a plurality of sensors; performing data preprocessing on data measured by the plurality of sensors; Determine the tracking target based on the preprocessed data, and associate and fuse the tracking target; Screening the tracking target according to the driving path of the mine vehicle, and determining the closest tracking target as a dangerous target; Calculating the warning time and braking time of the collision between the dangerous target and the mine vehicle, and controlling the warning or braking of the mine vehicle according to the warning time and braking time.

Images