WO2022041921A1

WO2022041921A1 - Guiding control method and device, security check vehicle, medium, and program product

Info

Publication number: WO2022041921A1
Application number: PCT/CN2021/099046
Authority: WO
Inventors: 袁新; 李建; 许艳伟; 王永明; 孙尚民; 宗春光; 胡煜
Original assignee: 同方威视技术股份有限公司
Priority date: 2020-08-25
Filing date: 2021-06-09
Publication date: 2022-03-03
Also published as: GB2611650A; GB202218800D0; GB2611650B; PL443285A1; CN114089733B; CN116880509A; CN114089733A

Abstract

A guiding control method, a guiding control device (700), a security check vehicle (110), a medium, and a program product. The guiding control method is applied to the security check vehicle (110). The security check vehicle (110) comprises a vehicle body (111), a security check door (113), and at least one laser radar (112). The guiding control method comprises: obtaining environmental point cloud data of the security check vehicle (110) using the at least one laser radar (112) (S210); on the basis of the environmental point cloud data, determining position information of a plurality of reference objects located in the external environment of the security check vehicle (110) (S220); determining a guiding path on the basis of the position information of the plurality of reference objects (S230); and performing guiding control on the vehicle body (111) on the basis of the guiding path (S240). When the security check vehicle (110) is in a security check state, the vehicle body (111) subjected to the guiding control drives the security check door (113) to move with respect to an object to be checked (120) located in the external environment, such that the object to be checked (120) passes through the security check door (113).

Description

Guidance control method, device, security vehicle, medium and program product

technical field

Embodiments of the present disclosure relate to the field of security inspection, and in particular, to a guidance control method, device, security inspection vehicle, medium, and program product.

Background technique

When a security inspection vehicle performs a security inspection on an object to be inspected, the vehicle body needs to be guided and controlled so that the object to be inspected relatively passes through the security inspection door of the security inspection vehicle, thereby realizing the security inspection. In one processing method, most of the automatic guidance systems of security inspection vehicles use single-line LiDAR for environmental perception. Due to the limited detection capability of single-line lidar, the detection information obtained by single-line lidar only supports linear guidance control for security inspection vehicles. In addition, because the single-line lidar has a large detection blind spot, the security inspection vehicle cannot effectively avoid obstacles located in the detection blind spot.

SUMMARY OF THE INVENTION

According to the embodiments of the present disclosure, a guidance control method, device, security inspection vehicle, medium and program product are provided.

In one aspect of the present disclosure, a guidance control method is proposed, which is applied to a security inspection vehicle. The security inspection vehicle includes a vehicle body, a security inspection door, and at least one multi-line laser radar. The method includes: using the above at least one multi-line laser radar to obtain environmental point cloud data of the security inspection vehicle; based on the environmental point cloud data, determining the position information of multiple reference objects located in the external environment of the security inspection vehicle; then, based on the plurality of benchmarks The position information of the object is used to determine a guide path; then, based on the guide path, the vehicle body is guided and controlled. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.

According to an embodiment of the present disclosure, the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars. The above-mentioned use of at least one multi-line laser radar to obtain the environmental point cloud data of the security inspection vehicle includes: at any moment, obtaining respective point cloud data from a plurality of multi-line laser radars. And, the point cloud data of each multi-line lidar in the multiple multi-line lidars are converted from the coordinate system of each multi-line lidar to the reference coordinate system to form the environmental point cloud data at any moment.

According to an embodiment of the present disclosure, the method further includes: before converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system, based on each The positional relationship of each multi-line laser radar relative to the vehicle body is determined, and the rotational transformation relationship and translation transformation relationship between the coordinate system of each multi-line laser radar and the reference coordinate system are determined. The above-mentioned conversion of the point cloud data of each multi-line laser radar in the plurality of multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system includes: The point cloud data of the line lidar is transformed from the coordinate system of each multi-line lidar to the reference coordinate system.

According to an embodiment of the present disclosure, the above method further includes: before converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system, converting each A multi-line lidar obtains detection data for a predetermined target, and uses a random sampling consensus algorithm to extract the same-name vector representation and the same-name point representation for characterizing the predetermined target from the detection data. Then, based on the Rodrigues rotation equation, the respective vector representations of the same name of multiple multi-line lidars are processed to obtain the relationship between the coordinate system of any one of the multiple multi-line lidars and the reference coordinate system. Rotation transformation relationship. In addition, based on the point representation of the same name of each of the plurality of multi-line lidars, the translational transformation relationship between the coordinate system of any one of the plurality of multi-line lidars and the reference coordinate system is determined. On this basis, converting the point cloud data of each multi-line lidar in the multiple multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system includes: The rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line lidar and the reference coordinate system, and the point cloud data of multiple multi-line lidars are converted from the respective coordinate systems of multiple multi-line lidars to reference coordinates. Tie.

According to an embodiment of the present disclosure, the above-mentioned determining the position information of multiple reference objects located in the external environment of the security inspection vehicle based on the environmental point cloud data includes: extracting first feature point cloud data from the environmental point cloud data; The cloud data is clustered to obtain multiple clustering results, and the multiple clustering results are respectively used as sub-point cloud data of multiple reference objects. Then, based on the sub-point cloud data of each of the plurality of reference objects, position information of each of the plurality of reference objects is determined.

According to an embodiment of the present disclosure, the above-mentioned determining the guide path based on the position information of the plurality of reference objects includes: performing curve fitting based on the respective position information of the plurality of reference objects to obtain a fitted lane line. And, based on the fitting lane line, a guide line is determined so that the distance between any point on the guide line and the fitting lane line is the radius of a predetermined circle.

According to the embodiment of the present disclosure, the radius of the predetermined circle is larger than the radius of the circumscribed circle of the security inspection vehicle.

According to an embodiment of the present disclosure, the above method further includes: extracting second feature point cloud data from environmental point cloud data at any moment; using a predetermined matching algorithm to compare the second feature point cloud data at any moment with the moment match between the second feature point cloud data at the previous moment to determine the rotation matrix and translation matrix. Then, based on the rotation matrix and the translation matrix, the attitude change information of the security inspection vehicle at any moment is determined.

According to an embodiment of the present disclosure, the above-mentioned guiding control of the vehicle body based on the guiding path includes: determining the magnitude and direction of the traction force for the security inspection vehicle according to the guiding path and attitude change information. The body is then guided and controlled based on the traction force.

According to an embodiment of the present disclosure, the above method further includes: determining the contour information of the vehicle body and the contour information of at least one obstacle based on the environmental point cloud data; and then, for each obstacle in the at least one obstacle, based on the The contour information and the contour information of the obstacle determine the distance between the vehicle body and the obstacle, and determine the magnitude and direction of the repulsive force based on the distance between the two. According to the guidance path and attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle. Next, based on the traction force and the repulsive force with respect to the at least one obstacle, a comprehensive traction force is determined, and the vehicle body is guided and controlled based on the comprehensive traction force.

According to an embodiment of the present disclosure, the above-mentioned determining the comprehensive traction force based on the traction force and the repulsive force against the at least one obstacle includes: using a preset first weight and a second weight to perform a calculation on the traction force and the repulsive force against the at least one obstacle. Weighted summation to get combined traction.

In another aspect of the present disclosure, a guidance control device is proposed, which is applied to a security inspection vehicle. The security inspection vehicle includes a vehicle body, a security inspection door, and at least one multi-line laser radar. The guidance control device includes: an acquisition module, a first determination module, a second determination module and a control module. The acquisition module is used for acquiring the environmental point cloud data of the security inspection vehicle by using the above at least one multi-line laser radar. The first determining module is configured to determine, based on the environmental point cloud data, position information of multiple reference objects located in the external environment of the security inspection vehicle. The second determining module is configured to determine the guiding path based on the position information of the plurality of reference objects. The control module is used for guiding and controlling the vehicle body based on the guiding path. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.

In another aspect of the present disclosure, a security inspection vehicle is proposed, comprising: a vehicle body, a security inspection door, at least one multi-line laser radar, a memory, and at least one processor. Memory is used to store instructions. At least one processor executes instructions stored in memory to implement a method as described in any of the above embodiments.

According to the embodiment of the present disclosure, when the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars, at least two multi-line lidars in the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range of the two multi-line lidars covers 360° around the vehicle body.

According to an embodiment of the present disclosure, at least one of the multiple multi-line laser radars other than the at least two multi-line laser radars is located inside the security gate.

In another aspect of the present disclosure, a computer-readable storage medium is provided with computer instructions stored thereon, the computer instructions implementing the method described in any of the above embodiments when executed by a processor.

In another aspect of the present disclosure, a computer program product is proposed, comprising executable instructions that, when executed by a processor, implement the method as described in any of the above embodiments.

According to the guidance control solution of the embodiment of the present disclosure, for a security inspection vehicle in a security inspection state, at least one multi-line laser radar is used to collect environmental point cloud data, and path planning and guidance control are performed based on the environmental point cloud data, so that the inspected Objects relatively pass through a security gate in a security vehicle. Because multi-line lidar has a relatively larger detection range and smaller detection blind area, it has stronger ability to identify surrounding environmental information and anti-interference, and can obtain more accurate and comprehensive environmental point cloud data. The environmental point cloud data can support the guidance control of various types of paths for security inspection vehicles in various places, improve the environmental adaptability and flexibility of the guidance control of security inspection vehicles, and further improve the scope of application of security inspection vehicles for security inspections .

Description of drawings

For a better understanding of the embodiments of the present disclosure, the embodiments of the present disclosure will be described in detail according to the following drawings:

FIG. 1 schematically shows an application scenario of the steering control method and apparatus according to an embodiment of the present disclosure;

FIG. 2 schematically shows a flowchart of a steering control method according to an embodiment of the present disclosure;

FIG. 3 schematically shows an example diagram of environment perception by a security inspection vehicle using a multi-line lidar according to an embodiment of the present disclosure;

FIG. 4 schematically shows an example top view of a security inspection vehicle according to an embodiment of the present disclosure;

5A-5B schematically illustrate example top views of a security inspection vehicle according to another embodiment of the present disclosure;

6A-6C schematically illustrate exemplary diagrams of a process of determining a guide path according to an embodiment of the present disclosure;

FIG. 7 schematically shows a block diagram of a steering control apparatus according to an embodiment of the present disclosure; and

FIG. 8 schematically shows an example structural diagram of a security inspection vehicle suitable for implementing the above-described method according to an embodiment of the present disclosure.

detailed description

Specific embodiments of the present disclosure will be described in detail below. It should be noted that the embodiments described herein are only used for illustration and are not used to limit the embodiments of the present disclosure. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It will be apparent, however, to one of ordinary skill in the art that these specific details need not be employed to practice embodiments of the present disclosure. In other instances, well-known structures, materials, or methods have not been described in detail in order to avoid obscuring the disclosed embodiments.

Throughout this specification, references to "one embodiment," "an embodiment," "an example," or "an example" mean that a particular feature, structure, or characteristic described in connection with the embodiment or example is included in the present disclosure in at least one embodiment. Thus, appearances of the phrases "in one embodiment," "in an embodiment," "one example," or "an example" in various places throughout this specification are not necessarily all referring to the same embodiment or example. Furthermore, the particular features, structures or characteristics may be combined in any suitable combination and/or subcombination in one or more embodiments or examples. Furthermore, those of ordinary skill in the art should understand that as used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

Embodiments of the present disclosure provide a guidance control method and device applied to a security inspection vehicle, a security inspection vehicle, a medium, and a program product. Wherein, the security inspection vehicle may include a vehicle body, a security inspection door and at least one multi-line laser radar. The steering control method may include an acquisition process, a first determination process, a second determination process, and a control process. In the acquisition process, at least one multi-line laser radar of the security inspection vehicle is used to acquire environmental point cloud data of the security inspection vehicle. Then, a first determination process is performed based on the acquired environment point cloud data to determine the position information of a plurality of reference objects located in the external environment of the security inspection vehicle. A second determination process is then performed based on the position information of the plurality of reference objects to determine the guide path. Next, the control process is performed based on the guidance path, that is, the guidance control is performed on the body of the security inspection vehicle. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.

FIG. 1 schematically shows an application scenario of a steering control method and apparatus according to an embodiment of the present disclosure. It should be noted that FIG. 1 is only an example of a scenario to which the embodiments of the present disclosure can be applied, so as to help those skilled in the art to understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be applied to other devices , system, environment or scene.

As shown in FIG. 1 , a scene in which the security inspection vehicle 110 performs security inspection on the inspected object 120 is exemplarily shown. It should be noted that this example and the following are described with reference to the vehicle body coordinate system o-xyz, where the x and y directions are parallel to the horizontal plane, the x and y directions are perpendicular to each other, and the z direction is perpendicular to the horizontal plane. In this example, the security inspection vehicle 110 may include a vehicle body 111 , at least one lidar 112 and a security inspection door 113 . At least one lidar 112 is used to acquire environmental information of the security inspection vehicle 110 when the security inspection vehicle 110 is moving or stationary. Based on the environmental information, the security inspection vehicle 110 can guide and control the movement of the vehicle body. When the security inspection vehicle 110 is in the security inspection state, the vehicle body 111 is fixedly connected to the security inspection door 113 , and the movement of the vehicle body 111 can drive the security inspection door 113 to move relative to the inspected object 120 , so that the inspected object 120 passes through the security inspection door 113 . For example, the security gate 113 acts as an X-ray detection device, and performs X-ray scanning on the object under inspection 120 passing through it, so as to obtain an X-ray perspective view of the object under inspection 120 . Exemplarily, the security inspection vehicle 110 may perform security inspection on inspected objects such as containers, large vehicles, and small vehicles in places such as customs, ports, border crossings, and the like. Through the X-ray projection scanning image, it is determined whether the material, volume, quantity, etc. of the goods inside the inspected object are consistent with the checklist, and whether the inspected object has dangerous goods and prohibited items, etc.

In the example shown in FIG. 1 , when the security inspection vehicle is in the security inspection state, the security inspection door is located outside one side of the vehicle body. In other examples, the security inspection door may also be located inside the vehicle body. The inspected object can be moving or stationary.

It should be noted that, the guidance control method provided by the embodiment of the present disclosure may be executed by the above-mentioned security inspection vehicle 110 . Correspondingly, the guidance control device provided by the embodiment of the present disclosure may be provided in the security inspection vehicle 110 . Alternatively, the guidance control method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the security inspection vehicle 110 and can communicate with the security inspection vehicle 110 . Correspondingly, the guidance control device provided by the embodiment of the present disclosure may also be provided in a server or a server cluster that is different from the security inspection vehicle 110 and can communicate with the security inspection vehicle 110 .

Based on the above application scenarios, when a security inspection vehicle conducts a safety inspection on the object to be inspected, it is necessary to conduct guidance control on the vehicle body so that the object to be inspected relatively passes through the security inspection door of the security inspection vehicle, so as to realize the safety inspection. In one processing method, most of the automatic guidance control systems of security inspection vehicles use single-line LiDAR for environmental perception. Due to the limited detection capability of single-line lidar, only one detection scan line can be emitted, and the maximum horizontal scanning angle can only cover 190°. The environment recognition ability is weak, and the requirements for the flatness of the workplace and the arrangement of the reference objects are relatively strict. Poor adaptability. The detection information obtained by the single-line lidar only supports the straight-line guidance control for the security inspection vehicle, and cannot control the security inspection vehicle to make turns and other movements. In addition, because the single-line lidar has a large detection blind spot, the security inspection vehicle cannot effectively avoid obstacles located in the detection blind spot.

According to the embodiments of the present disclosure, a steering control method is provided to further improve the environmental adaptability and flexibility of the steering control. The method is exemplified below by means of a legend. It should be noted that the sequence numbers of the respective operations in the following methods are only used as representations of the operations for the convenience of description, and should not be regarded as representing the execution order of the respective operations. The methods need not be performed in the exact order shown unless explicitly stated.

FIG. 2 schematically shows a flowchart of a steering control method according to an embodiment of the present disclosure. The guidance control method can be applied to a security inspection vehicle as shown in FIG. 1 , and the security inspection vehicle may include a vehicle body, a security inspection door and at least one multi-line laser radar.

As shown in FIG. 2, the guidance control method may include the following operations S210-S240.

In operation S210, the environment point cloud data of the security inspection vehicle is acquired by using the above at least one multi-line lidar.

Lidar is one of the most important sensors for environmental perception of security inspection vehicles. Different installation and use methods have different effects on the results of environmental perception. According to the embodiments of the present disclosure, the automatic guidance system of the security inspection vehicle is improved, and at least one multi-line laser radar is used instead of the single-line laser radar for environmental perception. The environmental perception may include the perception of the security inspection vehicle's own posture information and contour information, and the perception of the external environment information of the security inspection vehicle. Compared with single-line lidar, multi-line lidar has a larger detection range and smaller detection blind area, which can achieve more accurate environmental perception. Multi-line lidars include, for example, 4-line, 16-line, 32-line, and 64-line lidars, etc. The 16-line lidar is used as an example for illustration below.

FIG. 3 schematically shows an example diagram of environment perception by a security inspection vehicle using a multi-line lidar according to an embodiment of the present disclosure. As shown in FIG. 3 , the security inspection vehicle 310 includes a vehicle body 311 and at least one multi-line laser radar 312, and the multi-line laser radar 312 is, for example, a 16-line laser radar. The horizontal scanning range of the 16-line lidar can reach 360°, and the vertical scanning line can reach 16, which are evenly distributed at 2° angular intervals, and the scanning angle range is -15° to +15°. Compared with single-line LiDAR, it has stronger recognition ability and anti-interference ability for surrounding environment information, and can obtain stable information of reference objects and obstacles in the environment. In the example shown in FIG. 3 , the reference object 320 exists in the external environment of the security inspection vehicle 310 . The environmental point cloud data acquired by the multi-line lidar 312 can reflect the three-dimensional information of the reference object 320 .

Continuing to refer to FIG. 2 , in operation S220, based on the environmental point cloud data, position information of a plurality of reference objects located in the external environment of the security inspection vehicle is determined.

According to the embodiments of the present disclosure, when the guidance control of the security inspection vehicle is performed, a plurality of reference objects need to be preset in the guidance control field, and the guidance path of the guidance control is determined by using the plurality of reference objects as a reference. This operation S220 is to determine the position information of a plurality of preset reference objects based on the environmental point cloud data acquired by the multi-line lidar.

In operation S230, a guide path is determined based on the position information of the plurality of reference objects.

In operation S240, guidance control is performed on the vehicle body based on the guidance path.

According to the embodiments of the present disclosure, when the security inspection vehicle is in the security inspection state, the vehicle body that has been guided and controlled drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door, so as to achieve the goal of targeting the inspected object. Check the object's security check. When the security inspection vehicle is in a non-security inspection state, the vehicle body can be controlled to move to a predetermined position, site transfer, etc., through the above-mentioned guidance control process. Exemplarily, during the guidance control process, the above-mentioned operations S210-S240 may be performed periodically, for example, operations S210-S240 are performed every predetermined time interval, so as to realize real-time guidance control for the security inspection vehicle.

Those skilled in the art can understand that, according to the guidance control method of the embodiment of the present disclosure, for a security inspection vehicle in a security inspection state, at least one multi-line laser radar is used to collect environmental point cloud data, and based on the environmental point cloud data, path planning and Guidance control so that the object to be inspected relatively passes through the security gate in the security vehicle. Because multi-line lidar has a relatively larger detection range and smaller detection blind area, it has stronger ability to identify surrounding environmental information and anti-interference, and can obtain more accurate and comprehensive environmental point cloud data. The environmental point cloud data can support the guidance control of various types of paths for security inspection vehicles in various places, improve the environmental adaptability and flexibility of the guidance control of security inspection vehicles, and further improve the scope of application of security inspection vehicles for security inspections .

According to the embodiment of the present disclosure, in order to obtain more comprehensive environmental point cloud data, the above-mentioned at least one multi-line laser radar may include multiple multi-line laser radars. When the above-mentioned at least one multi-line lidar includes a plurality of multi-line lidars, at least two multi-line lidars in the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range covers 360° around the vehicle body as much as possible. In some cases, the scanning range of the above at least two multi-line lidars cannot reach 360° due to the shape of the vehicle body or the occlusion of equipment.

FIG. 4 schematically shows an example top view of a security inspection vehicle according to an embodiment of the present disclosure, and exemplarily shows an arrangement of a multi-line laser radar on a security inspection vehicle. As shown in FIG. 4 , the security inspection vehicle 410 includes a vehicle body 411 and two multi-line laser radars 4121 to 4122 . Exemplarily, on the o-xy plane, two multi-line lidars 4121 to 4122 are arranged on the outer side of the vehicle body 411 and symmetrically arranged with respect to the center point o of the vehicle body 411 . Figure 4 shows that the scanning range of the two multi-line lidars 4121-4122 can cover 360° around the vehicle body 411, thereby further reducing the detection blind spot of the lidar in the security inspection vehicle or even realizing no detection blind spot.

In the following, the setting method of the multi-line lidar is exemplarily described with reference to two examples. 5A schematically shows an example top view of a security inspection vehicle according to another embodiment of the present disclosure, and FIG. 5B schematically shows an example top view of a security inspection vehicle according to another embodiment of the present disclosure.

As shown in FIG. 5A , the security inspection vehicle 510 includes a vehicle body 511 , a first multi-line lidar 5121 , a second multi-line lidar 5122 , a third multi-line lidar 5123 , and a security gate 513 . In this example, for example, the vehicle body 511 has an inverted U-shaped structure, and the security inspection door 513 is located inside the vehicle body 511 to form an inspection channel. During the security inspection process, the inspection channel is used for the object to be inspected to pass through actively or passively. The first multi-line laser radar 5121 and the second multi-line laser radar 5122 are located on the outside of the vehicle body 511 and are symmetrically arranged with respect to the center point of the vehicle body 511 , in the same manner as the two multi-line laser radars 4121 to 4122 in FIG. 4 . The first multi-line lidar 5121 and the second multi-line lidar 5122 can be used to obtain environmental point cloud data on the outside of the security inspection vehicle. Based on the environmental point cloud data, for example, the position information and contours of reference objects and obstacles in the external environment can be extracted. information, extract the contour information of the security inspection vehicle, calculate the posture information of the security inspection vehicle, etc. The third multi-line lidar 5123 can be arranged inside the security gate 513, and can be used to obtain the environmental point cloud data of the inspection channel. Based on the environmental point cloud data, relevant information in the inspection channel can be determined, for example, the object under inspection is in the inspection channel. attitude information, check whether there are other obstacles in the channel, etc.

As shown in FIG. 5B, the security inspection vehicle 510' includes a vehicle body 511', a first multi-line laser radar 5121', a second multi-line laser radar 5122', a third multi-line laser radar 5123', and a security inspection door 513'. In this example, the security inspection vehicle 510' deploys or retracts the security inspection door 513', for example, through a boom. When the security inspection door 513' is in a retracted state, the security inspection vehicle 510' is in a non-security inspection state, and operations such as site transfer can be performed. At this time, the first multi-line lidar 5121' is located at the head of the security inspection vehicle, the second multi-line lidar 5122' is located on the left side of the rear of the security inspection vehicle, and the third multi-line lidar 5123' is located on the right side of the rear of the security inspection vehicle. All three multi-line lidars can be used to obtain environmental point cloud data outside the security inspection vehicle to extract contour information, calculate attitude information, and avoid obstacles. When the security inspection door 513' is unfolded through the boom, an inspection channel is formed, and the security inspection vehicle 510' can start the security inspection operation. At this time, the third multi-line laser radar 5123' is in the inspection channel, and the third multi-line laser radar 5123' can be used to obtain the environmental point cloud data in the inspection channel, so that the environment point cloud data in the inspection channel can be determined based on the environmental point cloud data. Relevant information, such as the identification of intruders, the identification of the vehicle type to be inspected, and the measurement of the speed and position of the vehicle to be inspected. 5B shows the above-mentioned security inspection vehicle 510' in a security inspection state.

According to an embodiment of the present disclosure, the above-mentioned process of obtaining environmental point cloud data of a security inspection vehicle by using at least one multi-line laser radar may include: at any moment, obtaining respective point cloud data from multiple multi-line laser radars, and, The point cloud data of each multi-line lidar in the multiple multi-line lidars are converted from the coordinate system of each multi-line lidar to the reference coordinate system to form environmental point cloud data at any time. Among them, the point cloud data of each multi-line lidar refers to the point cloud data collected by each multi-line lidar, and the coordinate system of each multi-line lidar refers to the measurement coordinate system of each multi-line lidar. The purpose of this embodiment is to fuse the point cloud data collected by multiple multi-line laser radars into the same reference coordinate system, that is, to calibrate multiple multi-line laser radars, so as to form complete environmental point cloud data of the scene. The reference coordinate system can be selected according to the actual situation, for example, it can be the vehicle body coordinate system, or it can be the coordinate system of a certain multi-line laser radar itself, which is not limited here.

Exemplarily, in order to complete the above calibration process, the transformation relationship between the coordinate system of each multi-line laser radar itself and the reference coordinate system needs to be predetermined. For example, the guidance control method according to the embodiment of the present disclosure may further include: converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system Previously, based on the positional relationship of each multi-line lidar relative to the vehicle body, the rotation transformation relationship and translation transformation relationship between the coordinate system of each multi-line lidar and the reference coordinate system were determined. The above-mentioned conversion of the point cloud data of each multi-line laser radar in the plurality of multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system includes: The point cloud data of the line lidar is transformed from the coordinate system of each multi-line lidar to the reference coordinate system.

For example, the coordinate system of a multi-line lidar is S ₁ , the reference coordinate system is S ₂ , and there is a transformation relationship between the two coordinate systems of rotation (R) and translation (T). The point cloud data of the line lidar is transformed from the coordinate system S ₁ to the coordinate system S ₂ .

S ₂ =RS ₁ +T (1)

Among them, for example, R is a 3×3 rotation transformation matrix, and T is a 3×1 translation transformation matrix.

When the size of the security inspection vehicle and the installation position of each lidar are known, the transformation relationship between the coordinate systems can be directly obtained based on the above embodiment. In the case where the above transformation relationship cannot be obtained, the predetermined target can be calibrated by placing the calibration target in the common observation area of multiple lidars. The Rodrigues rotation equation is used to solve the above-mentioned rotation transformation matrix R, and the above-mentioned translation transformation matrix T is solved through the representation of the points with the same name in different coordinate systems.

Exemplarily, the guidance control method according to the embodiment of the present disclosure may further include: converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to a reference Before the coordinate system, the detection data for the predetermined target is obtained by each multi-line lidar, and the Random Sample Consensus (RANSAC) algorithm is used to extract the detection data from each multi-line lidar to characterize the predetermined target. The eponymous vector representation and the eponymous point representation of .

Then, based on the Rodrigues rotation equation, the respective vector representations of the same name of multiple multi-line lidars are processed to obtain the rotational transformation relationship between the coordinate systems of any two multi-line lidars in the multiple multi-line lidars . And, based on the point representations of the same names of the plurality of multi-line lidars, the translational transformation relationship between the coordinate systems of any two multi-line lidars in the plurality of multi-line lidars is determined.

For example, a predetermined target with three observable planes is placed in the measurement environment. Use multiple multi-line lidars to observe them respectively to obtain the detection data of each multi-line lidar for the predetermined target. For the detection data of each multi-line lidar, the following operations are performed: the sub-point cloud data of the predetermined target is extracted from the detection data. Then, the RANSAC algorithm is used to perform plane segmentation on the sub-point cloud data of the predetermined target to extract the respective plane parameters of the three observable planes for the predetermined target. Based on the plane parameters of the above three planes, the normal vectors of the three planes are used as the vector with the same name, and the intersection of the three planes is used as the point with the same name. It can be understood that, based on the detection data of each multi-line lidar, a set of identically named vector representations and identically named point representations for the coordinate system of the multi-line lidar can be obtained.

According to the Rodrigues rotation equation, the rotation matrix R between coordinate systems can be obtained only by two or more sets of vectors with the same name. On this basis, the translation matrix T can be determined by knowing the coordinate vector of at least one point with the same name. In this way, the solution of the rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line laser radar and the reference coordinate system is realized.

On this basis, the above process of converting the point cloud data of each of the multiple multi-line laser radars from the coordinate system of each multi-line laser radar to the reference coordinate system may include: The rotation transformation relationship and translation transformation relationship between the coordinate system of any multi-line lidar in the radar and the reference coordinate system, and the point cloud data of multiple multi-line lidars are converted from the respective coordinate systems of multiple multi-line lidars. to the base coordinate system.

Through the above embodiment, the point cloud data of multiple laser radars in the security inspection vehicle can be converted to the same reference coordinate system to complete the calibration. For each measurement moment, a frame of environmental point cloud data describing the complete environmental information around the vehicle body can be formed. to characterize the external environment information shown in Figure 4 above. Based on the first feature point cloud data in the environmental point cloud data, relevant information of the reference object in the external environment can be determined. If there is no other device near the installation location of the lidar to block the scan line, the vehicle body contour information of the security inspection vehicle can be extracted from the fused environmental point cloud data, and the information of obstacles in the external environment of the security inspection vehicle can also be extracted from the environmental point cloud data. profile information. According to the contour information of the vehicle body and the contour information of the obstacle, it can be used to judge the distance between the obstacle and the vehicle body during the obstacle avoidance process. In addition, for each frame of environmental point cloud data, the second characteristic point cloud data can be extracted according to the distribution characteristics of the environmental point cloud data. For the second feature point cloud data between adjacent frames, a predetermined matching algorithm can be used to iteratively close the point (Iterative Closest Point, ICP) algorithm to find the optimal matching of the second feature point cloud data between frames, and adjacent frames can be obtained. The rigid body rotation matrix R' and the translation matrix T' between the environmental point cloud data, so that the attitude change information of the security inspection vehicle can be determined. Exemplarily, the predetermined matching algorithm can be, for example, an iterative Closest Point (Iterative Closest Point, ICP) algorithm, and in other examples, the predetermined matching algorithm can be an improved algorithm of various ICPs, such as PL-ICP (Point to Line ICP, point to line ICP) algorithm. To line iteration closest point), N-ICP (Normal ICP, regular iteration closest point), IMLS-ICP (Implicit Moving Least Square ICP, implicit moving least squares iteration closest point), and NDT (normal distribution) and other others Principle matching algorithm. It should be noted that, the above processing process can be performed on the security inspection vehicle, or can be performed in other devices that can pass through the security inspection vehicle.

The following is an exemplary description of the process of acquiring environmental information and vehicle body information based on environmental point cloud data, and performing steering control based on the environmental information and vehicle body information.

According to the embodiment of the present disclosure, based on the environmental point cloud data, the position information of a plurality of reference objects located in the external environment of the security inspection vehicle can be determined. The process may include: extracting first feature point cloud data from environmental point cloud data; clustering the first feature point cloud data to obtain multiple clustering results, where the multiple clustering results are respectively used as multiple reference objects The respective sub-point cloud data. Then, based on the sub-point cloud data of each of the plurality of reference objects, position information of each of the plurality of reference objects is determined. The first feature point cloud data is point cloud data matched with the preset feature information of the reference object. For example, the reference object can be a predetermined road sign or other predetermined target object, and the reference object can be set on the side of the vehicle body equipped with the multi-line laser radar at the front of the security inspection vehicle. For example, in the example shown in FIG. There is the first multi-line laser radar 5121, so the reference object can be arranged in the external environment on the left side of the vehicle body to ensure that the first multi-line laser radar 5121 can be used to obtain high-precision point cloud data for the reference object. In other examples, an auxiliary reference object can also be set on the other side of the vehicle body, and the fused environment point cloud data can be used to assist the vehicle in performing attitude adjustment. After the position information of each of the plurality of reference objects is determined, then, based on the determined position information of the plurality of reference objects, a guide route can be determined, so that the security inspection vehicle can be guided and controlled according to the guide route.

Exemplarily, the security inspection vehicle may include two motion modes: one is a linear reciprocating motion during the security inspection process, and the other is a trajectory curve motion during the security inspection vehicle transition process or a complex security inspection process. The guidance control scheme according to the embodiment of the present disclosure needs to ensure that the security inspection vehicle will not deviate from the original route due to road conditions, control deviations and other reasons during movement, and can provide a return-to-center function. The process of determining the guidance path will be exemplarily described below with reference to specific examples.

Taking the use of road sign datum objects to provide guidance for the automatic guidance control system as an example, place road sign datum objects on the left side of the security inspection vehicle's driving direction. A void is identified as a passable area for a security vehicle.

6A to 6C schematically illustrate example diagrams of a process of determining a guide path according to an embodiment of the present disclosure.

As shown in FIG. 6A , a plurality of road marking fiducials 620 are set in the external environment of the security inspection vehicle 610 . In this example, the road marking fiducials are placed in a curve, which exemplarily shows a solution for guiding control along a trajectory curve. According to the environmental point cloud data, the reference object information in the external environment of the security inspection vehicle can be obtained. The sub-point cloud data for each fiducial object are obtained by the point cloud segmentation and clustering method. From the sub-point cloud data for each fiducial object, the position information of the corresponding fiducial object can be extracted. Curve fitting is performed based on the respective position information of the plurality of reference objects, for example, piecewise linear fitting is performed on the position information of the plurality of reference objects by the least square method to obtain the fitted lane line 630 . As shown in FIG. 6B , after the fitting lane line 630 is determined, the guide line 640 is determined based on the fitting lane line 630, so that the distance between any point on the guide line 640 and the fitted lane line 630 is the radius of the predetermined circle 650, The size of the predetermined circle 650 defines the lateral attitude deviation space of the security inspection vehicle. In the subsequent guidance control process, the guidance line 640 may be used as a guidance path for the security inspection vehicle.

In order to ensure the smooth running of the security inspection vehicle along the guide path and avoid collision with the reference object, the above-mentioned method for obtaining the driving guide path through the fitted lane line may be shown in FIG. 6C . Taking the origin of the vehicle body coordinate system as the center of the circle, the circumscribed circle 660 of the vehicle body outline is obtained according to the vehicle body outline information. On this basis, the safety distance r required for the vehicle body to run is retained, and a predetermined circle 650 for the safe operation of the vehicle with the origin of the vehicle body coordinate system as the center of the circle can be obtained. In FIG. 6B , the predetermined circle 650 is made to move tangentially to the fitted lane line 630 , and the movement trajectory of the center of the predetermined circle 650 is the guide line 640 . The guidance control scheme according to the embodiment of the present disclosure can calculate the running direction and speed of the vehicle according to the current vehicle body attitude information, and make the origin of the vehicle body coordinate system move along the trajectory on the guidance path as much as possible during the guidance control process of the vehicle body.

In the example of the straight-line guidance scheme, the reference object can be placed in a straight line, and the guidance control scheme according to the embodiment of the present disclosure can directly fit the position information of the reference object into a straight line fitting lane line through the least square method, so as to determine the alignment with the line. The straight line fits the guide line with the lane line at a predetermined distance, so that the security inspection vehicle moves along the guide line to complete the guidance control work. Among them, in order to reserve safe movement space, the distance between the guide line and the fitted lane line is greater than the radius of the circumcircle of the vehicle body.

In an embodiment of the present disclosure, the above-mentioned process of performing guidance control on the vehicle body based on the guidance path includes: according to the above-determined guidance path (eg, guidance line) and attitude change information, the magnitude of the traction force for the security inspection vehicle and the direction. Then, based on the traction force, the vehicle body is automatically guided and controlled, so that the security inspection vehicle travels along the guiding path.

In another embodiment of the present disclosure, during the guidance control process, the influence of obstacles in the external environment on the operation of the security inspection vehicle may also be evaluated. For example, based on the environmental point cloud data, contour information of the vehicle body and contour information of at least one obstacle may be determined. Then, for each obstacle in the at least one obstacle, the distance between the vehicle body and the obstacle is determined based on the contour information of the vehicle body and the contour information of the obstacle, and the rejection is determined based on the distance between the two. The magnitude and direction of the force. According to the guidance path and attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle. Next, based on the traction force and the repulsive force with respect to the at least one obstacle, a comprehensive traction force is determined, and the vehicle body is guided and controlled based on the comprehensive traction force.

Exemplarily, when the distance between the obstacle and the vehicle body is within a certain range, the obstacle will act as a repulsive force on the vehicle body. The magnitude of the repulsive force is inversely proportional to the distance from the obstacle to the vehicle body, and the direction of the repulsive force is from the obstacle to the vehicle body. According to the embodiment of the present disclosure, the traction force and the repulsion force generated by the vehicle body form a comprehensive traction force, which jointly determines the actual running direction of the vehicle body. For example, the comprehensive traction force is calculated by formula (2), as shown in the following formula:

ρ(θ)=μ _α ·α+μβ · _β (2)

Among them, ρ(θ), α and β are in vector form, ρ(θ) represents the comprehensive traction force, α represents the traction force, β represents the repulsive force, μ _α and μ _β are the first and second weights, respectively, and μ _α + _μβ =1. The values of μ _α and μ _β are determined by the steering control strategy. When μ _α > μ _β , the system is mainly guided; when μ _α < μ _β , the system is dominated by obstacle avoidance.

According to the guidance control scheme of the embodiment of the present disclosure, the vehicle body is controlled to move forward along the calculated driving guidance line, and at the same time, the vehicle body is instructed to adjust the driving route according to the distribution of obstacles, until the security inspection vehicle runs to the end of the driving guidance line (that is, at the end of the driving guidance line). If the reference object is not detected in the front of the running direction of the vehicle body, and the forward fitting lane line cannot be obtained), it is considered that the destination is reached, and the guidance control process ends.

In other embodiments of the present disclosure, based on the environmental point cloud data, relevant information in the inspection channel as shown in FIGS. 5A to 5B can also be detected. For example, when it is detected that an unrelated person breaks into the inspection channel, the inspected object deviates from the inspection channel and other emergencies, according to a predetermined strategy, an alarm can be issued and the security inspection vehicle can be controlled to stop the security inspection process.

It can be understood that, based on the descriptions of the above embodiments, the guidance control scheme according to the embodiments of the present disclosure uses a multi-line laser as a scanning device to enhance the detection accuracy of obstacles, reference objects, etc. in the environment, reduce the scope of scanning blind spots, and improve security inspection. Safety of vehicle operation. In addition, by calibrating multiple multi-line laser radars on the vehicle body and fusing point cloud data, it is convenient to obtain vehicle body contour information, vehicle body attitude information and surrounding environment information, and improve the accuracy of positioning and automatic guidance systems. In addition, the guiding effect based on the guiding path is combined with the repulsive effect based on the distribution of obstacles to precisely control the driving path of the security inspection vehicle.

FIG. 7 schematically shows a block diagram of a steering control apparatus according to an embodiment of the present disclosure. The guidance control device can be applied to a security inspection vehicle, and the security inspection vehicle can include a vehicle body, a security inspection door and at least one multi-line laser radar.

As shown in FIG. 7 , the guidance control apparatus 700 may include: an acquisition module 710 , a first determination module 720 , a second determination module 730 and a control module 740 .

The acquiring module 710 is configured to acquire the environmental point cloud data of the security inspection vehicle by using the above at least one multi-line lidar.

The first determining module 720 is configured to determine, based on the environmental point cloud data, position information of multiple reference objects located in the external environment of the security inspection vehicle.

The second determining module 730 is configured to determine the guiding path based on the position information of the plurality of reference objects.

The control module 740 is used for guiding and controlling the vehicle body based on the guiding path. Wherein, when the security inspection vehicle is in the security inspection state, the vehicle body under the guidance control drives the security inspection door to move relative to the inspected object located in the external environment, so that the inspected object passes through the security inspection door.

It should be noted that the implementations of each module/unit/subunit, etc., the technical problems solved, the functions realized, and the technical effects achieved in some embodiments of the apparatus are respectively the implementations of the corresponding steps in the embodiments of the method part. , the technical problem solved, the function realized, and the technical effect achieved are the same or similar, and will not be repeated here.

FIG. 8 schematically shows an example structural diagram of a security inspection vehicle suitable for implementing the above-described method according to an embodiment of the present disclosure. The security inspection vehicle shown in FIG. 8 is only an example, and should not impose any limitations on the structure, function and scope of use of the embodiments of the present disclosure.

As shown in FIG. 8 , the security inspection vehicle 800 includes a processor 810 , a computer-readable storage medium 820 , a vehicle body 830 , a security inspection door 840 , and at least one multi-line lidar 850 . The security inspection vehicle 800 may execute the method according to the embodiment of the present disclosure.

According to the embodiment of the present disclosure, when the above-mentioned at least one multi-line lidar 850 includes a plurality of multi-line lidars, at least two of the plurality of multi-line lidars are distributed outside the vehicle body, so that the at least two multi-line lidars are distributed outside the vehicle body. The scanning range of the two multi-line lidars covers 360° around the vehicle body.

According to an embodiment of the present disclosure, at least one of the multiple multi-line laser radars 850 other than the at least two multi-line laser radars is located inside the security gate.

Specifically, the processor 810 may include, for example, a general-purpose microprocessor, an instruction set processor and/or a related chipset, and/or a special-purpose microprocessor (eg, an application specific integrated circuit (ASIC)), and the like. The processor 810 may also include onboard memory for caching purposes. The processor 810 may be a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

The computer-readable storage medium 820 can be, for example, a non-volatile computer-readable storage medium, and specific examples include but are not limited to: magnetic storage devices, such as magnetic tapes or hard disks (HDDs); optical storage devices, such as compact disks (CD-ROMs) ; memory, such as random access memory (RAM) or flash memory; etc.

The computer-readable storage medium 820 may include a computer program 821, which may include code/computer-executable instructions that, when executed by the processor 810, cause the processor 810 to perform methods according to embodiments of the present disclosure or any variation thereof.

The computer program 821 may be configured with computer program code comprising, for example, computer program modules. For example, in an example embodiment, the code in computer program 821 may include one or more program modules, including, for example, 821A, module 821B, . . . It should be noted that the division method and number of modules are not fixed, and those skilled in the art can use appropriate program modules or combination of program modules according to the actual situation. When these combination of program modules are executed by the processor 810, the processor 810 can A method according to an embodiment of the present disclosure or any variation thereof is performed.

According to an embodiment of the present disclosure, at least one of the acquisition module 710 , the first determination module 720 , the second determination module 730 , and the control module 740 may be implemented as the computer program modules described with reference to FIG. 8 , which when executed by the processor 810 , the method described above can be implemented.

The present disclosure also provides a computer-readable storage medium. The computer-readable storage medium may be included in the device/apparatus/system described in the above embodiments; it may also exist alone without being assembled into the device/system. device/system. The above-mentioned computer-readable storage medium carries one or more programs, and when the above-mentioned one or more programs are executed, implement the method according to the embodiment of the present disclosure.

According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as, but not limited to, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM) , erasable programmable read only memory (EPROM or flash memory), portable compact disk read only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In this disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

Although the present disclosure has been shown and described with reference to specific exemplary embodiments of the present disclosure, those skilled in the art will appreciate that, without departing from the spirit and scope of the present disclosure as defined by the appended claims and their equivalents, Various changes in form and detail have been made in the present disclosure. Therefore, the scope of the present disclosure should not be limited to the above-described embodiments, but should be determined not only by the appended claims, but also by their equivalents.

Claims

A guidance control method is applied to a security inspection vehicle, the security inspection vehicle includes a vehicle body, a security inspection door and at least one multi-line laser radar, and the method includes:

Obtain the environmental point cloud data of the security inspection vehicle by using the at least one multi-line lidar;

determining, based on the environmental point cloud data, position information of a plurality of reference objects located in the external environment of the security inspection vehicle;

determining a guide path based on the positional information of the plurality of fiducials; and

Based on the guide path, guide control is performed on the vehicle body, wherein when the security inspection vehicle is in a security inspection state, the vehicle body passing through the guide control drives the security inspection door relative to the external environment. The inspected object moves so that the inspected object passes through the security gate.
The method of claim 1, wherein the at least one multi-line lidar comprises a plurality of multi-line lidars;

The obtaining of the environmental point cloud data of the security inspection vehicle by using the at least one multi-line lidar includes:

For any moment, the respective point cloud data are acquired by the multiple multi-line lidars; and

Converting the point cloud data of each of the multiple multi-line lidars from the coordinate system of each of the multi-line lidars to the reference coordinate system to form the environmental point cloud data at the any moment .
The method of claim 2, further comprising:

Before the converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of the each multi-line lidar to the reference coordinate system, based on the each multi-line lidar The positional relationship of the radar relative to the vehicle body, determining the rotation transformation relationship and translation transformation relationship between the coordinate system of each multi-line laser radar and the reference coordinate system;

The converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system includes: according to the rotation transformation relationship and translation transformation relationship, the point cloud data of each multi-line lidar is converted from the coordinate system of each multi-line lidar to the reference coordinate system.
The method of claim 2, further comprising:

before converting the point cloud data of each multi-line lidar in the plurality of multi-line lidars from the coordinate system of each multi-line lidar to the reference coordinate system,

Obtaining detection data for a predetermined target from each of the multi-line laser radars, and using a random sampling consistency algorithm to extract the same-name vector representation and the same-name point representation for characterizing the predetermined target from the detection data;

The respective vector representations of the same name of the multiple multi-line lidars are processed based on the Rodrigues rotation equation, so as to obtain the relationship between the coordinate system of any one of the multiple multi-line lidars and the reference coordinate system Rotation transformation relationship between; and

Determine the translation transformation relationship between the coordinate system of any one of the multiple multi-line laser radars and the reference coordinate system based on the respective same-name point representations of the multiple multi-line laser radars;

The converting the point cloud data of each of the plurality of multi-line lidars from the coordinate system of each of the multi-line lidars to the reference coordinate system includes: according to the plurality of multi-line lidars. The rotation transformation relationship and translation transformation relationship between the coordinate system of any one of the multi-line laser radars and the reference coordinate system, and the point cloud data of the multiple multi-line laser radars are converted from the respective multi-line laser radars. The coordinate system is converted to the reference coordinate system.
The method according to claim 1, wherein the determining, based on the environmental point cloud data, the location information of a plurality of reference objects located in the external environment of the security inspection vehicle comprises:

extracting first feature point cloud data from the environmental point cloud data;

Performing clustering on the first feature point cloud data to obtain a plurality of clustering results, and the plurality of clustering results are respectively used as sub-point cloud data of the plurality of reference objects; and

Based on the respective sub-point cloud data of the plurality of reference objects, position information of each of the plurality of reference objects is determined.
The method according to claim 1, wherein the determining a guide path based on the position information of the plurality of fiducial objects comprises:

Based on the respective position information of the plurality of reference objects, curve fitting is performed to obtain a fitted lane line; and

Based on the fitted lane line, the guide line is determined so that the distance between any point on the guide line and the fitted lane line is the radius of a predetermined circle.
The method according to claim 6, wherein the radius of the predetermined circle is larger than the radius of the circumscribed circle of the security inspection vehicle.
The method of claim 2, further comprising:

extracting second feature point cloud data from the environmental point cloud data at any time;

Using a predetermined matching algorithm, matching between the second feature point cloud data at any moment and the second feature point cloud data at the previous moment at any moment to determine a rotation matrix and a translation matrix; and

Based on the rotation matrix and the translation matrix, the attitude change information of the security inspection vehicle at the any moment is determined.
The method according to claim 8, wherein the guiding control of the vehicle body based on the guiding path comprises:

According to the guide path and the attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle; and

Guidance control of the vehicle body is performed based on the traction force.
The method of claim 8, further comprising:

Based on the environmental point cloud data, determine the contour information of the vehicle body and the contour information of at least one obstacle;

For each obstacle in the at least one obstacle, the distance between the vehicle body and the obstacle is determined based on the outline information of the vehicle body and the outline information of the obstacle, and based on the The distance determines the magnitude and direction of the repulsive force;

According to the guide path and the attitude change information, determine the magnitude and direction of the traction force for the security inspection vehicle;

determining a combined traction force based on the traction force and the repulsive force for the at least one obstacle; and

Guidance control of the vehicle body is performed based on the integrated traction force.
11. The method of claim 10, wherein the determining a combined traction force based on the traction force and the repulsive force for the at least one obstacle comprises:

Using a preset first weight and a second weight, the traction force and the repulsive force for the at least one obstacle are weighted and summed to obtain the comprehensive traction force.
A guidance control device is applied to a security inspection vehicle, the security inspection vehicle includes a vehicle body, a security inspection door and at least one multi-line laser radar, and the device includes:

an acquisition module, configured to acquire the environmental point cloud data of the security inspection vehicle by using the at least one multi-line lidar;

a first determining module, configured to determine, based on the environmental point cloud data, position information of multiple reference objects located in the external environment of the security inspection vehicle;

a second determining module, configured to determine a guide path based on the position information of the plurality of reference objects; and

A control module is configured to perform guidance control on the vehicle body based on the guidance path, wherein when the security inspection vehicle is in a security inspection state, the vehicle body passing through the guidance control drives the security inspection door relative to the security inspection door. The object under inspection in the external environment moves so that the object under inspection passes through the security gate.
A security inspection vehicle, comprising:

body;

security gate;

At least one multi-line lidar;

memory for storing instructions; and

At least one processor for executing instructions stored in the memory to implement the method according to one of claims 1-11.
The security inspection vehicle according to claim 13, wherein when the at least one multi-line lidar includes a plurality of multi-line lidars, at least two multi-line lidars in the plurality of multi-line lidars are dispersedly distributed in the the outside of the vehicle body, so that the scanning range of the at least two multi-line laser radars covers 360° of the periphery of the vehicle body.
The security inspection vehicle according to claim 14, wherein at least one of the plurality of multi-line laser radars other than the at least two multi-line laser radars is located inside the security inspection door.
A computer-readable storage medium is applied to a security inspection vehicle. The security inspection vehicle includes a vehicle body, a security inspection door, and at least one multi-line laser radar. Computer instructions are stored on the computer-readable storage medium, and the computer instructions are processed. The method according to one of claims 1 to 11 is implemented when the device is executed.
A computer program product is applied to a security inspection vehicle, the security inspection vehicle includes a vehicle body, a security inspection door and at least one multi-line laser radar, the computer program product includes executable instructions, and the instructions are executed by a processor. The method described in any one of 1 to 11.