Unmanned equipment control method, device, storage medium and electronic equipment

Abstract

The present specification discloses an unmanned equipment control method, device, storage medium and electronic device. In the embodiments of the present specification, each degree of freedom combination and the point cloud area of ​​each degree of freedom combination are determined. For each degree of freedom combination, the first point cloud and the second point cloud in the point cloud area of ​​the degree of freedom combination are collected by the first radar and the second radar in any two radars, and the external parameters between any two radars calibrated in advance, the index deviation between the first point cloud and the second point cloud is determined, and based on the index deviation, the verification result corresponding to the degree of freedom combination is determined. The unmanned equipment is controlled according to the verification result of each degree of freedom combination. In this method, for each degree of freedom combination obtained after the external parameters of the two radars are decoupled, it can be determined whether there is an abnormality in the verification result of each degree of freedom combination between the two radars to verify whether the external parameters between the two radars are accurate, thereby ensuring the safety of the unmanned equipment.

Description

Technical Field

[0001] This specification relates to the field of unmanned driving, and in particular to an unmanned equipment control method, device, storage medium and electronic device. Background Art

[0002] In the field of unmanned driving, in order to enable unmanned equipment to drive safely, it is necessary to install sensors that can sense the surrounding environment information of the unmanned equipment, such as cameras, radars, GPS, etc. Generally, unmanned equipment needs to process the environmental information obtained by each sensor, and then determine the control strategy for safe driving for the unmanned equipment based on the processed environmental information, and control the unmanned equipment to drive safely based on the control strategy.

[0003] Taking radar as an example, in order to detect obstacles around unmanned equipment, radars need to be installed at different locations of the unmanned equipment. However, the coordinate system of each radar detecting environmental information is different. Therefore, when processing the environmental information obtained by radars at different locations, it is necessary to convert the obtained environmental information to the same radar coordinate system based on the pre-calibrated external parameters between radars at different locations. Therefore, during the driving process of unmanned equipment, the accuracy of the external parameters between radars at different locations affects the safety of the driving of the unmanned equipment.

[0004] However, during the driving process of unmanned equipment, due to the influence of the environment around the unmanned equipment, the external parameters between radars at different locations are changing in real time. In order to ensure the safe driving of the unmanned equipment, the accuracy of the external parameters between radars needs to be verified in real time. Therefore, how to verify the accuracy of the external parameters between radars at different locations is an urgent problem to be solved. Summary of the invention

[0005] The embodiments of this specification provide an unmanned equipment control method, device, storage medium and electronic device to partially solve the problems existing in the above-mentioned prior art.

[0006] The embodiments of this specification adopt the following technical solutions:

[0007] This manual provides an unmanned equipment control method, including:

[0008] Obtain point cloud data collected by each radar installed on the unmanned equipment, and determine the combination of each degree of freedom;

[0009] Randomly select two radars from the radars as the first radar and the second radar, and for each degree of freedom combination, determine a point cloud area corresponding to the degree of freedom combination for verifying the degree of freedom combination as the target area;

[0010] Determine point cloud data located within the target area from the point cloud data collected by the first radar as a first point cloud, and determine point cloud data located within the target area from the point cloud data collected by the second radar as a second point cloud;

[0011] Projecting the first point cloud and the second point cloud into a unified coordinate system according to the pre-calibrated external parameters between the first radar and the second radar to determine an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation;

[0012] The unmanned equipment is controlled according to the verification result corresponding to each degree of freedom combination.

[0013] Optionally, the plurality of degree-of-freedom combinations include: a non-parallel ground degree-of-freedom combination, a yaw angle degree-of-freedom combination, and a parallel ground degree-of-freedom combination;

[0014] The non-parallel ground degree of freedom combination includes a pitch angle, a roll angle and a height translation distance, the yaw angle degree of freedom combination includes a yaw angle, and the parallel ground degree of freedom combination includes a lateral translation distance and a longitudinal translation distance of a horizontal plane;

[0015] For each degree of freedom combination, determine the point cloud area corresponding to the degree of freedom combination for verifying the point cloud area, including:

[0016] For the non-parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the non-parallel ground degree of freedom combination for verifying the point cloud area corresponding to the non-parallel ground degree of freedom combination is a ground point cloud;

[0017] For the yaw angle degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the yaw angle degree of freedom combination for verifying the point cloud area corresponding to the yaw angle degree of freedom combination is a point cloud area in a plane perpendicular to the ground;

[0018] For the parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine the point cloud area corresponding to the parallel ground degree of freedom combination for verifying the point cloud area corresponding to the parallel ground degree of freedom combination is an obstacle point cloud.

[0019] Optionally, determining point cloud data located in the target area from the point cloud data collected by the first radar as a first point cloud, and determining point cloud data located in the target area from the point cloud data collected by the second radar as a second point cloud, specifically includes:

[0020] Determine point cloud data located in the target area from the point cloud data collected by the first radar as a first initial point cloud, and determine point cloud data located in the target area from the point cloud data collected by the second radar as a second initial point cloud;

[0021] The first initial point cloud and the second initial point cloud are filtered to obtain the first point cloud and the second point cloud.

[0022] Optionally, filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes:

[0023] For the non-parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the first filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud; wherein the first filtering index includes the height threshold of the point cloud point and the ground true normal vector.

[0024] Optionally, filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes:

[0025] For the yaw angle degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the second filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud; wherein the second filtering index includes the height range of the point cloud point and the true normal vector of the plane perpendicular to the ground.

[0026] Optionally, filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes:

[0027] For the parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered according to the third filtering index to obtain the point cloud with the highest overlap rate between the first initial point cloud and the second initial point cloud, which are used as the first point cloud corresponding to the first radar and the second point cloud corresponding to the second radar; wherein the third filtering index includes: the pre-calibrated height difference and horizontal distance difference between the first radar and the second radar, and the field viewing angles of the first radar and the second radar respectively.

[0028] Optionally, determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes:

[0029] Fitting a first spatial plane according to the first point cloud, and fitting a second spatial plane according to the second point cloud;

[0030] Determine at least one index deviation between the first point cloud and the second point cloud according to the first spatial plane and the second spatial plane; the at least one index deviation includes: a normal vector angle between the first spatial plane and the second spatial plane, an average distance between the first spatial plane and the second spatial plane, a distance variance, and a maximum distance difference, wherein the maximum distance difference is a difference between a maximum distance and a minimum distance between the first spatial plane and the second spatial plane;

[0031] According to the at least one indicator deviation and the preset threshold values ​​corresponding to the indicator deviations, the roll angle, pitch angle and height translation distance in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the non-parallel ground degree of freedom combination.

[0032] Optionally, determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes:

[0033] Convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the first horizontal plane;

[0034] Fitting a first spatial straight line according to the first point cloud in the first horizontal plane, and fitting a second spatial straight line according to the second point cloud in the first horizontal plane;

[0035] Determine an index deviation between the first point cloud and the second point cloud according to the first space straight line and the second space straight line, the index deviation comprising: an angle between the first space straight line and the second space straight line;

[0036] According to the index deviation, the yaw angles in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the degree of freedom combination.

[0037] Optionally, determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes:

[0038] Convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the second horizontal plane;

[0039] Determine point cloud points of the same obstacle from the first point cloud and the second point cloud in the second horizontal plane, and use the point cloud points of the same obstacle determined in the first point cloud as first point cloud points, and use the point cloud points of the same obstacle determined in the second point cloud as second point cloud points;

[0040] Determine an index deviation between the first point cloud and the second point cloud according to the first point cloud point and the second point cloud point; the index deviation includes: a lateral translation distance difference between the first point cloud point and the second point cloud point, and a longitudinal translation distance difference between the first point cloud point and the second point cloud point;

[0041] According to the index deviation, the lateral translation distance and the longitudinal translation distance in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the degree of freedom combination.

[0042] Optionally, determining point cloud points of the same obstacle from the first point cloud and the second point cloud in the second horizontal plane specifically includes:

[0043] Selecting a point cloud point closest to the origin in the unified coordinate system from the first point cloud as an initial first point cloud point, and selecting a point cloud point closest to the origin in the unified coordinate system from the second point cloud as an initial second point cloud point;

[0044] Determining whether the initial first point cloud point and the initial second point cloud point belong to the same obstacle according to a matching index between the initial first point cloud point and the initial second point cloud point, wherein the matching index includes at least one of a distance between the initial first point cloud point and the initial second point cloud point, and an angle between a line connecting the initial first point cloud point and the origin and a line connecting the initial second point cloud point and the origin;

[0045] If the initial first point cloud point and the initial second point cloud point belong to the same obstacle, the initial first point cloud point is used as the first point cloud point, and the initial second point cloud point is used as the second point cloud point.

[0046] Optionally, controlling the unmanned equipment according to the verification result corresponding to each degree of freedom combination specifically includes:

[0047] For each calibration in a preset degree of freedom calibration cycle, judging whether there is an abnormality in the external parameters between the first radar and the second radar in the calibration according to the calibration results corresponding to each degree of freedom combination in the calibration;

[0048] According to the judgment result of each verification, determining the number of times that an abnormality is detected in the external parameter between the first radar and the second radar in the degree of freedom verification cycle;

[0049] According to the number of times, a control strategy for the unmanned equipment corresponding to the number of times is determined, and based on the control strategy, the unmanned equipment is controlled.

[0050] Optionally, the method further comprises:

[0051] When an abnormality is found in the external parameters between the first radar and the second radar for a consecutive preset number of times in the degree of freedom verification cycle, the unmanned equipment is controlled based on a control strategy corresponding to the abnormality of the verification results for the consecutive preset number of times.

[0052] Optionally, the method further comprises:

[0053] For each degree of freedom combination, determine the change rule of the verification result corresponding to the degree of freedom combination in a preset degree of freedom verification cycle, and obtain the change rule of the verification result corresponding to the degree of freedom combination;

[0054] According to a change rule of the verification result corresponding to each degree of freedom combination, an extrinsic parameter calibration period between the first radar and the second radar is determined, and based on the extrinsic parameter calibration period, the extrinsic parameters between the first radar and the second radar are recalibrated.

[0055] This manual provides an unmanned equipment control device, including:

[0056] An acquisition module is used to acquire point cloud data collected by various radars installed on unmanned equipment and determine the combination of various degrees of freedom;

[0057] A region determination module is used to select any two radars from the radars as the first radar and the second radar, and for each degree of freedom combination, determine a point cloud region corresponding to the degree of freedom combination for verifying the degree of freedom combination as a target region;

[0058] a point cloud determination module, configured to determine point cloud data located within the target area from the point cloud data collected by the first radar as a first point cloud, and to determine point cloud data located within the target area from the point cloud data collected by the second radar as a second point cloud;

[0059] a verification result determination module, configured to project the first point cloud and the second point cloud into a unified coordinate system according to the pre-calibrated external parameters between the first radar and the second radar, so as to determine an index deviation corresponding to the first point cloud and the second point cloud, and determine a verification result corresponding to the degree of freedom combination according to the index deviation;

[0060] The control module is used to control the unmanned equipment according to the verification result corresponding to each degree of freedom combination.

[0061] This specification provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the unmanned equipment control method described above is implemented.

[0062] This specification provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned unmanned equipment control method when executing the program.

[0063] At least one of the above technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects:

[0064] In the embodiments of this specification, each degree of freedom combination is obtained and the point cloud area corresponding to each degree of freedom combination is determined. For each degree of freedom combination, according to the first point cloud in the point cloud area corresponding to the degree of freedom combination collected by the first radar of any two radars and the second point cloud in the point cloud area corresponding to the degree of freedom combination collected by the second radar of any two radars, and the external parameters between any two radars calibrated in advance, the first point cloud and the second point cloud are projected to the same coordinate system, and the index deviation between the first point cloud and the second point cloud is determined. Based on the index deviation, the verification result corresponding to the degree of freedom combination is determined. According to the verification result of each degree of freedom combination, the unmanned equipment is controlled. In this method, for each degree of freedom combination obtained after the external parameters of the two radars are decoupled, it can be determined whether there is an abnormality in the verification result of each degree of freedom combination between the two radars to verify whether the external parameters between the two radars are accurate, thereby ensuring the safety of the unmanned equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The drawings described herein are used to provide a further understanding of this specification and constitute a part of this specification. The illustrative embodiments and descriptions of this specification are used to explain this specification and do not constitute an improper limitation on this specification. In the drawings:

[0066] Figure 1 A schematic diagram of the unmanned equipment control process provided in the embodiments of this specification;

[0067] Figure 2 A schematic diagram of a first radar coordinate system provided in an embodiment of this specification;

[0068] Figure 3 A schematic diagram of the specified deviations in the non-parallel ground degree of freedom combination provided for the embodiments of this specification;

[0069] Figure 4 A schematic diagram of curb point cloud filtering provided in an embodiment of this specification;

[0070] Figure 5 A schematic diagram of a specified deviation of a yaw angle degree of freedom combination provided in an embodiment of this specification;

[0071] Figure 6 A schematic diagram of the specified deviations of the parallel ground degree of freedom combination provided for the embodiments of this specification;

[0072] Figure 7 A schematic diagram of the calibration of external parameters between the first radar and the second radar provided in the embodiment of this specification;

[0073] Figure 8 A schematic diagram of controlling unmanned equipment provided in an embodiment of this specification;

[0074] Fig. 9 A schematic diagram of another method for controlling unmanned equipment provided in an embodiment of this specification;

[0075] Fig.10 A schematic diagram of the structure of an unmanned equipment control device provided in an embodiment of this specification;

[0076] Fig.11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this specification. DETAILED DESCRIPTION

[0077] In the field of unmanned driving, in order to enable the unmanned equipment to accurately sense obstacles within the preset range of the unmanned equipment, radar sensors for sensing obstacles can usually be installed on the top, left and right sides of the unmanned equipment. When there are multiple radar sensors, when processing the point clouds collected by each radar sensor, in order to improve the processing efficiency, the point clouds collected by the radar sensors on the left and right sides need to be converted to the coordinate system of the radar sensor on the top of the unmanned equipment. Therefore, the external parameters between the radar sensors can be calibrated according to the relative posture between the radar sensors.

[0078] During the driving process of the unmanned equipment, due to reasons such as high or low weather temperature, uneven road surface, etc., the relative posture between any two radar sensors will change during the driving process of the unmanned equipment, and the pre-calibrated external parameters between any two radar sensors cannot adapt to the changes in the relative posture between the two radar sensors in real time. This may cause the pre-calibrated external parameters between any two radar sensors to be inconsistent with the current relative posture between the two radar sensors. In this case, the point cloud obtained after the coordinate transformation of the point cloud collected by the two radar sensors through the pre-selected calibrated external parameters is problematic and is not suitable for obstacle analysis and determining the control strategy of the unmanned equipment. Therefore, it is necessary to verify the accuracy of the external parameters between any two radar sensors. That is, it is necessary to determine whether the current relative posture between any two radar sensors matches the calibrated external parameters between the two radar sensors.

[0079] The unmanned equipment control method provided in this specification aims to judge the accuracy of the pre-calibrated external parameters between any two radars based on the differences in each degree of freedom of the point cloud obtained by the current relative posture of the two radars.

[0080] In order to make the purpose, technical solutions and advantages of this specification more clear, the technical solutions of this specification will be clearly and completely described below in combination with the specific embodiments of this specification and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0081] The technical solutions provided by the embodiments of this specification are described in detail below in conjunction with the accompanying drawings.

[0082] Figure 1 The unmanned equipment control flow diagram provided for the embodiments of this specification includes:

[0083] S100: Acquire point cloud data collected by each radar installed on the unmanned equipment, and determine the combination of each degree of freedom.

[0084] S102: arbitrarily selecting two radars from the radars as a first radar and a second radar, and for each degree of freedom combination, determining a point cloud area corresponding to the degree of freedom combination for verifying the degree of freedom combination as a target area.

[0085] S104: Determine point cloud data located within the target area from the point cloud data collected by the first radar as a first point cloud, and determine point cloud data located within the target area from the point cloud data collected by the second radar as a second point cloud.

[0086] In the embodiments of the present specification, multiple radars can be installed on the unmanned equipment. Since the multiple radars can be distributed at different positions on the unmanned equipment, that is, the relative postures between the radars are different, each radar has a different coordinate system. Therefore, the posture transformation between the same point cloud data collected by each radar installed on the unmanned equipment within the preset range of the unmanned equipment based on its own coordinate system can reflect the conversion relationship between different radar coordinate systems. Among them, the posture of the point cloud collected by each radar in its own coordinate system can be jointly represented by six degrees of freedom. The six degrees of freedom are: roll angle, pitch angle, yaw angle, height translation distance, lateral translation distance in the horizontal plane, and longitudinal translation distance in the horizontal plane.

[0087] When multiple radars are installed on an unmanned device, two radars can be arbitrarily selected from the multiple radars, one of which is used as the first radar and the other as the second radar. Taking the first radar installed on the top of the unmanned device as an example, assume that the coordinate system of the first radar is XYZ, the origin of the coordinate system is O, the XY plane is parallel to the ground, and the Z axis is perpendicular to the XY plane. The head of the unmanned device is in the Y-axis direction, the roll angle is the angle formed by the rotation around the Y-axis, the pitch angle is the angle formed by the rotation around the X-axis, and the yaw angle is the angle formed by the rotation around the Z-axis. Figure 2 shown.

[0088] Next, taking the first radar and the second radar as examples, Figure 1 The unmanned equipment control method shown is explained.

[0089] When calibrating the external parameters between the first radar and the second radar, the external parameters between the first radar and the second radar can be calibrated according to the position and posture of the point cloud collected by the first radar and the second radar. That is, the conversion relationship of the coordinate system between the first radar and the second radar is calibrated. The external parameters between the first radar and the second radar are the rotation matrix and the translation matrix between the first radar and the second radar. The rotation matrix involves the roll angle, pitch angle and yaw angle, and the translation matrix involves the distance translated along the coordinate system axis.

[0090] Therefore, when verifying the external parameters calibrated between the first radar and the second radar, the degrees of freedom involved in the external parameters can be decoupled to obtain the degrees of freedom such as the roll angle, pitch angle, yaw angle, and the distance translated along the coordinate system axis. Then, based on the differences in each degree of freedom between the point cloud collected in the coordinate system of the first radar and the point cloud collected in the coordinate system of the second radar, it is determined whether the external parameters calibrated between the first radar and the second radar are accurate.

[0091] After the degrees of freedom involved in the external parameters are decoupled to obtain the degrees of freedom, the degrees of freedom can be grouped according to a preset degree of freedom grouping method to determine the combination of the degrees of freedom. The preset degree of freedom grouping method can be determined according to the mutual influence between the degrees of freedom.

[0092] Specifically, when the radar has a roll angle, the pitch angle and altitude translation distance will inevitably be generated. Therefore, the roll angle, pitch angle and altitude translation distance influence each other, that is, the three degrees of freedom of roll angle, pitch angle and altitude translation distance are a group, called a non-parallel ground degree of freedom combination; there is no mutual influence between the yaw angle and the translation distance of the horizontal plane, so the yaw degree of freedom can be regarded as a group, called a yaw angle degree of freedom combination; the horizontal plane translation distance includes the lateral translation distance and the longitudinal translation distance. When the unmanned equipment moves on the horizontal plane, the lateral translation distance and the longitudinal translation distance in the horizontal plane also change accordingly. Therefore, the lateral translation distance and the longitudinal translation distance can be regarded as a group, called a parallel ground degree of freedom combination.

[0093] In the embodiment of the present specification, after determining each degree of freedom combination, the external parameters calibrated between the first radar and the second radar can be verified based on the differences in the point clouds collected by the first radar and the second radar on the unmanned equipment under each degree of freedom combination to determine whether the external parameters calibrated between the first radar and the second radar are accurate.

[0094] Specifically, the point cloud data in the specified area are obtained by the first radar and the second radar installed on the unmanned device, and the point cloud data obtained by the first radar is used as the global first point cloud, and the point cloud data obtained by the second radar is used as the global second point cloud. The specified area can be a point cloud within the preset range of the unmanned device. Then, for each degree of freedom combination in each degree of freedom combination, the degree of freedom in the degree of freedom combination calibrated between the first radar and the second radar is verified according to the difference between the global first point cloud and the global second point cloud under the degree of freedom combination.

[0095] In order to improve the calibration accuracy and efficiency of the external parameters calibrated between the first radar and the second radar, for each degree of freedom combination, according to the degrees of freedom contained in the degree of freedom combination, the region of interest corresponding to the degree of freedom combination can be determined as the target area. Among them, the region of interest corresponding to the degree of freedom combination can be used to verify the point cloud area corresponding to the degree of freedom combination. That is, according to the degrees of freedom contained in the degree of freedom combination, the point cloud area corresponding to the degree of freedom combination is determined as the target area.

[0096] Specifically, for each degree of freedom combination, the point cloud data collected by the first radar and the second radar may be cropped to determine a point cloud area corresponding to the degree of freedom combination for verifying the degree of freedom combination.

[0097] For the non-parallel ground DOF combination, the degrees of freedom in the non-parallel ground DOF combination are not parallel to the ground, so the ground can be selected as a reference to determine the change of the degrees of freedom in the non-parallel ground DOF combination. That is, the ground area is used as the region of interest corresponding to the non-parallel ground DOF combination, that is, the ground area is used as the target area corresponding to the non-parallel ground DOF combination. And the ground point cloud is used as the point cloud in the target area corresponding to the non-parallel ground DOF combination.

[0098] For the yaw angle DOF combination, the yaw angle in the yaw angle DOF combination is the angle formed by rotating around the coordinate axis perpendicular to the ground. Therefore, the plane area perpendicular to the ground can be used as the region of interest corresponding to the yaw angle DOF combination. That is, the plane area perpendicular to the ground is used as the target area corresponding to the yaw angle DOF combination. And the point cloud in the plane perpendicular to the ground is used as the point cloud in the target area corresponding to the yaw angle DOF combination. For example: the plane area perpendicular to the ground can be a curb, billboard, etc., and the curb point cloud and billboard point cloud are used as the point cloud in the target area corresponding to the yaw angle DOF combination.

[0099] For the parallel ground DOF combination, the degrees of freedom in the parallel ground DOF combination are parallel to the ground, and the changes in the lateral distance and longitudinal distance of the same horizontal plane need to be determined. Therefore, the obstacle area can be selected as the region of interest corresponding to the parallel ground DOF combination. That is, the obstacle area is used as the target area corresponding to the parallel ground DOF combination. And the obstacle point cloud is used as the point cloud in the target area corresponding to the parallel ground DOF combination.

[0100] Therefore, for the non-parallel ground degree of freedom combination, the point cloud data collected by the first radar and the second radar are cropped to determine the point cloud area corresponding to the non-parallel ground degree of freedom combination for verification. The point cloud area corresponding to the non-parallel ground degree of freedom combination is the ground point cloud.

[0101] For the yaw angle degree of freedom combination, the point cloud data collected by the first radar and the second radar are cropped to determine the point cloud area corresponding to the yaw angle degree of freedom combination for verifying the point cloud area corresponding to the yaw angle degree of freedom combination is a point cloud area in a plane perpendicular to the ground.

[0102] For the parallel ground degree of freedom combination, the point cloud data collected by the first radar and the second radar are cropped to determine the point cloud area corresponding to the parallel ground degree of freedom combination for verifying the point cloud area corresponding to the parallel ground degree of freedom combination is the obstacle point cloud.

[0103] After determining the target area corresponding to each degree of freedom combination, for each degree of freedom combination, point cloud data located within the target area corresponding to the degree of freedom combination can be determined from the point cloud data collected by the first radar as the first point cloud, and point cloud data located within the target area corresponding to the degree of freedom combination can be determined from the point cloud data collected by the second radar as the second point cloud.

[0104] Specifically, for each degree of freedom combination, the global first point cloud collected by the first radar and the global second point cloud collected by the second radar are clipped according to the target area corresponding to the degree of freedom combination to obtain an initial first point cloud and an initial second point cloud. Then, the initial first point cloud and the initial second point cloud are filtered to obtain a first point cloud and a second point cloud.

[0105] When cropping the global first point cloud and the global second point cloud, for each degree of freedom combination, it is necessary to verify the first point cloud in the target area corresponding to the degree of freedom combination collected by the first radar and the second point cloud in the target area corresponding to the degree of freedom combination collected by the second radar. Therefore, in order to accurately crop the point clouds in the same target area from the global first point cloud and the global second point cloud, the global second point cloud can be converted to the first radar coordinate system. In this way, the point clouds in the same target area of ​​the global second point cloud and the global first point cloud can be cropped in the first radar coordinate system.

[0106] It should be noted that the unmanned equipment in this specification may include unmanned vehicles and drones. Unmanned equipment can be used in the field of logistics and distribution, including both instant delivery fields such as takeout and delivery, and other non-instant delivery fields. In addition, the unmanned equipment in this specification may also include: unmanned taxis, unmanned buses, shuttle buses and other unmanned equipment for carrying people.

[0107] also, Figure 1 The unmanned device control method shown can be applied to unmanned devices, and can also be applied to a server that controls the unmanned devices.

[0108] S106: Based on the pre-calibrated external parameters between the first radar and the second radar, the first point cloud and the second point cloud are projected into a unified coordinate system to determine an index deviation corresponding to the first point cloud and the second point cloud, and based on the index deviation, a verification result corresponding to the degree of freedom combination is determined.

[0109] In an embodiment of the present specification, for each degree of freedom combination, after obtaining the initial first point cloud under the degree of freedom combination collected by the first radar and the initial second point cloud collected by the second radar, the initial first point cloud and the initial second point cloud are filtered to obtain the first point cloud and the second point cloud. Then, according to the pre-calibrated external parameters between the first radar and the second radar, the first point cloud and the second point cloud are projected into a unified coordinate system, and the index deviation corresponding to the first point cloud and the second point cloud is determined. Finally, according to the index deviation, the verification result corresponding to the degree of freedom combination is determined. That is, according to the index deviation, it is determined whether the degree of freedom in the degree of freedom combination involved in the external parameters between the first radar and the second radar is accurate. That is, according to the index deviation, the first point cloud and the second point cloud are verified for degrees of freedom to obtain a verification result.

[0110] For the non-parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the first filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud. The first filtering index includes the height threshold of the point cloud point and the ground truth normal vector.

[0111] Specifically, according to the height translation distance and the height threshold of each point cloud point, the initial first point cloud and the initial second point cloud are respectively screened to obtain the screened initial first point cloud and the screened initial second point cloud. According to the normal vector of each point cloud point and the ground truth normal vector, the screened initial first point cloud and the screened initial second point cloud are respectively filtered to obtain the first point cloud and the second point cloud. The first point cloud and the second point cloud may be ground point clouds.

[0112] In addition, the ground point cloud can be extracted from the initial first point cloud and the initial second point cloud by using a pre-trained point cloud extraction model, wherein the point cloud extraction model can be a PointNet model, a PointCNN model, etc.

[0113] Then, according to the first point cloud, fit the first spatial plane, and according to the second point cloud, fit the second spatial plane. According to the first spatial plane and the second spatial plane, determine at least one index deviation between the first point cloud and the second point cloud as the first index deviation. According to at least one first index deviation and the preset thresholds corresponding to each first index deviation, verify the roll angle, pitch angle and height translation distance in the first point cloud and the second point cloud to obtain the verification result corresponding to the non-parallel ground degree of freedom combination. Among them, at least one first index deviation includes: the normal vector angle between the first spatial plane and the second spatial plane, the average distance between the first spatial plane and the second spatial plane, the distance variance, and the maximum distance difference. The maximum distance difference is the difference between the maximum distance and the minimum distance between the first spatial plane and the second spatial plane. Figure 3 shown.

[0114] exist Figure 3 In the example, the first spatial plane is P1, the second spatial plane is P2, and the normal vector angle between P1 and P2 is Distance variance d std , the maximum distance difference d diff_max . n1 is the normal vector of the first space plane, and n2 is the normal vector of the second space plane.

[0115] When fitting the spatial plane, the first point cloud and the second point cloud can be plane-fitted using the Ransac algorithm, and the normal vectors of the first spatial plane and the second spatial plane can be obtained.

[0116] When determining the average distance between the first spatial plane and the second spatial plane, for each point in the first spatial plane, the vertical distance from the point to the second spatial plane can be calculated to obtain the distance corresponding to the point. Then, the distances corresponding to all points in the first spatial plane are averaged to obtain the average distance between the first spatial plane and the second spatial plane. At the same time, the maximum distance difference between the minimum distance and the maximum distance and the distance variance are calculated.

[0117] When checking the roll angle and pitch angle between the first radar and the second radar, the distance threshold corresponding to the maximum distance difference and the distance variance threshold corresponding to the distance variance can be determined according to the preset normal vector angle threshold between the first spatial plane and the second spatial plane. Then, the normal vector angle between the first spatial plane and the second spatial plane is compared with the normal vector angle threshold to obtain a first verification result. The maximum distance difference between the first spatial plane and the second spatial plane is compared with the distance threshold to obtain a second verification result. The distance variance between the first spatial plane and the second spatial plane is compared with the distance variance threshold to obtain a third verification result.

[0118] If the first verification result, the second verification result, and the third verification result are all normal, it is determined that the roll angle and the pitch angle calibrated between the first radar and the second radar are normal. If there is an abnormality in the first verification result, the second verification result, and the third verification result, it is determined that the roll angle and the pitch angle calibrated between the first radar and the second radar are abnormal.

[0119] When checking the calibrated height translation distance between the first radar and the second radar, the average distance between the first spatial plane and the second spatial plane is compared with the average distance threshold to obtain a fourth verification result. If the fourth verification result is normal, it is determined that the calibrated height translation distance between the first radar and the second radar is normal; if the fourth verification result is abnormal, it is determined that the calibrated height translation distance between the first radar and the second radar is abnormal.

[0120] For the yaw angle degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the second filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud. The second filtering index includes the height interval of the point cloud point and the true normal vector of the plane perpendicular to the ground.

[0121] Specifically, according to the height interval corresponding to each point cloud point, the initial first point cloud and the initial second point cloud are respectively screened to obtain the screened initial first point cloud and the screened initial second point cloud. According to the normal vector of each point cloud point and the true normal vector perpendicular to the ground, the screened initial first point cloud and the screened initial second point cloud are respectively filtered to obtain the first point cloud and the second point cloud. Among them, the height interval is determined by the size of the plane perpendicular to the ground. The first point cloud and the second point cloud can be point clouds on a plane perpendicular to the ground, and the first point cloud and the second point cloud belong to the same plane.

[0122] In addition, the initial first point cloud and the initial second point cloud may be filtered according to the normal vector of each point cloud point and the true normal vector perpendicular to the ground to obtain the filtered initial first point cloud and the filtered initial second point cloud. Then, according to the height interval corresponding to the point cloud points, the filtered initial first point cloud and the filtered initial second point cloud are filtered to obtain the first point cloud and the second point cloud.

[0123] Taking the curb point cloud as an example, the point cloud in the plane perpendicular to the ground is filtered for the initial first point cloud, such as Figure 4 As shown. Figure 4 In the example, the point cloud of the curb between ground 1 and ground 2 is obtained. Since the laser emitted by the radar itself is at a certain angle, the points on the curb scanned by the radar are distributed in a diagonal line. In order to avoid the interference of the ground point cloud at the edge of the curb, the point cloud in the middle area of ​​the curb can be selected as the first point cloud, that is, the point cloud in the area covered by the dotted box.

[0124] In addition, when obtaining the first point cloud and the second point cloud, a pre-trained deep learning model can be used to extract the point cloud in the plane perpendicular to the ground to obtain the first point cloud and the second point cloud. The deep learning model can be a PointNet model, a PointCNN model, etc.

[0125] Then, each point in the first point cloud and each point in the second point cloud are converted to the same horizontal plane as the first horizontal plane. The first point cloud and the second point cloud are converted to the same horizontal plane to remove the characteristics of the roll angle, pitch angle and height translation distance of the point cloud and retain the yaw angle characteristics of the point cloud.

[0126] According to the first point cloud in the first horizontal plane, a first spatial straight line is fitted, and according to the second point cloud in the first horizontal plane, a second spatial straight line is fitted. According to the angle between the first spatial straight line and the second spatial straight line, an index deviation between the first point cloud and the second point cloud is determined as a second index deviation, wherein the second index deviation includes at least one of the difference between the angle between the first spatial straight line and the second spatial straight line, the slope between the first spatial straight line and the longitudinal direction of the horizontal plane, and the slope between the second spatial straight line and the longitudinal direction of the horizontal plane. According to the second index deviation, the yaw angles in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the degree of freedom combination.

[0127] The second indicator deviation takes the angle between the first spatial straight line and the second spatial straight line as an example, Figure 5 shown.

[0128] When verifying the yaw angle calibrated between the first radar and the second radar, the angle between the first space straight line and the second space straight line is compared with the preset angle threshold to obtain a fifth verification result. If the angle between the first space straight line and the second space straight line is greater than the preset angle threshold, it is determined that the yaw angle calibrated between the first radar and the second radar is abnormal; if the angle between the first space straight line and the second space straight line is not greater than the preset angle threshold, it is determined that the yaw angle calibrated between the first radar and the second radar is normal.

[0129] exist Figure 5 In the example, the first space straight line is L1, the second space straight line is L2, and the angle between the first space straight line and the second space straight line is

[0130] For the parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered according to the third filtering index to obtain the point cloud with the highest overlap rate in the first initial point cloud and the second initial point cloud as the first point cloud corresponding to the first radar and the second point cloud corresponding to the second radar. The third filtering index includes: the pre-calibrated height difference and horizontal distance difference between the first radar and the second radar, and the field viewing angle of each of the first radar and the second radar.

[0131] Specifically, according to the pre-calibrated height distance and horizontal distance between the first radar and the second radar and the field of view of the first radar and the second radar, the point cloud with the highest overlap rate between the initial first point cloud and the initial second point cloud is obtained as the first point cloud and the second point cloud. And the point cloud points in the first point cloud and the point cloud points in the second point cloud are converted to the same horizontal plane as the second horizontal plane.

[0132] The point cloud with the highest overlap rate between the first point cloud and the second point cloud is obtained to increase the probability of determining the same obstacle point from the point cloud with the highest overlap rate. The point cloud with the highest overlap rate is converted to the same horizontal plane to remove the characteristics of the roll angle, pitch angle and height translation distance of the point cloud and retain the horizontal plane characteristics of the point cloud.

[0133] Then, point cloud points of the same obstacle are determined from the first point cloud in the second horizontal plane and the second point cloud in the second horizontal plane, and the point cloud points of the same obstacle determined in the first point cloud are used as the first point cloud points, and the point cloud points of the same obstacle determined in the second point cloud are used as the second point cloud points. According to the first point cloud points and the second point cloud points, the index deviation between the first point cloud and the second point cloud is determined as the third index deviation. Among them, the third index deviation includes: the lateral translation distance difference between the first point cloud point and the second point cloud point, and the longitudinal translation distance difference between the first point cloud point and the second point cloud point. According to the third index deviation, the lateral translation distance and the longitudinal translation distance in the first point cloud and the second point cloud are verified to obtain the verification result corresponding to the degree of freedom combination.

[0134] When determining the point cloud points of the same obstacle from the first point cloud in the second horizontal plane and the second point cloud in the second horizontal plane, the point cloud point closest to the origin in the unified coordinate system is selected from the first point cloud as the initial first point cloud point, and the point cloud point closest to the origin in the unified coordinate system is selected from the second point cloud as the initial second point cloud point. According to the matching index between the initial first point cloud point and the initial second point cloud point, it is judged whether the initial first point cloud point and the initial second point cloud point belong to the same obstacle. Among them, the matching index includes: at least one of the distance between the initial first point cloud point and the initial second point cloud point, and the angle between the line connecting the initial first point cloud point and the origin and the line connecting the initial second point cloud point and the origin. If the initial first point cloud point and the initial second point cloud point belong to the same obstacle, the initial first point cloud point is used as the first point cloud point, and the initial second point cloud point is used as the second point cloud point. If the initial first point cloud point and the initial second point cloud point do not belong to the same obstacle, the verification of the lateral translation distance and the longitudinal translation distance between the first point cloud and the second point cloud in the parallel ground degree of freedom combination is skipped.

[0135] Specifically, according to the distance between the initial second point cloud point and the initial first point cloud point, and the angle between the line connecting the initial second point cloud point and the origin and the line connecting the initial first point cloud point and the origin, it is determined whether the initial second point cloud point and the initial first point cloud point are point cloud points of the same obstacle. If so, the initial first point cloud point is used as the first point cloud point, and the initial second point cloud point is used as the second point cloud point.

[0136] When verifying the lateral translation distance and the longitudinal translation distance in the first point cloud and the second point cloud according to the third indicator deviation, the lateral translation distance difference between the first point cloud point and the second point cloud point and the longitudinal translation distance difference between the first point cloud point and the second point cloud point are determined. According to the lateral translation distance difference, the preset lateral translation distance difference threshold, the longitudinal translation distance difference and the longitudinal translation distance difference threshold, the lateral translation distance and the longitudinal translation distance difference between the first point cloud point and the second point cloud point are verified. Figure 6 shown.

[0137] exist Figure 6 In , after determining the first point cloud point a and the second point cloud point b of the same obstacle, the lateral translation distance difference |X| between the first point cloud point a and the second point cloud point b is determined. diff and the difference in longitudinal translation distance |Y| diff .

[0138] In addition, when selecting the first point cloud point and the second point cloud point on the same obstacle, the first point cloud point and the second point cloud point of the same obstacle can be determined based on a point cloud matching algorithm before converting the first point cloud and the second point cloud to the same horizontal plane. The point cloud matching algorithm can be an ICP algorithm, etc.

[0139] When verifying the calibrated horizontal lateral translation distance and horizontal longitudinal translation distance between the first radar and the second radar, the horizontal lateral translation distance difference between the first point cloud point and the second point cloud point is compared with a preset lateral translation distance difference threshold to obtain a sixth verification result. The horizontal longitudinal translation distance difference between the first point cloud point and the second point cloud point is compared with a preset longitudinal translation distance difference threshold to obtain a seventh verification result.

[0140] If the horizontal lateral translation distance difference between the first point cloud point and the second point cloud point is greater than the preset lateral translation distance difference threshold, the calibration verification result of the horizontal lateral translation distance between the first radar and the second radar is determined to be abnormal. If the horizontal lateral translation distance difference between the first point cloud point and the second point cloud point is not greater than the preset lateral translation distance difference threshold, the calibration verification result of the horizontal lateral translation distance between the first radar and the second radar is determined to be normal. Similarly, if the horizontal longitudinal translation distance difference between the first point cloud point and the second point cloud point is greater than the preset longitudinal translation distance difference threshold, the calibration verification result of the horizontal longitudinal translation distance between the first radar and the second radar is determined to be abnormal. If the horizontal longitudinal translation distance difference between the first point cloud point and the second point cloud point is not greater than the preset longitudinal translation distance difference threshold, the calibration verification result of the horizontal longitudinal translation distance between the first radar and the second radar is determined to be normal.

[0141] S108: Controlling the unmanned equipment according to the verification result corresponding to each degree of freedom combination.

[0142] In the embodiment of the present specification, when the pre-calibrated external parameters between the first radar and the second radar are verified, the above steps S100 to S106 can be a process of verifying the external parameters between the first radar and the second radar once, and the verification results corresponding to each degree of freedom combination during the one verification are obtained.

[0143] In an embodiment of the present specification, a degree of freedom verification cycle can be pre-set, and the pre-calibrated external parameters between the first radar and the second radar can be verified multiple times in one degree of freedom verification cycle. For each verification, it can be determined whether there is an abnormality in the external parameters between the first radar and the second radar in this verification based on the verification results corresponding to each degree of freedom combination in this verification, that is, it can be determined whether the external parameters between the first radar and the second radar in this verification are accurate. According to the judgment result of each verification, the number of times the external parameters between the first radar and the second radar are verified to be abnormal in the degree of freedom verification cycle is determined. According to the number of times there are abnormalities, the control strategy of the unmanned equipment corresponding to the number of times there are abnormalities is determined, and the unmanned equipment is controlled based on the control strategy.

[0144] When judging whether there is an abnormality in the external parameters between the first radar and the second radar in this calibration, for each calibration, when there is an abnormal calibration result in the calibration results corresponding to each degree of freedom combination in this calibration, it is determined that there is an abnormality in the external parameters between the first radar and the second radar in this calibration.

[0145] When determining the control strategy of the unmanned device corresponding to the number of abnormalities, if the number of abnormalities in the external parameters between the first radar and the second radar is not greater than the number threshold, the first control strategy of the unmanned device is determined, and the unmanned device is controlled according to the first control strategy so that the unmanned device continues to be in the state of automatic driving. If the number of abnormalities in the external parameters between the first radar and the second radar is greater than the number threshold, the second control strategy of the unmanned device is determined, and the unmanned device is controlled according to the second control strategy so that the unmanned device pulls over and slowly stops moving. Among them, the first control strategy can be to control the unmanned device to maintain the current motion state of the unmanned device for driving, and the second control strategy can be to control the unmanned device to pull over and slowly stop moving.

[0146] For example, if the degree of freedom verification cycle is 120s and one verification is 1s, 120 verifications are required in the degree of freedom verification cycle. The preset number threshold is 80. If the number of abnormalities between the first radar and the second radar is 85, the second control strategy of the unmanned device is used, and the unmanned device slowly stops moving to the side.

[0147] In addition, when an abnormality is found in the external parameters between the first radar and the second radar for a continuous preset number of times in the degree of freedom verification cycle, the unmanned equipment is controlled based on the second control strategy corresponding to the abnormality of the verification results for the continuous preset number of times, so that the unmanned equipment pulls to the side and slowly stops moving.

[0148] For example, if the degree of freedom verification cycle is 100s and one verification is 1s, 100 verifications are required in the degree of freedom verification cycle. If the external parameters between the first radar and the second radar are abnormal for 10 consecutive times, the second control strategy of the unmanned device is determined when the abnormality is determined for 10 consecutive times, and the unmanned device is controlled to make the unmanned device move to the side and slowly stop.

[0149] In addition, for the verification results corresponding to the index deviation between the first point cloud and the second point cloud determined in each free combination, the verification results may include normal and abnormal. Among them, the normal verification results may be subdivided into multiple verification results within the normal range, and the multiple verification results may include: excellent, good, ordinary and near abnormal, etc. In this way, the change law of the verification results of the external parameters calibrated between the first radar and the second radar can be monitored, so as to re-formulate the verification cycle.

[0150] When the normal verification results are subdivided, the normal threshold interval can be determined for each degree of freedom combination according to the threshold value corresponding to the normal verification result of the degree of freedom combination. Then, the normal threshold interval is divided into equal intervals to obtain different threshold sub-intervals, wherein each threshold sub-interval corresponds to a verification result in the normal range. Finally, according to each threshold sub-area and the indicator deviation between the first point cloud and the second point cloud under the degree of freedom combination, the indicator deviation between the first point cloud and the second point cloud is verified to obtain the verification result under the degree of freedom combination. At this time, the verification results under the degree of freedom combination may include: excellent, good, ordinary, near abnormal, abnormal, etc.

[0151] When re-establishing the calibration cycle, for each degree of freedom combination, the variation rule of the calibration result corresponding to the degree of freedom combination in the preset degree of freedom calibration cycle can be determined to obtain the variation rule of the calibration result corresponding to the degree of freedom combination. And according to the variation rule of the calibration result corresponding to each degree of freedom combination, the external parameter calibration cycle between the first radar and the second radar is determined. Based on the determined external parameter calibration cycle, the external parameters between the first radar and the second radar are re-calibrated.

[0152] Among them, the external parameter calibration period between the first radar and the second radar can be determined according to the change law of the verification results corresponding to all degree of freedom combinations, and based on the determined external parameter calibration period, the external parameters involved in all degree of freedom combinations between the first radar and the second radar are recalibrated.

[0153] In addition, for each degree of freedom combination, according to the change rule of the verification result corresponding to the degree of freedom combination, the external parameter calibration period for the degree of freedom combination between the first radar and the second radar can be determined, and based on the determined external parameter calibration period, the external parameters involved in the degree of freedom combination between the first radar and the second radar can be recalibrated.

[0154] For example, in the yaw angle degree of freedom combination, the calibration result of the yaw angle calibrated between the first radar and the second radar in the 5th degree of freedom calibration cycle is normal, the calibration result of the yaw angle calibrated between the first radar and the second radar in the 6th degree of freedom calibration cycle is near abnormal, and the calibration result of the yaw angle calibrated between the first radar and the second radar in the 7th degree of freedom calibration cycle is abnormal. In this case, the yaw angle between the first radar and the second radar can be recalibrated in the 6th degree of freedom calibration cycle to prevent the calibration result of the yaw angle calibrated between the first radar and the second radar from being abnormal.

[0155] Based on the above Figure 1 The unmanned equipment control method shown in the figure, the embodiment of this specification provides a schematic diagram of the calibration of the external parameters calibrated between the first radar and the second radar, such as Figure 7 shown.

[0156] Through the above Figure 1 It can be seen from the method shown that this specification obtains each degree of freedom combination and determines the area of ​​interest (i.e., point cloud area) corresponding to each degree of freedom combination. For each degree of freedom combination, according to the first point cloud in the area of ​​interest corresponding to the degree of freedom combination collected by the first radar of any two radars and the second point cloud in the area of ​​interest corresponding to the degree of freedom combination collected by the second radar of any two radars, and the external parameters between any two radars calibrated in advance, the first point cloud and the second point cloud are projected to the same coordinate system, and the index deviation between the first point cloud and the second point cloud is determined. Based on the index deviation, the verification result corresponding to the degree of freedom combination is determined. According to the verification result of each degree of freedom combination, the unmanned equipment is controlled. In this method, for each degree of freedom combination obtained after the external parameters of the two radars are decoupled, it can be determined whether there is an abnormality in the verification result of each degree of freedom combination between the two radars to verify whether the external parameters between the two radars are accurate, thereby ensuring the safety of the unmanned equipment.

[0157] Furthermore, in Figure 1In steps S100 to S104 shown, when the degrees of freedom in the degree-of-freedom combination calibrated between the first radar and the second radar are verified based on the difference between the global first point cloud and the global second point cloud in the degree-of-freedom combination, the filtering index corresponding to the degree-of-freedom combination can be determined for different degree-of-freedom combinations, and the global first point cloud and the global second point cloud are filtered according to the filtering index corresponding to the degree-of-freedom combination to obtain the first point cloud and the second point cloud corresponding to the degree-of-freedom combination.

[0158] In such Figure 1 In step S106 shown, for each degree of freedom combination, after filtering the initial first point cloud and the initial second point cloud to obtain the first point cloud and the second point cloud, it can be determined whether the number of point cloud points in the first point cloud and the number of point cloud points in the second point cloud are greater than the number threshold according to the number of point cloud points in the first point cloud and the second point cloud and the number threshold corresponding to the degree of freedom combination. If so, the first point cloud and the second point cloud are projected into a unified coordinate system according to the external parameters between the first radar and the second radar calibrated in advance, and the index deviation corresponding to the first point cloud and the second point cloud is determined. According to the index deviation, the verification result corresponding to the degree of freedom combination is determined. If not, there is no need to determine the verification result corresponding to the degree of freedom combination, that is, the verification of the degrees of freedom in the degree of freedom combination is skipped.

[0159] During the degree of freedom verification process for the first point cloud and the second point cloud, for the index deviation determined in each degree of freedom combination, determine whether the index deviation is greater than the index deviation abnormal threshold. The index deviation abnormal threshold can be the minimum threshold for abnormal changes in the index deviation due to abnormal acquisition of point cloud data. If so, there is no need to determine the verification result corresponding to the degree of freedom combination, that is, skip the verification of the degrees of freedom in the degree of freedom combination. If not, based on the external parameters between the first radar and the second radar that are pre-calibrated, project the first point cloud and the second point cloud into a unified coordinate system, and determine the index deviation corresponding to the first point cloud and the second point cloud. Based on the index deviation, determine the verification result corresponding to the degree of freedom combination.

[0160] In a preset degree of freedom verification cycle, when determining the number of times that an abnormality is detected in the external parameters between the first radar and the second radar during the degree of freedom verification cycle, for each verification in the degree of freedom verification cycle, if there is no verification result for each degree of freedom combination during the verification process (i.e., all are skipped), the verification is not recorded. If there is an abnormal verification result during the verification process, the number of abnormalities in the external parameters between the first radar and the second radar is increased by one. If there are normal verification results during the verification process, the number of normal external parameters between the first radar and the second radar is increased by one. The total number of verifications that obtain verification results during the degree of freedom verification cycle can be counted.

[0161] In addition, within the preset degree of freedom verification cycle, when the ratio between the number of times the external parameters between the first radar and the second radar are abnormal and the total number of verifications is greater than the first ratio threshold, the second control strategy is determined to control the unmanned device. When the ratio between the number of times the external parameters between the first radar and the second radar are abnormal and the number of times the external parameters between the first radar and the second radar are normal is greater than the second ratio threshold, the second control strategy is determined to control the unmanned device.

[0162] Based on the above judgment on whether to skip the degree of freedom check for each degree of freedom combination, and Figure 1 In step S108 shown in the figure, it is determined whether there is an abnormality in the external parameters calibrated between the first radar and the second radar during the degree of freedom verification period. The embodiment of this specification provides a schematic diagram of controlling an unmanned device, such as Figure 8 As shown, the present specification provides another schematic diagram of controlling unmanned equipment, such as Fig. 9 As shown. Among them, Figure 8 The strategy for controlling unmanned equipment is determined based on the total number of anomalies that occur during the degree of freedom check cycle. Fig. 9 The strategy for controlling unmanned equipment is determined based on a continuous preset number of times.

[0163] The above is the unmanned equipment control method provided in the embodiments of this specification. Based on the same idea, this specification also provides corresponding devices, storage media and electronic devices.

[0164] Fig.10 A schematic diagram of the structure of an unmanned equipment control device provided in an embodiment of this specification, the device comprising:

[0165] The acquisition module 1001 is used to acquire point cloud data collected by each radar installed on the unmanned equipment and determine the combination of each degree of freedom;

[0166] The region determination module 1002 is used to select any two radars from the radars as the first radar and the second radar, and for each degree of freedom combination, determine a point cloud region corresponding to the degree of freedom combination for verifying the degree of freedom combination as the target region;

[0167] A point cloud determination module 1003 is used to determine point cloud data located in the target area from the point cloud data collected by the first radar as a first point cloud, and to determine point cloud data located in the target area from the point cloud data collected by the second radar as a second point cloud;

[0168] A verification result determination module 1004 is used to project the first point cloud and the second point cloud into a unified coordinate system according to the pre-calibrated external parameters between the first radar and the second radar, so as to determine the index deviation corresponding to the first point cloud and the second point cloud, and determine the verification result corresponding to the degree of freedom combination according to the index deviation;

[0169] The control module 1005 is used to control the unmanned equipment according to the verification result corresponding to each degree of freedom combination.

[0170] Optionally, the degree-of-freedom combinations include: a non-parallel ground degree-of-freedom combination, a yaw angle degree-of-freedom combination, and a parallel ground degree-of-freedom combination; the non-parallel ground degree-of-freedom combination includes a pitch angle, a roll angle, and a height translation distance, the yaw angle degree-of-freedom combination includes a yaw angle, and the parallel ground degree-of-freedom combination includes a lateral translation distance and a longitudinal translation distance in a horizontal plane.

[0171] Optionally, the area determination module 1002 is specifically used to crop the point cloud data collected by each radar for the non-parallel ground degree of freedom combination, and determine the point cloud area corresponding to the non-parallel ground degree of freedom combination for verifying the non-parallel ground degree of freedom combination; wherein the point cloud area corresponding to the non-parallel ground degree of freedom combination is the ground point cloud; for the yaw angle degree of freedom combination, the point cloud data collected by each radar is cropped to determine the point cloud area corresponding to the yaw angle degree of freedom combination for verifying the point cloud area corresponding to the yaw angle degree of freedom combination; wherein the point cloud area corresponding to the yaw angle degree of freedom combination is a point cloud area within a plane perpendicular to the ground; for the parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine the point cloud area corresponding to the parallel ground degree of freedom combination for verifying the parallel ground degree of freedom combination; wherein the point cloud area corresponding to the parallel ground degree of freedom combination is an obstacle point cloud.

[0172] Optionally, the point cloud determination module 1003 is specifically used to determine point cloud data located within the target area from the point cloud data collected by the first radar as a first initial point cloud, and to determine point cloud data located within the target area from the point cloud data collected by the second radar as a second initial point cloud; and to filter the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud.

[0173] Optionally, the point cloud determination module 1003 is specifically used to, for the non-parallel ground degree of freedom combination, filter the first initial point cloud and the second initial point cloud respectively according to the first filtering index corresponding to each point cloud point, to obtain the first point cloud and the second point cloud; wherein the first filtering index includes the height threshold of the point cloud point and the ground true normal vector.

[0174] Optionally, the point cloud determination module 1003 is specifically used to filter the first initial point cloud and the second initial point cloud respectively according to the second filtering index corresponding to each point cloud point for the yaw angle degree of freedom combination, so as to obtain the first point cloud and the second point cloud; wherein the second filtering index includes the height range of the point cloud point and the true normal vector of the plane perpendicular to the ground.

[0175] Optionally, the point cloud determination module 1003 is specifically used to filter the first initial point cloud and the second initial point cloud according to a third filtering index for a parallel ground degree of freedom combination, and obtain the point cloud with the highest overlap rate between the first initial point cloud and the second initial point cloud as the first point cloud corresponding to the first radar and the second point cloud corresponding to the second radar; wherein the third filtering index includes: the pre-calibrated height difference and horizontal distance difference between the first radar and the second radar, and the field viewing angles of the first radar and the second radar respectively.

[0176] Optionally, the verification result determination module 1004 is specifically used to fit a first spatial plane based on the first point cloud, and to fit a second spatial plane based on the second point cloud; determine at least one index deviation between the first point cloud and the second point cloud based on the first spatial plane and the second spatial plane; the at least one index deviation includes: the normal vector angle between the first spatial plane and the second spatial plane, the average distance between the first spatial plane and the second spatial plane, the distance variance, and the maximum distance difference, the maximum distance difference being the difference between the maximum distance and the minimum distance between the first spatial plane and the second spatial plane; based on the at least one index deviation and the preset thresholds corresponding to each index deviation, the roll angle, pitch angle and height translation distance in the first point cloud and the second point cloud are verified to obtain the verification result corresponding to the non-parallel ground degree of freedom combination.

[0177] Optionally, the verification result determination module 1004 is specifically used to convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the first horizontal plane; fit a first spatial straight line according to the first point cloud in the first horizontal plane, and fit a second spatial straight line according to the second point cloud in the first horizontal plane; determine an index deviation between the first point cloud and the second point cloud according to the first spatial straight line and the second spatial straight line, the index deviation including: the angle between the first spatial straight line and the second spatial straight line; based on the index deviation, verify the yaw angles in the first point cloud and the second point cloud to obtain a verification result corresponding to the degree of freedom combination.

[0178] Optionally, the verification result determination module 1004 is specifically used to convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the second horizontal plane; determine the point cloud points of the same obstacle from the first point cloud and the second point cloud in the second horizontal plane, and use the point cloud points of the same obstacle determined in the first point cloud as the first point cloud points, and use the point cloud points of the same obstacle determined in the second point cloud as the second point cloud points; determine the index deviation between the first point cloud and the second point cloud based on the first point cloud points and the second point cloud points; the index deviation includes: the lateral translation distance difference between the first point cloud point and the second point cloud point, and the longitudinal translation distance difference between the first point cloud point and the second point cloud point; based on the index deviation, verify the lateral translation distance and the longitudinal translation distance in the first point cloud and the second point cloud to obtain the verification result corresponding to the degree of freedom combination.

[0179] Optionally, the verification result determination module 1004 is specifically used to select a point cloud point closest to the origin in the unified coordinate system from the first point cloud as an initial first point cloud point, and to select a point cloud point closest to the origin in the unified coordinate system from the second point cloud as an initial second point cloud point; based on a matching index between the initial first point cloud point and the initial second point cloud point, determine whether the initial first point cloud point and the initial second point cloud point belong to the same obstacle, and the matching index includes: at least one of the distance between the initial first point cloud point and the initial second point cloud point, and the angle between the line connecting the initial first point cloud point and the origin and the line connecting the initial second point cloud point and the origin; if the initial first point cloud point and the initial second point cloud point belong to the same obstacle, use the initial first point cloud point as the first point cloud point and the initial second point cloud point as the second point cloud point.

[0180] Optionally, the control module 1005 is specifically used to, for each verification in a preset degree of freedom verification cycle, determine whether there is an abnormality in the external parameters between the first radar and the second radar in the verification according to the verification results corresponding to each degree of freedom combination in the verification; determine the number of times that abnormalities are found in the external parameters between the first radar and the second radar in the degree of freedom verification cycle according to the judgment results of each verification; determine the control strategy of the unmanned equipment corresponding to the number of times according to the number, and control the unmanned equipment based on the control strategy.

[0181] Optionally, the control module 1005 is specifically used to control the unmanned equipment based on a control strategy corresponding to abnormal verification results for the consecutive preset number of times when an abnormality is found in the external parameters between the first radar and the second radar during the degree of freedom verification cycle.

[0182] The device further includes: a calibration module 1006;

[0183] The calibration module 1006 is used to determine, for each degree of freedom combination, a change rule of the verification result corresponding to the degree of freedom combination in a preset degree of freedom verification period, and obtain the change rule of the verification result corresponding to the degree of freedom combination; determine the external parameter calibration period between the first radar and the second radar according to the change rule of the verification result corresponding to each degree of freedom combination, and re-calibrate the external parameters between the first radar and the second radar based on the external parameter calibration period.

[0184] This specification also provides a computer-readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, it can be used to perform the above Figure 1 An unmanned equipment control method is provided.

[0185] based on Figure 1 The unmanned equipment control method shown in the present specification also provides Fig.11 The structural diagram of the electronic device shown in FIG. Fig.11 At the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 The unmanned equipment control method.

[0186] Of course, in addition to software implementation, this specification does not exclude other implementation methods, such as logic devices or a combination of software and hardware, etc., that is to say, the executor of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0187] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0188] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0189] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0190] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0191] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0192] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0193] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0194] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0195] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0196] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0197] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0198] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0199] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0200] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0201] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0202] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A method for controlling unmanned equipment, characterized in that: include: Obtain point cloud data collected by each radar installed on the unmanned equipment, and determine the combination of each degree of freedom; Randomly select two radars from the radars as the first radar and the second radar, and for each degree of freedom combination, determine a point cloud area corresponding to the degree of freedom combination for verifying the degree of freedom combination as the target area; Determine point cloud data located within the target area from the point cloud data collected by the first radar as a first point cloud, and determine point cloud data located within the target area from the point cloud data collected by the second radar as a second point cloud; Projecting the first point cloud and the second point cloud into a unified coordinate system according to the pre-calibrated external parameters between the first radar and the second radar to determine an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation; Controlling the unmanned equipment according to the verification result corresponding to each degree of freedom combination; The degree of freedom combinations include: a non-parallel ground degree of freedom combination, a yaw angle degree of freedom combination, and a parallel ground degree of freedom combination; The non-parallel ground degree of freedom combination includes a pitch angle, a roll angle and a height translation distance; the yaw angle degree of freedom combination includes a yaw angle; the parallel ground degree of freedom combination includes a lateral translation distance and a longitudinal translation distance of a horizontal plane; For each degree of freedom combination, determine the point cloud area corresponding to the degree of freedom combination for verifying the point cloud area, including: For the non-parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the non-parallel ground degree of freedom combination for verifying the point cloud area corresponding to the non-parallel ground degree of freedom combination is a ground point cloud; For the yaw angle degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the yaw angle degree of freedom combination for verifying the point cloud area corresponding to the yaw angle degree of freedom combination is a point cloud area in a plane perpendicular to the ground; For the parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine the point cloud area corresponding to the parallel ground degree of freedom combination for verifying the point cloud area corresponding to the parallel ground degree of freedom combination is an obstacle point cloud.

2. The method according to claim 1, characterized in that Determining point cloud data located in the target area from the point cloud data collected by the first radar as a first point cloud, and determining point cloud data located in the target area from the point cloud data collected by the second radar as a second point cloud, specifically includes: Determine point cloud data located in the target area from the point cloud data collected by the first radar as a first initial point cloud, and determine point cloud data located in the target area from the point cloud data collected by the second radar as a second initial point cloud; The first initial point cloud and the second initial point cloud are filtered to obtain the first point cloud and the second point cloud.

3. The method according to claim 2, characterized in that Filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes: For the non-parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the first filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud; wherein the first filtering index includes the height threshold of the point cloud point and the ground true normal vector.

4. The method according to claim 2, characterized in that Filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes: For the yaw angle degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered respectively according to the second filtering index corresponding to each point cloud point to obtain the first point cloud and the second point cloud; wherein the second filtering index includes the height range of the point cloud point and the true normal vector of the plane perpendicular to the ground.

5. The method according to claim 2, characterized in that Filtering the first initial point cloud and the second initial point cloud to obtain the first point cloud and the second point cloud specifically includes: For the parallel ground degree of freedom combination, the first initial point cloud and the second initial point cloud are filtered according to the third filtering index to obtain the point cloud with the highest overlap rate between the first initial point cloud and the second initial point cloud, which are used as the first point cloud corresponding to the first radar and the second point cloud corresponding to the second radar; wherein the third filtering index includes: the pre-calibrated height difference and horizontal distance difference between the first radar and the second radar, and the field viewing angles of the first radar and the second radar respectively.

6. The method according to claim 3, characterized in that Determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes: Fitting a first spatial plane according to the first point cloud, and fitting a second spatial plane according to the second point cloud; Determine at least one index deviation between the first point cloud and the second point cloud according to the first spatial plane and the second spatial plane; the at least one index deviation includes: a normal vector angle between the first spatial plane and the second spatial plane, an average distance between the first spatial plane and the second spatial plane, a distance variance, and a maximum distance difference, wherein the maximum distance difference is a difference between a maximum distance and a minimum distance between the first spatial plane and the second spatial plane; According to the at least one indicator deviation and the preset threshold values ​​corresponding to the indicator deviations, the roll angle, pitch angle and height translation distance in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the non-parallel ground degree of freedom combination.

7. The method according to claim 4, characterized in that Determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes: Convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the first horizontal plane; Fitting a first spatial straight line according to the first point cloud in the first horizontal plane, and fitting a second spatial straight line according to the second point cloud in the first horizontal plane; Determine an index deviation between the first point cloud and the second point cloud according to the first space straight line and the second space straight line, the index deviation comprising: an angle between the first space straight line and the second space straight line; According to the index deviation, the yaw angles in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the degree of freedom combination.

8. The method according to claim 5, characterized in that Determining an index deviation corresponding to the first point cloud and the second point cloud, and determining a verification result corresponding to the degree of freedom combination according to the index deviation, specifically includes: Convert each point cloud point in the first point cloud and each point cloud point in the second point cloud to the same horizontal plane as the second horizontal plane; Determine point cloud points of the same obstacle from the first point cloud and the second point cloud in the second horizontal plane, and use the point cloud points of the same obstacle determined in the first point cloud as first point cloud points, and use the point cloud points of the same obstacle determined in the second point cloud as second point cloud points; Determine an index deviation between the first point cloud and the second point cloud according to the first point cloud point and the second point cloud point; the index deviation includes: a lateral translation distance difference between the first point cloud point and the second point cloud point, and a longitudinal translation distance difference between the first point cloud point and the second point cloud point; According to the index deviation, the lateral translation distance and the longitudinal translation distance in the first point cloud and the second point cloud are verified to obtain a verification result corresponding to the degree of freedom combination.

9. The method according to claim 8, characterized in that Determining point cloud points of the same obstacle from the first point cloud and the second point cloud in the second horizontal plane specifically includes: Selecting a point cloud point closest to the origin in the unified coordinate system from the first point cloud as an initial first point cloud point, and selecting a point cloud point closest to the origin in the unified coordinate system from the second point cloud as an initial second point cloud point; Determining whether the initial first point cloud point and the initial second point cloud point belong to the same obstacle according to a matching index between the initial first point cloud point and the initial second point cloud point, wherein the matching index includes at least one of a distance between the initial first point cloud point and the initial second point cloud point, and an angle between a line connecting the initial first point cloud point and the origin and a line connecting the initial second point cloud point and the origin; If the initial first point cloud point and the initial second point cloud point belong to the same obstacle, the initial first point cloud point is used as the first point cloud point, and the initial second point cloud point is used as the second point cloud point.

10. The method according to claim 1, characterized in that According to the verification results corresponding to each degree of freedom combination, the unmanned equipment is controlled, specifically including: For each calibration in a preset degree of freedom calibration cycle, judging whether there is an abnormality in the external parameters between the first radar and the second radar in the calibration according to the calibration results corresponding to each degree of freedom combination in the calibration; According to the judgment result of each verification, determining the number of times that an abnormality is detected in the external parameter between the first radar and the second radar in the degree of freedom verification cycle; According to the number of times, a control strategy for the unmanned equipment corresponding to the number of times is determined, and based on the control strategy, the unmanned equipment is controlled.

11. The method according to claim 10, characterized in that The method further comprises: When an abnormality is found in the external parameters between the first radar and the second radar for a consecutive preset number of times in the degree of freedom verification cycle, the unmanned equipment is controlled based on a control strategy corresponding to the abnormality of the verification results for the consecutive preset number of times.

12. The method according to any one of claims 1 to 11, characterized in that: The method further comprises: For each degree of freedom combination, determine the change rule of the verification result corresponding to the degree of freedom combination in a preset degree of freedom verification cycle, and obtain the change rule of the verification result corresponding to the degree of freedom combination; According to a change rule of the verification result corresponding to each degree of freedom combination, an extrinsic parameter calibration period between the first radar and the second radar is determined, and based on the extrinsic parameter calibration period, the extrinsic parameters between the first radar and the second radar are recalibrated.

13. An unmanned equipment control device, characterized in that: include: An acquisition module is used to acquire point cloud data collected by various radars installed on unmanned equipment and determine the combination of various degrees of freedom; A region determination module is used to select any two radars from the radars as the first radar and the second radar, and for each degree of freedom combination, determine a point cloud region corresponding to the degree of freedom combination for verifying the degree of freedom combination as a target region; a point cloud determination module, configured to determine point cloud data located within the target area from the point cloud data collected by the first radar as a first point cloud, and to determine point cloud data located within the target area from the point cloud data collected by the second radar as a second point cloud; a verification result determination module, configured to project the first point cloud and the second point cloud into a unified coordinate system according to the pre-calibrated external parameters between the first radar and the second radar, so as to determine an index deviation corresponding to the first point cloud and the second point cloud, and determine a verification result corresponding to the degree of freedom combination according to the index deviation; A control module, used for controlling the unmanned equipment according to the verification result corresponding to each degree of freedom combination; The degree of freedom combinations include: a non-parallel ground degree of freedom combination, a yaw angle degree of freedom combination, and a parallel ground degree of freedom combination; The non-parallel ground degree of freedom combination includes a pitch angle, a roll angle and a height translation distance; the yaw angle degree of freedom combination includes a yaw angle; the parallel ground degree of freedom combination includes a lateral translation distance and a longitudinal translation distance of a horizontal plane; For each degree of freedom combination, determine the point cloud area corresponding to the degree of freedom combination for verifying the point cloud area, including: For the non-parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the non-parallel ground degree of freedom combination for verifying the point cloud area corresponding to the non-parallel ground degree of freedom combination is a ground point cloud; For the yaw angle degree of freedom combination, the point cloud data collected by each radar is cropped to determine a point cloud area corresponding to the yaw angle degree of freedom combination for verifying the point cloud area corresponding to the yaw angle degree of freedom combination is a point cloud area in a plane perpendicular to the ground; For the parallel ground degree of freedom combination, the point cloud data collected by each radar is cropped to determine the point cloud area corresponding to the parallel ground degree of freedom combination for verifying the point cloud area corresponding to the parallel ground degree of freedom combination is an obstacle point cloud.

14. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

15. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method described in any one of claims 1 to 12 is implemented.

Images