Abnormal positioning processing method and device, storage medium and electronic equipment

Abstract

The application discloses an abnormal positioning processing method and device, a storage medium and an electronic device, and relates to the field of robot vision. First, a positioning instruction is responded to, and it is judged whether an abnormal positioning scene exists at present. Then, if the abnormal positioning scene exists, a normal positioning unit in a positioning unit is determined according to the abnormal positioning scene. Finally, if at least one normal positioning unit exists, positioning is performed according to data output by the normal positioning unit. Since positioning abnormalities may occur if the robot directly performs positioning after the abnormal positioning scene exists, remedial measures can be taken in time, that is, the normal positioning unit is determined, and positioning is performed through the data output by the normal positioning unit, so that the accuracy of the positioning data of the robot can be ensured, and the operation safety of the robot is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of robot vision, and in particular to an abnormal positioning processing method and device, a storage medium, and an electronic device. BACKGROUND

[0002] With the rapid development of science and technology, more and more robots that facilitate service provision to users begin to appear in the field of vision of various industries. In the related art, when the positioning of a robot is abnormal, no timely remedial measures are taken, resulting in a large error in the positioning data of the robot. SUMMARY

[0003] The present application provides an abnormal positioning processing method and device, a storage medium, and an electronic device, which can solve the technical problem that in the related art, when the positioning of a robot is abnormal, no timely remedial measures are taken, resulting in a large error in the positioning data of the robot.

[0004] In a first aspect, an embodiment of the present application provides an abnormal positioning processing method, which comprises:

[0005] In response to a positioning instruction, determining whether an abnormal positioning scenario exists at present;

[0006] If the abnormal positioning scenario exists, determining a normal positioning unit in a positioning unit according to the abnormal positioning scenario;

[0007] If at least one normal positioning unit exists, positioning according to data output by the normal positioning unit.

[0008] In a second aspect, an embodiment of the present application provides an abnormal positioning processing device, which comprises:

[0009] An abnormal positioning determination module, configured to determine whether an abnormal positioning scenario exists at present in response to a positioning instruction;

[0010] A positioning unit determination module, configured to determine a normal positioning unit in a positioning unit according to the abnormal positioning scenario if the abnormal positioning scenario exists;

[0011] A positioning module, configured to position according to data output by the normal positioning unit if at least one normal positioning unit exists.

[0012] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are adapted to be loaded by a processor and execute the steps of the above method.

[0013] In a fourth aspect, an embodiment of the present application provides an electronic device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0014] The technical scheme provided by some embodiments of the present application has at least the following beneficial effects:

[0015] The present application provides an abnormal positioning processing method. First, a positioning instruction is responded to, and it is determined whether there is an abnormal positioning scene at present. Then, if there is an abnormal positioning scene, a normal positioning unit in a positioning unit is determined according to the abnormal positioning scene. Finally, if there is at least one normal positioning unit, positioning is performed according to data output by the normal positioning unit. Since positioning will be abnormal if the robot directly performs positioning after the existence of an abnormal positioning scene, remedial measures can be taken in time, that is, a normal positioning unit is determined, and positioning is performed through data output by the normal positioning unit, which can ensure the accuracy of the positioning data of the robot and improve the operation safety of the robot. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical scheme in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0017] Figure 1 An exemplary system architecture diagram of an abnormal positioning processing method provided by an embodiment of the present application;

[0018] Figure 2 A robot structure schematic diagram of an abnormal positioning processing method provided by an embodiment of the present application;

[0019] Figure 3 A flowchart of an abnormal positioning processing method provided by an embodiment of the present application;

[0020] Figure 4 A flowchart of an abnormal positioning method provided by another embodiment of the present application;

[0021] Figure 5 A flowchart of an abnormal positioning method provided by another embodiment of the present application;

[0022] Figure 6 A structure schematic diagram of an abnormal positioning processing device provided by another embodiment of the present application;

[0023] Figure 7 A structure schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to make the features and advantages of the present application more apparent and easy to understand, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0025] Figure 1 An exemplary system architecture diagram of an abnormal positioning processing method provided by the embodiments of the present application.

[0026] As shown in Figure 1 , the system architecture can include an electronic device 101, a network 102 and a server 103. The network 102 is used to provide a communication link medium between the electronic device 101 and the server 103. The network 102 can include various types of wired communication links or wireless communication links, for example, the wired communication links include optical fiber, twisted pair or coaxial cable, and the wireless communication links include Bluetooth communication link, Wireless-Fidelity (Wi-Fi) communication link or microwave communication link, etc.

[0027] The electronic device 101 can interact with the server 103 through the network 102 to receive messages from the server 103 or send messages to the server 103. The electronic device 101 can be hardware or software. When the electronic device 101 is hardware, it can be various electronic devices including but not limited to smart robots, smart watches, smart phones, tablet computers, laptop computers and desktop computers, etc. When the electronic device 101 is software, it can be installed in the above-mentioned listed electronic devices, which can be implemented as multiple software or software modules (for example, used to provide distributed services) or as a single software or software module, which is not specifically limited here.

[0028] The server 103 can be a service server providing various services. It should be noted that the server 103 can be hardware or software. When the server 103 is hardware, it can be implemented as a distributed server cluster composed of multiple servers or as a single server. When the server 103 is software, it can be implemented as multiple software or software modules (for example, used to provide distributed services) or as a single software or software module, which is not specifically limited here.

[0029] It should be understood that Figure 1 the number of electronic devices, networks and servers in is only illustrative, and can be any number of electronic devices, networks and servers according to the needs of implementation.

[0030] For the convenience of description, the electronic device is taken as a robot as an example for introduction below.

[0031] Please refer to Figure 2 , Figure 2 A schematic diagram of a robot structure of an abnormal positioning processing method provided by the embodiment of the application.

[0032] As Figure 2 shown, the robot 200 can at least include a laser radar 201, a motor encoder 202, a processor 203, a robot joint 204, and a power supply 205, wherein:

[0033] The laser radar 201 can be considered as a radar positioning unit in the application. The laser radar 201 can obtain a timestamp of each frame of radar data and point cloud data in a radar coordinate system for each timestamp at any time. The timestamp of each frame of radar data can be understood as the data acquisition frequency of the laser radar in a preset period. For example, 10 frames of radar data are obtained within a preset period from the current frame to the next second. The timestamp corresponding to each frame of radar data is 0.1 seconds, that is, the point cloud data in the radar coordinate system is obtained every 0.1 seconds in the preset period.

[0034] It can be understood that the laser radar 201 in the embodiment can not be limited to a multi-line laser radar or a single-line laser radar. The points in the point cloud data obtained by the multi-line laser radar can be represented as (x, y, z), and the points in the first point cloud data obtained by the single-line laser radar can be represented as (x, y).

[0035] When the laser radar 201 is a multi-line laser radar, it can be specifically a millimeter wave radar. In addition to providing x, y, and z coordinate information of the point cloud, the millimeter wave radar can also provide velocity information of the moving point. The coordinate information of the point cloud provided by the millimeter wave radar is equivalent to the three-dimensional point cloud coordinate information of the multi-line laser radar. Therefore, the advantages of the millimeter wave radar over the general multi-line laser radar are strong anti-interference capability, low cost, and can be used in harsh indoor and outdoor environments.

[0036] In addition, the robot in the embodiment of the application can be a legged robot or a wheeled robot. The wheel odometer in the wheeled robot can only provide 3dof odometer information, that is, (x, y, yaw), while the leg odometer in the legged robot can provide 6dof odometer information, that is, (x, y, z, roll, pitch, yaw). Therefore, the abnormal positioning processing method in the embodiment of the application can cover the application range of the legged robot and the wheeled robot.

[0037] The foot-type odometer in the foot-type robot can be considered as a motion positioning unit. The foot-type odometer can obtain the pose offset amount through the motor encoder 202. Specifically, the motor encoder 202 can obtain the three-dimensional pose offset amount in the foot-type robot coordinate system corresponding to each timestamp of the laser radar 201. For example, referring to the above-mentioned 10 frames of radar data obtained within the preset time period of the current frame and the next second, the motor encoder 202 obtains the three-dimensional pose offset amount in the foot-type robot coordinate system every 0.1 second. It can be understood that each three-dimensional pose offset amount obtained by the motor encoder 202 can be represented as (x, y, z, θ).

[0038] In addition, the motor encoder 202 in the embodiment can also be replaced by a motor encoder and an inertial sensor. Since the attitude angle error obtained by the motor encoder is large, the inertial sensor can be introduced to correct the attitude angle obtained by the motor encoder, and the three-dimensional pose offset amount obtained through Kalman filtering can be represented as (x, y, z, roll, pitch, yaw).

[0039] The processor 203 can generate a point cloud grid map according to the plurality of three-dimensional pose offset amounts obtained by the motor encoder 202 and the point cloud data corresponding to each three-dimensional pose offset amount, and control the robot joint 204 to rotate in combination with the operation instruction obtained by the foot-type robot. For example, the processor 203 can send the point cloud grid map to the foot-type robot control terminal after generating the point cloud grid map, receive the operation instruction sent by the foot-type robot control terminal, and control the robot joint 204 to perform forward or backward operation according to the operation instruction.

[0040] The power supply 205 can be used to supply power to the laser radar 201, the motor encoder 202, the processor 203, and the robot joint 204, respectively.

[0041] It should be noted that the abnormal positioning processing method proposed in the present application can not be limited to the field of robots mentioned above, and can also be applied to the field of automatic driving or visual analysis.

[0042] For the convenience of description, the electronic device is taken as a foot-type robot, the laser radar is taken as a multi-line laser radar, and the processor in the foot-type robot is taken as an execution body to describe the abnormal positioning processing method in detail.

[0043] Please refer to Figure 3 , Figure 3 A flowchart of an abnormal positioning processing method provided by the embodiment of the present application.

[0044] As Figure 3 shown, the method comprises:

[0045] S301, in response to the positioning instruction, determining whether there is an abnormal positioning scene at present.

[0046] For the robot, during the operation of the robot, the current positioning information of the robot may need to be obtained at any time, so that the processor of the robot controls the joints of the robot to advance or retreat according to the positioning information and the point cloud grid map.

[0047] Therefore, after the processor receives the positioning instruction, that is, at this time, the robot needs to be positioned, the processor can respond to the positioning instruction and determine whether the robot has an abnormal positioning before positioning according to the related data, so that the processor takes relevant measures to ensure that the robot obtains accurate related data for positioning, so as to ensure that the robot is positioned accurately. The positioning instruction can be sent by the control end of the robot, for example, when the administrator of the robot needs to obtain the positioning information of the robot, the positioning instruction can be sent to the robot to make the robot position based on the positioning instruction; The positioning instruction can also be a positioning instruction generated by the robot during movement, so that the robot can obtain the current positioning information at any time during movement, ensuring the safety of the robot.

[0048] It can be understood that if the robot has an abnormal positioning, one possible situation is that the positioning unit in the robot can normally collect data, but due to changes in the external environment of the robot, abnormalities, or the components or structures of the robot itself cannot work normally, that is, the robot currently has an abnormal positioning scene, and due to the limitation of the specific method used by the robot during positioning, the positioning unit in the robot can normally collect data, but the data output by the positioning unit in the robot cannot be positioned. Therefore, one feasible method for determining whether the robot has an abnormal positioning before positioning is to determine whether the robot currently has an abnormal positioning scene after responding to the positioning instruction.

[0049] The method for determining whether the robot currently has an abnormal positioning scene can not be limited, and one feasible determination idea can be that since the limitation of the specific method used by the robot during positioning causes the positioning unit in the robot to normally collect data, but the data output by the positioning unit in the robot cannot be positioned, in the embodiment of the present application, the method for determining whether there is an abnormal positioning scene is related to the specific method for positioning according to the data output by the positioning unit in the embodiment of the present application.

[0050] S302, if there is an abnormal positioning scene, determining the normal positioning unit in the positioning unit according to the abnormal positioning scene.

[0051] Since there are multiple positioning units in the robot, the data output by one or more positioning units in the robot can not be used for positioning, and there can be more than one abnormal positioning scenario. Therefore, after determining whether there is an abnormal positioning scenario, if there is an abnormal positioning scenario, it can be determined that there is only one abnormal positioning scenario, or there can be multiple abnormal positioning scenarios. However, regardless of whether there is one or multiple abnormal positioning scenarios, it can be determined that there is at least one positioning unit whose output data cannot be used for positioning.

[0052] One possible implementation is to determine the specific positioning unit whose output data cannot be used for positioning according to the abnormal positioning scenario. This positioning unit can be considered as an abnormal positioning unit. It is worth noting that the data output by the abnormal positioning unit can only be unusable in a certain step of the robot positioning process, but does not affect the use of the data output by the abnormal positioning unit in other steps of the robot positioning process.

[0053] Therefore, after determining the abnormal positioning unit, the normal positioning unit currently existing in the robot can be determined according to all the positioning units used in the robot and the abnormal positioning unit.

[0054] S303, if there is at least one normal positioning unit, positioning is performed according to the data output by the normal positioning unit.

[0055] After determining the normal positioning unit currently existing in the robot, the number of normal positioning units can be determined first. If there is at least one normal positioning unit, it can be determined that the data output by at least one positioning unit can be used for positioning of the robot. Therefore, the data output by the normal unit can be obtained for positioning.

[0056] The present application provides an abnormal positioning processing method. First, in response to a positioning instruction, it is determined whether there is an abnormal positioning scenario. Then, if there is an abnormal positioning scenario, the normal positioning unit in the positioning unit is determined according to the abnormal positioning scenario. Finally, if there is at least one normal positioning unit, positioning is performed according to the data output by the normal positioning unit. Since the robot will have positioning abnormalities if it directly performs positioning after an abnormal positioning scenario, remedial measures can be taken in time at this time, that is, the normal positioning unit is determined, and positioning is performed through the data output by the normal positioning unit, which can ensure the accuracy of the robot positioning data and improve the operation safety of the robot.

[0057] Please refer to Figure 4 , Figure 4 A flowchart of an abnormal positioning method provided by another embodiment of the present application is shown.

[0058] As Figure 4 shown, the method comprises:

[0059] S401, in response to the positioning instruction, determining whether an abnormal positioning scenario exists currently, wherein in the abnormal positioning scenario, an abnormal pose offset determined according to data output by a positioning unit corresponding to the abnormal positioning scenario cannot be used for positioning.

[0060] In the embodiment of the present application, when the processor performs positioning according to the data output by the positioning unit, specifically, a corresponding pose offset is determined according to the data output by the positioning unit, and then the positioning information of the robot is calculated based on the pose offset. Since in the embodiment of the present application, the method of determining whether an abnormal positioning scenario exists currently is related to the specific method of positioning according to the data output by the positioning unit in the embodiment of the present application, that is, the method of determining whether an abnormal positioning scenario exists currently is related to the determination of a corresponding pose offset according to the data output by the corresponding positioning unit in the current scenario.

[0061] Therefore, it can be determined in advance whether the determination of a corresponding pose offset according to the data output by the corresponding positioning unit in different positioning scenarios can be used for positioning. If the determination of a corresponding pose offset according to the data output by the corresponding positioning unit in one or more positioning scenarios cannot be used for positioning, these positioning scenarios can be determined as abnormal positioning scenarios. Then, after responding to the positioning instruction, one method of determining whether an abnormal positioning scenario exists currently is to identify the type or characteristics of the current positioning scenario according to the related data, and then determine whether the current positioning scenario is an abnormal positioning scenario. Then, in the abnormal positioning scenario, the abnormal pose offset determined according to the data output by the positioning unit corresponding to the abnormal positioning scenario cannot be used for positioning.

[0062] S402, if an abnormal positioning scenario exists, determining a normal positioning unit in the positioning unit according to the abnormal positioning scenario.

[0063] For step S402, refer to the description in S302, which will not be repeated here.

[0064] S403, if at least one normal positioning unit exists, determining a current normal pose offset according to the data output by the normal positioning unit, and performing positioning according to the normal pose offset.

[0065] In the embodiment of the present application, when the processor performs positioning according to the data output by the positioning unit, specifically, a corresponding pose offset is determined according to the data output by the positioning unit, and then the positioning information of the robot is calculated based on the pose offset. Therefore, if at least one normal positioning unit exists, a current normal pose offset can be determined according to the data output by the normal positioning unit, and positioning can be performed according to the normal pose offset.

[0066] Specifically, first, the first pose offset corresponding to the current timestamp and the second pose offset corresponding to the last timestamp can be determined according to the data output by the normal positioning unit, and the normal pose offset corresponding to the current timestamp can be determined according to the first pose offset and the second pose offset.

[0067] For example, when the data output by the normal positioning unit is three-dimensional pose data, in order to determine the expected pose of the current frame in the preset coordinate system according to the three-dimensional pose data, one timestamp can be set for each frame of three-dimensional pose data, so that the three-dimensional pose data of the current frame corresponds to the three-dimensional pose data of the current timestamp, and then the first three-dimensional pose data corresponding to the current timestamp and the second three-dimensional pose data corresponding to the last timestamp of the current timestamp can be obtained. Then, the three-dimensional pose data corresponding to the current timestamp (the first three-dimensional pose data) and the three-dimensional pose data corresponding to the last timestamp (the second three-dimensional pose data) are compared, and the normal pose offset corresponding to the current timestamp can be calculated. Since the three-dimensional pose data can also be represented as (x1, y1, z1, roll, pitch, yaw), the normal pose offset corresponding to the previous timestamp can include the offset of each component of x1, y1, z1, roll, pitch, and yaw.

[0068] Then, the expected pose corresponding to the current timestamp in the preset coordinate system can be determined according to the normal pose offset and the real pose corresponding to the last timestamp in the preset coordinate system.

[0069] For example, when the data output by the normal positioning unit is three-dimensional pose data, specifically, after determining the normal pose offset corresponding to the current timestamp, the real pose corresponding to the last timestamp in the preset coordinate system can be obtained, and then the real pose corresponding to the last timestamp in the preset coordinate system is added to the normal pose offset to obtain the expected pose corresponding to the current timestamp in the preset coordinate system.

[0070] Finally, the first point cloud data of the current frame point cloud data in the preset coordinate system is determined based on the expected pose, and the real pose of the current frame in the preset coordinate system is determined based on the first point cloud data.

[0071] For example, when the data output by the normal positioning unit is three-dimensional pose data, and the current frame point cloud data is two-dimensional point cloud data (the current frame point cloud data can also be three-dimensional point cloud data, which is not described here), specifically, in order to determine the real pose of the current frame robot in the preset coordinate system, one feasible implementation manner is to first determine the first two-dimensional point cloud data of the current frame two-dimensional point cloud data in the preset coordinate system based on the expected pose.

[0072] The two-dimensional point cloud data can include coordinates of a plurality of points generated based on a radar coordinate system. The radar coordinate system can be a two-dimensional rectangular coordinate system established with the center of the single-line laser radar as the origin. Each point included in the two-dimensional point cloud data can be represented as (x2, y2) in the radar coordinate system. The x2 and y2 can be understood as values corresponding to the x-axis and y-axis of each point in the two-dimensional point cloud data in the radar coordinate system. It can be understood that the radar coordinate system is not the same coordinate system as the above-mentioned foot-type robot coordinate system. There is an offset between the two coordinate systems, that is, the positions of the origins of the coordinate systems are different and the angles of the x-axis and y-axis planes in the coordinate systems are different. The processor in the foot-type robot can obtain the two-dimensional point cloud data of the current frame of the robot based on the single-line laser radar.

[0073] Since each three-dimensional pose data has corresponding two-dimensional point cloud data, that is, each frame of three-dimensional pose data of the robot has a corresponding relationship with each frame of two-dimensional point cloud data, after determining the expected pose of the current frame of the robot in the preset coordinate system according to the three-dimensional pose data, the expected pose is used as an intermediate, a transformation matrix is obtained according to the expected pose, the two-dimensional point cloud data of the current frame of the robot is obtained based on the single-line laser radar, and is transformed to the preset coordinate system to obtain transformed two-dimensional point cloud data. The transformed two-dimensional point cloud data can be regarded as the first two-dimensional point cloud data, that is, the first two-dimensional point cloud data of the current frame of two-dimensional point cloud data in the preset coordinate system is determined based on the expected pose. Since the expected pose is not the final real pose, the first two-dimensional point cloud data determined according to the expected pose is also not the final real two-dimensional point cloud data, and the first two-dimensional point cloud data needs to be corrected subsequently.

[0074] A feasible implementation manner is that the expected pose can be corrected to obtain the real pose, and the real two-dimensional point cloud data corresponding to the real pose can be obtained based on the real pose. Therefore, after obtaining the first two-dimensional point cloud data, the real pose corresponding to the current frame of the robot in the preset coordinate system can be determined based on the first two-dimensional point cloud data.

[0075] A preset grid map corresponding to the preset coordinate system is obtained, and third two-dimensional point cloud data of the two-dimensional point cloud data in the preset coordinate system is determined based on the preset grid map.

[0076] In the process of determining the real pose corresponding to the current frame in the preset coordinate system based on the first two-dimensional point cloud data, a feasible idea is that a standard two-dimensional point cloud data compared with the first two-dimensional point cloud data can be determined, and then the expected pose is corrected according to the difference between the standard two-dimensional point cloud data and the first two-dimensional point cloud data, and the real pose is obtained.

[0077] Specifically, a corresponding preset grid map in a preset coordinate system can be acquired. The preset grid map can be acquired in advance. For example, after the foot-type robot respectively acquires each three-dimensional pose data and two-dimensional point cloud data corresponding to each three-dimensional pose data, the foot-type robot can generate a point cloud grid map according to each three-dimensional pose data and the two-dimensional point cloud data corresponding to the three-dimensional pose data. It can be understood that when the point cloud grid map is generated according to each three-dimensional pose data and the two-dimensional point cloud data corresponding to the three-dimensional pose data, each two-dimensional point cloud data can be subjected to grid processing (which can also be understood as mesh processing). The grid processing can be to apply coordinates of all points included in each two-dimensional point cloud data to regularly divided multiple grid point clouds, and each grid point cloud can include points in multiple two-dimensional point clouds. Further, after applying all points included in each two-dimensional point cloud data to the regularly divided multiple grid point clouds, the point cloud grid map is generated according to the multiple grid point clouds including all points in each two-dimensional point cloud data. In the embodiments of the present application, the three-dimensional pose data can be used to reduce the accuracy loss of the two-dimensional point cloud data in different directions in the process of constructing the grid map, so as to improve the accuracy and stability of the grid map and bring better user experience.

[0078] Further, before the foot-type robot generates a map according to each three-dimensional pose data and two-dimensional point cloud data corresponding to the three-dimensional pose data, the foot-type robot can convert the multiple position corresponding three-dimensional pose data generated based on the foot-type robot coordinate system into three-dimensional pose data generated based on the world coordinate system, and then generate a grid map according to each three-dimensional pose data generated based on the world coordinate system and two-dimensional point cloud data corresponding to the three-dimensional pose data generated based on the world coordinate system.

[0079] Since the grid map is generated based on the two-dimensional point cloud data corresponding to the three-dimensional pose data generated based on the world coordinate system, the grid map and the two-dimensional point cloud data can be converted to the world coordinate system (i.e., the preset coordinate system), and each coordinate point in the grid map is accurate and real, so that the third two-dimensional point cloud data of the two-dimensional point cloud data in the preset coordinate system can be directly determined based on the preset grid map. The third two-dimensional point cloud data is also the standard two-dimensional point cloud data compared with the first two-dimensional point cloud data.

[0080] Specifically, determining the third two-dimensional point cloud data of the two-dimensional point cloud data in the preset coordinate system based on the preset grid map can include searching for adjacent coordinate points within a preset range of each coordinate point in the first two-dimensional point cloud data in the preset grid map, removing all adjacent coordinate points, and taking all remaining coordinate points as the third two-dimensional point cloud data of the two-dimensional point cloud data in the preset coordinate system.

[0081] Since the third two-dimensional point cloud data is the standard two-dimensional point cloud data compared with the first two-dimensional point cloud data, the third two-dimensional point cloud data and the first two-dimensional point cloud data can be compared to determine the real pose corresponding to the preset coordinate system.

[0082] Specifically, the third two-dimensional point cloud data and the first two-dimensional point cloud data can be matched to obtain a two-dimensional point cloud error, where the two-dimensional point cloud error can be a transformation matrix between the third two-dimensional point cloud data and the first two-dimensional point cloud data. Then, the expected pose is corrected according to the two-dimensional point cloud error to obtain the real pose corresponding to the preset coordinate system, that is, the expected pose of the robot is corrected according to the calculated transformation matrix to obtain the real pose of the robot in the current frame in the preset coordinate system.

[0083] In the embodiments of the present application, when the processor performs positioning according to the data output by the positioning unit, specifically, the corresponding pose offset is determined according to the data output by the positioning unit, and then the positioning information of the robot is calculated based on the pose offset. Therefore, the method of determining whether the current scene is an abnormal positioning scene is related to the specific method of positioning according to the data output by the positioning unit in the embodiments of the present application, that is, the method of determining whether the current scene is an abnormal positioning scene is related to the determination of the corresponding pose offset based on the data output by the corresponding positioning unit in the current scene. Therefore, the corresponding pose offset can be determined based on the data output by the corresponding positioning unit in the current scene, and whether the current scene is an abnormal positioning scene can be accurately determined.

[0084] Please refer to Figure 5 , Figure 5 The flowchart of an abnormal positioning method provided by another embodiment of the present application.

[0085] As Figure 5 shown, the method comprises:

[0086] S501, in response to a positioning instruction, obtaining current image data of a camera unit, and determining whether a first abnormal positioning scene exists according to the current image data, where in the first abnormal positioning scene, an abnormal pose offset determined according to the data output by a radar positioning unit corresponding to the first abnormal positioning scene cannot be used for positioning.

[0087] In order to facilitate the description of the specific process of determining whether the current scene is an abnormal positioning scene, the following will take the positioning unit comprising a radar positioning unit and a motion positioning unit as an example for introduction. The radar positioning unit is also the multi-line laser radar or single-line laser radar in the above embodiments, and the motion positioning unit is also the foot-type odometer or wheel-type odometer in the above embodiments. The following will take the radar positioning unit as a multi-line laser radar and the motion positioning unit as a foot-type odometer for introduction.

[0088] It can be understood that when the robot is currently in the degenerative scene, the abnormal pose offset determined by the data output by the radar positioning unit at this time cannot be positioned. Based on this idea, after responding to the positioning instruction, the current image data of the camera unit can be obtained first, and then it is determined whether the first abnormal positioning scene exists currently according to the current image data, that is, it is determined whether the degenerative scene exists currently. In the first abnormal positioning scene, the abnormal pose offset determined by the data output by the radar positioning unit corresponding to the first abnormal positioning scene cannot be positioned.

[0089] Specifically, in the process of obtaining the current image data of the camera unit and determining whether the first abnormal positioning scene exists currently according to the current image data, the current image data of the camera unit can be obtained first, the object feature information in the current image data is determined, and then it is determined whether the first abnormal positioning scene exists currently according to the object feature information. Because when the robot is currently in the degenerative scene, a large amount of glass in the scene will cause laser refraction, resulting in a decrease in the accuracy of the returned laser data or even making the laser data unusable, for example, a large amount of black light-absorbing material in the scene will cause the laser radar to not receive the returned laser distance data, for example, the scene is a regular square, and so on. The data output by the radar positioning unit is similar. At this time, the pose offset determined by the data output by the radar positioning unit cannot reflect the changes in the environment around the robot. Therefore, it can be determined whether the radar degenerative feature information exists in the object feature information, and the radar degenerative feature information includes at least one of the reflected object feature information, the light-absorbing material feature information, and the regular environment feature information. If the radar degenerative feature information exists in the object feature information, it is determined that the first abnormal positioning scene exists currently.

[0090] S502, in response to the positioning instruction, obtaining the current driving data of the driving unit, and determining whether the second abnormal positioning scene exists currently according to the current driving data, wherein in the second abnormal positioning scene, the abnormal pose offset determined by the data output by the motion positioning unit corresponding to the second abnormal positioning scene cannot be positioned.

[0091] It can be understood that when the robot is currently in the foot end slip scene, the abnormal pose offset determined by the data output by the motion positioning unit at this time cannot be positioned. Based on this idea, after responding to the positioning instruction, the current driving data of the driving unit can be obtained, and it is determined whether the second abnormal positioning scene exists currently according to the current driving data, that is, it is determined whether the foot end slip scene exists currently. Then, in the second abnormal positioning scene, the abnormal pose offset determined by the data output by the motion positioning unit corresponding to the second abnormal positioning scene cannot be positioned.

[0092] Specifically, in the process of determining whether the second abnormal positioning scenario exists according to the torque information, the current driving data of the driving unit can be acquired first, the torque information corresponding to the current driving data is determined, and then whether the second abnormal positioning scenario exists is determined according to the torque information. When the robot is currently in the foot slipping scenario, the output power cannot all act on the ground, so part of the power is lost, and the actual output torque and the theoretical output torque of the robot will have a large difference. Therefore, the actual output torque and the theoretical output torque in the torque information can be acquired. Specifically, the current robot motor position, speed data, actual output torque data, imu linear acceleration and angular velocity data are acquired, and the full-body dynamics model of the legged robot is established based on the legged robot, and the friction coefficient of the ground is considered. The theoretical output torque of the foot motor is calculated according to the acquired motor position, speed data, imu linear acceleration and angular velocity data. If the difference between the actual output torque and the theoretical output torque is greater than the preset difference threshold, it is determined that the second abnormal positioning scenario exists.

[0093] Alternatively, when the motion positioning unit is a wheeled odometer, a chassis dynamics model can be established based on the configuration of the wheeled robot chassis, and the full-body dynamics model of the legged robot is replaced by the dynamics model of the chassis. Then, the theoretical output torque of the chassis motor is calculated according to the motor position, speed data, imu linear acceleration and angular velocity data. If the difference between the actual output torque and the theoretical output torque is greater than the preset difference threshold, it is determined that the second abnormal positioning scenario exists.

[0094] S503, if the first abnormal positioning scenario exists, determining the normal positioning unit in the positioning unit as the motion positioning unit according to the first abnormal positioning scenario.

[0095] After determining whether the first abnormal positioning scenario exists according to the current image data, if only the first abnormal positioning scenario exists, that is, the abnormal pose offset determined by the data output by the radar positioning unit cannot be positioned, and the pose offset determined by the data output by the motion positioning unit can be positioned. Therefore, the normal positioning unit in the positioning unit is the motion positioning unit.

[0096] S504, if the second abnormal positioning scenario exists, determining the normal positioning unit in the positioning unit as the radar positioning unit according to the second abnormal positioning scenario.

[0097] After determining whether the second abnormal positioning scenario exists according to the current image data, if only the second abnormal positioning scenario exists, that is, the abnormal pose offset determined by the data output by the motion positioning unit cannot be positioned, and the pose offset determined by the data output by the radar positioning unit can be positioned. Therefore, the normal positioning unit in the positioning unit is the radar positioning unit.

[0098] S505, if the first abnormal positioning scenario and the second abnormal positioning scenario exist, determining that there is no normal positioning unit in the positioning units according to the first abnormal positioning scenario and the second abnormal positioning scenario.

[0099] After judging whether the first abnormal positioning scenario and the second abnormal positioning scenario exist according to the current image data, and judging whether the first abnormal positioning scenario and the second abnormal positioning scenario exist according to the current image data, if the first abnormal positioning scenario and the second abnormal positioning scenario exist, it means that the abnormal pose offset determined by the data output by the radar positioning unit cannot be positioned, and the abnormal pose offset determined by the data output by the motion positioning unit cannot be positioned, so there is no normal positioning unit in the positioning units.

[0100] S506, if there is at least one normal positioning unit, positioning according to the data output by the normal positioning unit.

[0101] For step S506, please refer to the description in step S403, which will not be repeated here.

[0102] S507, if there is no normal positioning unit, suspending driving and / or positioning, and uploading abnormal positioning information to a preset management device.

[0103] If there is no normal positioning unit, it means that the robot may be in a relatively extreme scenario at this time, at which time driving and / or positioning can be suspended, and abnormal positioning information can be uploaded to a preset management device. Abnormal positioning information can include problem logs, abnormal positioning scenarios, and real-time video images and other data, and a background user can obtain abnormal positioning information of the robot through the preset management device. The robot is manually controlled.

[0104] S508, receiving abnormal positioning solution information sent by the preset management device based on the abnormal positioning information, and re-driving and / or positioning based on the abnormal positioning solution information.

[0105] After the background user obtains the abnormal positioning information of the robot through the preset management device, the abnormal positioning solution information can be sent to the robot based on the abnormal positioning information, so that the robot can receive the abnormal positioning solution information sent by the preset management device based on the abnormal positioning information, and re-drive and / or position based on the abnormal positioning solution information.

[0106] For example, the background user can remotely control the robot, manually remotely control the robot to move a distance according to the real-time video image until the robot is out of the degenerative scenario and the slippery ground. If remote control cannot make the robot out of the current predicament, a staff can be arranged to solve the problem on site, and the robot can be manually controlled.

[0107] S509. If there is no abnormal positioning scenario, positioning is performed according to data output by any one of the positioning units.

[0108] If there is no abnormal positioning scenario, a pose offset determined according to data output by any one of the positioning units can be used for positioning.

[0109] In the embodiments of the present application, whether the robot is in a degenerative scenario can be determined according to current image data of the camera unit, or whether the robot is in a foot slipping scenario can be determined according to current driving data of the driving unit, so as to accurately determine whether the robot is in an abnormal positioning scenario.

[0110] Please refer to Figure 6 , Figure 6 FIG. 1 is a structural schematic diagram of an abnormal positioning processing device according to another embodiment of the present application.

[0111] As shown in Figure 6 FIG. 6, the abnormal positioning processing device 600 comprises:

[0112] An abnormal positioning judgment module 610 is configured to, in response to a positioning instruction, judge whether there is an abnormal positioning scenario at present.

[0113] A positioning unit determination module 620 is configured to, if there is an abnormal positioning scenario, determine a normal positioning unit in the positioning units according to the abnormal positioning scenario.

[0114] A positioning module 630 is configured to, if there is at least one normal positioning unit, perform positioning according to data output by the normal positioning unit.

[0115] Optionally, in the abnormal positioning scenario, an abnormal pose offset determined according to data output by a positioning unit corresponding to the abnormal positioning scenario cannot be used for positioning.

[0116] Optionally, the positioning module 630 is further configured to determine a current normal pose offset according to data output by the normal positioning unit, and perform positioning according to the normal pose offset.

[0117] Optionally, the positioning module 630 is further configured to determine a first pose offset corresponding to the current timestamp and a second pose offset corresponding to the previous timestamp according to data output by the normal positioning unit, and determine a normal pose offset corresponding to the current timestamp according to the first pose offset and the second pose offset; determine an expected pose in the preset coordinate system corresponding to the current timestamp according to the normal pose offset and a real pose in the preset coordinate system corresponding to the previous timestamp; determine first point cloud data of the current frame of point cloud data in the preset coordinate system based on the expected pose, and determine a real pose of the current frame in the preset coordinate system based on the first point cloud data.

[0118] Optionally, the positioning unit includes a radar positioning unit and a motion positioning unit, and the abnormal positioning judgment module 610 is further configured to acquire current image data of the camera unit, and determine whether a first abnormal positioning scenario exists currently according to the current image data, wherein in the first abnormal positioning scenario, an abnormal pose offset determined according to data output by the radar positioning unit corresponding to the first abnormal positioning scenario cannot be used for positioning; acquire current driving data of the driving unit, and determine whether a second abnormal positioning scenario exists currently according to the current driving data, wherein in the second abnormal positioning scenario, an abnormal pose offset determined according to data output by the motion positioning unit corresponding to the second abnormal positioning scenario cannot be used for positioning.

[0119] Optionally, the abnormal positioning judgment module 610 is further configured to acquire current image data of the camera unit, and determine object feature information in the current image data; and determine whether a first abnormal positioning scenario exists currently according to the object feature information.

[0120] Optionally, the abnormal positioning judgment module 610 is further configured to determine whether radar degradation feature information exists in the object feature information, the radar degradation feature information including at least one of reflected object feature information, light-absorbing material feature information, and regular environment feature information; and if the radar degradation feature information exists in the object feature information, it is determined that the first abnormal positioning scenario exists currently.

[0121] Optionally, the abnormal positioning judgment module 610 is further configured to acquire current driving data of the driving unit, and determine torque information corresponding to the current driving data; and determine whether a second abnormal positioning scenario exists currently according to the torque information.

[0122] Optionally, the abnormal positioning judgment module 610 is further configured to acquire actual output torque and theoretical output torque in the torque information; and if a difference between the actual output torque and the theoretical output torque is greater than a preset difference threshold, it is determined that the second abnormal positioning scenario exists currently.

[0123] Optionally, the positioning unit determination module 620 is further configured to: if the first abnormal positioning scenario exists, determine the normal positioning unit in the positioning units as the motion positioning unit according to the first abnormal positioning scenario; if the second abnormal positioning scenario exists, determine the normal positioning unit in the positioning units as the radar positioning unit according to the second abnormal positioning scenario; and if the first abnormal positioning scenario and the second abnormal positioning scenario exist, determine that there is no normal positioning unit in the positioning units according to the first abnormal positioning scenario and the second abnormal positioning scenario.

[0124] Optionally, the abnormal positioning processing apparatus 600 further comprises:

[0125] The abnormal processing module is configured to: if there is no normal positioning unit, suspend driving and / or positioning, and upload abnormal positioning information to a preset management device; receive abnormal positioning solution information sent by the preset management device based on the abnormal positioning information, and re-perform driving and / or positioning based on the abnormal positioning solution information.

[0126] Optionally, the abnormal positioning processing apparatus 600 further comprises:

[0127] The normal positioning implementation module is configured to: if there is no abnormal positioning scenario, perform positioning according to data output by any one of the positioning units.

[0128] In the embodiments of the present application, an abnormal positioning processing apparatus comprises: an abnormal positioning judgment module configured to judge whether an abnormal positioning scenario exists currently in response to a positioning instruction; a positioning unit determination module configured to determine a normal positioning unit in the positioning units according to the abnormal positioning scenario if the abnormal positioning scenario exists; and a positioning module configured to perform positioning according to data output by the normal positioning unit if at least one normal positioning unit exists. Since positioning of the robot will be abnormal if the robot directly performs positioning after the abnormal positioning scenario exists, remedial measures can be taken in time, that is, the normal positioning unit is determined, and positioning is performed according to data output by the normal positioning unit, so that the accuracy of the positioning data of the robot can be ensured, and the operation safety of the robot can be improved.

[0129] The embodiments of the present application also provide a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded and executed by a processor to perform the steps of the method in any one of the above embodiments.

[0130] Further, please refer to Figure 7 , Figure 7 A structural schematic diagram of an electronic device is provided for the embodiments of the present application. As shown in Figure 7 , the electronic device 700 can comprise at least one central processor 701, at least one network interface 704, a user interface 703, a memory 705, and at least one communication bus 702.

[0131] The communication bus 702 is configured to realize the connection communication between the components.

[0132] The user interface 703 can include a display screen, a camera, and optionally, a standard wired interface and a wireless interface.

[0133] The network interface 704 can optionally include a standard wired interface and a wireless interface (e.g., a WI-FI interface).

[0134] The central processor 701 can include one or more processing cores. The central processor 701 connects various parts in the electronic device 700 through various interfaces and lines, executes various functions of the electronic device 700 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 705 and calling data stored in the memory 705. Optionally, the central processor 701 can be implemented in at least one of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The central processor 701 can be integrated with a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process an operating system, a user interface, and an application program; the GPU is used to render and draw the content to be displayed on the display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the central processor 701, but can be implemented by a separate chip.

[0135] The memory 705 can include a random access memory (RAM) and can also include a read-only memory (ROM). Optionally, the memory 705 includes a non-transitory computer-readable storage medium. The memory 705 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 705 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 705 can also be at least one storage device located away from the central processing unit 701. As shown in Figure 7 The memory 705 as a computer storage medium can include an operating system, a network communication module, a user interface module, and an exception positioning processing program.

[0136] In the electronic device 700 shown in Figure 7 In the electronic device 700 shown in

[0137] In response to the positioning instruction, it is determined whether there is an exception positioning scenario at present.

[0138] If there is an exception positioning scenario, a normal positioning unit in the positioning unit is determined according to the exception positioning scenario.

[0139] If there is at least one normal positioning unit, positioning is performed according to the data output by the normal positioning unit.

[0140] Optionally, in the exception positioning scenario, the exception pose offset determined according to the data output by the positioning unit corresponding to the exception positioning scenario cannot be positioned.

[0141] Optionally, positioning according to the data output by the normal positioning unit includes determining a current normal pose offset according to the data output by the normal positioning unit, and positioning according to the normal pose offset.

[0142] Optionally, the current normal pose offset is determined according to the data output by the normal positioning unit, and the positioning is performed according to the normal pose offset, comprising: determining a first pose offset corresponding to a current timestamp and a second pose offset corresponding to a previous timestamp according to the data output by the normal positioning unit, and determining a normal pose offset corresponding to the current timestamp according to the first pose offset and the second pose offset; determining an expected pose of the current timestamp in a preset coordinate system according to the normal pose offset and a real pose corresponding to the previous timestamp in the preset coordinate system; determining first point cloud data of the current frame point cloud data in the preset coordinate system based on the expected pose, and determining a real pose of the current frame in the preset coordinate system based on the first point cloud data.

[0143] Optionally, the positioning unit comprises a radar positioning unit and a motion positioning unit, and the determination of whether the current is an abnormal positioning scene comprises: acquiring current image data of the camera unit, and determining whether the current is a first abnormal positioning scene according to the current image data, wherein in the first abnormal positioning scene, an abnormal pose offset determined according to data output by the radar positioning unit corresponding to the first abnormal positioning scene cannot be used for positioning; acquiring current driving data of the driving unit, and determining whether the current is a second abnormal positioning scene according to the current driving data, wherein in the second abnormal positioning scene, an abnormal pose offset determined according to data output by the motion positioning unit corresponding to the second abnormal positioning scene cannot be used for positioning.

[0144] Optionally, the acquisition of the current image data of the camera unit and the determination of whether the current is a first abnormal positioning scene according to the current image data comprise: acquiring the current image data of the camera unit, and determining object feature information in the current image data; and determining whether the current is a first abnormal positioning scene according to the object feature information.

[0145] Optionally, the determination of whether the current is a first abnormal positioning scene according to the object feature information comprises: determining whether radar degradation feature information is present in the object feature information, the radar degradation feature information comprising at least one of reflection object feature information, light-absorbing material feature information, and regular environment feature information; and if the radar degradation feature information is present in the object feature information, it is determined that the current is a first abnormal positioning scene.

[0146] Optionally, the acquisition of the current driving data of the driving unit and the determination of whether the current is a second abnormal positioning scene according to the current driving data comprise: acquiring the current driving data of the driving unit, and determining torque information corresponding to the current driving data; and determining whether the current is a second abnormal positioning scene according to the torque information.

[0147] Optionally, determining whether the second abnormal positioning scenario exists according to the torque information comprises: obtaining the actual output torque and the theoretical output torque in the torque information; and determining that the second abnormal positioning scenario exists currently if the difference between the actual output torque and the theoretical output torque is greater than a preset difference threshold.

[0148] Optionally, if the abnormal positioning scenario exists, determining the normal positioning unit in the positioning unit according to the abnormal positioning scenario comprises: if the first abnormal positioning scenario exists, determining the normal positioning unit in the positioning unit as the motion positioning unit according to the first abnormal positioning scenario; if the second abnormal positioning scenario exists, determining the normal positioning unit in the positioning unit as the radar positioning unit according to the second abnormal positioning scenario; and if the first abnormal positioning scenario and the second abnormal positioning scenario exist, determining that no normal positioning unit exists in the positioning unit according to the first abnormal positioning scenario and the second abnormal positioning scenario.

[0149] Optionally, if the normal positioning unit does not exist, suspending driving and / or positioning, and uploading abnormal positioning information to a preset management device; receiving abnormal positioning solution information sent by the preset management device based on the abnormal positioning information, and re-performing driving and / or positioning based on the abnormal positioning solution information.

[0150] Optionally, if the abnormal positioning scenario does not exist, positioning is performed according to the data output by any one of the positioning units.

[0151] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, apparatuses or modules, and can be electrical, mechanical or other forms.

[0152] The modules illustrated as separate components can or can not be physically separate, and the components illustrated as modules can or can not be physical modules, i.e., can be located in one place or can be distributed to a plurality of network modules. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0153] In addition, each function module in each embodiment of the present application can be integrated in one processing module, or each module can exist physically, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.

[0154] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various program code storage media.

[0155] It should be noted that, for the foregoing method embodiments, in order to facilitate description, they are all described as a combination of a series of actions, but those skilled in the art should know that the present application is not limited by the order of the described actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0156] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0157] The above is the description of the abnormal positioning processing method, device, storage medium and electronic equipment provided by the present application. For those skilled in the art, according to the idea of the embodiments of the present application, there will be changes in specific implementation and application range. In conclusion, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An abnormality positioning processing method characterized by comprising: The method comprises: in response to the positioning instruction, determining whether an abnormal positioning scenario exists at present; if the first abnormal positioning scenario exists, determining a normal positioning unit in the positioning unit as a motion positioning unit according to the first abnormal positioning scenario; wherein the positioning unit comprises a radar positioning unit and the motion positioning unit, and in the first abnormal positioning scenario, an abnormal pose offset determined according to the data output by the radar positioning unit corresponding to the first abnormal positioning scenario cannot be positioned; if the second abnormal positioning scenario exists, determining a normal positioning unit in the positioning unit as the radar positioning unit according to the second abnormal positioning scenario; wherein in the second abnormal positioning scenario, an abnormal pose offset determined according to the data output by the motion positioning unit corresponding to the second abnormal positioning scenario cannot be positioned; if the first abnormal positioning scenario and the second abnormal positioning scenario exist, determining that there is no normal positioning unit in the positioning unit according to the first abnormal positioning scenario and the second abnormal positioning scenario; if at least one normal positioning unit exists, positioning according to the data output by the normal positioning unit.

2. The method of claim 1, wherein, In the abnormal positioning scenario, an abnormal pose offset determined according to the data output by the positioning unit corresponding to the abnormal positioning scenario cannot be positioned.

3. The method according to claim 1 or 2, characterized in that, The positioning according to the data output by the normal positioning unit comprises: determining a current normal pose offset according to the data output by the normal positioning unit, and positioning according to the normal pose offset.

4. The method of claim 3, wherein, The positioning according to the data output by the normal positioning unit, comprising: determining a current normal pose offset according to the data output by the normal positioning unit, and positioning according to the normal pose offset. The positioning according to the data output by the normal positioning unit, comprising: determining a first pose offset corresponding to a current timestamp and a second pose offset corresponding to a previous timestamp according to the data output by the normal positioning unit, and determining a normal pose offset corresponding to the current timestamp according to the first pose offset and the second pose offset; 5. The method of claim 2, wherein, determining an expected pose of the current timestamp in a preset coordinate system according to the normal pose offset and a real pose of the previous timestamp in the preset coordinate system; determining first point cloud data of the current frame point cloud data in the preset coordinate system based on the expected pose, and determining a real pose of the current frame in the preset coordinate system based on the first point cloud data. The determination of whether an abnormal positioning scenario exists at present comprises:

6. The method of claim 5, wherein, acquiring current image data of a camera unit, and determining whether the first abnormal positioning scenario exists at present according to the current image data; acquiring current driving data of a driving unit, and determining whether the second abnormal positioning scenario exists at present according to the current driving data. The acquisition of the current image data of the camera unit and the determination of whether the first abnormal positioning scenario exists at present according to the current image data comprise: acquiring current image data of a camera unit, and determining object feature information in the current image data; determining whether the first abnormal positioning scenario exists at present according to the object feature information.

7. The method of claim 6, wherein, The method comprises the following steps: determining whether the object feature information contains radar degradation feature information, wherein the radar degradation feature information comprises at least one of reflection object feature information, light-absorbing material feature information, and regular environment feature information; if the object feature information contains the radar degradation feature information, determining that the first abnormal positioning scenario currently exists.

8. The method of claim 5, wherein, The method comprises the following steps: acquiring current driving data of the driving unit, determining torque information corresponding to the current driving data; determining whether the second abnormal positioning scenario currently exists according to the torque information.

9. The method of claim 8, wherein, The method comprises the following steps: acquiring actual output torque and theoretical output torque in the torque information; if a difference between the actual output torque and the theoretical output torque is greater than a preset difference threshold, determining that the second abnormal positioning scenario currently exists.

10. The method of claim 1, and characterized in that, if the normal positioning unit does not exist, driving and / or positioning are suspended, and abnormal positioning information is uploaded to a preset management device; receiving abnormal positioning solution information sent by the preset management device based on the abnormal positioning information, and resuming driving and / or positioning based on the abnormal positioning solution information.

11. The method of claim 1, wherein, If the abnormal positioning scenario does not exist, positioning is performed according to data output by any one of the positioning units.

12. An abnormality positioning processing apparatus characterized by comprising: The device comprises: an abnormal positioning determination module configured to determine whether an abnormal positioning scenario currently exists in response to a positioning instruction; a positioning unit determination module configured to, if a first abnormal positioning scenario exists, determine a normal positioning unit in the positioning units to be a motion positioning unit according to the first abnormal positioning scenario, wherein the positioning units comprise a radar positioning unit and the motion positioning unit, and in the first abnormal positioning scenario, an abnormal pose offset determined according to data output by the radar positioning unit corresponding to the first abnormal positioning scenario cannot be used for positioning; if a second abnormal positioning scenario exists, determine a normal positioning unit in the positioning units to be the radar positioning unit according to the second abnormal positioning scenario, wherein in the second abnormal positioning scenario, an abnormal pose offset determined according to data output by the motion positioning unit corresponding to the second abnormal positioning scenario cannot be used for positioning; and if the first abnormal positioning scenario and the second abnormal positioning scenario exist, determine that no normal positioning unit exists in the positioning units according to the first abnormal positioning scenario and the second abnormal positioning scenario; a positioning module configured to, if at least one normal positioning unit exists, perform positioning according to data output by the normal positioning unit.

13. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions, which are suitable for being loaded and executed by a processor to perform the steps of the method of any one of claims 1-11.

14. An electronic device, comprising: A computer program product comprising a memory, a processor and a computer program stored on the memory and loadable on the processor, the processor implementing the steps of the method according to any one of claims 1 to 11 when running the program.

Images