Robot detection method, device and robot

Abstract

The present application is applicable to the field of vehicle maintenance technology, and provides a robot detection method, device and robot, including: obtaining three-dimensional point cloud data of a vehicle to be detected on a site; determining at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and a pre-stored relative posture; for each detection point, the robot performs the following steps: determining the current posture of the robot on the site during the movement of the robot toward the detection point; determining the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the site and the three-dimensional point cloud data of the vehicle to be detected; adjusting the current relative posture according to the pre-stored relative posture corresponding to the detection point, stopping movement when the current relative posture is the same as the pre-stored relative posture, and detecting the vehicle to be detected. The above method can improve the efficiency of vehicle detection.

Description

Technical Field

[0001] The present application belongs to the field of vehicle maintenance technology, and in particular relates to a robot detection method, device, robot, and computer-readable storage medium. Background Art

[0002] With the improvement of economic level, more and more users own vehicles. In order to improve the safety of vehicles, it is necessary to inspect the vehicles on time.

[0003] Currently, vehicles to be inspected need to be driven to a designated site and then inspected by staff, but this method is inefficient.

[0004] Therefore, it is necessary to provide a new method to solve the above technical problems. Summary of the Invention

[0005] The embodiments of the present application provide a robot detection method, device, and robot, which can solve the problem of low efficiency of manual vehicle inspection.

[0006] In a first aspect, an embodiment of the present application provides a vehicle detection method, applied to a robot, comprising:

[0007] Obtain three-dimensional point cloud data of the vehicle to be detected on the site;

[0008] Determine at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and the pre-stored relative posture, wherein the detection point is the position where the robot is located when detecting the vehicle to be detected;

[0009] For each detection point, the robot performs the following steps:

[0010] Determining a current position of the robot on the field during movement of the robot toward the detection point;

[0011] Determining the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected;

[0012] The current relative posture is adjusted according to the pre-stored relative posture corresponding to the detection point. When the current relative posture is the same as the pre-stored relative posture, the movement is stopped and the vehicle to be detected is detected.

[0013] In a second aspect, an embodiment of the present application provides a vehicle detection device, applied to a robot, comprising:

[0014] A three-dimensional point cloud data acquisition module is used to acquire three-dimensional point cloud data of the vehicle to be detected on the site;

[0015] a detection point determination module, configured to determine at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and a pre-stored relative position and posture, wherein the detection point is the position at which the robot is located when detecting the vehicle to be detected;

[0016] a current posture determination module, configured to determine the current posture of the robot on the field during the process of the robot moving toward the detection point;

[0017] a current relative posture determination module, configured to determine the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected;

[0018] The vehicle detection module is used to adjust the current relative posture according to the pre-stored relative posture corresponding to the detection point, stop moving when the current relative posture is the same as the pre-stored relative posture, and detect the vehicle to be detected.

[0019] In a third aspect, an embodiment of the present application provides a robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the computer program.

[0020] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when run on a robot, enables the robot to execute the method described in the first aspect above.

[0022] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0023] In the embodiment of the present application, at least one detection point can be determined on the site based on the three-dimensional point cloud data of the vehicle to be detected on the site and the pre-stored relative posture, and the detection point is the position point where the robot is located when detecting the vehicle to be detected. Therefore, based on the determined detection point, the robot can know the position point it needs to reach. At the same time, since the robot can calculate the current relative posture of the robot and the vehicle to be detected based on its current posture at the current moment during the process of moving to the detection point, the robot can timely compare its current relative posture with the pre-stored relative posture corresponding to the detection point, so as to be able to timely determine whether it has reached the detection point, and detect the vehicle to be detected when it reaches the detection point, thereby improving the timeliness and accuracy of obtaining the detection results. In addition, since the detection of the vehicle to be detected is performed by the robot, no human intervention is required, and the robot can work for a long time, it can greatly improve the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art.

[0025] Figure 1 This is a flowchart of a robot detection method provided by an embodiment of the present application;

[0026] Figure 2 is a schematic diagram of a robot provided in one embodiment of the present application;

[0027] Figure 3 This is a schematic diagram of a detection point for a vehicle to be detected provided by an embodiment of the present application;

[0028] Figure 4 This is a schematic structural diagram of a robot detection device provided in one embodiment of the present application;

[0029] Figure 5 This is a schematic structural diagram of a robot provided in another embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0031] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0032] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0033] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0034] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in yet other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized.

[0035] Example 1:

[0036] When inspecting a vehicle, if it is done only by manpower, the inspection efficiency will be too low.

[0037] To improve vehicle detection efficiency, embodiments of the present application provide a vehicle detection method. In this method, a vehicle to be detected is moved to a site, and then a robot is moved to a detection point to detect the vehicle. Because robots can operate for extended periods of time, using robots to detect vehicles can significantly improve vehicle detection efficiency.

[0038] The vehicle detection method provided in the embodiments of the present application is described below with reference to the accompanying drawings.

[0039] Figure 1 A flow chart of a vehicle detection method provided in an embodiment of the present application is shown. The vehicle detection method is applied to a robot and is described in detail as follows:

[0040] Step S11: Acquire three-dimensional point cloud data of the vehicle to be detected on the site.

[0041] Specifically, the vehicle to be inspected is moved to the inspection station on the site, and after determining that the vehicle to be inspected needs to be inspected, the point cloud information of the site where the inspection station is located is obtained through a three-dimensional reconstruction device, and then the point cloud information belonging to the ground is segmented from the point cloud information to obtain the point cloud information belonging to the vehicle to be inspected, that is, the three-dimensional point cloud data of the vehicle to be inspected is obtained.

[0042] The three-dimensional reconstruction device may be a plurality of multi-line laser radars, or a plurality of depth cameras, or a plurality of binocular cameras, or a plurality of monocular cameras.

[0043] In some embodiments, the 3D reconstruction device of the present application is fixedly mounted above the vehicle to be inspected. Because more information about the vehicle to be inspected can be obtained from above, and the information obtained from above can reduce the degree of distortion of the 3D point cloud data, the 3D point cloud data obtained from the information obtained by the 3D reconstruction device mounted above the vehicle to be inspected is more accurate.

[0044] Step S12: determining at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and the pre-stored relative posture, wherein the detection point is the position where the robot is located when detecting the vehicle to be detected.

[0045] Among them, the pre-stored relative posture is the relative posture between the robot and the vehicle to be detected, and its number is usually greater than or equal to 1. In some embodiments, since the models, manufacturers, etc. of the vehicles to be detected are usually different, there may be some differences in the positions of the parts of different vehicles to be detected. At this time, the relative posture between the robot and the vehicle to be detected can be determined according to the model of the vehicle to be detected, that is, vehicles to be detected of different models correspond to different relative postures. In some embodiments, the robot can obtain the relative posture of each model through manual teaching. Specifically, the robot is manually pushed to reach each detection point of the vehicle to be detected, and the robot's mechanical arm is moved to detect the vehicle to be detected, such as the robot's mechanical arm is moved to shoot the vehicle to be detected, and the robot records its current posture as the relative posture corresponding to the detection point and stores it. Among them, the robot of the embodiment of the present application can be as follows Figure 2 shown.

[0046] Specifically, considering that vehicle inspections typically involve multiple locations, and that it's often difficult to inspect multiple locations at a single inspection point, corresponding inspection points can be set based on the location to be inspected. For example, if you need to obtain a vehicle's license plate number, you can set a inspection point in front of the vehicle to capture an image of the license plate. If you need to obtain the status of an in-vehicle instrument, you can set a inspection point next to the passenger door to capture an image of the instrument through the open passenger door.

[0047] In some embodiments, considering that vehicle inspection (such as annual vehicle inspection) usually requires checking the vehicle's engine number, frame number, tires, appearance and other locations, the determined inspection points can be as follows: Figure 3 As shown. Figure 3 In this example, the robot starts at the standby point and follows the order of the inspection points, first arriving at Inspection Point 1. After obtaining vehicle information at Inspection Point 1, it continues to Inspection Point 2. After obtaining vehicle information at each inspection point, the robot returns to the charging station at the standby point for recharging. The robot can then analyze the vehicle information obtained at each inspection point to conduct vehicle inspections.

[0048] For each of the above detection points, the above robot performs steps S13 to S15:

[0049] Step S13: Determine the current position of the robot on the field while the robot is moving toward the detection point.

[0050] In the embodiment of the present application, as the robot moves toward a detection point, the robot needs to determine its current position on the field. This current position is the global position. Specifically, because the robot's position is related to its displacement, the robot's current position can be periodically determined based on the period of obtaining the displacement. For example, a current position is determined after obtaining a displacement.

[0051] Step S14: determining the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected.

[0052] In the embodiment of the present application, as the robot moves toward the detection point, the current relative position of the robot and the vehicle to be detected is calculated multiple times to promptly determine whether the robot has reached the detection point. Specifically, the position of the vehicle to be detected (or its components) on the field is determined based on the three-dimensional point cloud data of the vehicle to be detected. Combined with the current position of the robot on the field, the current relative position of the robot and the vehicle to be detected can be determined.

[0053] Step S15, adjusting the current relative posture according to the pre-stored relative posture corresponding to the detection point, stopping movement when the current relative posture is the same as the pre-stored relative posture, and detecting the vehicle to be detected.

[0054] Since the relative position and posture of the robot and the vehicle to be inspected are typically different at different inspection points, after determining the inspection point, it is necessary to determine the corresponding pre-stored relative position and posture. Subsequently, as the robot moves toward the inspection point, the current relative position and posture of the vehicle to be inspected is compared with the pre-stored relative position and posture corresponding to the inspection point. If the corresponding positions and postures are the same, the robot has reached the inspection point and can use the current posture to inspect the vehicle to be inspected. Of course, if the corresponding positions are the same but the postures are different, the robot's posture should be adjusted before inspecting the vehicle to be inspected, such as by adjusting the posture of the robot's robotic arm.

[0055] In an embodiment of the present application, when the current relative posture is the same as the pre-stored relative posture corresponding to the detection point, it indicates that the robot has reached the detection point and its posture also meets the requirements. At this time, the robot will detect the vehicle to be detected at the current position, such as by photographing the vehicle to be detected through its own installed shooting equipment to obtain relevant information of the vehicle to be detected. In this way, the detection result of the vehicle to be detected can be obtained by subsequently analyzing the relevant information of the vehicle to be detected.

[0056] Of course, if the current relative posture is different from the pre-stored relative posture corresponding to the above detection point (such as the position and posture are different), return to step S13 and subsequent steps until the information of the vehicle to be detected is obtained at each detection point.

[0057] In the embodiment of the present application, at least one detection point can be determined on the site based on the three-dimensional point cloud data of the vehicle to be detected on the site and the pre-stored relative posture, and the detection point is the position point where the robot is located when detecting the vehicle to be detected. Therefore, based on the determined detection point, the robot can know the position point it needs to reach. At the same time, since the robot can calculate the current relative posture of the robot and the vehicle to be detected based on its current posture at the current moment during the process of moving to the detection point, the robot can timely compare its current relative posture with the pre-stored relative posture corresponding to the detection point, so as to be able to timely determine whether it has reached the detection point, and detect the vehicle to be detected when it reaches the detection point, thereby improving the timeliness and accuracy of obtaining the detection results. In addition, since the detection of the vehicle to be detected is performed by the robot, no human intervention is required, and the robot can work for a long time, it can greatly improve the detection efficiency.

[0058] In the embodiments of the present application, the current position of the robot on the field can be determined in different ways. In some embodiments, the current position of the robot can be determined based on the initial position and displacement of the robot on the field. In this case, in step S13, determining the current position of the robot on the field includes:

[0059] A1. Obtain the initial posture of the robot.

[0060] The initial position is the robot's initial position on the field, which can be the robot's position at a standby point. The standby point is where the robot is located when it is not performing any inspection tasks. Charging stations are usually placed at the standby point to ensure timely charging of the robot.

[0061] A2. Determine the current posture of the robot on the field based on the initial posture and the displacement of the robot on the field.

[0062] In an embodiment of the present application, the displacement of the robot on the field can be obtained by fusing the odometer and inertial measurement unit (IMU) of the robot chassis. Since the odometer can measure the robot's travel, and the IMU can measure the object's three-axis attitude angle (or angular rate) and acceleration, the current position of the robot on the field can be determined based on the current data corresponding to the odometer, IMU, etc. and its initial position on the field. In addition, since the robot can quickly obtain the corresponding data of the odometer and IMU, the current position of the robot on the field can be quickly obtained according to the above method.

[0063] In some embodiments, if the current posture of the robot on the field is determined based on the initial posture of the robot and the displacement of the robot on the field, the above step S14 includes:

[0064] B1. Determine the initial relative position of the robot and the vehicle to be detected based on the current position of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected.

[0065] In an embodiment of the present application, considering that the displacement of the robot increases with time, its error will accumulate. Therefore, the initial relative posture can be determined first based on the current posture and the three-dimensional point cloud data of the vehicle to be detected, and then the initial relative posture can be corrected to obtain the current relative posture of the robot and the vehicle to be detected.

[0066] B2. Obtain point cloud information on the site through the three-dimensional reconstruction equipment installed on the above-mentioned robot.

[0067] Among them, the three-dimensional reconstruction equipment includes a depth camera, a multi-line lidar device, etc.

[0068] Specifically, since the robot is moving towards the detection point, and the detection point is located near the vehicle to be detected, the point cloud information on the site obtained by the three-dimensional reconstruction device installed on the robot will include the point cloud information of the vehicle to be detected.

[0069] B3. Determine the point cloud information belonging to the vehicle to be detected from the point cloud information on the field according to the initial relative posture of the robot and the vehicle to be detected.

[0070] Since the position information of the robot on the site can be obtained from the robot itself, and the initial relative posture of the robot and the vehicle to be detected is also known, based on the position information of the robot on the site and the above-mentioned initial relative posture, the point cloud information belonging to the vehicle to be detected can be determined from the point cloud information on the site.

[0071] B4. Determine the current relative position of the robot and the vehicle to be detected based on the point cloud information of the vehicle to be detected and the three-dimensional point cloud data of the vehicle to be detected.

[0072] Specifically, the point cloud information belonging to the vehicle to be detected is matched with the 3D data in the 3D point cloud data of the vehicle to be detected. The current relative position of the robot and the vehicle to be detected is then determined based on the matched point cloud information. Because the point cloud information is a global variable, it has a high degree of accuracy, making the current relative position of the robot and the vehicle to be detected determined based on the matched point cloud information more accurate.

[0073] In some embodiments, a target object may be set on the field, and the current posture of the robot may be determined by determining the relative posture between the target object and the robot. In this case, determining the current posture of the robot on the field in step S13 includes:

[0074] C1. The target object is photographed by a photographing device installed on the robot to obtain a target image. The position information of the target object on the field is known.

[0075] The target object includes marking patterns such as a QR code and a car frame pattern, and may also include a column, etc. In the embodiment of the present application, after one or more target objects are set near the detection station on the site, the position information of the target object will be determined.

[0076] In some embodiments, to avoid the entire field being filled with target objects, the target objects can be spaced out. For example, when the target objects are QR codes, the QR codes can be spaced out near the detection stations to avoid a poor user experience.

[0077] In the embodiment of the present application, when the robot moves toward the detection point, it will encounter a target object set on the field. After photographing the target object it encounters, a target image containing the target object can be obtained.

[0078] C2. Determine the current posture of the robot based on the position information of the target object on the field, the position information of the target object in the target image, the installation position of the shooting device on the robot, and the displacement of the robot.

[0079] Specifically, based on the position information of the target object in the target image and the parameters of the shooting device itself, the relative position of the target object and the shooting device can be calculated. Combined with the installation position of the shooting device on the robot, the relative position of the target object and the robot can be determined. Finally, combined with the position information of the target object on the site and the displacement of the robot, the current position of the robot can be determined.

[0080] In some embodiments, the robot's displacement on the field can be obtained by integrating the robot's chassis' odometry and IMU. In this case, the robot's current position and pose can be periodically calculated based on the periodicity of the odometry and IMU output data. It should be noted that when using this method to calculate the robot's current position and pose, even if the target object is not continuously positioned on the field, as long as a target image containing the target object is captured, the robot's current position and pose can be accurately calculated based on the target image.

[0081] In some embodiments, the position and posture of the robot can be determined directly based on the point cloud information of the robot on the field. In this case, determining the current position and posture of the robot on the field in step S13 includes:

[0082] D1. Obtain point cloud information on the site.

[0083] Specifically, point cloud information on the site can be obtained through a three-dimensional reconstruction device, such as a three-dimensional reconstruction device installed above the vehicle to be detected, and the three-dimensional reconstruction device then sends the obtained point cloud information to the robot.

[0084] D2. Identify the point cloud information belonging to the robot from the point cloud information on the field.

[0085] Specifically, based on the characteristics of the robot itself, point cloud information belonging to the robot is identified from the point cloud information on the site.

[0086] D3. Determine the current position of the robot on the field based on the point cloud information belonging to the robot.

[0087] In the embodiment of the present application, since the point cloud information belonging to the robot in the venue can accurately reflect the posture of the robot on the venue, the accuracy of the determined current posture can be guaranteed by the above method.

[0088] In some embodiments, a marker object is pre-installed on the robot, and the current position of the robot on the field is determined based on the position of the marker object on the field. In this case, determining the current position of the robot on the field in step S13 includes:

[0089] E1. Obtain the position and posture of the above-mentioned marked objects on the field.

[0090] The marking object may be a QR code or other marking objects.

[0091] In an embodiment of the present application, a photographing device can be used to photograph the marking object on the robot to obtain an image containing the marking object, and the image containing the marking object can be analyzed to obtain the position information of the marking object in the image. The relative position and posture of the photographing device and the marking object can be determined based on the position information and the parameters of the photographing device, and then the position and posture of the marking object on the field can be determined in combination with the position and posture of the photographing device on the field. It should be pointed out that the position and posture of the marking object on the field can be calculated by other devices or by the robot. For example, the robot obtains the image containing the marking object captured by the photographing device, the parameters of the photographing device, and the position and posture of the photographing device on the field, and calculates the position and posture of the marking object on the field based on the various information it obtains.

[0092] E2. Determine the current position of the robot on the field based on the position of the marking object on the field and the installation position of the marking object on the robot.

[0093] In the embodiment of the present application, since the marking object is installed on the robot, after determining the position of the marking object on the field, the current position of the robot on the field can be accurately determined based on the installation position of the marking object on the robot.

[0094] In some embodiments, after the above step S11, the method further includes:

[0095] F1. Determine the state of a designated part of the vehicle to be detected based on the three-dimensional point cloud data of the vehicle to be detected, where the state of the designated part includes an open state or a closed state.

[0096] The designated parts of the vehicle to be inspected include at least one of the following: a hood, a door (such as a passenger door).

[0097] For example, when inspecting a vehicle, it is necessary to check the vehicle's engine and other components. Since the engine is under the hood, the maintenance personnel need to open the hood first so that the robot can obtain relevant information about the various components under the hood. That is, in an embodiment of the present application, when the designated part includes the hood, it is necessary to analyze whether the hood in the three-dimensional point cloud data is open.

[0098] F2. If the state of the designated part of the vehicle to be inspected does not meet the requirements, a prompt is issued to indicate that the state of the designated part is wrong.

[0099] When a vehicle needs to be inspected, it is usually necessary to keep designated parts such as the hood and / or doors open. In this case, the state of these designated parts corresponds to the requirement that the state is open. In an embodiment of the present application, when the state of the designated parts corresponds to the requirement that the state is open, if it is determined that the designated part of the vehicle to be inspected is not in the open state, a prompt is issued so that the maintenance personnel can adjust the state of the designated part of the vehicle to be inspected in a timely manner.

[0100] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0101] Example 2:

[0102] Corresponding to the vehicle detection method of the above embodiment, Figure 4 A structural block diagram of a vehicle detection device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0103] Reference Figure 4 The vehicle detection device 4 is applied to a robot and includes: a three-dimensional point cloud data acquisition module 41, a detection point determination module 42, a current posture determination module 43, a current relative posture determination module 44, and a vehicle detection module 45. Among them:

[0104] The three-dimensional point cloud data acquisition module 41 is used to acquire three-dimensional point cloud data of the vehicle to be detected on the site.

[0105] Specifically, the vehicle to be inspected is moved to the inspection station on the site, and after determining that the vehicle to be inspected needs to be inspected, the point cloud information of the site where the inspection station is located is obtained through the three-dimensional reconstruction equipment, and then the point cloud information belonging to the ground is segmented from the point cloud information to obtain the point cloud information belonging to the vehicle to be inspected. Finally, the three-dimensional point cloud data of the vehicle to be inspected is reconstructed based on the point cloud information belonging to the vehicle to be inspected.

[0106] The three-dimensional reconstruction device may be a plurality of multi-line laser radars, or a plurality of depth cameras, or a plurality of binocular cameras, or a plurality of monocular cameras.

[0107] In some embodiments, the three-dimensional reconstruction device of the present application is fixedly installed above the vehicle to be detected.

[0108] The detection point determination module 42 is used to determine at least one detection point on the above-mentioned site based on the three-dimensional point cloud data of the above-mentioned vehicle to be detected and the pre-stored relative posture, wherein the above-mentioned detection point is the position point where the above-mentioned robot is located when detecting the above-mentioned vehicle to be detected.

[0109] The current posture determination module 43 is used to determine the current posture of the robot on the field during the process of the robot moving toward the detection point.

[0110] The current relative posture determination module 44 is used to determine the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected.

[0111] The vehicle detection module 45 is used to adjust the above-mentioned current relative posture according to the pre-stored relative posture corresponding to the above-mentioned detection point, stop moving when the above-mentioned current relative posture is the same as the above-mentioned pre-stored relative posture, and detect the above-mentioned vehicle to be detected.

[0112] In the embodiment of the present application, at least one detection point can be determined on the site based on the three-dimensional point cloud data of the vehicle to be detected on the site and the pre-stored relative posture, and the detection point is the position point where the robot is located when detecting the vehicle to be detected. Therefore, based on the determined detection point, the robot can know the position point it needs to reach. At the same time, since the robot can calculate the current relative posture of the robot and the vehicle to be detected based on its current posture at the current moment during the process of moving to the detection point, the robot can timely compare its current relative posture with the pre-stored relative posture corresponding to the detection point, so as to be able to timely determine whether it has reached the detection point, and detect the vehicle to be detected when it reaches the detection point, thereby improving the timeliness and accuracy of obtaining the detection results. In addition, since the detection of the vehicle to be detected is performed by the robot, no human intervention is required, and the robot can work for a long time, it can greatly improve the detection efficiency.

[0113] In some embodiments, when determining the current posture of the robot on the field, the current posture determination module 43 is specifically used to:

[0114] Get the initial pose of the robot.

[0115] The current posture of the robot on the field is determined based on the initial posture and the displacement of the robot on the field.

[0116] In the embodiment of the present application, the displacement of the robot on the field can be obtained by integrating the odometer and IMU of the robot chassis.

[0117] In some embodiments, the current relative pose determination module 44 includes:

[0118] The initial relative posture determination unit is used to determine the initial relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the site and the three-dimensional point cloud data of the vehicle to be detected.

[0119] The point cloud information acquisition unit is used to acquire point cloud information on the site through a three-dimensional reconstruction device installed on the above-mentioned robot.

[0120] The point cloud information determination unit belonging to the vehicle to be detected is used to determine the point cloud information belonging to the vehicle to be detected from the point cloud information on the field according to the initial relative posture of the robot and the vehicle to be detected.

[0121] The current relative posture determination unit is used to determine the current relative posture of the robot and the vehicle to be detected based on the point cloud information belonging to the vehicle to be detected and the three-dimensional point cloud data of the vehicle to be detected.

[0122] In some embodiments, when determining the current posture of the robot on the field, the current posture determination module 43 is specifically used to:

[0123] The target object is photographed by a photographing device arranged on the robot to obtain a target image, and the position information of the target object on the field is known.

[0124] The current posture of the robot is determined based on the position information of the target object on the site, the position information of the target object in the target image, the installation position of the shooting device on the robot, and the displacement of the robot.

[0125] When determining the current posture of the robot on the field, the current posture determination module 43 is specifically used to:

[0126] Get point cloud information on the site.

[0127] Point cloud information belonging to the robot is identified from the point cloud information on the field.

[0128] The current position of the robot on the field is determined based on the point cloud information belonging to the robot.

[0129] When determining the current posture of the robot on the field, the current posture determination module 43 is specifically used to:

[0130] Get the position and pose of the above-mentioned marker objects on the site.

[0131] The current posture of the robot on the field is determined based on the posture of the marking object on the field and the installation position of the marking object on the robot.

[0132] In some embodiments, the vehicle detection device 4 provided in the embodiments of the present application further includes:

[0133] The module for determining the state of the designated part is used to determine the state of the designated part of the vehicle to be detected based on the three-dimensional point cloud data of the vehicle to be detected. The state of the designated part includes an open state or a closed state.

[0134] The prompt module is used to issue a prompt indicating that the state of the designated part of the vehicle to be detected is wrong if the state of the designated part does not meet the requirements.

[0135] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0136] Example 3:

[0137] Figure 5 This is a schematic diagram of the structure of a robot provided in one embodiment of the present application. Figure 5 As shown, the robot 5 of this embodiment includes: at least one processor 50 ( Figure 5 Only one processor is shown in the figure), a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, wherein the processor 50 implements the steps of any of the above-mentioned method embodiments when executing the computer program 52.

[0138] The robot 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 This is merely an example of the robot 5 and does not constitute a limitation on the robot 5 . The robot 5 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the robot 5 may also include input and output devices, network access devices, etc.

[0139] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0140] In some embodiments, the memory 51 may be an internal storage unit of the robot 5, such as a hard drive or memory of the robot 5. In other embodiments, the memory 51 may also be an external storage device of the robot 5, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the robot 5. Furthermore, the memory 51 may include both an internal storage unit of the robot 5 and an external storage device. The memory 51 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 51 may also be used to temporarily store data that has been output or is about to be output.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0142] An embodiment of the present application also provides a network device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor implements the steps of any of the above-mentioned method embodiments when executing the computer program.

[0143] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0144] An embodiment of the present application provides a computer program product. When the computer program product runs on a robot, the robot can implement the steps in the above-mentioned various method embodiments when executing the computer program product.

[0145] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / robot, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard drive, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0146] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0147] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0148] In the embodiments provided in this application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0150] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A vehicle detection method, characterized in that: Applications in robots include: Obtain three-dimensional point cloud data of the vehicle to be detected on the site; Determine at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and the pre-stored relative posture, wherein the detection point is the position where the robot is located when detecting the vehicle to be detected; For each detection point, the robot performs the following steps: Determining a current position of the robot on the field during movement of the robot toward the detection point; Determining the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected; Adjust the current relative posture according to the pre-stored relative posture corresponding to the detection point. When the current relative posture is the same as the pre-stored relative posture, stop moving and detect the vehicle to be detected. When the position point corresponding to the current relative posture is the same as the position point corresponding to the pre-stored relative posture, but the posture corresponding to the current relative posture is different from the posture corresponding to the pre-stored relative posture, adjust the posture of the robot and then detect the vehicle to be detected. When the current relative posture is different from the pre-stored relative posture, return to the step of determining the current posture of the robot on the site and subsequent steps during the process of the robot moving toward the detection point.

2. The vehicle detection method according to claim 1, wherein: Determining the current position of the robot on the field includes: Obtaining the initial posture of the robot; The current posture of the robot on the field is determined according to the initial posture and the displacement of the robot on the field.

3. The vehicle detection method according to claim 2, wherein: Determining the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected includes: Determining an initial relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected; Acquiring point cloud information on the site through a three-dimensional reconstruction device installed on the robot; Determining point cloud information belonging to the vehicle to be detected from the point cloud information on the site according to the initial relative posture of the robot and the vehicle to be detected; The current relative position of the robot and the vehicle to be detected is determined based on the point cloud information belonging to the vehicle to be detected and the three-dimensional point cloud data of the vehicle to be detected.

4. The vehicle detection method according to claim 1, wherein: Determining the current position of the robot on the field includes: photographing a target object by a photographing device provided on the robot to obtain a target image, wherein the position information of the target object on the field is known; The current posture of the robot is determined according to the position information of the target object on the field, the position information of the target object in the target image, the installation position of the shooting device on the robot, and the displacement of the robot.

5. The vehicle detection method according to claim 1, wherein: Determining the current position of the robot on the field includes: Obtain point cloud information on the site; Identifying point cloud information belonging to the robot from the point cloud information on the field; The current position of the robot on the field is determined based on the point cloud information belonging to the robot.

6. The vehicle detection method according to claim 1, wherein: The robot is equipped with a marking object, and determining the current position of the robot on the field includes: Obtaining the position of the marked object on the field; The current posture of the robot on the field is determined according to the posture of the marking object on the field and the installation position of the marking object on the robot.

7. The vehicle detection method according to any one of claims 1 to 6, characterized in that: After acquiring the three-dimensional point cloud data of the vehicle to be detected on the site, the method further includes: Determining a state of a designated portion of the vehicle to be detected based on the three-dimensional point cloud data of the vehicle to be detected, where the state of the designated portion includes an open state or a closed state; If the state of the designated part of the vehicle to be inspected does not meet the requirements, a prompt is issued to indicate that the state of the designated part is wrong.

8. A vehicle detection device, characterized in that: Applications in robots include: A three-dimensional point cloud data acquisition module is used to acquire three-dimensional point cloud data of the vehicle to be detected on the site; a detection point determination module, configured to determine at least one detection point on the site based on the three-dimensional point cloud data of the vehicle to be detected and a pre-stored relative position and posture, wherein the detection point is the position at which the robot is located when detecting the vehicle to be detected; a current posture determination module, configured to determine the current posture of the robot on the field during the process of the robot moving toward the detection point; a current relative posture determination module, configured to determine the current relative posture of the robot and the vehicle to be detected based on the current posture of the robot on the field and the three-dimensional point cloud data of the vehicle to be detected; A vehicle detection module is used to adjust the current relative posture according to the pre-stored relative posture corresponding to the detection point, stop moving when the current relative posture is the same as the pre-stored relative posture, and detect the vehicle to be detected. When the position point corresponding to the current relative posture is the same as the position point corresponding to the pre-stored relative posture, but the posture corresponding to the current relative posture is different from the posture corresponding to the pre-stored relative posture, adjust the posture of the robot and then detect the vehicle to be detected. When the current relative posture is different from the pre-stored relative posture, return to the step of determining the current posture of the robot on the site and subsequent steps during the process of the robot moving toward the detection point.

9. A robot comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images