Acquisition method of point cloud data

Abstract

The embodiment of the invention provides a point cloud data acquisition method, which is applied to an autonomous mobile device, and comprises the following steps: in an advancing process, obtaining position information of an obstacle on an advancing path; based on the position information and preset position information of the obstacles in a marching map, target state labels corresponding to the obstacles are determined, and the marching map is generated by the obstacles which hinder the autonomous mobile device from moving and paths among the obstacles; according to the target state tag and a preset state tag corresponding to the obstacle, determining a current point cloud collection number corresponding to the obstacle; and based on the point cloud acquisition number, acquiring point cloud data of the obstacle. According to the target state label and the preset state label corresponding to the obstacle, the current point cloud collection number corresponding to the obstacle is determined, and the point cloud data collection modes are enriched, so that the subsequent obstacle recognition accuracy is improved.

Description

Technical Field

[0001] The embodiments of the present specification relate to the field of computer technology, and in particular to a method for collecting point cloud data. Background Art

[0002] At present, in order to improve the efficiency of map construction, sensors are usually used to collect point cloud data in the area, so as to complete the map construction based on the point cloud data.

[0003] However, the collection of point cloud data is usually based on a preset total number of point clouds; if the position of objects in the map changes, it will affect the equipment traveling in the map, resulting in an inability to accurately determine the map; and, since the collection of point cloud data is evenly distributed, there is no multi-point cloud data layout for key objects, resulting in low recognition accuracy.

[0004] Therefore, how to achieve the collection of point cloud data while ensuring recognition accuracy has become a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0005] In view of this, an embodiment of this specification provides a method for collecting point cloud data. One or more embodiments of this specification also involve an autonomous mobile device, a computing device, a computer-readable storage medium and a computer program to solve the technical defects existing in the prior art.

[0006] According to a first aspect of an embodiment of this specification, a method for collecting point cloud data is provided, which is applied to an autonomous mobile device, comprising:

[0007] During the travel process, obtain the location information of obstacles on the travel path;

[0008] Determining a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles;

[0009] Determining the current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle;

[0010] Based on the point cloud collection quantity, point cloud data of the obstacle is collected.

[0011] According to a second aspect of an embodiment of this specification, an autonomous mobile device is provided, the autonomous mobile device comprising an information collection module and an information processing module, wherein:

[0012] The information acquisition module acquires the position information of obstacles on the travel path during the travel process and sends it to the information processing module;

[0013] The information processing module determines a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles; determines a current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle, and sends the current point cloud collection quantity to the information collection module;

[0014] The information collection module collects point cloud data of the obstacle based on the point cloud collection quantity.

[0015] According to a third aspect of an embodiment of this specification, a computing device is provided, including:

[0016] Memory and processor;

[0017] The memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions. When the computer executable instructions are executed by the processor, the steps of the above-mentioned point cloud data collection method are implemented.

[0018] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided, which stores computer-executable instructions, and when the instructions are executed by a processor, the steps of the above-mentioned point cloud data collection method are implemented.

[0019] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned point cloud data collection method.

[0020] An embodiment of the present specification realizes obtaining the position information of obstacles on the travel path during the travel process; determining the target state label corresponding to the obstacle based on the position information and the preset position information of the obstacle in the travel map, wherein the travel map is generated by the obstacles that hinder the movement of the autonomous mobile device and the paths between the obstacles; determining the current point cloud collection quantity corresponding to the obstacle based on the target state label and the preset state label corresponding to the obstacle; and collecting the point cloud data of the obstacle based on the point cloud collection quantity. The target state label is determined through the position information and the preset position information, thereby preliminarily determining the category of the obstacle, and the current point cloud collection quantity corresponding to the obstacle is determined based on the target state label and the preset state label, thereby further determining the category of the obstacle and the point cloud collection quantity corresponding to the category, thereby realizing the collection of obstacle point cloud data based on the point cloud collection quantity corresponding to the label, enriching the way of collecting point cloud data, so as to improve the subsequent recognition accuracy of obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a scene schematic diagram of a method for collecting point cloud data provided by an embodiment of this specification;

[0022] Figure 2 is a flow chart of a method for collecting point cloud data provided by an embodiment of this specification;

[0023] Figure 3a is a schematic diagram of relocation provided by an embodiment of this specification;

[0024] Figure 3b is a schematic diagram of map reconstruction provided by an embodiment of this specification;

[0025] Figure 4 is a flowchart of a processing process of a method for collecting point cloud data provided by an embodiment of this specification;

[0026] Figure 5 It is a structural schematic diagram of an autonomous mobile device provided by an embodiment of this specification;

[0027] Figure 6 It is a structural block diagram of a computing device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0028] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0029] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a", "said" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0030] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0031] In addition, it should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0032] First, the terms involved in one or more embodiments of this specification are explained.

[0033] Point cloud: Point cloud is a common form of data representation. Point cloud is a collection of a large number of points in three-dimensional space, which can represent information such as the surface of objects and spatial structure in the environment. Point cloud data is usually collected by some specific sensors.

[0034] Map presentation: Point cloud can be used as an intuitive 3D map presentation to store and describe geometric information in the environment. This representation is of great value for robots to perform tasks such as positioning, navigation, and obstacle avoidance.

[0035] Point cloud registration: During the map construction process, the robot needs to fuse the point cloud data captured at different times to obtain a complete map. Point cloud registration is a method for solving the best alignment transformation between point clouds, such as the ICP (Iterative Closest Point) algorithm. Through point cloud registration, local point cloud data can be integrated into a global map.

[0036] SLAM: SLAM (Simultaneous Localization and Mapping) is a technology that allows robots to simultaneously locate and map in unknown environments. In a point cloud-based SLAM system, point cloud data is not only used for map representation, but also for robot positioning. By comparing the current point cloud with the point cloud in the constructed map, the robot can estimate its own position in real time.

[0037] Point cloud segmentation and recognition: In the process of robot map construction, segmentation and recognition of point cloud data can help the robot better understand the environment. For example, by clustering, segmenting and extracting features from point cloud data, objects, ground, walls and other structures in the environment can be identified, thereby generating a more structured map.

[0038] At present, when a sweeping robot uses point cloud data to "reposition" a map, inaccurate positioning may occur due to various reasons. First, changes in the environment are a major reason why the robot cannot match the original map. When the robot creates a map, it builds a map based on the information in the current environment. When the environment changes, such as the movement of furniture and the appearance of obstacles. These changes will cause the robot to be unable to accurately locate and match the original map in subsequent tasks. Secondly, an insufficient number of distributed points in the point cloud may lead to inaccurate positioning. Currently, when the sweeping robot collects point cloud data, the collected point cloud data is limited. When the number of points in the point cloud data is not large enough, the robot may not be able to accurately determine its position, which affects its positioning accuracy on the map.

[0039] The present invention provides a new point cloud distribution method. By adopting this method, the robot can more accurately match the map during the map "repositioning" process, reducing the impact of environmental changes and the small number of point cloud distribution points. Specifically, in the "map creation" process, AI technology is used to identify the frequently moving / unchangeable attributes of the object, and a non-uniformly distributed point cloud is generated based on the distribution results. And in the "subsequent work tasks", the point cloud distribution is dynamically adjusted according to environmental changes.

[0040] In this specification, a method for collecting point cloud data is provided. This specification also involves an autonomous mobile device, a computing device, and a computer-readable storage medium, which are described in detail one by one in the following embodiments.

[0041] See also Figure 1 , Figure 1 A schematic diagram of a scene of a method for collecting point cloud data provided according to an embodiment of the present specification is shown, specifically comprising:

[0042] When the robot accurately identifies some objects through AI technology during the first mapping, it can further classify these objects into objects that are not easily changed and objects that are easy to move according to the accuracy of the recognition, and generate a non-uniformly distributed point cloud based on these classification results. Specifically, for objects that are not easily changed, more markers can be added to the point cloud to more accurately represent their position and shape. For objects that are easy to move, the distribution of the point cloud can be reduced to avoid excessive fixation of their positions. Figure 1 As shown in the figure, in the map construction, the point cloud is non-uniformly distributed according to whether the object is moving. Specifically, if the left wall is determined to be a fixed object, more point clouds are added to the left wall, while the flower pot and the chair are moving objects, the distribution of point clouds on the two objects is reduced, that is, a preset state label is set for each object.

[0043] In subsequent work tasks, the robot will determine which objects do not change frequently and which objects move frequently based on changes in the home environment. Based on these changes, the robot will dynamically adjust the number of point cloud distributions to adapt to dynamic changes in the environment; specifically, during the robot's movement, the robot obtains the position information of obstacles on the path; based on the position information and the preset position information of the obstacle in the travel map, the target state label corresponding to the obstacle is determined, wherein the travel map is generated by the obstacles that hinder the movement of the autonomous mobile device and the paths between the obstacles; based on the target state label and the preset state label corresponding to the obstacle, the current point cloud collection quantity corresponding to the obstacle is determined; based on the point cloud collection quantity, the point cloud data of the obstacle is collected.

[0044] Through the above two judgment methods, the furniture environment is marked as static / dynamic, and the number of point cloud distribution is intelligently adjusted. In the case of limited point cloud data points, more data points are distributed on objects that are not easy to change. The robot uses static objects as the basis for environmental recognition and judgment, thereby increasing the probability of successful matching of the robot in the point cloud map.

[0045] See also Figure 2 , Figure 2A flow chart of a method for collecting point cloud data provided according to an embodiment of the present specification is shown. The method is applied to an autonomous mobile device and specifically includes the following steps.

[0046] Step 202: During the traveling process, obtain the position information of obstacles on the traveling path.

[0047] The travel path refers to the area in the target area where the device can be driven, and the target area refers to the area used to perform the target business; the location information of the obstacle refers to the location information of the obstacle in the target area, for example, the coordinate value in the target area; the obstacle refers to an object occupying the target area that affects the movement of the driving device. Autonomous mobile devices specifically refer to devices that can move by themselves, such as sweeping robots, guide robots, etc.

[0048] Specifically, the point cloud data collection method of the present specification can be applied to equipment that moves in a fixed area to complete business tasks; when the equipment is moving on a path, the information collection device contained in the equipment is used to collect the position information corresponding to each obstacle on the path, and then the category of the obstacle is further determined based on the position information.

[0049] In a specific implementation of the present specification, the sweeping robot travels in an area to be cleaned; during the travel, the position information of each obstacle on the travel path is obtained, including the position coordinates of obstacles such as flower pots, chairs, tables, etc. in the area to be cleaned.

[0050] By obtaining the position information of each obstacle on the travel path during the travel process, the obstacles can be further analyzed based on the position information.

[0051] Step 204: Determine a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles.

[0052] Among them, the preset position information refers to the position information of the obstacle determined before the travel process; the target state label refers to the label indicating the movement status corresponding to the obstacle; and the travel map refers to the map containing the travel path and obstacle information.

[0053] Specifically, before determining the target state label corresponding to the obstacle based on the position information and the preset position information, it is necessary to first collect map information based on the information collection module in the device, and generate a moving map based on the map information, wherein the moving map contains preset position information corresponding to each obstacle; in actual applications, since the position of the obstacle in the moving map may change after the moving map is generated, the target state label corresponding to the obstacle is determined based on the collected position information and the preset position information in the moving map, that is, to determine whether the obstacle has moved compared to the time when the moving map is generated.

[0054] In a specific implementation of the present specification, based on the position information of obstacle A collected by the device on the travel path and the preset position information of obstacle A contained in the device, the target state label corresponding to the obstacle is determined according to the position information and the preset position information.

[0055] Further, based on the position information and the preset position information of the obstacle in the driving map, the method for determining the target state label corresponding to the obstacle may include:

[0056] Determining whether the location information is consistent with the preset location information;

[0057] If yes, it is determined that the obstacle corresponds to a static state label;

[0058] If not, it is determined that the obstacle corresponds to a dynamic state label.

[0059] Specifically, the location information is compared with the preset location information; when the location information is consistent with the preset location information, it means that the obstacle has not moved after the moving map is generated, that is, it is in a stationary state, and a static state label is set for the obstacle; when the location information is inconsistent with the preset location information, it means that the obstacle has moved after the moving map is generated, and a dynamic state label is set for the obstacle.

[0060] In a specific implementation of the present specification, if it is determined that the position information of obstacle a is consistent with the preset position information, a static state label can be set for obstacle a; if it is determined that the position information of obstacle b is inconsistent with the preset position information, a dynamic state label can be set for obstacle b.

[0061] It should be noted that the purpose of setting static status labels and dynamic status labels for obstacles in this manual is to adjust the amount of point cloud data collected for different types of obstacles. That is, when the total amount of point cloud data remains unchanged, the amount of point cloud data collected for static obstacles can be increased, and the amount of point cloud data collected for dynamic obstacles can be reduced.

[0062] After determining the target state label corresponding to the obstacle, the number of point cloud collections corresponding to the obstacle is further adjusted according to the different target state labels, including:

[0063] When the target state label corresponding to the obstacle is a static state label, increasing the number of point cloud collections of the obstacle;

[0064] When the target state label corresponding to the obstacle is a dynamic state label, the number of point cloud collections of the obstacle is reduced.

[0065] Specifically, when the target state label of the obstacle is a static state label, it means that the obstacle does not move. Since the accuracy of the recognition result is higher when identifying a fixed obstacle, the number of point cloud collections corresponding to the obstacles with static state labels can be increased to further improve the subsequent recognition accuracy of the fixed obstacles. When the target state label of the obstacle is a dynamic state label, it means that the obstacle has moved. Since the accuracy is low when identifying dynamic obstacles, the number of point cloud collections corresponding to the obstacles with dynamic state labels can be reduced to reduce the subsequent recognition calculation of moving obstacles.

[0066] It should be noted that during the movement, the position information of the obstacle may be obtained multiple times. After the position information is obtained each time or every preset number of times, the target state label corresponding to the obstacle is re-determined based on the position information and the preset position information; the number of point cloud collections corresponding to the obstacle is dynamically adjusted according to the target state label corresponding to the obstacle, so that the number of point cloud collections corresponding to fixed obstacles increases, and the number of point cloud collections corresponding to dynamic obstacles decreases.

[0067] By comparing the position information with the preset position information, the target state label of the obstacle is determined, so that the actual state of the obstacle can be further determined based on the target state label.

[0068] Step 206: Determine the current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle.

[0069] Specifically, the actual state label corresponding to the obstacle is analyzed according to the target state label and the preset state label to determine whether it is a static label or a dynamic label; if it is a static label, more point cloud data collection quantity is allocated to the obstacle; if it is a dynamic label, less point cloud data collection quantity is allocated to the obstacle, so that more point cloud data of static obstacles can be collected subsequently, thereby reducing the collection of point cloud data of dynamic obstacles and ensuring the accuracy of obstacle recognition.

[0070] In practical applications, according to the target state label and the preset state label corresponding to the obstacle, the method for determining the current point cloud acquisition quantity corresponding to the obstacle may include:

[0071] When the target state label is consistent with the preset state label, the point cloud collection quantity corresponding to the preset state label is used as the current point cloud collection quantity of the obstacle;

[0072] When the target state label is inconsistent with the preset state label, the current state label corresponding to the obstacle is determined, and the point cloud collection quantity corresponding to the current state label is used as the current point cloud collection quantity.

[0073] The preset state label refers to a state label pre-set for an obstacle, that is, whether the obstacle is static or dynamic is pre-determined based on data collected during the process of generating the moving map.

[0074] Specifically, when the target state label is consistent with the preset state label, that is, the obstacle is determined to be dynamic or static twice, the point cloud collection quantity pre-set for the obstacle can be used as the current point cloud collection quantity without the need to calculate the point cloud collection quantity again; when the target state label is inconsistent with the preset state label, the target state label can be used as the current state label, and the point cloud collection quantity corresponding to the target state label can be used as the current point cloud collection quantity. The historical point cloud collection quantity corresponding to the obstacle can also be obtained, and the current point cloud collection quantity can be determined by combining the historical point cloud collection quantity and the point cloud collection quantity corresponding to the target state label.

[0075] In a specific implementation of the present specification, the target state label and the preset state label of the obstacle chair are obtained, and it is determined that both the target state label and the preset state label identify the obstacle chair as a dynamic object, and the point cloud collection quantity corresponding to the preset state label is used as the current point cloud collection quantity.

[0076] In another specific embodiment of the present specification, the target state label and the preset state label of the obstacle chair are obtained. Since the preset state label indicates that the obstacle chair is a static object, and the target state label indicates that the obstacle is a dynamic object, the obstacle chair can be classified as a dynamic object, and the point cloud collection quantity corresponding to the target state label is used as the current point cloud collection quantity.

[0077] The current point cloud collection quantity corresponding to the obstacle is determined through the target state label and the preset state label, thereby further determining the obstacle state so as to determine the corresponding point cloud collection method based on its state.

[0078] In practical applications, before determining the current state label corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle, the method further includes:

[0079] Identify obstacles contained in the travel map;

[0080] A corresponding preset status label is set for each obstacle based on the recognition accuracy corresponding to each obstacle.

[0081] The recognition accuracy refers to the recognition accuracy of obstacles. In practical applications, the movement of dynamic obstacles will lead to a decrease in recognition accuracy. Therefore, different preset state labels can be set for obstacles based on the recognition accuracy.

[0082] Specifically, obstacles included in the moving map are identified. For example, the obstacles included in the moving map may be determined by using AI recognition; and preset status labels are set for the obstacles according to the recognition accuracy corresponding to each obstacle.

[0083] Furthermore, a corresponding preset state label is set for each obstacle based on the recognition accuracy corresponding to each obstacle, including:

[0084] Get the preset number of point clouds corresponding to each obstacle;

[0085] When the recognition accuracy is greater than a preset accuracy threshold, increasing a preset point cloud quantity corresponding to the obstacle to obtain a first point cloud quantity, and setting a preset static label for the obstacle based on the first point cloud quantity;

[0086] When the recognition accuracy is less than or equal to a preset accuracy threshold, the preset point cloud quantity corresponding to the obstacle is reduced to obtain a second point cloud quantity, and a preset dynamic label is set for the obstacle based on the second point cloud quantity.

[0087] The preset number of point clouds refers to the number of point cloud data collected for obstacles in a uniformly distributed manner; the preset accuracy threshold refers to the threshold for determining whether an obstacle is dynamic or static.

[0088] Specifically, when the recognition accuracy is greater than the preset accuracy threshold, it indicates that the obstacle is a static object, and the number of point clouds of the first preset threshold can be increased on the basis of the preset point cloud number corresponding to the obstacle to obtain the first point cloud number; when the recognition accuracy is less than or equal to the accuracy threshold, it indicates that the obstacle is a dynamic object, and the number of point clouds of the second preset threshold can be reduced on the basis of the preset point number corresponding to the obstacle to obtain the second point cloud number; it should be noted that the first preset threshold and the second preset threshold can be equal or different.

[0089] In a specific implementation of the present specification, if it is determined that the recognition accuracy of obstacle A is greater than a preset accuracy threshold, 10 is added to the preset point cloud quantity 20 corresponding to obstacle A to obtain a first point cloud quantity of 30; a preset static label is set for obstacle A based on the first point cloud quantity 30, so that point cloud data of obstacle A can be collected subsequently based on the first point cloud quantity 30.

[0090] In another specific embodiment of the present specification, if it is determined that the recognition accuracy of obstacle B is less than a preset accuracy threshold, 10 is subtracted from the preset point cloud quantity 50 corresponding to obstacle B to obtain a second point cloud quantity 40; a preset dynamic label is set for obstacle B based on the second point cloud quantity 40, so that point cloud data of obstacle B can be collected subsequently based on the second point cloud quantity 40.

[0091] The number of point cloud collections of obstacles is determined through target state labels and preset state labels, thereby enriching the method of determining the number of point cloud collections, so that point cloud data with higher recognition accuracy can be collected subsequently based on the number of point cloud collections.

[0092] Step 208: Based on the point cloud collection quantity, collect point cloud data of the obstacle.

[0093] Specifically, after determining the number of point cloud collections corresponding to the obstacle, point cloud data of the obstacle is collected based on the number of point cloud collections; further, the obstacle is identified based on the collected point cloud data.

[0094] In addition, taking the sweeping robot as an example, when starting the cleaning task, the sweeping robot first starts from the base station and rotates in place to recognize the surrounding environment. Then, the identified environmental features are matched with the built-in map to confirm its specific location on the map. This process is called "repositioning". In the case where the sweeping robot cannot match the surrounding environment features with the built-in map, the robot will perform a "map reconstruction" operation of the surrounding environment. During this process, the robot will continue to identify the surrounding environment to implement a synchronous strategy of "repositioning" and "map reconstruction" to ensure efficient and accurate map matching.

[0095] At present, when the robot is "relocalizing" and "rebuilding the map" simultaneously, the technology is limited to recording a current map ID and displaying the new map reconstruction status in the APP interface. This status may cause users to misunderstand that the original map has been lost. In fact, there are two maps and two states involved in this process: 1) The robot performs a "relocalization" operation on the original map; 2) The robot "rebuilds" a new map for the environment. These two states have not yet been fully presented.

[0096] To solve the above problem, the method of this specification stores both the original map ID and the newly created map ID, and can use a picture-in-picture method to display the two maps simultaneously. Specifically, in actual application, the method also includes:

[0097] receiving a relocation request, and determining a historical travel map corresponding to the travel path in response to the relocation request;

[0098] The current travel map is collected, and the historical travel map and relocation prompt mark are displayed.

[0099] Among them, the relocation request refers to a request for the mobile device to determine its location after startup; the historical travel map refers to the travel map pre-set in the mobile device; the relocation prompt logo refers to the multimedia information that prompts the user that the mobile device is being relocated. For example, the charging prompt logo can be at least one of the multimedia information such as text, icon, etc. The relocation prompt logo can be.

[0100] In a specific implementation of this specification, when starting a business task, the mobile device first starts from the base station and rotates in place to realize the recognition of the surrounding environment; further, the recognized environmental features are matched with the historical travel map to confirm its specific position on the map; Figure 3a As shown, the historical travel map and the relocation mark are displayed simultaneously on the screen in a picture-in-picture manner.

[0101] Furthermore, in addition to prompting the relocation, if the map needs to be rebuilt, the rebuilt map can be displayed, that is, after collecting the current travel map and displaying the historical travel map and the relocation prompt mark, it also includes:

[0102] In the case where the current traveling map is inconsistent with the historical traveling map, collecting current map information corresponding to the current traveling map;

[0103] The historical travel map and a new map constructed based on the current map information are displayed.

[0104] The current map information refers to the map information re-collected by the device in the target area; the new map refers to the map constructed based on the current map information.

[0105] Specifically, the current travel map is compared with the historical travel map. If the comparison is inconsistent, the task of rebuilding the travel map is triggered; the reconstructed new map and the historical travel map are displayed so that the user can determine the current processing status of the device.

[0106] In a specific implementation of this specification, the current travel map is compared with the historical travel map. If the comparison is inconsistent, the travel map reconstruction task is performed; during the execution process, if Figure 3b As shown, the new map and the historical travel map are displayed simultaneously in a picture-in-picture manner.

[0107] By displaying new maps, historical travel maps, and relocation prompts, the user experience can be improved, possible misunderstandings can be reduced, and clear feedback on the processing status of the mobile device can be achieved.

[0108] The point cloud data collection method of this specification obtains the position information of obstacles on the travel path during the travel process; determines the target state label corresponding to the obstacle based on the position information and the preset position information of the obstacle in the travel map, wherein the travel map is generated by the obstacles that hinder the movement of the autonomous mobile device and the paths between the obstacles; determines the current point cloud collection quantity corresponding to the obstacle based on the target state label and the preset state label corresponding to the obstacle; and collects the point cloud data of the obstacle based on the point cloud collection quantity. The target state label is determined through the position information and the preset position information, thereby preliminarily determining the category of the obstacle, and the current point cloud collection quantity corresponding to the obstacle is determined based on the target state label and the preset state label, thereby further determining the category of the obstacle and the point cloud collection quantity corresponding to the category, thereby realizing the collection of obstacle point cloud data based on the point cloud collection quantity corresponding to the label, enriching the method of collecting point cloud data, so as to improve the subsequent recognition accuracy of obstacles.

[0109] The following combination Figure 4 Taking the application of the point cloud data collection method provided in this specification in a sweeping robot as an example, the point cloud data collection method is further described. Figure 4 A processing flow chart of a point cloud data collection method provided in an embodiment of the present specification is shown, which specifically includes the following steps.

[0110] Step 402: While the sweeping robot is moving, obtain the position information of the flower pots on the moving path.

[0111] Step 404: Based on the position information and the preset position information of the flower pot in the original map, determine that the state label corresponding to the flower pot is a dynamic state label.

[0112] Specifically, the location information is compared with the preset location information. If it is determined that the location information is inconsistent with the preset location information, it means that the flower pot has moved, and a dynamic state label is set for the flower pot.

[0113] Step 406: Determine the current point cloud collection quantity corresponding to the flower pot according to the dynamic state label and the preset dynamic label corresponding to the flower pot.

[0114] Specifically, the flower pot is determined to be a dynamic object according to the dynamic state tag and the preset dynamic tag, and the number of point cloud data collection corresponding to the dynamic object is used as the current point cloud collection number.

[0115] Step 408: Based on the number of point cloud collections, collect point cloud data of the flower pot.

[0116] The point cloud data collection method of this specification obtains the position information of obstacles on the travel path during the travel process; determines the target state label corresponding to the obstacle based on the position information and the preset position information of the obstacle in the travel map, wherein the travel map is generated by the obstacles that hinder the movement of the autonomous mobile device and the paths between the obstacles; determines the current point cloud collection quantity corresponding to the obstacle based on the target state label and the preset state label corresponding to the obstacle; and collects the point cloud data of the obstacle based on the point cloud collection quantity. The target state label is determined through the position information and the preset position information, thereby preliminarily determining the category of the obstacle, and the current point cloud collection quantity corresponding to the obstacle is determined based on the target state label and the preset state label, thereby further determining the category of the obstacle and the point cloud collection quantity corresponding to the category, thereby realizing the collection of obstacle point cloud data based on the point cloud collection quantity corresponding to the label, enriching the way of collecting point cloud data, so as to improve the subsequent recognition accuracy of obstacles.

[0117] See also Figure 5 , Figure 5 A schematic diagram of the structure of an autonomous mobile device provided according to an embodiment of the present specification is shown, wherein the autonomous mobile device comprises an information collection module and an information processing module, specifically including:

[0118] The information acquisition module 502 acquires the position information of obstacles on the travel path during the travel process and sends it to the information processing module;

[0119] The information processing module 504 determines a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles; determines a current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle, and sends the current point cloud collection quantity to the information collection module;

[0120] The information collection module 502 collects point cloud data of the obstacle based on the point cloud collection quantity.

[0121] The autonomous mobile device of the present specification determines the target state label through the position information and the preset position information, thereby preliminarily determining the category of the obstacle, and determines the current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label, thereby further determining the category of the obstacle and the point cloud collection quantity corresponding to the category, thereby realizing the collection of obstacle point cloud data based on the point cloud collection quantity corresponding to the label, enriching the way of collecting point cloud data, so as to improve the subsequent recognition accuracy of obstacles.

[0122] The above is a schematic scheme of a point cloud data collection method of this embodiment applied to an autonomous mobile device. It should be noted that the technical solution of the autonomous mobile device and the technical solution of the point cloud data collection method described above belong to the same concept, and the details not described in detail in the technical solution of the autonomous mobile device can be referred to the description of the technical solution of the point cloud data collection method described above.

[0123] Figure 6 The block diagram of a computing device 600 according to an embodiment of the present specification is shown. The components of the computing device 600 include but are not limited to a memory 610 and a processor 620. The processor 620 is connected to the memory 610 via a bus 630, and the database 650 is used to store data.

[0124] The computing device 600 also includes an access device 640, which enables the computing device 600 to communicate via one or more networks 660. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 640 may include one or more of any type of network interface (e.g., a network interface card (NIC)) of wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0125] In one embodiment of the present specification, the above components of the computing device 600 and Figure 6 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 6 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0126] The computing device 600 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 600 may also be a mobile or stationary server.

[0127] The processor 620 is used to execute the following computer executable instructions, which, when executed by the processor, implement the steps of the above-mentioned point cloud data collection method.

[0128] The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned point cloud data collection method belong to the same concept, and the details not described in detail in the technical scheme of the computing device can be referred to the description of the technical scheme of the above-mentioned point cloud data collection method.

[0129] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned point cloud data collection method.

[0130] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned point cloud data collection method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned point cloud data collection method.

[0131] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned point cloud data collection method.

[0132] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned point cloud data collection method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned point cloud data collection method.

[0133] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0134] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of patent practice. For example, in some regions, according to patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0135] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0136] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can well understand and use this specification. This specification is only limited by the claims and their full scope and equivalents.

Claims

1. A method for collecting point cloud data, characterized in that: Applications in autonomous mobile devices, including: During the travel process, obtain the location information of obstacles on the travel path; Determining a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles; Determining the current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle; Based on the point cloud collection quantity, point cloud data of the obstacle is collected.

2. The method according to claim 1, characterized in that Determining a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in the moving map includes: Determining whether the location information is consistent with the preset location information; If yes, it is determined that the obstacle corresponds to a static state label; If not, it is determined that the obstacle corresponds to a dynamic state label.

3. The method according to claim 2, characterized in that The method further comprises: When the target state label corresponding to the obstacle is a static state label, increasing the number of point cloud collections of the obstacle; When the target state label corresponding to the obstacle is a dynamic state label, the number of point cloud collections of the obstacle is reduced.

4. The method according to claim 1, characterized in that Before determining the current state label corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle, the method further includes: Identify obstacles contained in the travel map; A corresponding preset status label is set for each obstacle based on the recognition accuracy corresponding to each obstacle.

5. The method according to claim 4, characterized in that A corresponding preset status label is set for each obstacle based on the recognition accuracy corresponding to each obstacle, including: Get the preset number of point clouds corresponding to each obstacle; When the recognition accuracy is greater than a preset accuracy threshold, increasing a preset point cloud quantity corresponding to the obstacle to obtain a first point cloud quantity, and setting a preset static label for the obstacle based on the first point cloud quantity; When the recognition accuracy is less than or equal to a preset accuracy threshold, the preset point cloud quantity corresponding to the obstacle is reduced to obtain a second point cloud quantity, and a preset dynamic label is set for the obstacle based on the second point cloud quantity.

6. The method according to claim 1, characterized in that Determining the current point cloud acquisition quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle includes: When the target state label is consistent with the preset state label, the point cloud collection quantity corresponding to the preset state label is used as the current point cloud collection quantity of the obstacle; When the target state label is inconsistent with the preset state label, the current state label corresponding to the obstacle is determined, and the point cloud collection quantity corresponding to the current state label is used as the current point cloud collection quantity.

7. The method according to claim 1, characterized in that The method further comprises: receiving a relocation request, and determining a historical travel map corresponding to the travel path in response to the relocation request; The current travel map is collected, and the historical travel map and relocation prompt mark are displayed.

8. The method according to claim 7, characterized in that After collecting the current travel map and displaying the historical travel map and the relocation prompt mark, the method further includes: In the case where the current traveling map is inconsistent with the historical traveling map, collecting current map information corresponding to the current traveling map; The historical travel map and a new map constructed based on the current map information are displayed.

9. An autonomous mobile device, characterized in that: The autonomous mobile device comprises an information collection module and an information processing module, wherein: The information acquisition module acquires the position information of obstacles on the travel path during the travel process and sends it to the information processing module; The information processing module determines a target state label corresponding to the obstacle based on the position information and preset position information of the obstacle in a moving map, wherein the moving map is generated by obstacles that hinder the movement of the autonomous mobile device and paths between the obstacles; determines a current point cloud collection quantity corresponding to the obstacle according to the target state label and the preset state label corresponding to the obstacle, and sends the current point cloud collection quantity to the information collection module; The information collection module collects point cloud data of the obstacle based on the point cloud collection quantity.

10. A computing device, characterized in that include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method described in any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the method described in any one of claims 1 to 8.

Images