Map construction method and device, robot, storage medium and computer program product

Abstract

The invention relates to a map construction method and device, a robot and a storage medium. The method comprises the steps of obtaining multiple different types of environment data collected by different types of sensors on a preset robot; generating a positioning map based on the plurality of different types of environmental data, and drawing a topological map based on the positioning map; and distributing the positioning map and the topological map to a plurality of types of robots. The map construction method can be suitable for scheduling multiple different types of robots in the same operation scene, and the operation efficiency is high.

Description

Technical Field

[0001] The present application relates to the field of robotics technology, and in particular to a map construction method, device, robot, storage medium and computer program product. Background Art

[0002] With the rapid development of machine learning and perception technology, the application scope of intelligent robots is becoming more and more extensive. Restaurants, shopping malls, banks and other commercial places can all use intelligent robots to improve work efficiency and reduce labor costs. In some application scenarios, there may be multiple robots of different types performing different tasks at the same time. For example, in a hotel scenario, the cleaning robot is performing cleaning tasks, the guide robot is guiding guests, and the food delivery robot is delivering food to the guest's room.

[0003] In a multi-category robot operation scenario similar to the above, multiple robots of the same type can be scheduled based on the same positioning map and topology map because they use the same positioning map and the topology map formed based on the same positioning map. However, robots of different categories use different positioning sensors, which leads to different positioning methods, and the generated positioning maps and topology maps are also different, so they cannot be scheduled uniformly. Summary of the invention

[0004] Based on this, it is necessary to provide a map construction method, device, robot, computer-readable storage medium and computer program product to address the above-mentioned technical problems, which can be used to schedule multiple different types of robots in the same operating scenario.

[0005] In a first aspect, the present application provides a map construction method, the map construction method comprising:

[0006] Acquire multiple different types of environmental data collected by different types of sensors on a preset robot;

[0007] Generate a positioning map based on the multiple different types of environmental data, and draw a topological map based on the positioning map;

[0008] The positioning map and the topology map are distributed to robots of multiple categories.

[0009] In one embodiment, the preset robot includes a main body sensor fixed on the preset robot and an external sensor plugged into the preset robot; the multiple categories of robots are respectively equipped with different types of main body sensors according to each category.

[0010] In one embodiment, generating a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map includes:

[0011] Based on the multiple different types of environmental data, generating sub-positioning maps corresponding to the types of environmental data respectively according to corresponding mapping algorithms;

[0012] Performing spatial position alignment processing on the sub-positioning maps to obtain a composite positioning map with the sub-positioning maps as layers;

[0013] A new topological map layer is created on the composite positioning map, and topological path elements are drawn on the topological map layer to form the topological map.

[0014] In one embodiment, distributing the positioning map and the topology map to multiple categories of robots includes: distributing each of the sub-positioning maps and the topology map to each category of robots according to the type of sensors installed on the robots of each category.

[0015] In one embodiment, generating a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map includes:

[0016] Respectively obtain timestamps of the multiple different types of environmental data;

[0017] According to the timestamp, aligning the multiple different types of environmental data in time series;

[0018] The environmental data after the alignment process is fused to obtain a fused positioning map;

[0019] Topological path elements are drawn on the fused positioning map to form the topological map.

[0020] In one of the embodiments, distributing the positioning map and the topology map to multiple categories of robots includes: distributing the fused positioning map and the topology map to the multiple categories of robots.

[0021] In a second aspect, the present application provides a map construction device. The device comprises:

[0022] A data acquisition module, used to acquire multiple different types of environmental data collected by different types of sensors on a preset robot;

[0023] A map drawing module, used for generating a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map;

[0024] The map distribution module is used to distribute the positioning map and the topology map to robots of multiple categories.

[0025] In a third aspect, the present application further provides a robot comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the map construction method described in any one of the above embodiments are implemented.

[0026] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the map construction method described in any of the above embodiments are implemented.

[0027] In a fifth aspect, the present application further provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the map construction method described in any one of the above embodiments are implemented.

[0028] The above-mentioned map construction method, device, storage medium and computer program product obtain multiple different types of environmental data collected by different types of sensors on a preset robot; generate a positioning map based on the multiple different types of environmental data, and draw a topological map based on the positioning map; distribute the positioning map and the topological map to multiple categories of robots. Since different types of environmental data are collected by the preset robot running at the same time, the positioning map constructed based on the different types of environmental data has a high consistency, and then the topological map drawn based on the positioning map with high consistency has consistency. After distributing the above-mentioned positioning map and topological map to different types of robots, different types of robots can be uniformly scheduled in the same operation scene because they have positioning maps and topological maps with good consistency. In addition, by plugging in external sensors to the preset robot, only one environmental data collection work is required to complete the construction of positioning maps for multiple different types of robots, and the operation efficiency is high. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of a process of a map construction method in one embodiment;

[0030] Figure 2 A schematic diagram of the positioning sensor composition of a preset robot in one embodiment;

[0031] Figure 3 This is a flow chart of an implementation of step S140 in an embodiment;

[0032] Figure 4This is a flow chart of another implementation of step S140 in one embodiment;

[0033] Figure 5 It is a structural block diagram of a map construction device in one embodiment;

[0034] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described below are only used to explain the present application and are not used to limit the present application.

[0036] In order to make the purpose, technical solutions and advantages of this application more clear, in each embodiment of the following text of this application, three types of robots in the hotel scene in the above background technology part are used as examples, among which the cleaning robot is used to perform cleaning tasks, the guide robot is used to guide guests into the elevator or hotel room, and the food delivery robot is configured to deliver food to the guest room. It should be understood that the specific embodiments described below are only used to explain this application and are not used to limit this application.

[0037] It is understandable that different types of robots are equipped with sensors for perception and positioning, and the generation of positioning maps is based on the environmental data collected by these sensors. Commonly used positioning sensors include but are not limited to lidar, road sign cameras, wide-angle cameras, etc.

[0038] Assume that the cleaning robot, guide robot and food delivery robot in the above hotel scene have positioning sensors fixed on their bodies respectively being lidar, road sign recognition camera and wide-angle camera. For the sake of convenience, the three different types of robots are respectively recorded as Class A robots, Class B robots and Class C robots.

[0039] In the prior art, a Class A robot collects laser feature data (generally referred to as a laser point cloud) through its fixed laser radar sensor, and constructs a laser positioning map based on the laser feature data, and then draws a topological map based on the laser positioning map, and finally runs and performs tasks in the hotel operation scenario based on the positioning map and the topological map. Multiple robots belonging to the same category of Class A robots (such as A1 robots, A2 robots, and A3 robots) can be uniformly and freely dispatched in this scenario. The same is true for Class B robots and Class C robots.

[0040] However, since the three different categories of robots A, B, and C use different positioning methods, the positioning maps they construct and the topological maps formed based on their positioning maps are also different. Therefore, when the three robots A, B, and C perform work tasks at the same time in the hotel operation scenario, they cannot be uniformly scheduled due to the inconsistency of the maps, and conflicts may even occur.

[0041] Based on this, in order to solve the above-mentioned technical problems, an embodiment of the present application provides a map construction method, which can be applied to the above-mentioned distributed application scenarios of multiple categories of robots, and can realize the scheduling of multiple different categories of robots in the same operating scenario.

[0042] like Figure 1 As shown, a map construction method according to an embodiment of the present application includes:

[0043] Step S120, obtaining a plurality of different types of environmental data collected by different types of sensors on a preset robot;

[0044] Step S140, generating a positioning map based on a plurality of different types of environmental data, and drawing a topological map based on the positioning map;

[0045] Step S160, distributing the positioning map and the topology map to robots of multiple categories.

[0046] Among them, the preset robot refers to a robot that uses multiple different types of positioning sensors to simultaneously collect multiple different types of environmental data.

[0047] In one embodiment, the preset robot includes a body sensor fixed on the preset robot and an external sensor plugged into the preset robot. Multiple categories of robots are respectively equipped with different types of body sensors according to each category. In other words, the preset robot can be arbitrarily selected from the above-mentioned multiple different categories of robots that need to run in the same scene at the same time. The preset robot not only includes its own fixed body sensor, but can also carry positioning sensors of other categories of robots in the same operation scene by plugging. Of course, it should be understood that the preset robot needs to preset the interface of the external sensor in hardware and software, which is the inherent meaning of the preset robot being able to carry external sensors.

[0048] Based on the above embodiments, it can be understood that before step S120, the step is also included: selecting one robot of any category of robots among multiple different categories of robots in the same operating scene as a preset robot, such as the A1 robot among the Class A robots, and connecting the positioning sensors of other categories of robots to the preset robot by plugging them in.

[0049] In another embodiment, the preset robot is equipped with a plurality of different types of positioning sensors, and the types of its built-in positioning sensors cover other types of robots running in the same scene at the same time. That is, the preset robot only includes the main body sensor, and does not carry external sensors by plugging in. For example, the A1 robot among the Class A robots is equipped with a laser radar sensor, a road sign recognition camera sensor, and a wide-angle camera sensor, the Class B robot is equipped with any one of the laser radar sensor, the road sign recognition camera sensor, and the wide-angle camera sensor, and the Class C robot is equipped with any one of the laser radar sensor, the road sign recognition camera sensor, and the wide-angle camera sensor that is different from the Class B robot. At this time, the Class A robot can be used as the preset robot, and the types of its built-in positioning sensors cover other types of robots running in the hotel scene at the same time.

[0050] The robot is configured to collect multiple types of environmental data simultaneously through multiple different types of positioning sensors. Different types of data represent the environmental information in the same operating scenario in different forms. Figure 2 As shown, a robot A1 belonging to the class A robots is equipped with a laser radar sensor (i.e., the body sensor of the class A robot itself). It is selected as the preset robot and is also connected with the following external sensors: a road sign recognition camera sensor (i.e., the body sensor of the class B robot) and a wide-angle camera sensor (i.e., the body sensor of the class C robot). The preset robot A1 simultaneously collects three different types of environmental data, namely, laser feature data, road sign feature data, and scene feature data, through the laser radar sensor, the road sign recognition camera sensor, and the wide-angle camera sensor. Different types of environmental data represent the environmental information in the same operating scene in different forms.

[0051] In one embodiment, the position of the external sensor plugged into the preset robot is consistent with the position of the main body sensor of the robot corresponding to the type of external sensor. That is, the position of the road sign recognition camera sensor plugged into the A1 robot is consistent with the position of the road sign recognition camera sensor fixed on the B-type robot; the position of the wide-angle camera sensor plugged into the A1 robot is consistent with the position of the wide-angle camera sensor fixed on the C-type robot. With this arrangement, the position of the external sensor plugged into the preset robot is consistent with the position where the sensor is fixed as the main body sensor of the corresponding category of robot, which can ensure that the collection of this type of environmental data and the application of the map constructed based on this type of environmental data have a consistent spatial coordinate system.

[0052] In the method of the embodiment of the present application, since different types of environmental data are collected by the preset robots running at the same time, the positioning maps constructed based on the above different types of environmental data have high consistency, and then the topological maps drawn based on the highly consistent positioning maps have consistency. After the above positioning maps and topological maps are distributed to different types of robots, different types of robots can be uniformly scheduled in the same operation scene because they have positioning maps and topological maps with good consistency. In addition, the above map construction method is implemented by plugging the preset robot into an external sensor. It only needs to perform one environmental data collection work to complete the construction of positioning maps for multiple different types of robots, and the operation efficiency is high.

[0053] Specifically, we continue to use the three types of robots in the above hotel scene as an example for explanation. We take the A1 robot among the A-type robots as the preset robot, and plug the road sign recognition camera sensor (i.e., the body sensor of the B robot) and the wide-angle camera sensor (i.e., the body sensor of the C robot) into its body as external sensors. By running the preset robot A1, the laser radar sensor, road sign recognition camera sensor, and wide-angle camera sensor on the preset robot A1 are used to simultaneously obtain the laser feature data, road sign feature data, and scene feature data collected by three different types of sensors; then, a positioning map is generated based on these three different types of environmental data, and a topological map is drawn based on the positioning map; finally, the positioning map and the topological map are distributed to the three types of robots A, B, and C, so that they can be uniformly scheduled in the hotel operation scene to perform their respective tasks. Since the laser feature data, road sign feature data and scene feature data are collected by the preset robot A1 running simultaneously, the positioning map constructed based on the three different types of environmental data has a high consistency, and the topological map drawn based on the highly consistent positioning map has consistency. After the above positioning map and topological map are distributed to the three robots A, B, and C, the three different types of robots A, B, and C have positioning maps and topological maps with good consistency. Therefore, when they perform their respective tasks in the above hotel scene, they can be uniformly dispatched, which is conducive to improving overall work efficiency and avoiding conflicts.

[0054] It should be noted that in the same operation scene, multiple robots of a certain category can be running at the same time. For example, in the above hotel scene, there can be multiple cleaning robots A1, A2, A3... performing cleaning operations at the same time, or multiple food delivery robots C1, C2, C3... delivering food to guests in different rooms at the same time. However, as mentioned above, the scheduling of multiple robots (such as robots A1, A2, and A3) belonging to a certain category of robots (such as robots of category A) belongs to the content of the prior art and is not the key to this application. Therefore, it will not be elaborated in this application, and for the convenience of explanation, each category of robots is simplified to one.

[0055] In one embodiment, the execution entity for obtaining multiple different types of environmental data in step S120 is a preset robot; the execution entity for generating a positioning map based on environmental data in step S140 and distributing the positioning map and topological map to multiple categories of robots in step S160 can be selected from a host computer, an industrial computer, a dispatching center, a physical server or a cloud server; of course, the preset robot can also serve as the execution entity of the above actions to complete map construction and map distribution as well as other scheduling tasks under certain conditions, for example, having a certain computing power and being able to communicate with robots of other categories.

[0056] The topological map described in step S140 is also called a topological path map, which is composed of topological elements such as waypoints and paths. It is built on a positioning map (such as a laser point cloud positioning map). It is usually formed by operators manually taking points on the constructed positioning map as waypoints, and then connecting the roads into paths. Therefore, the step of drawing a topological map based on the positioning map in step S140 is usually drawn by operators through relevant programs on devices such as host computers and industrial computers that act as dispatch centers. These paths need to cover all drivable channels, and waypoints need to cover all forks. They are channels in the physical world and are abstract descriptions of driving resources that robots can call during business operations.

[0057] In one embodiment, if Figure 3 As shown, a positioning map is generated based on multiple different types of environmental data, and a topological map is drawn based on the positioning map (i.e., step S140), which specifically includes:

[0058] Step 341, based on multiple different types of environmental data, generate sub-positioning maps corresponding to the environmental data types according to corresponding mapping algorithms, wherein each sub-positioning map is obtained by mapping based on a corresponding single type of environmental data, and can be used to locate the corresponding type of robot and obtain a topological map;

[0059] Step 343, performing spatial position alignment processing on each sub-positioning map to obtain a composite positioning map with each sub-positioning map as a layer;

[0060] Step 345: create a new topological map layer on the composite positioning map, draw topological path elements on the topological map layer, and obtain a topological map.

[0061] In the map construction method of this embodiment, different types of environmental data are not fused, but different types of sub-positioning maps are constructed separately based on their respective types, and then each sub-positioning map is used as a layer of a composite positioning map, and finally the composite positioning map is used as a base map to draw a topological map. Figure 2 Taking the preset robot A1 as an example, the laser feature data, road sign feature data and scene feature data collected by the preset robot A1 are not fused, but are separately constructed into a laser positioning map, a road sign positioning map and a scene positioning map; then, the three types of sub-positioning maps (laser positioning map, road sign positioning map and scene positioning map) are used as layers to form a composite positioning map; finally, a blank topological map layer is created on the composite positioning map, and topological elements are drawn on the topological map layer to obtain a topological map. Because different types of environmental data are not fused, the overall calculation amount is relatively small, the processing speed is faster, and the efficiency is higher.

[0062] In the above embodiment, based on multiple different types of environmental data, each sub-positioning map corresponding to the type of environmental data is generated according to the corresponding mapping algorithm (i.e., in step S341). Since the specific mapping algorithm does not belong to the invention of the present application, it is not described here in detail. For example, a laser point cloud positioning map is obtained by performing frame matching based on the laser feature data collected by the laser radar sensor. The specific frame matching algorithm can be used, but is not limited to the commonly used iterative closest point (ICP) algorithm, the gradient-based matching method (Optimization-based Method), and the inter-frame matching likelihood field method (Correlation-based Method, CSM). Similarly, based on the landmark feature data collected by the landmark recognition camera sensor, a landmark positioning map can be obtained through landmark matching. The specific method of landmark matching can be adopted, but is not limited to the method based on Harris, Shi-Tomasi and other corner point matching; scene feature point matching is performed according to the scene feature data collected by the wide-angle camera sensor to obtain a scene positioning map, which means performing scene feature point matching according to the scene feature data collected by the wide-angle camera sensor, stitching together images with the same feature points through feature matching, transforming images from multiple different perspectives to the same perspective, and stitching them into a wide-field image, i.e., a scene positioning map.

[0063] In one embodiment, each sub-positioning map is spatially aligned to obtain a composite positioning map with each sub-positioning map as a layer (i.e., step S343), further comprising: using the different sub-positioning maps as different layers, selecting the parts with the same features in each sub-positioning map as a reference for superposition, and superimposing them into a composite positioning map, so that each sub-positioning map layer has as many features as possible overlapped; then, further, a new topological map layer is created on the composite positioning map, and topological path elements (waypoints, paths, etc.) are drawn on the topological map layer, and the topological map is saved. In this way, the topological map is formed based on the above-mentioned different sub-positioning maps at the same time, and its formation process takes into account the environmental data collected by different types of positioning sensors, so it can be well used for scheduling the above-mentioned multiple different categories of robots.

[0064] Further, based on the above implementation, at this time, distributing the positioning map and the topology map to multiple categories of robots (i.e., step S160) specifically means distributing each of the sub-positioning maps and the topology map to each category of robots according to the type of the body sensor fixed to each category of the robots. That is, the laser positioning map and the above topology map, the landmark positioning map and the above topology map, the scene positioning map and the above topology map are sent to the A-type robot, the B-type robot, and the C-type robot, respectively.

[0065] In another embodiment, Figure 4 As shown, a positioning map is generated based on multiple different types of environmental data, and a topological map is drawn based on the positioning map (i.e., step S140), which specifically includes:

[0066] Step 441: respectively obtain timestamps of the multiple different types of environmental data;

[0067] Step 443: aligning the multiple different types of environmental data in time series according to the timestamp;

[0068] Step 445: fusing the environmental data after the alignment process to obtain a fused positioning map;

[0069] Step 447: Draw topological path elements on the fused positioning map to obtain the topological map.

[0070] The map construction method of this embodiment fuses different types of environmental data after alignment to obtain a unified fused positioning map; then draws topological path elements on the fused positioning map to obtain the topological map. Figure 2 Taking the preset robot A1 shown in the figure as an example, the laser feature data, road sign feature data and scene feature data collected by the preset robot A1 are aligned and then fused to obtain a unified fused positioning map; finally, topological elements are drawn on the fused positioning map to obtain a topological map. Due to the different characteristics of each sensor, the environmental data information they obtain has its own advantages and disadvantages. If the advantages of the three types of sensors can be comprehensively utilized and the data of the three types of sensors can be fused, a more accurate and dense positioning map can be provided in the robot positioning and mapping tasks, and the accuracy of robot positioning and map construction can also be improved.

[0071] It should be understood that the environmental data collected by the positioning sensor is a kind of time series data, including the collection time point of the environmental data (i.e., timestamp) and the environmental data result corresponding to the collection time point. Therefore, different types of environmental data collected by different types of positioning sensors on the preset robot all have timestamps; Figure 2As shown, it can be understood that the laser feature data collected by the laser radar sensor on the preset robot A1, the road sign feature data collected by the road sign recognition camera sensor, and the scene feature data collected by the wide-angle camera sensor all have their respective corresponding timestamps. Step S443 aligns multiple different types of environmental data in time series through timestamps, so that different types of environmental data can be synchronized on the same time coordinate and complement each other.

[0072] It should be noted that the data alignment processing method is a commonly used technical means in this field, which is usually implemented through interpolation methods such as linear interpolation, polynomial interpolation or spline interpolation. Since it is not the invention or innovation of this application, it will not be elaborated here.

[0073] In order to ensure that multiple different types of environmental data have the same starting collection time point (i.e., the timestamps are aligned at the initial moment) and reduce the workload of subsequent alignment processing, in one embodiment, before the preset robot collects different types of environmental data through different types of robots, it is necessary to ensure that the clock source is unified in hardware. In this regard, a common practice is to set a pulse generator, and all positioning sensors of different types on the preset robot are triggered by the pulse signal emitted by the pulse generator.

[0074] It should be understood that before aligning various types of environmental data in time series (ie, step S443), a step of preprocessing the data is also included, for example, calibrating and denoising the laser feature data to effectively remove noise and outliers in the point cloud.

[0075] Further, based on the above implementation, at this time, distributing the positioning map and the topology map to multiple categories of robots (i.e., step S160) specifically means distributing each of the fused positioning maps and the topology map to each of the categories of robots. That is, the same fused positioning map and topology map are sent to robots of category A, robots of category B, and robots of category C, respectively.

[0076] In an optional embodiment, distributing the positioning map and the topology map to multiple categories of robots (step S160) further includes: first packaging the sub-positioning map or fused positioning map and the topology map into a map package, and then distributing the map package to multiple categories of robots respectively; after receiving the map package, the robot of each category parses it to obtain the aforementioned topology map and its own sub-positioning map or fused positioning map. Distributing maps in the form of map packages facilitates the transmission and encryption of map data.

[0077] In an optional embodiment, the map construction method further comprises, after step S120, the step of uninstalling the external sensor plugged into the preset robot. After the external sensor completes the work of collecting environmental data, uninstalling it from the preset robot is conducive to reducing the load and energy consumption of the robot and avoiding forgetting or losing the external sensor.

[0078] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0079] Based on the same inventive concept, the embodiment of the present application also provides a map construction device for implementing the map construction method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more map construction device embodiments provided below can refer to the limitations on the robot executing the map construction method above, and will not be repeated here.

[0080] In one embodiment, Figure 5 As shown, a map construction device is provided, comprising:

[0081] The data acquisition module 520 is used to acquire a plurality of different types of environmental data collected by different types of sensors on a preset robot;

[0082] A map drawing module 540, configured to generate a positioning map based on the plurality of different types of environmental data, and draw a topological map based on the positioning map;

[0083] The map distribution module 560 is used to distribute the positioning map and the topology map to robots of multiple categories.

[0084] In one embodiment, the preset robot includes a main body sensor fixedly mounted on the preset robot and an external sensor plugged into the preset robot; the robots of the multiple categories are respectively equipped with the different types of main body sensors according to each category.

[0085] In one embodiment, the mapping module 540 is used to:

[0086] Based on the multiple types of environmental data, generating sub-positioning maps corresponding to the types of environmental data respectively according to corresponding mapping algorithms;

[0087] Performing spatial position alignment processing on the sub-positioning maps to obtain a composite positioning map with the sub-positioning maps as layers;

[0088] A new topological map layer is created on the composite positioning map, and topological path elements are drawn on the topological map layer to form the topological map.

[0089] Based on the above example, the map distribution module 560 is used to:

[0090] The sub-positioning maps and the topological maps are distributed to robots of each category according to the types of sensors installed on the robots of each category.

[0091] In another embodiment, the map drawing module 540 is used to:

[0092] Respectively obtain timestamps of the multiple different types of environmental data;

[0093] According to the timestamp, aligning the multiple different types of environmental data in time series;

[0094] The environmental data after the alignment process is fused to obtain a fused positioning map;

[0095] Topological path elements are drawn on the fused positioning map to form the topological map.

[0096] Based on the above example, the map distribution module 560 is used to:

[0097] The fused positioning map and the topological map are combined and distributed to the robots of the multiple categories.

[0098] Each module in the above-mentioned map construction device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of the processor in the robot in the form of hardware, or can be stored in the memory in the robot in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0099] In one embodiment, a computer device is also provided, whose internal structure diagram can be as follows: Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the robot is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external robot in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a map construction method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0100] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0101] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0102] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0103] 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 this application 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 relevant laws, regulations and standards of relevant countries and regions.

[0104] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0105] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0106] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A map construction method, characterized in that: The map construction method comprises: Acquire multiple different types of environmental data collected by different types of sensors on a preset robot; Generate a positioning map based on the multiple different types of environmental data, and draw a topological map based on the positioning map; The positioning map and the topology map are distributed to robots of multiple categories.

2. The map construction method according to claim 1, characterized in that: The preset robot includes a main body sensor fixedly mounted on the preset robot and an external sensor plugged into the preset robot; the robots of the multiple categories are respectively provided with the different types of main body sensors according to each category.

3. The map construction method according to claim 2, characterized in that: The generating of a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map, includes: Based on the multiple different types of environmental data, generating sub-positioning maps corresponding to the types of environmental data respectively according to corresponding mapping algorithms; Performing spatial position alignment processing on the sub-positioning maps to obtain a composite positioning map with the sub-positioning maps as layers; A new topological map layer is created on the composite positioning map, and topological path elements are drawn on the topological map layer to obtain the topological map.

4. The map construction method according to claim 3, characterized in that: The distributing the positioning map and the topology map to multiple categories of robots includes: distributing each of the sub-positioning maps and the topology map to each category of robots according to the type of sensors installed on the robots of each category.

5. The map construction method according to claim 2, characterized in that: The generating of a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map, includes: Respectively obtain timestamps of the multiple different types of environmental data; According to the timestamp, aligning the multiple different types of environmental data in time series; The environmental data after the alignment process is fused to obtain a fused positioning map; Topological path elements are drawn on the fused positioning map to obtain the topological map.

6. The map construction method according to claim 5, characterized in that: The distributing the positioning map and the topology map to robots of multiple categories includes: distributing the fused positioning map and the topology map to robots of multiple categories.

7. A map construction device, characterized in that: The device comprises: A data acquisition module, used to acquire multiple different types of environmental data collected by different types of sensors on a preset robot; A map drawing module, used for generating a positioning map based on the multiple different types of environmental data, and drawing a topological map based on the positioning map; The map distribution module is used to distribute the positioning map and the topology map to robots of multiple categories.

8. A robot comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the map construction method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the map construction method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the map construction method according to any one of claims 1 to 6 are implemented.

Images