CN117928514A

CN117928514A - Topology map construction method, control method, device, equipment and storage medium

Info

Publication number: CN117928514A
Application number: CN202311848641.8A
Authority: CN
Inventors: 宫睿; 吴德明; 王斌
Original assignee: Shenzhen Zhumang Technology Co ltd
Current assignee: Shenzhen Zhumang Technology Co ltd
Priority date: 2023-12-28
Filing date: 2023-12-28
Publication date: 2024-04-26

Abstract

The embodiment of the application provides a topology map construction method, a control method and device of self-mobile equipment, the self-mobile equipment and a storage medium. The method comprises the following steps: acquiring a point cloud map of a target scene needing topology map construction; moving to an external keypoint in response to a first external operation indicating that the mobile device is moved to the external keypoint, the external keypoint indicating a pre-calibrated scene location point in the target scene; determining that the external key points correspond to topological nodes in the point cloud map; determining a topological relationship between different topological nodes based on a response to the first external operation; and generating a topological map of the target scene according to the topological nodes and the topological relation. The application aims to construct a topological map with richer semantic information based on the point cloud map, and reduces the construction cost of the topological map.

Description

Topology map construction method, control method, device, equipment and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method for constructing a topology map, a method for controlling a self-mobile device, a device for constructing a topology map, a self-mobile device, and a computer readable storage medium.

Background

The topological map is a map composed of topological nodes and topological relations, and can abstract the environment into a plurality of topological nodes with topological relations, so that the storage burden of map data can be effectively reduced, and meanwhile, the topological structure enables the self-mobile device to directly utilize the map to carry out path planning tasks and scene recognition tasks, so that the self-mobile device is widely used in the work of the self-mobile device.

In the related art, the topology map is mainly constructed by laser SLAM (Simultaneous Localization AND MAPPING, instant localization and mapping). Specifically, the laser SLAM may obtain a dense point cloud in the scene, and obtain a grid map according to the dense point cloud, so as to convert the grid map into a topological map. However, because of the high cost of obtaining a dense point cloud based on laser SLAM, the cost of building a topological map by way of laser SLAM is also relatively high.

Disclosure of Invention

The application provides a topology map construction method, a control method of self-mobile equipment, a topology map construction device, self-mobile equipment and a computer readable storage medium, aiming at constructing a topology map with richer semantic information based on a point cloud map and reducing construction cost of the topology map.

In order to achieve the above object, the present application provides a method for constructing a topological map, the method comprising:

acquiring a point cloud map of a target scene needing topology map construction;

Controlling the self-mobile device to move to an external key point in response to a first external operation indicating the self-mobile device to move to the external key point, wherein the external key point indicates a pre-calibrated scene position point in the target scene;

determining that the external key points correspond to topological nodes in the point cloud map;

Determining a topological relationship between different topological nodes based on a response to the first external operation;

and generating a topological map of the target scene according to the topological nodes and the topological relation.

In addition, to achieve the above object, the present application further provides a control method of a self-mobile device, the method including:

Obtaining a topological map of a target scene, wherein the topological map is generated according to topological nodes and topological relations, the topological nodes are obtained by determining positions of external key points in the target scene in a point cloud map of the target scene, and the topological relations are determined by responding to external operations indicating a first self-mobile device to move to the external key points;

Determining a current location and a target location of the second self-mobile device;

Determining a moving path of the second self-moving device according to the topological map, the current position and the target position;

and controlling the second self-mobile device to move from the current position to the target position based on the moving path.

In addition, in order to achieve the above object, the present application also provides a device for constructing a topological map, including:

the acquisition module is used for acquiring a point cloud map of a target scene which needs to be constructed by the topological map;

The mobile module is used for responding to an external operation indicating the self-mobile device to move to an external key point, and controlling the self-mobile device to move to the external key point, wherein the external key point indicates a scene position point calibrated in advance in the target scene;

The topological node determining module is used for determining topological nodes in the point cloud map corresponding to the external key points;

A topology relationship determination module for determining a topology relationship between different topology nodes based on a response to the first external operation;

And the topology map construction module is used for generating a topology map of the target scene according to the topology nodes and the topology relation.

In addition, to achieve the above object, the present application also provides a self-mobile device including a memory and a processor; the memory is used for storing a computer program; the processor is configured to execute the computer program and implement the steps of the method for constructing a topological map and the steps of the method for controlling the self-mobile device according to any one of the embodiments of the present application when the computer program is executed.

In addition, to achieve the above object, the present application further provides a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to implement the steps of the topology map construction method according to any one of the embodiments of the present application, and the steps of the control method of the self-mobile device.

The topology map construction method, the control method of the self-mobile device, the topology map construction device, the self-mobile device and the computer readable storage medium disclosed by the embodiment of the application can acquire the point cloud map of the target scene required to be constructed by the topology map, provide a foundation for the construction of the subsequent topology map and realize clearer scene understanding. And further controlling movement from the mobile device to an external keypoint in response to a first external operation indicating movement from the mobile device to the external keypoint, wherein the external keypoint indicates a pre-calibrated scene location point in the target scene. Further, it may be determined that the external keypoints correspond to topological nodes in the point cloud map, and a topological relationship between different topological nodes is determined based on a response to the first external operation. Finally, a topological map of the target scene can be generated according to the topological nodes and the topological relation, and the topological nodes and the topological relation provide the relevance information among all the position points in the target scene, so that the topological map generated based on the topological nodes and the topological relation has path planning and navigation capability. Compared with the prior art that the cost for constructing the topological map by using the laser SLAM is high, the method can acquire the topological map based on the point cloud map construction, and the construction cost of the topological map is reduced because the laser SLAM is not needed in the process.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of a method for constructing a topological map according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a second flow of a topology map construction method according to an embodiment of the present application

FIG. 3 is a schematic flow chart of generating a topological map of a target scene according to an embodiment of the present application;

Fig. 4 is a schematic flow chart of acquiring a point cloud map according to an embodiment of the present application;

Fig. 5 is a flow chart of a control method of a self-mobile device according to an embodiment of the present application;

FIG. 6 is a schematic block diagram of a topology map construction apparatus provided by an embodiment of the present application;

fig. 7 is a schematic block diagram of a computer device provided by an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations. In addition, although the division of the functional modules is performed in the apparatus schematic, in some cases, the division of the modules may be different from that in the apparatus schematic.

The term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.

Some embodiments of the present application are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.

Referring to fig. 1 and fig. 2, fig. 1 is a first flow diagram of a topology map construction method according to an embodiment of the present application; fig. 2 is a second flow diagram of a topology map construction method according to an embodiment of the present application. As shown in fig. 1, the method for constructing the topological map includes steps S11 to S15.

Step S11: and acquiring a point cloud map of the target scene needing to be topologically constructed.

The target scene is a scene needing to be topologically constructed, and the application is not limited to this, for example, the target scene includes an indoor scene, an outdoor scene, and the like, which can be specifically set according to the requirement of the self-mobile device.

It should be noted that a point cloud map is a map for representing a data structure of points in a three-dimensional space, which is generally used for modeling and describing objects or environments in the real world. The point cloud in the point cloud map can be obtained through a mode of a visual sensor such as laser scanning, radar or photography, and a large number of discrete coordinate points are formed. The point cloud map is widely applied in the fields of automatic driving, building design, geographic Information Systems (GIS), virtual reality and the like, and is used for reconstructing and analyzing real-world space information.

Optionally, the point cloud map is a sparse point cloud map. Wherein the sparse point cloud map represents a relatively sparse, rather than dense, distribution of point clouds in the map. Since in sparse point cloud maps only key points in the target scene (typically salient features of the environment such as walls, pillars or other important structures) need to be saved, each possible point need not be saved. Therefore, by using a sparse point cloud map, it is possible to reduce the storage requirements of the map and to improve the processing efficiency while retaining an effective representation of the environmentally important information.

Further, the sparse point cloud map may be obtained by means of visual SLAM (Simultaneous Localization AND MAPPING). Specifically, after the image information of the target scene is acquired through the vision sensor, the image information of the target scene can be processed through the vision SLAM (Simultaneous Localization AND MAPPING), so that a sparse point cloud is obtained to be used for constructing a sparse point cloud map, and further, the construction of the topological map is realized based on the sparse point cloud map. Compared with the prior art that dense point clouds in a scene are obtained through laser SLAM, and a grid map is obtained according to the dense point clouds, and then the grid map is converted into a topological map, the method and the device can obtain the sparse point cloud map through visual SLAM, so that the topological map is constructed, and the construction cost of the topological map is reduced.

It should be noted that visual SLAM is a technique for enabling a self-mobile device or other device to locate its own position and construct a map at the same time in an unknown environment. It mainly uses visual sensors (e.g. cameras) to capture image information within a scene to enable continuous identification of feature points in the surrounding environment and uses these feature points to locate the position of the device or to construct a point cloud map. Compared with the laser SLAM hardware which is a laser radar and the visual SLAM hardware which is a visual sensor, the cost for obtaining the point cloud map by using the visual SLAM is lower, so that the construction cost of the subsequent topological map can be reduced.

In the embodiment of the application, the point cloud map of the target scene which needs to be constructed by the topological map can be obtained, so that a foundation is provided for the construction of the subsequent topological map, and clearer scene understanding is realized.

Step S12: and controlling the movement from the mobile device to the external key point in response to a first external operation indicating the movement from the mobile device to the external key point, wherein the external key point indicates a pre-calibrated scene position point in the target scene.

Step S13: and determining that the external key points correspond to topological nodes in the point cloud map.

Wherein the first external operation is an external operation indicating movement from the mobile device to an external key point.

It should be noted that, the external key point is a location point with a unique feature, for example, when the target scene is a restaurant, the external key point may be a distribution location point of the restaurant, may be a turning point of a path in the restaurant, or may be customized according to a user's requirement, which is not limited in the present application.

Specifically, a first external operation indicating movement from the mobile device to an external keypoint may be received, and movement from the mobile device to the external keypoint may be controlled in response to the first external operation. Further, the point cloud map generated in the first step can be used as a global map to determine the position of the self-mobile device in each external key point relative to the point cloud map, and the position is used as a topological node of the topological map, so that the traversal of each external key point and the determination of the topological node in the topological map are realized.

In the embodiment of the application, the mobile equipment can be controlled to move to the external key points in response to the first external operation so as to realize the traversal of the external key points, and further, the topology nodes corresponding to the external key points are determined based on the point cloud map, so that a foundation is provided for the construction of the topology map.

Step S14: based on the response to the first external operation, a topological relationship between the different topological nodes is determined.

Step S15: and generating a topological map of the target scene according to the topological nodes and the topological relation.

Specifically, after obtaining the topology nodes of the topology map, the operation of traversing each topology node may be repeated based on the response to the first external operation to determine the topology relationship between the different topology nodes. Wherein, the topological relation comprises a connectivity relation, an adjacent relation and the like among topological nodes, and the application is not limited to the above. Thus, a topological map of the target scene can be generated according to the topological nodes and the topological relation for realizing positioning, navigation and path planning of the self-mobile device.

Optionally, after generating the topological map of the target scene according to the topological nodes and the topological relation, the method further comprises: controlling the mobile device to move within the preset range of each external key point in response to a second external operation indicating the mobile device to move within the preset range of the external key point; determining topology nodes corresponding to external key points in a point cloud map; determining a new topology relationship between the different topology nodes based on the response to the second external operation; and updating the topological map of the target scene according to the new topological relation.

Wherein the second external operation is an external operation within a preset range indicating movement from the mobile device to an external key point.

The preset range of the present application is not limited, and may be, for example, a range of 5cm around the external key point, a range of 10cm around the external key point, or the like, and may be specifically set according to the need.

Since the position of the topology node may not be accurately reached when the self-mobile device traverses the topology node again, after receiving the second external operation, the self-mobile device may be instructed to move to within a preset range of the external key point in response to the second external operation, so that the self-mobile device can traverse the corresponding topology node within the preset range of the external key point. Further, a new topological relationship (e.g., a new adjacency relationship or connectivity relationship) between the different topological nodes may be determined based on the response to the second external operation. Thus, the new topological relation can be updated to the original topological map, and the update of the topological map can be realized.

In the embodiment of the application, the topological relation among different topological nodes can be determined based on the response to the first external operation, and then the topological map of the target scene is generated according to the topological nodes and the topological relation. In addition, updating of the topology map may also be achieved in accordance with a response to the second external operation. Therefore, the real-time performance and the accuracy of the topological map are maintained, and the self-mobile device can position and navigate in a changed environment and understand the structure of the target scene.

As shown in fig. 2, the self-mobile device (another type is described as a mobile robot) may complete the initialization of the point cloud map of the target scene through the visual SLAM (i.e., SLAM system), thereby obtaining the point cloud map of the target scene. Further, the movement from the mobile device to the external keypoints may be controlled in response to a first external operation indicating movement from the mobile device to the external keypoints to determine that the external keypoints correspond to topological nodes in the point cloud map to traverse the topological nodes (e.g., coordinates recorded in the point cloud map). Furthermore, the topological relation among the topological nodes can be determined, so that a topological map can be constructed based on the topological nodes and the topological relation.

In addition, after the topology map is constructed, a new topology relationship between different topology nodes can be determined in response to a second external operation. Thus, the new topology relationship can be updated to the original topology map.

The method for constructing the topological map can acquire the point cloud map of the target scene required to be constructed by the topological map, provides a basis for the construction of the subsequent topological map, and realizes clearer scene understanding. And further controlling movement from the mobile device to an external keypoint in response to a first external operation indicating movement from the mobile device to the external keypoint, wherein the external keypoint indicates a pre-calibrated scene location point in the target scene. Further, it may be determined that the external keypoints correspond to topological nodes in the point cloud map, and a topological relationship between different topological nodes is determined based on a response to the first external operation. Finally, a topological map of the target scene can be generated according to the topological nodes and the topological relation, and the topological nodes and the topological relation provide the relevance information among all the position points in the target scene, so that the topological map generated based on the topological nodes and the topological relation has path planning and navigation capability. Compared with the prior art that the cost for constructing the topological map by using the laser SLAM is high, the method can acquire the topological map based on the point cloud map construction, and the construction cost of the topological map is reduced because the laser SLAM is not needed in the process.

Referring to fig. 3, fig. 3 is a flowchart illustrating a topology map of a target scene according to an embodiment of the present application. As shown in fig. 3, the topological relation includes a connection relation, and the generation of the topological map of the target scene according to the topological node and the topological relation can be realized through steps S151 to S153.

Step S151: a number of topological nodes having a connection relationship are determined as traversable paths.

Step S152: and acquiring the weight of each passable path, wherein the weight is used for reflecting the priority degree of the passable path.

Step S153: and generating a topological map of the target scene according to each passable path and the weight thereof.

In particular, a number of topological nodes in the topological map having connection relationships may be determined as passable paths to represent that the self-mobile device is capable of moving in passable paths formed by the topological nodes having connection relationships. Further, a weight for each traversable path can be obtained for determining a priority of the traversable paths based on the weights. Thus, a topological map of the target scene can be generated according to the passable path and the corresponding weight thereof. For example, the traversable paths can be used as edges in a topological map while preserving the corresponding weights to generate a topological map of the target scene.

In the embodiment of the application, the trafficability among paths and the weight of the trafficable paths, namely the priority degree, can be considered in the construction process of the topological map of the target scene. Therefore, the topology map constructed based on the passable paths and the weights can help to improve the navigation effect of the self-mobile device in the target scene, and the self-mobile device can select an appropriate path to move more intelligently.

Optionally, acquiring the weight of each passable path includes: acquiring path influence indexes of each passable path, wherein the path influence indexes comprise at least one of path distance, path time consumption, path danger degree and environment information quantity of the path; and determining the weight of each passable path according to the path influence index.

Specifically, for each passable path, a corresponding path impact index may be obtained, so as to evaluate the priority of the passable path, and further obtain a corresponding weight. Wherein, different path impact indexes can be combined according to preset rules (such as calculating a mean value or calculating a sum, etc.) to calculate the weight of the corresponding passable path; the weight of the corresponding passable path can be determined by selecting only one path influence index according to the requirement, and the application is not limited to the above.

The path influence index includes at least one of path distance, path time consumption, path risk degree, and path environmental information amount, which is not limited in the present application. Where path distance represents the length of the traversable path, typically by measuring the distance between topological nodes. It will be appreciated that a trafficable path having a shorter path distance is preferred over a trafficable path having a longer path distance, and thus the trafficable path having a shorter path distance is generally weighted more than the trafficable path having a longer path distance.

The path elapsed time represents the time required to traverse a traversable path from the mobile device. It will be appreciated that a traversable path that is less time consuming than a traversable path that is more time consuming than a path, and therefore the traversable path that is less time consuming than a path is typically weighted more than the traversable path that is more time consuming.

The path hazard level indicates the hazard level of the passable path, which may be affected by environmental conditions, obstacles, and the like. It will be appreciated that trafficable paths with less path risk are prioritized over trafficable paths with greater path risk, and thus trafficable paths with less path risk are typically weighted more than trafficable paths with less path risk.

The environmental information amount of the path represents environmental information of the area through which the path passes, possibly including key landmarks, special structures, or other environmental related information. It will be appreciated that a trafficable path having a greater amount of environmental information for a path is preferred over a trafficable path having a lesser amount of environmental information for a path, and thus the trafficable path having a greater amount of environmental information for a path is generally weighted more than the trafficable path having a lesser amount of environmental information for a path.

In the embodiment of the application, the weight of the corresponding passable path can be determined based on various path influence indexes, so that the topological map constructed based on the weight can be provided for the path which is suitable for specific conditions and requirements of the self-mobile equipment, and the intelligence and the adaptability of the path planning of the self-mobile equipment are improved.

Referring to fig. 4, fig. 4 is a flowchart of acquiring a point cloud map according to an embodiment of the present application. As shown in fig. 4, the acquisition of the point cloud map of the target scene requiring topology map construction may be realized through steps S111 to S112.

Step S111: visual images of different space positions in a target scene are acquired, and the visual images are acquired through a visual sensor.

Step S112: and constructing a point cloud map of the target scene according to the visual image.

Specifically, visual images of different spatial locations within the target scene may be acquired using visual sensors (e.g., cameras, etc.). For example, a user may move in a target scene from a mobile device via a remote control such as a cell phone, remote control, voice, etc., to obtain visual images of different spatial locations within the target scene. Further, the acquired visual images may be processed using visual SLAM techniques to construct a point cloud map of the target scene. The point cloud map is a three-dimensional map composed of discrete point coordinates, namely a sparse point cloud map.

It can be appreciated that, because the cost of using the visual SLAM technique is low, the cost of generating the point cloud map based on the visual SLAM technique is also low. In addition, the constructed point cloud map also provides a foundation for the construction of a subsequent topological map, so that clearer scene understanding is realized.

Optionally, constructing a point cloud map corresponding to the target scene includes: determining whether path loop is generated between the space positions corresponding to different visual images according to the feature similarity between the different visual images; if yes, optimizing paths among the spatial positions corresponding to different visual images through a loop algorithm to obtain optimized paths; and constructing a point cloud map based on the optimized path.

The self-mobile device may generate position offset in the moving process, so that an error may occur in the point cloud map. Therefore, in order to reduce the error of the point cloud map, it is also possible to determine whether a path loop is generated between the spatial positions corresponding to the different visual images by analyzing the feature similarity between the different visual images. It can be appreciated that when the feature similarity between different visual images is high, it means that a path loop is generated between the corresponding spatial positions, that is, the robot returns to the spatial position visited previously from the mobile device.

Further, after determining that the path loop is generated, the loop algorithm can be used for optimizing the paths between the spatial positions corresponding to different visual images to obtain the optimized paths. It can be appreciated that the optimized path can reflect the real motion trail of the self-mobile device in the target scene, and noise influence caused by sensor errors and the like is reduced. Therefore, a point cloud map with higher accuracy can be constructed based on the optimized path.

It should be noted that the present application is not limited to the type of the loop algorithm, and includes, for example, graph optimization, pose graph optimization, factor graph optimization, etc., for adjusting the estimated spatial positions of the self-mobile device at different time points and optimizing the paths between the spatial positions.

In the embodiment of the application, whether the self-mobile equipment generates a path loop or not in the moving process can be determined, and after the path loop is determined to be generated, the paths among the spatial positions corresponding to different visual images are optimized through a loop algorithm, so that a point cloud map with higher accuracy can be constructed based on the optimized paths.

Referring to fig. 5, fig. 5 is a flowchart illustrating a control method of a self-mobile device according to an embodiment of the application. As shown in fig. 5, control of the self-mobile device may be achieved through steps S21 to S24.

Step S21: the method comprises the steps of obtaining a topological map of a target scene, wherein the topological map is generated according to topological nodes and topological relations, the topological nodes are obtained by determining positions of external key points in the target scene in a point cloud map of the target scene, and the topological relations are determined by responding to external operations indicating that a first self-mobile device moves to the external key points.

Step S22: a current location of the second self-mobile device and a target location are determined.

Step S23: and determining the moving path of the second self-moving device according to the topological map, the current position and the target position.

Step S24: and controlling the second self-mobile device to move from the current position to the target position based on the moving path.

The first mobile device is a self-mobile device for constructing a topological map; the second self-mobile device is the self-mobile device to be subjected to path planning; the target location is a location to be reached by the second self-mobile device.

Specifically, a topological map of the target scene may be obtained. The topological map is generated according to topological nodes and topological relations, the topological nodes are obtained by determining positions of external key points in a target scene in a point cloud map of the target scene, and the topological relations are determined by responding to external operations indicating the first self-mobile device to move to the external key points. Reference should be made in particular to the above embodiments, which are not intended to be limiting in order to avoid repetition.

Since different location points in the target scene and the connection relationship between them are described in the pre-constructed topological map. Thus, after determining the current location and the target location of the second self-mobile device, a movement path between the current location and the target location may be determined from the topology map. Thereby, the second self-moving device can be controlled to move from the current position to the target position according to the movement path.

In the embodiment of the application, the topological map of the target scene can be generated according to the topological nodes and the topological relation, and then the path planning of the self-mobile equipment is realized based on the topological map, so that the self-mobile equipment can accurately navigate to the target position set by the user in an unknown or dynamic environment.

Referring to fig. 6, fig. 6 is a schematic block diagram of a topology map construction apparatus according to an embodiment of the present application. The topology map construction device can be configured in a server for executing the topology map construction method.

As shown in fig. 5, the topology map construction apparatus 200 includes: an acquisition module 201, a mobile module 202, a topology node determination module 203, a topology relationship determination module 204, and a topology map construction module 205.

An acquisition module 201, configured to acquire a point cloud map of a target scene that needs to be constructed by a topology map;

a moving module 202, configured to control the self-mobile device to move to an external key point in response to an external operation indicating the self-mobile device to move to the external key point, where the external key point indicates a pre-calibrated scene position point in the target scene;

a topology node determining module 203, configured to determine that the external key point corresponds to a topology node in the point cloud map;

a topology relationship determination module 204 for determining a topology relationship between different topology nodes based on a response to the first external operation;

the topology map construction module 205 is configured to generate a topology map of the target scene according to the topology nodes and the topology relationship.

The topology map construction module 205 is further configured to determine a plurality of topology nodes having the connection relationship as passable paths; acquiring a weight of each passable path, wherein the weight is used for reflecting the priority degree of the passable path; and generating a topological map of the target scene according to each passable path and the weight thereof.

The topology map construction module 205 is further configured to obtain a path impact indicator of each passable path, where the path impact indicator includes at least one of a path distance, a path time consumption, a path risk degree, and an environmental information amount of the path; and determining the weight of each passable path according to the path influence index.

The acquisition module 201 is further configured to acquire visual images of different spatial positions in the target scene, where the visual images are acquired by a visual sensor; and constructing a point cloud map of the target scene according to the visual image.

The obtaining module 201 is further configured to determine whether a path loop is generated between spatial positions corresponding to different visual images according to feature similarities between the different visual images; if yes, optimizing paths among the spatial positions corresponding to the different visual images through a loop algorithm to obtain optimized paths; and constructing the point cloud map based on the optimized path.

The topology map construction module 205 is further configured to control the self-mobile device to move within a preset range of each of the external keypoints in response to a second external operation indicating that the self-mobile device moves within the preset range of the external keypoints; determining that the external key points correspond to topological nodes in the point cloud map; determining a new topological relation between the different topological nodes based on the response to the second external operation; and updating the topological map of the target scene according to the new topological relation.

It should be noted that, for convenience and brevity of description, specific working processes of the above-described apparatus and each module, unit may refer to corresponding processes in the foregoing method embodiments, which are not repeated herein.

The inventive methods are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.

By way of example, the methods, apparatus described above may be implemented in the form of a computer program that is executable on a self-mobile device as shown in fig. 7.

Referring to fig. 7, fig. 7 is a schematic diagram of a self-mobile device according to an embodiment of the application. The self-mobile device may be a server.

As shown in fig. 7, the self-mobile device 400 includes a processor 401, a memory 402, and a network interface connected through a system bus, wherein the memory 402 may include a volatile storage medium, a nonvolatile storage medium, and an internal memory.

The non-volatile storage medium may store an operating system and a computer program. The computer program comprises program instructions which, when executed, cause the processor 401 to perform any of the methods of constructing a topological map and the method of controlling a self-mobile device.

The processor 401 serves to provide computing and control capabilities, supporting the operation of the entire self-mobile device 400.

The internal memory provides an environment for the execution of a computer program in the non-volatile storage medium, which when executed by the processor, causes the processor to perform any of the methods of constructing a topological map and the method of controlling the self-mobile device.

The network interface is used for network communication such as transmitting assigned tasks and the like. It will be appreciated by those skilled in the art that the architecture of the computer device is merely a block diagram of some of the structures associated with the present application and is not limiting of the self-mobile device 400 to which the present application may be applied, and that a particular self-mobile device 400 may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.

It should be appreciated that the Processor 401 may be a central processing unit (Central Processing Unit, CPU), and the Processor 401 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Wherein in some embodiments the processor 401 is configured to execute a computer program stored in a memory to implement the steps of: acquiring a point cloud map of a target scene needing topology map construction; controlling the self-mobile device to move to an external key point in response to a first external operation indicating the self-mobile device to move to the external key point, wherein the external key point indicates a pre-calibrated scene position point in the target scene; determining that the external key points correspond to topological nodes in the point cloud map; determining a topological relationship between different topological nodes based on a response to the first external operation; and generating a topological map of the target scene according to the topological nodes and the topological relation.

In some embodiments, the processor 401 is further configured to determine a number of topological nodes having the connection relationship as passable paths; acquiring a weight of each passable path, wherein the weight is used for reflecting the priority degree of the passable path; and generating a topological map of the target scene according to each passable path and the weight thereof.

In some embodiments, the processor 401 is further configured to obtain a path impact indicator of each passable path, where the path impact indicator includes at least one of a path distance, a path time consumption, a path risk level, and an environmental information amount of the path; and determining the weight of each passable path according to the path influence index.

In some embodiments, the processor 401 is further configured to acquire visual images of different spatial positions in the target scene, where the visual images are acquired by a visual sensor; and constructing a point cloud map of the target scene according to the visual image.

In some embodiments, the processor 401 is further configured to determine whether a path loop is generated between spatial positions corresponding to different visual images according to feature similarities between the different visual images; if yes, optimizing paths among the spatial positions corresponding to the different visual images through a loop algorithm to obtain optimized paths; and constructing the point cloud map based on the optimized path.

In some embodiments, the processor 401 is further configured to control the self-mobile device to move within a preset range of each of the external keypoints in response to a second external operation indicating that the self-mobile device moves within a preset range of the external keypoints; determining that the external key points correspond to topological nodes in the point cloud map; determining a new topological relation between the different topological nodes based on the response to the second external operation; and updating the topological map of the target scene according to the new topological relation.

In some embodiments, the processor 401 is further configured to obtain a topology map of a target scene, the topology map being generated according to topology nodes obtained by determining locations of external keypoints in the target scene in a point cloud map of the target scene, and a topology relationship determined by responding to an external operation indicating a first slave mobile device to move to the external keypoints; determining a current location and a target location of the second self-mobile device; determining a moving path of the second self-moving device according to the topological map, the current position and the target position; and controlling the second self-mobile device to move from the current position to the target position based on the moving path.

The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium is stored with a computer program, the computer program comprises program instructions, and the program instructions realize the construction method of any topological map and the control method of the self-mobile device when being executed.

The computer readable storage medium may be an internal storage unit of the computer device according to the foregoing embodiment, for example, a hard disk or a memory of the computer device. The computer readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided on the computer device.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like.

While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims

1. A method of constructing a topological map, the method comprising:

2. The method of claim 1, wherein the topological relation comprises a connection relation, and wherein the generating the topological map of the target scene according to the topological node and the topological relation comprises:

determining a plurality of topological nodes with the connection relation as passable paths;

acquiring a weight of each passable path, wherein the weight is used for reflecting the priority degree of the passable path;

And generating a topological map of the target scene according to each passable path and the weight thereof.

3. The method of claim 2, wherein the obtaining the weight of each traversable path comprises:

Obtaining a path influence index of each passable path, wherein the path influence index comprises at least one of path distance, path time consumption, path danger degree and path environment information quantity;

and determining the weight of each passable path according to the path influence index.

4. The method according to claim 1, wherein the obtaining a point cloud map of a target scene requiring topology mapping comprises:

visual images of different spatial positions in the target scene are acquired, and the visual images are acquired through a visual sensor;

and constructing a point cloud map of the target scene according to the visual image.

5. The method of claim 4, wherein the constructing the point cloud map corresponding to the target scene comprises:

Determining whether path loop is generated between the spatial positions corresponding to different visual images according to the feature similarity between the different visual images;

If yes, optimizing paths among the spatial positions corresponding to the different visual images through a loop algorithm to obtain optimized paths;

And constructing the point cloud map based on the optimized path.

6. The method according to any one of claims 1 to 5, wherein after generating a topological map of the target scene from the topological nodes and the topological relationships, the method further comprises:

Controlling the self-mobile device to move within a preset range of each external key point in response to a second external operation indicating the self-mobile device to move within the preset range of the external key point;

determining a new topological relation between the different topological nodes based on the response to the second external operation;

And updating the topological map of the target scene according to the new topological relation.

7. A method of controlling a self-mobile device, the method comprising:

8. A topology map construction apparatus, comprising:

9. A self-moving device, comprising: a memory and a processor; wherein the memory is connected to the processor for storing a program, the processor being configured to implement the steps of the method of constructing a topological map according to any one of claims 1 to 6 and the steps of the method of controlling a self-mobile device according to claim 7 by running the program stored in the memory.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, causes the processor to implement the steps of the topology map construction method of any one of claims 1 to 6, and to implement the steps of the control method of the self-mobile device of claim 7.