Elevator space state determination method, device, apparatus, and storage medium

Abstract

The application discloses an elevator space state judgment method and device and a computer readable storage medium, and is used for improving the safety of a robot entering an elevator. The method part comprises the following steps: judging whether a robot is aligned with an elevator door; if the robot is aligned with the elevator door, acquiring image information of a region in front of the robot and projection information of the robot itself; and judging a space state of the elevator according to the image information of the region in front of the robot and the projection information of the robot itself.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, and in particular to an elevator space state judgment method, device, equipment and computer readable storage medium. BACKGROUND

[0002] In the process of autonomous elevator riding of an intelligent mobile robot, it is necessary to perceive whether the area in front of the robot is an elevator entrance, whether the elevator car door is open, and whether the internal space of the elevator after opening is sufficient for accommodation. The inventor realizes that in the traditional scheme, the robot perceives the elevator space state as an ordinary scene environment, that is, as ordinary obstacle recognition. However, the elevator has certain particularity. Once the elevator space state is abnormal, the robot recklessly triggers the operation of the robot entering the elevator, which may be dangerous and has low safety. SUMMARY

[0003] The present application provides an elevator space state judgment method, device and computer equipment storage medium to solve the problem of low safety when triggering the robot to enter the elevator in the traditional scheme.

[0004] In a first aspect, an elevator space state judgment method is provided, comprising:

[0005] judging whether a robot is aligned with an elevator entrance;

[0006] if the robot is aligned with the elevator entrance, acquiring image information of an area in front of the robot and projection information of the robot itself;

[0007] judging a space state of the elevator according to the image information of the area in front of the robot and the projection information of the robot itself.

[0008] Further, the image information of the elevator entrance area includes a two-dimensional obstacle graph corresponding to an obstacle in front of the robot, and the projection information of the robot itself includes a two-dimensional projection of the robot. The judgment of the space state of the elevator according to the image information of the area in front of the robot and the projection information of the robot itself comprises:

[0009] performing binaryzation processing on the two-dimensional obstacle graph to acquire a target binary graph;

[0010] performing connected domain labeling on the target binary graph to acquire each connected domain of the target binary graph;

[0011] comparing the radius of the largest inscribed circle of each connected domain with the radius of the smallest circumscribed circle of the two-dimensional projection of the robot to acquire a target connected domain in which the radius of the largest inscribed circle is greater than a preset threshold value;

[0012] The region where the robot is projected is taken as an initial region, and region growing is performed on the target connected domain to obtain a final connected domain;

[0013] The spatial state of the elevator is determined according to the final connected domain.

[0014] Further, the determination of the spatial state of the elevator according to the final connected domain comprises:

[0015] A target position is determined in the final connected domain, which satisfies a preset distance from the center of the initial region;

[0016] When the actual position corresponding to the target position is in the elevator, it is determined that the spatial state of the elevator is an accessible state;

[0017] When the actual position corresponding to the target position is not in the elevator, it is determined that the spatial state of the elevator is an inaccessible state.

[0018] Further, the determination of the target position in the final connected domain, which satisfies a preset distance from the center of the initial region, comprises:

[0019] In the final connected domain, a position farthest from the center of the initial region in the Euclidean distance is determined as the target position.

[0020] Further, the determination of whether the robot is aligned with the elevator door comprises:

[0021] A two-dimensional H-shaped template graph is obtained in advance;

[0022] The two-dimensional obstacle graph and the two-dimensional H-shaped template graph are shape matched;

[0023] When matched, it is determined that the robot is aligned with the elevator door;

[0024] When not matched, it is determined that the robot is not aligned with the elevator door.

[0025] Further, the shape matching of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph comprises:

[0026] The shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle graph and the shape of the two-dimensional H-shaped template graph is determined;

[0027] When the shape matching error degree is less than a preset error threshold, it is determined that the shapes of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph are matched;

[0028] When the shape matching error degree is greater than or equal to a preset error threshold, it is determined that the two-dimensional obstacle graph and the two-dimensional zigzag template graph shape are not matched.

[0029] In a second aspect, an elevator space state determination device is provided, comprising:

[0030] A first determination module is configured to determine whether a robot is aligned with an elevator door.

[0031] An acquisition module is configured to acquire image information of a region in front of the robot and projection information of the robot itself if the robot is aligned with the elevator door.

[0032] A second determination module is configured to determine a space state of the elevator according to the image information of the region in front of the robot and the projection information of the robot itself.

[0033] An elevator space state determination device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the elevator space state determination method when executing the computer program.

[0034] A computer readable storage medium stores a computer program, and the computer program implements the steps of the elevator space state determination method when executed by a processor.

[0035] In one scheme of the elevator space state determination method, device, and storage medium, when it is determined that the robot is aligned with the elevator door, the image information of the region in front of the robot and the projection information of the robot itself are acquired, and then whether the robot collides with an obstacle during entering the elevator is determined according to the image information of the region in front of the robot and the projection information of the robot itself, so that the space state of the elevator is determined, and whether the elevator can be entered is accurately determined, thereby effectively improving the safety of the robot entering the elevator. BRIEF DESCRIPTION OF DRAWINGS

[0036] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort on the basis of these drawings.

[0037] Figure 1 is a flowchart of an elevator space state determination method in the embodiments of the present application;

[0038] Figure 2 is Figure 1A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0039] Figure 3 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps: Figure 2 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0040] Figure 4 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps: Figure 1 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0041] Figure 5 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0042] Figure 6 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0043] Figure 7 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps: DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0045] The embodiments of the present application provide a method for judging the space state of an elevator and a corresponding device for judging the space state of an elevator, which are applied to various intelligent robots with moving functions. In order to improve the safety of the intelligent robots when they enter an elevator, the embodiments of the present application correspondingly provide a method for judging the space state of an elevator, which will be described in detail below.

[0046] Please refer to Figure 1 , Figure 1 A flowchart of one embodiment of the method for judging the space state of an elevator according to the present application is shown in FIG. 1, which comprises the following steps:

[0047] S10: judging whether the robot is aligned with the elevator door.

[0048] Nowadays, intelligent robots are applied to various application scenarios such as restaurants, offices, exhibition halls, etc. to complete certain specific work by the robots. In such application scenarios, the robots usually need to take an elevator. In order to ensure the accuracy and improve the safety during the process of the robot taking an elevator, the robot needs to be aligned with the elevator door, and after judging that the elevator is accessible, the robot is controlled to move to the elevator according to the aligned elevator door to complete the taking work. Therefore, when the robot needs to take an elevator, it is necessary to first judge whether the robot is aligned with the elevator door.

[0049] S20: If the robot is aligned with the elevator entrance, obtain image information of the area in front of the robot and the robot's own projection information.

[0050] S30: Determine the spatial state of the elevator based on the image information of the area in front of the robot and the robot's own projection information.

[0051] For steps S20-S30, after determining that the robot is aligned with the elevator entrance, further safety assessments are needed to improve the robot's safety upon entering the elevator. This involves acquiring image information of the area in front of the robot and the robot's own projection information. The image information of the area in front of the robot shows obstacles and other conditions in that area. Since the robot is already aligned with the elevator entrance, this image information reflects the situation in the elevator entrance area. The robot's own projection information reflects its size. Therefore, based on the image information of the area in front of the robot and its own projection information, it is possible to further determine whether the robot encounters obstacles during its entry into the elevator, assess the elevator's spatial state, and accurately determine whether entry into the elevator is permitted, effectively improving the robot's safety upon entering the elevator.

[0052] It should be noted that, in this embodiment of the invention, there are multiple ways to determine the spatial state of the elevator based on the image information of the area in front of the robot and the projection information of the robot itself. In one embodiment, the image information of the elevator entrance area includes a two-dimensional obstacle map corresponding to the obstacle in front of the robot, and the projection information of the robot itself includes a two-dimensional projection of the robot. Specifically, the spatial state of the elevator can be determined based on the two-dimensional obstacle map corresponding to the obstacle in front of the robot and the two-dimensional projection of the robot, which will be described below.

[0053] In one embodiment, such as Figure 2 As shown, the image information of the elevator entrance area includes a two-dimensional obstacle map corresponding to the obstacle in front of the robot, and the projection information of the robot itself includes a two-dimensional projection of the robot. In step S30, that is, based on the image information of the area in front of the robot and the projection information of the robot itself, the spatial state of the elevator is determined, which specifically includes the following steps:

[0054] S31: Perform binarization on the two-dimensional obstacle map to obtain the target binary map.

[0055] After judging that the robot is aligned with the elevator entrance, the obtained two-dimensional obstacle map is binarized to obtain a target binary image. As an example, the two-dimensional obstacle map is a top view formed by two-dimensional projection of point cloud data of obstacles in front of the robot, and the top view reflects the distribution of obstacles in front of the robot. Since the robot is aligned with the elevator entrance at this time, the top view reflects the elevator in front of the robot. It should be noted that in some embodiments, the two-dimensional obstacle map can also be a top view formed by two-dimensional projection of other three-dimensional images of obstacles in front of the robot.

[0056] In the embodiments of the present application, a point cloud data collector can be arranged at a preset position of the robot, and the point cloud data collector is used to collect point cloud data of the object in front of the robot. As an example, the point cloud data collector uses an RGBD camera and a laser radar as a point cloud data collector to collect corresponding point cloud data of the object in front of the robot, and the specific implementation is not limited. It can be seen that the point cloud data of the obstacle in front of the robot can be obtained in real time by using the point cloud data collector arranged on the robot. It should be noted that the point cloud data of the obstacle is a set of vectors of the obstacle in a three-dimensional coordinate system, and the point cloud data of the obstacle reflects the coordinate position of the obstacle in front of the robot in space, that is, the spatial information of the obstacle inside the elevator.

[0057] After the point cloud data collector collects the point cloud data of the object in front of the robot, the point cloud data can be projected into a plane, that is, the point cloud data is two-dimensionally projected to form a top view, so as to obtain a two-dimensional obstacle map, which reflects the two-dimensional relationship of the obstacle in front of the robot.

[0058] After obtaining the two-dimensional obstacle map, the two-dimensional obstacle map is binarized to obtain a target binary image. It can be understood that the binarization of the two-dimensional obstacle map is to convert the gray value of the point on the two-dimensional obstacle map to 0 or 255, so as to obtain a binary image that can reflect the overall and local features of the image. It should be noted that in the embodiments of the present application, there are various ways to obtain the target binary image corresponding to the two-dimensional obstacle map, and the specific implementation is not limited, and will not be described one by one. Specifically, in the embodiments of the present application, the pixel position with obstacle information in the two-dimensional obstacle map is marked as "0", and the position without obstacle information is marked as "1", so as to obtain the above-mentioned target binary image.

[0059] S32: The target binary image is labeled with a connected domain to obtain each connected domain of the target binary image.

[0060] After obtaining the target binary image, in order to further analyze the situation of the obstacle in front of the robot, including the state in front of the elevator door and inside the elevator, the target binary image needs to be labeled with connected components to obtain each connected component of the target binary image. It can be understood that the connected component (Connected Component) refers to an image region (Region, Blob) composed of foreground pixel points with the same pixel value and adjacent positions in the target binary image. Connected region labeling refers to finding and labeling each connected component in the target binary image, so as to divide each different region in the target binary image, so that the obstacle region and the non-obstacle region can be divided according to each different connected component.

[0061] S33: Compare the radius of the maximum inscribed circle of each connected component with the radius of the minimum circumscribed circle of the two-dimensional projection of the robot to obtain the target connected component in which the maximum inscribed circle has a radius greater than a preset threshold.

[0062] The circumscribed circle refers to a circle intersecting each vertex of the polygon; the inscribed circle, also known as the tangent circle, refers to a circle tangent to each side of the polygon. It can be understood that according to the specific obstacle situation in front of the robot, each connected component of the target binary image is usually an irregular polygon, and the embodiment of the present application needs to determine the inscribed circle of each connected component in the target binary image, so as to determine whether the position corresponding to each connected component has sufficient position for the robot to stand or pass. Specifically, according to the radius of the inscribed circle of each connected component, the maximum inscribed circle in each connected component is determined, and the minimum circumscribed circle of the two-dimensional projection of the robot and the radius of the minimum circumscribed circle are determined. The minimum circumscribed circle of the two-dimensional projection of the robot reflects the position area range required by the robot itself, so in the embodiment of the present application, by comparing the radius of the maximum inscribed circle of each connected component with the radius of the minimum circumscribed circle of the two-dimensional projection of the robot, the space in which the robot can stand or move in the elevator can be determined.

[0063] It should be noted that the embodiment of the present application can have various ways to determine the maximum inscribed circle in each connected component and the minimum circumscribed circle of the two-dimensional projection of the robot, and the present application does not limit the specific embodiment.

[0064] Then, the radius of the maximum inscribed circle of each connected component is compared with the radius of the minimum circumscribed circle of the two-dimensional projection of the robot to obtain the target connected component in which the maximum inscribed circle has a radius greater than a preset threshold.

[0065] S34: The region where the two-dimensional projection of the robot is located is taken as an initial region, and region growing is performed with the target connected component to obtain a final connected component.

[0066] S35: Determine the space state of the elevator according to the final connected component.

[0067] In the embodiment of the present application, the area where the two-dimensional projection of the robot body is located is taken as an initial area, and region growing is performed with the target connected domain to obtain a final connected domain. It should be noted that region growing refers to a process of developing a set of pixels or regions into a larger region, and region growing can segment out a connected region with the same characteristics. It can be seen that the final connected domain reflects the situation of obstacles and non-obstacles in front of the robot inside and outside the elevator. It can be seen that, through the final connected domain, whether there is an obstacle from the current position of the robot to the position of the target connected domain can be reflected. Therefore, the spatial state of the elevator can be determined according to the final connected domain and the two-dimensional projection of the robot, that is, whether the elevator can be entered.

[0068] It can be seen that the embodiment of the present application provides a method for judging the spatial state of an elevator. After judging that the robot is aligned with the elevator door, binary processing is first performed on the two-dimensional obstacle graph to obtain a target binary graph, wherein the two-dimensional obstacle graph is a top view formed by two-dimensional projection of point cloud data of obstacles in front of the robot. Connected domain labeling is performed on the target binary graph to obtain each connected domain of the target binary graph. The radii of the largest inscribed circles of each connected domain are compared with the radius of the smallest circumscribed circle of the two-dimensional projection of the robot to obtain the target connected domain where the radius of the largest inscribed circle is greater than a preset threshold, so as to determine the position range of the robot that can stand inside the elevator. Subsequently, the area where the two-dimensional projection of the robot is located is taken as an initial area, and region growing is performed with the target connected domain to obtain a final connected domain. According to the final connected domain and the two-dimensional projection of the robot, the spatial state of the elevator can be determined, and whether there is an obstacle in the process of entering the elevator can be further determined, so that whether the elevator can be entered is accurately determined, and the safety of the robot entering the elevator is effectively improved.

[0069] It should be noted that, according to the image information of the area in front of the robot and the projection information of the robot itself, the spatial state of the elevator can also be determined in other embodiments, which are not limited by the present application and will not be described in detail. For example, the two-dimensional obstacle graph can not be subjected to binary processing, but can be directly determined according to the two-dimensional obstacle graph and the projection information of the robot itself.

[0070] In an embodiment, as shown in Figure 3 In step S35, that is, judging the spatial state of the elevator according to the final connected domain, the following steps are included:

[0071] S351: In the final connected domain, a target position whose distance from the center of the initial area satisfies a preset distance is determined.

[0072] As described above, after the final connected domain is obtained, the current position of the robot and the situation of the elevator obstacle in front are known, and in order to further determine the spatial state of the elevator, the embodiment of the application provides a manner of judging the spatial state of the elevator according to the final connected domain and the two-dimensional projection of the robot, that is, first determining a target position in the final connected domain, which satisfies a preset distance from the center of the initial region. As an example, the target position in the final connected domain, which satisfies the preset distance from the center of the initial region, refers to determining a position in the final connected domain, which satisfies the Euclidean distance from the center of the initial region, as the target position. The target position refers to the position farthest from the center of the initial region in the final connected domain, which indicates that the actual position corresponding to the target position is a position that the robot can go to. It should be noted that the target position can also be other preset positions in the final connected domain, and the specific form is not limited. It should be noted that the target position is a position determined based on the final connected domain, and therefore, the target position is a position in the image, and the actual position corresponding to the target position.

[0073] S352: judging whether the target position is in the elevator.

[0074] S353: when the actual position corresponding to the target position is in the elevator, judging that the spatial state of the elevator is an accessible state.

[0075] S354: when the actual position corresponding to the target position is not in the elevator, judging that the spatial state of the elevator is an inaccessible state.

[0076] After the target position is determined, it is judged whether the actual position corresponding to the target position is in the elevator. If the actual position corresponding to the target position is in the elevator, it indicates that the robot can move into the elevator at this time and will not encounter an obstacle. If the actual position corresponding to the target position is not in the elevator, it indicates that the robot cannot move into the elevator at this time due to no space in the elevator or an obstacle in front. It should be noted that after the target position is determined, whether the actual position corresponding to the target position is in the elevator can be judged according to the distance between the target position and the center of the initial region and the distance between the center of the initial region and the door of the elevator, which is not described in detail here.

[0077] In an optional embodiment, judging whether the actual position corresponding to the target position is in the elevator specifically refers to whether the actual position corresponding to the target position is located in the elevator. If the actual position corresponding to the target position is located in the elevator, it indicates that the actual position corresponding to the target position is in the elevator. If only part of the actual position corresponding to the target position or none of the actual position corresponding to the target position is located in the elevator, it indicates that the actual position corresponding to the target position is not in the elevator.

[0078] It can be seen that the embodiment of the present invention provides a specific method for judging the spatial state of the elevator according to the final connected domain and the two-dimensional projection of the robot, which improves the feasibility of the solution.

[0079] It should be noted that as mentioned in step S10, in the embodiment of the present invention, it is necessary to first judge whether the robot is aligned with the elevator entrance. The embodiment of the present invention provides various methods for judging whether the robot is aligned with the elevator entrance, such as Figure 4 As shown, in one embodiment, in step S10, judging whether the robot is aligned with the elevator entrance specifically includes the following steps:

[0080] S11: Obtain a pre-constructed two-dimensional "J" - shaped template diagram.

[0081] It can be understood that as Figure 5 shown, the elevator entrance is generally composed of a "J" - shaped groove. Based on this feature, the present invention first constructs a two - dimensional "J" - shaped template diagram, and the top view of the elevator entrance can be as Figure 4 shown.

[0082] S12: Perform shape matching between the two - dimensional obstacle diagram and the two - dimensional "J" - shaped template diagram.

[0083] S13: When they are matched, it is judged that the robot is aligned with the elevator entrance.

[0084] S14: When they are not matched, it is judged that the robot is not aligned with the elevator entrance.

[0085] After the pre-constructed two-dimensional H-shaped template image is obtained, shape matching is performed between the two-dimensional obstacle image and the two-dimensional H-shaped template image. It can be understood that if the robot is currently aligned with the elevator door, the two-dimensional obstacle image obtained at this time is image data converted from the elevator door, and therefore, when the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image should be matched, if the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are not matched, it can be indicated that the robot is not aligned with the elevator door. In an embodiment, the shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle image and the shape of the two-dimensional H-shaped template image is determined; when the shape matching error degree is less than a preset error threshold, it is determined that the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are matched; and when the shape matching error degree is greater than or equal to the preset error threshold, it is determined that the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are not matched. For example, if the shape of the elevator frame region in the two-dimensional obstacle image is a H-shaped, it can be indicated that the shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle image and the shape of the two-dimensional H-shaped template image is low, and it is determined that the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are matched. If the shape of the elevator frame region in the two-dimensional obstacle image is a H-shaped, it can be indicated that the shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle image and the shape of the two-dimensional H-shaped template image is also low, and it is determined that the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are matched. If the shape of the elevator frame region in the two-dimensional obstacle image is a triangle, it can be indicated that the shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle image and the shape of the two-dimensional H-shaped template image is high, and it is determined that the shapes of the two-dimensional obstacle image and the two-dimensional H-shaped template image are not matched. It should be noted that the embodiment of the present application can have various ways to determine the shape matching error degree, which are not limited and will not be described one by one. After the two-dimensional obstacle image is obtained, the elevator frame region is recognized according to the image recognition algorithm, and shape recognition is performed to determine the shape of the elevator frame region and perform subsequent shape matching. Details are not described here.

[0086] It should be noted that in an embodiment, when the forward direction obtained by robot positioning is used as the initial direction of rotation adjustment, when it is not matched, the robot is fine-tuned in a limited rotation direction change range to align the robot with the elevator door. During fine-tuning, the fine-tuning can be performed according to the shape matching result.

[0087] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiment of the present application.

[0088] In an embodiment, an elevator space state judgment device is provided, which corresponds to the elevator space state judgment method in the above embodiment. As shown in the figure, the elevator space state judgment device comprises a first judgment module 100, an acquisition module 101 and a second judgment module 102. The functions of each module are described in detail as follows: Figure 6

[0089] The first judgment module is configured to judge whether the robot is aligned with the elevator door.

[0090] The acquisition module is configured to acquire image information of an area in front of the robot and projection information of the robot itself if the robot is aligned with the elevator door.

[0091] The second judgment module is configured to judge the space state of the elevator according to the image information of the area in front of the robot and the projection information of the robot itself.

[0092] Further, the image information of the elevator door area comprises a two-dimensional obstacle graph corresponding to obstacles in front of the robot, and the projection information of the robot itself comprises a two-dimensional projection of the robot. The second judgment module is specifically configured to:

[0093] perform binaryzation processing on the two-dimensional obstacle graph to obtain a target binary graph;

[0094] perform connected domain labeling on the target binary graph to obtain each connected domain of the target binary graph;

[0095] compare the radius of the largest inscribed circle of each connected domain with the radius of the smallest circumscribed circle of the two-dimensional projection of the robot to obtain a target connected domain in which the largest inscribed circle has a radius greater than a preset threshold;

[0096] regard the area in which the two-dimensional projection of the robot is located as an initial area, and perform region growing on the target connected domain to obtain a final connected domain;

[0097] judge the space state of the elevator according to the final connected domain.

[0098] Further, the second judgment module is further configured to:

[0099] determine a target position in the final connected domain that satisfies a preset distance from the center of the initial area;

[0100] when the target position is in the elevator, judge that the space state of the elevator is an accessible state;

[0101] when the target position is not in the elevator, judge that the space state of the elevator is an inaccessible state.

[0102] ​Further, the second judging module is further used for:

[0103] In the final connected domain, a position with the farthest Euclidean distance from the initial region center is determined as the target position.

[0104] Further, the first judging module is specifically used for:

[0105] acquiring a pre-constructed two-dimensional H-shaped template graph;

[0106] performing shape matching between the two-dimensional obstacle graph and the two-dimensional H-shaped template graph;

[0107] when the shape matching is matched, it is determined that the robot is aligned with the elevator door;

[0108] when the shape matching is not matched, it is determined that the robot is not aligned with the elevator door.

[0109] Further, the first judging module 100 is specifically used for:

[0110] judging a shape matching error degree of an elevator frame region in the two-dimensional obstacle graph and the two-dimensional H-shaped template graph;

[0111] when the shape matching error degree is less than a preset error threshold, it is determined that the shape of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph is matched;

[0112] when the shape matching error degree is greater than or equal to the preset error threshold, it is determined that the shape of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph is not matched.

[0113] It can be seen that the embodiment of the present application provides an elevator space state judging device. When the robot is determined to be aligned with the elevator door, the two-dimensional obstacle graph is first binarized to obtain a target binary graph, wherein the two-dimensional obstacle graph is a top view formed by two-dimensional projection of point cloud data of obstacles in front of the robot; the target binary graph is marked with connected domains to obtain each connected domain of the target binary graph; the radius of the largest inscribed circle of each connected domain is compared with the radius of the smallest circumscribed circle of the two-dimensional projection of the robot to obtain a target connected domain of the largest inscribed circle with a radius greater than a preset threshold, so as to determine a position range in which the robot can stand in the elevator; then, the region where the two-dimensional projection of the robot is located is taken as an initial region, and region growing is performed on the initial region and the target connected domain to obtain a final connected domain, and the space state of the elevator is judged according to the final connected domain and the two-dimensional projection of the robot, so that whether there is an obstacle in the process of entering the elevator can be further determined, the elevator can be accurately determined to be entered, and the safety of the robot entering the elevator is effectively improved.

[0114] The specific limitations of the elevator space state judgment device can refer to the limitations of the elevator space state judgment method described above, and will not be repeated here. Each module in the above elevator space state judgment device can be realized by software, hardware and their combination. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor calls and executes the operations corresponding to each module.

[0115] In one embodiment, an elevator space state judgment device is provided, which can be a server or a controller integrated inside a robot, and its internal structure diagram can be as shown in Figure 7 The computer device includes a processor, a memory, a network interface and a database connected by a system bus. 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, a computer program and a database. The computer program is executed by the processor to implement an elevator space state judgment method.

[0116] In one embodiment, an elevator space state judgment device is provided, which includes a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to implement the following steps:

[0117] determine whether the robot is aligned with the elevator door;

[0118] if the robot is aligned with the elevator door, obtain image information of the area in front of the robot and projection information of the robot itself;

[0119] determine the space state of the elevator according to the image information of the area in front of the robot and the projection information of the robot itself.

[0120] In one embodiment, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the following steps:

[0121] determine whether the robot is aligned with the elevator door;

[0122] if the robot is aligned with the elevator door, obtain image information of the area in front of the robot and projection information of the robot itself;

[0123] determine the space state of the elevator according to the image information of the area in front of the robot and the projection information of the robot itself.

[0124] 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. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0125] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified. In actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0126] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not to limit it. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features. Such modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. An elevator space state determination method characterized by comprising: The method comprises the following steps: determining whether the robot is aligned with the elevator door; if the robot is aligned with the elevator door, obtaining image information of a region in front of the robot and projection information of the robot, the image information of the region in front of the robot being capable of reflecting the situation of the region of the elevator door, and the projection information of the robot being capable of reflecting the size of the robot itself; judging the space state of the elevator according to the image information of the region in front of the robot and the projection information of the robot; the image information of the region in front of the robot comprises a two-dimensional obstacle graph corresponding to the obstacles in front of the robot, and the projection information of the robot comprises a two-dimensional projection of the robot, and the judging the space state of the elevator according to the image information of the region in front of the robot and the projection information of the robot comprises: performing binaryzation processing on the two-dimensional obstacle graph to obtain a target binary graph; performing connected domain labeling on the target binary graph to obtain each connected domain of the target binary graph; comparing the radius of the largest inscribed circle of each connected domain with the radius of the smallest circumscribed circle of the two-dimensional projection of the robot to obtain a target connected domain in which the radius of the largest inscribed circle is greater than a preset threshold; regarding the region in which the two-dimensional projection of the robot is located as an initial region, and performing region growing on the target connected domain to obtain a final connected domain; judging the space state of the elevator according to the final connected domain.

2. The elevator space state determination method according to claim 1, characterized by the judging the space state of the elevator according to the final connected domain comprises: determining a target position in the final connected domain which satisfies a preset distance from the center of the initial region; when the actual position corresponding to the target position is in the elevator, judging that the space state of the elevator is an accessible state; when the actual position corresponding to the target position is not in the elevator, judging that the space state of the elevator is an inaccessible state.

3. The elevator space state determination method according to claim 2, characterized by the determining a target position in the final connected domain which satisfies a preset distance from the center of the initial region comprises: determining a position in the final connected domain which is farthest from the center of the initial region as the target position.

4. The elevator space state determination method according to any one of claims 1 to 3, characterized by, the determining whether the robot is aligned with the elevator door comprises: obtaining a two-dimensional H-shaped template graph constructed in advance; performing shape matching on the two-dimensional obstacle graph and the two-dimensional H-shaped template graph; when the shape matching is matched, judging that the robot is aligned with the elevator door; when the shape matching is not matched, judging that the robot is not aligned with the elevator door.

5. The elevator space state determination method according to claim 4, characterized by the performing shape matching on the two-dimensional obstacle graph and the two-dimensional H-shaped template graph comprises: judging the shape matching error degree of the shape of the elevator frame region in the two-dimensional obstacle graph and the shape of the two-dimensional H-shaped template graph; when the shape matching error degree is less than a preset error threshold, judging that the shapes of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph are matched; when the shape matching error degree is greater than or equal to the preset error threshold, judging that the shapes of the two-dimensional obstacle graph and the two-dimensional H-shaped template graph are not matched.

6. The elevator space state determination method according to any one of claims 1 to 3, characterized by, the two-dimensional obstacle graph is a top view formed by two-dimensional projection of point cloud data of the obstacles in front of the robot.

7. An elevator space state determination device, characterized in that, The method comprises the following steps: The first judging module is configured to judge whether the robot is aligned with the elevator door. The acquisition module is configured to acquire image information of a region in front of the robot and projection information of the robot if the robot is aligned with the elevator door, the image information of the region in front of the robot being capable of reflecting a situation of the elevator door region, and the projection information of the robot being capable of reflecting a size of the robot. The second judging module is configured to judge a space state of the elevator according to the image information of the region in front of the robot and the projection information of the robot. The image information of the region in front of the robot includes a two-dimensional obstacle graph corresponding to an obstacle in front of the robot, and the projection information of the robot includes a two-dimensional projection of the robot. The method comprises the following steps: performing binaryzation processing on the two-dimensional obstacle graph to obtain a target binary graph; performing connected domain marking on the target binary graph to obtain each connected domain of the target binary graph; comparing radii of maximum inscribed circles of the each connected domain with a radius of a minimum circumscribed circle of the two-dimensional projection of the robot to obtain a target connected domain in which a maximum inscribed circle has a radius greater than a preset threshold value; regarding a region in which the two-dimensional projection of the robot is located as an initial region, and performing region growing on the target connected domain to obtain a final connected domain; judging the space state of the elevator according to the final connected domain.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8.

8. An elevator space state judging device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements steps of the elevator space state judging method according to any one of claims 1-6 when executing the computer program. The computer program is executable on the processor to implement steps of the elevator space state judging method according to any one of claims 1-6.

Images