Elevator entering control method and device, electronic equipment and computer program product
By obtaining cost maps and target cost images, the robot's ladder entry solution is solved, and the convenience and reliability of ladder entry is improved.
Patent Information
- Application Number
- CN202510520805.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-23
- Publication Date
- 2025-08-15
AI Technical Summary
The existing robotic ladder access solution relies on sensor data to search for accessible areas, which makes the robot prone to park in an inconvenient location and lacks convenience in ladder access.
By obtaining the cost map, the candidate stopping point in the elevator is determined, and the robot is controlled to go to the target stopping point based on the target cost image, and the selection of stopping point is optimized based on the positional relationship between the candidate stopping point and the attraction point.
It improves the convenience of the robot's ladder, ensures the passability of the parking point and the convenience of entering and exiting the ladder.
Smart Images
Figure CN120491634A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of robotics technology, and in particular relates to an elevator entry control method, device, electronic device, and computer program product. Background Art
[0002] Cross-floor navigation is a common robot use case. The key and challenge of cross-floor navigation lies in properly managing the elevator entry process. Robotic elevator entry relies on the robot's sensors. Current solutions often rely on the robot searching for accessible, vacant areas based on sensor data and then entering. However, this approach can easily lead to the robot stopping in locations that are inconvenient for the robot or others, resulting in inconvenience. Summary of the Invention
[0003] Embodiments of the present application provide an elevator entry control method, device, electronic device, and computer program product, which can improve the convenience of a robot taking an elevator.
[0004] A first aspect of an embodiment of the present application provides an elevator entry control method, comprising: obtaining a cost map in response to a robot satisfying an elevator entry condition; determining candidate stopping points in the elevator based on the cost map; obtaining a target cost image, wherein the target cost image represents a positional relationship between the candidate stopping points and a preset attraction point in the elevator; and controlling the robot to go to a target stopping point in the elevator based on the target cost image, wherein the target stopping point is included in the candidate stopping point presented in the target cost image.
[0005] In some embodiments of the first aspect, before obtaining the cost map, the elevator control method also includes: detecting a passable area along the direction of the elevator door of the elevator, the size of the passable area is related to the shape information of the robot; if the passable area does not exist, determining the total number of first lines that do not pass through obstacles, the first lines being the lines between the current position of the robot and each point on the preset horizontal line in the elevator; in response to the total number being greater than a quantity threshold, controlling the robot to move toward the elevator; in response to the distance between the robot and the elevator being less than a first distance threshold, the robot detects the passable area and determines that the robot meets the elevator riding conditions.
[0006] In some embodiments of the first aspect, the elevator includes a first area close to the elevator door and a second area away from the elevator door; before obtaining the cost map, the elevator entry control method also includes: obtaining a first proportion of non-obstacle points in the first area in the first area; if the first proportion is less than a first proportion threshold, obtaining a second proportion of robot visible points in the second area in the second area; if the first proportion is greater than or equal to the first proportion threshold, or the second proportion is greater than or equal to the second proportion threshold, it is determined that the robot meets the elevator riding conditions.
[0007] In some embodiments of the first aspect, before obtaining the target cost image, the elevator entry control method also includes: taking the center position between the door center point and the door end point of the elevator as the attraction point; performing distance transformation on the distance between each point in the elevator and the attraction point to obtain an attraction image, wherein the attraction image represents the positional relationship between each point in the elevator and the attraction point.
[0008] In some embodiments of the first aspect, determining candidate stopping points in the elevator based on the cost map includes: determining points in the elevator in the cost map; for each point in the elevator, determining a second line between the point and the current position of the robot, and using points on the second line that do not pass through obstacles as candidate stopping points.
[0009] In some embodiments of the first aspect, controlling the robot to move to a target stopping point in the elevator based on the target cost image includes: determining a current stopping point in the elevator based on the target cost image; determining the target stopping point between the current stopping point and historical stopping points; and controlling the robot to move to the target stopping point.
[0010] In some embodiments of the first aspect, determining the target stopping point between the current stopping point and the historical stopping points includes: if a first distance between the historical stopping point and the attraction point is greater than a second distance threshold, taking the current stopping point as the target stopping point; if the first distance is less than or equal to the second distance threshold, taking the point between the current stopping point and the historical stopping point that is closest to the current position of the robot as the target stopping point.
[0011] A second aspect of an embodiment of the present application provides an elevator entry control device, comprising: a cost map acquisition unit, for acquiring a cost map in response to a robot satisfying an elevator riding condition; a candidate point determination unit, for determining a candidate stopping point in the elevator based on the cost map; a target cost image acquisition unit, for acquiring a target cost image, wherein the target cost image represents a positional relationship between the candidate stopping point and a preset attraction point in the elevator; and an elevator entry control unit, for controlling the robot to go to a target stopping point in the elevator based on the target cost image, wherein the target stopping point is included in the candidate stopping point presented in the target cost image.
[0012] A third aspect of an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned elevator control method when executing the computer program.
[0013] A fourth aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned elevator control method are implemented.
[0014] A fifth aspect of the embodiments of the present application provides a computer program product, which enables the above-mentioned elevator control method to be executed when the computer program is run.
[0015] In an embodiment of the present application, in response to the robot meeting the conditions for taking the elevator, a cost map is obtained, and based on the cost map, candidate stopping points in the elevator are determined. Based on the positional relationship between the candidate stopping points represented in the target cost image and the preset attraction points in the elevator, the robot is controlled to go to the target stopping point in the elevator presented in the target cost image. In this way, on the one hand, the accessibility of the robot's stopping point can be guaranteed with reference to the cost map. On the other hand, combined with the positional relationship between each candidate stopping point and the attraction point, an association between the stopping point and a specific position can be established, for example, the stopping point can be brought closer to the attraction point that is convenient for entering and exiting the elevator, which helps to improve the convenience of the robot taking the elevator. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.
[0017] Figure 1 This is a schematic diagram of an implementation flow of an elevator entry control method provided in an embodiment of the present application;
[0018] Figure 2 This is a schematic diagram of the formatting provided by the embodiment of the present application;
[0019] Figure 3 This is a schematic diagram of a first specific implementation process for determining whether a robot meets the conditions for taking an elevator provided in an embodiment of the present application;
[0020] Figure 4 is a schematic diagram of detecting a traversable area provided in an embodiment of the present application;
[0021] Figure 5 is a schematic diagram of a first connection provided in an embodiment of the present application;
[0022] Figure 6 is a schematic diagram of the first area and the second area provided in an embodiment of the present application;
[0023] Figure 7 This is a schematic diagram of a second specific implementation flow for determining whether a robot meets the conditions for taking an elevator provided in an embodiment of the present application;
[0024] Figure 8 is a schematic diagram of first images corresponding to the attraction points on both sides of the elevator door provided by an embodiment of the present application;
[0025] Figure 9 is a schematic diagram of second images corresponding to the attraction points on both sides of the elevator door provided by an embodiment of the present application;
[0026] Figure 10 is a schematic diagram of an attractive image provided by an embodiment of the present application;
[0027] Figure 11 Schematic diagram of the elevator entry cost map provided in an embodiment of the present application;
[0028] Figure 12 This is a schematic diagram of a specific implementation flow of an elevator entry control method provided in an embodiment of the present application;
[0029] Figure 13 This is a structural diagram of an elevator control device provided in an embodiment of the present application;
[0030] Figure 14 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0031] In order to make the purpose, technical solutions and advantages of this application more clear, the present application is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without making any creative work are protected by this application.
[0032] Cross-floor navigation is a common robot use case. The key and challenge of cross-floor navigation lies in properly managing the elevator entry process. Robotic elevator entry relies on the robot's sensors. Current solutions often rely on the robot searching for accessible, vacant areas based on sensor data and then entering. However, this approach can easily lead to the robot stopping in locations that are inconvenient for the robot or others, resulting in inconvenience.
[0033] In view of this, the present application proposes a method for controlling elevator access, which can use the cost map as a reference to ensure the accessibility of the robot's stopping point. At the same time, combined with the positional relationship between each candidate stopping point and the attraction point, it can establish an association between the stopping point and the specific position, thereby improving the convenience of the robot's stopping point.
[0034] In order to illustrate the technical solution of the present application, specific embodiments are provided below.
[0035] Figure 1 The following is a schematic diagram illustrating an implementation flow of an elevator entry control method provided in an embodiment of the present application. The method can be applied to electronic devices. The electronic device can be a computer, tablet computer, mobile phone, or other smart device used to control a robot, or it can be a robot that needs to enter an elevator, or an elevator control device that is interacting with the robot, without limitation in this application.
[0036] Specifically, the above elevator entry control method may include the following steps S101 to S104.
[0037] Step S101: In response to the robot meeting the elevator riding conditions, a cost map is obtained.
[0038] The robot meeting the elevator entry conditions means that the robot needs to enter the elevator and the elevator has space to accommodate the robot. The robot can confirm its need to enter the elevator when it autonomously detects the need to enter the elevator based on the navigation destination or receives an elevator entry command. If the robot needs to enter the elevator, it can use sensors such as image sensors, radar, depth sensors, or sensors within the elevator (such as gravity sensors) to confirm whether there is space for the robot to enter the elevator.
[0039] If the robot meets the elevator entry conditions, indicating that it can be controlled to enter the elevator, the robot's cost map can be obtained. The cost map is a map used for robot navigation, which helps the robot plan its path by assigning different cost values to different areas in the environment.
[0040] Step S102: Determine candidate stopping points in the elevator based on the cost map.
[0041] In the embodiments of this application, the cost values in the costmap can reflect the presence of obstacles in the environment. Based on the cost values of various points within the elevator in the costmap, candidate stopping points can be determined within the elevator. Candidate stopping points within the elevator are locations where the robot can stop after entering the elevator.
[0042] Step S103: Acquire a target cost image.
[0043] The target cost image represents the positional relationship between the candidate stopping point and a preset attraction point within the elevator. The preset attraction point is the point that the robot needs to approach as close as possible after entering the elevator. It can be inside the elevator or on the elevator frame. The positional relationship between the candidate stopping point and the attraction point may include, but is not limited to, the distance between the candidate stopping point and the attraction point.
[0044] Specifically, the target cost image may present pixels associated with the candidate boarding points, and the pixel values of these pixels are associated with the positional relationship between the candidate stopping point and the attraction point. For example, the closer the distance, the lower the pixel value.
[0045] Step S104: Based on the target cost image, control the robot to go to the target stopping point in the elevator.
[0046] Among them, the target stopping point is included in the candidate stopping points presented in the target cost image, which is the position where the robot stops after entering the elevator.
[0047] Specifically, when there is only one candidate stopping point, the target cost map will present only one candidate stopping point, and this candidate stopping point can be used as the target stopping point. When there are multiple candidate stopping points, these multiple candidate stopping points can be presented in the cost map, and the target stopping point can be selected from the multiple candidate stopping points based on the positional relationship between the candidate stopping point and the attraction point.
[0048] In an embodiment of the present application, in response to the robot meeting the conditions for taking the elevator, a cost map is obtained, and based on the cost map, candidate stopping points in the elevator are determined. Based on the positional relationship between the candidate stopping points represented by the target cost image and the preset attraction points in the elevator, the robot is controlled to go to the target stopping point in the elevator presented in the target cost image. In this way, on the one hand, the accessibility of the robot's stopping point can be guaranteed with reference to the cost map. On the other hand, combined with the positional relationship between each candidate stopping point and the attraction point, an association between the stopping point and a specific position can be established, for example, the stopping point can be brought closer to the attraction point for easy entry and exit of the elevator, which helps to improve the convenience of the robot taking the elevator.
[0049] In some embodiments of the present application, before obtaining the costmap, the elevator entry control method may further include: obtaining elevator data and door data, and formatting the elevator data and door data.
[0050] Specifically, elevator data can include coordinate information for each point within the elevator, and door data can include coordinate information for each point on the elevator door. Elevator and door data can be pre-calibrated. To facilitate calculations, these data can be converted to the costmap's coordinate system. Furthermore, given that the order of elevator and door data may differ, potentially leading to subsequent calculation errors, the electronic device can format the elevator and door data to ensure that the order of the points in each data point is consistent.
[0051] As an example, see Figure 2 When the robot / human stands inside the polygon (the waiting polygon when waiting for the elevator, the interior polygon when riding the elevator), facing the elevator door, the left and right sides of the elevator door are determined. The points can be sorted in the following order: left front, right front, right back, left back.
[0052] Subsequently, an image coordinate system (UV coordinate system) can be generated, and the conversion relationship between the image coordinate system and the costmap coordinate system can be calculated. Specifically, the minimum bounding rectangle of the polygon (elevator waiting polygon or elevator interior polygon) can be calculated. According to the order of the points mentioned above, the rectangular points near the first point are used as the origin of the image coordinate system, and the direction angle points to the second point. At this point, based on the origin and direction angle, the coordinates of the image and the costmap can be converted back and forth.
[0053] In some embodiments of the present application, Figure 3 As shown, before obtaining the cost map, the elevator entry control method may further include steps S301 to S304.
[0054] Step S301: Detect the passable area along the direction of the elevator door.
[0055] The size of the traversable area is related to the shape information of the robot, and there are no obstacles in the traversable area.
[0056] Specifically, the shape information can be the robot's footprint information. The footprint information represents the robot's 2D shape on the map and is used to represent the robot's interaction boundary with the environment during navigation and path planning. The size of the traversable area is associated with the robot's shape information so that the size of the traversable area can accommodate the robot. Figure 4 , set the size of the area according to the shape information, and check from left to right along the direction of the elevator door to see if the entire interior is a passable (free) area.
[0057] If there is a passable area, it means that there is a large space near the door in the elevator, and the robot can enter. At this time, it can be determined that the robot meets the conditions for taking the elevator.
[0058] Step S302: If there is no passable area, determine the total number of first lines that do not pass through obstacles.
[0059] Among them, if there is no passable area, it means that there is no large accommodation space in the area near the door in the elevator. At this time, it is necessary to determine whether the robot can squeeze into the elevator.
[0060] The first line connects the robot's current position with points on a preset horizontal line within the elevator. The preset horizontal line is parallel to the elevator door and lies between the first and second lines. The first line is the elevator frame, parallel to and away from the door. The second line connects the midpoints of the two sides of the elevator frame.
[0061] Please refer to Figure 5 , traverse each point on the preset horizontal line, connect each point with the robot's current position, and obtain several first connecting lines. For each first connecting line, check whether it does not pass through any obstacles (that is, all points on the first connecting line are free). Then, the total number of first connecting lines that do not pass through any obstacles can be counted.
[0062] Step S303: In response to the total number being greater than the number threshold, the robot is controlled to move toward the elevator.
[0063] Step S304: In response to the distance between the robot and the elevator being less than the first distance threshold, the robot detects a passable area and determines that the robot meets the conditions for taking the elevator.
[0064] If there is no passable area and the total number of first lines is less than or equal to the quantity threshold, it means that there is no space to accommodate the robot in the area far away from the elevator door. At this time, it can be determined that the robot does not meet the conditions for taking the elevator.
[0065] If there is no passable area, but the total number of first lines is greater than the threshold, this indicates that there is some space away from the elevator door, allowing for entry. The robot can then be controlled to move toward the elevator. Typically, people inside the elevator will move to make room upon seeing the robot attempt to enter. Therefore, by re-executing steps S301 and S302, if the distance between the robot and the elevator is less than the first distance threshold, the robot has detected a passable area, indicating that the robot can enter, and can be determined to meet the elevator entry requirements.
[0066] If, during the process of re-executing steps S301 to S302, it is detected that the total number of first lines is less than or equal to the number threshold, or, in response to the robot moving towards the elevator until the distance between the robot and the elevator is less than the first distance threshold, and the robot still fails to detect a passable area, it means that the attempt to squeeze into the elevator has failed, and it can be determined that the robot does not meet the conditions for taking the elevator.
[0067] It is understandable that the process of entering an elevator is often a process of interaction with people, and the environment will continue to change. Figure 3 In the method shown, when the people's standing positions just block the elevator entrance (that is, they are all located in the area close to the elevator door), or when the people's standing positions are relatively scattered, the robot can try to squeeze into the elevator, thereby increasing the success rate of entering the elevator.
[0068] In some embodiments of the present application, the elevator may include a first area close to the elevator door and a second area away from the elevator door. The first area and the second area may be divided proportionally.
[0069] For example, see Figure 6 , the elevator frame where the elevator door is located can be used as a side frame of the first area, and the first area can be divided from the elevator according to the first ratio. Similarly, the elevator frame away from the elevator door can be used as a side frame of the second area, and the second area can be divided from the elevator according to the second ratio. Both the first ratio and the second ratio can be 0.3 or other empirical values, which are not limited by this application.
[0070] At this time, if Figure 7 As shown, before obtaining the cost map, the elevator entry control method may further include steps S701 to S703.
[0071] Step S701: Obtain a first proportion of non-obstacle points in a first area.
[0072] After the first area is determined, non-obstacle points within the first area may be determined. Non-obstacle points are free points (cells).
[0073] Then, the first proportion of non-obstacle points in the first area can be obtained Among them, S black and N black_cells Represent the area and number of non-obstacle points, S total and N total_cells represent the area and quantity of the first region respectively.
[0074] Step S702 : If the first proportion is less than the first proportion threshold, obtain a second proportion of the robot's visible point in the second area in the second area.
[0075] The first ratio threshold value may be set according to actual needs. Considering that sufficient space is required at this time, this ratio may be set to 0.7.
[0076] If the first ratio is less than the first ratio threshold, it indicates that there is insufficient space within the first area. In this case, a second ratio of robot-visible points within the second area can be obtained. Robot-visible points refer to points that the robot can observe through sensors, including those visible through gaps in obstacles (such as people).
[0077] Step S703: If the first proportion is greater than or equal to the first proportion threshold, or the second proportion is greater than or equal to the second proportion threshold, it is determined that the robot meets the elevator riding condition.
[0078] The second ratio threshold can be set according to actual needs. In order to allow the robot to try as much as possible, this ratio can be set to 0.2.
[0079] If the first ratio is greater than or equal to the first ratio threshold, it indicates that there is sufficient space in the first area. If the first ratio is less than the first ratio threshold and the second ratio is greater than the second ratio threshold, it indicates that there is more space in the second area and the robot can try to squeeze in. In both cases, it can be determined that the robot meets the conditions for taking the elevator.
[0080] If the first proportion is less than the first proportion threshold and the second proportion is less than the second proportion threshold, it means that there is no space in the elevator to accommodate the robot, and it can be determined that the robot does not meet the conditions for taking the elevator.
[0081] Similarly, through Figure 7 In the method shown, when the people's standing positions just block the elevator entrance (that is, they are all located in the area close to the elevator door), or when the people's standing positions are relatively scattered, the robot can try to squeeze into the elevator, thereby increasing the success rate of entering the elevator.
[0082] In some embodiments of the present application, before obtaining the target cost image, the elevator entry control method may further include: determining the center position between the elevator door center point and the door end point as the attraction point; and performing a distance transform on the distances between each point in the elevator and the attraction point to obtain an attraction image. The attraction image represents the positional relationship between each point in the elevator and the attraction point.
[0083] Specifically, we can first calculate the center point of the door:
[0084] P c .x=0.5*(P left .x+P right .x);
[0085] P c .y=0.5*(P left .y+P right .y);
[0086] Next, calculate the attraction point on the left side of the elevator door:
[0087] P 1. x=0.5*(P left .x+P c .x);
[0088] P 1. y=0.5*(P left .y+P c .y);
[0089] And the attraction point on the right side of the elevator door:
[0090] P 2. x=0.5*(P right .x+P c .x);
[0091] P 2. y=0.5*(P right .y+P c .y).
[0092] For each attraction point, the first image corresponding to the attraction point can be obtained through distance transformation ( Figure 8 The first image corresponding to the attraction points on both sides of the elevator door is shown, so that the pixel value of each pixel in the first image is associated with the distance between the point represented by the pixel and the attraction point. The closer the distance, the lower the pixel value.
[0093] Considering that the overall pixel value in the first image is relatively small, the initial image can be changed by using an exponential function or other functions to obtain the second image corresponding to each attraction point ( Figure 9 The second images corresponding to the attraction points on both sides of the elevator door are shown).
[0094] At different pixel positions, the lower pixel values between the second images corresponding to different attractive points are retained to obtain an attractive image, such as Figure 10 At this time, the pixel values in the attraction image can represent the distance between each point in the elevator and the attraction point.
[0095] By setting the above-mentioned attraction points, on the one hand, the robot will not block the middle of the elevator after entering, leaving sufficient space for others to exit the elevator. At the same time, after entering the elevator, the robot will not be too close to the side frame of the elevator, which can facilitate the robot's exit and help improve the convenience of taking the elevator.
[0096] In some embodiments of the present application, determining candidate stopping points in an elevator based on a cost map may include: determining points in the elevator in the cost map; for each point in the elevator, determining a second line between the point and the current position of the robot, and using points where the second line does not pass through obstacles as candidate stopping points.
[0097] First, in the costmap LocalCostmap, the points outside the elevator polygon need to be set as unselectable, while the points inside the elevator are retained. The non-obstacle areas along the robot's field of view that are blocked by obstacles in the costmap are selectable, but the robot needs to go around behind the obstacles when entering the elevator. If a problem is found in the selected target stop point during this process, it will need to be reprocessed after the robot enters the elevator, resulting in increased computational complexity and even the robot encountering an abnormality in the elevator. In view of this, each point in the elevator can be connected to the current position of the robot to obtain a second line. If the second line passes through an obstacle, the point is also marked as an obstacle. Then, the points on the second line that do not pass through the obstacle are used as candidate stop points, so that the part of the robot blocked by the obstacle is not selected.
[0098] Please refer to Figure 11 , according to the cost map LocalCostmap, mark the pixels outside the elevator polygon as 255, and further Figure 11 The back areas blocked by a cube and cylinder, represented by 110 and 111 respectively, are marked as 255. The cost values of the remaining pixels in the elevator are retained as pixel values to obtain the initial cost image. At this time, the initial cost image retains the original cost values of the candidate elevator points in the cost map.
[0099] At this time, based on the candidate climbing points in the initial cost image, the cost values of these candidate climbing points are replaced with the pixel values in the aforementioned attractiveness image to obtain the target cost image.
[0100] Furthermore, in order to prevent the robot from getting too close to the elevator frame, a safety distance can be set, and pixels whose distance from the elevator frame is greater than or equal to the safety distance are retained in the target cost image.
[0101] Specifically, a straight line of 255 can be drawn along the elevator border according to the safety distance in the target cost image, indicating that these positions cannot be stopped.
[0102] In the target cost image, the candidate multiplication point with the smallest pixel value (i.e., cost value) (i.e., the candidate multiplication point closest to the attraction point) can be selected as the target multiplication point. Of course, other candidate multiplication points with pixel values less than a specific threshold can also be selected as the target multiplication point, and this application does not impose any restrictions on this.
[0103] Because the robot's elevator ride is a dynamic process, it can iteratively determine its stopping point during the elevator ride. Controlling the robot to its target stopping point within the elevator based on the target cost image can include: determining the current stopping point within the elevator based on the target cost image; determining a target stopping point between the current stopping point and previous stopping points; and controlling the robot to move toward the target stopping point.
[0104] The current stop point is the stop point determined during this iteration based on the target cost image obtained in real time. For example, it is the candidate boarding point with the smallest pixel value in the target cost image. A historical stop point is a stop point determined in the past. If a historical stop point is available between the current and historical stops, the historical stop point can be used as the target stop point to reduce changes to the navigation control logic. If a historical stop point is unavailable, the current stop point can be used as the target stop point to ensure reliable boarding.
[0105] Specifically, determining the target stopping point between the current stopping point and the historical stopping points may include: if a first distance between the historical stopping point and the attraction point is greater than a second distance threshold, then using the current stopping point as the target stopping point; and if the first distance is less than or equal to the second distance threshold, then using the point closest to the current position of the robot between the current stopping point and the historical stopping point as the target stopping point.
[0106] Specifically, if the pixel value of the historical stopping point in the current target cost image is higher, it means that the first distance between the historical stopping point and the attraction point is larger. In this case, the current stopping point is selected as the target stopping point. If the pixel value of the historical stopping point in the current target cost image is lower, it means that the historical stopping point can also be used. Then, the distance between the current stopping point and the historical stopping point and the current position of the robot is compared, and the point closer to the current position of the robot is selected as the target stopping point.
[0107] This point selection method can improve the success rate of entering the elevator, improve the robustness and stability of elevator navigation, and, by comparing with historical stop points, can reuse historical stop points in some cases, reducing changes in the robot's navigation control logic and improving elevator entry efficiency.
[0108] For ease of understanding, Figure 12 The specific flow chart of the elevator control method provided by this application is shown in FIG. Figure 12 First, the electronic device can obtain the elevator data and door data and format the elevator data and door data. Then it establishes the image coordinate system and obtains the current position of the robot. Figure 3 or Figure 7 The provided method can determine whether the robot meets the conditions for elevator boarding. If the robot does not meet the conditions, elevator boarding control is terminated, and an alarm can be issued or an action can be actively executed to eliminate obstacles in the elevator. If the robot meets the conditions, a target cost image is obtained and used to select the current stop point. The current stop point is compared with the historical stop points to determine whether to reuse the historical stop point. The current stop point or the historical stop point is then used as the target stop point, and the robot is controlled to move to the target stop point.
[0109] It should be noted that, for the sake of simplicity of description, the aforementioned method embodiments are all expressed as a series of action combinations. However, those skilled in the art should be aware that this application is not limited to the described order of actions, because according to this application, certain steps can be performed in other orders.
[0110] like Figure 13 FIG2 is a schematic structural diagram of an elevator control device 1300 provided in an embodiment of the present application. The elevator control device 1300 is configured on an electronic device.
[0111] Specifically, the elevator control device 1300 may include:
[0112] The cost map acquisition unit 1301 is configured to acquire a cost map in response to the robot meeting the elevator riding condition;
[0113] A candidate point determination unit 1302 is configured to determine candidate stopping points in the elevator based on the cost map;
[0114] A target cost image acquisition unit 1303 is configured to acquire a target cost image, wherein the target cost image represents a positional relationship between the candidate stopping point and a preset attraction point in the elevator;
[0115] The elevator entry control unit 1304 is configured to control the robot to go to a target stopping point in the elevator based on the target cost image, where the target stopping point is included in the candidate stopping points presented in the target cost image.
[0116] In some embodiments of the present application, the elevator control device 1300 may further include an elevator taking determination unit, which is used to: detect a passable area along the direction of the elevator door of the elevator, the size of the passable area is related to the shape information of the robot, and there are no obstacles in the passable area; if the passable area does not exist, determine the total number of first connecting lines that do not pass through obstacles, and the first connecting lines are the connecting lines between the current position of the robot and each point on the preset horizontal line in the elevator; in response to the total number being greater than a quantity threshold, control the robot to move toward the elevator; in response to the distance between the robot and the elevator being less than a first distance threshold, the robot detects the passable area and determines that the robot meets the elevator taking condition.
[0117] In some embodiments of the present application, the elevator includes a first area close to the elevator door and a second area away from the elevator door; the elevator entry control device 1300 may also include an elevator riding determination unit, which is used to: obtain a first proportion of non-obstacle points in the first area in the first area; if the first proportion is less than a first proportion threshold, obtain a second proportion of robot visible points in the second area in the second area; if the first proportion is greater than or equal to the first proportion threshold, or the second proportion is greater than or equal to the second proportion threshold, it is determined that the robot meets the elevator riding condition.
[0118] In some embodiments of the present application, the elevator control device 1300 may also include an attraction image acquisition unit, which is used to: use the center position between the door center point and the door end point of the elevator as the attraction point; perform distance transformation on the distance between each point in the elevator and the attraction point to obtain an attraction image, wherein the attraction image represents the positional relationship between each point in the elevator and the attraction point.
[0119] In some embodiments of the present application, the candidate point determination unit 1302 can be specifically used to: determine the points in the elevator in the cost map; for each point in the elevator, determine a second line between the point and the current position of the robot, and use the points where the second line does not pass through obstacles as the candidate stopping points.
[0120] In some embodiments of the present application, the elevator entry control unit 1304 can be specifically used to: determine the current stopping point in the elevator based on the target cost image; determine the target stopping point between the current stopping point and the historical stopping points; and control the robot to go to the target stopping point.
[0121] In some embodiments of the present application, the elevator control unit 1304 can be specifically used to: if the first distance between the historical stop point and the attraction point is greater than a second distance threshold, then the current stop point is used as the target stop point; if the first distance is less than or equal to the second distance threshold, then the point between the current stop point and the historical stop point that is closest to the current position of the robot is used as the target stop point.
[0122] It should be noted that for the convenience and simplicity of description, the specific working process of the above elevator control device 1300 can be referred to Figures 1 to 12 The corresponding process of the method will not be described in detail here.
[0123] like Figure 14 , which is a schematic diagram of an electronic device provided in an embodiment of the present application. Specifically, the electronic device 14 may include: a processor 140, a memory 141, and a computer program 142 stored in the memory 141 and executable on the processor 140, such as an elevator control program. When the processor 140 executes the computer program 142, the steps in the above-mentioned various elevator control method embodiments are implemented, such as Figure 1 Alternatively, when the processor 140 executes the computer program 142, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 13 The functions of the cost map acquisition unit 1301, the candidate point determination unit 1302, the target cost image acquisition unit 1303 and the elevator entry control unit 1304 are shown.
[0124] The computer program may be divided into one or more modules / units, which are stored in the memory 141 and executed by the processor 140 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.
[0125] For example, the computer program can be divided into: a cost map acquisition unit, a candidate point determination unit, a target cost image acquisition unit, and an elevator entry control unit. The specific functions of each unit are as follows: the cost map acquisition unit is used to acquire a cost map in response to the robot meeting the elevator boarding conditions; the candidate point determination unit is used to determine the candidate stopping points in the elevator based on the cost map; the target cost image acquisition unit is used to acquire a target cost image, the target cost image representing the positional relationship between the candidate stopping points and the preset attraction points in the elevator; the elevator entry control unit is used to control the robot to go to the target stopping point in the elevator based on the target cost image, the target stopping point being included in the candidate stopping points presented in the target cost image.
[0126] The electronic device may include, but is not limited to, a processor 140 and a memory 141. Those skilled in the art will appreciate that Figure 14 These are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.
[0127] The processor 140 may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.
[0128] The memory 141 may be an internal storage unit of the electronic device, such as a hard disk or memory of the electronic device. The memory 141 may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Furthermore, the memory 141 may also include both an internal storage unit of the electronic device and an external storage device. The memory 141 is used to store the computer program and other programs and data required by the electronic device. The memory 141 may also be used to temporarily store data that has been output or is to be output.
[0129] It should be noted that, for the convenience and brevity of description, the structure of the above electronic device can also refer to the specific description of the structure in the method embodiment, which will not be repeated here.
[0130] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.
[0131] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.
[0132] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0133] In the embodiments provided in the present application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0134] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.
[0135] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.
[0136] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.
[0137] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.
Claims
1. A method for controlling elevator entry, characterized in that: include: In response to the robot meeting the elevator riding conditions, obtaining a cost map; Determining candidate stopping points in the elevator based on the cost map; Acquire a target cost image, wherein the target cost image represents a positional relationship between the candidate stopping point and a preset attraction point in the elevator; Based on the target cost image, the robot is controlled to go to a target stopping point in the elevator, where the target stopping point is included in the candidate stopping points presented in the target cost image.
2. The elevator control method according to claim 1, wherein: Before obtaining the cost map, the elevator entry control method further includes: Detecting a passable area along a direction of an elevator door of the elevator, wherein a size of the passable area is associated with shape information of the robot; If the traversable area does not exist, determining the total number of first connecting lines that do not pass through obstacles, where the first connecting lines are connecting the current position of the robot and each point on a preset horizontal line in the elevator; In response to the total number being greater than a number threshold, controlling the robot to move toward the elevator; In response to the distance between the robot and the elevator being less than a first distance threshold, the robot detects the passable area and determines that the robot meets the elevator riding condition.
3. The elevator control method according to claim 1, wherein: The elevator comprises a first area close to the elevator door and a second area away from the elevator door; Before obtaining the cost map, the elevator entry control method further includes: Obtain a first proportion of non-obstacle points in the first area; If the first proportion is less than a first proportion threshold, obtaining a second proportion of the robot's visible point in the second area in the second area; If the first proportion is greater than or equal to a first proportion threshold, or the second proportion is greater than or equal to a second proportion threshold, it is determined that the robot meets the elevator riding condition.
4. The elevator control method according to any one of claims 1 to 3, characterized in that: Before acquiring the target cost image, the elevator entry control method further includes: The center position between the door center point and the door end point of the elevator is used as the attraction point; Distance transformation is performed on the distances between each point in the elevator and the attraction point to obtain an attraction image, where the attraction image represents the positional relationship between each point in the elevator and the attraction point.
5. The elevator control method according to any one of claims 1 to 3, characterized in that: Determining a candidate stopping point in the elevator based on the cost map includes: Determining a point within the elevator in the costmap; For each point in the elevator, a second line between the point and the current position of the robot is determined, and points on the second line that do not pass through obstacles are used as candidate stopping points.
6. The elevator entry control method according to any one of claims 1 to 3, characterized in that: The controlling the robot to move to a target stopping point in the elevator based on the target cost image includes: determining a current stopping point in the elevator based on the target cost image; Determine the target stopping point between the current stopping point and the historical stopping points; Control the robot to go to the target stopping point.
7. The elevator control method according to claim 6, wherein: Determining the target stopping point between the current stopping point and the historical stopping points includes: If the first distance between the historical stopping point and the attraction point is greater than a second distance threshold, taking the current stopping point as the target stopping point; If the first distance is less than or equal to a second distance threshold, the point between the current stopping point and the historical stopping points that is closest to the current position of the robot is used as the target stopping point.
8. An elevator control device, characterized in that: include: a cost map acquisition unit, configured to acquire a cost map in response to the robot meeting an elevator riding condition; a candidate point determination unit, configured to determine candidate stopping points in the elevator based on the cost map; a target cost image acquisition unit, configured to acquire a target cost image, wherein the target cost image represents a positional relationship between the candidate stopping point and a preset attraction point in the elevator; An elevator entry control unit is used to control the robot to go to a target stopping point in the elevator based on the target cost image, where the target stopping point is included in the candidate stopping points presented in the target cost image.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the elevator control method according to any one of claims 1 to 7 are implemented.
10. A computer program product, characterized in that The invention comprises a computer program, which, when executed, enables the elevator control method according to any one of claims 1 to 7 to be executed.