A method, device, computer equipment and storage medium for counting goods on shelves

Abstract

The present disclosure provides a method, apparatus, computer equipment and storage medium for counting goods on shelves, wherein the method comprises: in response to receiving an inventory task, determining channel information corresponding to a target site based on a graph structure; determining the position information of the starting point and the position information of the end point of the channel to be counted according to the position information of the passage nodes of each channel of the target site and the reachable path; determining the nodes to be passed in the channel to be counted in the inventory direction according to the position information of the starting point, the position information of the end point and the orientation information of the inventory robot to be oriented at each passage node; starting from the starting point, determining the next node to be passed that is closest to the inventory robot in the inventory direction according to the current posture information of the inventory robot and the position information of each node to be passed, and controlling the inventory robot to move to the next node to be passed to count the goods on the shelves until the last node to be passed is reached.

Description

Technical Field

[0001] The present disclosure relates to the technical field of goods inventory, and in particular to a method, apparatus, computer equipment, and storage medium for inventorying goods on shelves. Background Art

[0002] In logistics and warehouse management, inventory counting robots are commonly used to count goods on shelves. These intelligent devices automatically identify items on shelves without stopping, providing timely and accurate inventory data. While identifying items on shelves, these robots need to select a path to conduct a comprehensive and efficient inventory count. Currently, efficient inventory counting remains a significant concern. Summary of the Invention

[0003] The embodiments of the present disclosure at least provide a method, apparatus, computer equipment, and storage medium for inventorying goods on shelves.

[0004] In a first aspect, embodiments of the present disclosure provide a method for inventorying goods on shelves. A graph structure is pre-modeled for a target site where goods on shelves are located. The graph structure includes a plurality of passage nodes, each passage node having corresponding orientation information, and a line connecting the passage nodes represents a reachable path between the two passage nodes. The method includes:

[0005] In response to receiving an inventory task for a passage to be inventoried in the target site, determining passage information corresponding to the target site based on the graph structure; the inventory task includes an inventory direction for the passage to be inventoried; the passage information corresponding to the target site includes position information of passage nodes of each passage of the target site, orientation information of an inventory robot to be oriented at each passage node, and reachable paths between passage nodes;

[0006] Determine the location information of the starting point and the end point of the channel to be counted based on the location information of the pass nodes of each channel of the target site and the reachable paths between the pass nodes;

[0007] Determining a node to be passed in the to-be-passed passage in the to-be-passed direction based on the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory robot on the reachable path;

[0008] Starting from the starting point of the aisle to be counted, the next node to be passed closest to the inventory robot in the inventory direction is determined based on the current posture information of the inventory robot and the position information of each node to be passed, and the inventory robot is controlled to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

[0009] In an optional embodiment, controlling the inventory counting robot to move to the next node to be passed to perform inventory counting of goods on shelves includes:

[0010] Determining, based on the current posture information of the inventory counting robot and the position information of the next node to be passed, the deflection angle information of the orientation of the inventory counting robot at the current position relative to the direction of the line connecting the current position and the next node to be passed;

[0011] When the deflection angle is not zero, based on the deflection angle information, the inventory robot is controlled to rotate until the deflection angle is zero and then move to the next node to be passed to perform inventory of goods on the shelf.

[0012] In an optional embodiment, determining the node to be passed in the passage to be counted in the inventory direction based on the position information of the starting point, the position information of the end point, and the direction information of each pass node on the reachable path to be oriented by the inventory robot includes:

[0013] Determining, based on the direction information of each pass node on the reachable path toward which the inventory counting robot is directed, a first pass node in the inventory counting direction located in the passage to be counted, among the pass nodes;

[0014] According to the position information of the starting point and the position information of the end point, a second pass node interpolated between the starting point and the end point is determined; based on the first pass node and the second pass node, the node to be passed is determined; wherein the distance between any two adjacent nodes to be passed is equal.

[0015] In an optional embodiment, the inventory direction includes an entry direction and a return direction; and the method further includes:

[0016] In response to the inventory robot reaching the end point of the aisle to be inventoried, the inventory robot is controlled to rotate to the return direction at the end point according to the orientation information of the inventory robot to be directed at the end point, and starting from the end point, the next node to be passed that is closest to the inventory robot in the return direction is determined according to the current posture information of the inventory robot and the position information of each node to be passed, and the inventory robot is controlled to move to the next node to be passed to perform inventory of shelf goods until it reaches the starting point.

[0017] In an optional embodiment, the passage to be inventoried includes a flue; the node to be passed includes a flue node in the flue; and the method further includes:

[0018] In response to the inventory robot arriving at the smoke node in the smoke duct, the inventory robot is controlled to rotate at the smoke node according to the orientation information of the inventory robot to be directed at the smoke node, and starting from the smoke node, the next node to be passed that is closest to the inventory robot in the smoke direction is determined according to the current posture information of the inventory robot and the position information of each node to be passed in the smoke duct, and the inventory robot is controlled to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed in the smoke duct.

[0019] In an optional embodiment, the channel information corresponding to the target site includes lifting information of the inventory robot at the flue node; and the method further includes:

[0020] In response to the inventory counting robot arriving at the flue node, the inventory counting robot is controlled to be raised or lowered according to the lifting and lowering information of the inventory counting robot at the flue node.

[0021] In an optional embodiment, there are multiple passages to be counted; before controlling the counting robot to move to the next node to be passed for inventory counting, the method further includes:

[0022] In response to the inventory robot returning to the starting point of the current aisle to be counted and the number of remaining aisles to be counted is at least one, determining a target aisle to be counted adjacent to the current aisle to be counted among the remaining aisles to be counted;

[0023] Determining the orientation information of the inventory robot at the starting point of the current aisle to be inventoried based on the orientation information of the target aisle to be inventoried relative to the current aisle to be inventoried;

[0024] Determining the rotation angle information of the inventory counting robot according to the current posture information of the inventory counting robot and the orientation information to be oriented;

[0025] According to the rotation angle information, the inventory robot is controlled to rotate to the orientation to be faced, so that the inventory robot moves to the starting point of the target channel to be inventoried according to the orientation to be faced.

[0026] In a second aspect, an embodiment of the present disclosure further provides a device for inventorying goods on shelves, which pre-models a graph structure for a target site where goods on shelves are located. The graph structure includes a plurality of passage nodes, each passage node having corresponding orientation information, and a line between passage nodes represents a reachable path between the two passage nodes. The device includes:

[0027] A first determination module is configured to, in response to receiving an inventory task for an aisle to be inventoried in the target site, determine, based on the graph structure, a channel information corresponding to the target site; the inventory task includes an inventory direction for the aisle to be inventoried; the channel information corresponding to the target site includes position information of passage nodes of each aisle of the target site, orientation information of an inventory robot to be oriented at each passage node, and reachable paths between passage nodes;

[0028] A second determining module is configured to determine the location information of the starting point and the ending point of the passage to be inventoried based on the location information of the passage nodes of each passage of the target site and the reachable paths between the passage nodes;

[0029] a third determining module, configured to determine a node to be passed in the passage to be counted in the direction of the inventory counting based on the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory counting robot on the reachable path;

[0030] The first control module is used to start from the starting point of the inventory channel, determine the next node to be passed that is closest to the inventory robot in the inventory direction based on the current posture information of the inventory robot and the position information of each node to be passed, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

[0031] In a third aspect, an embodiment of the present disclosure further provides a computer device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are performed.

[0032] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0033] The above-mentioned shelf goods inventory method provided by the embodiment of the present disclosure pre-models a graph structure for the target site where the shelf goods are located. The graph structure can record multiple access nodes of the target site, and each access node has corresponding orientation information to be oriented. The connection between the graph nodes can represent that the path between the two graph nodes is reachable. In this way, in the robot inventory process, after determining each to-be-passed node in the to-be-inventory channel that is located in the inventory direction, starting from the starting point of the to-be-inventory channel, the next to-be-passed node closest to the inventory robot in the inventory direction is determined in sequence. In the above process, each next to-be-passed node found is the reachable to-be-passed node closest to the current node. Therefore, the inventory robot can move according to the shortest path in the to-be-inventory channel, which can improve the inventory efficiency of the inventory robot.

[0034] For a description of the effects of the above-mentioned shelf goods inventory counting device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned shelf goods inventory counting method, which will not be repeated here.

[0035] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0037] Figure 1 A flowchart of a shelf goods inventory method provided by an embodiment of the present disclosure is shown;

[0038] Figure 2 shows a graph structure corresponding to a target site provided by an embodiment of the present disclosure;

[0039] Figure 3 A schematic structural diagram of a shelf cargo inventory device provided by an embodiment of the present disclosure is shown;

[0040] Figure 4 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0042] Research has found that in logistics and warehouse management, inventory robots are commonly used to count goods on shelves. These robots traverse various aisles, counting goods on shelves and providing timely and accurate inventory data. When identifying items on shelves, these robots require route selection to optimize item identification. However, how to select the right route for efficient inventory counting remains a significant challenge.

[0043] Based on this, the present disclosure provides a method for inventorying goods on shelves, which pre-models a graph structure for the target site where the goods on the shelves are located. The graph structure can record multiple passage nodes of the target site, and each passage node has corresponding orientation information to be oriented. The connection between the graph nodes can represent that the path between the two graph nodes is reachable. In this way, during the robot inventory process, after determining each to-be-passed node in the to-be-inventory channel that is located in the inventory direction, starting from the starting point of the to-be-inventory channel, the next to-be-passed node closest to the inventory robot in the inventory direction is determined in sequence. In the above process, each next to-be-passed node found is the reachable to-be-passed node closest to the current node, so that the inventory robot can move along the shortest path in the to-be-inventory channel, thereby improving the inventory efficiency of the inventory robot.

[0044] The defects of the above solutions and the proposed solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0045] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0046] To facilitate understanding of this embodiment, a shelf inventory method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the shelf inventory method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.

[0047] See also Figure 1 FIG. 1 is a flowchart of a method for counting goods on shelves according to an embodiment of the present disclosure. The method includes steps S101 to S104, wherein:

[0048] S101: In response to receiving an inventory task for a channel to be inventoried in a target site, determining channel information corresponding to the target site based on a graph structure; the inventory task includes the inventory direction of the channel to be inventoried; the channel information corresponding to the target site includes the position information of the passage nodes of each channel of the target site, the orientation information of the inventory robot to be oriented at each of the passage nodes, and the reachable paths between the passage nodes.

[0049] S102: Determine the location information of the starting point and the end point of the channel to be inventoried based on the location information of the pass nodes of each channel of the target site and the reachable paths between the communication nodes.

[0050] S103: Determine the node to be passed in the inventory direction in the channel to be counted based on the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory robot on the reachable path.

[0051] S104: Starting from the starting point of the channel to be counted, the next node to be passed closest to the inventory robot in the inventory direction is determined based on the current posture information of the inventory robot and the position information of each node to be passed, and the inventory robot is controlled to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

[0052] In the embodiment of the present disclosure, the target site may be, for example, a warehouse, library, archive storehouse, etc. The shelves in the target site may be arranged into at least one aisle in any form, that is, the target site may include at least one aisle.

[0053] After receiving the inventory task assigned by the user, the inventory robot can autonomously complete the task of passing through the aisle and taking inventory of the goods on the shelves in the aisle.

[0054] In one embodiment, the inventory task may include identification information for the channel to be inventoried and the inventory direction for the channel to be inventoried. In specific implementations, the identification information for the channel to be inventoried may include the channel code, channel name, channel location information, etc., which are not specifically limited here. The inventory direction for the channel to be inventoried may include the entry direction (which may include entering the channel to be inventoried to the end point, or entering the channel to the target access node before the end point), the return direction (which may include returning from the end point of the channel to be inventoried, or returning from a target access node between the end points), etc., which are not specifically limited here.

[0055] In one example, an inventory task could be: Channel 1 (False, True), where Channel 1 represents the channel number of the channel to be inventoried; False and True represent the counting direction of the channel to be inventoried. Specifically, False represents the entry direction, specifically the direction from the channel to the end point; True represents the return direction, specifically the direction from the end point of the channel to be inventoried. In one embodiment, an inventory task can include the identification information of at least one channel to be inventoried and at least one counting direction for each channel to be inventoried.

[0056] In one example, an inventory task might be: Channel 1 (False, True). In this example, the task includes the identification of a channel to be counted (Channel 1), as well as two counting directions for Channel 1 (the direction from Channel 1 to the end point, and the direction from the end point back to the end point). In other words, the task indicates that the counting robot needs to enter Channel 1 for inventory and then return from the end point.

[0057] In another example, an inventory task can be: Channel 1 (False, True); Channel 2 (False). In this example, the inventory task contains the identification information of two tasks to be inventoried (Channel 1 and Channel 2), as well as two inventory directions of Channel 1 (the direction from entering Channel 1 to the end point and the direction from the end point of Channel 1 back to the end point) and one inventory direction of Channel 2 (the direction from entering the end point of Channel 2). In other words, the inventory task can indicate that the inventory robot needs to enter Channel 1 for inventory, return from the end point of Channel 1, and then enter Channel 2 for inventory. In one embodiment, the inventory task is: Channel 1 (False); Channel 2 (False), which can also indicate that the inventory robot needs to enter Channel 1 for inventory, return from the end point of Channel 1, and then enter Channel 2 for inventory. This embodiment is mainly for situations where the inventory robot can only exit Channel 1 first and then enter Channel 2, for example, if the end point of Channel 1 is an obstacle and the inventory robot cannot pass through. After the inventory robot enters channel 1 and completes the inventory, it needs to exit channel 1 first if it wants to enter channel 2 for inventory. Therefore, even if the inventory task does not include the inventory direction of returning from the end point of channel 1, the inventory robot still needs to execute the action of returning from the end point of channel 1.

[0058] In the embodiment of the present disclosure, a graph structure model is pre-made for the target site where the goods on the shelf are located, such as Figure 2 As shown. This graph structure can include channel information corresponding to the target site. Specifically, the graph structure can include the access nodes of each channel of the target site. Each access node has corresponding orientation information. The solid line between the access nodes represents that the path between the two access nodes is reachable. The bidirectional arrows between the access nodes represent that the inventory robot can turn between the two access nodes. Figure 2 Only one passageway and its access nodes are shown. The node information for each access node in the graph structure can include the corresponding access node's location information and the orientation information that the inventory counting robot should be oriented toward at the corresponding access node. Here, the orientation information that the inventory counting robot should be oriented toward at the access node refers to the orientation information that controls the inventory counting robot's orientation when it moves to the access node.

[0059] Figure 2In the example, nodes 0 through 11 are the access nodes within a channel. Nodes 0 through 3 represent the access nodes at the channel's starting point, nodes 4 through 7 represent the access nodes at the channel's flue, and nodes 8 through 11 represent the access nodes at the channel's end point. Taking node 0 as an example, in its node information (0 / -2.75, -85, 0), the first 0 represents the access node's number, -2.75 and -85 represent the node's horizontal and vertical coordinates within its coordinate system, respectively. The second 0 represents the orientation of the inventory robot at the access node, where 0 represents 0 degrees.

[0060] The inventory robot can have four directions at the same position: front, back, left, and right. It should be understood that the four directions are relative to the direction of entering the passage, for example, the direction of entering the passage is the forward direction. Figure 2 The styles of the passing nodes can be used to distinguish them. Take the nodes 0 to 3 at the starting point as an example. Figure 2 As shown, a solid node can indicate that the inventory robot is facing forward or backward, and a hollow node can indicate that the inventory robot is facing left or right. Whether the inventory robot is facing forward, backward, left or right can be further determined based on the orientation information in the node information. For example, the orientation information of node 0 is 0 degrees, which means that the inventory robot is facing forward at this position. The orientation information of node 1 is 90 degrees, which means that the inventory robot is facing right at this position. The orientation information of node 2 is 180 degrees, which means that the inventory robot is facing backward at this position. The orientation information of node 3 is 270 degrees, which means that the inventory robot is facing left at this position.

[0061] In addition, Figure 2 In this example, taking nodes 0, 4, and 8 as examples, these nodes have different abscissas, but the same ordinates (all -1.85) and the same orientation (all 0 degrees). This shows that the trajectory of the counting robot when following nodes 0, 4, and 8 should be: moving horizontally and forward to the endpoint. Taking nodes 8 and 10 as examples, these nodes have the same abscissas (all 99.9) and ordinates (all -1.85), but the orientation has changed from 0 degrees to 180 degrees. This shows that the trajectory of the counting robot when following nodes 8 to 10 should be: rotating 180 degrees backward in place. Taking nodes 10, 6, and 2 as examples, these nodes have different abscissas, but the same ordinates (all -1.85) and the same orientation (all 180 degrees). This shows that the trajectory of the counting robot when following nodes 10, 6, and 2 should be: returning horizontally from the endpoint.

[0062] In one embodiment, the inventory task may include the target site's site information. This site information may include location information, identification information, physical scene information, and the like. In a specific implementation, upon receiving an inventory task for a channel to be inventoried, the channel information corresponding to the target channel may be determined based on the aforementioned graph structure and the target site's site information. The graph structure may be pre-stored in the inventory robot's storage device or retrieved from the backend by the inventory robot after receiving the inventory task. This is not specifically limited here.

[0063] After receiving the inventory task of the channel to be counted, the passage node of the channel to be counted can be determined according to the identification information of the channel to be counted. According to the position information of the passage node of the channel to be counted, the position information of the starting point and the position information of the end point of the channel to be counted can be determined.

[0064] Based on the location information of the starting point and end point of the passage to be inventoried, and the orientation information of the inventory robot at each pass node, the nodes to be passed in the passage to be inventoried and in the direction of the inventory can be determined. If the inventory direction includes the passage from the entry point of the passage to be inventoried to the end point, the starting point, the end point, and the pass nodes between them can be considered as the pass nodes to be passed. If the inventory direction includes the passage from the entry point of the passage to be inventoried to the target pass node before the end point, the starting point, the target pass node, and the pass nodes between them can be considered as the pass nodes to be passed.

[0065] For example, if the counting direction is the end point of the passage to be counted and the end point of the passage to be counted, it can be determined that the nodes to be passed can include at least the following nodes: the node at the starting position with the orientation information of 0 degrees (for example Figure 2 Node 1 in the end point; the node at the end point with the orientation information of 0 degrees (for example Figure 2 Node 8 in the end position; the node at the end position with the orientation information of 180 degrees (for example Figure 2 Node 10 in the starting position; the node with the orientation information of 180 degrees (for example Figure 2 Node 2 in ).

[0066] In order to enable the inventory robot to move from the starting point to the end point along the shortest route, in one embodiment, based on the position information of the starting point, the position information of the end point, and the direction information of each pass node on the reachable path that the inventory robot is facing, the nodes to be passed through located in the channel to be inventoryed and in the inventory direction are determined, which can include: determining the first pass node in the channel to be inventoryed and in the inventory direction among the pass nodes based on the direction information of each pass node on the reachable path that the inventory robot is facing; determining the second pass node interpolated between the starting point and the end point based on the position information of the starting point and the position information of the end point; determining the node to be passed through based on the first pass node and the second pass node; wherein the distance between any two adjacent nodes to be passed is equal.

[0067] In the above embodiment, the first pass node can be determined from the existing pass nodes according to the above method. Figure 2 The graph structure shown in FIG4 determines the first pass node.

[0068] The second pass node can be obtained through interpolation. Specifically, based on the starting point and the end point's location information, the distance between the starting point and the end point can be determined. Then, based on this distance, the second pass node interpolated between the starting point and the end point can be determined. In one approach, the starting point and the end point's location information within the channel to be inventoried can be input into a Pure Pursuit algorithm, which then uses this algorithm to obtain the interpolated location information for the second pass node.

[0069] If the inventory task indicates that the inventory direction includes entering the passage to be counted to the end point, the second pass node obtained by interpolation and the first pass node determined from the existing pass nodes can be used as the node to be passed. If the inventory task indicates that the inventory direction includes entering the passage to be counted to the target pass node before the end point, the second pass node obtained by interpolation and located before the target pass node and the first pass node determined from the existing pass nodes can be used as the node to be passed.

[0070] In a specific implementation, the more the number of interpolated second pass nodes is, that is, the shorter the distance between any two adjacent nodes to be passed is, the shorter the path of the inventory robot moving from the starting point to the end point is.

[0071] During the movement, the inventory robot can start from the starting point of the aisle to be counted, determine the next node to be passed closest to the inventory robot in the inventory direction according to the current posture information of the inventory robot and the position information of each node to be passed, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods.

[0072] The current position information of the inventory counting robot may include current position information and current orientation information. In a specific implementation, the Pure Pursuit algorithm can be used to find the next node to be passed closest to the inventory counting robot in the inventory counting direction based on the current position information, current orientation information, and the position information of each node to be passed.

[0073] In order to control the inventory robot to successfully move to the end point, in one embodiment, controlling the inventory robot to move to the next node to be passed to perform inventory of goods on the shelves may include: determining, based on the current posture information of the inventory robot and the position information of the next node to be passed, the deflection angle information of the inventory robot at the current position relative to the direction of the line between the current position and the next node to be passed; when the deflection angle is not zero, based on the deflection angle information, controlling the inventory robot to rotate until the deflection angle is zero and then move to the next node to be passed to perform inventory of goods on the shelves.

[0074] In the above embodiment, as previously described, the current posture information of the inventory robot may include current position information and current orientation information. Based on the current position information, the position information of the next node to be passed can be obtained, and the direction of the line between the current position and the next node to be passed can be obtained. Based on the current orientation information of the inventory robot and the aforementioned connecting line direction, the deflection angle information of the inventory robot's orientation at the current position relative to the connecting line direction can be determined. In a specific implementation, the Pure Pursuit algorithm can be used to determine the deflection angle information based on the current posture information of the inventory robot and the position information of the next node to be passed.

[0075] When the deflection angle information indicates a zero deflection angle, it indicates that the inventory counting robot can move directly from its current position to the next node to be passed according to its current orientation. When the deflection angle information indicates a non-zero deflection angle, it indicates that the inventory counting robot cannot move directly from its current position to the next node to be passed according to its current orientation. In this case, the deflection angle information can be converted into a robot chassis control code. The chassis control code can control the inventory counting robot to rotate until the deflection angle is zero, and then move to the next node to be passed to perform inventory of shelf goods.

[0076] The above process is then repeated until the robot reaches the last node to be passed. If the counting direction only includes the entry direction, the last node to be passed is the end point of the passage to be counted. As the robot moves from the starting point to the end point, it can continuously adjust its direction, and the path it travels is a curve that generally converges to a straight line.

[0077] In one embodiment, when the inventory direction includes an entry direction and a return direction, the above method may further include: in response to the inventory robot reaching the end point of the channel to be inventoried, according to the orientation information of the inventory robot to be directed at the end point, controlling the inventory robot to rotate to the return direction at the end point, and starting from the end point, according to the current posture information of the inventory robot and the position information of each node to be passed, determining the next node to be passed closest to the inventory robot in the return direction, and controlling the inventory robot to move to the next node to be passed to perform inventory of the shelf goods until it reaches the starting point.

[0078] In the above embodiment, when the inventory counting robot reaches the end of the channel to be counted, the inventory counting robot is facing forward, for example, Figure 2 In the graph structure shown, the inventory robot is located at node 8, and the orientation information is 0 degrees. Since the inventory direction includes the return direction, the inventory robot needs to rotate 180 degrees at the end point, that is, the orientation information to be faced by the inventory robot at the end point is 180 degrees. Figure 2 According to the nodes shown in the graph structure, the inventory robot should move according to node 8 to node 10. Therefore, based on the node information of node 8 and node 10, the inventory robot can be controlled to rotate in place at the end point to the return direction.

[0079] Afterwards, starting from the end point, the robot can determine the next node closest to the robot in the return direction based on the robot's current posture and the location information of each node to be passed. The robot can then be controlled to move to the next node to pass and count the shelf goods until it reaches the starting point. This process is similar to the aforementioned process of starting from the starting point and determining the next node closest to the robot in the return direction based on the robot's current posture and the location information of each node to be passed, until it reaches the last node to be passed. This process will not be repeated here.

[0080] In one embodiment, the passage to be counted may include a smoke duct, and the node to be passed may include a smoke duct node in the smoke duct. The method may further include: in response to the inventory robot reaching a smoke duct node in the smoke duct, based on the orientation information of the inventory robot at the smoke duct node to be oriented, controlling the inventory robot to rotate at the smoke duct node, and starting from the smoke duct node, determining the next node to be passed closest to the inventory robot in the smoke duct direction based on the current posture information of the inventory robot and the position information of each node to be passed in the smoke duct, and controlling the inventory robot to move to the next node to be passed to perform inventory of goods on the shelves, until reaching the last node to be passed in the smoke duct.

[0081] In the above embodiment, when the inventory counting robot reaches the flue node in the flue, the direction of the inventory counting robot is forward or backward. Figure 2In the graph structure shown, the inventory robot is located at node 4 or node 6, and the orientation information is 0 degrees or 180 degrees. Usually, the direction of the flue is inconsistent with the direction of the passage, so the inventory robot needs to rotate 90 degrees in place at the current position, that is, the orientation information of the inventory robot at the current flue node is 90 degrees or 270 degrees. Figure 2 For the nodes shown in the graph structure shown, the inventory robot should move according to node 4-node 7 or node 6-node 7. Therefore, based on the node information of node 4 and node 7, the inventory robot can be controlled to rotate 90 degrees to the left at the current position to the direction of the flue, or based on the node information of node 6 and node 7, the inventory robot can be controlled to rotate 90 degrees to the right at the current position to the direction of the flue.

[0082] Afterwards, starting from this chimney node, the robot can determine the next nearest node in the chimney direction based on the robot's current posture and the location information of each pending node in the chimney. The robot can then be controlled to move to the next pending node to count the shelf goods until it reaches the last pending node in the chimney. This process is similar to the aforementioned process of starting from the starting point and determining the next nearest node in the return direction based on the robot's current posture and the location information of each pending node, and so will not be repeated here.

[0083] In the disclosed embodiments, various flue nodes within the flue may differ in height, necessitating that the inventory robot perform lifting and lowering actions at the corresponding flue nodes. In one embodiment, the channel information corresponding to the target site may also include information about the elevation of the inventory robot at the flue node. The method may further include, in response to the inventory robot arriving at the flue node, controlling the inventory robot to raise or lower itself based on the elevation information at the flue node.

[0084] When the inventory robot reaches the flue node, it can obtain the flue node's elevation information. This elevation information can include the robot's elevation height. Based on this elevation information at the flue node, the inventory robot is controlled to raise or lower itself, allowing for a comprehensive inventory of the shelves.

[0085] In the embodiment of the present disclosure, the number of aisles to be inventoried can be multiple, that is, the inventory task can instruct to inventory the goods on shelves in multiple aisles to be inventoried. In one embodiment, before controlling the inventory robot to move to the next node to be passed for inventory, the above method also includes: in response to the inventory robot returning to the starting point of the current aisle to be inventoried, and the number of remaining aisles to be inventoried is at least one, determining a target aisle to be inventoried adjacent to the current aisle to be inventoried among the remaining aisles to be inventoried; determining the orientation information of the inventory robot at the starting point of the current aisle to be inventoried based on the orientation information of the target aisle to be inventoried relative to the current aisle to be inventoried; determining the rotation angle information of the inventory robot based on the current position information of the inventory robot and the orientation information to be oriented; and controlling the inventory robot to rotate to the orientation to be oriented based on the rotation angle information, so that the inventory robot moves to the starting point of the target aisle to be inventoried according to the orientation to be oriented.

[0086] In the above embodiment, when the inventory counting robot returns to the starting point of the current aisle to be counted, the direction of the inventory counting robot is backward. Figure 2 In the graph structure shown, the inventory robot is located at node 2, with its orientation indicated as 180 degrees. When there is at least one remaining aisle to be inventoried, the inventory robot must rotate in place at its current position and move to the next aisle to be inventoried. Here, the target aisle adjacent to the current aisle to be inventoried can be determined. The target aisle adjacent to the current aisle to be inventoried may be located to the left or right of the current aisle to be inventoried. In other words, the target aisle to be inventoried is located to the left or right of the current aisle to be inventoried.

[0087] If the target aisle to be inventoried is on the left relative to the current aisle to be inventoried, the inventory robot can be determined to be oriented to the left at the starting point of the current aisle to be inventoried. If the target aisle to be inventoried is on the right relative to the current aisle to be inventoried, the inventory robot can be determined to be oriented to the right at the starting point of the current aisle to be inventoried.

[0088] If the orientation information to be oriented is leftward, the rotation angle information of the inventory robot can be determined to be 90 degrees (or 270 degrees) to the left based on the current position information of the inventory robot and the orientation information to be oriented. If the orientation information to be oriented is rightward, the rotation angle information of the inventory robot can be determined to be 90 degrees to the right based on the current position information of the inventory robot and the orientation information to be oriented.

[0089] Based on the rotation angle information determined above, the inventory counting robot can be controlled to rotate to the desired orientation, so that the inventory counting robot moves to the starting point of the target aisle to be counted according to the desired orientation. Next, the shelf inventory of the target aisle to be counted can be carried out according to the above process.

[0090] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0091] Based on the same inventive concept, the embodiments of the present disclosure also provide a shelf cargo inventory device corresponding to the shelf cargo inventory method. Since the principle of solving the problem by the device in the embodiments of the present disclosure is similar to that of the above-mentioned shelf cargo inventory method in the embodiments of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0092] Reference Figure 3 FIG. 1 is a schematic diagram of a device for counting goods on shelves provided by an embodiment of the present disclosure. A graph structure is pre-modeled for a target site where goods on shelves are located. The graph structure includes a plurality of passage nodes, each passage node having corresponding orientation information. A line between passage nodes represents a reachable path between the two passage nodes. The device includes:

[0093] A first determining module 301 is configured to, in response to receiving an inventory task for an aisle to be inventoried in the target site, determine aisle information corresponding to the target site based on the graph structure; the inventory task includes an inventory direction for the aisle to be inventoried; the aisle information corresponding to the target site includes position information of passage nodes of each aisle of the target site, orientation information of an inventory robot to be oriented toward each of the passage nodes, and reachable paths between passage nodes;

[0094] A second determining module 302 is configured to determine the location information of the starting point and the ending point of the passage to be inventoried based on the location information of the passage nodes of each passage of the target site and the reachable paths between the passage nodes;

[0095] A third determining module 303 is configured to determine a node to be passed in the passage to be counted in the counting direction based on the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory counting robot on the reachable path;

[0096] The first control module 304 is configured to determine, starting from the starting point of the aisle to be counted, the next node to be passed that is closest to the inventory robot in the inventory direction based on the current posture information of the inventory robot and the position information of each node to be passed, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

[0097] In an optional implementation, the first control module 304 is specifically configured to:

[0098] Determining, based on the current posture information of the inventory counting robot and the position information of the next node to be passed, the deflection angle information of the orientation of the inventory counting robot at the current position relative to the direction of the line connecting the current position and the next node to be passed;

[0099] When the deflection angle is not zero, based on the deflection angle information, the inventory robot is controlled to rotate until the deflection angle is zero and then move to the next node to be passed to perform inventory of goods on the shelf.

[0100] In an optional implementation manner, the third determining module 303 is specifically configured to:

[0101] Determining, based on the direction information of each pass node on the reachable path toward which the inventory counting robot is directed, a first pass node in the inventory counting direction located in the passage to be counted, among the pass nodes;

[0102] Determining a second pass node interpolated between the starting point and the end point according to the position information of the starting point and the position information of the end point;

[0103] The node to be passed is determined based on the first pass node and the second pass node; wherein the distance between any two adjacent nodes to be passed is equal.

[0104] In an optional embodiment, the inventory direction includes an entry direction and a return direction; and the device further includes:

[0105] The second control module is used to control the inventory robot to rotate to the return direction at the end point in response to the inventory robot reaching the end point of the channel to be inventoried, according to the orientation information of the inventory robot to be oriented at the end point, and starting from the end point, determine the next node to be passed that is closest to the inventory robot in the return direction according to the current posture information of the inventory robot and the position information of each node to be passed, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods until it reaches the starting point.

[0106] In an optional embodiment, the passage to be inventoried includes a flue; the node to be passed includes a flue node in the flue; and the device further includes:

[0107] The third control module is used to control the inventory robot to rotate at the smoke node in response to the inventory robot arriving at the smoke node in the smoke, according to the orientation information of the inventory robot to be directed at the smoke node, and starting from the smoke node, determine the next node to be passed that is closest to the inventory robot in the smoke direction according to the current posture information of the inventory robot and the position information of each node to be passed in the smoke, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed in the smoke.

[0108] In an optional embodiment, the channel information corresponding to the target site includes the lifting and lowering information of the inventory robot at the flue node; and the device further includes:

[0109] The fourth control module is used to control the inventory robot to rise or fall in response to the inventory robot arriving at the flue node according to the lifting and lowering information of the inventory robot at the flue node.

[0110] In an optional embodiment, the number of the passages to be counted is multiple; before controlling the inventory robot to move to the next node to be passed for inventory counting, the device further comprises:

[0111] a fourth determining module configured to, in response to the inventory robot returning to the starting point of the current aisle to be inventoried and the number of remaining aisles to be inventoried being at least one, determine a target aisle to be inventoried adjacent to the current aisle to be inventoried among the remaining aisles to be inventoried;

[0112] a fifth determining module, configured to determine, based on the position information of the target aisle to be inventoried relative to the current aisle to be inventoried, the position information of the inventory robot to be oriented at the starting point of the current aisle to be inventoried;

[0113] a sixth determining module, configured to determine the rotation angle information of the inventory counting robot according to the current posture information of the inventory counting robot and the orientation information to be oriented;

[0114] The fifth control module is configured to control the inventory counting robot to rotate to a desired orientation according to the rotation angle information, so that the inventory counting robot moves to a starting point of the target channel to be inventoried according to the desired orientation.

[0115] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0116] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Figure 4 4 is a schematic diagram of the structure of a computer device 400 provided in an embodiment of the present disclosure, including a processor 401, a memory 402, and a bus 403. The memory 402 is used to store execution instructions and includes a memory 4021 and an external memory 4022. The memory 4021 is also referred to as internal memory and is used to temporarily store operation data in the processor 401 and data exchanged with an external memory 4022 such as a hard disk. The processor 401 exchanges data with the external memory 4022 through the memory 4021. When the computer device 400 is running, the processor 401 communicates with the memory 402 via the bus 403, so that the processor 401 executes the following instructions:

[0117] In response to receiving an inventory task for a passage to be inventoried in a target site, determining passage information corresponding to the target site based on a graph structure; the inventory task includes an inventory direction for the passage to be inventoried; the passage information corresponding to the target site includes position information of passage nodes of each passage of the target site, orientation information of an inventory robot to be oriented at each passage node, and reachable paths between passage nodes;

[0118] Determine the location information of the starting point and the end point of the channel to be counted based on the location information of the pass nodes of each channel of the target site and the reachable paths between the pass nodes;

[0119] Determining a node to be passed in the to-be-passed passage in the to-be-passed direction based on the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory robot on the reachable path;

[0120] Starting from the starting point of the aisle to be counted, the next node to be passed closest to the inventory robot in the inventory direction is determined based on the current posture information of the inventory robot and the position information of each node to be passed, and the inventory robot is controlled to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

[0121] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the shelf inventory counting method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0122] The embodiments of the present disclosure further provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the shelf goods inventory method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0123] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0124] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, 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 communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0125] 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.

[0126] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0128] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for counting goods on shelves, characterized in that: A graph structure model is pre-modeled for the target site where the shelf goods are located. The graph structure includes multiple pass nodes, each pass node has corresponding orientation information, and the connection between the pass nodes represents the path between the two pass nodes, including: In response to receiving an inventory task for a passage to be inventoried in the target site, determining passage information corresponding to the target site based on the graph structure; the inventory task includes an inventory direction of the passage to be inventoried; the passage information corresponding to the target site includes position information of passage nodes of each passage of the target site, orientation information of an inventory robot to be oriented at each passage node, and reachable paths between passage nodes; Determine the location information of the starting point and the end point of the channel to be counted according to the location information of the pass nodes of each channel of the target site and the reachable paths between the pass nodes; Determine the node to be passed in the to-be-passed channel in the direction of the inventory counting according to the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory counting robot on the reachable path; Starting from the starting point of the channel to be counted, the next node to be passed closest to the inventory robot in the inventory direction is determined according to the current posture information of the inventory robot and the position information of each node to be passed, and the inventory robot is controlled to move to the next node to be passed to count the goods on the shelves until it reaches the last node to be passed.

2. The method according to claim 1, characterized in that: The controlling the inventory counting robot to move to the next node to be passed to perform inventory counting of goods on the shelf includes: Determine, according to the current position information of the inventory counting robot and the position information of the next node to be passed, the deflection angle information of the orientation of the inventory counting robot at the current position relative to the direction of the line between the current position and the next node to be passed; When the deflection angle is not zero, based on the deflection angle information, the inventory counting robot is controlled to rotate until the deflection angle is zero and then move to the next node to be passed to perform inventory counting of goods on the shelf.

3. The method according to claim 1, characterized in that The determining of the nodes to be passed in the to-be-passed channel in the direction of the inventory counting according to the position information of the starting point, the position information of the end point, and the direction information to be oriented of each pass node of the inventory counting robot on the reachable path comprises: According to the direction information of each pass node on the reachable path of the inventory counting robot, determine, among the each pass node, a first pass node in the inventory counting direction that is located in the passage to be counted; Determine, according to the position information of the starting point and the position information of the end point, a second pass node interpolated between the starting point and the end point; The node to be passed is determined based on the first pass node and the second pass node; wherein the distance between any two adjacent nodes to be passed is equal.

4. The method according to claim 1, characterized in that The inventory direction includes an entry direction and a return direction; the method further includes: In response to the inventory robot arriving at the end point of the channel to be counted, according to the orientation information of the inventory robot to be oriented at the end point, the inventory robot is controlled to rotate to the return direction at the end point, and starting from the end point, according to the current posture information of the inventory robot and the position information of each of the nodes to be passed, the next node to be passed that is closest to the inventory robot in the return direction is determined, and the inventory robot is controlled to move to the next node to be passed to perform inventory of the goods on the shelves until it reaches the starting point.

5. The method according to claim 1, characterized in that The passage to be inventoried includes a flue; the node to be passed includes a flue node in the flue; the method further includes: In response to the inventory counting robot arriving at a smoke node in the smoke duct, according to the orientation information of the inventory counting robot to be oriented at the smoke node, the inventory counting robot is controlled to rotate at the smoke node, and starting from the smoke node, according to the current posture information of the inventory counting robot and the position information of each node to be passed in the smoke duct, the next node to be passed that is closest to the inventory counting robot in the smoke duct direction is determined, and the inventory counting robot is controlled to move to the next node to be passed to perform inventory of goods on the shelves until it reaches the last node to be passed in the smoke duct.

6. The method according to claim 5, characterized in that The channel information corresponding to the target site includes the lifting and lowering information of the inventory counting robot at the flue node; the method further includes: In response to the inventory counting robot arriving at the flue node, the inventory counting robot is controlled to be lifted or lowered according to the lifting and lowering information of the inventory counting robot at the flue node.

7. The method according to claim 1, characterized in that The number of the passages to be counted is multiple; before the inventory counting robot is controlled to move to the next node to be passed for inventory counting, the method further includes: In response to the inventory counting robot returning to the starting point of the current channel to be counted, and the number of remaining channels to be counted is at least one, determining a target channel to be counted adjacent to the current channel to be counted among the remaining channels to be counted; Determine the orientation information of the inventory counting robot at the starting point of the current channel to be counted according to the orientation information of the target channel to be counted relative to the current channel to be counted; Determining the rotation angle information of the inventory counting robot according to the current posture information of the inventory counting robot and the orientation information to be oriented; According to the rotation angle information, the inventory counting robot is controlled to rotate to the orientation to be faced, so that the inventory counting robot moves to the starting point of the target channel to be counted according to the orientation to be faced.

8. A shelf cargo inventory device, characterized in that: A graph structure model is pre-modeled for the target site where the shelf goods are located. The graph structure includes multiple pass nodes, each pass node has corresponding orientation information, and the connection between the pass nodes represents the path between the two pass nodes, including: an acquisition module, configured to determine channel information corresponding to the target site based on the graph structure in response to receiving an inventory task for a channel to be inventoried in the target site; the inventory task includes an inventory direction of the channel to be inventoried; the channel information corresponding to the target site includes position information of passage nodes of each channel of the target site, orientation information of an inventory robot to be oriented at each passage node, and reachable paths between passage nodes; A first determination module is used to determine the location information of the starting point and the end point of the channel to be counted according to the location information of the pass nodes of each channel of the target site and the reachable paths between the pass nodes; A second determination module is used to determine the node to be passed in the to-be-passed channel in the inventory direction according to the position information of the starting point, the position information of the end point, and the orientation information of each pass node to be oriented by the inventory counting robot on the reachable path; The first control module is used to determine, starting from the starting point of the channel to be counted, the next node to be passed that is closest to the inventory robot in the inventory direction according to the current posture information of the inventory robot and the position information of each node to be passed, and control the inventory robot to move to the next node to be passed to perform inventory of shelf goods until it reaches the last node to be passed.

9. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the shelf goods inventory method according to any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the shelf goods inventory counting method as claimed in any one of claims 1 to 7.

Images