Path planning method and device, storage medium and electronic equipment

Abstract

The invention relates to a path planning method and device, a storage medium and electronic equipment, in particular to the technical field of intelligent warehousing, and the method comprises the steps: firstly obtaining a queuing area corresponding to a workstation; robot queuing information is monitored based on the queuing area; and dynamically adjusting the path of the robot to the workstation according to the robot queuing information. By applying the technical scheme, the robot queuing condition is monitored according to the queuing area corresponding to the workstation, and the path of the robot to the workstation is dynamically adjusted, so that reasonable path planning for the robot waiting in line is realized, the robot can quickly and accurately reach the workstation, and the working efficiency is improved. And meanwhile, the situation that the queued teams of the robots occupy the passing paths of other robots is avoided, so that passing delay of other robots is avoided, and the working efficiency of the robots and the overall working efficiency are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent warehousing technology, and in particular to a path planning method, device, storage medium and electronic device. Background Art

[0002] In modern smart warehouses, robots are widely used in material handling and shelf transportation. Efficient scheduling and path planning of robots are crucial to smart warehousing and logistics systems. Smart warehousing and logistics systems can accurately calculate the movement routes of robots to ensure that goods can be delivered to designated workstations (or picking workbenches, workstations, etc.) quickly and accurately.

[0003] At present, after arriving at a workstation, the robot generally enters a waiting queue until the operator at the workstation completes the picking task. Due to factors such as peak hours or work efficiency, there may be multiple robots waiting at the same time. However, these waiting robots cannot perform reasonable path planning and are likely to form a long robot queue, thereby occupying the passage path of other robots, causing delays for other robots. Summary of the invention

[0004] In view of this, the present disclosure provides a path planning method, device, storage medium and electronic device, the main purpose of which is to improve the problem in the current related technology that it is impossible to reasonably plan the path of robots waiting in line, and the robots in line may occupy the passage path of other robots, thereby causing delays in the passage of other robots.

[0005] In a first aspect, the present disclosure provides a path planning method, comprising:

[0006] Get the queue area corresponding to the workstation;

[0007] Based on the queuing area, monitoring robot queuing information;

[0008] The path of the robot to the workstation is dynamically adjusted according to the robot queuing information.

[0009] Optionally, there are multiple queuing paths in the queuing area that can reach the workstation;

[0010] The dynamically adjusting the path of the robot to the workstation according to the robot queuing information includes:

[0011] According to the plurality of queuing paths and the robot queuing information, the path of the robot to the workstation is dynamically adjusted.

[0012] Optionally, dynamically adjusting the path of the robot to the workstation according to the plurality of queuing paths and the robot queuing information includes:

[0013] Obtaining the number of robots queued on each queue path from the robot queue information;

[0014] According to the number of robots queued on each queuing path, the robot's queuing path is dynamically adjusted according to the balanced allocation rule.

[0015] Optionally, dynamically adjusting the path of the robot to the workstation according to the robot queuing information includes:

[0016] According to the robot queuing information, a target robot that is outside the queuing area and whose destination is the workstation is obtained;

[0017] The path of the target robot is replanned.

[0018] Optionally, replanning the path of the target robot includes:

[0019] When the following conditions are met, the path of the target robot is replanned;

[0020] The distance between the target robot and the workstation is less than a preset distance threshold;

[0021] The number of entrances to the queuing area is greater than or equal to a preset number threshold;

[0022] The current queuing position of the target robot is occupied at the entrance corresponding to the queuing area.

[0023] Optionally, replanning the path of the target robot includes:

[0024] If there is an unoccupied idle entrance in the queuing area, a path for the target robot to go to the workstation is planned according to the idle entrance.

[0025] Optionally, if there is an unoccupied idle entrance in the queuing area, planning a path for the target robot to go to the workstation according to the idle entrance includes:

[0026] If there are multiple idle entrances, selecting a target idle entrance from the multiple idle entrances according to the distance cost information of the target robot going to the idle entrance;

[0027] According to the target idle entrance, a path for the target robot to go to the workstation is planned.

[0028] Optionally, before obtaining the queuing area corresponding to the workstation, the method further includes:

[0029] Identifying key points on each path leading to the workstation;

[0030] The queuing area is generated according to the key points.

[0031] Optionally, the identifying key points on each path leading to the workstation includes:

[0032] The key point is determined according to the in-degree and out-degree of cells around the workstation.

[0033] Optionally, determining the key point according to the in-degree and out-degree of cells around the workstation includes:

[0034] Traversing and searching for a target cell based on the in-degree and out-degree of the cell, wherein the target cell is a cell on a path leading to the workstation, and all paths corresponding to the out-degree of the target cell pass through the workstation;

[0035] The target cell is determined as the cell where the key point is located.

[0036] Optionally, generating the queuing area according to the key points includes:

[0037] The cells where the key points are located constitute the queuing area.

[0038] Optionally, robots entering the queuing area have equal right of way.

[0039] In a second aspect, the present disclosure provides a path planning device, comprising:

[0040] An acquisition module is configured to acquire a queuing area corresponding to a workstation;

[0041] A monitoring module is configured to monitor robot queuing information based on the queuing area;

[0042] The adjustment module is configured to dynamically adjust the path of the robot to the workstation according to the robot queuing information.

[0043] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the path planning method described in the first aspect.

[0044] In a fourth aspect, the present disclosure provides an electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the path planning method described in the first aspect when executing the computer program.

[0045] In a fifth aspect, the present disclosure provides a computer program product, including a computer program, which implements the path planning method described in the first aspect when executed by a processor.

[0046] By means of the above technical solution, the present disclosure provides a path planning method, device, storage medium and electronic device. Compared with the current related technologies, the present disclosure first obtains the queue area corresponding to the workstation; then monitors the robot queue information based on the queue area; and then dynamically adjusts the path of the robot to the workstation according to the robot queue information. By applying the technical solution of the present disclosure, the robot queue situation is monitored according to the queue area corresponding to the workstation, and the path of the robot to the workstation is dynamically adjusted, so as to realize reasonable path planning for the robots waiting in line, ensure that the robots can reach the workstation quickly and accurately, and avoid the situation where the robot queue occupies the passage path of other robots, thereby avoiding delays in the passage of other robots, and improving the work efficiency of the robot and the overall operation efficiency.

[0047] The above description is only an overview of the technical solution of the present disclosure. In order to more clearly understand the technical means of the present disclosure, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present disclosure more obvious and easy to understand, the specific implementation methods of the present disclosure are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0050] Figure 1 A schematic diagram of a process flow of a path planning method provided by an embodiment of the present disclosure is shown;

[0051] Figure 2 A schematic diagram of a process flow of a path planning method provided by an embodiment of the present disclosure is shown;

[0052] Figure 3A schematic diagram showing an example provided by an embodiment of the present disclosure;

[0053] Figure 4 A schematic diagram of a process flow of a path planning method provided by an embodiment of the present disclosure is shown;

[0054] Figure 5 A schematic diagram showing an example provided by an embodiment of the present disclosure;

[0055] Figure 6 A schematic diagram of the structure of a path planning device provided by an embodiment of the present disclosure is shown;

[0056] Figure 7 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0057] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0058] Many specific details are described in the following description to facilitate a full understanding of the present disclosure. However, the present disclosure can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present disclosure, so the present disclosure is not limited by the specific implementation disclosed below.

[0059] The terms used in one or more embodiments of the present disclosure are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present disclosure. The singular forms of "a", "said" and "the" used in one or more embodiments of the present disclosure and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present disclosure refers to and includes any or all possible combinations of one or more associated listed items.

[0060] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of the present disclosure, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present disclosure, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0061] In order to improve the problem that the robots waiting in line cannot be reasonably planned in the current related technology, and the robots in line may occupy the passage paths of other robots, thereby causing delays in the passage of other robots, the present disclosure provides a path planning method, such as Figure 1 As shown, the method includes the following steps 101 to 103:

[0062] Step 101: Get the queue area corresponding to the workstation.

[0063] For example, in order to ensure that the robots can queue up effectively and orderly around the workstation, a specific queuing area can be identified on the directed map. The queuing area can refer to a temporary storage area for one or more robots when they are waiting to enter the workstation or perform the next operation. These areas are usually located around the workstation and can accommodate several waiting robots while ensuring that they do not hinder the passage of other robots or personnel.

[0064] In some examples, the queue area corresponding to the workstation can be planned in advance and marked accordingly on the map. For example, by monitoring with a camera, the queue situation of robots waiting for picking near the workstation in each time period is counted, and the queue area corresponding to the queue situation is determined on the map, so that each time period corresponds to a queue area, and then the queue areas corresponding to these time periods are summarized and superimposed to obtain the area range that can contain all these queue areas as the queue area corresponding to the workstation, and mark it accordingly on the map, and then the queue area corresponding to the workstation can be obtained through the map marking.

[0065] In some examples, queuing areas can help warehouse management systems process tasks in an orderly manner and avoid the chaos caused by multiple robots arriving at the same workstation at the same time. By prearranging the order and time of the robots' arrival, unnecessary waiting can be reduced, allowing the workstation to process tasks more efficiently. The queuing mechanism can also help balance the load between different workstations, avoiding situations where some workstations are overloaded while others are idle. By properly planning the queuing area, limited space can be better utilized to ensure that congestion is not caused by the disorderly gathering of robots. Ensuring the effectiveness and orderliness of the queuing area can not only improve overall work efficiency, but also reduce the risk of collisions and blockages.

[0066] Step 102: Based on the queuing area, monitor the robot queuing information.

[0067] For example, in order to achieve more intelligent and efficient queue management, the system can monitor the position and status of the robots in real time, as well as the congestion inside and outside the queue area. By integrating advanced positioning technology and sensors, the system can accurately track the position of each robot in the queue area and obtain its current working status (such as idle, busy, faulty, etc.).

[0068] For example, cameras, infrared sensors or other environmental sensing devices can be used to monitor the density of robots in the queuing area, the speed of movement, and whether there are potential congestion points. In addition, the system should also have the ability to analyze the traffic flow outside the queuing area to predict and respond to external factors that may affect the robot queue. By applying the method of this embodiment, it is possible to accurately track the position and status of the robot, as well as effectively manage the congestion inside and outside the queuing area. This not only improves the operating efficiency of the system, but also enhances safety and reduces potential operational problems.

[0069] Step 103: Dynamically adjust the path of the robot to the workstation according to the robot queuing information.

[0070] In some examples, the system can quickly respond and adjust the robot's path based on real-time data such as robot queue information. When congestion is detected in the queue area or surrounding areas, the system can re-plan the route to guide the robot to bypass the congestion point or choose a more unobstructed path to the workstation. This real-time adjustment mechanism helps reduce waiting time, improve overall efficiency, and ensure orderly flow between robots. By continuously collecting and analyzing real-time data, the system can continuously optimize the robot's movement strategy to adapt to the ever-changing working environment and needs.

[0071] Exemplarily, the system can be scheduled according to the robot's destination and workstation to ensure that the robot can reach the destination smoothly. For example, a graph-based search algorithm or a heuristic search algorithm can be used to dynamically calculate and adjust the robot's optimal path based on the real-time collected queue information and robot status, consider the position of obstacles and other robots in path planning, avoid collisions through prediction and coordination, and achieve collaborative work between robots. It can also comprehensively consider multiple goals such as path length, waiting time, and robot energy consumption, and seek the optimal solution through a multi-objective optimization algorithm, or use historical data and machine learning algorithms to predict the queue trend of workstations in the future, and perform path planning and task allocation in advance. And according to the actual situation and performance indicators of the system operation, the path planning algorithm and scheduling strategy are automatically adjusted to adapt to different working environments and task requirements. The robot's action path and task allocation are adjusted in time through the feedback mechanism to deal with emergencies or unexpected situations.

[0072] For example, for a robot that is about to go to the workstation, its current position and the positions of other possible target workstations are analyzed. If the queue area of ​​a workstation is found to be full, the path replanning mechanism can be triggered. The path from the current position to the nearest available entrance is calculated for each robot, and path instructions are sent to the relevant robots. In this process, the robot's movement can be continuously monitored, and data can be collected and analyzed to further optimize system performance.

[0073] Compared with the current related technologies, the embodiment of the present disclosure can first obtain the queue area corresponding to the workstation; then monitor the robot queue information based on the queue area; and then dynamically adjust the robot's path to the workstation according to the robot queue information. By applying the technical solution of the embodiment of the present disclosure, the robot queue situation is monitored according to the queue area corresponding to the workstation, and the robot's path to the workstation is dynamically adjusted, which realizes reasonable path planning for the robots waiting in line, ensuring that the robots can reach the workstation quickly and accurately, and at the same time avoids the situation where the robot queue occupies the passage path of other robots, thereby avoiding delays in the passage of other robots, and improving the robot's work efficiency and overall operation efficiency.

[0074] Further, as Figure 1 An optional method of the embodiment, such as Figure 2 As shown, the method may include the following steps 201 to 203:

[0075] Step 201: Obtain the queuing area corresponding to the workstation.

[0076] In some examples, the queuing area can be a predefined area on a map that contains a series of points that not only define the boundaries of the queuing area, but also identify the positions that the robots should occupy when waiting to enter the workstation. In this way, the system can more effectively manage the queue order of the robots and ensure that they queue up according to the established rules, thereby improving overall work efficiency and safety.

[0077] For example, one or more queuing areas can be clearly defined on the map. These areas should be large enough to accommodate a certain number of robots without interfering with each other or obstructing the passage of other robots or people. The queuing area contains a series of points, which are the specific positions that robots should occupy when waiting. The point layout should take into account the size of the robot, the turning radius, and the safe distance between each other to ensure that the robot can park comfortably and respond quickly to dispatch instructions.

[0078] Optionally, the method of this embodiment may specifically include: identifying key points on each path leading to the workstation; and generating a queuing area according to the key points.

[0079] In some examples, according to the characteristics of the picking workstation path setting, adding a queue area recognition algorithm can effectively identify the key points on each path leading to the workstation, and then identify the queue area corresponding to the workstation, and then adjust the robot's queue position according to the recognition result. The queue area recognition algorithm is an innovative technology for robot traffic management in an automated environment. It can achieve efficient scheduling and control of robot behavior by intelligently mapping and defining the waiting area of ​​the robot around the workstation. Through the queue area recognition algorithm, efficient scheduling and control of robot behavior can be achieved, improving the operating efficiency and response speed of the entire system.

[0080] For example, the queue area recognition algorithm can identify key points through iterative search when the system is initialized, and combine the cells where these key points are located to form a clear queue area. The size and shape of the queue area can also be flexibly determined according to the path. At the same time, the algorithm uses an iterative search strategy to intelligently determine the boundaries of the queue area and clearly identify the entry and exit points. This method reduces the reliance on manual intervention and improves the accuracy and efficiency of queue area division.

[0081] In some examples, queue area identification can be formed when the map is initialized, which can quickly identify all possible queue areas when the system starts and provide initial navigation data for the robot. After the system has identified and verified the map areas as valid queue areas, these areas will be clearly recorded in the system's database.

[0082] Exemplarily, the generation of the queuing area on the map can take into account multiple factors, including area demarcation, point layout, exclusion of inappropriate points, and support for efficient scheduling. For example, if some points are identified as workstation-associated / peripheral points that are not the robot's entry path, it can be determined that these points are not suitable as queuing areas. In order to reserve support for the robot to leave the workstation quickly, these points can be excluded to avoid obstructing the normal flow of the robot, causing congestion, collisions or delays, thereby supporting the efficient scheduling of the robot. Through scientific planning and reasonable design, it can be ensured that the robots queue up in an orderly manner around the workstation and complete various tasks efficiently.

[0083] Optionally, the above-mentioned identifying key points on each path leading to the workstation may specifically include: determining the key points according to the in-degree and out-degree of cells around the workstation.

[0084] For example, Figure 3As shown in the figure, in the intelligent logistics scenario, the map can usually be modeled as a directed graph to more accurately guide the robot to move in a specific direction. In a directed graph, the edge has a direction and can represent a unidirectional relationship from one vertex to another. This representation method helps to simulate the one-way channel in the actual warehouse or limit the direction of the robot to ensure that the robot does not try to take an unreachable or prohibited path. Among them, in the intelligent logistics scenario, the vertex can represent a shelf, workstation, charging station or other key location, and the edge represents the connection relationship between the vertices, which is directional and represents the path that the robot can travel in this direction. The edge can also carry a weight, which represents the distance, time or other cost indicators from one vertex to another. The out-degree of a vertex refers to the number of edges emitted from the vertex, which represents the number of directions in which the robot can leave the vertex; the in-degree of a vertex refers to the number of edges entering the vertex, which represents the number of directions in which the robot can reach the vertex.

[0085] For example, Figure 3 In the figure, A, B, C, I, and P are the vertices of 5 cells respectively, and AD, BE, BF, CG, CH, IJ, and PQ are edges, among which BF can represent a unidirectional relationship from vertex B to vertex A, and CG can represent a unidirectional relationship from vertex C to vertex B. In the figure, the number of directions in which the robot can leave vertex A is 1 (AD), and the number of directions in which it can reach vertex A is 1 (BF), that is, the out-degree and in-degree of vertex A are both 1; the number of directions in which the robot can leave vertex B is 2 (BE, BF), and the number of directions in which it can reach vertex B is 2 (CG, IJ), that is, the out-degree and in-degree of vertex B are both 2; the number of directions in which the robot can leave vertex C is 2 (CH, CG), and the number of directions in which it can reach vertex C is 1 (PQ), that is, the out-degree of vertex C is 2 and the in-degree is 1.

[0086] In some examples, the directed map and the layout of the workstations can be analyzed by algorithms, and the key points can be determined by combining the in-degree and out-degree of the cells around the workstations. Figure 3 The key points in the middle queue area are the key points corresponding to the workstations in the box. These key points are usually the necessary paths for robots to enter or leave the workstations. In order to support efficient robot scheduling, it is necessary to ensure that there is enough space around the workstation for the robot to leave quickly. This includes setting up clear exit paths and buffer zones so that the robot can evacuate quickly after completing the task to avoid conflicts with robots in the queue.

[0087] Optionally, the above-mentioned determining the key point based on the in-degree and out-degree of the cells around the workstation may specifically include: traversing and searching for the target cell based on the in-degree and out-degree of the cell, wherein the target cell is a cell on the path leading to the workstation, and all paths corresponding to the out-degree of the target cell pass through the workstation; determining the target cell as the cell where the key point is located.

[0088] For example, in path planning, considering the out-degree and in-degree of vertices is crucial to determining the robot's route. For example, if the out-degree of a vertex is zero, it means that the robot cannot leave from this point, which may be a dead end or the end point. On the contrary, if the in-degree is zero, the point may be the starting point or cannot be reached from other points.

[0089] In some examples, the entry point of the queue area is the starting point for the robot to enter the queue area. The identification of the queue area boundary can be completed by iteratively searching for points on the path around the workstation. When it is found that all the paths corresponding to the out-degree of a point belong to the known queue area, this point can be considered as the entry point of the queue area. These entry points are determined by analyzing the points that must be passed in all paths passing through the workstation. The entry points can be clearly marked and easily identified on the map so that the robot can accurately navigate to the queue area.

[0090] Exemplarily, the queue area identification algorithm can be used to iteratively search from the location of a workstation until all workstations are calculated. The algorithm traverses the in-degree cells around the workstation (i.e., the cells whose corresponding paths can reach the workstation). If all the paths corresponding to an in-degree cell (i.e., the cells that can be reached by the corresponding path starting from the cell) must pass through the workstation, then this cell is added to the queue area. This process continues until no more qualified in-degree cells can be found. Then, the qualified cells can form a queue area, and the last added edge cell can be used as the boundary of the queue area. The algorithm can also identify the entry points of the queue area, that is, those cells with in-degrees from non-queue areas. These cells can become the portals for the robot to enter the queue area.

[0091] Optionally, the generating of the queuing area according to the key points includes: forming the queuing area from cells where the key points are located.

[0092] In some examples, by combining the cells where these key points are located, a clear queuing area is formed, such as Figure 3The 12 cells in the box constitute the queue area of ​​the corresponding workstation, and according to the out-degree and in-degree of the cells, it can be determined that there are 3 cells in the queue area that can be used as entry points. These areas are temporary stops for robots while waiting to enter the workstation, and they need enough space to avoid congestion and conflict. The robot needs to move in the area according to the path or sequence guided by these points to achieve orderly queuing and efficient entry into the workstation.

[0093] In some examples, the layout of the queuing area and the point allocation can also have a certain degree of flexibility to adapt to changes in workstation demand. For example, when the workstation load increases, the queuing area can be temporarily expanded or the number of points can be increased; when the load decreases, the area can be reduced accordingly or the point layout can be adjusted to improve space utilization.

[0094] In the disclosed embodiment, the queue area recognition algorithm based on the iterative search strategy can accurately define the queue area and the entry point, ensuring that the robot can clearly identify the entrance location and smoothly enter the queue area. It can also maximize the use of limited space resources and avoid waste of resources. The algorithm optimizes the robot's movement path, reduces invalid movements and conflicts, and thus improves the operating efficiency of the entire system.

[0095] Step 202: Monitor robot queue information based on the queue area.

[0096] In some examples, the position and status of the robot, as well as the congestion inside and outside the queuing area, can be monitored in real time, including the position and status of the robot in the queuing area and the position and status of the robot within a preset range outside the queuing area, so that the subsequent dynamic path planning system can adjust the path of the robot in real time to avoid congestion in the queuing area.

[0097] For example, based on the data collected by real-time monitoring, the system can dynamically evaluate the current working conditions and requirements, and update and optimize the robot's movement strategy accordingly. Real-time monitoring and dynamic update mechanisms ensure that the system can still operate efficiently in the face of changing working conditions, enhancing the adaptability and reliability of the system.

[0098] Step 203: dynamically adjust the path of the robot to the workstation according to the multiple queue paths that can reach the workstation in the queue area and the robot queue information.

[0099] For example, the robot that is about to enter the queue area is dynamically planned based on the monitoring data of the queue information to respond to changes in the queue area in real time, which can ensure that the robot can operate stably and complete tasks efficiently in a dynamic environment. Specifically, the system can dynamically adjust the robot's path based on the current queue area and the robot's queue situation. This intelligent scheduling method improves the robot's work efficiency and reduces waiting time and potential congestion.

[0100] In some examples, the congestion level, estimated travel time, etc. of each path can be evaluated based on multiple paths that can reach the workstation in the queue area. The path planning algorithm is combined with real-time traffic data (such as robot density, moving speed, etc.) to perform path evaluation. The robot's path planning is dynamically adjusted according to the real-time monitored queue information and workstation status. When a path is seriously congested, the robot is guided to choose other more unobstructed paths to the workstation. If the queue area is full and there are three robots queuing on the highway, these three robots can be preferentially assigned to the point closest to the workstation (when a robot leaves the queue area). In a multi-robot system, robots can work together and use sensors (such as lidar, ultrasonic sensors, etc.) to monitor the surrounding environment in real time to avoid path conflicts and collisions between robots and obstacles or other robots. When a potential collision risk is detected, the robot's movement direction and speed can be adjusted in time to avoid collisions.

[0101] In some examples, when planning the path for the robot to reach the workstation, not only the congestion of multiple accessible paths in the queuing area, the estimated travel time, the robot status, etc. can be considered, but also the preset priority of the robot can be considered comprehensively. Among them, the preset priority is used to identify the order of the workstation tasks corresponding to the robot. When the system is initialized or the task is assigned, a preset priority is set for each robot. This priority can be determined based on a variety of factors, such as the urgency of the task, the performance of the robot, the load of the workstation, etc. According to the preset priority, the path and order for the robot to reach the workstation are planned. On the basis of the sorting, the optimal path is planned for each robot, which may require considering the mutual influence between the robots, such as avoiding path conflicts and collisions, and optimizing the overall travel time. Then send instruction information to the robot to instruct the robot to act according to the planned path. The instruction information may also include the location of the workstation, the specific travel path, the speed requirement, the collision avoidance strategy, etc.

[0102] Exemplarily, after receiving the instruction information, the robot starts to move according to the path planning information therein. During the movement, the robot needs to perceive the surrounding environment in real time to ensure that it moves along the planned path. If the robot encounters an emergency during the movement (such as an obstacle, conflict with other robots, etc.), it can make dynamic adjustments based on the collision avoidance mechanism to ensure that it arrives safely at the workstation. After the robot arrives at the workstation, it starts to perform the task according to the preset task sequence and requirements. During the execution process, the system can continuously monitor the robot's working status and task progress to ensure that the system can adapt to the ever-changing working environment and needs.

[0103] For example, for robots whose destination is clearly a certain workstation, the system can give priority to importing them into the queue sequence corresponding to the workstation to reduce the waiting time in front of the workstation and improve processing efficiency. Specifically, when assigning tasks, the system can identify and record the destination workstation of each robot, maintain an independent queue sequence for each workstation, and when the robot is ready to enter the queue area, the system checks its destination workstation and imports it into the queue sequence of the corresponding workstation with priority.

[0104] For example, when certain conditions are met (such as the workstation is idle, there is enough space in the queuing area, a specific time interval is reached, etc.), the system will trigger the queuing function, allowing the robot to enter the workstation in a predetermined order. When the conditions are met, the system starts the queuing mechanism, assigns the order of entering the workstation to the robots according to preset rules (such as priority, first-come-first-served, etc.), and allows the robots to enter the workstation to perform tasks in the assigned order. This will achieve an efficient robot queuing and task allocation mechanism, and improve production efficiency and resource utilization.

[0105] Optionally, step 203 may specifically include: obtaining the number of robots queued on each queuing path from the robot queuing information; and dynamically adjusting the robot queuing path according to the balanced allocation rule based on the number of robots queued on each queuing path.

[0106] For example, the number of robots in queue on each path can be collected through the data processing system, and timed tasks or trigger events can be set to update this data regularly or in real time. Balanced distribution rules can be formulated based on a variety of factors, such as path length, expected travel time, workstation load, etc., in order to reduce the difference in the number of robots between paths and improve the overall queuing efficiency. When the number of robots on a path exceeds the preset threshold or differs greatly from the number of robots on other paths, the dynamic adjustment mechanism is triggered to analyze the congestion of each path, the expected travel time and other factors, and select the optimal path for the robot that is about to join the queue. Heuristic algorithms, machine learning models and other methods can also be used to optimize the path selection process. Send new path instructions to the robot that is about to join the queue to guide it to the adjusted path. Ensure that the robot can accurately receive and understand the instructions and follow the new path.

[0107] For example, the performance of the system can be evaluated regularly, including the effect of balanced allocation, robot queue time, workstation load, etc., and the balanced allocation rules and dynamic adjustment strategies can be adjusted according to the evaluation results. By intelligently scheduling robots on the queue path through balanced allocation rules, effective collaboration between robots can be ensured. Such a collaborative mode can not only improve the work efficiency of a single robot, but also optimize the performance of the entire robot team.

[0108] Optionally, the method of this embodiment may further specifically include: robots entering the queuing area have equal right of way.

[0109] In some examples, the system automatically identifies and prioritizes robots that need to reach workstations to enter the queuing area. At the same time, when robots in the queuing area queue up to enter the workstation, it is necessary to ensure that all robots have fair right of way to reach the workstation. For example, if conflicting points are identified in multiple paths that can reach the workstation, the order in which robots queuing on different paths pass through the conflicting points can be set.

[0110] For example, the robot can be identified and its needs evaluated first. The system can perceive the needs of each robot in real time, including whether they need to enter the workstation, the urgency of the task, the required resources, etc., and can set priorities for the robots according to preset rules (such as the priority of the task, the waiting time of the robot, the load of the workstation, etc.). After the system automatically identifies the status of the queue area, it dynamically allocates positions according to the priority of the robot and the capacity of the queue area, and plans a collision-free and as short a path as possible for each robot in the queue area to reach the workstation. During the path planning process, if a potential path conflict is detected (such as two robots may occupy the same position at the same time), the system can immediately replan the path to avoid collision. The concept of time slices can also be introduced to allocate a certain time window for each robot in the queue area to perform its mobile operation. In this way, even in a high-density environment, it can ensure that each robot has an equal opportunity to move forward.

[0111] In some examples, the position and status of robots in the queuing area can be tracked in real time through sensors and monitoring systems, and then the scheduling strategy can be dynamically adjusted based on real-time data, such as re-evaluating priorities, reallocating the location of the queuing area, etc. The scheduling strategy can also be continuously improved through machine learning or optimization algorithms to improve overall efficiency and fairness, thereby improving overall work efficiency and improving system reliability.

[0112] Compared with the current related technologies, by applying the technical solution of the embodiment of the present disclosure, the robot queue situation is monitored according to the queue area corresponding to the workstation, and the path of the robot to the workstation is dynamically adjusted, so as to realize reasonable path planning for the robots waiting in line, ensure that the robots can reach the workstation quickly and accurately, and avoid the situation where the robot queue occupies the passage path of other robots, thereby avoiding delays in the passage of other robots, and improving the work efficiency of the robot and the overall operation efficiency. Through automated queue area identification and real-time intelligent scheduling, the need for manual operation is reduced, labor costs are reduced, the management efficiency of robot traffic in the automated environment is significantly improved, and the safety of operation is improved. The application of the embodiment of the present disclosure can not only optimize the workflow of the robot, but also bring higher production efficiency and lower operating costs to the enterprise.

[0113] Furthermore, in the actual process of robot path planning, if the number of robots queued at the current workstation exceeds the queue area, and when the robots outside the queue area meet the conditions for re-planning the path, the system will trigger the fast path switching logic and re-dynamically plan the path for the robot to reach the workstation based on the robot queue information to maintain the efficient operation of the system and the smooth scheduling of the robot. Figure 4 As shown, the method may include the following steps 301 to 302:

[0114] Step 301: According to the robot queuing information, a target robot that is outside the queuing area and whose destination is a workstation is obtained.

[0115] For example, robots whose destinations (or end points) are workstations may be identified first, and then robots that are not in the queue area may be selected from these robots, which are the target robots. Since the position and state of the robots are dynamically changing, these selection conditions need to be updated regularly or in real time to ensure that the latest target robot information is always available.

[0116] Step 302: replan the path of the target robot.

[0117] For example, based on the data content of the known queuing area, the system can optimize the intelligent scheduling of the automated guided vehicle (AGV) and add fast path switching logic to maintain the efficient operation of the system and the smooth scheduling of the robots. The current position and final destination of all target robots that have not entered the queuing area can be evaluated, the time when the target robots arrive at the queuing area can be predicted, and the real-time traffic conditions and other possible influencing factors in the entire factory / warehouse can be considered to calculate new optimal paths for these robots, avoid known congestion points, and shorten the total waiting time as much as possible.

[0118] For example, when the number of robots on a certain path reaches the upper limit (i.e. the path is full), the system can give priority to robots that have been waiting for a long time (i.e. "burst") to enter the queue area to reduce their waiting time. Specifically, the system can monitor the number of robots on each path in real time, record the waiting time for each robot waiting to enter the queue area, and when the path is full, the system adjusts the priority algorithm, places robots with longer waiting times at a higher priority, and replans the paths of robots with higher priorities.

[0119] Optionally, step 302 may specifically include: replanning the path of the target robot when the following conditions are met: the distance between the target robot and the workstation is less than a preset distance threshold; the number of entrances to the queuing area is greater than or equal to a preset number threshold; the target robot's current queuing position is occupied at the entrance corresponding to the queuing area.

[0120] Exemplarily, the system can detect whether the following conditions are met simultaneously through a real-time monitoring system or a sensor network: the distance between the target robot and the workstation: calculate the distance between the current position of the target robot and its target workstation, and determine whether the distance is less than a preset distance threshold. This threshold can be set according to the layout of the workstation, the driving speed of the target robot, and the system's response time requirements; check whether the number of available entrances in the current queuing area is greater than or equal to a preset number threshold. This number threshold is used to ensure that after replanning the path, the target robot has enough entrance options to avoid further congestion or waiting; confirm whether the entrance corresponding to the current queue of the target robot has been occupied by other robots.

[0121] For example, the conditions for triggering fast path change can be set as follows: the robot is a target robot that has not entered the queue area; the distance between the target robot and the workstation is less than 10 meters; the number of entrances to the queue area is greater than or equal to 2; the current queue entrance is occupied by other robots, and the waiting point information of the blocking robot is not updated in time, etc. Once all the trigger conditions are met, the affected robots are immediately replanned to find a new feasible path. Send new path instructions to the robots, and ensure that they can respond quickly and adjust the driving direction. This can effectively solve the problem of congestion at the queue entrance and improve the efficiency and smoothness of the robot's operation.

[0122] Optionally, step 302 may further specifically include: if there is an unoccupied idle entrance in the queuing area, planning a path for the target robot to go to the workstation according to the idle entrance.

[0123] Exemplarily, the occupancy status of each entrance in the queuing area can be detected in real time through a sensor network, video surveillance, or an interface with other systems to determine which entrances are idle. After determining the idle entrance, the system needs to evaluate and select the optimal idle entrance for the target robot to use, including the distance between the current robot and the idle entrance, the traffic congestion around the idle entrance, the priority of the entrance, etc. For example, the idle entrance closest to the current position of the target robot can be selected to reduce driving time and energy consumption. The traffic congestion around the entrance can also be considered to select the entrance with the shortest estimated travel time. If there is a priority setting in the system, the entrance can be selected in combination with the priority of the target robot. When selecting an idle entrance, the overall state of the system, such as the position of other robots, task allocation, etc., can also be considered to avoid new congestion points or imbalances.

[0124] In some examples, planning the path of the target robot to the workstation can include evaluating all possible paths based on the current system status and real-time data, including alternative paths that bypass occupied entrances. An optimal path is selected based on factors such as path length, estimated travel time, traffic congestion, priority, etc. The re-planned path instructions are sent to the target robot, and it is notified to follow the new path. While the target robot is traveling along the new path, the system can monitor its status and position in real time to ensure the effectiveness of the path re-planning. If new obstacles or congestion are encountered on the new path, the system needs to be able to dynamically adjust the path planning to ensure that the target robot can successfully reach its destination.

[0125] In some examples, if there are no unoccupied free entrances in the queuing area, all entrances are occupied, and the target robot cannot directly enter the workstation through the queuing area. Then the entrance status of the queuing area can be continuously monitored. Once an entrance becomes free, the path for the robot that needs to be transferred can be replanned immediately, the shortest or optimal path to the free entrance can be selected, and instructions can be sent to the target robot. Furthermore, the number and length of the robot teams at each entrance can be detected, and the entrance with the shorter expected queuing time can be selected as the target entrance according to the balanced allocation rule, and the path for the robots that need to be transferred can be replanned to ensure that they can efficiently reach the queue at the target entrance. The robots at the entrance with a long queue can be reasonably allocated to other entrances with short queues, thereby improving the work efficiency of the robots.

[0126] In some examples, such as Figure 5 As shown, there are three entrances (entrance A, entrance B and entrance C) in the queuing area, and the waiting conditions of entrances A, B and C are collected in real time. If there are 5 robots (such as robots No. 1 to No. 5) waiting at entrance A, and entrances B and C are relatively idle, based on the collected information, in order to reduce the robots waiting at entrance A from occupying too much of the passage paths of other robots, in path planning, the robots waiting to enter the queuing area at entrance A can be changed to enter the queuing area via entrance B or entrance C, so that the cells in the queuing area are filled first, the number of robots waiting in line at entrance A is reduced, and the situation where the robot queues occupy the passage paths of other robots is reduced.

[0127] For example, after the path planning is completed, the system sends a new movement instruction to the robot, including the new target location (entrance B or entrance C) and navigation points along the way. After receiving the new instruction, the robot will start to execute the path and go to entrance B or entrance C. During this process, the robot should continue to monitor the surrounding environment, avoid obstacles and adjust the speed as needed, and ensure the coordination between other robots at entrance A and robots at entrance B or entrance C to avoid confusion or conflict caused by the new path planning.

[0128] Furthermore, in some examples, robots entering the queuing area have equal right of way. Figure 5 As shown in Figure 2, after the robot enters the queuing area through entrances A, B, and C, there are multiple queuing paths that can reach the workstation, and some queuing paths may be partially overlapping, such as Figure 5 Both robot No. 6 and robot No. 7 need to pass through the path where cell P is located to reach the workstation. Therefore, as an implementation method, the robots can be set to pass through cell P alternately to avoid the robots on one of the queue paths from stagnating for a long time, so as to reduce the waiting time.

[0129] In order to meet more practical needs, as an implementation method, the path planning can also be adjusted according to the task priority of each robot. Figure 5 As shown, when both robot No. 6 and robot No. 7 need to pass through the next cell (cell P), if the task priority of robot No. 6 is higher than that of robot No. 7, robot No. 6 can be arranged to pass through cell P first, and robot No. 7 can wait for robot No. 6 to leave cell P before passing through cell P; or if, while robot No. 7 is waiting, another robot needs to pass through cell P (such as a new robot entering the cell corresponding to robot No. 6 in the figure), and the task priority of the new robot is also higher than that of robot No. 7, the new robot will continue to be arranged to pass through cell P first, and robot No. 7 can wait for the new robot to leave cell P before passing through cell P, thereby meeting more actual needs.

[0130] Optionally, if there is an unoccupied idle entrance in the queuing area, the path for the target robot to reach the workstation is planned based on the idle entrance. Specifically, it may also include: if there are multiple idle entrances, selecting a target idle entrance from the multiple idle entrances based on the distance cost information for the target robot to reach the idle entrance; and planning the path for the target robot to reach the workstation based on the target idle entrance.

[0131] For example, dynamic costs can be added during replanning: if there are idle entrances, the corresponding distance cost (or line segment cost) for the robot to enter from the outside can be added to each entrance. The distance cost can be evaluated based on the direct distance between the robot and the entrance or the shortest path length, the estimated time required to pass this path, the energy required to move this distance, and the influence of other robots or obstacles. After calculating the costs of all idle entrances, compare these values ​​and select the one with the smallest cost as the target entrance. If there are multiple entrances with the same cost, you can choose any one or decide based on additional criteria (such as priority rules). Then, based on the distance costs corresponding to each entrance, the path for the target robot to enter the queue area can be replanned, so that the robot can fill the queue area first, improve work efficiency and utilization of the queue area.

[0132] For example, according to the travel costs corresponding to each idle entrance, the entrance with the lowest cost can be selected as the target idle entrance, so that the robot can enter the queuing area with the lowest cost. This not only helps to optimize the path planning, but also improves the working efficiency of the overall system.

[0133] By applying the technical solutions of the embodiments of the present disclosure, the intelligent warehousing and logistics system can manage the robot queuing area more efficiently, monitor the robot queuing situation according to the queuing area corresponding to the workstation, and dynamically adjust the path of the robot to the workstation, thereby realizing reasonable path planning for the robots waiting in line, ensuring that the robots can reach the workstation quickly and accurately, and avoiding the situation where the robot queue occupies the passage path of other robots, thereby avoiding delays in the passage of other robots, improving the work efficiency of the robots and the overall operation efficiency, and even when the capacity of the queuing area is limited, the efficient operation of the system and the smooth scheduling of the robots can be maintained.

[0134] Further, as Figures 1 to 5 In the specific implementation of the example shown, the present disclosure provides a path planning device, such as Figure 6 As shown, the device includes: an acquisition module 41, a monitoring module 42, and an adjustment module 43.

[0135] An acquisition module 41 is configured to acquire a queuing area corresponding to a workstation;

[0136] A monitoring module 42 is configured to monitor robot queuing information based on the queuing area;

[0137] The adjustment module 43 is configured to dynamically adjust the path of the robot to the workstation according to the robot queuing information.

[0138] In some embodiments, there are multiple queue paths in the queue area that can reach the workstation; accordingly, the adjustment module 43 is also configured to dynamically adjust the path of the robot to the workstation according to the multiple queue paths and the robot queue information.

[0139] In some embodiments, the adjustment module 43 is further configured to obtain the number of robots queued on each queuing path from the robot queuing information; and dynamically adjust the robot queuing path according to the balanced allocation rule based on the number of robots queued on each queuing path.

[0140] In some embodiments, the adjustment module 43 is further configured to obtain a target robot that is outside the queuing area and whose destination is the workstation based on the robot queuing information; and re-plan the path of the target robot.

[0141] In some embodiments, the adjustment module 43 is further configured to re-plan the path of the target robot when the following conditions are met: the distance between the target robot and the workstation is less than a preset distance threshold; the number of entrances to the queuing area is greater than or equal to a preset number threshold; the current queuing position of the target robot is occupied at the entrance corresponding to the queuing area.

[0142] In some embodiments, the adjustment module 43 is further configured to plan a path for the target robot to go to the workstation according to an unoccupied idle entrance in the queuing area.

[0143] In some embodiments, the adjustment module 43 is further configured to, if there are multiple idle entrances, select a target idle entrance from the multiple idle entrances based on the distance cost information of the target robot traveling to the idle entrance; and plan the path of the target robot to the workstation based on the target idle entrance.

[0144] In some embodiments, the acquisition module 41 is further configured to identify key points on each path leading to the workstation; and generate the queuing area according to the key points.

[0145] In some embodiments, the acquisition module 41 is further configured to determine the key point according to the in-degree and out-degree of cells around the workstation.

[0146] In some embodiments, the acquisition module 41 is further specifically configured to traverse and search for a target cell based on the in-degree and out-degree of the cell, wherein the target cell is a cell on a path leading to the workstation, and all paths corresponding to the out-degree of the target cell pass through the workstation; the target cell is determined to be the cell where the key point is located.

[0147] In some embodiments, the acquisition module 41 is further configured to form the queuing area with the cells where the key points are located.

[0148] In some embodiments, the adjustment module 43 is further configured to ensure that robots entering the queuing area have equal right of way.

[0149] It should be noted that for other corresponding descriptions of the functional units involved in the path planning device provided in the embodiment of the present disclosure, reference can be made to Figures 1 to 5 The corresponding description in will not be repeated here.

[0150] Based on the above Figures 1 to 5 The example shown in the figure, accordingly, the embodiment of the present disclosure also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figures 1 to 5 Example method shown.

[0151] Based on the above Figures 1 to 5 The example shown, accordingly, the embodiment of the present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned Figures 1 to 5 Example method shown.

[0152] Based on this understanding, the technical solution of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various implementation scenarios of the present disclosure.

[0153] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0154] Figure 7 A schematic block diagram of an example electronic device 1000 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0155] like Figure 7As shown, the device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in a ROM (Read-Only Memory) 1002 or a computer program loaded from a storage unit 1008 to a RAM (Random Access Memory) 1003. In the RAM 1003, various programs and data required for the operation of the device 1000 can also be stored. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An I / O (Input / Output) interface 1005 is also connected to the bus 1004.

[0156] A number of components in the device 1000 are connected to the I / O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a disk, an optical disk, etc.; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1009 allows the device 1000 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0157] The computing unit 1001 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a CPU (Central Processing Unit), a GPU (Graphic Processing Units), various dedicated AI (Artificial Intelligence) computing chips, various computing units running machine learning model algorithms, a DSP (Digital Signal Processor), and any appropriate processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as a control method for a robot. For example, in some embodiments, the control method for a robot may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the method described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to execute the aforementioned robot control method in any other appropriate manner (eg, by means of firmware).

[0158] Various embodiments of the systems and techniques described above herein may be implemented in digital electronic circuit systems, integrated circuit systems, FPGAs (Field Programmable Gate Arrays), ASICs (Application-Specific Integrated Circuits), ASSPs (Application Specific Standard Products), SOCs (System On Chips), CPLDs (Complex Programmable Logic Devices), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor that may be a dedicated or general-purpose programmable processor that may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0159] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0160] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include electrical connections based on one or more lines, portable computer disks, hard disks, RAM, ROM, EPROM (Electrically Programmable Read-Only-Memory) or flash memory, optical fiber, CD-ROM (Compact Disc Read-Only Memory), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0161] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (Cathode-Ray Tube) or LCD (Liquid Crystal Display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0162] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: LAN (Local Area Network), WAN (Wide Area Network), the Internet, and blockchain networks.

[0163] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services ("Virtual Private Server", or "VPS" for short). The server may also be a server of a distributed system, or a server combined with a blockchain.

[0164] It should be noted that artificial intelligence is a discipline that studies how computers can simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), and includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0165] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0166] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A path planning method, characterized in that: include: Get the queue area corresponding to the workstation; Based on the queuing area, monitoring robot queuing information; The path of the robot to the workstation is dynamically adjusted according to the robot queuing information.

2. The method according to claim 1, characterized in that: There are multiple queuing paths in the queuing area that can reach the workstation; The dynamically adjusting the path of the robot to the workstation according to the robot queuing information includes: According to the plurality of queuing paths and the robot queuing information, the path of the robot to the workstation is dynamically adjusted.

3. The method according to claim 2, characterized in that The dynamically adjusting the path of the robot to the workstation according to the plurality of queuing paths and the robot queuing information comprises: Obtaining the number of robots queued on each queue path from the robot queue information; According to the number of robots queued on each queuing path, the robot's queuing path is dynamically adjusted according to the balanced allocation rule.

4. The method according to claim 1, characterized in that The dynamically adjusting the path of the robot to the workstation according to the robot queuing information includes: According to the robot queuing information, a target robot that is outside the queuing area and whose destination is the workstation is obtained; The path of the target robot is replanned.

5. The method according to claim 4, characterized in that Replanning the path of the target robot includes: When the following conditions are met, the path of the target robot is replanned; The distance between the target robot and the workstation is less than a preset distance threshold; The number of entrances to the queuing area is greater than or equal to a preset number threshold; The current queuing position of the target robot is occupied at the entrance corresponding to the queuing area.

6. The method according to claim 4, characterized in that The replanning of the path of the target robot includes: If there is an unoccupied idle entrance in the queuing area, a path for the target robot to go to the workstation is planned according to the idle entrance.

7. The method according to claim 6, characterized in that If there is an unoccupied idle entrance in the queuing area, planning a path for the target robot to go to the workstation according to the idle entrance includes: If there are multiple idle entrances, selecting a target idle entrance from the multiple idle entrances according to the distance cost information of the target robot going to the idle entrance; According to the target idle entrance, a path for the target robot to go to the workstation is planned.

8. The method according to claim 1, characterized in that: Before obtaining the queuing area corresponding to the workstation, the method further includes: Identifying key points on each path leading to the workstation; The queuing area is generated according to the key points.

9. The method according to claim 8, characterized in that The identifying key points on each path leading to the workstation includes: The key point is determined according to the in-degree and out-degree of cells around the workstation.

10. The method according to claim 9, characterized in that Determining the key point according to the in-degree and out-degree of cells around the workstation includes: Traversing and searching for a target cell based on the in-degree and out-degree of the cell, wherein the target cell is a cell on a path leading to the workstation, and all paths corresponding to the out-degree of the target cell pass through the workstation; The target cell is determined as the cell where the key point is located.

11. The method according to claim 10, characterized in that The step of generating the queuing area according to the key points includes: The cells where the key points are located constitute the queuing area.

12. The method according to any one of claims 1 to 11, characterized in that Robots entering the queuing area have equal right of way.

13. A path planning device, characterized in that: include: An acquisition module is configured to acquire a queuing area corresponding to a workstation; A monitoring module is configured to monitor robot queuing information based on the queuing area; The adjustment module is configured to dynamically adjust the path of the robot to the workstation according to the robot queuing information.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

15. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 12 is implemented.

16. A computer program product comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 12 when executed by a processor.

Images