CN116048092A

CN116048092A - Agent scheduling method and device, computer readable medium and electronic equipment

Info

Publication number: CN116048092A
Application number: CN202310113560.7A
Authority: CN
Inventors: 宗师
Original assignee: Shanghai Wanchip Technology Co ltd
Current assignee: Shanghai Wanchip Technology Co ltd
Priority date: 2023-02-14
Filing date: 2023-02-14
Publication date: 2023-05-02

Abstract

The embodiment of the application provides an agent scheduling method, an agent scheduling device, a computer readable medium and electronic equipment. The method comprises the following steps: acquiring map data and specification data of an agent, wherein the map data comprises a directed graph matched with a scheduling area; determining, based on the map data and the specification data, agent collision data for recording whether there is a spatial collision at the same time when any two agents move in the scheduling area; determining path reference data for recording a shortest path of the agent between any two nodes in the directed graph based on the map data and the specification data; based on the map data, the agent conflict data, and the path reference data, each agent is scheduled to perform a transport task in the scheduling area. The technical scheme of the embodiment of the application can improve the response speed of scheduling the intelligent agent.

Description

Agent scheduling method and device, computer readable medium and electronic equipment

Technical Field

The present application relates to the field of computers and intelligent handling technologies, and in particular, to an agent scheduling method, an agent scheduling device, a computer readable medium, and an electronic device.

Background

In an agent scheduling scenario, such as an AGV scheduling scenario in a trolley or an AMR robot, generally taking global efficiency optimization as an optimization target, the method generally includes a handling task assignment, path planning and scheduling, that is, tasks are reasonably assigned to agents, time and space are considered, collision-free paths of all agents are planned, and commands such as start, stop, turn and the like are issued for each agent, so that the handling task is completed. However, since the mixed scheduling of multiple agents needs to consider factors such as the shape, size, running speed of different agents, the scheduling problem is large in scale and long in operation time, so that the instantaneity of the scheduling of the agents is poor. Based on this, how to improve the response speed of scheduling the agent is a technical problem to be solved.

Disclosure of Invention

The embodiment of the application provides an agent scheduling method, an agent scheduling device, a computer program product or a computer program, a computer readable medium and electronic equipment, and further can improve the response speed of scheduling the agent at least to a certain extent.

Other features and advantages of the present application will be apparent from the following detailed description, or may be learned in part by the practice of the application.

According to an aspect of the embodiments of the present application, there is provided an agent scheduling method, including: obtaining map data and specification data of an agent, wherein the map data comprises a directed graph matched with a scheduling area, and a plurality of nodes and a plurality of continuous edges are distributed in the directed graph, and any continuous edge is connected with two nodes; determining agent conflict data based on the map data and the specification data, wherein the agent conflict data is used for recording whether space conflicts exist at the same time when any two agents move in the scheduling area; determining path reference data based on the map data and the specification data, wherein the path reference data is used for recording the shortest path of the intelligent agent between any two nodes in the directed graph; and acquiring transport tasks respectively assigned to at least one agent, and scheduling each agent to execute the transport tasks in the scheduling area based on the map data, the agent conflict data and the path reference data.

In some embodiments of the present application, based on the foregoing solution, the scheduling each agent to perform a handling task in the scheduling area based on the map data, the agent collision data, and the path reference data includes: based on the map data, the agent conflict data and the path reference data, path planning is carried out for each agent according to the carrying task, and at least one piece of path information is obtained; and scheduling each agent to execute the transport task in the scheduling area according to the path information.

In some embodiments of the present application, based on the foregoing solution, the planning a path for each agent according to the transport task based on the map data, the agent collision data, and the path reference data, to obtain at least one piece of path information includes: determining a starting node and a terminating node of each intelligent agent for executing a corresponding carrying task in the directed graph based on the map data; determining the shortest path of each agent when executing the corresponding handling task in the directed graph according to the initial node and the termination node corresponding to each agent based on the path reference data; based on the agent conflict data, grouping each agent according to the shortest path to obtain a plurality of agent groups, wherein any one agent in any one agent group and any one agent in other agent groups do not have space conflict at the same time when moving in the scheduling area according to the shortest path; and planning paths of the intelligent agents in each target intelligent agent group aiming at each target intelligent agent group to obtain at least one piece of path information, wherein the target intelligent agent group is any one of the plurality of intelligent agent groups.

In some embodiments of the present application, based on the foregoing solution, the performing path planning on each agent in the target agent group to obtain at least one piece of path information includes: acquiring the priority of the transport tasks corresponding to the intelligent agents in the target intelligent agent group, and sequentially selecting one target transport task from the transport tasks corresponding to the intelligent agents in the target intelligent agent group according to a planning sequence defined by the priority; and planning a path for the intelligent agent corresponding to the target carrying task based on the map data to obtain at least one piece of path information.

In some embodiments of the present application, based on the foregoing solution, the planning a path for an agent corresponding to the target handling task based on the map data includes: acquiring paths planned for other intelligent agents as historical paths; determining a candidate path based on the map data, the candidate path having no conflict with the historical path in time and space; and selecting a target path for the intelligent agent corresponding to the target carrying task from the candidate paths.

In some embodiments of the present application, based on the foregoing solution, the selecting, from the candidate paths, a target path for an agent corresponding to the target handling task includes: calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each connecting edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path; and selecting the candidate path with the lowest path cost as a target path for the intelligent agent to execute the target carrying task.

In some embodiments of the present application, based on the foregoing solution, the selecting, from the candidate paths, a target path for an agent corresponding to the target handling task includes: calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each connecting edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path; acquiring the time cost of the agent on the candidate path; calculating a composite cost of the agent on the candidate path based on the path cost and the time cost; and selecting the candidate path with the lowest comprehensive cost as a target path for the intelligent agent to execute the target carrying task.

According to an aspect of the embodiments of the present application, there is provided an agent scheduling apparatus, including: the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring map data and specification data of an agent, the map data comprises a directed graph matched with a scheduling area, a plurality of nodes and a plurality of continuous edges are distributed in the directed graph, and any continuous edge is connected with two nodes; a first determining unit configured to determine, based on the map data and the specification data, agent conflict data for recording whether there is a spatial conflict at the same time when any two agents move in the scheduling area; a second determining unit, configured to determine path reference data based on the map data and the specification data, where the path reference data is used to record a shortest path of the agent between any two nodes in the directed graph; and a second acquiring unit configured to acquire transport tasks respectively assigned to at least one agent, and schedule each agent to perform a transport task in the scheduling area based on the map data, the agent collision data, and the path reference data.

According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method described in the above embodiment.

According to an aspect of the embodiments of the present application, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method as described in the above embodiments.

According to an aspect of an embodiment of the present application, there is provided an electronic device including: one or more processors; and storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method as described in the above embodiments.

In the technical solutions provided in some embodiments of the present application, before each agent is scheduled to perform a transport task in the scheduling area, the relevant scheduling data is preprocessed, map data, agent conflict data, and path reference data are determined and obtained, the preprocessed data are stored in advance, and then each agent is scheduled to perform the transport task in the scheduling area based on the map data, the agent conflict data, and the path reference data, so that the response speed of scheduling the agents in a transport scenario, particularly in a transport scenario of a plurality of types of agents is improved, thereby improving efficiency and scientificity of the agents when performing the transport task, reducing manual intervention, improving scenario compatibility and practicality, and providing a high-quality and high-stability scheduling decision.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is apparent that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:

fig. 1 shows a schematic view of a scenario in which the technical solution of the embodiments of the present application may be applied;

FIG. 2 illustrates a flow chart of an agent scheduling method according to one embodiment of the present application;

FIG. 3 illustrates a schematic diagram of an agent's positional relationship between two nodes according to one embodiment of the present application;

FIG. 4 illustrates a schematic diagram of an agent rotation profile according to one embodiment of the present application;

FIG. 5 illustrates a detailed flow diagram for scheduling individual agents to perform a transport task in the scheduling area based on the map data, the agent conflict data, and the path reference data, according to one embodiment of the present application;

FIG. 6 illustrates a schematic view of a scenario in which an agent is routed in a directed graph according to one embodiment of the present application;

FIG. 7 illustrates a detailed flow diagram of path planning for individual agents according to the transport tasks based on the map data, the agent conflict data, and the path reference data, according to one embodiment of the present application;

FIG. 8 illustrates a schematic diagram of performing an agent scheduling method according to one embodiment of the present application;

FIG. 9 illustrates a block diagram of an agent scheduler according to one embodiment of the present application;

fig. 10 shows a schematic diagram of a computer system suitable for use in implementing the electronic device of the embodiments of the present application.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the present application. One skilled in the relevant art will recognize, however, that the aspects of the application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

It should be noted that: references herein to "a plurality" means two or more. "and/or" describes an association relationship of an association object, meaning that there may be three relationships, e.g., a and/or B may represent: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the objects so used may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described.

Fig. 1 shows a schematic view of a scenario in which the technical solution of the embodiments of the present application may be applied.

The system architecture shown in fig. 1 may include a server 101 (which may also be one or more of a smart phone, tablet computer, and portable computer), a network 102, and an agent 103 (such as an automated guided vehicle, automated Guided Vehicle, AGV, also such as an autonomous mobile robot, autonomous Mobile Robot, AMR). The network 102 is the medium used to provide the communication link between the server 101 and the agent 103. Network 102 may include various connection types, such as wired communication links, wireless communication links, and the like.

In one embodiment of the present application, the agent scheduling method may be performed by the server 101, further may be performed by the agent 103 in cooperation with the server 101, in the scheduling area 104 as shown in fig. 1, may be scheduling one or more agents 103 to perform a handling task, in this case, may be acquiring map data by the server 101, and acquiring specification data of the agents, the map data including a directed graph matched with the scheduling area, then determining, by the server 101, agent collision data for recording whether there is a spatial collision of any two agents at the same time when moving in the scheduling area based on the map data and the specification data, and determining path reference data for recording a shortest path of an agent between any two nodes in the directed graph based on the map data and the specification data, and finally scheduling each agent to perform the handling task in the scheduling area by the server 101 based on the map data, the agent collision data, and the path reference data.

In the application, before each agent is scheduled to execute the carrying task in the scheduling area, the related scheduling data is preprocessed to determine map data, agent conflict data and path reference data, and then based on the map data, the agent conflict data and the path reference data, each agent is scheduled to execute the carrying task in the scheduling area, so that the response speed of scheduling the agents can be improved.

The implementation details of the technical solutions of the embodiments of the present application are described in detail below:

fig. 2 shows a flow chart of an agent scheduling method according to an embodiment of the present application, which may be performed by a device having a calculation processing function, such as may be performed by the server shown in fig. 1. Referring to fig. 2, the agent scheduling method at least includes steps 210 to 270, which are described in detail as follows:

in step 210, map data is acquired, and specification data of an agent is acquired, where the map data includes a directed graph matched with a scheduling area, and a plurality of nodes and a plurality of edges are distributed in the directed graph, where any one edge connects two nodes.

In this application, the map data includes a directed graph matched with the scheduling area, specifically, the map data may be represented based on graph theory, where a directed graph g= (N, a), n= { n_1, n_2, …, n_n } represents nodes in the graph, and a= { a_1, a_2, …, a_m } represents a continuous edge between each node in the graph. In order to adapt to the application of agent scheduling in a carrying scene, a plurality of corresponding properties can be endowed for each node and the connecting edge in the map data, and the nodes and the connecting edges are stored in the map data together.

Wherein the node property may include a node name; two-dimensional coordinate information (representing the position of a node on a plane); floor information (information indicating that a node is at a height); whether the node can stay with the agent; whether the node is an elevator, etc.

Wherein the conjoined nature may include a start and end point name; bezier curve information; the length of the connecting edge; whether a gate is present (e.g., whether a gate is present on the connection), etc. Further, the directed graph may further include a weighted length of each edge (it should be noted that, the weighted length of the edge is not necessarily equal to the actual length of the edge, and the weighted length is a proportion of the actual length, which is used to enhance or weaken the probability that the edge is selected), and a direction of the edge (which may include unidirectional or bidirectional).

In addition, in the present application, constraint information of the movement of the agent in the scheduling area may also be written in the map data. Such as, for example, the restriction information of the agent in the node (e.g., non-driving-in or non-rotation of the corresponding agent, etc.); loading speed or idle speed of the intelligent body on the connecting edge; the intelligent body needs to travel along the connecting edge when moving, and after entering one connecting edge, the intelligent body must reach the other end point (node) of the edge along the moving direction; the intelligent body can execute the movement forms of stopping, rotating, steering and the like at the node; no conflict exists among the agents on different floors; if a certain node can not stay, the intelligent agent can not stay in a static state at the node; the intelligent body moves across floors as far as possible through the elevators, and one elevator can only bear one intelligent body at a time; if there is a door on a link, the link can be passed after a door crossing command is issued.

In the application, the agent map in the production/handling/logistics scene can be described according to the data format, and stored as input data of other subsequent preprocessing operations and basic data in the actual running process.

In this application, specification data of the agent may also be obtained, for example, the specification data of the agent may be a shape, a size, a model, a carrying speed, a rotation angle range, or the like of the agent.

In the present application, the types of the related agents may include a plurality of types, each type of agents having specification data unique to itself and being distinguished from specification data of other types of agents. In the actual scheduling process, the intelligent agent can be abstracted into a more characteristic and generalized geometric shape, and different properties are endowed to the intelligent agent, so that the intelligent agent is used for describing the characteristics of the intelligent agent. The agent properties may include an agent name; shape of agent (rectangle/circle); the size of the agent (length and width for rectangular, radius for circular; different size can be set for each agent corresponding to empty/cargo); speed (straight speed, turning speed, rotational speed, etc.).

With continued reference to fig. 2, in step 230, agent conflict data is determined based on the map data and the specification data, the agent conflict data being used to record whether there is a spatial conflict at the same time when any two agents move in the scheduling area.

In the application, preprocessing of the collision data of the agent can be performed by considering the map data and the specification data of the agent, and the preprocessing is used as a collision judgment standard in the real-time scheduling process.

In the present application, since the directed graph corresponding to the scheduling area includes a plurality of nodes and a connecting edge connecting the plurality of nodes, the agents may collide with each other when the agents move in the scheduling area (a plurality of agents appear at a certain position in the directed graph at the same time, thereby causing collision). Based on this, it is possible to determine agent collision data for recording whether there is a spatial collision at the same time when any two agents move in the scheduling area, based on the map data and specification data of the agents.

Specifically, in the present application, whether there is a spatial conflict at the same time when two agents move in the scheduling area may include three cases, that is, whether there is a spatial conflict when two agents are both on a node at the same time; secondly, when two intelligent agents are respectively positioned on a node and a connecting edge at the same time, whether space conflict exists or not; thirdly, if two agents are on the link at the same time, whether there is a space conflict.

In order to better understand the present application, the following describes the three possible conflicting situations.

And combining map data and agent specification data, and combining agent properties and the position of the agent to generate relevant agent conflict data. For each type of agent, conflict data of all other types of agents and the other types of agents are generated, and the specifically generated conflict data are shown as follows:

first, node conflict-a conflict when both agents are on a node.

When an agent is rectangular, the angle that a rectangular agent may exist at each node is considered to be the angle of the "edge that ends at that node" without regard to rotation. Thus, in node avoidance, rectangular agents consider avoidance between a limited number of fixed angles at each node. If the intelligent agent conflicts in the rectangle and the angle randomness of the rectangle is strong, whether each side of the rectangle conflicts or not is judged. Let the sides to be judged to intersect be (P1, P2) and (Q1, Q2), where p1= (x 1, y 1), p2= (x 2, y 2), p3= (x 3, y 3), p4= (x 4, y 4), the specific method is as follows:

quick rejection test: if the rectangles with (P1, P2) and (Q1, Q2) as diagonal lines do not intersect, the two line segments do not intersect. It is required that max (x 1, x 2) > min (x 3, x 4) and max (y 1, y 2) > min (y 3, y 4) and max (x 3, x 4) > = min (x 1, x 2) and max (y 3, y 4) > = min (y 1, y 2).

Straddling test: if intersecting, points P1 and P2 are on either side of line segment (Q1, Q2), and Q1 and Q2 are on either side of line segment (P1, P2). The [ (P1, Q1) × (P1, Q2) ] [ (P2, Q1) × (P2, Q2) ] < 0 and [ (Q1, P1) × (Q1, P2) ] [ (Q2, P1) × [ (Q2, P2) ] < 0.

Judging whether any two edges are intersected or not by the two-step method, if a group of edges are intersected, judging that two rectangles are intersected, obtaining a conclusion that two intelligent agents have space conflict when being on nodes at the same time, and storing the conclusion as related conflict data.

For example, referring to fig. 3, a schematic diagram of the positional relationship of an agent between two nodes according to one embodiment of the present application is shown. As shown in fig. 300 (a), when the agent 1 is on the node M and the agent 2 is on the node N, since any contour edge of the agent 1 and any contour edge of the agent 2 do not intersect, it can be concluded that there is no space conflict when the agent 1 and the agent 2 are both on the node at the same time; as shown in fig. 300 (b), where the agent 3 is at node Q and the agent 4 is at node P, since the partial contour edge of the agent 3 and the partial contour edge of the agent 4 intersect, it can be concluded that there is a spatial conflict when both the agent 3 and the agent 4 are at the node at the same time.

When the agent is round, if the agent is abstracted into a circle, it is required to set the coordinates of the center point of the agent to be (x 1, y 1) and (x 2, y 2) and the radii to be r1 and r2, respectively

If the data do not meet the data, the data are in conflict, and relevant data are saved.

Second, nodes, edge collision—when one agent is on an edge, the other is on the node's back-off.

The edge where an agent is located is abstracted into a rectangle with the length of the edge and the width of the edge being the width/radius of the agent. Consider that there is another agent at the neighboring node: if the intelligent agent at the node is a rectangle, whether the intelligent agent conflicts with the rectangle abstracted by the edges under different angles is considered, and the method can adopt the rapid rejection test and the hurdle test to test whether any two edges of the two rectangles are intersected or not; if the agent at the node is a circle, judging whether any edge of the rectangle abstracted by the circle and the edge intersects. If the data are intersected, the data are considered to be conflicted, and relevant conflicted data are saved.

Further, consider the rotation of the rectangular agent at the nodes. According to the rotation track, abstracting the rotation action of the rectangular intelligent agent between any two feasible angles at the node into two symmetrical sectors, judging the conflict situation of the rectangular intelligent agent and the intelligent agent at the adjacent node, and storing related conflict data. Referring to fig. 4, a schematic diagram 400 of an agent rotation profile (sector) is shown, according to one embodiment of the present application.

Third, edge collision—avoidance when both agents are on edge.

The edges where two intelligent agents are located are abstracted into two rectangles with the edge length and the width of the intelligent agents being equal to the width/radius, the rapid rejection test and the cross test can be adopted to test whether any two edges of the two rectangles are intersected, and if so, relevant conflict data are stored.

In the method, the device and the system, the data are preprocessed to obtain the conflict data of the agents which record whether the space conflict exists at the same time when any two agents move in the scheduling area, so that data reference and support can be provided for scheduling of the follow-up handling tasks, the accuracy and stability of the follow-up handling tasks can be enhanced, the data calculation amount in the follow-up handling task scheduling process can be reduced, and the scheduling efficiency and response speed of the follow-up handling tasks are improved.

With continued reference to fig. 2, in step 250, path reference data is determined based on the map data and the specification data, the path reference data being used to record a shortest path of an agent between any two nodes in the directed graph.

In the present application, path reference data for recording the shortest path of the agent between any two nodes in the directed graph may be determined based on the map data and specification data of the agent. In the data preprocessing stage, the conflict among the intelligent agents is not considered, the shortest path between any two points of each type of intelligent agent in the map can be calculated and used as path reference data and used as input data of real-time scheduling, and the purpose of improving the real-time scheduling efficiency is achieved.

Specifically, the method can adopt a bellman-ford algorithm to calculate, and aims at minimizing the path cost, calculates the shortest path of each task without considering conflict, records the related path information, and adopts the following calculation modes:

d _v ←min{d _v ,d _u +c _uv ·w _uv }

if d _v changes,thenπ _v ←u

wherein v, u is any two nodes in the directed graph; d, d _v ，d _u Path cost from the start point to the nodes v, u; c _uv Is the length of the connecting edge (u, v), w _uv Weight coefficients for edges (u, v); in the calculation process, the path cost from the starting point to each node in the calculation process is guaranteed to be the shortest, and the path is updated.

In the method, the path reference data of the shortest path of the recording agent between any two nodes in the directed graph is obtained by preprocessing the data, so that data reference and support can be provided for the scheduling of the follow-up carrying task, the accuracy and stability of the follow-up carrying task scheduling can be enhanced, the data calculation amount in the follow-up carrying task scheduling process can be reduced, and the scheduling efficiency and response speed of the follow-up carrying task are improved.

With continued reference to fig. 2, in step 270, the individually assigned handling tasks for at least one agent are obtained, and based on the map data, the agent conflict data, and the path reference data, the respective agents are scheduled to perform the handling tasks in the scheduling area.

In one embodiment of step 270 shown in fig. 2, scheduling individual agents to perform a transport task in the scheduling area based on the map data, the agent collision data, and the path reference data may be performed in accordance with the steps shown in fig. 5.

Referring to fig. 5, a detailed flow diagram of scheduling individual agents to perform a transport task in the scheduling area based on the map data, the agent collision data, and the path reference data is shown according to one embodiment of the present application. Specifically, steps 271 to 272 are included:

step 271, performing path planning for each agent according to the handling task based on the map data, the agent conflict data, and the path reference data, to obtain at least one piece of path information.

And step 272, scheduling each agent to execute the transport task in the scheduling area according to the path information.

In the present application, the path information refers to a movement path of the agent to execute the transport task in the directed graph reflected in the dispatch area. It may be determined from map-based data, agent collision data, and path reference data, based on assigned handling tasks for the agent. Fig. 6 illustrates a schematic view of a scenario for path planning of an agent in a directed graph according to one embodiment of the present application. For example, path a is planned for agent a, path B is planned for agent B, and path C is planned for agent C.

In this application. The accuracy and stability of data processing in the process of carrying task scheduling can be enhanced by preprocessing the data to obtain the agent conflict data and the path reference data, the calculated amount of data processing in the process of carrying task scheduling can be reduced, and the scheduling efficiency of carrying tasks can be improved.

In this embodiment, that is, in step 271 shown in fig. 5, based on the map data, the agent collision data, and the path reference data, path planning is performed for each agent according to the handling task, so as to obtain at least one piece of path information, which may be performed according to the steps shown in fig. 7.

Referring to fig. 7, a detailed flow diagram of path planning for each agent according to the transport task based on the map data, the agent conflict data, and the path reference data is shown according to one embodiment of the present application. Specifically, the method comprises steps 2711 to 2714:

step 2711, determining a start node and a stop node of each agent for executing the corresponding handling task in the directed graph based on the map data.

Step 2712, determining the shortest path of each agent when executing the corresponding handling task in the directed graph according to the start node and the end node corresponding to each agent based on the path reference data.

Step 2713, grouping each agent according to the shortest path based on the agent conflict data to obtain a plurality of agent groups, wherein any one agent in any one agent group and any one agent in other agent groups do not have space conflict at the same time when moving in the scheduling area according to the shortest path.

Step 2714, for each target agent group, performing path planning on each agent in the target agent group to obtain at least one piece of path information, where the target agent group is any one of the multiple agent groups.

Traditional multi-agent path planning selects each path of all agents in a map (one path from one node to another node) as a sub-node to maintain a path search tree with a larger scale, and in the application, relevant grouping operation can be performed by using agent conflict data and path reference data obtained by the data preprocessing. The method comprises the following specific steps:

firstly, receiving real-time conveying task data of the intelligent agents, obtaining starting and ending points of all conveying tasks (all conveying tasks comprise the new conveying tasks and the conveying tasks which are already executed, and the starting point of the conveying tasks which are already executed is set to be corresponding to the current node or edge of the intelligent agents).

In the method, the path search tree is decomposed into a plurality of path search trees with smaller scale through grouping, so that the problem scale is greatly reduced, and the real-time scheduling efficiency is improved.

In this embodiment, path planning is performed on each agent in the target agent group to obtain at least one piece of path information, which may be performed according to the following steps 281 to 282:

step 281, obtaining priorities of the transport tasks corresponding to the respective agents in the target agent group, and sequentially selecting a target transport task from the transport tasks corresponding to the respective agents in the target agent group according to a planning order defined by the priorities.

And 282, planning a path for the intelligent agent corresponding to the target carrying task based on the map data to obtain at least one piece of path information.

In the method, the path is planned for each agent according to the priority order of each carrying task, so that the method has the advantage of improving the rationality of scheduling the agents.

In the present application, path planning for the agent corresponding to the target handling task may be implemented based on an improved a-algorithm.

Specifically, the algorithm a is a more common path planning algorithm in the industry, and is also one of the bases of the multi-agent scheduling algorithm. The algorithm formula is as follows:

f(n)＝h(n)+g(n)

Wherein n represents the current node searched in the path searching process of the intelligent agent; f (n) is the minimum cost estimate from the task start point to the task target end point via node n; g (n) is the minimum cost value from the task start point to node n; h (n) is the minimum cost estimate to reach the task target endpoint from node n.

Further, g (n) is a determined value as a minimum cost value of the searched path; and h (n) is the minimum cost estimated value of the node n to the task target end point, and the difference of the estimated method selection can greatly influence the searching efficiency. The general estimation method for h (n) includes: 1) Estimating a linear distance; 2) Manhattan distance estimation, however, neither method can restore the exact value of the node n to the target destination of the task. In the scheme, the data can be preprocessed by using the bellman-ford shortest path, the cost from the real node n to the target terminal point is used as h (n), and the efficiency of the A-algorithm searching process can be greatly improved.

In this embodiment, route planning for the agent corresponding to the target handling task based on the map data may be performed according to the following steps 2821 to 2823:

in step 2821, the planned path for the other agents is obtained as a historical path.

Step 2822, determining a candidate path based on the map data, the candidate path having no conflict with the historical path in time and space.

And 2823, selecting a target path for the intelligent agent corresponding to the target handling task from the candidate paths.

Further, in this embodiment, selecting a target path for an agent corresponding to the target handling task from the candidate paths may be performed according to the following steps 291 to 292:

and step 291, calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each continuous edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path.

Step 292, selecting the candidate path with the lowest path cost as the target path for the agent to execute the target transport task.

In the method, the probability of selecting the continuous edge can be enhanced or weakened in path planning by considering the edge weight coefficient of each continuous edge, so that a certain path is emphasized or avoided being selected as a part of a final path, for example, the requirement that a certain continuous edge is not taken or is emphasized in an actual scene can be met, and individuation in the path planning process is facilitated.

In this embodiment, selecting a target path for an agent corresponding to the target handling task from the candidate paths may be further performed according to steps 291 to 292 as follows:

and 293, calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each continuous edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path.

Step 294, obtaining a time cost of the agent on the candidate path.

Step 295, calculating a composite cost of the agent on the candidate path based on the path cost and the time cost.

And step 296, selecting the candidate path with the lowest comprehensive cost as a target path for the agent to execute the target transport task.

Based on the above embodiments, it will be appreciated by those skilled in the art that a multi-agent path search tree is maintained for each packet for maintaining agent's planning priority. Each round of planning sequentially plans the complete path of each agent according to the priority order, records the path and the time window passing through each node and side on the path, and the agents with the rear priority perform conflict-free path planning based on the path and the occupied time window of the preceding vehicle. The core of collision-free path planning is to use the collision preprocessing data of multiple agents for judgment, and the specific key points are as follows:

1. Carrying out path planning by adopting the improved A-type algorithm according to the priority order in the group, and storing paths;

2. in the planning process, the agent with the later priority needs to judge whether the node and the edge which arrive at the current step conflict with the existing paths of other agents on a time axis in each path search. If the conflict exists, discarding the node, and continuing to search other paths from the previous node in the paths; if no conflict exists, the node is saved.

3. After the searching of the paths in the group is finished, the paths are saved and used as conflict judgment data of the next group of path planning, so that the conflict-free paths of all agents are ensured.

In the application, after the final planned path information is obtained, each agent can be scheduled to execute the transport task in the scheduling area according to the path information. By adopting the scheduling scheme provided by the application, the scheduling method and the system can greatly reduce the problem scale, improve the scheduling efficiency and reduce the algorithm response time, and simultaneously, the path planning and the scheduling instructions are stably output while the safety of the intelligent agent is considered.

In order for those skilled in the art to better understand the present solution as a whole, reference is made to fig. 8, which is a schematic diagram 800 for performing an agent scheduling method according to an embodiment of the present application.

In one embodiment of the present application, three data interfaces are designed: 1) A map data interface; 2) An agent specification data interface; 3) And carrying task data interfaces in real time.

The interfaces 1 and 2 respectively receive map data and intelligent agent data, store the data, combine the two data and perform data preprocessing operation to obtain map data, intelligent agent conflict data and path reference data. The interface 3 receives the real-time transport task data, combines the processed data of the interfaces 1 and 2 and the real-time transport task data, and outputs corresponding path planning and scheduling results.

In the application, before each agent is scheduled to execute a carrying task in the scheduling area, the related scheduling data is preprocessed, map data, agent conflict data and path reference data are obtained, the preprocessed data are stored in advance, then each agent is scheduled to execute the carrying task in the scheduling area based on the map data, the agent conflict data and the path reference data, and the response speed of scheduling the agents in a carrying scene, particularly in a carrying scene of a plurality of types of agents can be improved, so that efficiency and scientificity of the agents in executing the carrying task are improved, manual intervention is reduced, scene compatibility and practicality are improved, and a high-quality and high-stability scheduling decision is provided.

The following describes an embodiment of an apparatus of the present application, which may be used to perform the agent scheduling method in the foregoing embodiments of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the agent scheduling method described in the present application.

Fig. 9 shows a block diagram of an agent scheduler according to one embodiment of the present application.

Referring to fig. 9, an agent scheduling apparatus 900 according to an embodiment of the present application includes: a first acquisition unit 901, a first determination unit 902, a second determination unit 903, and a second acquisition unit 904.

The first obtaining unit 901 is configured to obtain map data, and obtain specification data of an agent, where the map data includes a directed graph matched with a scheduling area, and a plurality of nodes and a plurality of edges are distributed in the directed graph, where any one edge connects two nodes; a first determining unit 902, configured to determine, based on the map data and the specification data, agent conflict data, where the agent conflict data is used to record whether there is a spatial conflict at the same time when any two agents move in the scheduling area; a second determining unit 903, configured to determine path reference data based on the map data and the specification data, where the path reference data is used to record a shortest path of the agent between any two nodes in the directed graph; a second obtaining unit 904, configured to obtain the transport tasks respectively assigned to at least one agent, and schedule each agent to perform the transport tasks in the scheduling area based on the map data, the agent collision data, and the path reference data.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is configured to: based on the map data, the agent conflict data and the path reference data, path planning is carried out for each agent according to the carrying task, and at least one piece of path information is obtained; and scheduling each agent to execute the transport task in the scheduling area according to the path information.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is further configured to: determining a starting node and a terminating node of each intelligent agent for executing a corresponding carrying task in the directed graph based on the map data; determining the shortest path of each agent when executing the corresponding handling task in the directed graph according to the initial node and the termination node corresponding to each agent based on the path reference data; based on the agent conflict data, grouping each agent according to the shortest path to obtain a plurality of agent groups, wherein any one agent in any one agent group and any one agent in other agent groups do not have space conflict at the same time when moving in the scheduling area according to the shortest path; and planning paths of the intelligent agents in each target intelligent agent group aiming at each target intelligent agent group to obtain at least one piece of path information, wherein the target intelligent agent group is any one of the plurality of intelligent agent groups.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is further configured to: acquiring the priority of the transport tasks corresponding to the intelligent agents in the target intelligent agent group, and sequentially selecting one target transport task from the transport tasks corresponding to the intelligent agents in the target intelligent agent group according to a planning sequence defined by the priority; and planning a path for the intelligent agent corresponding to the target carrying task based on the map data to obtain at least one piece of path information.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is further configured to: acquiring paths planned for other intelligent agents as historical paths; determining a candidate path based on the map data, the candidate path having no conflict with the historical path in time and space; and selecting a target path for the intelligent agent corresponding to the target carrying task from the candidate paths.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is further configured to: calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each connecting edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path; and selecting the candidate path with the lowest path cost as a target path for the intelligent agent to execute the target carrying task.

In some embodiments of the present application, based on the foregoing solution, the second obtaining unit 904 is further configured to: calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each connecting edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path; acquiring the time cost of the agent on the candidate path; calculating a composite cost of the agent on the candidate path based on the path cost and the time cost; and selecting the candidate path with the lowest comprehensive cost as a target path for the intelligent agent to execute the target carrying task.

It should be noted that, the computer system 1000 of the electronic device shown in fig. 10 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.

As shown in fig. 10, the computer system 1000 includes a central processing unit (Central Processing Unit, CPU) 1001 that can perform various appropriate actions and processes, such as performing the method described in the above embodiment, according to a program stored in a Read-Only Memory (ROM) 1002 or a program loaded from a storage section 1008 into a random access Memory (Random Access Memory, RAM) 1003. In the RAM 1003, various programs and data required for system operation are also stored. The CPU 1001, ROM 1002, and RAM 1003 are connected to each other by a bus 1004. An Input/Output (I/O) interface 1005 is also connected to bus 1004.

The following components are connected to the I/O interface 1005: an input section 1006 including a keyboard, a mouse, and the like; an output portion 1007 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and a speaker; a storage portion 1008 including a hard disk or the like; and a communication section 1009 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1009 performs communication processing via a network such as the internet. The drive 1010 is also connected to the I/O interface 1005 as needed. A removable medium 1011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like, is installed on the drive 1010 as needed, so that a computer program read out therefrom is installed into the storage section 1008 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 1009, and/or installed from the removable medium 1011. When executed by a Central Processing Unit (CPU) 1001, the computer program performs various functions defined in the system of the present application.

It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the method described in the above embodiment.

As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit, in accordance with embodiments of the present application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.

Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.

It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. An agent scheduling method, the method comprising:

obtaining map data and specification data of an agent, wherein the map data comprises a directed graph matched with a scheduling area, and a plurality of nodes and a plurality of continuous edges are distributed in the directed graph, and any continuous edge is connected with two nodes;

determining agent conflict data based on the map data and the specification data, wherein the agent conflict data is used for recording whether space conflicts exist at the same time when any two agents move in the scheduling area;

determining path reference data based on the map data and the specification data, wherein the path reference data is used for recording the shortest path of the intelligent agent between any two nodes in the directed graph;

and acquiring transport tasks respectively assigned to at least one agent, and scheduling each agent to execute the transport tasks in the scheduling area based on the map data, the agent conflict data and the path reference data.

2. The method of claim 1, wherein the scheduling each agent to perform a transport task in the scheduling area based on the map data, the agent collision data, and the path reference data comprises:

Based on the map data, the agent conflict data and the path reference data, path planning is carried out for each agent according to the carrying task, and at least one piece of path information is obtained;

and scheduling each agent to execute the transport task in the scheduling area according to the path information.

3. The method of claim 2, wherein the performing path planning for each agent based on the map data, the agent collision data, and the path reference data according to the transport task to obtain at least one piece of path information includes:

determining a starting node and a terminating node of each intelligent agent for executing a corresponding carrying task in the directed graph based on the map data;

determining the shortest path of each agent when executing the corresponding handling task in the directed graph according to the initial node and the termination node corresponding to each agent based on the path reference data;

based on the agent conflict data, grouping each agent according to the shortest path to obtain a plurality of agent groups, wherein any one agent in any one agent group and any one agent in other agent groups do not have space conflict at the same time when moving in the scheduling area according to the shortest path;

And planning paths of the intelligent agents in each target intelligent agent group aiming at each target intelligent agent group to obtain at least one piece of path information, wherein the target intelligent agent group is any one of the plurality of intelligent agent groups.

4. The method of claim 3, wherein the performing path planning on each agent in the target agent group to obtain at least one piece of path information includes:

acquiring the priority of the transport tasks corresponding to the intelligent agents in the target intelligent agent group, and sequentially selecting one target transport task from the transport tasks corresponding to the intelligent agents in the target intelligent agent group according to a planning sequence defined by the priority;

and planning a path for the intelligent agent corresponding to the target carrying task based on the map data to obtain at least one piece of path information.

5. The method of claim 4, wherein the planning a path for an agent corresponding to the target transport task based on the map data comprises:

acquiring paths planned for other intelligent agents as historical paths;

determining a candidate path based on the map data, the candidate path having no conflict with the historical path in time and space;

And selecting a target path for the intelligent agent corresponding to the target carrying task from the candidate paths.

6. The method of claim 5, wherein selecting a target path for an agent corresponding to the target handling task from the candidate paths comprises:

calculating the path cost of the intelligent agent on the candidate path according to the edge length and the edge weight coefficient of each connecting edge on the candidate path, wherein the path cost is used for representing the cost of the intelligent agent for executing the carrying task on the candidate path;

and selecting the candidate path with the lowest path cost as a target path for the intelligent agent to execute the target carrying task.

7. The method of claim 5, wherein selecting a target path for an agent corresponding to the target handling task from the candidate paths comprises:

acquiring the time cost of the agent on the candidate path;

Calculating a composite cost of the agent on the candidate path based on the path cost and the time cost;

and selecting the candidate path with the lowest comprehensive cost as a target path for the intelligent agent to execute the target carrying task.

8. An agent scheduling apparatus, the apparatus comprising:

the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring map data and specification data of an agent, the map data comprises a directed graph matched with a scheduling area, a plurality of nodes and a plurality of continuous edges are distributed in the directed graph, and any continuous edge is connected with two nodes;

a first determining unit configured to determine, based on the map data and the specification data, agent conflict data for recording whether there is a spatial conflict at the same time when any two agents move in the scheduling area;

a second determining unit, configured to determine path reference data based on the map data and the specification data, where the path reference data is used to record a shortest path of the agent between any two nodes in the directed graph;

and a second acquiring unit configured to acquire transport tasks respectively assigned to at least one agent, and schedule each agent to perform a transport task in the scheduling area based on the map data, the agent collision data, and the path reference data.

9. A computer readable storage medium having stored therein at least one program code loaded and executed by a processor to implement operations performed by the method of any of claims 1 to 7.

10. An electronic device comprising one or more processors and one or more memories, the one or more memories having stored therein at least one piece of program code that is loaded and executed by the one or more processors to implement the operations performed by the method of any of claims 1-7.