Semi-centralized robot fleet management system and management method

Abstract

The present invention provides a semi-centralized robot fleet management system and management method. A semi-centralized robot fleet management system according to an embodiment of the present invention includes: a task allocation module for allocating a task to be performed to each of a plurality of robots; a path planning module for calculating a moving path along which the respective robots can move to a destination in order to complete the allocated task without colliding with each other; a traffic control module for generating a traffic signal for controlling an entry order and a moving direction of at least one robot in a waypoint node of an intersection; and a communication interface for communicating the moving path and the traffic signal to the robot. The semi-centralized robot fleet management system and management method of the present invention can utilize advantages of both centralized and decentralized control methods and minimize disadvantages thereof, thereby realizing optimization of multi-robot control.

Description

Semi-centralized robot fleet management system and management method

[0001] The present invention relates to robot control, and more particularly, to a semi-centralized robot fleet management system and management method capable of efficiently managing multiple autonomous mobile robots (AMRs).

[0002]

[0003] The logistics industry has recently seen a growing demand for logistics automation technology, particularly logistics transport robots, that can handle large volumes of goods quickly and efficiently. Logistics sites are seeking to address high labor costs and labor shortages by introducing logistics robots, leading to a surge in demand for logistics robots that enable automated logistics operations.

[0004] Most sites using logistics robots in Korea operate a small number of mobile robots (less than 10), but recently, large logistics warehouses and manufacturing sites are attempting to operate a large number of robots (more than 50).

[0005] To operate such large-scale robots, a fleet management system (FMS) must provide multi-robot control capabilities to ensure that the robots move smoothly without colliding with each other.

[0006] In multi-robot control systems, centralized control and decentralized control methods provide different approaches to operating and coordinating robots.

[0007] Centralized control involves all decisions and control made by a single central control unit or system. It is primarily used in systems such as automated guided vehicles (AGVs) that move along a designated path. In this approach, the central control system collects status information from all robots, makes optimal decisions to achieve the overall system's goals, and issues specific instructions to each robot.

[0008] The advantage of centralized control is that it allows for integrated management and optimization of the entire system. However, because all information and control commands are processed centrally, increased system complexity can lead to processing delays, communication bottlenecks, and dynamic obstacles that require waiting for the obstacle to be removed or requiring the central system to designate a different route.

[0009] On the other hand, autonomous mobile robots (AMRs) can easily avoid obstacles because they are capable of autonomous avoidance maneuvers, but it is difficult to utilize these functions under centralized control, making it difficult to respond immediately to dynamic obstacles.

[0010] Distributed control is a method that reduces dependence on a central control unit by allowing each robot to make decisions and act independently. In this method, each robot perceives its surroundings and the status of other robots, making independent judgments and moving autonomously.

[0011] The advantages of distributed control include superior system flexibility and scalability, and the ability to avoid bottlenecks and single points of failure associated with centralized systems. It is particularly suited to autonomous mobile robots (AMRs) with autonomous avoidance capabilities, and can be effectively deployed in environments with people or other dynamic obstacles.

[0012] However, since each robot makes decisions and acts independently, comprehensive optimization for the overall system's goals becomes difficult, and collisions or deadlocks between robots are likely to occur. Deadlocks are particularly frequent in spaces with numerous narrow passageways, such as logistics or manufacturing sites, limiting the utility of distributed control methods.

[0013] Therefore, there is a need for a system that achieves optimal multi-robot control performance by leveraging the advantages of each method of centralized and distributed control systems and minimizing their disadvantages.

[0014]

[0015] The present invention provides a hybrid semi-centralized robot fleet management system and management method that appropriately combines centralized and distributed control methods for efficient operation of multiple autonomous mobile robots (AMRs).

[0016] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0017]

[0018] A semi-centralized robot fleet management system according to one embodiment of the present invention,

[0019] It includes a task assignment module that assigns a task to be performed to each of a plurality of robots; a path planning module that calculates a movement path that each of the robots can move to a destination to complete the assigned task without colliding with each other; a traffic control module that generates a traffic signal for controlling the entry order and movement direction of at least one of the robots at a waypoint node of an intersection; and a communication interface that communicates the movement path and the traffic signal to the robots.

[0020] Preferably, each robot that has received the above movement path can identify its location through a mounted sensor and recognize obstacles to move autonomously.

[0021] Preferably, the autonomous movement of the robot along the movement path is possible in an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone is characterized in that it does not include the waypoint node.

[0022] Preferably, in the autonomous driving zone, the robot is capable of autonomous movement according to preset right-hand traffic rules.

[0023] Preferably, the traffic signal includes information about the entry order and movement direction of at least one robot in a single-lane passage.

[0024] Preferably, the traffic control module stores the movement order of at least one robot in the waypoint node in the form of a dependency graph, and the dependency graph represents each of a plurality of waypoint nodes that the at least one robot must pass through over time as a vertex, and represents movement conditions between robots for at least one waypoint node represented as a vertex as an edge.

[0025] Preferably, the calculation of the movement path by the path planning module is performed using multi-agent path search (MAPF), and the objective function of the multi-agent path search (MAPF) is characterized in that it is the sum of the movement distance / time on the path of each robot (sum of costs) or the maximum required time / distance (makespan) of each robot.

[0026] A semi-centralized robot fleet management method according to one embodiment of the present invention, comprising: a task assignment step of assigning a task to be performed to each of a plurality of robots; a path planning step of calculating a movement path along which each of the robots can move to a destination to complete the assigned task without colliding with each other; a traffic control step of generating a traffic signal to control the entry order and movement direction of at least one of the robots at a waypoint node of an intersection; and

[0027] A communication step of communicating the above movement path and the above traffic signal to the robot is included.

[0028] Preferably, each robot that has received the above movement path can identify its location through a mounted sensor and recognize obstacles to move autonomously.

[0029] Preferably, the autonomous movement of the robot along the movement path is possible in an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone is characterized in that it does not include the waypoint node.

[0030] Preferably, in the autonomous driving zone, the robot is capable of autonomous movement according to preset right-hand traffic rules.

[0031] Preferably, the traffic signal includes information about the entry order and movement direction of at least one robot in a single-lane passage.

[0032] Preferably, the traffic control step includes a step of generating a movement order of at least one robot in the waypoint node in the form of a dependency graph, wherein the dependency graph represents each of a plurality of waypoint nodes that the at least one robot must pass through over time as a vertex, and represents a movement condition between robots for at least one waypoint node represented as a vertex as an edge.

[0033] Preferably, the path planning step includes a step of performing calculation of a movement path using a multi-agent path search (MAPF), and the objective function of the multi-agent path search (MAPF) is characterized in that it is a sum of costs of movement distances / times on the path of each robot or a maximum required time / distance of each robot.

[0034] Specific details of other embodiments are included in the detailed description and drawings.

[0035]

[0036] The semi-centralized robot fleet management system and management method of the present invention can realize optimization of multi-robot control by utilizing the advantages of both centralized and distributed control methods and minimizing their disadvantages.

[0037] The semi-centralized robot fleet management system and management method of the present invention prevents collisions or deadlocks by allowing robots to move along optimal paths while reducing the complexity of the system.

[0038] The semi-centralized robot fleet management system and management method of the present invention can be applied to various types of robots, including automatic guided vehicles (AGVs) and autonomous mobile robots (AMRs), and can also be applied to third-party robots with restricted access to internal application programming interfaces (APIs), enabling operation by simply designating the next waypoint node.

[0039] The semi-centralized robot fleet management system and management method of the present invention enable robots to effectively avoid obstacles even in an environment with people or other dynamic obstacles, thereby enabling robots to immediately avoid obstacles and perform tasks.

[0040] However, the effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

[0041]

[0042] FIG. 1 is a schematic diagram of a semi-centralized robot fleet management system according to one embodiment of the present invention.

[0043] FIG. 2 is a diagram illustrating an exemplary map utilized to operate robots in a semi-centralized robot fleet management system according to one embodiment of the present invention.

[0044] Figure 3 is a diagram illustrating an example of a dependency graph that expresses as edges the prerequisites that robots must check in order to move to each waypoint node.

[0045] FIG. 4 is a diagram illustrating the input and output of the multi-agent path search (MAPF) of the path planning module of the present invention.

[0046] Figure 5 is a table summarizing the features of the semi-centralized control method of the present invention compared with the conventional centralized control and distributed control.

[0047] FIG. 6 is a flowchart illustrating a semi-centralized robot fleet management method according to one embodiment of the present invention.

[0048] FIG. 7 is a diagram illustrating an exemplary computing device that may implement a device and / or system according to various embodiments of the present invention.

[0049]

[0050] The advantages and features of the present invention, and the methods for achieving them, will become clearer with reference to the embodiments described in detail below together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below and may be implemented in various different forms. These embodiments are provided only to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Like reference numerals designate like elements throughout the specification.

[0051] Embodiments described herein will be described with reference to cross-sectional and / or plan views, which are ideal illustrations of the present invention. In the drawings, the thicknesses of components are exaggerated for the purpose of effectively explaining the technical contents. Accordingly, the components illustrated in the drawings have a schematic nature, and the shapes of the components illustrated in the drawings are intended to illustrate specific forms of the components and are not intended to limit the scope of the invention. Although terms such as first, second, and third are used to describe various components in various embodiments of the present specification, these components should not be limited by such terms. These terms are used only to distinguish one component from another. The embodiments described and illustrated herein also include complementary embodiments thereof.

[0052] The terminology used herein is for the purpose of describing embodiments only and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components, steps, operations, and / or elements to the mentioned components, steps, operations, and / or elements.

[0053] Unless otherwise defined, all terms (including technical and scientific terms) used herein may be used in their common sense to those of ordinary skill in the art to which the present invention pertains. Furthermore, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0054] Hereinafter, with reference to the drawings, the concept of the present invention and embodiments thereof will be described in detail.

[0055] FIG. 1 is a schematic diagram of a semi-centralized robot fleet management system according to one embodiment of the present invention.

[0056] The semi-centralized robot fleet management system (100) of the present invention presents a hybrid semi-centralized control method that combines centralized and distributed control methods for efficient operation of multiple robots.

[0057] The semi-centralized robot fleet management system (100) of the present invention achieves optimal multi-robot control performance by taking advantage of the advantages of each of the centralized and distributed control methods and minimizing their disadvantages.

[0058] The semi-centralized robot fleet management system (100) of the present invention reduces system complexity while providing optimal movement paths, thereby preventing collisions and deadlocks between robots. In particular, it is compatible with various types of robots, including automated guided vehicles (AGVs) and autonomous mobile robots (AMRs), and can be effectively used in environments where people or other dynamic obstacles are present.

[0059] The semi-centralized robot fleet management system (100) of the present invention proposes a new type of robot control method that provides an optimal path to the robot and enables autonomous avoidance maneuvers of the robot in order to efficiently manage multiple autonomous mobile robots (AMRs).

[0060] A semi-centralized robot fleet management system (100) according to one embodiment of the present invention includes a task assignment module (110) that assigns a task to be performed to each of a plurality of robots, a path planning module (120) that calculates a movement path along which each robot can move to a destination to complete the assigned task without colliding with each other, a traffic control module (130) that generates a traffic signal for controlling the entry order and movement direction of at least one robot at a waypoint node of an intersection, and a communication interface (140) that communicates the movement path and traffic signal to the robots.

[0061] The task allocation module (110) of the semi-centralized robot fleet management system (100) of the present invention calculates and stores the optimal task execution order from the task list given to the robots (150).

[0062] When new tasks are added, the task allocation module (110) batch processes the added tasks and recalculates the optimal order.

[0063] When the robot (150) completes the assigned task, it requests the next new task from the semi-centralized robot fleet management system (100), and the semi-centralized robot fleet management system (100) assigns the next task to the robot (150).

[0064] The path planning module (120) of the semi-centralized robot fleet management system (100) of the present invention uses a multi-agent pathfinding (MAPF) algorithm to calculate an optimal path through which all robots can move to a destination without colliding with each other.

[0065] When the path planning module (120) receives a next task request from the robot (150), it designates the next destination of the robot (150), recalculates the paths of all robots, and stores them in the path table.

[0066] The traffic control module (130) of the semi-centralized robot fleet management system (100) of the present invention stores the movement order of the robots when passing a specific waypoint node in the form of a dependency graph based on the route table.

[0067] The traffic control module (130) extracts the prerequisites required to pass through each waypoint node on the planned route, as shown in FIG. 3, represents it as a dependency graph, and controls traffic using the dependency graph.

[0068] In the present invention, the robot is a mobile robot (150), including an automatic guided vehicle (AGV), an autonomous mobile robot (AMR), and an unmanned forklift (AGF: Automated Guided Forklift).

[0069] The mobile robot (150) of the present invention includes a communication interface (160) that communicates with the communication interface (140) of the semi-centralized robot fleet management system (100), a robot manager (170) that controls mode conversion (e.g., from a centralized mode to a distributed mode or from a distributed mode to a centralized mode) and manages robot operations, and a robot autonomous driving module (180) that identifies a location through a sensor such as LiDAR, recognizes obstacles, and performs autonomous driving.

[0070] In one embodiment, each robot (150) receives a movement path, determines its location through equipped sensors, and recognizes obstacles to enable autonomous movement.

[0071] In one embodiment, in an autonomous driving zone, a robot (150) is capable of autonomous movement according to preset right-hand traffic rules.

[0072] In one embodiment, the autonomous movement of the robot along the movement path is possible in an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone does not include a waypoint node (220 in FIG. 2).

[0073] In one embodiment, the traffic signal includes information regarding the entry order and direction of movement of at least one robot in a single lane passage.

[0074] Robots move in a distributed manner in spaces outside of designated nodes. These spaces are controlled differently, with two-lane or more (capable of transporting two or more robots) and single-lane corridors.

[0075] In conventional centralized systems, robots continuously transmit location and status information to the fleet management system, and the fleet management system continuously transmits movement paths and control signals to the robots.

[0076] However, in the present invention, the robot (150) requests the semi-centralized robot fleet management system (100) for task assignment, destination setting, approval for passage through a specific waypoint, etc., and the semi-centralized robot fleet management system (100) is operated in a manner that provides a response thereto.

[0077] The semi-centralized robot fleet management system (100) of the present invention only needs to respond to requests from robots (150), so there is no need for a continuous network connection, and network delay or bandwidth issues can be resolved.

[0078] In addition, the semi-centralized robot fleet management system (100) of the present invention can be implemented by simply adding a communication interface (160) and a robot manager module (170) to a robot with a built-in autonomous driving function in order to link with a robot (150). Therefore, the semi-centralized robot fleet management system (100) of the present invention can be linked with various types of robots.

[0079]

[0080] FIG. 2 is a diagram illustrating an exemplary map utilized to operate robots in a semi-centralized robot fleet management system according to one embodiment of the present invention.

[0081] The present invention provides a robot fleet management system (FMS) capable of efficiently managing multiple autonomous mobile robots (AMRs) when people and robots collaborate in logistics and manufacturing sites.

[0082] The semi-centralized robot fleet management system (100) of the present invention proposes a hybrid semi-centralized control method that combines centralized and distributed control methods to optimize robot operation and increase efficiency. The semi-centralized robot fleet management system (100) of the present invention determines optimal paths for robots while reducing system complexity, thereby controlling them to operate smoothly without collisions or deadlocks.

[0083] Additionally, the automatic avoidance function of autonomous mobile robots (AMRs) supports effective operation of robots even in dynamic environments that require cooperation with workers.

[0084] In the present invention, the robot (150) is capable of autonomous movement within a general node (210) on the map of FIG. 2. Neighboring nodes are connected by edges to form a graph, and task allocation and path planning are performed based on this graph.

[0085] Specific nodes at intersections on the map are designated as waypoint nodes (220), and traffic control is implemented at the waypoint nodes (220). The semi-centralized robot fleet management system (100) of the present invention centrally manages robots (150) at the waypoint nodes (220).

[0086] The semi-centralized robot fleet management system (100) of the present invention allows robots (150) to operate independently in a distributed control manner in a general node (210).

[0087] In the map of Fig. 2, the area where the general node (210) is located is called an autonomous driving zone, and the robots move autonomously in this area while avoiding each other.

[0088] The intersection area with the waypoint node (220) is called a centralized control area, and when the robot (150) arrives at the waypoint node (220), it checks whether the next movement is possible and moves to the next waypoint node.

[0089] Traffic control at the waypoint node (220) functions as a traffic light, and the traffic control module (130) generates traffic signals to optimize the movement order of the robot.

[0090]

[0091] Figure 3 is a diagram illustrating an example of a dependency graph that expresses as edges the prerequisites that robots must check in order to move to each waypoint node.

[0092] The traffic control module (130) stores the movement order of at least one robot in the waypoint node in the form of a dependency graph, and the dependency graph represents each of a plurality of waypoint nodes that at least one robot must pass through over time as a vertex, and expresses movement conditions between robots for at least one waypoint node represented as a vertex as an edge.

[0093] The traffic control module (130) extracts the prerequisites required to pass through each waypoint node on the planned route and represents them as a dependency graph, as illustrated in FIG. 3.

[0094] The traffic control module (130) controls traffic using a dependency graph.

[0095] To create a dependency graph along the planned path, the locations that the robot must pass through at each time step are set as vertices.

[0096] If another robot must visit a specific node before moving to that node, the relationship is connected with an edge (340).

[0097] Traffic control checks the prerequisites in the dependency graph in real time and classifies each node into (1) movement complete, (2) movement possible, and (3) movement impossible based on the robot's current location information.

[0098] By continuously receiving location information from robots, the system updates information about possible waypoints for the robots to move to. When a robot reaches a waypoint, it sends a transit request to the next waypoint, indicating whether it can move to the next one. The dependency graph is updated to inform the robot of its transit possibility. The robot's path is also communicated along with the transit possibility.

[0099] In one embodiment, in the case of a two-lane or more roadway, collisions can be prevented by operating with standards such as right-hand traffic rules when robots move in different directions.

[0100] For example, robots can follow right-of-way rules and avoid dynamic obstacles using avoidance techniques like velocity obstacles (VO). Robots may arrive at waypoints out of the planned order, requiring reconnections in the dependency graph to reestablish dependencies.

[0101] If a cycle occurs in the reset graph, a deadlock may occur, so the original movement order is followed. If robots arrive out of order near a waypoint node, they wait near that node and, based on priority, may move ahead of waiting robots.

[0102] In one embodiment, robots cannot cross paths in a single-lane corridor, and all robots must move in only one direction. The entry order and movement direction of the robots are predetermined based on an optimized path plan, and the traffic control module (130) adjusts the robots accordingly. This eliminates the possibility of robots entering from opposite directions or the occurrence of deadlocks. Therefore, if one robot waits at a waypoint node, subsequent robots wait in that order and pass through the corridor in sequence.

[0103] FIG. 4 is a diagram illustrating the input and output of the multi-agent path search (MAPF) of the path planning module of the present invention.

[0104] In one embodiment of the present invention, the calculation of the movement path by the path planning module (120) is performed using multi-agent path search (MAPF). The objective function of multi-agent path search (MAPF) is the sum of the movement distance / time on the path of each robot (sum of costs) or the maximum time / distance required for each robot (makespan).

[0105] Multi-Agent Path Finding (MAPF) is a problem of finding a collision-free path in space and time for multiple robots with a starting point and a destination. Traditional MAPF defines the problem as a search in a graph, with inputs and outputs represented as shown in Figure 4. Based on this definition, there are several methods for solving MAPF.

[0106] Representative methods for solving multi-agent path finding (MAPF) problems include the Priority Planning (PP) method, which sequentially searches paths of previously searched robots using obstacles as the paths of robots based on priorities among robots; the Independent Detection (ID) method, which groups robots that collide in their paths and performs A* search on each individual group; and the Conflict Based Search (CBS) method, which searches until an optimal solution is derived that avoids sections where collisions occur in the middle based on the paths of each robot.

[0107] Although there are differences depending on the multi-agent path search (MAPF) method, optimal or near-optimal paths can be found depending on the desired objective function. The objective function is typically the sum of the distances and times traveled by all robots along the path (sum of costs) or the maximum time and distance traveled by all robots (makespan).

[0108] Figure 5 is a table summarizing the features of the semi-centralized control method of the present invention compared with the conventional centralized control and distributed control.

[0109] As illustrated in FIG. 5, the semi-centralized robot fleet management method of the present invention enables optimization, deadlock prevention, large-scale robot expansion, and dynamic environment response, has no communication bottleneck, is compatible with heterogeneous systems, and is applicable to automatic guided vehicles (AGVs) and autonomous mobile robots (AMRs).

[0110] FIG. 6 is a flowchart illustrating a semi-centralized robot fleet management method according to one embodiment of the present invention.

[0111] A semi-centralized robot fleet management method according to one embodiment of the present invention includes a task assignment step (S610) of assigning a task to be performed to each of a plurality of robots, a path planning step (S620) of calculating a movement path along which each robot can move to a destination to complete the assigned task without colliding with each other, a traffic control step (S630) of generating a traffic signal for controlling the entry order and movement direction of at least one robot at a waypoint node of an intersection, and a communication step (S640) of communicating the movement path and traffic signal to the robots.

[0112] In one embodiment, each robot that receives a movement path can determine its location through equipped sensors and recognize obstacles to move autonomously.

[0113] In one embodiment, the autonomous movement of the robot along the movement path is possible in an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone does not include a waypoint node.

[0114] In one embodiment, the robot is capable of autonomously moving in an autonomous driving zone according to preset right-hand traffic rules.

[0115] In one embodiment, the traffic signal includes information regarding the entry order and direction of movement of at least one robot in a single lane passage.

[0116] In one embodiment, the traffic control step includes a step of generating a movement order of at least one robot in a waypoint node in the form of a dependency graph, wherein the dependency graph represents each of a plurality of waypoint nodes that the at least one robot must pass through over time as a vertex, and represents a movement condition between the robots for at least one waypoint node represented as a vertex as an edge.

[0117] In one embodiment, the path planning step includes performing a calculation of a movement path using a multi-agent path search (MAPF), wherein an objective function of the multi-agent path search (MAPF) is characterized in that the sum of the distances / times traveled along the path of each robot (sum of costs) or the maximum time / distance required for each robot (makespan).

[0118] FIG. 7 is a diagram illustrating an exemplary computing device that may implement a device and / or system according to various embodiments of the present invention.

[0119] An exemplary computing device (700) capable of implementing devices according to some embodiments of the present disclosure will now be described in more detail with reference to FIG. 7.

[0120] A computing device (700) may include one or more processors (710), a bus (750), a communication interface (770), a memory (730) for loading a computer program (791) executed by the processor (710), and a storage (790) for storing the computer program (791). However, only components related to the embodiment of the present disclosure are illustrated in FIG. 7.

[0121] Accordingly, a person skilled in the art will appreciate that the present disclosure may include other general components in addition to the components illustrated in FIG. 7.

[0122] The processor (710) controls the overall operation of each component of the computing device (700). The processor (710) may include a central processing unit (CPU), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphic processing unit (GPU), or any other form of processor (710) well known in the art of the present disclosure. In addition, the processor (710) may perform operations for at least one application or program for executing a method according to embodiments of the present disclosure. The computing device (700) may include one or more processors (710). The computing device (700) may refer to artificial intelligence (AI).

[0123] The memory (730) stores various data, commands, and / or information. The memory (730) can load one or more programs (791) from the storage (790) to execute methods according to embodiments of the present disclosure. The memory (730) may be implemented as volatile memory, such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0124] The bus (750) provides communication between components of the computing device (700). The bus (750) may be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0125] The communication interface (770) supports wired and wireless Internet communication of the computing device (700). Furthermore, the communication interface (770) may support various communication methods other than Internet communication. To this end, the communication interface (770) may be configured to include a communication module well known in the technical field of the present disclosure.

[0126] According to some embodiments, the communication interface (770) may be omitted.

[0127] Storage (790) can non-temporarily store one or more programs (791) and various data.

[0128] Storage (790) may be configured to include non-volatile memory such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which the present disclosure pertains.

[0129] The computer program (791) may include one or more instructions that, when loaded into the memory (730), cause the processor (710) to perform methods / operations according to various embodiments of the present disclosure. That is, the processor (710) may perform methods / operations according to various embodiments of the present disclosure by executing one or more instructions.

[0130] Although the preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and various modifications may be made by a person skilled in the art without departing from the gist of the present invention as claimed in the claims. Furthermore, such modifications should not be understood individually from the technical idea or prospect of the present invention.

Claims

1. A task assignment module that assigns tasks to be performed to each of multiple robots; A path planning module that calculates a movement path along which each of the above robots can move to a destination to complete the assigned task without colliding with each other; A traffic control module that generates a traffic signal for controlling the entry order and movement direction of at least one robot at a waypoint node of an intersection; and A semi-centralized robot fleet management system, comprising a communication interface for communicating the movement path and the traffic signal to the robot.

2. In claim 1, A semi-centralized robot fleet management system in which each robot that receives the above movement path can identify its location through a mounted sensor, recognize obstacles, and move autonomously.

3. In claim 2, A semi-centralized robot fleet management system, characterized in that the autonomous movement of the robot along the above movement path is an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone does not include the waypoint node.

4. In claim 3, A semi-centralized robot fleet management system in which the robot can move autonomously according to preset right-hand traffic rules in the autonomous driving zone.

5. In claim 1, A semi-centralized robot fleet management system, wherein the above traffic signal includes information about the entry order and movement direction of at least one robot in a first-lane passage.

6. In claim 1, A semi-centralized robot fleet management system in which the traffic control module stores the movement order of at least one robot in the waypoint node in the form of a dependency graph, and the dependency graph represents each of a plurality of waypoint nodes that the at least one robot must pass through over time as a vertex, and represents movement conditions between robots for at least one waypoint node represented as a vertex as an edge.

7. In claim 1, A semi-centralized robot fleet management system, characterized in that the calculation of the movement path by the above-mentioned path planning module is performed using multi-agent path search (MAPF), and the objective function of the multi-agent path search (MAPF) is the sum of the movement distance / time on the path of each robot (sum of costs) or the maximum required time / distance (makespan) of each robot.

8. Task assignment step for assigning tasks to be performed to each of multiple robots; A path planning step for calculating a movement path along which each of the above robots can move to a destination to complete the assigned task without colliding with each other; A traffic control step of generating a traffic signal for controlling the entry order and movement direction of at least one robot at a waypoint node of an intersection; and A semi-centralized robot fleet management method, comprising a communication step of communicating the movement path and the traffic signal to the robot.

9. In claim 8, A semi-centralized robot fleet management method in which each robot that receives the above movement path can identify its location through a mounted sensor, recognize obstacles, and move autonomously.

10. In claim 9, A semi-centralized robot fleet management method, characterized in that the autonomous movement of the robot along the above movement path is an autonomous driving zone with a passageway of two or more lanes, and the autonomous driving zone does not include the waypoint node.

11. In claim 10, A semi-centralized robot fleet management method in which the robot can move autonomously according to preset right-hand traffic rules in the autonomous driving zone.

12. In claim 8, A semi-centralized robot fleet management method, wherein the above traffic signal includes information about the entry order and movement direction of at least one robot in a first-lane passage.

13. In claim 8, A semi-centralized robot fleet management method, wherein the traffic control step includes a step of generating a movement order of at least one robot in the waypoint node in the form of a dependency graph, wherein the dependency graph represents each of a plurality of waypoint nodes that the at least one robot must pass through over time as a vertex, and represents movement conditions between robots for at least one waypoint node represented as a vertex as an edge.

14. In claim 8, A semi-centralized robot fleet management method, characterized in that the above path planning step includes a step of calculating a movement path using a multi-agent path search (MAPF), and the objective function of the multi-agent path search (MAPF) is a sum of the movement distance / time on the path of each robot (sum of costs) or a maximum required time / distance (makespan) of each robot.

Images