Multi-robot task allocation method and system based on local area network instruction control

Abstract

The invention provides a multi-robot task allocation method and system based on local area network instruction control, and the method specifically comprises the steps: building a local area network hierarchical control structure, an upper-layer task scheduling server and a lower-layer robot group control node, and achieving task instruction transmission based on a user-defined lightweight local area network communication protocol; when the task scheduling server distributes tasks, the task scheduling server decomposes the whole task into a plurality of instruction segments which are independently executed and caches the instruction segments to the target robot node; in a task execution process, constructing a task communication topological graph, and dynamically adjusting a local area network communication path through a task topology sensing algorithm; when signal attenuation caused by construction obstacles or metal shielding is detected, a communication path is automatically re-planned; and based on task execution feedback information returned by the robot nodes, a task scheduling strategy and a communication path are dynamically updated, so that the whole system can adaptively optimize a multi-robot task allocation process according to the change of a construction environment.

Description

Technical Field

[0001] This invention relates to the field of local area network (LAN) command control technology, and mainly to a multi-robot task allocation method and system based on LAN command control. Background Technology

[0002] With the increasing automation at construction sites, multi-robot systems are widely used in tasks such as material handling, welding, pouring, and inspection. However, existing multi-robot task allocation methods still have some shortcomings.

[0003] In existing technologies, the complex environment of construction sites makes local area network communication susceptible to the effects of metal structures, building materials, and signal attenuation, resulting in unstable transmission of task instructions. Central scheduling relies on fixed topology or repeated broadcasting, making it difficult to guarantee continuous task execution.

[0004] Traditional task allocation is mostly based on static rules or real-time scheduling, which only considers robot capabilities and task requirements. It lacks comprehensive analysis of historical execution records, execution efficiency, energy consumption and network status, resulting in insufficient allocation efficiency and robustness.

[0005] Furthermore, existing methods typically do not fully utilize the spatial and temporal constraints of tasks, nor do they take into account the decay of historical experience over time and space, as well as network topology status, thus failing to achieve efficient and adaptive task allocation in dynamic construction environments. Summary of the Invention

[0006] To address the above shortcomings, this invention provides a method for adaptively allocating multi-robot tasks by combining local area network topology, robot historical task records, and task space information, thereby improving task execution efficiency and collaborative stability. According to a first aspect of this invention, a multi-robot task allocation method based on local area network command control is proposed, the specific steps of which include: A local area network hierarchical control structure is established, which includes an upper-layer task scheduling server and a lower-layer robot group control node, wherein each robot node has a local autonomous control module; After the control structure is established, task instructions are transmitted based on a custom lightweight local area network communication protocol. The communication protocol includes a robot node fast registration and identity recognition mechanism, a serverless communication mechanism, and a task tokenization mechanism. When distributing tasks, the task scheduling server breaks down the overall task into several independently executable instruction fragments and caches them in the target robot nodes. When network latency or connection interruption is detected, each robot node executes the delayed task according to the locally cached instruction fragments. During task execution, a task communication topology map is constructed based on the spatial layout information of the construction site and the real-time position information of the robot, and the local area network communication path is dynamically adjusted through the task topology perception algorithm; when construction obstacles or metal obstructions are detected that cause signal attenuation, the communication path is automatically replanned. Based on the task execution feedback information returned by the robot nodes, the task scheduling strategy and communication path are dynamically updated, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

[0007] Furthermore, the local autonomous control module continues to perform local task collaboration based on cached instruction fragments when the local area network connection is interrupted.

[0008] Furthermore, the specific steps for implementing task instruction transmission based on the custom lightweight LAN communication protocol include: When a new robot node connects to the construction site's local area network, the node's communication module automatically broadcasts a registration request data packet. The registration request data packet includes the node's unique identifier, task execution capability description information, and an encrypted verification token. After receiving the registration request data packet, the task scheduling server or a registered node in the local area network authenticates the node according to a preset authentication algorithm and assigns a local temporary address and communication channel number to the node, thereby enabling the node to quickly connect and confirm its identity. After node registration is completed, the communication protocol adopts a distributed message middleware architecture, and establishes a direct communication link between robot nodes through a serverless communication mechanism. Each robot node is equipped with a message sending and receiving buffer queue, and packages and distributes task data according to task type, priority and signal quality. When the task scheduling server generates a new task instruction, it encapsulates the task information into a task token containing a task number, execution priority, task spatial location, resource requirement parameters, and validity period field, and publishes it in the local area network in the form of a broadcast data packet. After receiving the broadcast packet, each robot node calculates its suitability score based on its own task capability description information, current position, and remaining energy parameters, and feeds back the response data packet to the task scheduling server.

[0009] When multiple robot nodes respond to the same task simultaneously, the communication protocol determines the execution node through a task token arbitration rule. The arbitration rule comprehensively considers the signal strength, response delay, adaptability score, remaining energy, and communication link stability of each node, and calculates a comprehensive score through a weighted scoring algorithm to select the main execution node. The remaining nodes automatically enter the candidate or auxiliary state. When the main execution node goes offline or malfunctions during task execution, the node with the second highest score automatically takes over based on the local area network message middleware.

[0010] Furthermore, the construction of the task communication topology graph and the dynamic adjustment of the local area network communication path through the task topology awareness algorithm specifically include: A weighted communication topology is constructed based on the spatial layout information, obstacle distribution information, and real-time position information of each robot node at the construction site. Each node includes coordinates, communication capability, energy status, and role attributes. The weight of each communication edge is determined by a weighted combination of link delay, packet loss rate, signal strength, link stability, obstacle penetration penalty factor, and energy consumption parameters. The link quality estimation algorithm is used to perform exponential weighted moving average smoothing on the signal strength, signal-to-noise ratio, round-trip delay and packet loss rate of each side, and the link stability index is calculated within the sliding time window. The multi-path shortest path algorithm is executed based on the weighted communication topology graph to select the main path and backup path between the task start point and the target node based on the comprehensive cost function. When a heartbeat signal loss, signal attenuation, or link disconnection is detected, a candidate relay node is selected through local neighbor nodes to quickly replace the route, or a local area network rediscovery and topology reconstruction process is triggered to update the communication path; and after the path switch, the routing field in the task token is updated to achieve continuous transmission of task data and link self-recovery.

[0011] Furthermore, the automatic replanning of the communication path when construction obstacles or metal obstructions are detected causing signal attenuation specifically includes: An obstacle feature database is established based on a three-dimensional spatial model of the construction site. The database records the spatial coordinates, boundary range, and material electromagnetic property parameters of each obstacle. When the link quality estimation algorithm detects that the signal strength of any communication link is lower than the preset threshold or the signal-to-noise ratio decrease rate exceeds the threshold, the obstacle association analysis module is triggered. The spatial intersection relationship between the communication path and the obstacle is determined by ray tracing or line segment penetration calculation method, and the obstacle penetration penalty value is calculated based on the material absorption coefficient and penetration distance. The penalty value is injected into the edge weights of the communication topology graph. The routing planning module calls the weighted shortest path algorithm based on obstacle constraints to recalculate the feasible communication path and selects the set of edges with high link stability and low penetration penalty to form a new main path and backup path. When changes in the construction site space or robot movement cause the obstacle occlusion pattern to be updated, the system automatically performs incremental updates to the topology map to achieve dynamic reconstruction of the communication link.

[0012] Furthermore, by utilizing the historical task execution records accumulated in the local area network, a lightweight allocation model is trained for allocation and prediction. The lightweight allocation model directly sorts the tasks based on probability results and selects the robot to be executed according to the sorting results.

[0013] Furthermore, the calculation formula for the lightweight allocation model is as follows: ; ; in, This represents the i-th candidate robot node. This indicates a new task to be assigned. Represents robots A score indicating suitability for the new task. Indicates the time decay factor. The similarity is represented by k, where k represents the k-th historical task. Indicates network topology coupling, robot The topological distance weighted average to task-related nodes. Represents the sensitivity coefficient of task feature similarity. This represents the squared Euclidean distance between the feature vectors of the new task and the historical task.

[0014] According to a second aspect of the present invention, a multi-robot task allocation system for construction sites based on local area network command control is proposed, specifically comprising: A local area network (LAN) command unit is configured to establish a hierarchical LAN control structure, which includes an upper-layer task scheduling server and lower-layer robot group control nodes, wherein each robot node has a local autonomous control module. The instruction protocol unit is configured to transmit task instructions based on a custom lightweight local area network communication protocol after the control structure is established. The communication protocol includes a robot node fast registration and identity recognition mechanism, a serverless communication mechanism, and a task tokenization mechanism. The instruction caching and delayed execution unit is configured to decompose the overall task into several independently executable instruction fragments and cache them to the target robot node when the task scheduling server distributes tasks. When network latency or connection interruption is detected, each robot node executes the delayed task according to the locally cached instruction fragments. The task topology adaptive routing unit is configured to construct a task communication topology map based on the spatial layout information of the construction site and the real-time position information of the robot during task execution, and dynamically adjust the local area network communication path through the task topology perception algorithm; when construction obstacles or metal obstructions are detected that cause signal attenuation, the communication path is automatically replanned. The task execution feedback unit is configured to dynamically update the task scheduling strategy and communication path based on the task execution feedback information returned by the robot nodes, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

[0015] According to a third aspect of the present invention, a computer program product is provided, on which one or more computer programs are stored, which, when executed by a computer processor, implement the method described above.

[0016] The above-described one or more technical solutions in the embodiments of this application have at least one of the following technical effects: 1. Significantly enhanced task continuity and self-healing ability: Through instruction fragment caching and delayed execution mechanisms, as well as task topology awareness algorithms, this invention can ensure local autonomous cooperation of the robot and dynamic replanning of communication paths in the event of local area network link interruption or signal attenuation, thus achieving uninterrupted task operation.

[0017] 2. Enhanced intelligence and adaptability of allocation decisions: This invention introduces a spatiotemporal-network coupled prediction model based on historical task execution records, which enables robot adaptability scoring to consider historical experience, task characteristics, spatial location, and network link reliability simultaneously. It can dynamically select the optimal execution robot according to the real-time status of the construction site, thereby improving task completion efficiency and reliability.

[0018] 3. Communication robustness and topology adaptability optimization: This invention achieves dynamic updating of link weights through task topology awareness algorithm and topology coupling factor. Combined with local relay and proxy mechanism, it can automatically cope with signal attenuation caused by metal structures and obstacles, and realize self-healing of local area network communication links.

[0019] 4. Comprehensive improvement in overall system efficiency: While ensuring task safety and stability, this invention can reduce the central scheduling load, reduce network broadcast redundancy, and achieve load balancing and energy optimization for multi-robot collaboration, thereby significantly improving the overall task execution efficiency of the multi-robot system on the construction site.

[0020] This invention is the first to integrate historical task spatiotemporal decay, task feature similarity, and local area network topology coupling into task allocation decision-making, and combines it with instruction fragment caching, delayed execution, and dynamic self-healing routing mechanisms to achieve efficient, continuous, and adaptive task allocation for multi-robot systems in dynamic and complex construction environments. Attached Figure Description

[0021] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated in and constitute a part of this specification. The drawings illustrate embodiments and, together with the description, serve to explain the principles of the invention. Other embodiments and many anticipated advantages of the embodiments will be readily recognized as they become better understood through reference to the following detailed description. Elements in the drawings are not necessarily to scale. The same reference numerals refer to corresponding similar parts.

[0022] Figure 1A schematic diagram of the framework of a multi-robot task allocation method based on local area network command control according to an embodiment of the present invention is shown.

[0023] Figure 2 A schematic diagram illustrating the communication protocol and fault-tolerant task execution flow according to an embodiment of the present invention is shown.

[0024] Figure 3 A schematic diagram of an initial communication topology according to an embodiment of the present invention is shown.

[0025] Figure 4 A schematic diagram of a dynamically adjusted communication topology according to an embodiment of the present invention is shown.

[0026] Figure 5 A schematic flowchart of a closed-loop adaptive optimization method according to an embodiment of the present invention is shown.

[0027] Figure 6 This is a schematic diagram of the structure of a computer system suitable for implementing the electronic devices of the present application embodiments. Detailed Implementation

[0028] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0029] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0030] Figure 1 A schematic diagram of the framework of a multi-robot task allocation method based on local area network command control according to an embodiment of the present invention is shown, such as... Figure 1 As shown: S1. Establish a local area network hierarchical control structure, which includes an upper-layer task scheduling server for generating and distributing task instructions; and lower-layer robot group control nodes for receiving the task instructions and executing the corresponding tasks. Each robot node is equipped with a local autonomous control module, which can perform local task collaboration based on cached instruction fragments when the local area network connection is interrupted.

[0031] By establishing a hierarchical local area network (LAN) control structure, task scheduling at the construction site achieves a combination of centralized management and distributed execution. The upper-level task scheduling server is responsible for global task planning and instruction distribution, while the lower-level robot swarm control nodes possess local autonomy, enabling them to independently complete local task collaboration based on cached instruction fragments even in the event of network interruptions or signal attenuation. This design significantly improves the system's task continuity, communication robustness, and autonomous collaboration capabilities in complex construction environments, avoiding task interruptions caused by network fluctuations and achieving stable and efficient execution of multi-robot collaborative operations.

[0032] S2. After the control structure is established, as follows: Figure 2 As shown, task instruction transmission is achieved based on a custom lightweight local area network communication protocol. The communication protocol includes a robot node fast registration and identity recognition mechanism, a serverless communication mechanism, and a task tokenization mechanism to enable rapid access, task broadcasting, and arbitration among multiple robots.

[0033] The specific steps for transmitting task instructions based on the custom lightweight LAN communication protocol include: S2.1, Node fast access mechanism; When a new robotic device enters the construction site, its communication module automatically broadcasts a registration request data packet in the local area network. The data packet contains the device's unique identifier, task capability description information, and a security verification token. Upon receiving the request, the task scheduling server or other registered nodes within the local area network return registration confirmation information according to a preset authentication algorithm and assign a local temporary address and communication channel number to the node. In this way, robot nodes can complete network access and identity verification within seconds without human intervention, enabling rapid deployment.

[0034] S2.2 Serverless communication mechanism; The communication protocol adopts a distributed message middleware structure and transmits messages in a peer-to-peer manner within a local area network. Each robot node has a message sending and receiving cache queue, which can package and distribute data according to task type and priority; When the task scheduling server is offline, robot nodes can establish direct communication links based on the local area network broadcast discovery mechanism to achieve the sharing and transmission of task information, thereby ensuring that the system still has communication capabilities when there is no central node.

[0035] S2.3, Task broadcasting mechanism; After generating a task instruction, the task scheduling server encapsulates the task information into a task broadcast packet in a tokenized format. The task token contains the task ID, execution priority, spatial location information, resource requirements, and validity period. The server broadcasts the task packet over the local area network. Each robot node calculates its suitability score based on its own capability description and current position, and returns the result in the form of a response data packet. If the server goes offline, the node with the highest communication signal quality will temporarily act as the broadcast proxy to ensure that the task information is reliably disseminated within the local area network.

[0036] S2.4, Task arbitration mechanism; When multiple robot nodes respond to the same task simultaneously, the protocol determines the final execution node through task token arbitration rules; The arbitration rules comprehensively consider node signal strength, response delay, task adaptability, and remaining energy parameters, and use a weighted scoring algorithm to calculate the comprehensive value. The node with the highest final score gains the right to execute the task, while the remaining nodes automatically enter the candidate or auxiliary state and automatically take over if the task execution fails.

[0037] S2.5 Communication status maintenance and self-recovery; The protocol includes a periodic heartbeat detection mechanism to monitor node connection status and signal quality. When a node is detected to be disconnected or the link is weakened, the system automatically triggers the local area network rediscovery process to rebuild the communication link and restore task data transmission, ensuring the continuous stability of multi-robot collaboration.

[0038] S3. When the task scheduling server distributes tasks, it decomposes the overall task into several independently executable instruction fragments and caches them in the target robot node. When network latency or connection interruption is detected, each robot node executes the delayed task according to the locally cached instruction fragments. In actual construction sites, local area network signals are often interfered with by steel bars, formwork, metal equipment, etc., and communication links are prone to temporary interruptions. Once the traditional centralized control system loses connection, the robot will stop working and wait for instructions, causing work interruption.

[0039] This invention enables robots to autonomously execute some tasks based on cached instructions even when they lose real-time connectivity, thereby achieving the ability to "operate offline". Even if there is a partial network interruption, the task can still proceed smoothly, avoiding production stoppage.

[0040] S4. During task execution, a task communication topology map is constructed based on the spatial layout information of the construction site and the robot's real-time position information. The local area network communication path is dynamically adjusted using a task topology perception algorithm. When construction obstacles or metal obstructions cause signal attenuation, the communication path is automatically replanned. In this embodiment, for example... Figure 3 As shown, construct the initial topology graph, as follows: Figure 4 As shown, the communication topology is dynamically adjusted using a task topology awareness algorithm.

[0041] The specific steps for constructing the task communication topology map and dynamically adjusting the local area network communication path using the task topology awareness algorithm include: A weighted communication topology is constructed based on the spatial layout information, obstacle distribution information, and real-time position information of each robot node at the construction site. Each node includes coordinates, communication capability, energy status, and role attributes. The weight of each communication edge is determined by a weighted combination of link delay, packet loss rate, signal strength, link stability, obstacle penetration penalty factor, and energy consumption parameters. The link quality estimation algorithm is used to perform exponential weighted moving average smoothing on the signal strength, signal-to-noise ratio, round-trip delay and packet loss rate of each side, and the link stability index is calculated within the sliding time window. An improved multi-path shortest path algorithm is executed based on the weighted topology graph. The main path and backup path are selected between the task start point and the target node based on a comprehensive cost function, which comprehensively considers latency cost, packet loss cost, stability cost, obstacle penalty and energy cost. When a heartbeat signal loss, signal attenuation, or link disconnection is detected, a candidate relay node is selected through local neighbor nodes to quickly replace the route, or a local area network rediscovery and topology reconstruction process is triggered to update the communication path; and after the path switch, the routing field in the task token is updated to achieve continuous transmission of task data and link self-recovery.

[0042] The obstacle penetration penalty factor is a mathematical quantity used to quantitatively penalize links affected by obstacles, allowing the system to automatically avoid signal-blocked areas or high-loss paths when calculating the optimal communication path or task allocation weights.

[0043] In a specific preferred embodiment, an exponential penalty model can be used: ,in, , and This represents an empirical parameter used to adjust the penalty sensitivity. The mathematical quantification of the penalty factor, when the communication link is completely unobstructed. , The thickness of the obstacle at position (i,j) is represented. Indicates the material's absorbency. This represents the propagation direction effect, and serves as a direction penalty coefficient. Indicates the angle of incidence of the signal.

[0044] When construction obstacles or metal obstructions are detected that cause signal attenuation, the communication path is automatically replanned. Specifically, this includes: An obstacle feature database is established based on a three-dimensional spatial model of the construction site. The database records the spatial coordinates, boundary range, and material electromagnetic property parameters of each obstacle. When the link quality estimation algorithm detects that the signal strength of any communication link is lower than the preset threshold or the signal-to-noise ratio decrease rate exceeds the threshold, the obstacle association analysis module is triggered. The spatial intersection relationship between the communication path and the obstacle is determined by ray tracing or line segment penetration calculation method, and the obstacle penetration penalty value is calculated based on the material absorption coefficient and penetration distance. The penalty value is injected into the edge weights of the communication topology graph. The routing planning module calls the weighted shortest path algorithm based on obstacle constraints to recalculate the feasible communication path and selects the set of edges with high link stability and low penetration penalty to form a new main path and backup path. When changes in the construction site space or robot movement cause the obstacle occlusion pattern to be updated, the system automatically performs incremental updates to the topology map to achieve dynamic reconstruction of the communication link.

[0045] S5. Based on the task execution feedback information returned by the robot nodes, the task scheduling strategy and communication path are dynamically updated, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

[0046] Using the historical task execution records accumulated in the local area network, a lightweight allocation model is trained for allocation and prediction. The lightweight allocation model directly sorts the tasks based on probability results and selects the robot to be executed according to the sorting results.

[0047] The lightweight allocation model of this invention focuses on mapping the robot's historical task execution, local area network topology state, and task spatial location to graph structure features, forming graph embedding and local area network memory weighting.

[0048] A spatiotemporal-network coupling factor is introduced to dynamically adjust the task fit score, including: the decay of the robot's historical performance over time, the similarity between the current task space and the historical task space, and the influence of the current local area network link topology.

[0049] The output fitness score is not just a single-value score, but a probability distribution with network fitness, which can be directly used for multi-robot task allocation.

[0050] Specifically, the calculation formula for the lightweight allocation model is as follows: ; ; in, This represents the i-th candidate robot node. This indicates a new task to be assigned. Represents robots The suitability score for the new task.

[0051] This represents the time decay factor, and its time decay function is: , >0, where Indicates the current time. Indicates the time when a historical task was completed.

[0052] Spatial similarity is represented by the function: .

[0053] k represents the k-th historical task. Indicates network topology coupling, robot The topological distance weighted average to task-related nodes. Represents the sensitivity coefficient of task feature similarity. Indicates a new task With historical mission The squared Euclidean distance between the eigenvectors.

[0054] Furthermore, such as Figure 5 The flowchart of the closed-loop adaptive optimization of the present invention is shown. After the entire system converges, the task scheduler only transmits the change amount relative to the previous state, realizing the differential instruction mechanism and reducing the system burden.

[0055] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing electronic devices according to embodiments of the present application. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0056] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0057] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a liquid crystal display (LCD) and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card and a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0058] Specifically, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined in the methods of this application. It should be noted that the computer-readable storage medium of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. Program code contained on a computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0059] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0060] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0061] The modules described in the embodiments of this application can be implemented in software or in hardware.

[0062] In another aspect, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable storage medium carries one or more programs. When the electronic device executes the aforementioned one or more programs, the electronic device: establishes a hierarchical local area network control structure, with an upper-layer task scheduling server and lower-layer robot group control nodes, and implements task instruction transmission based on a custom lightweight local area network communication protocol; when distributing tasks, the task scheduling server decomposes the overall task into several independently executable instruction fragments and caches them to the target robot nodes; during task execution, it constructs a task communication topology graph and dynamically adjusts the local area network communication path through a task topology awareness algorithm; when construction obstacles or metal obstructions cause signal attenuation, it automatically replans the communication path; based on the task execution feedback information returned by the robot nodes, it dynamically updates the task scheduling strategy and communication path, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

[0063] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A construction site multi-robot task allocation method based on local area network instruction control, characterized in that, The specific steps include: A local area network hierarchical control structure is established, which includes an upper-layer task scheduling server and a lower-layer robot group control node, wherein each robot node has a local autonomous control module; After the control structure is established, task instructions are transmitted based on a custom lightweight local area network communication protocol. The communication protocol includes a robot node fast registration and identity recognition mechanism, a serverless communication mechanism, and a task tokenization mechanism. When distributing tasks, the task scheduling server breaks down the overall task into several independently executable instruction fragments and caches them in the target robot nodes. When network latency or connection interruption is detected, each robot node executes the delayed task according to the locally cached instruction fragments. During task execution, a task communication topology map is constructed based on the spatial layout information of the construction site and the real-time position information of the robot, and the local area network communication path is dynamically adjusted through the task topology perception algorithm; when construction obstacles or metal obstructions are detected that cause signal attenuation, the communication path is automatically replanned. Based on the task execution feedback information returned by the robot nodes, the task scheduling strategy and communication path are dynamically updated, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

2. The construction site multi-robot task allocation method based on local area network instruction control according to claim 1, characterized in that, The local autonomous control module continues to perform local task collaboration based on cached instruction fragments when the local area network connection is interrupted.

3. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 1, characterized in that, The specific steps for transmitting task instructions based on the custom lightweight LAN communication protocol include: When a new robot node connects to the construction site's local area network, the node's communication module automatically broadcasts a registration request data packet. The registration request data packet includes the node's unique identifier, task execution capability description information, and an encrypted verification token. After receiving the registration request data packet, the task scheduling server or a registered node in the local area network authenticates the node according to a preset authentication algorithm and assigns a local temporary address and communication channel number to the node, thereby enabling the node to quickly connect and confirm its identity. After node registration is completed, the communication protocol adopts a distributed message middleware architecture, and establishes a direct communication link between robot nodes through a serverless communication mechanism. Each robot node is equipped with a message sending and receiving buffer queue, and packages and distributes task data according to task type, priority and signal quality. When the task scheduling server generates a new task instruction, it encapsulates the task information into a task token containing a task number, execution priority, task spatial location, resource requirement parameters, and validity period field, and publishes it in the local area network in the form of a broadcast data packet. After receiving the broadcast packet, each robot node calculates its suitability score based on its own task capability description information, current position, and remaining energy parameters, and feeds back the response data packet to the task scheduling server.

4. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 3, characterized in that, When multiple robot nodes respond to the same task simultaneously, the communication protocol determines the execution node through a task token arbitration rule. The arbitration rule comprehensively considers the signal strength, response delay, adaptability score, remaining energy, and communication link stability of each node, and calculates a comprehensive score through a weighted scoring algorithm to select the main execution node. The remaining nodes automatically enter the candidate or auxiliary state. When the main execution node goes offline or malfunctions during task execution, the node with the second highest score automatically takes over based on the local area network message middleware.

5. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 1, characterized in that, The construction of the task communication topology map and the dynamic adjustment of the local area network communication path through the task topology awareness algorithm specifically include: A weighted communication topology is constructed based on the spatial layout information, obstacle distribution information, and real-time position information of each robot node at the construction site. Each node includes coordinates, communication capability, energy status, and role attributes. The weight of each communication edge is determined by a weighted combination of link delay, packet loss rate, signal strength, link stability, obstacle penetration penalty factor, and energy consumption parameters. The link quality estimation algorithm is used to perform exponential weighted moving average smoothing on the signal strength, signal-to-noise ratio, round-trip delay and packet loss rate of each side, and the link stability index is calculated within the sliding time window. The multi-path shortest path algorithm is executed based on the weighted communication topology graph to select the main path and backup path between the task start point and the target node based on the comprehensive cost function. When a heartbeat signal loss, signal attenuation, or link disconnection is detected, a candidate relay node is selected through local neighbor nodes to quickly replace the route, or a local area network rediscovery and topology reconstruction process is triggered to update the communication path; and after the path switch, the routing field in the task token is updated to achieve continuous transmission of task data and link self-recovery.

6. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 1, characterized in that, The automatic replanning of the communication path when construction obstacles or metal obstructions are detected causing signal attenuation also includes: An obstacle feature database is established based on a three-dimensional spatial model of the construction site. The database records the spatial coordinates, boundary range, and material electromagnetic property parameters of each obstacle. When the link quality estimation algorithm detects that the signal strength of any communication link is lower than the preset threshold or the signal-to-noise ratio decrease rate exceeds the threshold, the obstacle association analysis module is triggered to determine the spatial intersection relationship between the communication path and the obstacle, and calculate the obstacle penetration penalty value based on the material absorption coefficient and penetration distance. The penalty value is injected into the edge weights of the communication topology graph. The routing planning module calls the weighted shortest path algorithm based on obstacle constraints to recalculate the feasible communication path and selects the set of edges with high link stability and low penetration penalty to form a new main path and backup path. When changes in the construction site space or robot movement cause the obstacle occlusion pattern to be updated, the system automatically performs incremental updates to the topology map to achieve dynamic reconstruction of the communication link.

7. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 1, characterized in that, Using the historical task execution records accumulated in the local area network, a lightweight allocation model is trained for allocation and prediction. The lightweight allocation model directly sorts the tasks based on probability results and selects the robot to be executed according to the sorting results.

8. The method for multi-robot task allocation on a construction site based on local area network command control according to claim 7, characterized in that, The calculation formula for the lightweight allocation model is as follows: ； ； in, This represents the i-th candidate robot node. This indicates a new task to be assigned. Represents robots A score indicating suitability for the new task. Indicates the time decay factor. The similarity is represented by k, where k represents the k-th historical task. Indicates network topology coupling, robot The topological distance weighted average to task-related nodes. Represents the sensitivity coefficient of task feature similarity. This represents the squared Euclidean distance between the feature vectors of the new task and the historical task.

9. A multi-robot task allocation system for construction sites based on local area network command control, characterized in that, Specifically, it includes: A local area network (LAN) command unit is configured to establish a hierarchical LAN control structure, which includes an upper-layer task scheduling server and lower-layer robot group control nodes, wherein each robot node has a local autonomous control module. The instruction protocol unit is configured to transmit task instructions based on a custom lightweight local area network communication protocol after the control structure is established. The communication protocol includes a robot node fast registration and identity recognition mechanism, a serverless communication mechanism, and a task tokenization mechanism. The instruction caching and delayed execution unit is configured to decompose the overall task into several independently executable instruction fragments and cache them to the target robot node when the task scheduling server distributes tasks. When network latency or connection interruption is detected, each robot node executes the delayed task according to the locally cached instruction fragments. The task topology adaptive routing unit is configured to construct a task communication topology map based on the spatial layout information of the construction site and the real-time position information of the robot during task execution, and dynamically adjust the local area network communication path through the task topology perception algorithm; when construction obstacles or metal obstructions are detected that cause signal attenuation, the communication path is automatically replanned. The task execution feedback unit is configured to dynamically update the task scheduling strategy and communication path based on the task execution feedback information returned by the robot nodes, enabling the entire system to adaptively optimize the multi-robot task allocation process according to changes in the construction environment.

10. A computer program product, characterized in that, It stores a computer program that, when executed by a processor, implements the method as described in any one of claims 1-8.

Images