Multi-robot collaborative task planning method and system based on multi-factor coupling optimization

Abstract

The application belongs to the field of multi-robot collaborative task planning, and provides a multi-robot collaborative task planning method and system based on multi-factor coupling optimization, acquires the three-dimensional space position of fruits in the robot base coordinate system, constructs an original fruit point set, and constructs a neighborhood set; a local density function is introduced to describe the fruit distribution, and the clustering radius of each point is adaptively determined based on the local density function; a work unit is constructed based on the clustering radius, the geometric center of each work unit is determined, the reachable space model of each robot arm is established combined with the structural parameters of the multi-robot, the reachable robot arm set of each work unit is constructed, task allocation is performed, and the spatial continuity constraint, the load balancing constraint, the direction consistency term and the conflict suppression mechanism are introduced to determine the optimal allocation robot arm for each work unit, and according to the allocation result, a path sequence is formed to generate an execution trajectory. The application realizes the efficiency and stability of multi-robot collaborative work.

Description

Technical Field

[0001] This invention belongs to the field of multi-manipulator collaborative task planning, specifically involving a multi-manipulator collaborative task planning method and system based on multi-factor coupling optimization. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] Multi-arm collaborative operation technology has been widely used in the field of agricultural harvesting robots, especially in standardized orchard environments. The use of a gantry structure to deploy multiple robotic arms can significantly improve the coverage area and harvesting efficiency. Among them, the four-arm gantry harvesting robot, through its layered and symmetrical structure, enables multiple robotic arms to collaboratively perform harvesting tasks within a shared work space. Its overall performance largely depends on the rationality of the task planning method.

[0004] Existing task planning methods typically treat fruits as discrete work points, allocating tasks by constructing distance- or time-based optimization models. However, these methods ignore the local clustering characteristics of fruits in space, leading to frequent cross-region switching by the robotic arm during execution, reducing motion continuity and operational efficiency. Furthermore, when fruits are unevenly distributed, uneven task allocation can easily occur, causing some robotic arms to be overloaded while others are underutilized.

[0005] Furthermore, due to the overlapping workspaces of multiple robotic arms, redundant reachable areas are prevalent during task allocation. Existing methods often treat these as simple conflicts, lacking effective utilization mechanisms and failing to fully leverage the collaborative advantages of multiple robotic arms. During collaborative operations, spatial interference problems easily arise between robotic arms, and existing methods mostly handle collision avoidance during the path planning phase, which is essentially a correction during the planning process and cannot fundamentally improve system stability. Summary of the Invention

[0006] To address the aforementioned problems, this invention proposes a multi-robot collaborative task planning method and system based on multi-factor coupling optimization. This invention extracts spatial structural features under the condition of natural fruit distribution and introduces effective constraints in the task allocation stage to achieve high efficiency and stability of multi-robot collaborative operation.

[0007] According to some embodiments, the present invention adopts the following technical solution: A multi-robot collaborative task planning method based on multi-factor coupling optimization includes the following steps: Obtain the three-dimensional spatial position of the fruit in the robot's base coordinate system, construct the original fruit point set, construct a neighborhood set for each point, and obtain smooth points through filtering; A local density function is introduced to describe the fruit distribution, and the cluster radius of each point is adaptively determined based on the local density function. Based on the clustering radius, a work unit is constructed using the neighborhood clustering method, and the geometric center of each work unit is determined. Based on the geometric center and combined with the structural parameters of the multiple robotic arms, an reachable space model for each robotic arm is established, and a set of reachable robotic arms for each work unit is further constructed. Based on the set of reachable robotic arms, tasks are assigned, and spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms are introduced during the task assignment process. The optimal robotic arm is determined for each work unit, and the path is sorted and the execution trajectory is generated according to the assignment results.

[0008] As an alternative implementation, the process of obtaining the three-dimensional spatial position of the fruit in the robot's base coordinate system, constructing an original fruit point set, constructing a neighborhood set for each point, and obtaining smoothed points through filtering includes: obtaining the three-dimensional spatial position of the fruit in the robot's base coordinate system. Construct the original fruit point set: ; Perform neighborhood-based smoothing on the point set, for any point... Construct its neighborhood set: ; And the smoothed point is obtained by local mean filtering: ; in, Let N be the number of fruit points, and N be the total number of fruits. is the neighborhood radius.

[0009] As an alternative implementation, a local density function is introduced to describe the fruit distribution. Based on this local density function, the process of adaptively determining the cluster radius of each point includes: introducing a local density function to describe the fruit distribution. ; in, For the fruit point, For neighborhood points, parameters Represents the density-aware scale, used to define the range of influence in the neighborhood. When the value is greater than the set threshold, the density distribution is smoother, which is suitable for scenarios where the fruit is evenly distributed; when When the value is less than or equal to a set threshold, it can more accurately reflect local clustering characteristics, which is beneficial for fine modeling. Based on density information, the clustering radius of each point is adaptively determined. ; in, and These represent the lower and upper bounds of the task unit scale, respectively, and their physical meaning lies in limiting the granularity of task division; parameters This is used to adjust the degree of influence of density on the division scale. When its value is greater than the set value, the working unit is more sensitive to density changes, thereby forming a finer-grained division in high-density areas.

[0010] As an alternative implementation, the process of constructing job units based on the clustering radius using a neighborhood clustering method and determining the geometric center of each job unit includes: constructing job units using a neighborhood clustering method: ; in, The neighborhood radius, Let the fruit point be defined as follows: ; Simultaneously define the weights of the work units: ; This is used to characterize the task scale and intensity of the work unit, realize the transformation from discrete point tasks to regional tasks, and enable task planning to have spatial structure expression capabilities.

[0011] As an alternative implementation, based on the geometric center and combined with the structural parameters of the multiple robotic arms, the process of establishing the reachability space model of each robotic arm and further constructing the reachability robotic arm set of each work unit includes: Let the current end-effector position of the i-th robotic arm be q, and its workspace be... Define the reachability determination function: ; in, As the geometric center, For workspace, This represents the error in solving the inverse kinematics problem. An allowable error threshold is used to limit the achievable accuracy range of the robotic arm towards the target point, thereby constructing the set of achievable robotic arms for the work unit: ; When|A k When |=1, the job unit is directly assigned; when |A k When |>1, the optimal allocation phase begins.

[0012] As an alternative implementation, in the process of introducing spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms, the distance cost is defined as follows: ; As the geometric center, It is a point in set q; Define the load of the robotic arm This is used to reflect the current task load of the robotic arm and achieve load balancing. ; It is the weight of the work unit. The set of tasks already assigned to the i-th robotic arm; Define continuity metrics: ; c j The task center of the workspace; This is used to constrain the spatial continuity of tasks, allowing the robotic arm to prioritize tasks in the vicinity. Introducing a direction consistency term This is used to describe the deviation between the current direction of motion and the target direction, and to suppress frequent changes in direction of the robotic arm by using the direction vector from the previous task to the current task, thereby improving trajectory smoothness. ; The geometric center of the current job cell to be assigned. The geometric center of the robotic arm's last task execution. Let be the direction vector from the previous task to the current task. Let be the current motion direction vector of the i-th robotic arm.

[0013] As a further defined implementation method, the comprehensive cost function is: ; in, ~ Each factor represents its weight. Considering the cooperative interference problem among multiple robotic arms, a conflict suppression term is introduced: ; in, As the task center for other robotic arms, The geometric center of the current job unit to be assigned; The scope of the conflict's impact is indicated, and the safe collaborative distance between the robotic arms is defined and added to the total cost function: ; parameter It is used to adjust the importance of conflict constraints. When its value is greater than the set value, it tends to avoid spatial conflicts.

[0014] As an alternative implementation, the process of determining the optimal allocation of robotic arms for each work unit includes: Solve ; in, Given the total cost function, determine the optimal allocation of robotic arms and update the task set iteratively to achieve stable allocation.

[0015] As an alternative implementation, the process of generating execution trajectories by forming path sorting based on the allocation results includes: after completing task allocation, sorting the paths for each robotic arm's set of work units: ; This generates a continuous execution sequence, optimizing the order of fruit access within the job unit: ; in, , These represent the two task points, one before and one after. And combine the inverse kinematics model to generate the execution trajectory: ; Where IK is the inverse kinematics function.

[0016] A multi-robotic arm collaborative task planning system based on multi-factor coupling optimization includes: The point set construction module is configured to obtain the three-dimensional spatial position of the fruit in the robot's base coordinate system, construct the original fruit point set, construct a neighborhood set for each point, and obtain smooth points through filtering; The fruit distribution description module is configured to introduce a local density function to describe the fruit distribution, and adaptively determine the cluster radius of each point based on the local density function. The job unit construction module is configured to construct job units based on the clustering radius using a neighborhood clustering method, and determine the geometric center of each job unit. The reachable robotic arm assembly construction module is configured to establish a reachable space model of each robotic arm based on the geometric center and the structural parameters of the multiple robotic arms, and further construct a reachable robotic arm assembly for each work unit. The execution trajectory survival module is configured to perform task allocation based on the set of reachable robotic arms. During the task allocation process, spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms are introduced to determine the optimal robotic arm for each work unit and to generate an execution trajectory based on the allocation results.

[0017] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention significantly enhances the structural representation of the task space and the local continuity of task allocation during multi-robot task planning by introducing a task modeling method based on work units. Compared to traditional methods that rely solely on discrete fruit points for independent task allocation, this invention effectively integrates the clustering and hierarchical characteristics of fruit spatial distribution into the task planning process through local density estimation, adaptive work unit partitioning, and reachability mapping analysis. This achieves continuous expression of tasks at the spatial structure level, making the task allocation process more holistic and interpretable. Simultaneously, by explicitly constructing redundant reachability relationships between the robot arm and work units, the utilization efficiency of redundant workspace in multi-robot collaborative operations is effectively improved, resulting in a more balanced and rational task allocation and increased overall system efficiency.

[0018] This invention constructs a multi-factor coupled cost function that integrates distance cost, task load, spatial continuity, directional consistency, and conflict suppression, and uses an iterative optimization strategy to complete task allocation. This effectively avoids the problems of strong path dispersion, local task overload, and frequent robot arm collaboration conflicts caused by traditional methods that rely solely on single distance optimization, thereby improving the stability of the task planning process and the rationality of the optimization results.

[0019] This invention introduces a conflict suppression mechanism in advance during the task allocation stage to identify and constrain potential spatial interference, thereby reducing the complexity of collision avoidance adjustment in subsequent trajectory planning. This improves the stability and safety of multi-robotic arm collaborative execution while ensuring controllable computational complexity.

[0020] This invention does not rely on complex global optimization solutions or high-frequency online replanning, and has strong engineering feasibility and deployment flexibility. It is applicable to multi-robotic arm collaborative harvesting systems in various standardized orchard environments and has good promotion and application value.

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0022] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0023] Figure 1 This is a schematic diagram of a method flow according to one embodiment. Detailed Implementation

[0024] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0025] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0026] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0027] Where there is no conflict, the embodiments and features described in this application may be combined with each other.

[0028] Example 1 This embodiment uses a four-arm gantry-type harvesting robot as an example for illustration.

[0029] A task planning method based on job unit modeling and multi-factor coupled optimization, such as Figure 1 As shown, this method is based on the spatial distribution of fruits. By constructing a structured task expression form and introducing spatial continuity constraints, load balancing constraints and conflict suppression mechanisms in the task allocation stage, it achieves unified modeling and efficient solution of multi-robotic arm collaborative task planning.

[0030] First, the three-dimensional spatial position of the fruit in the robot's base coordinate system is obtained through the vision system, and the original fruit point set is constructed: ; Considering the visual measurement errors and the impact of outliers, neighborhood-based smoothing is applied to the point set to improve data stability.

[0031] For any point Construct its neighborhood set: ; And the smoothed point is obtained by local mean filtering: ; in, For the fruit point, Let N be the neighboring points, and N be the total number of fruits. is the neighborhood radius.

[0032] By reducing the impact of random measurement errors on individual points through local spatial averaging, the spatial distribution of fruits becomes smoother and more continuous, while avoiding outliers from interfering with subsequent density estimation and task division.

[0033] Building upon this, to avoid the high-frequency switching issues caused by point-to-point task allocation, discrete fruit points are transformed into task units with spatial structural significance. A local density function is introduced to describe the fruit distribution: ; in, For the fruit point, For neighborhood points, parameters This represents the density-aware scale, used to define the range of influence within the neighborhood. When When the value is large, the density distribution is smoother, which is suitable for scenarios where the fruit is evenly distributed; when When the value is smaller, it can more accurately reflect local clustering characteristics, which is beneficial for refined modeling. Based on density information, the cluster radius of each point is adaptively determined: ; in, and These represent the lower and upper bounds of the task unit scale, respectively, and their physical meaning lies in limiting the granularity of task division; parameters It is used to adjust the degree of influence of density on the division scale. When its value is large, the working unit is more sensitive to density changes, thus forming a finer-grained division in high-density areas.

[0034] Based on the aforementioned adaptive radius, the work unit is constructed using a neighborhood clustering method: ; The neighborhood radius, Let be the fruit point, and define its geometric center as: ; Simultaneously define the weights of the work units: ; This is used to characterize the task scale and intensity of the work unit. Through the above process, the task is transformed from a discrete point task to a regional task, enabling task planning to have spatial structure expression capabilities.

[0035] After dividing the work units, and based on the structural parameters of the four-arm gantry robot, an reachable space model for each arm is established. Let the current end effector position of the i-th arm be q; its workspace is... Then define the reachability determination function: ; in, As the geometric center, For workspace, This represents the error in solving the inverse kinematics problem. An allowable error threshold is used to limit the achievable accuracy range of the robotic arm towards the target point. This leads to the construction of the set of reachable robotic arms for each work unit: ; When|A k When |=1, the job unit is directly assigned; when |A k When |>1, the optimal allocation phase begins. For redundant reachable job units, a multi-factor coupled cost function is constructed. The distance cost is defined as follows: ; As the geometric center, It is a point in set q; This refers to the basic motion cost required for the robotic arm to perform the task. The robotic arm's load is also defined. ; Used to reflect the current task load of the robotic arm and achieve load balancing.

[0036] To ensure the spatial continuity of task execution, a continuity index is defined: ; This term is used to constrain the spatial coherence of tasks, allowing the robotic arm to prioritize tasks in nearby areas. A further directional consistency term is introduced: ; It is used to describe the deviation between the current direction of motion and the target direction, and is used to suppress frequent changes in direction of the robotic arm and improve the smoothness of the trajectory.

[0037] The geometric center of the current job cell to be assigned. The geometric center of the robotic arm's last task execution. Let be the direction vector from the previous task to the current task. Let be the current motion direction vector of the i-th robotic arm.

[0038] Based on this, construct the comprehensive cost function: ; in, ~ Each factor represents its weight.

[0039] Considering the cooperative interference problem among multiple robotic arms, a conflict suppression term is introduced: ; in, This indicates the scope of the conflict's impact and defines the safe collaborative distance between the robotic arms. It is then added to the total cost function. ; parameter This is used to adjust the importance of conflict constraints; when the value is large, the system is more inclined to avoid spatial conflicts.

[0040] For each work unit, solve: ; The optimal allocation of robotic arms is determined, and the task set is updated iteratively to achieve stable allocation.

[0041] After task allocation is completed, the work unit set of each robotic arm is sorted by path: ; This generates a sequential execution sequence. Subsequently, the order of fruit access is further optimized within the job unit: ; And combine the inverse kinematics model to generate the execution trajectory: ; Where IK is the inverse kinematics function.

[0042] From an overall process perspective, this invention employs a unified framework of spatial density modeling, operational unit construction, accessibility mapping, multi-factor optimization allocation, and conflict suppression to couple the spatial structure information of the fruit with the collaborative constraints of multiple robotic arms. Each parameter corresponds to physical meanings such as spatial scale, task load, motion continuity, and safety constraints, and strategy switching under different operational requirements is achieved through weight adjustment.

[0043] Through the above mechanism, the present invention can suppress collaborative conflicts in advance during the task allocation stage and guide the robotic arm to form a spatially continuous and directional execution path, thereby significantly improving the system's operational efficiency and stability while ensuring controllable computational complexity.

[0044] Example 2 A multi-robotic arm collaborative task planning system based on multi-factor coupling optimization includes: The point set construction module is configured to obtain the three-dimensional spatial position of the fruit in the robot's base coordinate system, construct the original fruit point set, construct a neighborhood set for each point, and obtain smooth points through filtering; The fruit distribution description module is configured to introduce a local density function to describe the fruit distribution, and adaptively determine the cluster radius of each point based on the local density function. The job unit construction module is configured to construct job units based on the clustering radius using a neighborhood clustering method, and determine the geometric center of each job unit. The reachable robotic arm assembly construction module is configured to establish a reachable space model of each robotic arm based on the geometric center and the structural parameters of the multiple robotic arms, and further construct a reachable robotic arm assembly for each work unit. The execution trajectory survival module is configured to perform task allocation based on the set of reachable robotic arms. During the task allocation process, spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms are introduced to determine the optimal robotic arm for each work unit and to generate an execution trajectory based on the allocation results.

[0045] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of one or more computer-usable storage media (including, but not limited to, disk storage, etc.) containing computer-usable program code. CD - ROM It takes the form of a computer program product implemented on (such as optical memory, etc.).

[0046] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made by those skilled in the art without creative effort within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-robot collaborative task planning method based on multi-factor coupling optimization, characterized in that, Includes the following steps: Obtain the three-dimensional spatial position of the fruit in the robot's base coordinate system, construct the original fruit point set, construct a neighborhood set for each point, and obtain smooth points through filtering; A local density function is introduced to describe the fruit distribution, and the cluster radius of each point is adaptively determined based on the local density function. Based on the clustering radius, a work unit is constructed using the neighborhood clustering method, and the geometric center of each work unit is determined. Based on the geometric center and combined with the structural parameters of the multiple robotic arms, an reachable space model for each robotic arm is established, and a set of reachable robotic arms for each work unit is further constructed. Based on the set of reachable robotic arms, tasks are assigned, and spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms are introduced during the task assignment process. The optimal robotic arm is determined for each work unit, and the path is sorted and the execution trajectory is generated according to the assignment results.

2. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, The process of obtaining the 3D spatial position of the fruit in the robot's base coordinate system, constructing an original fruit point set, building a neighborhood set for each point, and obtaining smoothed points through filtering includes: obtaining the 3D spatial position of the fruit in the robot's base coordinate system. Construct the original fruit point set: ； Perform neighborhood-based smoothing on the point set, for any point... Construct its neighborhood set: ； And the smoothed point is obtained by local mean filtering: ； in, Let N be the number of fruit points, and N be the total number of fruits. The neighborhood radius, For neighboring points.

3. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, it introduces... The local density function describes the fruit distribution. Based on this local density function, the process of adaptively determining the cluster radius for each point includes: introducing a local density function to describe the fruit distribution. ； in, For the fruit point, For neighborhood points, parameters Represents the density-aware scale, used to define the range of influence in the neighborhood. When the value is greater than the set threshold, the density distribution is smoother, which is suitable for scenarios where the fruit is evenly distributed; when When the value is less than or equal to a set threshold, it can more accurately reflect local clustering characteristics, which is beneficial for fine modeling. Based on density information, the clustering radius of each point is adaptively determined. ； in, and These represent the lower and upper bounds of the task unit scale, respectively, and their physical meaning lies in limiting the granularity of task division; parameters This is used to adjust the degree of influence of density on the division scale. When its value is greater than the set value, the working unit is more sensitive to density changes, thereby forming a finer-grained division in high-density areas.

4. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, Based on the clustering radius, the process of constructing work units using the neighborhood clustering method and determining the geometric center of each work unit includes: constructing work units using the neighborhood clustering method: ； in, The neighborhood radius, Let the fruit point be defined as follows: ； Simultaneously define the weights of the work units: ； This is used to characterize the task scale and intensity of the work unit, realize the transformation from discrete point tasks to regional tasks, and enable task planning to have spatial structure expression capabilities.

5. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, Based on the geometric center and combined with the structural parameters of the multiple robotic arms, the process of establishing the reachable space model of each robotic arm and further constructing the reachable robotic arm set of each work unit includes: Let the current end-effector position of the i-th robotic arm be q, and its workspace be... Define the reachability determination function: ； in, As the geometric center, For workspace, This represents the error in solving the inverse kinematics problem. An allowable error threshold is used to limit the achievable accuracy range of the robotic arm towards the target point, thereby constructing the set of achievable robotic arms for the work unit: ； When|A k When |=1, the job unit is directly assigned; when |A k When |>1, the optimal allocation phase begins.

6. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 5, characterized in that, In the process of introducing spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms, the distance cost is defined as follows: ； As the geometric center, It is a point in set q; Define the load of the robotic arm This is used to reflect the current task load of the robotic arm and achieve load balancing. ； It is the weight of the work unit. The set of tasks already assigned to the i-th robotic arm; Define continuity metrics: c j The task center of the workspace; This is used to constrain the spatial continuity of tasks, allowing the robotic arm to prioritize tasks in the vicinity. Introducing a direction consistency term This is used to describe the deviation between the current direction of motion and the target direction, and to suppress frequent changes in direction of the robotic arm by using the direction vector from the previous task to the current task, thereby improving trajectory smoothness. ； The geometric center of the current job unit to be assigned. The geometric center of the robotic arm's last task execution. Let be the direction vector from the previous task to the current task. Let be the current motion direction vector of the i-th robotic arm.

7. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 6, characterized in that, Comprehensive cost function: ； in, ~ Each factor represents its weight. Considering the cooperative interference problem among multiple robotic arms, a conflict suppression term is introduced: ； in, As the task center for other robotic arms, The geometric center of the current job unit to be assigned; The scope of the conflict's impact is indicated, and the safe collaborative distance between the robotic arms is defined and added to the total cost function: ； parameter It is used to adjust the importance of conflict constraints. When its value is greater than the set value, it tends to avoid spatial conflicts.

8. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, The process of determining the optimal allocation of robotic arms for each work unit includes: Solve ; in, Given the total cost function, determine the optimal allocation of robotic arms and update the task set iteratively to achieve stable allocation.

9. The multi-robot collaborative task planning method based on multi-factor coupling optimization as described in claim 1, characterized in that, Based on the allocation results, the process of forming a path order and generating the execution trajectory includes: after completing the task allocation, sorting the paths for each robotic arm's set of work units: ； This generates a continuous execution sequence, optimizing the order of fruit access within the job unit: ； in, , These represent the two task points, one before and one after. And combine the inverse kinematics model to generate the execution trajectory: ； in, IK It is the inverse kinematics function.

10. A multi-robotic arm collaborative task planning system based on multi-factor coupling optimization, characterized in that, include: The point set construction module is configured to obtain the three-dimensional spatial position of the fruit in the robot's base coordinate system, construct the original fruit point set, construct a neighborhood set for each point, and obtain smooth points through filtering; The fruit distribution description module is configured to introduce a local density function to describe the fruit distribution, and adaptively determine the cluster radius of each point based on the local density function. The job unit construction module is configured to construct job units based on the clustering radius using a neighborhood clustering method, and determine the geometric center of each job unit. The reachable robotic arm assembly construction module is configured to establish a reachable space model of each robotic arm based on the geometric center and the structural parameters of the multiple robotic arms, and further construct a reachable robotic arm assembly for each work unit. The execution trajectory survival module is configured to perform task allocation based on the set of reachable robotic arms. During the task allocation process, spatial continuity constraints, load balancing constraints, directional consistency terms, and conflict suppression mechanisms are introduced to determine the optimal robotic arm for each work unit and to generate an execution trajectory based on the allocation results.

Images