A control system for a cloud collaborative humanoid robot

Abstract

The application discloses a kind of control systems of cloud collaborative robot, the scheme includes cloud control platform and robot, robot is equipped with edge computing module and hardware module;Hardware module provides hardware components, collects environmental data, uploads cloud control platform;Edge computing module monitors robot state and collects execution data, uploads cloud control platform and updates robot local model parameters, uploads parameter to cloud control platform, and according to task strategy and optimization strategy controls robot;Cloud control platform is based on large model, according to the production task and environmental data received to formulate task strategy, according to the upload data received to formulate optimization strategy, according to the upload data and local model parameters and task experience pool to update large model, issue task strategy, optimization strategy and large model parameters to robot;It improves task execution efficiency and system control efficiency.The embodiment of the application can be widely applied to the field of robot control technology.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robot control, and in particular to a cloud collaborative humanoid robot control system. BACKGROUND

[0002] With the development of intelligent manufacturing, more and more robots are involved in production tasks; the existing multi-robot scheduling system usually adopts a preset scheduling algorithm and a centralized control mode, which is difficult to cope with changes in the environment and changes in task requirements, has low task execution efficiency, and has low collaborative control efficiency. SUMMARY

[0003] The main purpose of the embodiments of the present application is to provide a cloud collaborative humanoid robot control system, which can improve the task execution efficiency and improve the collaborative control efficiency.

[0004] To achieve the above-mentioned purpose, one aspect of an embodiment of the present application provides a cloud collaborative humanoid robot control system, the system comprising a cloud control platform and a humanoid robot, the humanoid robot comprising an edge computing module and a hardware module; wherein,

[0005] The hardware module is configured to collect environment data, send the environment data to the cloud control platform through the edge computing module, and provide hardware components to enable the robot to perform production tasks through the hardware components.

[0006] The edge computing module is configured to monitor the state of the humanoid robot, obtain monitoring data, and send the monitoring data to the cloud control platform; control the humanoid robot to perform the production task according to a task strategy and an optimization strategy, and feed back execution data to the cloud control platform; update a local model according to a model parameter to obtain a local parameter, and send the local parameter to the cloud control platform.

[0007] The cloud control platform is configured to receive the production task, input the production task and the environment data into a large model for analysis to determine the task strategy; determine the optimization strategy according to the execution data, the monitoring data, and the environment data; update the large model according to the environment data, the local parameter, and a task experience pool to obtain the model parameter; and distribute the task strategy, the optimization strategy, and the model parameter to the humanoid robot.

[0008] In some embodiments, the cloud control platform comprises any combination of multiple intelligent decision systems, intelligent allocation systems, intelligent energy management systems, adaptive software systems, or experience sharing systems; wherein,

[0009] The intelligent decision-making system is used to perform deep learning based on the production task, the environmental data, and the large model to obtain the task strategy; process the execution data, environmental data, and the large model to obtain the optimization strategy; analyze the monitoring data, and if abnormal state data exists, analyze the abnormal state data to determine the solution; and generate a fault report based on the abnormal data and the solution.

[0010] The intelligent allocation system is used to analyze the production tasks and the monitoring data to determine a task allocation scheme; and to analyze the execution data and the monitoring data to determine a resource sharing scheme.

[0011] The intelligent energy management system is used to analyze the monitoring data to determine energy consumption data, perform energy consumption analysis based on the production tasks, the energy consumption data, and the large model to determine an energy consumption optimization scheme; and analyze the execution data and monitoring data to determine a power allocation scheme.

[0012] The adaptive software system is used to generate custom production tasks in response to external input; and to generate feedback reports based on the execution data and the monitoring data.

[0013] The experience-sharing system is used to construct a task experience pool, update the task experience pool according to the execution data, update the parameters of the large model according to the task experience pool to obtain model parameters, and optimize the parameters of the large model according to the local parameters to obtain the optimized large model.

[0014] In some embodiments, the intelligent decision-making system includes a strategy generation module, a strategy optimization module, and a fault handling module; wherein,

[0015] The strategy generation module is used to analyze the production task to obtain task characteristics, analyze the environmental data to obtain environmental characteristics, match the task characteristics and environmental characteristics with the task experience pool to determine a first scheme, input the task characteristics and environmental characteristics into the large model for analysis to obtain task type and environmental elements, and process the task type, environmental elements, first scheme and large model to obtain the task strategy.

[0016] The strategy optimization module is used to analyze the execution data to determine task progress data, analyze the environmental data to determine environmental change data, and analyze the task progress data, environmental change data, the large model, and preset adjustment strategies to obtain the optimization strategy.

[0017] The fault processing module is configured to perform data extraction on the monitoring data to obtain robot state data, perform identification on the large model and the robot state data to determine an abnormal event, generate early warning information according to the abnormal event, determine an abnormal type according to the abnormal event, and determine the solution according to the abnormal type and a preset processing strategy.

[0018] In some embodiments, the intelligent allocation system comprises a task allocation module and a resource sharing module; wherein,

[0019] The task allocation module is configured to analyze the production task to determine a task priority, analyze the monitoring data to determine robot state data, determine a fitness score according to a preset scoring relationship of the robot state data, and match the task priority and the fitness score to determine the task allocation solution.

[0020] The resource sharing module is configured to analyze the monitoring data to determine resource usage data, analyze the execution data to determine resource demand, determine a resource sharing request according to the resource usage data and the resource demand, and determine the resource sharing solution according to the resource sharing request and the resource usage.

[0021] In some embodiments, the intelligent energy management system comprises an energy consumption optimization module and a power management module; wherein,

[0022] The energy consumption optimization module is configured to perform data extraction on the monitoring data to obtain energy consumption data, analyze the production task to determine a task priority, and input the energy consumption data and the task priority into the large model for processing to obtain an energy consumption optimization strategy.

[0023] The power management module is configured to analyze the execution data to determine task load data, determine a load level according to the task load data and a preset threshold, perform data extraction on the monitoring data to obtain power monitoring data, determine a power distribution solution according to the load level and the power monitoring data, and compare the power monitoring data with a preset threshold, and if the power monitoring data is less than or equal to the preset threshold, switch to a backup power supply and charge the power supply before switching.

[0024] In some embodiments, the adaptive software system comprises a task customization module and an interactive feedback module; wherein,

[0025] The task customization module is configured to analyze the external input request to determine a task mode, and generate a customized production task according to the task mode; wherein, the task mode comprises a task type, a module configuration, an execution parameter, a resource allocation strategy, and a fault response strategy.

[0026] The interaction feedback module is configured to generate a feedback report according to the monitoring data and the execution data, and send the feedback report, the monitoring data and the execution data to the human-computer interaction interface, so that the human-computer interaction interface displays the feedback report, the monitoring data and the execution data.

[0027] In some embodiments, the experience sharing system comprises a task experience library and a model updating module; wherein,

[0028] The task experience library is configured to record the execution data.

[0029] The model updating module is configured to classify the task experience library, update the large model according to the classified task experience library to obtain model parameters, aggregate the obtained local parameters to obtain first parameters, optimize the large model according to the first parameters, and obtain the optimized large model.

[0030] In some embodiments, the hardware module comprises any combination of a clamp module, a movement module, a sensing module or an arm and joint module; wherein,

[0031] The clamp module, the movement module and the arm and joint module are configured to provide replaceable hardware components for the humanoid robot.

[0032] The sensing module is configured to collect data of a current environment of the humanoid robot to obtain the environment data, and send the environment data to the edge computing module.

[0033] In some embodiments, the edge computing module is further configured to receive the environment data, upload the environment data to the cloud control platform, analyze the monitoring data to determine task progress data, upload the task progress data to the cloud control platform, analyze the task strategy or the optimization strategy to extract control instructions, and control the humanoid robot according to the control instructions, monitor power data of the humanoid robot, compare the power data with a preset value, and control the humanoid robot to switch to an energy-saving mode if the power data is less than or equal to the preset value.

[0034] In some embodiments, the edge computing module is further configured to perform parameter updating on the local model of the humanoid robot based on the model parameters, to obtain an updated local model; obtain current environment data and current execution data of the humanoid robot, and perform parameter adjustment on the updated local model based on the current environment data and the current execution data, to obtain updated local model parameters; encrypt the updated local model parameters to obtain encrypted data, and upload the encrypted data to the cloud control platform.

[0035] Implementing the embodiments of the present application has the following beneficial effects: the embodiments provide a cloud collaborative humanoid robot control system, which includes a cloud control platform and a humanoid robot, the humanoid robot including an edge computing module and a hardware module; the hardware module collects environment data and sends the environment data to the cloud control platform via the edge computing module, and provides hardware components for the humanoid robot to perform production tasks; the edge computing module monitors the state of the humanoid robot and feeds back the state of the humanoid robot to the cloud control platform, controls the humanoid robot to perform production tasks according to a task strategy and an optimization strategy, feeds back execution data to the cloud control platform, performs parameter updating on a local model according to model parameters, and sends the updated model parameters to the cloud control platform; the cloud control platform receives a production task, analyzes the production task and environment data according to a large model, to obtain a task strategy; determines an optimization strategy according to execution data, monitoring data and environment data, updates the large model according to environment data, local parameters and a task experience pool, and issues the obtained task strategy, optimization strategy and parameters of the large model to the humanoid robot; the edge computing module and the cloud control platform formulate a task strategy and an optimization strategy according to collected data, control the humanoid robot to perform production tasks, realize adaptive task scheduling and optimization, and improve task execution efficiency and collaborative control efficiency; the task experience pool, the edge computing module and the large model are set to share experience, optimize the parameters of the large model, improve the accuracy and efficiency of formulating the task strategy and the optimization strategy, and further improve the task execution efficiency and the collaborative control efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 is an implementation environment schematic diagram of a cloud collaborative humanoid robot control system provided by the embodiments of the present application;

[0037] Figure 2 is a structural block diagram of a cloud collaborative humanoid robot control system provided by the embodiments of the present application;

[0038] Figure 3 is a structural block diagram of a cloud control platform in a cloud collaborative humanoid robot control system provided by the embodiments of the present application;

[0039] Figure 4This is a structural block diagram of the intelligent decision-making system of the cloud control platform in a cloud-based collaborative humanoid robot control system provided in an embodiment of the present invention;

[0040] Figure 5 This is a structural block diagram of the intelligent allocation system of the cloud control platform in a cloud-based collaborative humanoid robot control system provided in an embodiment of the present invention;

[0041] Figure 6 This is a structural block diagram of the intelligent energy management system of the cloud control platform in the control system of a cloud-based collaborative humanoid robot provided in an embodiment of the present invention;

[0042] Figure 7 This is a structural block diagram of the adaptive software system of the cloud control platform in a cloud-based collaborative humanoid robot control system provided in an embodiment of the present invention;

[0043] Figure 8 This is a structural block diagram of an experience-sharing system for a cloud-based collaborative humanoid robot control platform provided in an embodiment of the present invention.

[0044] Figure 9 This is a flowchart illustrating the steps of a specific embodiment provided by the present invention. Detailed Implementation

[0045] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments. The step numbers in the following embodiments are only for ease of explanation and do not limit the order of the steps. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art.

[0046] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0047] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of the invention described herein can be implemented in an order other than that illustrated or described herein.

[0048] Unless otherwise defined, all technical and scientific terms used in the embodiments of this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in the embodiments of this invention is for descriptive purposes only and is not intended to limit the invention.

[0049] Please see Figure 1 , Figure 1 This is an implementation environment for a cloud-based collaborative humanoid robot control system provided in this embodiment of the invention; the cloud control platform is set in the cloud, and the cloud control platform can connect to several humanoid robots. The humanoid robots have edge computing capabilities, which enables the humanoid robots to have a certain level of intelligence.

[0050] Please see Figure 2 , Figure 2 This is a structural block diagram of a cloud-based collaborative humanoid robot control system provided in an embodiment of the present invention. The system includes a cloud control platform and a humanoid robot, the humanoid robot including an edge computing module and a hardware module; wherein,

[0051] The hardware module is used to collect environmental data and send the environmental data to the cloud control platform via the edge computing module; it also provides hardware components to enable the humanoid robot to perform production tasks.

[0052] The edge computing module is used to monitor the status of the humanoid robot, obtain monitoring data, and send it to the cloud control platform; control the humanoid robot to execute production tasks according to task strategies and optimization strategies, and feed back execution data to the cloud control platform; update the parameters of the local model according to the model parameters, obtain local parameters, and send the local parameters to the cloud control platform.

[0053] The cloud-based control platform receives production tasks, inputs production tasks and environmental data into a large model for analysis, and determines task strategies. It then determines optimization strategies based on execution data, monitoring data, and environmental data. The platform updates the large model based on environmental data, local parameters, and the task experience pool to obtain model parameters. Finally, it distributes the task strategies, optimization strategies, and model parameters to the humanoid robot.

[0054] In some embodiments, the hardware module is part of the humanoid robot, providing hardware for the humanoid robot to perform production tasks, including a gripper module, a movement module, a sensing module, and an arm and joint module. Each humanoid robot is equipped with an edge computing module to process the collected and received data, update the humanoid robot's local model, reduce data latency, and improve the system's response speed and intelligence level. The cloud control platform is located in the cloud, receiving data uploaded by all humanoid robots connected to the cloud control platform, processing and analyzing the uploaded data, formulating relevant strategies, generating corresponding control commands to control all humanoid robots to work collaboratively and complete production tasks. The cloud control platform has a large model and a task experience pool, recording data on the humanoid robots' task execution, and continuously optimizing the large model through collective learning and experience sharing to improve the overall system's intelligence level and task execution efficiency. Each humanoid robot connects to the cloud control platform via wireless communication methods, such as Bluetooth, 5G, etc., but not limited to these.

[0055] Please see Figure 3 In some embodiments, the cloud control platform includes an intelligent decision-making system, an intelligent allocation system, an intelligent energy management system, an adaptive software system, and an experience-sharing system; wherein,

[0056] The intelligent decision-making system is used to perform deep learning based on production tasks, environmental data, and large models to obtain task strategies; process execution data, environmental data, and large models to obtain optimization strategies; analyze monitoring data, and if abnormal state data exists, analyze the abnormal state data to determine solutions; and generate fault reports based on abnormal data and solutions.

[0057] The intelligent allocation system is used to analyze production tasks and monitoring data to determine task allocation schemes; and to analyze execution data and monitoring data to determine resource sharing schemes.

[0058] The intelligent energy management system is used to analyze monitoring data, determine energy consumption data, perform energy consumption analysis based on production tasks, energy consumption data and large models, and determine energy consumption optimization schemes; it also analyzes execution data and monitoring data to determine power allocation schemes.

[0059] An adaptive software system that responds to external inputs, generates custom production tasks, and generates feedback reports based on execution and monitoring data.

[0060] The experience-sharing system is used to build a task experience pool, update the task experience pool based on execution data, update the parameters of the large model based on the task experience pool to obtain model parameters, and optimize the parameters of the large model based on local parameters to obtain an optimized large model.

[0061] In some embodiments, the cloud control platform is primarily responsible for advanced management functions such as intelligent decision-making, task scheduling, experience sharing, and collective learning. It also handles edge computing synchronization and coordination, generates execution and optimization strategies for production tasks, and distributes them to the humanoid robots connected to the cloud control platform. Therefore, the cloud control platform is equipped with an intelligent decision-making system, an intelligent allocation system, an intelligent energy management system, and an experience sharing system based on its functions. In this embodiment, the cloud control platform has user-defined functions, allowing users to customize the tasks to be executed. Consequently, the cloud control platform also includes a custom software system. Through the intelligent decision-making system, the cloud control platform processes the data uploaded by each humanoid robot using a large-scale model to generate corresponding execution and optimization strategies for production tasks. The intelligent allocation system then distributes the generated execution and optimization strategies to the appropriate humanoid robots. The system monitors the resource utilization of humanoid robots in real time, using a large-scale model to regulate the allocation of idle resources, thereby improving resource utilization and task execution efficiency. An intelligent energy management system monitors the energy consumption status of each humanoid robot and device, using the large-scale model to optimize energy consumption and regulate power supply configuration to improve robot execution efficiency and energy utilization. A cloud-based control platform collects data from each humanoid robot during production tasks, records and stores it in an experience-sharing system, and continuously optimizes the large-scale model based on group learning and distributed learning, improving its accuracy and computational efficiency, thus enhancing the efficiency of humanoid robot task execution. The cloud-based control platform also enables human-machine interaction through a custom software system, generating user-defined production tasks and adjusting system execution parameters in real time to improve execution efficiency.

[0062] Please see Figure 4 In some embodiments, the intelligent decision-making system includes a strategy generation module, a strategy optimization module, and a fault handling module; wherein,

[0063] The strategy generation module is used to analyze production tasks to obtain task characteristics and analyze environmental data to obtain environmental characteristics; it matches the task characteristics and environmental characteristics with the task experience pool to determine the first solution; it inputs the task characteristics and environmental characteristics into the large model for analysis to obtain task type and environmental elements; and it processes the task type, environmental elements, first solution, and large model to obtain the task strategy.

[0064] The strategy optimization module is used to analyze execution data to determine task progress data and environmental data to determine environmental change data. Based on the task progress data, environmental change data, large model, and preset adjustment strategies, it analyzes the data to obtain optimization strategies.

[0065] The fault handling module is used to extract data from monitoring data to obtain robot status data; identify abnormal events based on the large model and robot status data; generate early warning information based on abnormal events; determine the abnormal type based on the abnormal events; and determine a solution based on the abnormal type and preset handling strategy.

[0066] In some embodiments, the intelligent decision-making system makes decisions based on a large model and a task experience pool set up on a cloud control platform. The intelligent decision-making system includes a strategy generation module, a strategy optimization module, and a fault handling module. The strategy generation module performs in-depth analysis of the received production tasks and environmental data collected by the humanoid robot using the large model to determine task characteristics such as task type and requirements, as well as environmental characteristics such as the current position of the humanoid robot, the status of each device on the humanoid robot, and the status of hardware resources. Based on the analyzed task and environmental characteristics, a preliminary matching is performed in the task experience pool to determine if there are similar task strategies. If so, existing task strategies can be used. The system makes minor adjustments to improve generation efficiency; if not, it uses a large model for planning to generate task strategies for production tasks, thereby controlling the robot to execute the corresponding tasks. The strategy optimization module uses the large model to generate optimization strategies based on real-time feedback from the robot on task execution progress and environmental change data. When the robot encounters obstacles or deviates from its intended path, it adjusts according to the optimization strategy to improve task execution efficiency. The fault handling module monitors the status of the cloud control platform, each robot, and equipment in real time. It identifies faults through the large model and task experience pool, generates corresponding solutions, and issues alarm information when faults occur, thereby improving the overall fault tolerance and stability of the system.

[0067] Please see Figure 5 In some embodiments, the intelligent allocation system includes a task allocation module and a resource sharing module; wherein,

[0068] The task allocation module is used to analyze production tasks and determine task priorities; analyze monitoring data to determine robot status data; determine suitability scores based on the relationship between robot status data and preset scoring; and match task priorities and suitability scores to determine task allocation schemes.

[0069] The resource sharing module is used to analyze monitoring data to determine resource usage data; analyze execution data to determine resource requirements; determine resource sharing requests based on resource usage data and resource requirements; and determine resource sharing schemes based on resource sharing requests and resource usage.

[0070] In some embodiments, the cloud control platform allocates production tasks and system resources through an intelligent allocation system. The intelligent allocation system includes a task allocation module and a resource sharing system. The task allocation module analyzes and determines the task requirements of received production tasks, including task type, urgency, and deadline. Based on these requirements, it assigns priorities to the received production tasks. For example, urgent tasks or tasks requiring immediate execution are assigned high priority, tasks requiring prompt completion but not affecting the production line are assigned medium priority, and non-urgent tasks that can be executed later are assigned low priority. Then, the task allocation module extracts the current status information of each robot from monitoring data, including the robot's current hardware configuration, current battery level and load, and working status. Based on a preset scoring system, it calculates a suitability score based on the acquired task requirements and robot status. The suitability score then determines the matching robot, and the production tasks are assigned accordingly. The task strategy is distributed to the matched robot. The resource sharing module analyzes the data uploaded by each robot, obtains the task execution progress and resource usage of each robot in the system in real time, and synchronizes the acquired data to each robot in real time to achieve overall system data synchronization, improving system collaboration efficiency and real-time performance. At the same time, the resource sharing module analyzes the uploaded data to determine whether the robot is experiencing resource shortages or overload, such as hardware module failure or excessive load. When resource shortages or overload occur, a resource sharing request is generated, the uploaded data is analyzed to identify idle resources, and a resource sharing plan is generated based on the resource sharing request and idle resources. This plan is then distributed to the robot, which automatically allocates resources according to the distributed resource sharing plan. For example, the receiver and the sharer can coordinate through wireless communication to share idle resources; or wireless communication can be used to control idle robots to perform part of the tasks for overloaded robots, improving the system's resource utilization rate.

[0071] Please see Figure 6 In some embodiments, the intelligent energy management system includes an energy consumption optimization module and a power management module; wherein,

[0072] The energy consumption optimization module is used to extract energy consumption data from monitoring data; analyze production tasks to determine task priorities; and input the energy consumption data and task priorities into a large model for processing to obtain energy consumption optimization strategies.

[0073] The power management module is used to analyze execution data, determine task load data, and determine the load level based on the task load data and preset thresholds; extract data from monitoring data to obtain power monitoring data; determine the power allocation scheme based on the load level and power monitoring data; compare the power monitoring data with preset thresholds, and if the power monitoring data is less than or equal to the preset thresholds, switch to backup power and charge the power supply before the switch.

[0074] In some embodiments, the cloud control platform sets up an intelligent energy management system for energy allocation and management. The intelligent energy management system includes an energy consumption optimization module and a power management module to achieve energy consumption optimization and energy management, respectively. The energy consumption optimization module acquires real-time monitoring data from each robot, extracts energy consumption information for each robot, including its battery level, current load, and running modules. It analyzes the extracted energy consumption information using a large model, adjusts energy allocation and power configuration based on the robot's task load and priority, generates an energy consumption optimization strategy, and sends it to the robot. The robot reduces its own power or optimizes energy consumption according to the energy consumption optimization strategy, allocating more resources to the modules performing tasks. For example, the large model analyzes the energy consumption of each robot. The system analyzes power consumption data to reduce the power of robots performing low-priority tasks or with low loads, thereby minimizing unnecessary energy consumption. For robots performing high-priority or high-load tasks, modules unrelated to the task are shut down, and power is prioritized for relevant modules to optimize robot energy consumption and ensure task execution. Based on the analysis results of the large model, the power management module monitors the power information and load level of each robot in real time, allocating more power to robots with high load levels to ensure the continuity and efficiency of robot task execution. Robots with low load levels are switched to energy-saving mode to reduce energy consumption. The system monitors the power supply in real time, and when the power supply falls below a certain threshold, it switches to the backup power supply and charges the low-power power supply during task execution intervals.

[0075] Please see Figure 7 In some embodiments, the adaptive software system includes a task customization module and an interactive feedback module; wherein,

[0076] The task customization module is used to analyze external input requests, determine the task mode, and generate custom production tasks based on the task mode. The task mode includes task type, module configuration, execution parameters, resource allocation strategy, and fault response strategy.

[0077] The interactive feedback module is used to generate feedback reports based on monitoring data and execution data, and send the feedback reports, monitoring data, and execution data to the human-computer interaction interface so that the human-computer interaction interface can display the feedback reports, monitoring data, and execution data.

[0078] In some embodiments, in addition to the production tasks being published to the cloud control platform by the intelligent production system, users can customize production tasks according to their needs and send them to the cloud control platform through an adaptive software system. The adaptive software system includes a task customization module and an interactive feedback module to enable user-defined functions and human-machine interaction feedback. The task customization module has an open interface, through which users can customize task modes and module configurations according to production needs, including custom task types, corresponding process steps, hardware modules required to execute the production task, and execution parameters. The task customization module determines the corresponding task requirements based on the user-defined content, assigns appropriate task priorities, dynamically adjusts the system's execution parameters, and matches the requirements. The corresponding robots execute user-defined production tasks, improving the system's task adaptability. The interactive feedback module features an interface through which the cloud control platform displays the task configuration interface, allowing users to customize tasks. The interactive feedback module statistically analyzes the data uploaded by each robot, displaying information such as robot status, task progress, and energy consumption on the interactive interface for real-time viewing and control by the user. Simultaneously, the interactive feedback module records relevant data from the tasks completed by the robots, analyzing and statistically obtaining key task execution data such as success rate, task time, and fault information, and generating feedback reports. Users obtain these feedback reports through the interactive interface and improve task processes and strategies based on them.

[0079] Please see Figure 8 In some embodiments, the experience-sharing system includes a task experience base and a model update module; wherein,

[0080] Task experience library, used to record execution data;

[0081] The model update module is used to classify the task experience base, update the large model according to the classified task experience base, and obtain model parameters; aggregate the obtained local parameters to obtain the first parameter, and optimize the large model according to the first parameter to obtain the optimized large model.

[0082] In some embodiments, the cloud control platform has a task experience pool that records execution data uploaded by each robot, including task parameters, environmental conditions, success rate, and reasons for failure. The task experience pool manages the recorded task execution data by labeling and classifying the data into different types, such as different task types and different execution strategies. The system extracts different types of data from the task experience pool at regular intervals as training samples to train and optimize the large model set on the cloud control platform, adjusting model parameters to improve the adaptability of the large model to different tasks and thus improve task execution efficiency. The experience sharing system in the cloud control platform also has a model update module, which can extract sample data from the task experience pool to train the large model, fine-tune the model parameters, and achieve group learning. The large model learns the execution experience of different tasks. The model update module distributes the updated large model to each robot, and the edge computing module in the robot distributes the large model. As a local model, the edge computing module processes the data and status information collected by the robot, improving the intelligence level of each robot. After the large model is distributed to the robot, the edge computing module updates the local model locally based on the robot's current task execution data and environmental data to make the local model more adaptable to the robot's current environment. The edge computing module adjusts the parameters of the local model in real time based on the current environment and task execution data, and uploads the adjusted local model parameters to the cloud control platform at a set upload cycle. The model update module assigns corresponding weights based on the task completion volume or data volume of different robots. The model update module then performs a weighted combination of the model parameters uploaded by different robots according to the assigned weights to obtain global model parameters. Through a federated learning mechanism, the global model parameters are integrated into the large model to improve the real-time performance and adaptability of the large model. Model distribution can improve the robot's adaptive adjustment in different production environments.

[0083] In some embodiments, the robot's hardware modules include any combination of gripper modules, motion modules, sensing modules, or arm and joint modules; wherein,

[0084] The gripper module, the movement module, and the arm and joint module are used to provide replaceable hardware components for the robot;

[0085] The sensing module is used to collect data on the robot's current environment, obtain environmental data, and send the environmental data to the edge computing module.

[0086] In some embodiments, the robot's hardware modules are part of the robot and can be categorized into any combination of gripper modules, movement modules, sensing modules, or arm and joint modules, depending on the application. The gripper module is equipped with different grippers depending on the type of production task to adapt to workpieces of different materials and shapes, such as magnetic grippers, pneumatic grippers, or flexible grippers, improving the robot's gripping flexibility and stability. The movement module is equipped with different movement components depending on the production environment, such as wheeled, tracked, or robotic leg modules. The system selects the appropriate movement module based on real-time collected environmental data to achieve the optimal movement method and improve the robot's task execution efficiency. The sensing module integrates multiple sensors, including vision sensors, LiDAR, depth cameras, and various environmental sensors. The sensing module perceives the robot's environment and task-related workpiece information in real time and generates environmental data. The arm and joint module includes a multi-degree-of-freedom robotic arm and joint structure to enable the robot to perform precise operations and multi-angle task execution, meeting the diverse needs of performing different types of tasks.

[0087] In some embodiments, the edge computing module is also used to receive environmental data and upload the environmental data to the cloud control platform; analyze the monitoring data, determine the task progress data, and upload the task progress data to the cloud control platform; parse the task strategy or optimization strategy, extract control instructions, and control the robot according to the control instructions; monitor the robot's power data, compare the power data with a preset value, and if the power data is less than or equal to the preset value, control the robot to switch to energy-saving mode.

[0088] In some embodiments, the edge computing module installed in the robot is also responsible for preprocessing the data collected by the robot and the data sent from the cloud control platform, extracting key information from the data, and reducing data transmission latency. Simultaneously, the edge computing module is also responsible for communication between the cloud control platform and the robot, improving the system's real-time response capability. In this embodiment, the edge computing module sends environmental data collected by the hardware module to the cloud control platform, monitors and analyzes the robot's status and task execution status in real time, determines the task progress of the robot's current production task, and uploads the task progress to the cloud control platform so that the remote control platform can monitor the status information of each robot in real time. The edge computing module parses the task strategies or optimization strategies sent from the cloud control platform to determine the control instructions, such as hardware module configuration, planned paths, and execution parameters. The edge computing module controls the robot according to the parsed control instructions. The edge computing module monitors the robot's battery information in real time. When the battery information is lower than a preset value, the edge computing module controls the robot to switch to energy-saving mode or adjusts the task execution parameters in real time to reduce energy consumption.

[0089] In some embodiments, the edge computing module is further configured to update the robot's local model with model parameters to obtain an updated local model; acquire the robot's current environment data and current execution data, adjust the parameters of the updated local model based on the current environment data and current execution data to obtain updated local model parameters; encrypt the updated local model parameters to obtain encrypted data, and upload the encrypted data to the cloud control platform.

[0090] In some embodiments, the edge computing module receives a large model from the cloud control platform and improves the robot's intelligence level based on the large model. It also periodically uploads the robot's local model parameters to the cloud control platform so that the platform can update the large model, learn from its experience in performing tasks on different robots, and improve the overall intelligence level of the system. In this embodiment, the edge computing module updates the robot's local model with the parameters of the large model sent from the cloud control platform, or uses the large model as the robot's new local model. The edge computing module adjusts the parameters of the new local model in real time based on the robot's current environmental data and task execution data, improving the adaptability of the new local model to the tasks performed by the robot. Furthermore, the edge computing module encrypts the adjusted local model parameters according to a preset upload cycle to improve data security before uploading the encrypted local model parameters to the cloud control platform for integration and updating into the large model, thereby improving the overall intelligence level of the system.

[0091] The solutions of the embodiments of the present invention will be described in detail below with reference to specific application examples:

[0092] Please see Figure 9The cloud control platform receives tasks from the intelligent production system. The robot uses sensors such as vision and lidar in its sensing module to collect environmental data in real time, including workpiece position, terrain features, and obstacle information. This data is then uploaded to the cloud control platform via wireless communication. The cloud control platform analyzes the task type, target location, and working conditions using a large model. If the task is determined to be a material handling task, the appropriate fixture module is used for workpiece handling. Further analysis of the uploaded environmental data determines the terrain, obstacle locations, and characteristics of the production site. If the terrain is flat, a wheeled mobile module can be used to improve task execution efficiency. Based on the analysis results, the cloud control platform uses the large model to further refine its design. The process involves path planning, module selection, task execution parameters determination, and generation of a task strategy for the production task. The cloud control platform analyzes the task requirements using a large-scale model, including task urgency, type, and deadline, assigning the task a high priority. Simultaneously, the large-scale model analyzes data uploaded from the robot's edge computing module and the production task, including robot location, resource status, and task requirements, determining the suitability score for different robots for the current task. Based on task priority and suitability score, the task strategy is assigned to the robot with the highest score. The edge computing module then controls the robot to execute the production task according to the task strategy, and the sensor module... The system uploads robot task execution data and environmental change data in real time. The cloud control platform uses a large-scale model to identify the data uploaded by the edge computing module. If an obstacle is detected in front of the robot, the system determines it to be a moderate event based on the large-scale model. The large-scale model analyzes the uploaded data and plans an optimization strategy based on the current environmental data and task execution progress, then distributes it to the robot. The robot's edge computing module controls the robot to navigate around the obstacle according to the optimization strategy. The large-scale model is updated to the task experience base based on the data uploaded by the edge computing module. The system updates the parameters of the large-scale model based on the task experience base and distributes the updated large-scale model to all robots. The robot's edge computing module then displays the updated large-scale model. As a local model, the system analyzes the energy consumption of uploaded data using a large model to determine if the robot's energy consumption is high. The system then generates an energy optimization strategy based on the large model and distributes it to the robot. The robot's edge computing module adjusts the power of each module according to the optimization strategy to optimize overall energy consumption. The system also analyzes uploaded data in real-time using the large model to identify robot malfunctions, such as vision sensor failures. In such cases, the system analyzes data uploaded by all robots and coordinates nearby robots to share idle vision sensors to complete production tasks. Finally, the system records all task execution data uploaded by the robots, generates task reports, and displays them through an interactive interface.

[0093] Implementing this embodiment of the invention has the following beneficial effects: This embodiment provides a control system for a cloud-based collaborative robot. The system includes a cloud control platform and a robot. The robot includes an edge computing module and a hardware module. The hardware module collects environmental data and sends the environmental data to the cloud control platform via the edge computing module, and provides hardware components for the robot to execute production tasks. The edge computing module monitors the robot's status and feeds back the robot's status to the cloud control platform. It controls the robot to execute production tasks according to task strategies and optimization strategies, feeds back execution data to the cloud control platform, updates the parameters of the local model according to the model parameters, and sends the updated model parameters to the cloud control platform. The cloud control platform receives the production tasks and, according to the large model... The system analyzes production tasks and environmental data to obtain task strategies; it determines optimization strategies based on execution data, monitoring data, and environmental data; it updates the large model based on environmental data, local parameters, and the task experience pool; and it distributes the obtained task strategies, optimization strategies, and large model parameters to the robot. Through the edge computing module and cloud control platform, it formulates task strategies and optimization strategies based on the collected data, controls the robot to execute production tasks, achieves adaptive task scheduling and optimization, and improves task execution efficiency and collaborative control efficiency. It also establishes a task experience pool, edge computing module, and large model for experience sharing, optimizes large model parameters, improves the accuracy and efficiency of formulating task strategies and optimization strategies, and thus improves task execution efficiency and collaborative control efficiency.

[0094] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A control system for a cloud-based collaborative humanoid robot, characterized in that, The system includes a cloud control platform and a humanoid robot, the humanoid robot comprising an edge computing module and a hardware module; wherein... The hardware module is used to collect environmental data and send the environmental data to the cloud control platform via the edge computing module; it also provides hardware components to enable the humanoid robot to perform production tasks. The edge computing module is used to monitor the status of the humanoid robot, obtain monitoring data, and send it to the cloud control platform; control the humanoid robot to execute the production task according to the task strategy and optimization strategy, and feed back the execution data to the cloud control platform; update the parameters of the local model according to the execution data, the environmental data, and the model parameters to obtain local parameters, and send the local parameters to the cloud control platform. The cloud control platform is used to receive the production task, input the production task and the environmental data into a large model for analysis, and determine the task strategy; determine the optimization strategy based on the execution data, the monitoring data, and the environmental data; update the large model based on the environmental data, the local parameters, and the task experience pool to obtain the model parameters; and distribute the task strategy, the optimization strategy, and the model parameters to the humanoid robot; wherein, updating the large model includes collective learning and experience sharing based on the task strategy, the optimization strategy, and the model parameters.

2. The system according to claim 1, characterized in that, The cloud control platform includes any combination of intelligent decision-making systems, intelligent allocation systems, intelligent energy management systems, adaptive software systems, or experience-sharing systems; wherein, The intelligent decision-making system is used to perform deep learning based on the production task, the environmental data, and the large model to obtain the task strategy; process the execution data, environmental data, and the large model to obtain the optimization strategy; analyze the monitoring data, and if abnormal state data exists, analyze the abnormal state data to determine the solution; and generate a fault report based on the abnormal state data and the solution. The intelligent allocation system is used to analyze the production tasks and the monitoring data to determine a task allocation scheme; and to analyze the execution data and the monitoring data to determine a resource sharing scheme. The intelligent energy management system is used to analyze the monitoring data to determine energy consumption data, perform energy consumption analysis based on the production tasks, the energy consumption data, and the large model to determine energy consumption optimization schemes, and analyze the execution data and monitoring data to determine power allocation schemes. The adaptive software system is used to generate custom production tasks in response to external input; and to generate feedback reports based on the execution data and the monitoring data. The experience-sharing system is used to construct a task experience pool, update the task experience pool according to the execution data, update the parameters of the large model according to the task experience pool to obtain model parameters, and optimize the parameters of the large model according to the local parameters to obtain the optimized large model.

3. The system according to claim 2, characterized in that, The intelligent decision-making system includes a strategy generation module, a strategy optimization module, and a fault handling module; wherein... The strategy generation module is used to analyze the production task to obtain task characteristics, analyze the environmental data to obtain environmental characteristics, match the task characteristics and environmental characteristics with the task experience pool to determine a first scheme, input the task characteristics and environmental characteristics into the large model for analysis to obtain task type and environmental elements, and process the task type, environmental elements, first scheme and large model to obtain the task strategy. The strategy optimization module is used to analyze the execution data to determine task progress data, analyze the environmental data to determine environmental change data, and analyze the task progress data, environmental change data, the large model, and preset adjustment strategies to obtain the optimization strategy. The fault handling module is used to extract data from the monitoring data to obtain robot status data; identify abnormal events based on the large model and the robot status data; generate early warning information based on the abnormal events; determine the abnormal type based on the abnormal events; and determine the solution based on the abnormal type and the preset handling strategy.

4. The system according to claim 2, characterized in that, The intelligent allocation system includes a task allocation module and a resource sharing module; wherein... The task allocation module is used to analyze the production tasks and determine task priorities; analyze the monitoring data and determine robot status data; determine a suitability score based on the robot status data and a preset scoring relationship; and match the task priorities and the suitability scores to determine the task allocation scheme. The resource sharing module is used to analyze the monitoring data to determine resource usage data; analyze the execution data to determine resource requirements; determine resource sharing requests based on the resource usage data and resource requirements; and determine the resource sharing scheme based on the resource sharing requests and resource usage.

5. The system according to claim 2, characterized in that, The intelligent energy management system includes an energy consumption optimization module and a power management module; wherein... The energy consumption optimization module is used to extract energy consumption data from the monitoring data; analyze the production tasks to determine task priorities; and input the energy consumption data and task priorities into the large model for processing to obtain an energy consumption optimization strategy. The power management module is used to analyze the execution data, determine the task load data, and determine the load level based on the task load data and a preset threshold; extract data from the monitoring data to obtain power monitoring data; determine a power allocation scheme based on the load level and the power monitoring data; compare the power monitoring data with a preset threshold, and if the power monitoring data is less than or equal to the preset threshold, switch to a backup power supply and charge the power supply before the switch.

6. The system according to claim 2, characterized in that, The adaptive software system includes a task customization module and an interactive feedback module; wherein... The task customization module is used to analyze the external input request, determine the task mode, and generate a custom production task according to the task mode; wherein, the task mode includes task type, module configuration, execution parameters, resource allocation strategy and fault response strategy; The interactive feedback module is used to generate a feedback report based on the monitoring data and the execution data, and send the feedback report, the monitoring data and the execution data to the human-computer interaction interface so that the human-computer interaction interface can display the feedback report, the monitoring data and the execution data.

7. The system according to claim 2, characterized in that, The experience-sharing system includes a task experience database and a model update module; wherein... The task experience base is used to record the execution data; The model update module is used to classify the task experience base, update the large model according to the classified task experience base to obtain model parameters; aggregate the obtained local parameters to obtain a first parameter, and optimize the large model according to the first parameter to obtain the optimized large model.

8. The system according to claim 1, characterized in that, The hardware module includes any combination of clamping modules, movement modules, sensing modules, or arm and joint modules; wherein... The clamping module, the moving module, and the arm and joint module are used to provide replaceable hardware components for the humanoid robot. The sensing module is used to collect data on the current environment of the humanoid robot, obtain the environmental data, and send the environmental data to the edge computing module.

9. The system according to claim 1, characterized in that, The edge computing module is also used to receive the environmental data and upload it to the cloud control platform; analyze the monitoring data to determine the task progress data and upload it to the cloud control platform; parse the task strategy or the optimization strategy, extract control instructions, and control the humanoid robot according to the control instructions; monitor the power data of the humanoid robot, compare the power data with a preset value, and if the power data is less than or equal to the preset value, control the humanoid robot to switch to energy-saving mode.

10. The system according to claim 1, characterized in that, The edge computing module is also used to update the parameters of the humanoid robot's local model using the model parameters to obtain an updated local model; acquire the current environment data and current execution data of the humanoid robot, adjust the parameters of the updated local model based on the current environment data and the current execution data to obtain updated local model parameters; encrypt the updated local model parameters to obtain encrypted data, and upload the encrypted data to the cloud control platform.

Images