Inspection robot charging control system and charging device thereof

Abstract

The invention discloses an inspection robot charging control system and a charging device thereof, relates to the technical field of inspection robots, and realizes the optimal balance of the inspection robot between the charging demand and task execution through a dynamic task and a charging scheduling algorithm. Data such as the position, the electric quantity, the current task state and the environment condition of the robot are monitored in real time; edge computing nodes are deployed in an inspection area, sensor data are processed and analyzed in real time, the burden of a central server is relieved, and data transmission delay is reduced; based on the characteristics of the inspection task and the movement track of the robot, charging points are flexibly arranged in the inspection area; through Internet of Things data analysis, the positions and the number of charging points are dynamically adjusted, and the return problem caused by fixed charging points is avoided; the mobile charging station actively goes to the position of the robot for charging according to the position and the electric quantity state of the robot, and the return time of the robot is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection robots, and in particular to a charging control system and a charging device of an inspection robot. Background Art

[0002] With the development of technologies such as computer vision and machine learning, the performance and functions of inspection robots have been continuously improved. The application of inspection robots has become more and more extensive, and the market demand has also been growing.

[0003] For example, the patent with publication number CN115986864A discloses a charging control system and method for a substation inspection robot. The system includes a battery management module and a charging management module that communicate with each other; the charging management module is used to obtain the battery pack charging voltage, battery pack matching mode and battery core material information when the charging device limit signal is detected to be valid, and control the charger to match the charging voltage output; the battery management module includes at least two independent chargers, and the chargers are initially in a non-charged state; the corresponding charging strategy is generated according to the robot battery pack voltage: when the robot battery pack voltage is lower than the preset threshold, all chargers are used in a simultaneous working mode; when the robot battery pack voltage is not lower than the preset threshold, the chargers are used in an alternating time-sharing mode.

[0004] The current patrol robot charging control system has problems with the utilization rate of charging piles. The utilization efficiency of charging stations cannot be coordinated with the efficiency of robot task completion, resulting in congestion at charging stations and obstruction of patrol tasks: when multiple robots need to be charged at the same time, congestion at charging stations is likely to occur, causing robots to wait in line, affecting the overall patrol efficiency; in addition, the robots need to return to fixed charging stations for charging, resulting in interruption of patrol tasks and increased return time. Therefore, there is an urgent need for a patrol robot charging control system and its charging device to solve such problems. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a patrol robot charging control system and a charging device thereof, which solve the problem in the prior art that when multiple robots need to be charged at the same time, congestion at the charging station is likely to occur, causing the robots to wait in line, affecting the overall patrol efficiency; and the robots need to return to fixed charging stations for charging, resulting in interruption of the patrol mission and increased return time.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a patrol robot charging control system, the patrol robot charging control system architecture comprises: a robot unit, an Internet of Things sensor network, an edge computing node, and a cloud platform; edge computing nodes are deployed in the patrol area to build an Internet of Things sensor network, and sensor data is processed and analyzed in real time; based on the Internet of Things sensor network and the edge computing nodes, a multi-robot collaborative scheduling algorithm is adopted, and a global scheduling decision output is performed in combination with the power of each robot, the urgency of the task, the current task progress, and the availability of charging stations; at the same time, different priorities are assigned according to the importance and urgency of the task, so as to ensure that the robot with a high priority task is not interrupted during charging; the overall architecture of the patrol robot charging control system comprises a robot unit, an Internet of Things sensor network, an edge computing node, and a cloud platform, and global scheduling of robot charging and tasks is achieved through these modules, and an optimal balance between the robot's charging demand and task execution is achieved through the multi-robot collaborative scheduling algorithm, thereby improving patrol efficiency, reducing charging waiting time and task interruption; The present invention is further configured that the robot unit comprises: a power management module, a task management module and a communication module; The IoT sensor network includes: data acquisition module and data transmission module; The edge computing node includes: data processing module and preliminary decision module; The cloud platform includes: data storage module, data analysis module and advanced decision-making module; Power management module, including: The power monitoring unit monitors the battery power of the robot in real time, sends power status data, uses AI models to predict power consumption trends, and plans charging in advance; Battery health unit, which monitors battery temperature, voltage, and charge and discharge cycle times to estimate battery life; Task management module, including: The task execution unit manages the tasks currently executed by the robot, updates the task progress in real time, and adjusts the task priority and path planning in real time in combination with edge computing; The task scheduling unit collaborates with the cloud platform and edge computing nodes to dynamically adjust task allocation and execution order; Communication module, including: Wireless communication unit, which communicates with edge computing nodes and cloud platforms to transmit data in real time and receive instructions; A local communication unit that communicates with nearby mobile charging stations to coordinate charging arrangements; Data acquisition module, including: Environmental monitoring unit, which collects environmental data, including temperature, humidity, and obstacle locations, to assist the robot in making decisions; Position tracking unit to locate robots and charging stations in real time; Data transmission module, including: Wireless transmission unit: transmits data from the sensor to the edge computing node in real time through wireless communication protocol; Data synchronization unit: synchronizes sensor data with cloud platform data; Data processing module, including: A real-time data processing unit processes the real-time data transmitted from sensors and robot units and performs preliminary analysis and filtering; The prediction model unit uses machine learning algorithms to predict the robot's power consumption and task completion time; Preliminary decision-making module, including: The task optimization unit adjusts task priorities and optimizes paths based on real-time data and prediction results; The charging scheduling unit generates a preliminary charging scheduling plan based on power forecast and task urgency, and sends it to the cloud platform for confirmation; Data storage module, including: Historical data storage unit, used to store historical data of robot operation for model training and trend analysis; A real-time data storage unit, used to store real-time data transmitted from the edge computing node; Data analysis modules, including: Advanced analytics unit for in-depth data analysis; Model training unit, which optimizes prediction and scheduling models based on historical data and real-time data; Advanced decision-making modules, including: The global optimization unit generates globally optimized tasks and charging scheduling solutions based on the status and tasks of all robots; The present invention is further configured to construct an Internet of Things sensor network, arrange multiple sub-areas in the inspection area, distribute multiple robots and sensors in each sub-area, and deploy edge computing nodes in the main inspection path; by arranging sensors and edge computing nodes in different areas, data transmission delay is reduced, and the real-time and accuracy of data processing are improved: The entire inspection area is divided into multiple sub-areas, and multiple robots and multiple sensors are distributed in each sub-area; Edge computing nodes are deployed in the main inspection paths and areas with frequent tasks in the sub-areas. Sensors and robots in each sub-area communicate with adjacent edge nodes and send data to adjacent edge computing nodes. The node receives and caches real-time data streams, performs data cleaning and preprocessing, filters out noise data, and formats raw data; Conduct data analysis and decision-making, and make preliminary analysis of data, including power forecasting and task progress assessment; Based on the analysis results, generate preliminary task adjustment and charging scheduling decisions and send the results to the robot unit; Regularly upload processed analysis results and model updates to the cloud platform; Regularly obtain the latest machine learning models from the cloud platform and update the models on the edge computing nodes; The present invention is further configured to perform data cleaning and preprocessing, use the moving average method to perform data smoothing, and use LSTM to perform power forecasting, so as to improve the accuracy of power forecasting and task progress evaluation and optimize scheduling decisions: Perform data cleaning and preprocessing to remove erroneous sensor readings from the data; convert the raw data into a unified format and normalize the data to scope: ,in is the original data, is the normalized data, is the minimum value of the data, is the maximum value of the data; Use a moving average to smooth the data: ,in For the moment The smoothed data, For the moment The original data, is the smoothing window size, Represents the index of the data point within the smoothing window; Use long short-term memory network LSTM for power forecasting, model formula: ; ; ; ,in is the hidden state vector, Represents the input vector, including the current power and task status, is the Sigmoid activation function, , is the weight matrix, and represents the bias term, Represents the state of the memory unit, It is the gate unit of LSTM; Use historical electricity data to train the LSTM model and adjust the weights and bias terms through the back-propagation algorithm; Use the trained LSTM model to predict the power consumption at future times: ,in is the predicted power at the next moment, Indicates the current power level; Perform task progress evaluation, task status parameters include task start time , Estimated completion time , Current time , task progress The calculation formula is: ,in Indicates the task progress percentage. Indicates the task start time. Indicates the estimated completion time of the task. is the current time; Predict the completion time of a task using a linear regression model: ,in represents the predicted completion time, Represents the task feature vector, including task type, task difficulty, and current progress. represents the weight vector, is the bias term; Make preliminary mission adjustments and charging scheduling decisions; The present invention is further configured to achieve efficient scheduling of tasks and charging by optimizing models and constraints, reduce robot waiting time, and ensure continuous execution of high-priority tasks. The preliminary task adjustment and charging scheduling decision steps include: Build a decision model, the decision parameters include the robot's power , Task Priority , Task Progress , Charging station availability , the optimization goal is defined as: minimizing the task interruption time and charging waiting time while maximizing the continuity of high priority tasks, then: ,in Represents the weight coefficient, which respectively represents the importance of task interruption time, charging waiting time and task priority, Representation Task The interruption time, It is a charging station The waiting time, Representation Task The priority factor of The constraints are: Robot power constraints: ,in It's a robot At the moment of electricity, It is the minimum safe power; Charging station capacity constraints: ,in It is a charging station At the moment Availability, Indicates the maximum capacity of the charging station; Based on the power forecast and task progress evaluation results, low-power robots are dispatched to available charging stations first, and a preliminary dispatch plan is generated based on task priority: ,in It is the scheduling plan; Send preliminary task adjustment and charging scheduling decision results to the robot unit to execute the scheduling instructions; The present invention is further configured such that the global scheduling decision output mode is: Define task priority parameters by assigning different priorities (high, medium, low) based on the importance and urgency of the task; Construct a global scheduling decision model with the objective function of minimizing task interruption time and charging waiting time while maximizing the continuity of high-priority tasks; The constraints include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node and assign robots to charging stations; The edge nodes perform local optimization based on real-time data and adjust tasks and charging plans; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; Use reinforcement learning (RL) to perform global optimization on the cloud platform and generate a scheduling solution; The globally optimized scheduling plan is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies; through global scheduling decisions and real-time optimization, the system's response speed and overall efficiency are improved; The present invention is further configured such that the global scheduling decision output step comprises: Each task is assigned a priority parameter , the priority parameter is divided into three values, high ,middle ,Low ; A global scheduling decision model is constructed, and the objective function is defined as: minimizing the task interruption time and charging waiting time, while maximizing the continuity of high-priority tasks, that is, ,Constraints also include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node, assign robots to charging stations, and optimize according to current power, task progress, and charging station availability; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; The reinforcement learning RL algorithm is used for global optimization on the cloud platform. The state, action, reward and objective function of the RL model are defined as: state : The current system status, including robot battery level, mission status, and charging station availability; action : Scheduling decisions under the current state, including task allocation and charging plan; award : The immediate reward calculated according to the objective function: ; Goal: Maximize cumulative rewards : ,in is the discount factor; The scheduling plan optimized by RL on the cloud platform is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies; The present invention also provides a charging device of a patrol robot charging control system, which uses the above-mentioned patrol robot charging control system. The charging device is arranged based on the characteristics of the patrol task and the robot activity trajectory, and dynamically adjusts the location and number of charging points based on the Internet of Things data analysis results of the data analysis module. The charging device includes: Fixed charging stations, including: Charging management unit, monitoring the charging process; A communication unit, which communicates with the robot unit and the cloud platform to receive and execute charging scheduling instructions; Mobile charging stations, including: The positioning and navigation unit actively moves to the vicinity of the robot for charging according to the robot's position and charging needs; A charging coordination unit that coordinates charging time and sequence with multiple robots; The present invention is further configured that the charging device is arranged in the following manner: Collect historical inspection task data, analyze the frequency, location and path of inspection tasks, and output key inspection areas and high-frequency inspection paths; Based on the results of task analysis, the initial fixed charging points are arranged in the inspection area, covering areas with frequent tasks and path intersections; reducing the initial return distance of the robot; IoT sensors are deployed in the inspection area to monitor the robot's position and power in real time, and upload the information to the edge computing node and cloud platform in real time; The location and number of charging points are dynamically adjusted as follows: Real-time monitoring of the usage of each fixed charging point, statistics on charging frequency, charging time and congestion; Dynamically adjust the location and number of charging points based on real-time and historical data; add temporary charging points in areas with high charging demand; The mobile charging station is equipped with a navigation system, which will proactively go to the robot's location for charging based on the robot's location and power status.

[0007] Compared with the prior art, the present invention has the following beneficial effects: This application is based on IoT technology and edge computing, and achieves the optimal balance between the inspection robot's charging needs and task execution through dynamic tasks and charging scheduling algorithms: The present invention arranges IoT sensors in the inspection area to monitor the robot's position, power, current task status, environmental conditions and other data in real time; and deploys edge computing nodes in the inspection area to process and analyze sensor data in real time, reducing the burden on the central server and data transmission delay; The present invention flexibly arranges charging points in the inspection area based on the characteristics of the inspection task and the activity trajectory of the robot; dynamically adjusts the location and number of charging points through IoT data analysis to avoid the return trip problem caused by fixed charging points; the mobile charging station actively goes to the location of the robot to charge according to the location and power status of the robot, thereby reducing the return trip time of the robot; The present invention, based on the Internet of Things and edge computing technology, adopts a multi-robot collaborative scheduling algorithm, combines the power of each robot, the urgency of the task, the current task progress and the availability of the charging station, and outputs a global scheduling decision. At the same time, different priorities are assigned according to the importance and urgency of the task, so that high-priority tasks are not interrupted when the robot is charging; The present invention solves the problem that when multiple robots need to be charged at the same time, the charging station is prone to congestion, causing the robots to wait in line and affecting the overall inspection efficiency; the robots need to return to fixed charging stations for charging, resulting in the interruption of inspection tasks and increased return time. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 This is a framework diagram of the inspection robot charging control system of the present invention. DETAILED DESCRIPTION

[0009] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0010] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0011] The present invention is further described in detail below in conjunction with the accompanying drawings: Example 1 See also Figure 1 The present invention provides a patrol robot charging control system, the patrol robot charging control system architecture includes: robot unit, Internet of Things sensor network, edge computing node, cloud platform; deploy edge computing nodes in the patrol area, build an Internet of Things sensor network, and process and analyze sensor data in real time; based on the Internet of Things sensor network and edge computing nodes, a multi-robot collaborative scheduling algorithm is adopted to combine the power of each robot, the urgency of the task, the current task progress and the availability of the charging station to output a global scheduling decision; at the same time, different priorities are assigned according to the importance and urgency of the task to ensure that the robot with high priority task is not interrupted during charging; The robot unit includes: a power management module, a task management module and a communication module; The IoT sensor network includes: data acquisition module and data transmission module; The edge computing node includes: data processing module and preliminary decision module; The cloud platform includes: data storage module, data analysis module and advanced decision-making module; Power management module, including: The power monitoring unit monitors the battery power of the robot in real time, sends power status data, uses AI models to predict power consumption trends, and plans charging in advance; Battery health unit, which monitors battery temperature, voltage, and charge and discharge cycle times to estimate battery life; Task management module, including: The task execution unit manages the tasks currently executed by the robot, updates the task progress in real time, and adjusts the task priority and path planning in real time in combination with edge computing; The task scheduling unit collaborates with the cloud platform and edge computing nodes to dynamically adjust task allocation and execution order; Communication module, including: Wireless communication unit, which communicates with edge computing nodes and cloud platforms to transmit data in real time and receive instructions; A local communication unit that communicates with nearby mobile charging stations to coordinate charging arrangements; Data acquisition module, including: Environmental monitoring unit, which collects environmental data, including temperature, humidity, and obstacle locations, to assist the robot in making decisions; Position tracking unit to locate robots and charging stations in real time; Data transmission module, including: Wireless transmission unit: transmits data from the sensor to the edge computing node in real time through wireless communication protocol; Data synchronization unit: synchronizes sensor data with cloud platform data; Data processing module, including: A real-time data processing unit processes the real-time data transmitted from sensors and robot units and performs preliminary analysis and filtering; The prediction model unit uses machine learning algorithms to predict the robot's power consumption and task completion time; Preliminary decision-making module, including: The task optimization unit adjusts task priorities and optimizes paths based on real-time data and prediction results; The charging scheduling unit generates a preliminary charging scheduling plan based on power forecast and task urgency, and sends it to the cloud platform for confirmation; Data storage module, including: Historical data storage unit, used to store historical data of robot operation for model training and trend analysis; A real-time data storage unit, used to store real-time data transmitted from the edge computing node; Data analysis modules, including: Advanced analytics unit for in-depth data analysis; Model training unit, which optimizes prediction and scheduling models based on historical data and real-time data; Advanced decision-making modules, including: The global optimization unit generates globally optimized tasks and charging scheduling solutions based on the status and tasks of all robots; Building an IoT sensor network and processing and analyzing sensor data in real time are as follows: The entire inspection area is divided into multiple sub-areas, and multiple robots and multiple sensors are distributed in each sub-area; Edge computing nodes are deployed in the main inspection paths and areas with frequent tasks in the sub-areas. Sensors and robots in each sub-area communicate with adjacent edge nodes and send data to adjacent edge computing nodes. The node receives and caches real-time data streams, performs data cleaning and preprocessing, filters out noise data, and formats raw data; Conduct data analysis and decision-making, and make preliminary analysis of data, including power forecasting and task progress assessment; Based on the analysis results, generate preliminary task adjustment and charging scheduling decisions and send the results to the robot unit; Regularly upload processed analysis results and model updates to the cloud platform; Regularly obtain the latest machine learning models from the cloud platform and update the models on the edge computing nodes; Data analysis and decision-making methods are: Perform data cleaning and preprocessing to remove erroneous sensor readings from the data; convert the raw data into a unified format and normalize the data to scope: ,in is the original data, is the normalized data, is the minimum value of the data, is the maximum value of the data; Use a moving average to smooth the data: ,in For the moment The smoothed data, For the moment The original data, is the smoothing window size, Represents the index of the data point within the smoothing window; Use long short-term memory network LSTM for power forecasting, model formula: ; ; ; ,in is the hidden state vector, Represents the input vector, including the current power and task status, is the Sigmoid activation function, , is the weight matrix, and represents the bias term, Represents the state of the memory unit, It is the gate unit of LSTM; Use historical electricity data to train the LSTM model and adjust the weights and bias terms through the back-propagation algorithm; Use the trained LSTM model to predict the power consumption at future times: ,in is the predicted power at the next moment, Indicates the current power level; Perform task progress evaluation, task status parameters include task start time , Estimated completion time , Current time , task progress The calculation formula is: ,in Indicates the task progress percentage. Indicates the task start time. Indicates the estimated completion time of the task. is the current time; Predict the completion time of a task using a linear regression model: ,in represents the predicted completion time, Represents the task feature vector, including task type, task difficulty, and current progress. represents the weight vector, is the bias term; Make preliminary mission adjustments and charging scheduling decisions; The initial task adjustment and charging scheduling decision steps include: Build a decision model, the decision parameters include the robot's power , Task Priority , Task Progress , Charging station availability , the optimization goal is defined as: minimizing the task interruption time and charging waiting time while maximizing the continuity of high priority tasks, then: ,in Represents the weight coefficient, which respectively represents the importance of task interruption time, charging waiting time and task priority, Indicates the task The interruption time, It is a charging station The waiting time, Indicates the task The priority factor of The constraints are: Robot power constraints: ,in It's a robot At the moment of electricity, It is the minimum safe power; Charging station capacity constraints: ,in It is a charging station At the moment Availability, Indicates the maximum capacity of the charging station; Based on the power forecast and task progress evaluation results, low-power robots are dispatched to available charging stations first, and a preliminary dispatch plan is generated based on task priority: ,in It is the scheduling plan; Send preliminary task adjustment and charging scheduling decision results to the robot unit to execute the scheduling instructions; The global scheduling decision output is as follows: Define task priority parameters by assigning different priorities (high, medium, low) based on the importance and urgency of the task; Construct a global scheduling decision model with the objective function of minimizing task interruption time and charging waiting time while maximizing the continuity of high-priority tasks; The constraints include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node and assign robots to charging stations; The edge nodes perform local optimization based on real-time data and adjust tasks and charging plans; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; Use reinforcement learning (RL) to perform global optimization on the cloud platform and generate a scheduling solution; The globally optimized scheduling plan is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies; The global scheduling decision output steps include: Each task is assigned a priority parameter , the priority parameter is divided into three values, high ,middle ,Low ; A global scheduling decision model is constructed, and the objective function is defined as: minimizing the task interruption time and charging waiting time, while maximizing the continuity of high-priority tasks, that is, ,Constraints also include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node, assign robots to charging stations, and optimize according to current power, task progress, and charging station availability; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; The reinforcement learning RL algorithm is used for global optimization on the cloud platform. The state, action, reward and objective function of the RL model are defined as: state : The current system status, including robot battery level, mission status, and charging station availability; action : Scheduling decisions under the current state, including task allocation and charging plan; award : The immediate reward calculated according to the objective function: ; Goal: Maximize cumulative rewards : ,in is the discount factor; The scheduling plan optimized by RL on the cloud platform is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies; The present invention also provides a charging device for a patrol robot charging control system. The charging device is arranged based on the patrol task characteristics and the robot activity trajectory, and dynamically adjusts the location and number of charging points based on the Internet of Things data analysis results of the data analysis module. The charging device includes: Fixed charging stations, including: Charging management unit, monitoring the charging process; A communication unit, which communicates with the robot unit and the cloud platform to receive and execute charging scheduling instructions; Mobile charging stations, including: The positioning and navigation unit actively moves to the vicinity of the robot for charging according to the robot's position and charging needs; A charging coordination unit that coordinates charging time and sequence with multiple robots; The charging device is arranged as follows: Collect historical inspection task data, analyze the frequency, location and path of inspection tasks, and output key inspection areas and high-frequency inspection paths; Based on the results of task analysis, the initial fixed charging points are arranged in the inspection area, covering areas with frequent tasks and path intersections; reducing the initial return distance of the robot; IoT sensors are deployed in the inspection area to monitor the robot's position and power in real time, and upload the information to the edge computing node and cloud platform in real time; The location and number of charging points are dynamically adjusted as follows: Real-time monitoring of the usage of each fixed charging point, statistics on charging frequency, charging time and congestion; Dynamically adjust the location and number of charging points based on real-time and historical data; add temporary charging points in areas with high charging demand; The mobile charging station is equipped with a navigation system, which will proactively go to the robot's location for charging based on the robot's location and power status.

[0012] The present invention deploys edge computing nodes in the inspection area, builds an Internet of Things sensor network, and realizes real-time processing and analysis of sensor data. The system adopts a multi-robot collaborative scheduling algorithm, combines the power of each robot, the urgency of the task, the current task progress and the status of the charging station to output a global scheduling decision, so that robots with high-priority tasks are not interrupted during charging. The robot unit includes a power management module, a task management module and a communication module; the power management module monitors the battery power in real time through the power monitoring unit, predicts the power consumption trend using the AI ​​model, and plans charging in advance; the battery health unit monitors the battery's temperature, voltage, and number of charge and discharge cycles, and estimates the battery life; the task management module includes a task execution unit, which manages the current task, updates the task progress in real time, and adjusts the task priority and path planning in real time in combination with edge computing; the task scheduling unit collaborates with the cloud platform and edge computing nodes to dynamically adjust task allocation and execution order; the communication module communicates with the edge computing nodes and the cloud platform through the wireless communication unit, transmits data in real time and receives instructions, and communicates with nearby mobile charging stations through the local communication unit to coordinate charging arrangements; The IoT sensor network includes a data acquisition module and a data transmission module; the data acquisition module consists of an environmental monitoring unit and a location tracking unit. The former collects environmental data to assist the robot in making decisions, while the latter locates the robot and charging station in real time. The data transmission module transmits sensor data to the edge computing node in real time through a wireless transmission unit, and synchronizes data with the cloud platform through a data synchronization unit. The edge computing node includes a data processing module and a preliminary decision-making module; the data processing module is responsible for processing the real-time data transmitted from the sensor and robot unit, performing preliminary analysis and filtering, and using the prediction model unit to use the machine learning algorithm to predict the robot's power consumption and task completion time; the preliminary decision-making module uses the task optimization unit and the charging scheduling unit to adjust the task priority and optimize the path according to the real-time data and prediction results, generate a preliminary charging scheduling plan, and send it to the cloud platform for confirmation; The cloud platform includes a data storage module, a data analysis module, and an advanced decision-making module; the data storage module stores historical data and real-time data, and supports model training and trend analysis; the data analysis module performs in-depth data analysis through an advanced analysis unit, and optimizes the prediction and scheduling model based on historical data and real-time data through a model training unit; the advanced decision-making module generates globally optimized tasks and charging scheduling plans based on the status and tasks of all robots through a global optimization unit; The charging device is arranged based on the characteristics of the inspection task and the robot's activity trajectory, and dynamically adjusts the location and number of charging points based on the results of IoT data analysis; the fixed charging station includes a charging management unit and a communication unit, which are responsible for monitoring the charging process and communicating with the robot unit and the cloud platform to execute charging scheduling instructions; the mobile charging station includes a positioning and navigation unit and a charging coordination unit, which can actively move to the vicinity of the robot for charging according to the robot's position and charging needs, and coordinate the charging time and sequence with multiple robots.

[0013] The above contents are only for explaining the technical idea of ​​the present invention and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution in accordance with the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A patrol robot charging control system, the patrol robot charging control system architecture includes: Robot unit, IoT sensor network, edge computing node, cloud platform; its characteristics are as follows: edge computing nodes are deployed in the inspection area to build an IoT sensor network to process and analyze sensor data in real time; based on the IoT sensor network and edge computing nodes, a multi-robot collaborative scheduling algorithm is adopted to output global scheduling decisions based on the power of each robot, the urgency of the task, the progress of the current task and the availability of charging stations; at the same time, different priorities are assigned according to the importance and urgency of the task to ensure that robots with high-priority tasks are not interrupted during charging.

2. A patrol robot charging control system according to claim 1, characterized in that: The robot unit includes: a power management module, a task management module and a communication module; The IoT sensor network includes: data acquisition module and data transmission module; The edge computing node includes: data processing module and preliminary decision module; The cloud platform includes: data storage module, data analysis module and advanced decision-making module; Power management module, including: The power monitoring unit monitors the battery power of the robot in real time, sends power status data, uses AI models to predict power consumption trends, and plans charging in advance; Battery health unit, which monitors battery temperature, voltage, and charge and discharge cycle times to estimate battery life; Task management module, including: The task execution unit manages the tasks currently executed by the robot, updates the task progress in real time, and adjusts the task priority and path planning in real time in combination with edge computing; The task scheduling unit collaborates with the cloud platform and edge computing nodes to dynamically adjust task allocation and execution order; Communication module, including: Wireless communication unit, which communicates with edge computing nodes and cloud platforms to transmit data in real time and receive instructions; A local communication unit that communicates with nearby mobile charging stations to coordinate charging arrangements; Data acquisition module, including: Environmental monitoring unit, which collects environmental data, including temperature, humidity, and obstacle locations, to assist the robot in making decisions; Position tracking unit to locate robots and charging stations in real time; Data transmission module, including: Wireless transmission unit: transmits data from the sensor to the edge computing node in real time through wireless communication protocol; Data synchronization unit: synchronizes sensor data with cloud platform data; Data processing module, including: A real-time data processing unit processes the real-time data transmitted from sensors and robot units and performs preliminary analysis and filtering; The prediction model unit uses machine learning algorithms to predict the robot's power consumption and task completion time; Preliminary decision-making module, including: The task optimization unit adjusts task priorities and optimizes paths based on real-time data and prediction results; The charging scheduling unit generates a preliminary charging scheduling plan based on power forecast and task urgency, and sends it to the cloud platform for confirmation; Data storage module, including: Historical data storage unit, used to store historical data of robot operation for model training and trend analysis; A real-time data storage unit, used to store real-time data transmitted from the edge computing node; Data analysis modules, including: Advanced analytics unit for in-depth data analysis; Model training unit, which optimizes prediction and scheduling models based on historical data and real-time data; Advanced decision-making modules, including: The global optimization unit generates globally optimized tasks and charging scheduling plans based on the status and tasks of all robots.

3. A patrol robot charging control system according to claim 2, characterized in that: Building an IoT sensor network and processing and analyzing sensor data in real time are as follows: The entire inspection area is divided into multiple sub-areas, and multiple robots and multiple sensors are distributed in each sub-area; Edge computing nodes are deployed in the main inspection paths and areas with frequent tasks in the sub-areas. Sensors and robots in each sub-area communicate with adjacent edge nodes and send data to adjacent edge computing nodes. The node receives and caches real-time data streams, performs data cleaning and preprocessing, filters out noise data, and formats raw data; Conduct data analysis and decision-making, and make preliminary analysis of data, including power forecasting and task progress assessment; Based on the analysis results, generate preliminary task adjustment and charging scheduling decisions and send the results to the robot unit; Regularly upload processed analysis results and model updates to the cloud platform; Regularly obtain the latest machine learning models from the cloud platform and update the models on the edge computing nodes.

4. A patrol robot charging control system according to claim 3, characterized in that: Data analysis and decision-making methods are: Perform data cleaning and preprocessing to remove erroneous sensor readings from the data; convert the raw data into a unified format and normalize the data to scope: ,in is the original data, is the normalized data, is the minimum value of the data, is the maximum value of the data; Use a moving average to smooth the data: ,in For the moment The smoothed data, For the moment The original data, is the smoothing window size, Represents the index of the data point within the smoothing window; Use long short-term memory network LSTM for power forecasting, model formula: ； ； ； ,in is the hidden state vector, Represents the input vector, including the current power and task status, is the Sigmoid activation function, , is the weight matrix, and represents the bias term, Represents the state of the memory unit, It is the gate control unit of LSTM; Use historical electricity data to train the LSTM model and adjust the weights and bias terms through the back-propagation algorithm; Use the trained LSTM model to predict the power consumption at future times: ,in is the predicted power at the next moment, Indicates the current power level; Perform task progress evaluation, task status parameters include task start time , Estimated completion time , Current time , task progress The calculation formula is: ,in Indicates the task progress percentage. Indicates the task start time. Indicates the estimated completion time of the task. is the current time; Predict the completion time of a task using a linear regression model: ,in represents the predicted completion time, Represents the task feature vector, including task type, task difficulty, and current progress. represents the weight vector, is the bias term; Make preliminary mission adjustments and charging scheduling decisions.

5. A patrol robot charging control system according to claim 4, characterized in that: The initial task adjustment and charging scheduling decision steps include: Build a decision model, the decision parameters include the robot's power , Task Priority , Task Progress , Charging station availability , the optimization goal is defined as: minimizing the task interruption time and charging waiting time while maximizing the continuity of high priority tasks, then: ,in Represents the weight coefficient, which respectively represents the importance of task interruption time, charging waiting time and task priority, Indicates the task The interruption time, It is a charging station The waiting time, Indicates the task The priority factor of The constraints are: Robot power constraints: ,in It's a robot At the moment of electricity, It is the minimum safe power; Charging station capacity constraints: ,in It is a charging station At the moment Availability, Indicates the maximum capacity of the charging station; Based on the power forecast and task progress evaluation results, low-power robots are dispatched to available charging stations first, and a preliminary dispatch plan is generated based on task priority: ,in It is the scheduling plan; The preliminary task adjustment and charging scheduling decision results are sent to the robot unit to execute the scheduling instructions.

6. A patrol robot charging control system according to claim 5, characterized in that: The global scheduling decision output is as follows: Define task priority parameters by assigning different priorities (high, medium, low) based on the importance and urgency of the task; Construct a global scheduling decision model with the objective function of minimizing task interruption time and charging waiting time while maximizing the continuity of high-priority tasks; The constraints include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node and assign robots to charging stations; The edge nodes perform local optimization based on real-time data and adjust tasks and charging plans; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; Use reinforcement learning (RL) to perform global optimization on the cloud platform and generate a scheduling solution; The globally optimized scheduling plan is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies.

7. A patrol robot charging control system according to claim 6, characterized in that: The global scheduling decision output steps include: Each task is assigned a priority parameter , the priority parameter is divided into three values, high ,middle ,Low ; A global scheduling decision model is constructed, and the objective function is defined as: minimizing the task interruption time and charging waiting time, while maximizing the continuity of high-priority tasks, that is, ,Constraints also include robot power constraints, charging station capacity constraints, and task priority constraints; Make preliminary scheduling decisions based on real-time data at the edge node, assign robots to charging stations, and optimize according to current power, task progress, and charging station availability; Upload the initial decisions and data of edge nodes to the cloud platform for global comprehensive analysis and optimization; The reinforcement learning RL algorithm is used for global optimization on the cloud platform. The state, action, reward and objective function of the RL model are defined as: state : The current system status, including robot battery level, mission status, and charging station availability; action : Scheduling decisions under the current state, including task allocation and charging plan; award : The immediate reward calculated according to the objective function: ; Goal: Maximize cumulative rewards : ,in is the discount factor; The scheduling plan optimized by RL on the cloud platform is sent to each robot through the edge node to execute the scheduling instructions; Edge nodes and cloud platforms monitor execution status in real time and dynamically adjust scheduling plans to deal with emergencies.

8. A charging device for a patrol robot charging control system, characterized in that: A patrol robot charging control system according to any one of claims 1 to 7 is used, the charging device is arranged based on the patrol task characteristics and the robot activity trajectory, and the location and number of charging points are dynamically adjusted based on the IoT data analysis results of the data analysis module, and the charging device includes: Fixed charging stations, including: Charging management unit, monitoring the charging process; A communication unit, which communicates with the robot unit and the cloud platform to receive and execute charging scheduling instructions; Mobile charging stations, including: The positioning and navigation unit actively moves to the vicinity of the robot for charging according to the robot's position and charging needs; The charging coordination unit coordinates the charging time and sequence with multiple robots.

9. A patrol robot charging control system according to claim 8, characterized in that: The charging device is arranged as follows: Collect historical inspection task data, analyze the frequency, location and path of inspection tasks, and output key inspection areas and high-frequency inspection paths; Based on the results of task analysis, the initial fixed charging points are arranged in the inspection area, covering areas with frequent tasks and path intersections; IoT sensors are deployed in the inspection area to monitor the robot's position and power in real time, and upload the information to the edge computing node and cloud platform in real time; The location and number of charging points are dynamically adjusted as follows: Real-time monitoring of the usage of each fixed charging point, statistics on charging frequency, charging time and congestion; Dynamically adjust the location and number of charging points based on real-time and historical data; add temporary charging points in areas with high charging demand; The mobile charging station is equipped with a navigation system, which will proactively go to the robot's location for charging based on the robot's location and power status.

Images