Unmanned aerial vehicle control system based on intelligent robot

Abstract

The invention provides an unmanned aerial vehicle control system based on an intelligent robot, which comprises a remote management platform, an aircraft, the intelligent robot and a honeycomb type centralized management station, and is characterized in that the remote management platform comprises an aircraft configuration module and an aircraft environment sensing and task processing function; the intelligent robot module is used for configuring a sensor, a camera, a hardware control unit and a software control framework for an intelligent robot; the site management module is used for performing internal monitoring, abnormity monitoring and collaborative management of the cellular centralized management station; the large model control module is used for performing closed-loop control on the system by using a plurality of models; and the monitoring and scheduling module is used for carrying out real-time monitoring, cooperative scheduling and fault response. According to the invention, robot cooperation can be used, automatic closed-loop management of flight of the aircraft is realized, personnel intervention is reduced, efficient scheduling, automatic control and maintenance of the aircraft are realized, and a safe, intelligent and extensible aircraft operation mode is provided.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft control, and in particular to an unmanned aircraft control system based on an intelligent robot. Background Art

[0002] An Unmanned Aerial Vehicle (UAV) is an aircraft driven by remote control or autonomous navigation technology and does not require a pilot on board. Aircraft use sensors, navigation systems, and communication modules to achieve flight operations. Currently, aircraft can be divided into military aircraft, commercial aircraft, consumer aircraft, and other categories according to their use. The use of aircraft can quickly complete many tasks that cannot be completed in a timely manner by manpower, such as searching for signs of life or quickly transporting supplies in disaster relief. In high-risk environments (such as war, fire, chemical leak sites, etc.), using aircraft instead of personnel to perform tasks can significantly reduce the risk of casualties. It can also be used in scientific research, entertainment and leisure, and has a wide range of application scenarios.

[0003] Currently, aircraft control is primarily manual, with operators using remote control devices (such as joysticks) to manually control the flight. This can lead to subjective errors, and complex missions place high demands on operators, as manual response times can be slow to keep up with changing emergency situations. Furthermore, research on multi-aircraft collaborative flight is still in the experimental stage, making it difficult to achieve efficient, synchronized flight over large areas, limiting the scale of swarm intelligent control. Summary of the Invention

[0004] In order to overcome the shortcomings of the existing technology, the purpose of the present invention is to provide an unmanned aerial vehicle control system based on an intelligent robot, which can realize automated closed-loop management of aircraft flight, achieve efficient scheduling and automated control of aircraft, and provide a safer, smarter and more scalable aircraft operation mode.

[0005] To achieve the above objectives, the present invention provides the following solution: an unmanned aerial vehicle control system based on an intelligent robot, comprising a remote management platform and an aircraft, an intelligent robot, and a cellular centralized management station connected to the remote management platform, wherein the remote management platform comprises:

[0006] An aircraft configuration module, configured to configure the aircraft's sensor components and the first embedded chip to implement the aircraft's environmental perception and mission processing functions; the aircraft includes but is not limited to unmanned aerial vehicles, manned aerial vehicles, unmanned vehicles, and unmanned ships;

[0007] An intelligent robot module is used to select an intelligent robot having a mobile mechanism and a robotic arm, and configure sensors, cameras, a hardware control unit, and a software control architecture for the intelligent robot;

[0008] a site management module, configured to deploy a plurality of surveillance cameras and environmental monitoring sensors in the cellular centralized management station to perform internal monitoring, equipment monitoring, and internal anomaly detection of the cellular centralized management station, and to clean, inspect, and manage the intelligent robots by numbering, thereby achieving collaborative management among the aircraft, the cellular centralized management station, and the intelligent robots;

[0009] A large model control module is used to utilize a collaborative control model to coordinate the scheduling of the aircraft, the intelligent robot, and the cellular centralized management station according to mission objectives and requirements; utilize a flight control model to automatically generate aircraft mission paths and execution scripts, dynamically plan the aircraft's mission sequence, and make decisions regarding abnormal situations; and utilize a data management model to implement algorithms and store information;

[0010] A monitoring and scheduling module, configured to monitor the aircraft, the intelligent robot, and the cellular centralized management station in real time, and to perform coordinated scheduling and fault response between multiple aircraft and multiple cellular centralized management stations;

[0011] Among them, the aircraft configuration module, the intelligent robot module, the site management module, the large model control module and the monitoring and scheduling module are interconnected.

[0012] Optionally, the honeycomb-type centralized management station includes a honeycomb chamber, a plurality of open-lid storage boxes arranged inside the honeycomb chamber, a plurality of the monitoring cameras and the environmental monitoring sensors. The open-lid storage box is provided with a pressure sensor for detecting whether an aircraft is stored and a travel switch sensor for detecting the opening and closing of the box cover. The environmental monitoring sensors include temperature and humidity sensors, dust monitoring sensors and noise sensors. The open-lid storage box and the aircraft are both numbered.

[0013] Optionally, the cellular centralized management station includes:

[0014] An internal management unit, configured to collect site video data and site environmental data of the cellular centralized management station in real time using the surveillance camera and the environmental monitoring sensor, and perform environmental anomaly monitoring based on the site video data and the site environmental data;

[0015] A storage location management unit is used to bind the open-lid storage box number to the corresponding aircraft number, establish a number mapping table, track the aircraft location and status in real time, and establish a storage box status table to mark the usage status of each open-lid storage box;

[0016] The safety management unit is used for the intelligent robot to separate and charge the battery of the aircraft after the aircraft lands in the designated area, and to put the aircraft back into the corresponding open-lid storage box for automatic recording and binding verification.

[0017] Optionally, the large model control module includes:

[0018] A collaborative control unit, configured to construct a collaborative task allocation model based on graph theory, and utilize the collaborative task allocation model to perform multi-agent collaborative scheduling, dynamic task planning, collaborative execution, and result rotation among the aircraft, the intelligent robot, and the cellular centralized management station;

[0019] A flight control model unit, used to construct a flight control model and use the flight control model to perform mission decomposition, path planning, and exception decision-making for the aircraft;

[0020] The data management model unit is used to combine algorithms to perform data structured management on the aircraft, the intelligent robot and the cellular centralized management station.

[0021] Optionally, the collaborative control unit includes:

[0022] A collaborative task modeling subunit is used to obtain the status and task requirement data of the aircraft, the intelligent robot, and the cellular centralized management station, use a collaborative task allocation model based on graph theory to decompose the overall task into multiple subtasks, and allocate tasks based on the capabilities, status, and geographic location of each node;

[0023] The collaborative scheduling algorithm subunit is used to introduce a MAS-based distributed protocol and adopt a dynamic allocation strategy based on reinforcement learning to build a collaborative scheduling algorithm that combines conflict detection, coordinated decision-making, and command issuance, enabling multi-aircraft collaborative flight, obstacle avoidance, and operational coordination.

[0024] The task dynamic planning subunit is used to re-plan tasks by combining the A algorithm and deep learning prediction model when there are environmental changes, path blockages, or equipment anomalies;

[0025] The collaborative execution and result feedback subunit is used to report the progress and status of the aircraft, the intelligent robot and the cellular centralized management station in real time, and to log and verify the progress and status reported in real time.

[0026] Optionally, the flight control model unit includes:

[0027] A task decomposition unit is used to introduce a path planning algorithm and an environment adaptation model into the deep learning model to obtain a flight control model. The flight control model decomposes the task according to the task goal input by the user to obtain multiple subtasks, dynamically adjusts the priority of the subtasks according to the urgency of the task, sorts the subtasks, obtains a subtask list, and then generates operation instructions based on the subtask list;

[0028] A path planning unit, configured to input the aircraft's sensor fusion data and the dynamic three-dimensional map acquired by the aircraft into the flight control model, obtain the mission path and flight time, and perform multi-constraint optimization of the total energy consumption of the mission path based on environmental variables;

[0029] The abnormality decision unit is used to make abnormality judgment and fault prediction based on the sensor fusion data, and to make potential fault judgment and realize fault prediction by combining the time series model and the classification model.

[0030] Optionally, the multi-constraint optimization expression of the total energy consumption of the task path is:

[0031]

[0032] Among them, E tatal is the total energy consumption of the task path, P hover is the hovering power consumption, P move (v,a) is the power consumption of the aircraft moving with speed and acceleration, ΔE env The impact of environmental variables on energy consumption.

[0033] Optionally, the data management model unit includes:

[0034] The data acquisition subunit is used to obtain aircraft sensor data, robot operation status, site environment data, and site scheduling data to obtain multi-source data, and use the buffer + write-before log to check the integrity and real-time performance of the multi-source data;

[0035] A data management subunit is configured to write the multi-source data into a distributed time series database, write structured business data and control logs into a relational database, and construct a multidimensional index and a timestamp index in the distributed time series database and the relational database to perform multi-condition combination queries;

[0036] The algorithm support subunit is used to regularly schedule tasks to perform desensitization, outlier detection, missing value filling, and labeling preprocessing on the multi-source data, and perform batch analysis on the multi-source data using Spark or Flink.

[0037] Optionally, the monitoring and scheduling module includes:

[0038] A real-time monitoring unit is configured to deploy a YOLO target detection model, collect monitoring data from the surveillance camera and the visual sensor on the aircraft to obtain a comprehensive monitoring video, and transmit the comprehensive monitoring video to the YOLO target detection model using a real-time streaming protocol for abnormality identification. The monitoring data of the sensor components and the robot status data are then collected to obtain comprehensive monitoring data, and the presence of an abnormal state is determined based on the comprehensive monitoring data and a preset abnormal data threshold.

[0039] A task scheduling unit is used to calculate the task urgency of the target device, the remaining battery power of the aircraft, and the distance to the device in a weighted manner to obtain the task priority. Based on the task priority, the distributed task scheduling framework is used to allocate and execute the task, and 5G communication is set as the primary communication channel and satellite communication as the backup communication channel. When the delay of the primary communication channel exceeds the set communication delay threshold, the communication mode is automatically switched to the backup communication channel;

[0040] The fault response unit is used to locate the faulty device based on the abnormality identification results and abnormal status judgment results, and call the backup device to respond to the task.

[0041] Optionally, the task priority expression is:

[0042]

[0043] Among them, P task is the task priority, U urg 、U power 、U dist are respectively mission urgency, aircraft remaining power and equipment distance, W urg 、W power 、W dist are weight factors, ∑W i is the sum of weight factors.

[0044] The present invention provides an unmanned aerial vehicle control system based on an intelligent robot, which discloses the following technical effects:

[0045] 1. By dividing the system into four major components: a remote management platform, an intelligent robot, an aircraft, and a cellular centralized management station, the present invention can achieve closed-loop management of aircraft flight, reduce manual control, and lower the possibility of subjective errors in flight operations. It can also achieve efficient scheduling and automated control of aircraft, providing a safer, more intelligent, and scalable aircraft operation mode.

[0046] 2. This invention utilizes a remote management platform that: 1) integrates a large model and automatically generates aircraft mission paths and execution scripts based on mission objectives, determines execution order, and makes decisions when anomalies occur. 2) It also enables real-time video and data monitoring of each cellular site, aircraft, and intelligent robot, enabling coordinated control of multiple machines and locations.

[0047] 3. The present invention utilizes an intelligent robot that: 1) can freely move within a honeycomb-like centralized management station, performing flexible operations such as grabbing, placing, and cleaning aircraft. 2) can also identify the codes of open-lid storage boxes and aircraft status in real time, and transmit operational status back to a remote management platform for two-way communication, thereby executing commands issued by the remote management platform.

[0048] 4. The present invention sets up a honeycomb-type centralized management station: 1) The open-lid storage box can perform one-to-one storage management of the aircraft, and detect the effective storage status of the aircraft in the box through a pressure sensor to prevent the aircraft from being placed incorrectly; the specific angle and completion status of the lid opening and closing are detected by a limit switch sensor, so that the open-lid storage box has maintenance capabilities to ensure that the aircraft is always in the best condition. 2) It can perform internal monitoring by setting up multiple cameras and environmental monitoring sensors to detect temperature, humidity, dust conditions, etc., and report the data to the management platform in real time. 3) Each storage box in the site is numbered, corresponding to a unique aircraft number, supporting rapid identification by intelligent robots to track the position and status of the aircraft in real time to meet the needs of dynamic automated management.

[0049] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 A schematic diagram of the system architecture provided by an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of the structure of a cellular centralized management station provided in an embodiment of the present invention;

[0053] Figure 3 A schematic structural diagram of an open-lid storage box provided in an embodiment of the present invention;

[0054] Figure 4 A diagram showing the architecture of the remote management platform provided in an embodiment of the present invention;

[0055] Description of reference numerals: 1. honeycomb chamber; 2. open-lid storage box. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0057] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] like Figure 1 As shown, the present invention provides an unmanned aerial vehicle control system based on an intelligent robot, including a remote management platform and an aircraft, an intelligent robot and a cellular centralized management station connected to the remote management platform.

[0059] The aircraft includes an aircraft body, a sensor assembly disposed on the aircraft body, and a first embedded chip connected to the sensor assembly, wherein the sensor assembly includes:

[0060] The IMU (Inertial Measurement Unit) can use a high-precision IMU module, such as the Bosch BMI270 or MPU-9250. These modules feature a three-axis accelerometer and a three-axis gyroscope, along with integrated temperature compensation and a low-power design. They provide real-time linear acceleration and angular velocity data, supporting the calculation of the aircraft's attitude angles (pitch, roll, and yaw).

[0061] Visual sensors can be equipped with a binocular stereo camera and a depth camera, such as the Intel Realsense D435i, to provide depth perception and obstacle distance measurement, thereby achieving short-range obstacle avoidance and environment construction.

[0062] Lidar, you can choose a rotating lidar like the Velodyne Puck VLP-16 or a low-cost lidar like the Livox Mid-360. Lidar is capable of long-range (over 100 meters) obstacle detection and is used for navigation in complex terrain.

[0063] GPS module, with optional high-precision RTK-GPS modules such as the Ublox ZED-F9P, which supports centimeter-level positioning and enables precise geographic location estimation and track tracking.

[0064] like Figure 2 、 Figure 3As shown, the honeycomb-type centralized management station includes a honeycomb chamber 1, a plurality of open-lid storage boxes 2 arranged inside the honeycomb chamber 1, a plurality of monitoring cameras and the environmental monitoring sensors. The open-lid storage box 2 is provided with a pressure sensor for detecting whether an aircraft is stored and a travel switch sensor for detecting the opening and closing of the box cover. The environmental monitoring sensors include temperature and humidity sensors, dust monitoring sensors and noise sensors. The open-lid storage box 2 and the aircraft are both numbered.

[0065] Dust monitoring sensors, such as the GP2Y1010AU0F dust sensor, are used to detect dust concentration in the air inside the cellular station to prevent dust accumulation on the aircraft body and affect mission efficiency; noise sensors ensure that the cellular station environment operates within the specified noise value.

[0066] The cellular centralized management station includes:

[0067] The internal management unit is used to use the monitoring camera and the environmental monitoring sensor to collect the site video data and site environmental data of the cellular centralized management station in real time, and perform environmental anomaly monitoring based on the site video data and the site environmental data, such as excessive temperature and humidity or excessive dust concentration.

[0068] The storage location management unit is used to bind the number of the open-lid storage box 2 and the corresponding aircraft number, and establish a number mapping table to track the aircraft position and status in real time, and establish a storage box status table to mark the usage status (idle / occupied / fault) of each open-lid storage box 2.

[0069] The safety management unit is used for the intelligent robot to separate and charge the battery of the aircraft after the aircraft lands in the designated area, and to put the aircraft back into the corresponding open-lid storage box 2 for automatic recording and binding verification.

[0070] like Figure 4 As shown, the remote management platform includes an aircraft configuration module, an intelligent robot module, a site management module, a large model control module and a monitoring and scheduling module that are interconnected.

[0071] 1. Aircraft configuration module

[0072] Used to configure the sensor components and the first embedded chip of the aircraft to realize the environmental perception and task processing functions of the aircraft; the aircraft includes but is not limited to unmanned aerial vehicles, manned aerial vehicles, unmanned vehicles and unmanned ships.

[0073] 2. Intelligent robot module

[0074] Used to select an intelligent robot with a mobile mechanism and a robotic arm, and configure sensors, cameras, hardware control units and software control architecture for the intelligent robot.

[0075] For example, laser radar and ultrasonic sensors are deployed at the front end of the mobile mechanism of the intelligent robot for movement and obstacle avoidance, and cameras, jet nozzles, and NFC scanning devices or QR code readers are deployed on the robotic arm for target recognition, grasping, cleaning, and number recognition.

[0076] A second embedded chip responsible for decision-making and communication, a microcontroller for controlling the mobile mechanism and the robotic arm, and a communication module, such as a 5G module and a LoRa module, are deployed in the intelligent robot.

[0077] In the intelligent robot, a distributed control framework is constructed based on the ROS framework to perform task parallel processing, such as parallel operation execution task scheduling, sensor data reading and real-time control of the robotic arm.

[0078] 3. Site Management Module

[0079] It is used to deploy multiple surveillance cameras and environmental monitoring sensors in the cellular centralized management station to carry out internal monitoring, equipment monitoring and internal anomaly detection of the cellular centralized management station, and to clean, detect and manage the intelligent robots through numbering, so as to realize collaborative management among the aircraft, the cellular centralized management station and the intelligent robots.

[0080] 4. Large model control module

[0081] It is used to utilize the collaborative control model to perform collaborative scheduling between the aircraft, the intelligent robot, and the cellular centralized management station according to mission objectives and requirements, utilize the flight control model to automatically generate aircraft mission paths and execution scripts, perform dynamic planning of aircraft mission sequences and abnormal situation decisions, and then utilize the data management model to implement algorithms and store information; the large model control module includes:

[0082] 4.1 Collaborative Control Unit

[0083] It is used to build a collaborative task allocation model based on graph theory, and use the collaborative task allocation model to perform multi-agent collaborative scheduling, dynamic task planning, collaborative execution and result rotation among the aircraft, the intelligent robot and the cellular centralized management station; the collaborative control unit includes:

[0084] 4.11 Collaborative Task Modeling Subunit

[0085] It is used to obtain the status and task requirement data of the aircraft, the intelligent robot and the cellular centralized management station, use the collaborative task allocation model based on graph theory to decompose the overall task into multiple subtasks, and allocate tasks based on the capabilities, status and geographical location of each node.

[0086] 4.12 Cooperative Scheduling Algorithm Subunit

[0087] It introduces a distributed protocol based on MAS and adopts a dynamic allocation strategy based on reinforcement learning to build a collaborative scheduling algorithm that combines conflict detection, coordination decision-making, and command issuance, enabling multi-vehicle collaborative flight, obstacle avoidance, and operational coordination.

[0088] 4.13 Task Dynamic Planning Subunit

[0089] It is used to re-plan tasks by combining algorithm A and deep learning prediction models when there are environmental changes, path blockages or equipment abnormalities.

[0090] 4.14 Collaborative Execution and Result Feedback to Subunits

[0091] It is used to report the progress and status of the aircraft, the intelligent robot and the cellular centralized management station in real time, and to perform logging and security verification on the progress and status reported in real time.

[0092] 4.2 Flight Control Model Unit

[0093] Used to build a flight control model, and use the flight control model to perform mission decomposition, path planning, and abnormal decision making for the aircraft. The flight control model unit includes:

[0094] 4.21 Task Decomposition Unit

[0095] It is used to introduce path planning algorithms and environmental adaptation models into deep learning models (with task decomposition and path planning capabilities) to obtain a flight control model. The flight control model decomposes tasks according to the task objectives input by the user to obtain multiple subtasks, dynamically adjusts the priorities of the subtasks according to the urgency of the tasks, sorts the subtasks, obtains a subtask list, and then generates operation instructions based on the subtask list.

[0096] Flight control model:

[0097] Input: User target task, such as delivering an item to location A.

[0098] Output: Path planning: aircraft waypoint coordinates, flight altitude, time window, etc., execution script: specific flight steps and backup strategies for controlling the aircraft.

[0099] Task decomposition: Users enter their goals on the platform, such as inspection areas or delivery tasks. After the large model parses the task, it is split into a list of executable subtasks and generates specific operation instructions.

[0100] Path Planning: Environmental perception data, such as maps, obstacle information, and weather conditions, is fed into a large-scale model, which then assigns waypoints to the aircraft and calculates the optimal path and flight time. Dynamic path optimization mechanisms, such as real-time obstacle avoidance strategy adjustments, are used to ensure efficient mission completion.

[0101] 4.22 Path Planning Unit

[0102] The sensor fusion data and the dynamic three-dimensional map are input into the flight control model to obtain the mission path and flight time, and the multi-constraint optimization (minimization of energy consumption) of the total energy consumption of the mission path is performed based on environmental variables (wind speed, airflow, dynamic obstacles, etc.). The multi-constraint optimization expression of the total energy consumption of the mission path is:

[0103]

[0104] Among them, E tatal is the total energy consumption of the task path, P hover is the hovering power consumption, P move (v,a) is the power consumption of the aircraft moving with speed and acceleration, ΔE env The impact of environmental variables on energy consumption.

[0105] 4.23 Abnormal Decision Unit

[0106] It is used to perform abnormality judgment and fault prediction based on the sensor fusion data, and combine the time series model (LSTM) and classification model to perform potential fault judgment, such as sensor abnormality and insufficient power, to achieve fault prediction.

[0107] 4.3 Data Management Model Unit

[0108] The data management model unit is used to combine algorithms to perform data structured management on the aircraft, the intelligent robot and the cellular centralized management station. The data management model unit includes:

[0109] 4.31 Data Acquisition Subunit

[0110] It is used to obtain aircraft sensor data, robot operation status, site environment data and site scheduling data, obtain multi-source data, and use the buffer + write-before log to check the integrity and real-time performance of the multi-source data.

[0111] 4.32 Data Management Subunit

[0112] It is used to write the multi-source data into a distributed time series database, write structured business data and control logs into a relational database, and build multidimensional indexes and timestamp indexes in the distributed time series database and the relational database to perform multi-condition combination queries.

[0113] 4.33 Algorithm Support Subunit

[0114] It is used to regularly schedule tasks to perform desensitization, outlier detection, missing value filling, and labeling preprocessing on the multi-source data, and to perform batch analysis on the multi-source data using Spark or Flink.

[0115] 5. Monitoring and scheduling module

[0116] Used to monitor the aircraft, the intelligent robot and the cellular centralized management station in real time, and to perform coordinated scheduling and fault response between multiple aircraft and multiple cellular centralized management stations; the monitoring and scheduling module includes:

[0117] 5.1 Real-time monitoring unit

[0118] It is used to deploy the YOLO target detection model (YOLOv5 or YOLOv8), collect monitoring data from the surveillance camera and the visual sensors on the aircraft, obtain a comprehensive monitoring video, and use the real-time streaming transmission protocol to transmit the comprehensive monitoring video to the YOLO target detection model for anomaly recognition, identify obstacles at the aircraft's take-off and landing points, such as unremoved obstacles and dynamically moving objects, and detect equipment failures, such as aircraft tilt or accidental fall.

[0119] The sensor assembly's monitoring data and robot status data (movement path, arm status, and load information) are then collected to generate comprehensive monitoring data. Based on this comprehensive monitoring data and preset abnormal data thresholds (flight speed exceeding the limit, battery power being low, or sensor overtemperature), the system determines whether an abnormal state exists. A time series database and dynamic alarm rules can also be used to link device status and sudden abnormalities to scheduling coordination, achieving a real-time closed-loop monitoring system.

[0120] 5.2 Task Scheduling Unit

[0121] It is used to weightedly calculate the task urgency of the target device, the remaining battery power of the aircraft, and the distance between the devices to obtain the task priority. Based on the task priority, a distributed task scheduling framework, such as Apache Airflow, is used to allocate and execute tasks, and 5G communication is set as the main communication channel and satellite communication as the backup communication channel. When the delay of the main communication channel exceeds the set communication delay threshold, the communication mode is automatically switched to the backup communication channel.

[0122] The expression of task priority is:

[0123]

[0124] Among them, P task is the task priority, U urg 、U power 、U dist are respectively mission urgency, aircraft remaining power and equipment distance, W urg 、W power 、W dist are the weight factors of mission urgency, aircraft remaining power and equipment distance, ΣW i is the sum of weight factors.

[0125] 5.3 Fault Response Unit

[0126] It is used to locate the faulty equipment (such as the failure of aircraft A) based on the abnormal identification results and abnormal status judgment results, and call the backup equipment from the idle equipment to respond to the mission and continue the mission.

[0127] 5.4 Data Storage

[0128] Distributed storage architecture: Use a time series database, such as InfluxDB or TimescaleDB, to store key aircraft data:

[0129] Mission data: including mission instructions, aircraft waypoints, flight speed, flight status updates, etc.

[0130] Environmental data: such as wind speed, air pressure, temperature, humidity and other sampling values.

[0131] Maintenance records: such as aircraft health status (battery charge, component abnormalities) and storage box operation status.

[0132] Therefore, the present invention provides an unmanned aerial vehicle control system based on an intelligent robot, which can realize automated closed-loop management of aircraft flight, achieve efficient scheduling and automated control of aircraft, and provide a safer, smarter and more scalable aircraft operation mode.

[0133] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0134] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. An unmanned aerial vehicle control system based on an intelligent robot, characterized in that: It includes a remote management platform and an aircraft, an intelligent robot and a cellular centralized management station connected to the remote management platform. The remote management platform includes: An aircraft configuration module, configured to configure the aircraft's sensor components and the first embedded chip to implement the aircraft's environmental perception and mission processing functions; the aircraft includes but is not limited to unmanned aerial vehicles, manned aerial vehicles, unmanned vehicles, and unmanned ships; An intelligent robot module is used to select an intelligent robot having a mobile mechanism and a robotic arm, and configure sensors, cameras, a hardware control unit, and a software control architecture for the intelligent robot; a site management module, configured to deploy a plurality of surveillance cameras and environmental monitoring sensors in the cellular centralized management station to perform internal monitoring, equipment monitoring, and internal anomaly detection of the cellular centralized management station, and to clean, inspect, and manage the intelligent robots by numbering, thereby achieving collaborative management among the aircraft, the cellular centralized management station, and the intelligent robots; A large model control module is used to utilize a collaborative control model to coordinate the scheduling of the aircraft, the intelligent robot, and the cellular centralized management station according to mission objectives and requirements; utilize a flight control model to automatically generate aircraft mission paths and execution scripts, dynamically plan the aircraft's mission sequence, and make decisions regarding abnormal situations; and utilize a data management model to implement algorithms and store information; A monitoring and scheduling module, configured to monitor the aircraft, the intelligent robot, and the cellular centralized management station in real time, and to perform coordinated scheduling and fault response between multiple aircraft and multiple cellular centralized management stations; Among them, the aircraft configuration module, the intelligent robot module, the site management module, the large model control module and the monitoring and scheduling module are interconnected.

2. The unmanned aerial vehicle control system based on an intelligent robot according to claim 1, characterized in that: The honeycomb-type centralized management station includes a honeycomb chamber, multiple open-lid storage boxes arranged inside the honeycomb chamber, multiple monitoring cameras and environmental monitoring sensors. The open-lid storage box is provided with a pressure sensor for detecting whether an aircraft is stored and a travel switch sensor for detecting the opening and closing of the box cover. The environmental monitoring sensor includes a temperature and humidity sensor, a dust monitoring sensor and a noise sensor. The open-lid storage box and the aircraft are both numbered.

3. The unmanned aerial vehicle control system based on an intelligent robot according to claim 2, characterized in that: The cellular centralized management station includes: An internal management unit, configured to collect site video data and site environmental data of the cellular centralized management station in real time using the surveillance camera and the environmental monitoring sensor, and perform environmental anomaly monitoring based on the site video data and the site environmental data; A storage location management unit is used to bind the open-lid storage box number to the corresponding aircraft number, establish a number mapping table, track the aircraft location and status in real time, and establish a storage box status table to mark the usage status of each open-lid storage box; The safety management unit is used for the intelligent robot to separate and charge the battery of the aircraft after the aircraft lands in the designated area, and to put the aircraft back into the corresponding open-lid storage box for automatic recording and binding verification.

4. The unmanned aerial vehicle control system based on an intelligent robot according to claim 3, characterized in that: The large model control module includes: A collaborative control unit, configured to construct a collaborative task allocation model based on graph theory, and utilize the collaborative task allocation model to perform multi-agent collaborative scheduling, dynamic task planning, collaborative execution, and result rotation among the aircraft, the intelligent robot, and the cellular centralized management station; A flight control model unit, used to construct a flight control model and use the flight control model to perform mission decomposition, path planning, and exception decision-making for the aircraft; The data management model unit is used to combine algorithms to perform data structured management on the aircraft, the intelligent robot and the cellular centralized management station.

5. The unmanned aerial vehicle control system based on an intelligent robot according to claim 4, characterized in that: The collaborative control unit includes: A collaborative task modeling subunit is used to obtain the status and task requirement data of the aircraft, the intelligent robot, and the cellular centralized management station, use a collaborative task allocation model based on graph theory to decompose the overall task into multiple subtasks, and allocate tasks based on the capabilities, status, and geographic location of each node; The collaborative scheduling algorithm subunit is used to introduce a MAS-based distributed protocol and adopt a dynamic allocation strategy based on reinforcement learning to build a collaborative scheduling algorithm that combines conflict detection, coordinated decision-making, and command issuance, enabling multi-aircraft collaborative flight, obstacle avoidance, and operational coordination. The task dynamic planning subunit is used to re-plan tasks by combining the A algorithm and deep learning prediction model when there are environmental changes, path blockages, or equipment anomalies; The collaborative execution and result feedback subunit is used to report the progress and status of the aircraft, the intelligent robot and the cellular centralized management station in real time, and to log and verify the progress and status reported in real time.

6. The unmanned aerial vehicle control system based on an intelligent robot according to claim 5, characterized in that: The flight control model unit includes: A task decomposition unit is used to introduce a path planning algorithm and an environment adaptation model into the deep learning model to obtain a flight control model. The flight control model decomposes the task according to the task goal input by the user to obtain multiple subtasks, dynamically adjusts the priority of the subtasks according to the urgency of the task, sorts the subtasks, obtains a subtask list, and then generates operation instructions based on the subtask list; A path planning unit, configured to input the aircraft's sensor fusion data and the dynamic three-dimensional map acquired by the aircraft into the flight control model, obtain the mission path and flight time, and perform multi-constraint optimization of the total energy consumption of the mission path based on environmental variables; The abnormality decision unit is used to make abnormality judgment and fault prediction based on the sensor fusion data, and to make potential fault judgment and realize fault prediction by combining the time series model and the classification model.

7. The unmanned aerial vehicle control system based on an intelligent robot according to claim 6, characterized in that: The multi-constraint optimization expression of the total energy consumption of the task path is: Among them, E tatal is the total energy consumption of the task path, P hover is the hovering power consumption, P move (v,a) is the power consumption of the aircraft moving with speed and acceleration, ΔE env The impact of environmental variables on energy consumption.

8. The unmanned aerial vehicle control system based on an intelligent robot according to claim 7, characterized in that: The data management model unit includes: The data acquisition subunit is used to obtain aircraft sensor data, robot operation status, site environment data, and site scheduling data to obtain multi-source data, and use the buffer + write-before log to check the integrity and real-time performance of the multi-source data; A data management subunit is configured to write the multi-source data into a distributed time series database, write structured business data and control logs into a relational database, and construct a multidimensional index and a timestamp index in the distributed time series database and the relational database to perform multi-condition combination queries; The algorithm support subunit is used to regularly schedule tasks to perform desensitization, outlier detection, missing value filling, and labeling preprocessing on the multi-source data, and perform batch analysis on the multi-source data using Spark or Flink.

9. The unmanned aerial vehicle control system based on an intelligent robot according to claim 8, characterized in that: The monitoring and scheduling module includes: A real-time monitoring unit is configured to deploy a YOLO target detection model, collect monitoring data from the surveillance camera and the visual sensor on the aircraft to obtain a comprehensive monitoring video, and transmit the comprehensive monitoring video to the YOLO target detection model using a real-time streaming protocol for abnormality identification. The monitoring data of the sensor components and the robot status data are then collected to obtain comprehensive monitoring data, and the presence of an abnormal state is determined based on the comprehensive monitoring data and a preset abnormal data threshold. A task scheduling unit is used to calculate the task urgency of the target device, the remaining battery power of the aircraft, and the distance to the device in a weighted manner to obtain the task priority. Based on the task priority, the distributed task scheduling framework is used to allocate and execute the task, and 5G communication is set as the primary communication channel and satellite communication as the backup communication channel. When the delay of the primary communication channel exceeds the set communication delay threshold, the communication mode is automatically switched to the backup communication channel; The fault response unit is used to locate the faulty device based on the abnormality identification results and abnormal status judgment results, and call the backup device to respond to the task.

10. The unmanned aerial vehicle control system based on an intelligent robot according to claim 9, characterized in that: The expression of task priority is: Among them, P task is the task priority, U urg 、U power 、U dist are respectively mission urgency, aircraft remaining power and equipment distance, W urg 、W power 、W dist are weight factors, ∑W i is the sum of weight factors.

Images