Urban low-altitude AI collaborative management and control method and system based on Beidou grid code and block chain

Abstract

The invention provides an urban low-altitude AI collaborative management and control method and system based on a Beidou grid code and a block chain, and the method comprises the steps: obtaining the information of an unmanned plane, and searching a corresponding evidence storage record in the block chain; the unmanned aerial vehicle information is obtained through a low-altitude intelligent flight control box compatible with various unmanned aerial vehicle protocols; verifying the qualification of the unmanned aerial vehicle through the evidence storage record, and bringing the unmanned aerial vehicle into a distributed collaborative management and control network for unified scheduling when the unmanned aerial vehicle passes the qualification authentication; setting flight authority according to airspace classification of the airspace map and generating a corresponding geofence to limit the flight range of each unmanned aerial vehicle; the airspace map is divided into space-time grids with specified resolution based on Beidou grid codes, state information of each grid unit in the space-time grids is analyzed based on an AI reinforcement learning engine, and flight paths of the unmanned aerial vehicles are dynamically optimized. Flight proxy of the unmanned aerial vehicles is realized through the low-altitude intelligent flight control box, unified scheduling of the multi-source heterogeneous unmanned aerial vehicles is realized, and the airspace use efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of UAV collaborative control and urban low-altitude economic management, and in particular to a method and system for urban low-altitude AI collaborative control based on Beidou grid code and blockchain. Background Art

[0002] In the current drone application environment, two significant technical challenges severely hinder the efficient operation and unified management of drone systems. On the one hand, drones from different brands (such as DJI and XAG) use independent and incompatible communication protocols. This protocol barrier makes information exchange and collaborative operations between drones from different brands extremely difficult, significantly limiting the integration of multi-source drone data and comprehensive management capabilities, and hindering the development of drone technology towards more intelligent and networked capabilities. On the other hand, traditional airspace management methods rely on static routing, which not only wastes airspace resources but also struggles to adapt to growing dynamic mission demands. Due to its lack of flexibility, the existing airspace management model cannot quickly respond and adjust to emergencies or temporary missions, thereby reducing the overall system's operational efficiency and service quality. Therefore, how to overcome protocol barriers, achieve seamless communication and collaboration between drones from different brands, and introduce dynamic airspace management mechanisms to improve airspace resource utilization and mission flexibility have become key issues that need to be addressed. Summary of the Invention

[0003] The present invention provides a method and system for urban low-altitude AI collaborative control based on Beidou grid code and blockchain to solve the problems existing in related technologies. The technical solution is as follows:

[0004] In a first aspect, an embodiment of the present invention provides a method for urban low-altitude AI collaborative control based on Beidou grid code and blockchain, including:

[0005] Obtain drone information and search for corresponding evidence records in the blockchain based on the drone information; drone information is obtained through a low-altitude intelligent flight control box that is compatible with multiple drone protocols;

[0006] Automatically verify the qualifications of drones through evidence records. Once a drone passes the qualification certification, it will be included in the distributed collaborative control network for unified scheduling.

[0007] Obtain an airspace map, set flight permissions based on the airspace classification on the airspace map, and generate corresponding geofences based on the flight permissions to limit the flight range of each drone in the distributed collaborative control network;

[0008] Based on the Beidou grid code, the airspace map is divided into space-time grids of specified resolution according to the time and space dimensions. The status information of each grid cell in the space-time grid is analyzed based on the AI reinforcement learning engine, and the flight path of each drone is dynamically optimized to generate the optimal route for each drone.

[0009] In one embodiment, it further includes:

[0010] Predefine flight airspace types, deploy corresponding smart contracts for each flight airspace type, and submit the smart contracts to the blockchain for evidence storage; the smart contracts define the storage rules, permission control mechanism, and conflict detection of flight data;

[0011] Obtain the flight data of the drone, including location information, timestamp, and flight status;

[0012] According to the spatiotemporal attributes of flight data, a dynamic sharding strategy is adopted to select the corresponding blockchain storage node, and the flight data is submitted to the corresponding blockchain storage node for storage.

[0013] In one embodiment, the method for generating the optimal route includes:

[0014] Use a pre-trained reinforcement learning model to perform multi-drone path planning for the drone swarm based on the state information of each grid cell, generating a flight path for each drone;

[0015] Based on the conflict detection model, the flight path of each drone in the drone swarm is detected for conflict, the probability of conflict between drones is predicted, and when the probability of conflict is higher than the threshold, the flight path of the drone swarm is dynamically adjusted to ensure conflict-free flight.

[0016] The priority of each drone is dynamically evaluated according to its status factors, airspace resources are allocated based on the priority, and the optimal route for each drone is finally output.

[0017] In one embodiment, it further includes:

[0018] Generate a check request at a specified time interval, and send a light-on command to the low-altitude intelligent flight control box connected to the drone based on the check request. The light-on command is used to control the drone to flash its lights according to a predetermined pattern, or to provide feedback on the drone's real-time status through light flashing;

[0019] By comparing the responses of each drone to the light-on command, abnormal drones can be identified and interference operations can be performed on the abnormal drones. Interference operations include location tracking, establishing a direct communication link, or sending interference signals to the abnormal drone to make it land safely.

[0020] In one embodiment, generating corresponding geo-fences according to flight permissions to limit the flight range of each drone in the distributed collaborative management and control network includes:

[0021] Divide the airspace map into four-dimensional grid cells of specified specifications;

[0022] Encode each four-dimensional grid cell based on the Beidou grid code to generate an identifier for each four-dimensional grid cell;

[0023] Generate geofences by using identifiers to define allowed or prohibited areas.

[0024] In one embodiment, it further includes:

[0025] Through the issuance of Token auctions on the blockchain, the right to use the designated space-time grid can be traded through Token auctions.

[0026] In a second aspect, an embodiment of the present invention provides an urban low-altitude AI collaborative control system based on Beidou grid code and blockchain, including:

[0027] Low-altitude intelligent flight control box, used to connect with the drone;

[0028] The cloud server is connected to the low-altitude intelligent flight control box through the network, and is used to execute the above-mentioned urban low-altitude AI collaborative control method based on Beidou grid code and blockchain.

[0029] In one embodiment, the low-altitude intelligent flight control box includes:

[0030] The blockchain encryption chip has a standardized interface compatible with multiple drone protocols. It connects to drones through the standardized interface and is used to record drone information in the blockchain after encryption. Drone information includes drone qualifications, flight data, and flight control instructions.

[0031] An edge computing chip, which makes obstacle avoidance decisions based on preset rules when obstacles are detected, and collaborates with a cloud server via a wireless network to request the cloud server to replan the route;

[0032] Dual-mode positioning chip, used to achieve dynamic centimeter-level positioning.

[0033] In one embodiment, the low-altitude intelligent flight control box further includes:

[0034] The optical signal module is used to feedback the flight status of the drone and switch the drone's light status according to the light-on command to achieve the purpose of troubleshooting.

[0035] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program runs on a computer, the method in any one of the above-mentioned embodiments is executed.

[0036] The advantages or beneficial effects of the above technical solution include at least:

[0037] The present invention connects to the drone through a low-altitude intelligent flight control box. The low-altitude intelligent flight control box is compatible with different drone protocols and can communicate with drones of different brands to achieve unified qualification certification for cross-brand drones. The present invention automatically reviews drone qualifications through blockchain evidence records to improve drone flight safety. Combined with the Beidou grid code to dynamically divide airspace resources and the AI agent algorithm to optimize route planning in real time, multiple flight routes for different drones in the same airspace can be quickly planned to achieve unified scheduling of multi-source heterogeneous drones in the city, making the use and management of airspace orderly and effectively improving the efficiency of airspace use.

[0038] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In the accompanying drawings, unless otherwise specified, the same reference numerals throughout the multiple drawings represent the same or similar components or elements. These drawings are not necessarily drawn to scale. It should be understood that these drawings only depict some embodiments disclosed herein and should not be construed as limiting the scope of the invention.

[0040] Figure 1 This is a flow chart of the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain in the present invention;

[0041] Figure 2 This is a schematic diagram of the composition of the urban low-altitude AI collaborative control system based on Beidou grid code and blockchain in the present invention;

[0042] Figure 3 This is a schematic diagram of the composition of the low-altitude intelligent flight control box of the present invention;

[0043] Figure 4 FIG. 1 is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0044] Hereinafter, only certain exemplary embodiments are briefly described. As will be appreciated by those skilled in the art, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and description are to be considered as illustrative in nature and not restrictive.

[0045] Example 1

[0046] This embodiment provides a method for urban low-altitude AI collaborative control based on Beidou grid code and blockchain. The executor of this method can be a cloud server, which realizes the unified scheduling of multi-source heterogeneous drones in the city; and the cloud server is connected to the drone through a low-altitude intelligent flight control box. Specifically, the low-altitude intelligent flight control box is compatible with multiple drone protocols. After connecting to the drone, the low-altitude intelligent flight control box can read the drone signal and add the drone to the drone group for collaborative control after passing the drone qualification certification.

[0047] like Figure 1 As shown, this embodiment of the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain specifically includes:

[0048] Step S1: Obtain drone information and search for corresponding evidence records in the blockchain based on the drone information; the drone information is obtained through a low-altitude intelligent flight control box that is compatible with multiple drone protocols.

[0049] In this embodiment, blockchain is used for drone qualification registration, flight data storage, smart contract storage, rights management storage, and airspace resource tokenization. Specifically:

[0050] Use blockchain to uniquely register and manage drone qualifications, ensuring that their qualification information is authentic, unique, and cannot be forged, and making it easier for regulators or platforms to quickly identify and track them.

[0051] Among them, each drone is assigned a unique identification code (such as MAC address, serial number, etc.) when it leaves the factory, and combined with the public key infrastructure (PKI), a pair of encryption keys are generated for the drone (the private key is stored in the device, and the public key is used for on-chain registration).

[0052] The drone’s qualification information (model, serial number, owner information, registration date, etc.) is written into the blockchain smart contract in advance to form an unchangeable registration record, so that the authenticity of the drone’s qualifications can be verified through the public key and on-chain evidence records in the future to prevent illegal modification or misuse of qualifications.

[0053] At the same time, information such as changes in drone ownership, maintenance records, and flight licenses can also be updated to the blockchain through authorization to form a complete life cycle archive.

[0054] The drone’s flight data is also stored on the chain. The flight data includes key data such as location information, timestamp, flight status, and operating instructions to ensure that the data is secure and cannot be tampered with, facilitating accident investigations, responsibility determination, and compliance audits.

[0055] It should be noted that flight data can be collected in real time through the sensor module originally equipped with the drone, or through the sensors on the external low-altitude intelligent flight control box; the flight data is uploaded to the blockchain node after being encrypted locally, or processed by the drone's edge computing device and then stored on the chain.

[0056] Flight data is stored on the blockchain using a dynamic sharding strategy. Drone flight data includes information such as timestamps and geographic locations. Based on these temporal and spatial attributes, flight data can be categorized and processed. For example, data from drones active in similar geographic areas during the same time period may be assigned to the same shard for processing.

[0057] Dynamic sharding intelligently selects the most appropriate blockchain node for storing a batch of flight data based on factors such as current network load and geographic proximity. This helps improve data processing efficiency, reduce latency, and enhance system scalability. As drones traverse different airspace types, their flight data is redistributed to the appropriate blockchain storage node based on the new spatiotemporal properties, ensuring effective data management and analysis.

[0058] This embodiment predefines flight airspace types, deploys corresponding smart contracts for each flight airspace type, and submits the smart contracts to the blockchain for evidence storage.

[0059] Among them, flight airspace types include:

[0060] Controlled airspace: Only government-authorized drones (such as police and emergency services) are allowed to fly, and secondary encryption authentication is required.

[0061] Surveillance airspace: Commercial drone operations (logistics, inspection) are open and flight data must be transmitted back to the regulatory platform in real time.

[0062] Reported airspace: Personal drone flights are allowed, but electronic fences must be opened and flight altitudes must be restricted (≤120 meters).

[0063] For each type of airspace, a specially designed smart contract is pre-deployed to define the corresponding rules. Specifically, in this embodiment, the smart contract defines flight data storage rules, access control mechanisms, and conflict detection. For example, controlled airspace may require more frequent flight data storage, stricter access control, and immediate conflict detection; while reporting airspace may only require simple pre-flight reports and post-flight summaries.

[0064] The permission control mechanism can be implemented through digital qualification authentication on the blockchain, and only authorized entities can access or modify specific data.

[0065] The conflict detection function can utilize the logical processing capabilities of smart contracts to predict potential collision risks by comparing the flight paths, speeds and other parameters of different drones in the smart contract, and automatically issue warnings or adjustment suggestions.

[0066] In this embodiment, airspace resource tokenization refers to improving the efficiency and transparency of airspace use by converting flight airspace into digital assets (tokens) that can be traded, managed, and distributed on the blockchain. The implementation of airspace resource tokenization is as follows:

[0067] First, the airspace needs to be carefully divided, taking into account factors such as altitude, geographical location, and time, to form multiple "airspace units." Each unit represents a specific three-dimensional spatial area within a specific time period.

[0068] Determine the attributes of each airspace unit, such as usage authority (commercial / private), maximum permitted flight altitude, maximum speed limit, etc.

[0069] Choose the appropriate token type based on your needs. For example, non-fungible tokens (NFTs) are used to represent unique or limited airspace usage rights, while homogeneous tokens (FTs) are suitable for a large number of similar airspace units. Define the rules for token behavior through smart contracts, including but not limited to the creation, transfer, and destruction of airspace units, verification logic for usage rights, and conflict detection and resolution mechanisms.

[0070] Dynamic pricing strategies (auction, fixed price, etc.).

[0071] In this embodiment, airspace use rights tokens can be issued to users through auction, lottery, or pre-allocation. A blockchain-based trading platform allows users to conveniently buy, sell, lease, or exchange airspace use rights tokens. Furthermore, it is necessary to ensure that all airspace use rights information is updated promptly within the blockchain network and that all nodes are synchronized to ensure data consistency and accuracy.

[0072] After completing the aforementioned blockchain evidence storage, a drone's qualifications can be verified through the stored records. When a drone connected to the low-altitude intelligent flight control box initiates a verification request, the low-altitude intelligent flight control box can obtain drone information, such as the drone's serial number and MAC address, and construct a query request. The query request is sent to any node or full node in the blockchain. Based on the query criteria, all historical records containing the drone's qualifications are extracted from the blockchain, which serves as the basis for qualification verification.

[0073] It should be noted that since the data on the blockchain has a timestamp and hash value, it can be traced back to the earliest qualification registration record and ensures that the data has not been tampered with since its creation.

[0074] Step S2: Automatically verify the qualifications of the drone through evidence records. If the drone passes the qualification certification, it will be included in the distributed collaborative management and control network for unified scheduling.

[0075] Qualification verification uses the signature provided by the drone (generated using its private key) to verify whether it matches the corresponding public key stored on the blockchain. If so, this proves that the drone possesses the correct private key, thereby confirming its legal status. After passing qualification authentication, the drone can join the distributed collaborative control network, which is composed of a group of legally qualified drones. All drones in the distributed collaborative control network are centrally scheduled by the cloud server, ensuring controllability, observability, and traceability of their flight status, mission execution, and airspace behavior.

[0076] Step S3: Obtain an airspace map, set flight permissions according to the airspace classification of the airspace map, and generate corresponding geographic fences based on the flight permissions to limit the flight range of each drone in the distributed collaborative control network.

[0077] The cloud server obtains the latest airspace map from the aviation management department under the premise of authorization. The airspace map contains the latest airspace classification information, such as the latitude and longitude coordinates, altitude restrictions, usage time, etc. of airspace classifications such as controlled airspace, monitored airspace, and reported airspace.

[0078] Within a given airspace range of the airspace map, several four-dimensional grid cells are divided according to the specified spatial resolution (such as 0.01°×0.01°×100 meters) and time granularity (such as every 5 minutes), where the four dimensions include longitude, latitude, altitude and time.

[0079] The coordinates of the center point of each four-dimensional grid cell are normalized, and the Beidou grid code generation algorithm is used to generate the corresponding BGC code. The time window information is appended to the BGC identifier to form a complete four-dimensional identifier. By classifying a series of Beidou grid identifiers as "allowed" or "forbidden" and combining them with time window constraints, a logical geofencing strategy is constructed.

[0080] During the flight of the drone, the location information reported by the drone is received in real time, parsed into the current BGC unit, and the fence status is checked in combination with the timestamp; if there is a violation, an alarm is triggered, the drone returns to the airframe, or even remotely takes over.

[0081] In this embodiment, the low-altitude intelligent flight control box can be directly integrated with a real-time updated airspace map. Through the Beidou / 5G-A positioning function of the low-altitude intelligent flight control box, it can automatically identify no-fly zones and restricted-fly zones, and synchronize with the local government's airspace management platform to trigger forced return or landing in case of illegal flight.

[0082] Step S4: Based on the Beidou grid code, the airspace map is divided into space-time grids of specified resolution according to the time and space dimensions. The state information of each grid cell in the space-time grid is analyzed based on the AI reinforcement learning engine, and the flight path of each drone in the distributed collaborative control network is dynamically optimized to generate the optimal route for each drone.

[0083] While constructing the geo-fence, this embodiment also divides the airspace map into centimeter-level spatiotemporal grids based on the BeiDou grid code. Each grid cell in the centimeter-level spatiotemporal grid can be uniquely identified as a four-dimensional coordinate, consisting of the ground horizontal position (x, y), altitude (z) and timestamp (t). A unique identifier is generated for each grid cell in combination with the BeiDou grid code (BGC). At the same time, data is collected in real time through a sensor network (such as radar, ADS-B, LiDAR) to obtain the status information of each grid cell. The status information includes static attributes (whether it is inside a building, whether it is a no-fly zone, whether it belongs to infrastructure (such as a high-voltage line)), dynamic attributes (real-time flight density, meteorological conditions (wind speed, air pressure), visibility, emergencies (such as fire)), and control strategies (whether a specific type of drone is allowed to enter, whether Token authorization is required, or whether it is temporarily closed).

[0084] The AI reinforcement learning engine in this embodiment mainly includes a multi-machine path planning module, a conflict detection model, and a dynamic priority scheduling module. Specifically:

[0085] The multi-machine path planning module is used to perform multi-machine path planning for the drone swarm based on the state information of each grid cell through a pre-trained reinforcement learning model, and generate a flight route for each drone.

[0086] The reinforcement learning model in this embodiment can be trained by pre-collecting a large amount of historical flight data, including flight records under different weather conditions and traffic densities; pre-defining the reinforcement learning environment, including the drone's state space (position, speed, direction, etc.), action space (changing course, adjusting speed, etc.), and reward function (such as minimizing total flight time, avoiding collisions, etc.). Training is performed using algorithms such as Deep Q Network (DQN), Proximal Policy Optimization (PPO), or distributed distributed reinforcement learning (such as A3C).

[0087] For each drone, input its starting point, target point and the status information of the current grid cell (such as obstacles, the position of other drones, etc.), and use the pre-trained model to output a preliminary flight route.

[0088] The conflict detection model is used to perform conflict detection on the flight path of each drone in the drone swarm, predict the probability of conflict between drones, and dynamically adjust the flight path of the drone swarm to ensure conflict-free flight when the probability of conflict is higher than a threshold.

[0089] The conflict detection model needs to pre-set the criteria for potential conflict between two drones, such as the distance being less than a certain threshold, and being expected to arrive at the same grid cell at the same time.

[0090] During the drone's flight mission, the positions of all drones are continuously monitored, and the presence of conflict risks is determined based on the prediction model. By analyzing the velocity vectors, current positions and expected trajectories of the two drones, the probability of their collision at some point in the future is calculated.

[0091] If the predicted collision probability exceeds a set threshold, a re-route mechanism is triggered. Local obstacle avoidance algorithms (such as RRT* and APF) can be used to quickly find an alternative path, or the reinforcement learning model can be used again to generate a new flight plan. Adjustments must take into account the overall efficiency of the entire drone swarm to avoid chain reactions in the path.

[0092] The dynamic priority scheduling module is used to dynamically evaluate the priority of each UAV according to its status factors, allocate airspace resources based on the priority, and finally output the optimal route for each UAV.

[0093] Priority assessment considers status factors such as urgency, remaining drone battery / fuel, payload, and flight performance. Each drone is assigned a priority score based on these status factors. Using a greedy algorithm or other optimization algorithm, airspace resources are allocated as fairly as possible while meeting the basic needs of each drone. High-priority drones are given priority to occupy favorable routes; for low-priority drones, suboptimal routes that do not compromise overall safety are sought.

[0094] Finally, AI analysis takes into account the results of all these aspects and generates a final optimal route for each drone. This includes not only the basic path from the starting point to the destination, but also backup plans for unexpected situations, ensuring efficient and safe operations throughout the flight.

[0095] In another embodiment, there may be drones that fly independently in the urban airspace without registering with the system. These drones are considered "illegal flights". The existence of "illegal flights" will disrupt the order of the airspace and affect the normal flight of other registered drones, resulting in collisions or flight behaviors that endanger public safety.

[0096] In order to solve the problem of "illegal flying", the cloud server generates an inspection request at a specified time, generates a lighting instruction based on the inspection request and sends it to each drone in the distributed collaborative management and control network. Among them, the drone can receive the lighting instruction through the connected low-altitude intelligent flight control box and control the drone to flash the lights according to the predetermined pattern corresponding to the lighting instruction, and even feedback the real-time status of the drone through the flashing of the light.

[0097] For example, the green light flashes when the operation is normal, the yellow light flashes when the aircraft is in hovering state, and the SOS signal flashes when the aircraft is in emergency state.

[0098] Abnormal drones are identified by comparing the responses of each drone to the light-on command. For example, if some drones are unable to perform the light-on operation corresponding to the light-on command, it can be considered that the drone is an "illegal" drone that has not been registered with the network and is marked as an abnormal drone. Interference operations are performed on the abnormal drone, including position tracking, establishing a direct communication link, or sending interference signals to the abnormal drone to make it land safely.

[0099] This embodiment connects to the drone through a low-altitude intelligent flight control box. The low-altitude intelligent flight control box is compatible with different drone protocols and can communicate with drones of different brands to achieve unified qualification certification for drones across brands, solving the problem that the communication protocols of drones of different brands (such as DJI and XAG) are not interoperable and unified management and control cannot be achieved. It also automatically reviews drone qualifications through blockchain evidence records to improve drone flight safety. It combines the Beidou grid code to dynamically divide airspace resources and the AI agent algorithm to optimize route planning in real time, and quickly plans multiple flight routes for different drones in the same airspace, so as to achieve orderly management of airspace use and improve airspace utilization efficiency.

[0100] Example 2

[0101] This embodiment provides an urban low-altitude AI collaborative control system based on Beidou grid code and blockchain, which mainly includes a low-altitude intelligent flight control box and a cloud server.

[0102] Among them, the low-altitude intelligent flight control box is used to connect to the drone; the cloud server communicates with the drone connected to the low-altitude intelligent flight control box through a wireless network, wherein the cloud server executes the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain as described in Example 1. Figure 2 As shown, Figure 2Here, a represents the cloud server, c represents the drone, and b represents the low-altitude intelligent flight control box connected to the drone.

[0103] It should be noted that the module functions of the cloud server can be found in the corresponding description of the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain in Example 1, and will not be repeated here.

[0104] In this embodiment, the low-altitude intelligent flight control box installed outside the drone includes a multi-modal chipset to implement flight command proxy execution and local emergency decision-making. Specifically:

[0105] like Figure 3 As shown, the low-altitude intelligent flight control box includes:

[0106] The blockchain encryption chip has a standardized interface compatible with multiple drone protocols. It connects to drones through the standardized interface to obtain drone information, and records the drone information in the blockchain after encryption to ensure that the information cannot be tampered with. Among them, drone information includes drone qualification information, flight data, flight control instructions, etc.

[0107] The edge computing chip is used to make obstacle avoidance decisions based on preset rules when local sensors detect obstacles during flight. It then collaborates with cloud servers via wireless networks to request path replanning. This embodiment of the edge computing chip supports local obstacle avoidance decisions within 0.3 seconds, avoiding the difficulty of handling sudden obstacle avoidance requests associated with traditional centralized cloud-based scheduling, often due to end-to-cloud communication delays. This reduces cloud-based reliance.

[0108] The dual-mode positioning chip uses RTK (Real-Time Kinematic) combined with the Beidou dual-mode chip to achieve dynamic centimeter-level positioning, greatly enhancing the operational performance of drones and other applications in a variety of complex environments. It not only improves positioning accuracy, but also enhances the robustness and adaptability of the system, broadening its application scope.

[0109] The optical signal module features multiple LED lights, which can be either the drone's original LEDs or additional LEDs added to the circuit board of the low-altitude intelligent flight control box. The optical signal module controls these LEDs to provide feedback on the drone's flight status. It also receives lighting commands from a cloud server and switches the lighting status of the multiple LEDs accordingly, thereby enabling the detection of illegal flights.

[0110] In addition, the low-altitude intelligent flight control box can also realize the following functions:

[0111] The low-altitude intelligent flight control box can also include an identity authentication chip. When the low-altitude intelligent flight control box is connected to the drone, the identity of the drone owner is authenticated, so that the actual owner of the drone is responsible for the flight behavior of the drone after the shortlisted application, and becomes a qualified cooperative flight user.

[0112] The low-altitude intelligent flight control box monitors the status of various aircraft components in real time through its built-in sensor network (IMU, GPS, barometer, gyroscope, battery management system, motor drive module, etc.). Furthermore, drones connected to the low-altitude intelligent flight control box can also perform delegated flight operations according to system schedules or operate autonomously in manual mode within designated areas, enabling them to adapt to both automated scheduling and flexible user control.

[0113] This embodiment's low-altitude intelligent flight control box works in conjunction with a cloud server that implements a collaborative drone control method. This system uses blockchain to achieve unified identity authentication across drone brands. It dynamically allocates airspace resources using Beidou grid codes, and an AI agent algorithm optimizes route planning in real time. The low-altitude intelligent flight control box incorporates a built-in multimodal chipset that supports edge computing for emergency obstacle avoidance and optical signal status feedback, addressing challenges such as illegal flight identification, airspace conflicts, and large-scale dispatching.

[0114] After experiments, this system has been applied to scenarios such as urban logistics and emergency rescue. The airspace utilization rate has increased by 300% and the accident rate has dropped to 0.02 times per 10,000 flights.

[0115] Example 3

[0116] This embodiment provides an electronic device, Figure 4 FIG. 1 shows a structural block diagram of an electronic device according to an embodiment of the present invention. Figure 4 As shown, the electronic device includes: a memory 100 and a processor 200. The memory 100 stores a computer program that can be executed on the processor 200. When the processor 200 executes the computer program, it implements the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain in the above embodiment. The number of memory 100 and processor 200 can be one or more.

[0117] The electronic device also includes:

[0118] The communication interface 300 is used to communicate with external devices and perform data exchange transmission.

[0119] If the memory 100, the processor 200, and the communication interface 300 are implemented independently, the memory 100, the processor 200, and the communication interface 300 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc.

[0120] Optionally, in a specific implementation, if the memory 100, the processor 200 and the communication interface 300 are integrated on a chip, the memory 100, the processor 200 and the communication interface 300 can communicate with each other through an internal interface.

[0121] An embodiment of the present invention provides a computer-readable storage medium storing a computer program. When the program is executed by a processor, the method provided in the embodiment of the present invention is implemented.

[0122] An embodiment of the present invention further provides a chip, which includes a processor for calling and executing instructions stored in a memory, so that a communication device equipped with the chip executes the method provided by the embodiment of the present invention.

[0123] An embodiment of the present invention also provides a chip, comprising: an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected via an internal connection path, and the processor is used to execute the code in the memory. When the code is executed, the processor is used to execute the method provided by the embodiment of the invention.

[0124] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. It is worth noting that the processor may be a processor that supports the advanced reduced instruction set machine (ARM) architecture.

[0125] Furthermore, optionally, the above-mentioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory may include random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available. For example, static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM) and direct rambus RAM (DR RAM).

[0126] In the above embodiments, all or part of the embodiments may be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the present invention are generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0127] In the description of this specification, reference to the terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. In addition, those skilled in the art may combine and integrate different embodiments or examples described in this specification, as well as features of different embodiments or examples, unless otherwise inconsistent.

[0128] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0129] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various modifications and substitutions within the technical scope disclosed in the present invention, and such modifications and substitutions are intended to be encompassed by the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain is characterized by: include: Obtain drone information and search for corresponding evidence records in the blockchain based on the drone information; wherein the drone information is obtained through a low-altitude intelligent flight control box that is compatible with multiple drone protocols; The qualifications of the drone are automatically verified through the stored records. If the drone passes the qualification certification, the drone is included in the distributed collaborative control network for unified scheduling; Obtain an airspace map, set flight permissions based on the airspace classification in the airspace map, and generate corresponding geofences based on the flight permissions to limit the flight range of each drone in the distributed collaborative control network; Based on the Beidou grid code, the airspace map is divided into space-time grids of specified resolution according to the time and space dimensions. Based on the AI reinforcement learning engine, the status information of each grid cell in the space-time grid is analyzed, and the flight path of each UAV is dynamically optimized to generate the optimal route for each UAV.

2. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain according to claim 1 is characterized in that: Also includes: Predefine flight airspace types, deploy corresponding smart contracts for each flight airspace type, and submit the smart contracts to the blockchain for evidence storage; the smart contracts define the storage rules, permission control mechanism, and conflict detection of flight data; Obtain the flight data of the drone, which includes location information, timestamp, and flight status; select the corresponding blockchain storage node using a dynamic sharding strategy based on the spatiotemporal attributes of the flight data, and submit the flight data to the corresponding blockchain storage node for evidence storage.

3. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain according to claim 1 is characterized in that: The method for generating the optimal route includes: Use a pre-trained reinforcement learning model to perform multi-drone path planning for the drone swarm based on the state information of each grid cell, generating a flight path for each drone; Based on the conflict detection model, the flight path of each drone in the drone swarm is detected for conflict, the probability of conflict between drones is predicted, and when the probability of conflict is higher than the threshold, the flight path of the drone swarm is dynamically adjusted to ensure conflict-free flight. The priority of each drone is dynamically evaluated according to its status factors, airspace resources are allocated based on the priority, and the optimal route for each drone is finally output.

4. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain according to claim 1 is characterized in that: Also includes: Generate a check request at a specified time interval, and send a light-on command to the low-altitude intelligent flight control box connected to the drone based on the check request. The light-on command is used to control the drone to flash its lights according to a predetermined pattern, or to provide feedback on the drone's real-time status through light flashing; By comparing the responses of each drone to the light-up command, abnormal drones are identified and interference operations are performed on the abnormal drones. The interference operations include position tracking, establishing a direct communication link, or sending interference signals to the abnormal drone to make it land safely.

5. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain according to claim 1 is characterized in that: Generating a corresponding geo-fence according to the flight permission to limit the flight range of each drone in the distributed collaborative management and control network includes: Dividing the airspace map into four-dimensional grid cells of specified specifications; Encoding each of the four-dimensional grid cells based on a Beidou grid code to generate an identifier for each of the four-dimensional grid cells; The geo-fence is generated by defining the allowed or prohibited areas using the identifier.

6. The urban low-altitude AI collaborative control method based on Beidou grid code and blockchain according to claim 1 is characterized in that: Also includes: Through the issuance of Token auctions on the blockchain, the right to use the designated space-time grid can be traded through Token auctions.

7. The urban low-altitude AI collaborative control system based on Beidou grid code and blockchain is characterized by: include: Low-altitude intelligent flight control box, used to connect with the drone; The cloud server is connected to the low-altitude intelligent flight control box through a network, and is used to execute the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain as described in any one of claims 1 to 6.

8. The urban low-altitude AI collaborative control system based on Beidou grid code and blockchain according to claim 7 is characterized in that: The low-altitude intelligent flight control box includes: A blockchain encryption chip with a standardized interface compatible with multiple drone protocols. It connects to drones through the standardized interface and is used to encrypt and record drone information on the blockchain. The drone information includes drone qualifications, flight data, and flight control commands. An edge computing chip, configured to make obstacle avoidance decisions according to preset rules when an obstacle is detected, and to coordinate with the cloud server via a wireless network to request the cloud server to replan a path; Dual-mode positioning chip, used to achieve dynamic centimeter-level positioning.

9. The urban low-altitude AI collaborative control system based on Beidou grid code and blockchain according to claim 7 is characterized in that: The low-altitude intelligent flight control box also includes: The optical signal module is used to feedback the flight status of the drone and switch the drone's light status according to the light-on command to achieve the purpose of troubleshooting.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the urban low-altitude AI collaborative control method based on Beidou grid code and blockchain as described in any one of claims 1 to 6.

Images