Management and control method, system and device of smart city unmanned system and medium

Abstract

The invention relates to a management and control method, system and device for a smart city unmanned system and a medium. The management and control method comprises the steps that real-time state data, collected by a sensor, of an unmanned aerial vehicle and an unmanned vehicle are received; acquiring urban traffic flow data and environmental data; performing moving trajectory prediction on the unmanned aerial vehicle and the unmanned vehicle to obtain an unmanned vehicle prediction trajectory and an unmanned aerial vehicle prediction trajectory; performing path intersection judgment on the unmanned aerial vehicle prediction trajectory and the unmanned vehicle prediction trajectory to obtain corresponding path intersection information; determining a potential conflict area according to the path intersection information, and performing conflict risk assessment on the potential conflict area in combination with the environment data and the path intersection information to obtain a conflict risk level; generating corresponding conflict early warning information according to the conflict risk level; and generating a corresponding path adjustment strategy based on the conflict early warning information and sending the path adjustment strategy to the unmanned system. According to the invention, the operation safety of the unmanned system in urban traffic can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of smart cities, and particularly to a control method, system, device and medium for an unmanned system in a smart city. Background Art

[0002] With the rapid development of unmanned system technology, especially the wide application of unmanned driving devices such as drones and unmanned vehicles, the construction of smart cities faces new challenges. The application of drones in fields such as logistics distribution, aerial inspection, and environmental monitoring is increasing continuously, while unmanned vehicles show great potential in urban public transportation, shared travel, and cargo transportation. While these unmanned systems provide convenience and improve efficiency, they also pose new problems in the scheduling and management of air and ground traffic resources.

[0003] Currently, urban traffic management systems usually focus on the planning and management of ground traffic, mainly relying on means such as traffic lights and road network planning for scheduling, but the management and scheduling system for aerial unmanned systems is not yet perfect. Since the air and ground traffic systems are usually managed by independent monitoring platforms, there is a lack of an effective sharing and cooperation mechanism for air monitoring and ground monitoring data. With the increasing number of drones and unmanned vehicles in the city, the conflict problem of air and ground traffic has become more complex and urgent. Especially when drones and unmanned vehicles operate in the same spatial area, conflicts between air and ground traffic may occur due to factors such as path intersections, speed differences, and real-time traffic changes, thus threatening urban public safety. Summary of the Invention

[0004] In order to improve the operating safety of unmanned systems in urban traffic, the present application provides a control method, system, device and medium for an unmanned system in a smart city.

[0005] In a first aspect, the present application provides a control method, system, device and medium for an unmanned system in a smart city, adopting the following technical solutions: A control method for an unmanned system in a smart city, the control method comprising: Receiving real-time status data of drones and unmanned vehicles collected by sensors; Obtaining urban traffic flow data and environmental data; Predicting the operation trajectory of the drone according to the real-time status data to obtain a predicted drone trajectory; Predicting the operation trajectory of the unmanned vehicle according to the real-time status data and urban traffic flow data to obtain a predicted unmanned vehicle trajectory; Judging the path intersection of the predicted drone trajectory and the predicted unmanned vehicle trajectory to obtain corresponding path intersection information; Determine potential conflict areas based on the path intersection information, and conduct a conflict risk assessment on the potential conflict areas by combining the environmental data and the path intersection information to obtain a conflict risk level; Generate corresponding conflict warning information according to the conflict risk level; Generate a corresponding path adjustment strategy based on the conflict warning information and send it to the unmanned system; wherein, the unmanned system is used to adjust the paths of the unmanned aerial vehicle and the unmanned vehicle respectively according to the path adjustment strategy.

[0006] By adopting the above technical solution, the system can accurately predict the respective movement trajectories in real time by collecting and analyzing the status data of the unmanned aerial vehicle and the unmanned vehicle, combining the urban traffic flow and environmental information, timely identify potential conflict areas, and judge the severity of the conflict through risk assessment to ensure real-time response to emergencies. At the same time, the conflict warning information and path adjustment strategy generated by the system can effectively reduce the conflict risk between unmanned systems, reduce the safety hazard problems in urban air-ground traffic, improve the operation safety of unmanned systems in urban traffic, and provide strong technical support for the sustainable development of smart cities.

[0007] Optionally, the steps of predicting the flight trajectory of the unmanned aerial vehicle according to the real-time status data to obtain the predicted trajectory of the unmanned aerial vehicle include: Analyze the real-time status data to obtain the current position, current speed, heading angle, flight altitude information and acceleration of the unmanned aerial vehicle; Based on the real-time status data, predict the future trajectory of the unmanned aerial vehicle based on a linear motion model, and calculate a sequence of unmanned aerial vehicle trajectory points within each preset time step; According to the current speed, acceleration and heading angle of the unmanned aerial vehicle, update the sequence of unmanned aerial vehicle trajectory points based on an acceleration correction model to obtain the predicted trajectory of the unmanned aerial vehicle in the future time period after correction.

[0008] By adopting the above technical solution, a preliminary prediction of the future trajectory of the unmanned aerial vehicle is made based on a linear motion model, which is applicable to steady-state flight scenarios; then, by introducing an acceleration correction model to dynamically correct the trajectory, factors such as acceleration and deceleration are considered, making the trajectory prediction more accurate and reliable. This technical solution improves the accuracy of unmanned aerial vehicle trajectory prediction, especially applicable to trajectory prediction in complex flight scenarios.

[0009] Optionally, the steps of predicting the driving trajectory of the unmanned vehicle according to the real-time status data and urban traffic flow data to obtain the predicted trajectory of the unmanned vehicle include: Analyze the real-time status data to obtain the current position, current speed, steering angle and acceleration information of the unmanned vehicle; Based on the real-time status data, predict the future trajectory of the driverless vehicle based on the vehicle dynamics model, and calculate the sequence of driverless vehicle trajectory points within each preset time step; Analyze the urban traffic flow data to obtain traffic signal status, lane information, and real-time road condition information; Modify the sequence of driverless vehicle trajectory points according to the urban traffic flow data to obtain the predicted trajectory of the driverless vehicle in the future time period after modification.

[0010] By adopting the above technical solution, predict the future trajectory of the driverless vehicle based on the vehicle dynamics model to ensure the rationality of the path. At the same time, dynamically modify the predicted trajectory in combination with traffic data, so that the driving path of the driverless vehicle can adapt to the changes of the external environment in real time. This technical solution provides a more accurate, intelligent, and dynamic driverless vehicle trajectory prediction system through comprehensive consideration of the driverless vehicle state and the external environment.

[0011] Optionally, the steps of judging the path intersection of the drone prediction trajectory and the driverless vehicle prediction trajectory to obtain the corresponding path intersection information include: Based on geometric modeling, convert the drone prediction trajectory and the driverless vehicle prediction trajectory into a drone trajectory path and a driverless vehicle trajectory path respectively; Perform intersection calculation on the drone trajectory path and the driverless vehicle trajectory path to determine the potential intersection information of the drone and the driverless vehicle; the potential intersection information includes the potential intersection position and the potential intersection time; Obtain the motion time windows of the drone and the driverless vehicle; Compare the motion time windows of the drone and the driverless vehicle respectively according to the potential intersection information; Judge whether the potential intersection time is within the motion time windows of the drone and the driverless vehicle; If not, determine the potential intersection as an invalid intersection; If so, determine the potential intersection as a valid intersection; Obtain the path intersection information according to the spatial coordinates and intersection time of the valid intersection.

[0012] By adopting the above technical solution, based on accurate geometric modeling and intersection calculation, combined with the comparison of the motion time windows, effectively judge the potential intersections between the drone path and the driverless vehicle path, and generate the corresponding path intersection information, so as to accurately identify the possible collision events between the two in the future, and provide reliable data support for subsequent conflict prediction and avoidance decision-making. This technical solution not only improves the accuracy of trajectory prediction, but also can dynamically adapt to complex air-ground environments, significantly enhancing the safety and efficiency of the unmanned system in the smart city environment.

[0013] Optionally, the step of determining a potential conflict area according to the path intersection information, and performing a conflict risk assessment on the potential conflict area in combination with the environmental data and the path intersection information to obtain a conflict risk level includes: Calculate the relative distance of each valid intersection point according to the path intersection information; Determine whether the relative distance of each valid intersection is less than a preset safety distance threshold, and if so, determine the area where the valid intersection is located as a potential conflict area; Obtaining the path intersection duration, relative distance, and relative speed difference of the UAV and the UGV in the potential conflict area; Calculating a corresponding environmental correction factor according to the environmental data; Correcting the relative distance and the relative speed difference based on the environmental correction factor to obtain a corrected relative distance and relative speed difference; Based on a preset risk assessment algorithm, a conflict risk score is calculated according to the path intersection time, the environmental correction factor, the corrected relative distance and the relative speed difference; Based on a preset level mapping table, a corresponding conflict risk level is determined according to the conflict risk score.

[0014] By employing this technical solution, the system integrates path intersection information, corrected relative distances, relative speed differences, and environmental data to calculate a conflict risk score. This score is then converted into a specific risk level using a pre-set level mapping table. This allows the system to accurately assess the potential conflict risk between drones and unmanned vehicles in future intersection areas. The risk assessment process dynamically adjusts the weights and correction factors of various factors to ensure the accuracy and real-time nature of conflict risk assessments, providing a scientific basis for subsequent path adjustments, collision avoidance strategies, and emergency response, significantly improving the safety of unmanned systems.

[0015] Optionally, the calculation formula of the preset risk assessment algorithm is: Risk_score=w1×T+w2×(1 / D′)+w3×V′+w4×α enu ; Among them, w1 is the intersection time weight, T is the path intersection time, D′ is the corrected relative distance, w2 is the relative distance weight, V′ is the corrected relative speed difference, w3 is the relative speed difference weight, α enu is the environmental correction factor, and w4 is the environmental weight.

[0016] Secondly, this application provides a smart city unmanned system management and control system, which adopts the following technical solutions: A management and control system for an unmanned system in a smart city, the management and control system comprising: A status data receiving module, configured to receive real-time status data of an unmanned aerial vehicle and an unmanned vehicle collected by sensors; An obtaining module, configured to obtain urban traffic flow data and environmental data; An unmanned aerial vehicle trajectory prediction module, configured to perform an operation trajectory prediction on the unmanned aerial vehicle according to the real-time status data to obtain an unmanned aerial vehicle predicted trajectory; An unmanned vehicle trajectory prediction module, configured to perform an operation trajectory prediction on the unmanned vehicle according to the real-time status data and urban traffic flow data to obtain an unmanned vehicle predicted trajectory; A path intersection analysis module, configured to perform a path intersection judgment on the unmanned aerial vehicle predicted trajectory and the unmanned vehicle predicted trajectory to obtain corresponding path intersection information; A conflict risk assessment module, configured to determine a potential conflict area according to the path intersection information, and perform a conflict risk assessment on the potential conflict area in combination with the environmental data and the path intersection information to obtain a conflict risk level; A conflict warning module, configured to generate corresponding conflict warning information according to the conflict risk level; A path strategy adjustment module, configured to generate a corresponding path adjustment strategy based on the conflict warning information and send it to an unmanned system; wherein, the unmanned system is configured to perform path adjustment on the unmanned aerial vehicle and the unmanned vehicle respectively according to the path adjustment strategy.

[0017] Optionally, the path intersection analysis module includes: A trajectory path conversion unit, configured to respectively convert the unmanned aerial vehicle predicted trajectory and the unmanned vehicle predicted trajectory into an unmanned aerial vehicle trajectory path and an unmanned vehicle trajectory path based on geometric modeling; An intersection calculation unit, configured to perform an intersection calculation on the unmanned aerial vehicle trajectory path and the unmanned vehicle trajectory path to determine potential intersection point information of the unmanned aerial vehicle and the unmanned vehicle; the potential intersection point information includes a potential intersection point position and a potential intersection point time; A time window obtaining unit, configured to obtain a motion time window of the unmanned aerial vehicle and the unmanned vehicle; A time comparison unit, configured to respectively compare the motion time window of the unmanned aerial vehicle and the unmanned vehicle according to the potential intersection point information; A judgment unit, configured to judge whether the potential intersection point time is within the motion time window of the unmanned aerial vehicle and the unmanned vehicle; if so, output an intersection point valid result, and determine the potential intersection point as a valid intersection point; A path intersection information generation unit, configured to, in response to the intersection point valid result, obtain path intersection information according to the spatial coordinates and intersection point time of the valid intersection point.

[0018] In a third aspect, the present application provides a computer device, adopting the following technical solution: A computer device includes a memory, a processor, and a computer program stored on the memory. The processor executes the computer program to implement the steps of the method described in the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, adopting the following technical solution: A computer-readable storage medium stores a computer program that can be loaded and executed by a processor to perform any of the methods in the first aspect.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: By combining real-time status data, environmental information, and trajectory prediction technology, it is possible to accurately identify potential conflict areas between drones and unmanned vehicles, and generate dynamic conflict warning information based on conflict risk assessment, thereby optimizing the operation paths of drones and unmanned vehicles in a timely manner, avoiding collision risks, and improving the safety and collaborative operation efficiency of the unmanned system. This intelligent control solution effectively enhances the adaptability of the unmanned system in complex environments and provides efficient and reliable technical support for the intelligent traffic management of smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 FIG. is a first flowchart showing a control method for an unmanned system in a smart city according to one embodiment of the present application.

[0022] Figure 2 FIG. is a second flowchart showing a control method for an unmanned system in a smart city according to one embodiment of the present application.

[0023] Figure 3 FIG. is a third flowchart showing a control method for an unmanned system in a smart city according to one embodiment of the present application.

[0024] Figure 4 FIG. is a fourth flowchart showing a control method for an unmanned system in a smart city according to one embodiment of the present application.

[0025] Figure 5 FIG. is a fifth flowchart showing a control method for an unmanned system in a smart city according to one embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] In order to make the objectives, technical solutions, and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying Figures 1-5 drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0027] Embodiments of the present application disclose a control method for an unmanned system in a smart city.

[0028] Referring toFigure 1 A method for controlling an unmanned system in a smart city, the method comprising: Step S101, receiving real-time status data of the UAV and the unmanned vehicle collected by sensors; Among them, the data collected by the sensors include the real-time position, speed, heading, flight altitude (for drones) and current road conditions (for unmanned vehicles) of drones and unmanned vehicles, as well as the acceleration, attitude angle, driving direction, etc. measured by the sensors.

[0029] In some embodiments, Internet of Things (IoT) devices can be used in conjunction with GPS, inertial measurement units (IMUs), lidar, cameras, and other sensors to acquire high-precision, real-time data. Drones might use GPS and IMUs to measure position and altitude, while autonomous vehicles (AVs) use GPS and onboard sensors (such as radar, cameras, and lidar) for state awareness. This data is then transmitted in real time to a data acquisition and processing platform.

[0030] Step S102, obtaining urban traffic flow data and environmental data; Among them, urban traffic flow data includes road capacity, traffic light status, traffic flow, congestion information, etc., and environmental data includes weather information, wind speed, temperature, humidity, road conditions, etc.

[0031] In some embodiments, urban traffic flow data can be obtained in real time through traffic surveillance cameras, roadside sensors, intelligent traffic signal systems, and existing traffic management platforms. Environmental data can be obtained through meteorological sensors, drone-based weather monitoring systems, or open public data platforms. After unified processing, this data will serve as input to support subsequent path intersection determination and conflict risk assessment.

[0032] It is understandable that taking traffic flow and environmental factors into consideration will help to make a comprehensive prediction of the operating conditions of drones and unmanned vehicles in complex urban environments, ensuring the accuracy and reliability of the prediction process.

[0033] Step S103: predicting the trajectory of the UAV based on the real-time status data to obtain a predicted trajectory of the UAV; In some embodiments, the trajectory prediction of a drone can be based on a physical motion model (e.g., a linear motion model, an acceleration model, etc.) combined with information such as the drone's current speed, heading, and altitude. By extrapolating the drone's current position and motion state, the drone's future trajectory can be derived.

[0034] Step S104: predicting the trajectory of the unmanned vehicle based on the real-time status data and the urban traffic flow data to obtain a predicted trajectory of the unmanned vehicle; For the trajectory prediction of the driverless vehicle, it can be based on the vehicle dynamics model and road condition information. Considering factors such as road traffic flow and traffic signals, the future trajectory of the driverless vehicle can be predicted by calculating its driving path. In addition, the driverless vehicle may adopt more complex models, such as lane keeping model, braking model, turning model, etc., to more accurately reflect the changes in the real environment.

[0035] Step S105, determine the path intersection of the predicted trajectory of the drone and the predicted trajectory of the driverless vehicle to obtain the corresponding path intersection information; Among them, by calculating the trajectory intersection of the drone and the driverless vehicle, use mathematical methods (such as geometric models, time window analysis) to judge whether they approach or coincide at a certain future time point, and determine the corresponding intersection area and intersection time.

[0036] Specifically, regard the trajectories of the drone and the driverless vehicle as paths in space. By calculating the intersection points of the two paths (based on the geometric parameters of the paths, such as the intersection of straight lines), for each possible intersection point, calculate the intersection time and determine whether it occurs within the movement time windows of the two, so as to determine the potential intersection area and provide a basis for conflict prediction.

[0037] Step S106, determine the potential conflict area according to the path intersection information, and combine the environmental data and the path intersection information to evaluate the conflict risk of the potential conflict area to obtain the conflict risk level; Among them, the path intersection information provides the spatial coordinates and time information of all the intersection points where the two systems (drone and driverless vehicle) meet. Through this information, it is possible to determine which intersection points are potential conflict areas. For example, for each intersection point, calculate the relative distance between the intersection points. If the relative distance is less than the preset safety distance threshold, then the intersection point and its nearby area can be regarded as potential conflict areas.

[0038] In some embodiments, the risk level of the potential conflict area can be evaluated according to various factors (such as path intersection time, relative speed, meteorological conditions, etc.). For example, the length of the path intersection time can be evaluated. If the intersection time is long, it means that the possibility of their coincidence in space is large and the conflict risk is high; according to information such as speed difference, heading angle difference, relative distance, etc., calculate the relative motion model to determine whether there will be a large impact; according to environmental factors, such as wind speed, weather changes, etc., further increase the accuracy of conflict assessment.

[0039] Step S107, generate the corresponding conflict warning information according to the conflict risk level; Among them, according to the evaluated conflict risk level, the system generates early warning information, and different levels of risks generate early warning signals of different intensities, which can be specifically pushed to the corresponding control center or unmanned system operator through text messages, emails, or mobile applications to guide them to take corresponding countermeasures.

[0040] Step S108, generate a corresponding path adjustment strategy based on the conflict early warning information and send it to the unmanned system; among them, the unmanned system is used to adjust the paths of the unmanned aerial vehicle and the unmanned vehicle respectively according to the path adjustment strategy.

[0041] Among them, according to the conflict early warning information and combined with the current states of the unmanned aerial vehicle and the unmanned vehicle, a path adjustment strategy is formulated. This strategy includes adjusting the speed, changing the heading or flight altitude, etc. For example, through algorithms (such as the A* algorithm, path optimization algorithm, etc.), a new safe path is calculated and sent to the unmanned system for execution.

[0042] In some embodiments, specific path adjustment strategies can be generated according to different conflict types. For example, when the conflict area is in front of the current path and the time is urgent, the path intersection time can be extended or shortened by adjusting the speed to reduce the possibility of encounter; when the conflict area is on the side of or approaching the current path, the heading angle or flight path can be changed to make the unmanned aerial vehicle or the unmanned vehicle deviate from the current path to avoid encounter; for flying objects (unmanned aerial vehicles) in three-dimensional space and vehicles (unmanned vehicles) in two-dimensional space, the potential conflict area can be avoided by adjusting the flight altitude or changing lanes respectively.

[0043] In the above implementation manner, by collecting and analyzing the state data of the unmanned aerial vehicle and the unmanned vehicle in real time and combining the urban traffic flow and environmental information, the system can accurately predict their respective movement trajectories, timely identify potential conflict areas, and judge the severity of the conflict through risk assessment to ensure real-time response to emergencies. At the same time, the conflict early warning information and path adjustment strategy generated by the system can effectively reduce the conflict risk between unmanned systems, reduce the potential safety hazard problems in urban air-ground traffic, improve the operation safety of unmanned systems in urban traffic, and provide strong technical support for the sustainable development of smart cities.

[0044] Refer to Figure 2 , as an implementation manner of step S103, the steps of predicting the operation trajectory of the unmanned aerial vehicle according to the real-time state data to obtain the predicted trajectory of the unmanned aerial vehicle include: Step S201, parse the real-time state data to obtain the current position, current speed, heading angle, flight altitude information and acceleration of the unmanned aerial vehicle; Among them, the motion information of the UAV is extracted from the real-time status data, including key parameters such as position, speed, heading, flight altitude, and acceleration. These data are sourced from various sensors on the UAV (such as GPS, Inertial Measurement Unit (IMU), speedometer, barometer, etc.) and are usually uploaded to the ground control system or flight controller in real time.

[0045] Step S202: Based on the real-time status data, perform future trajectory prediction on the UAV according to the linear motion model, and calculate the sequence of UAV trajectory points within each preset time step. Among them, the linear motion model calculates the future trajectory of the UAV for a period of time by using the current speed, heading angle, and current position.

[0046] Specifically, the core assumption of the linear motion model is that in the absence of external force interference, an object moves along a straight path at a constant speed. In practical applications, combined with the heading angle of the UAV, the velocity components in the horizontal and vertical directions can be calculated respectively, and the expected position of the UAV within each time step can be deduced. A new position coordinate point can be obtained for each preset time step (such as every second or every 10 milliseconds), thus forming a sequence of predicted trajectory points.

[0047] Step S203: Update the UAV trajectory point sequence based on the acceleration correction model according to the current speed, acceleration, and heading angle of the UAV, and obtain the predicted trajectory of the UAV in the future time period after correction.

[0048] Among them, the acceleration correction model is used to consider the dynamic changes during the UAV's motion (such as acceleration, deceleration, or turning). Since the linear motion model cannot accurately predict the trajectory in the case of acceleration or deceleration, it is necessary to introduce acceleration and turning changes to further correct the trajectory prediction. By considering the correction effect of acceleration on the UAV's path, the future trajectory is no longer limited to a straight line and can reflect more complex flight behaviors, such as acceleration or deceleration.

[0049] It can be understood that by introducing dynamic factors, the accuracy of trajectory prediction is significantly improved. Especially for UAVs that need to change speed or flight attitude, the model can adapt to the changes in their flight states and provide more accurate trajectory predictions. This is of great significance for safety issues such as avoiding collisions and flight path conflicts.

[0050] In the above implementation, the future trajectory of the UAV is initially predicted based on the linear motion model, which is applicable to steady-state flight scenarios; then, by introducing the acceleration correction model, the trajectory is dynamically corrected, considering factors such as acceleration and deceleration, making the trajectory prediction more accurate and reliable. This technical solution improves the accuracy of UAV trajectory prediction, especially applicable to trajectory prediction in complex flight scenarios.

[0051] Reference Figure 3 , as an implementation of step S104, the steps of predicting the running trajectory of the driverless vehicle according to the real-time status data and urban traffic flow data to obtain the predicted trajectory of the driverless vehicle include: Step S301, analyze the real-time status data to obtain the current position, current speed, steering angle, and acceleration information of the driverless vehicle; Among them, the motion parameters of the driverless vehicle are extracted from the real-time status data, including the current position, speed, steering angle, and acceleration. These data usually come from the sensor system inside the driverless vehicle (such as GPS, IMU, speed sensor, steering sensor, accelerometer, etc.). Each parameter plays a crucial role in trajectory prediction.

[0052] Step S302, based on the real-time status data, perform future trajectory prediction on the driverless vehicle based on the vehicle dynamics model, and calculate the sequence of trajectory points of the driverless vehicle within each preset time step; Among them, the vehicle dynamics model takes into account the physical characteristics of the vehicle (such as mass, friction, power transmission, etc.), as well as behaviors such as acceleration, deceleration, and steering that may occur during vehicle driving. According to information such as the current speed, acceleration, and steering angle of the vehicle, the dynamics model can deduce the position change of the driverless vehicle within the future time step through numerical solution or analytical method, including the predicted position of the driverless vehicle (including lateral and longitudinal positions), so as to obtain the sequence of trajectory points. For example, setting one time step per second, the trajectory points for each future second are gradually calculated through the current state information (speed, acceleration, and steering angle).

[0053] In some embodiments, common dynamics models include constant-speed driving models, acceleration and deceleration models, steering models, etc. When the driverless vehicle is driving at a constant speed, the constant-speed driving model can calculate the driving path of the vehicle based on the speed and steering angle; when the driverless vehicle is accelerating or decelerating, the acceleration and deceleration model can calculate the future speed change through the acceleration (positive or negative); when the driverless vehicle is turning, the motion path of the vehicle will change in a curve, and the steering model needs to consider factors such as the turning radius and direction change of the vehicle.

[0054] Step S303, analyze the urban traffic flow data to obtain the traffic signal status, lane information, and real-time road condition information; Among them, by incorporating external environmental factors (such as traffic signals, road conditions, lane information, etc.) into the trajectory prediction, the driving strategy and driving path are adjusted. Urban traffic flow data usually comes from devices such as traffic monitoring systems, road sensors, and vehicle-to-everything (V2X), and can provide real-time road information.

[0055] Step S303: Modify the sequence of the unmanned vehicle's trajectory points according to the urban traffic flow data to obtain the predicted trajectory of the unmanned vehicle in the future time period after correction.

[0056] In some embodiments, the trajectory of the unmanned vehicle can be adjusted based on urban traffic flow information (such as traffic signals, lane information, road conditions, etc.).

[0057] For example, if the traffic signal shows a red light, the system sets the driving speed of the unmanned vehicle to zero or adjusts the driving time according to the change of the traffic light. If the road condition information shows that there is congestion or an accident in certain sections, the system can adjust the path of the unmanned vehicle to avoid these areas, for example, by changing the driving lane or choosing other alternative routes. According to the lane information, the path sequence of the unmanned vehicle may change. For example, it may be necessary to change lanes to avoid obstacles or comply with traffic rules (for example, vehicles must drive in the specified lanes).

[0058] In the above embodiments, the future trajectory of the unmanned vehicle is predicted based on the vehicle dynamics model to ensure the rationality of the path. At the same time, the predicted trajectory is dynamically corrected in combination with traffic data, so that the driving path of the unmanned vehicle can adapt to the changes of the external environment in real time. This technical solution provides a more accurate, intelligent and dynamic unmanned vehicle trajectory prediction system by comprehensively considering the state of the unmanned vehicle and the external environment.

[0059] Referring to Figure 4 , as an implementation manner of step S105, the steps of performing path intersection judgment on the predicted trajectory of the unmanned aerial vehicle and the predicted trajectory of the unmanned vehicle to obtain the corresponding path intersection information include: Step S401: Based on geometric modeling, convert the predicted trajectory of the unmanned aerial vehicle and the predicted trajectory of the unmanned vehicle into the trajectory path of the unmanned aerial vehicle and the trajectory path of the unmanned vehicle respectively; Among them, the trajectory path of the unmanned aerial vehicle is based on its predicted trajectory point sequence, and through geometric modeling methods (such as interpolation algorithms, spline curves, etc.), it is converted from discrete point data into a smooth continuous trajectory curve. For example, the cubic spline interpolation method can be used to smooth the trajectory of the unmanned aerial vehicle in three-dimensional space.

[0060] Similarly, the trajectory path of the unmanned vehicle is also based on the predicted trajectory point sequence. However, since the trajectory of the unmanned vehicle usually travels on the ground, the path modeling can be based on a two-dimensional plane geometric model and use linear or non-linear interpolation methods to generate a smooth curve.

[0061] It should be noted that considering that the driving of the unmanned vehicle may be affected by factors such as traffic signals and lane restrictions, the trajectory modeling also needs to consider the boundary conditions of the road.

[0062] Step S402: performing intersection calculation on the UAV trajectory path and the unmanned vehicle trajectory path to determine potential intersection information of the UAV and the unmanned vehicle; the potential intersection information includes the potential intersection position and the potential intersection time; In one embodiment of the present application, it is assumed that the trajectory path of the drone is a three-dimensional curve, representing the drone's movement in the air, while the trajectory path of the unmanned vehicle is a two-dimensional curve, representing its movement on the ground. Intersection calculation is typically performed by solving the intersection point of the two paths. For example, the distance between the two paths can be calculated to obtain the possible intersection points. When the distance between the two paths is less than a certain threshold, it can be considered that there is a potential intersection point.

[0063] Specifically, regarding the intersection calculation, numerical calculation methods such as the shortest distance method and Newton's method can be used to infer the intersection of the two trajectories for the two curves, and the spatial position of the intersection and the corresponding time can be obtained by calculation.

[0064] It can be understood that by calculating the intersection of two trajectory paths, the potential intersection point between the two can be effectively identified, and a basis for further conflict prediction and avoidance can be provided, thereby providing the entire system with preliminary data related to the actual possibility of collision.

[0065] Step S403, obtaining the movement time windows of the UAV and the unmanned vehicle; Among them, each unmanned system has a movement time window, which represents its expected movement duration and available movement time period.

[0066] Specifically, a drone's movement time window is determined by the start and end times of its predicted trajectory, typically based on the drone's mission planning or flight control system. An unmanned vehicle's movement time window is determined by external factors such as the vehicle's travel plan, traffic signals, and traffic flow.

[0067] Step S404: comparing the motion time windows of the UAV and the UAV respectively based on the potential intersection information; The system analyzes the time windows of the drone and the unmanned vehicle to determine whether a potential collision will occur within the actual timeframe. For each potential intersection, the system checks whether its time falls within the timeframe of the drone and the unmanned vehicle. If the potential intersection falls within the timeframe of the two systems, it indicates that the intersection is likely to occur in reality. This effectively filters out intersections occurring in irrelevant timeframes, improving accuracy and reducing misjudgments.

[0068] Step S405: determine whether the potential intersection time is within the movement time window of the UAV and the unmanned vehicle; if so, jump to step S406; if not, jump to step S407; Step S406, determining the potential intersection points as valid intersection points; Step S407, determining the potential intersection points as invalid intersection points; Specifically, the system determines whether a potential intersection point is valid based on the result of the time window comparison. If the potential intersection point occurs within the movement time windows of both, then this intersection point is regarded as a valid intersection point, which means that they will meet at a certain point in time and there is a risk of collision. If the potential intersection point does not fall within the movement time windows of both, then this intersection point is determined to be an invalid intersection point and need not be considered.

[0069] Step S408, obtaining path intersection information based on the spatial coordinates and intersection time of the valid intersection points.

[0070] Among them, once a valid intersection point is determined, the system will generate path intersection information based on the spatial coordinates and intersection time of the valid intersection point. The path intersection information includes the specific location and specific time of occurrence of the collision risk area, serving as a key basis for subsequent conflict prediction and avoidance decisions.

[0071] Specifically, the spatial coordinates of the intersection point can be calculated through path intersection calculation, usually represented in a geographic coordinate system or a relative coordinate system, and these coordinates represent the positions where the UAV and the unmanned vehicle may have a conflict. The time of the intersection point is usually obtained through the time window comparison step, and this time represents the specific occurrence moment of the potential collision.

[0072] In the above implementation, based on precise geometric modeling and intersection calculation, combined with the comparison of movement time windows, the potential intersection points between the paths of the UAV and the unmanned vehicle are effectively judged, and the corresponding path intersection information is generated, so as to accurately identify the possible collision events between the two in the future and provide reliable data support for subsequent conflict prediction and avoidance decisions. This technical solution not only improves the accuracy of trajectory prediction, but also can dynamically adapt to complex air-ground environments, significantly enhancing the safety and efficiency of the unmanned system in the smart city environment.

[0073] Referring to Figure 5 , as an implementation of step S106, the steps of determining the potential conflict area according to the path intersection information and performing a conflict risk assessment on the potential conflict area in combination with the environmental data and the path intersection information to obtain the conflict risk level include: Step S501, calculating the relative distance of each valid intersection point according to the path intersection information; Among them, a valid intersection point refers to the spatial intersection area between the UAV and the unmanned vehicle within the predicted time period. By modeling the paths of the UAV and the unmanned vehicle (usually as a straight line or curve based on a sequence of trajectory points), and then calculating the minimum distance between the UAV and the unmanned vehicle within the intersection area.

[0074] Step S502: Determine whether the relative distance of each valid intersection point is less than a preset safety distance threshold. If so, determine the area where the valid intersection point is located as a potential conflict area. If not, re - execute Step S502 for the next valid intersection point; Among them, compare the calculated relative distance of each valid intersection point with the preset safety distance threshold to determine whether the relative distance is less than the threshold. If the relative distance is less than the safety distance threshold, it indicates that there may be a collision between the two, and thus the area where the intersection point is located can be determined as a potential conflict area.

[0075] Step S503: Obtain the path intersection duration, relative distance, and relative speed difference of the drone and the unmanned vehicle within the potential conflict area; In some embodiments, by analyzing the time window of the path intersection point (i.e., the duration of the intersection), the path intersection duration of the drone and the unmanned vehicle can be determined. The longer the path intersection duration, the larger the encounter time window, and the higher the conflict risk. The relative distance represents the minimum distance between the two within the intersection area. The smaller this distance, the higher the conflict risk. The relative speed difference represents the speed difference of the relative motion between the two within the intersection area, which can be obtained by calculating the difference of the speed components of the drone and the unmanned vehicle. The larger the relative speed difference, the higher the conflict risk.

[0076] Step S504: Calculate the corresponding environmental correction factor according to the environmental data; Among them, the environmental data includes wind speed data, weather data, and road condition data. Based on the environmental data, the correction factor α enu can be calculated through a weighted average model or a linear correction model. For example: α enu = f(wind_speed, weather, road_condition); Among them, f(·) represents a function that converts environmental data into an environmental correction factor.

[0077] It can be understood that environmental factors may affect the movement trajectories and intersection positions of the drone and the unmanned vehicle. For example, when the wind speed reaches a strong wind state, it may cause the trajectory of the drone to deviate, increasing the risk of conflict. When the weather conditions are rainfall, haze, etc., due to the impact on visibility, it may change the reaction time of the unmanned vehicle. When the road conditions are wet and slippery, congested, etc., it may affect the braking and reaction capabilities of the unmanned vehicle.

[0078] Step S505: Correct the relative distance and relative speed difference based on the environmental correction factor to obtain the corrected relative distance and relative speed difference; Among them, the corrected relative distance and relative speed difference can be obtained through the environmental correction factor α enuTo adjust the relative speed and relative speed difference, the correction formula usually multiplies the environmental factor by the original relative distance and speed difference. In an adverse environment (such as high wind speed or bad weather conditions), the relative distance can be appropriately enlarged and the relative speed difference can be reduced, so as to be more in line with the actual risk assessment.

[0079] For example, assume that at an intersection, the calculated relative distance D is 5 meters, and the relative speed difference V′ is 10 m / s. The environmental correction factor is calculated as 1.2 (there may be high wind speed, bad weather, etc.). At this time, the corrected relative distance D′ is 6 meters, and the corrected relative speed difference V′ is 12 m / s.

[0080] Step S506, based on a preset risk assessment algorithm, calculate the conflict risk score according to the path intersection duration, environmental correction factor, corrected relative distance, and relative speed difference. In one embodiment of the present application, the calculation formula of the preset risk assessment algorithm is: Risk_score = w1×T + w2×(1 / D′) + w3×V′ + w4×α enu ; In the above formula, w1 is the intersection duration weight, T is the path intersection duration, D′ is the corrected relative distance, w2 is the relative distance weight, V′ is the corrected relative speed difference, w3 is the relative speed difference weight, α enu is the environmental correction factor, and w4 is the environmental weight.

[0081] Among them, when the relative distance is small, the probability of collision is high. Therefore, the reciprocal of the relative distance 1 / D′ is used to amplify the conflict risk in the case of a small distance.

[0082] Specifically, the weight coefficients of each factor can be adjusted according to different actual application scenarios and empirical data. The weight coefficients reflect the relative importance of each factor to the conflict risk. For example, for the weight w1 of the path intersection duration, when the intersection time is long, the conflict risk is high, so the weight of this item is large. For the weight w2 of the relative distance, the smaller the relative distance, the greater the possibility of collision, so the weight of this item is also large. For the weight w3 of the relative speed difference, the greater the relative speed difference, the greater the impact force of the conflict, so the weight of this item is high. For the environmental weight w4, when the influence of environmental factors on the conflict is more complex, the weight can be dynamically adjusted through actual environmental data.

[0083] It can be understood that the conflict risk score Risk_score is a comprehensive score, usually generating a quantitative value, which is used to measure the possibility and severity of the conflict. The range of the score depends on the weights of each factor and their specific values. Usually, the conflict risk score will be normalized or limited to a specific range, such as the range from 0 to 1.

[0084] Step S507: Based on a preset level mapping table, determine the corresponding conflict risk level according to the conflict risk score.

[0085] Among them, after the conflict risk score is calculated, it is necessary to map the conflict risk score to a specific risk level. For this purpose, a level mapping table can be pre-configured. Usually, the conflict risk score is divided into several different levels, and each level represents different conflict probabilities and severities.

[0086] For example, if the conflict risk score is between 0 and 0.3, it is a low risk, indicating that the probability of a potential conflict occurring is relatively small, and the risk can be reduced through simple monitoring or adjustment operations. If the conflict risk score is between 0.3 and 0.7, it is a medium risk, indicating that the probability of a potential conflict occurring is relatively high, and the system should take corresponding warning measures, such as changing the flight or driving route, adjusting the speed, etc. If the conflict risk score exceeds 0.7, it is a high risk, indicating that the possibility of a conflict is extremely high, and the system should immediately take emergency measures, such as immediately avoiding or adjusting the path, to avoid danger.

[0087] In the above embodiment, by integrating the path intersection information, the corrected relative distance, the relative speed difference, and the environmental data, the conflict risk score is calculated and converted into a specific risk level through a preset level mapping table. The system can accurately evaluate the potential conflict risk of the drone and the unmanned vehicle in the future intersection area. The process of risk assessment can dynamically adjust the weights and correction factors of various factors to ensure the accuracy and real-time nature of the conflict risk assessment, providing a scientific basis for subsequent path adjustment, collision avoidance strategies, and emergency responses, thereby significantly improving the safety of the unmanned system.

[0088] The embodiment of the present application also discloses a control system for a smart city unmanned system.

[0089] A control system for a smart city unmanned system, the control system includes: A status data receiving module, configured to receive the real-time status data of the drone and the unmanned vehicle collected by the sensor; An acquisition module, configured to acquire urban traffic flow data and environmental data; A drone trajectory prediction module, configured to predict the operation trajectory of the drone based on the real-time status data to obtain a drone prediction trajectory; An unmanned vehicle trajectory prediction module, configured to predict the operation trajectory of the unmanned vehicle based on the real-time status data and the urban traffic flow data to obtain an unmanned vehicle prediction trajectory; A path intersection analysis module, configured to perform path intersection judgment on the drone prediction trajectory and the unmanned vehicle prediction trajectory to obtain corresponding path intersection information; A conflict risk assessment module, which is used to determine potential conflict areas based on path intersection information, and conduct conflict risk assessment on the potential conflict areas by combining environmental data and path intersection information to obtain conflict risk levels; A conflict warning module, which is used to generate corresponding conflict warning information according to the conflict risk level; A path strategy adjustment module, which is used to generate corresponding path adjustment strategies based on the conflict warning information and send them to the unmanned system; among them, the unmanned system is used to adjust the paths of the unmanned aerial vehicle and the unmanned vehicle respectively according to the path adjustment strategies.

[0090] In the above embodiments, by integrating multiple modules, real-time monitoring and intelligent scheduling of the unmanned aerial vehicle and the unmanned vehicle are realized. By receiving real-time status data and environmental data collected by sensors, combining trajectory prediction, path intersection judgment and conflict risk assessment, potential conflict areas are effectively identified, and conflict warning information is generated according to the assessment results. By dynamically adjusting the operation paths of the unmanned aerial vehicle and the unmanned vehicle, it is ensured that they avoid potential conflict areas in a complex urban environment, improving the safety, intelligence and emergency response capabilities of the unmanned system.

[0091] As an implementation manner of the path intersection analysis module, it specifically includes: A trajectory path conversion unit, which is used to convert the predicted trajectory of the unmanned aerial vehicle and the predicted trajectory of the unmanned vehicle into the trajectory path of the unmanned aerial vehicle and the trajectory path of the unmanned vehicle respectively based on geometric modeling; An intersection calculation unit, which is used to calculate the intersection of the trajectory path of the unmanned aerial vehicle and the trajectory path of the unmanned vehicle to determine the potential intersection information of the unmanned aerial vehicle and the unmanned vehicle; the potential intersection information includes the potential intersection position and the potential intersection time; A time window acquisition unit, which is used to acquire the movement time windows of the unmanned aerial vehicle and the unmanned vehicle; A time comparison unit, which is used to compare the movement time windows of the unmanned aerial vehicle and the unmanned vehicle respectively according to the potential intersection information; A judgment unit, which is used to judge whether the potential intersection time is within the movement time windows of the unmanned aerial vehicle and the unmanned vehicle; if so, output an intersection valid result and determine the potential intersection as a valid intersection; A path intersection information generation unit, which is used to respond to the intersection valid result and obtain path intersection information according to the spatial coordinates and intersection time of the valid intersection.

[0092] The control system of a smart city unmanned system in an embodiment of the present application can implement any of the above control methods, and the specific working processes of each module in the control system can refer to the corresponding processes in the above method embodiments.

[0093] In several embodiments provided by the present application, it should be understood that the provided methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for example, the division of a certain module is only a logical function division, and there may be other division methods in actual implementation. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0094] The embodiments of the present application also disclose a computer device.

[0095] The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements a control method for an unmanned system in a smart city as described above.

[0096] The embodiments of the present application also disclose a computer-readable storage medium.

[0097] The computer-readable storage medium stores a computer program that can be loaded and executed by a processor to implement any one of the control methods for an unmanned system in a smart city as described above.

[0098] Among them, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device; the program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical fiber, RF, etc., or any suitable combination of the above.

[0099] It should be noted that in the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] The above are all preferred embodiments of the present application. The protection scope of the present application is not limited thereby. Any feature disclosed in this specification (including the abstract and drawings), unless specifically described, can be replaced by other equivalent or similar-purpose alternative features. That is, unless specifically described, each feature is only an example of a series of equivalent or similar features.

Claims

1. A control method for an unmanned system in a smart city, characterized in that, The control method includes: Receiving real-time status data of the drone and the unmanned vehicle collected by the sensor; Obtaining urban traffic flow data and environmental data; Predicting the operation trajectory of the drone according to the real-time status data to obtain a predicted drone trajectory; Predicting the operation trajectory of the unmanned vehicle according to the real-time status data and urban traffic flow data to obtain a predicted unmanned vehicle trajectory; Judging the path intersection of the predicted drone trajectory and the predicted unmanned vehicle trajectory to obtain corresponding path intersection information; Determining a potential conflict area according to the path intersection information, and combining the environmental data and the path intersection information to evaluate the conflict risk of the potential conflict area to obtain a conflict risk level; Generating corresponding conflict warning information according to the conflict risk level; Generating a corresponding path adjustment strategy based on the conflict warning information and sending it to the unmanned system; wherein, the unmanned system is used to adjust the paths of the drone and the unmanned vehicle respectively according to the path adjustment strategy.

2. The control method of an unmanned system for a smart city according to claim 1, wherein The step of predicting the operation trajectory of the drone according to the real-time status data to obtain a predicted drone trajectory includes: Analyzing the real-time status data to obtain the current position, current speed, heading angle, flight altitude information and acceleration of the drone; Predicting the future trajectory of the drone based on a linear motion model according to the real-time status data, and calculating a sequence of drone trajectory points within each preset time step; Updating the drone trajectory point sequence based on an acceleration correction model according to the current speed, acceleration and heading angle of the drone to obtain a predicted drone trajectory in the corrected future time period.

3. The control method of an unmanned system for a smart city according to claim 1, wherein, The step of predicting the operation trajectory of the unmanned vehicle according to the real-time status data and urban traffic flow data to obtain a predicted unmanned vehicle trajectory includes: Analyzing the real-time status data to obtain the current position, current speed, steering angle and acceleration information of the unmanned vehicle; Predicting the future trajectory of the unmanned vehicle based on a vehicle dynamics model according to the real-time status data, and calculating a sequence of unmanned vehicle trajectory points within each preset time step; Analyzing the urban traffic flow data to obtain traffic signal status, lane information and real-time road condition information; Correcting the unmanned vehicle trajectory point sequence according to the urban traffic flow data to obtain a predicted unmanned vehicle trajectory in the corrected future time period.

4. A control method for an unmanned system in a smart city according to any one of claims 1 to 3, characterized in that, The step of judging the path intersection of the predicted drone trajectory and the predicted unmanned vehicle trajectory to obtain corresponding path intersection information includes: Based on geometric modeling, converting the predicted drone trajectory and the predicted unmanned vehicle trajectory into a drone trajectory path and an unmanned vehicle trajectory path respectively; Performing an intersection calculation on the drone trajectory path and the unmanned vehicle trajectory path to determine potential intersection information of the drone and the unmanned vehicle; the potential intersection information includes a potential intersection position and a potential intersection time; Obtaining the motion time windows of the drone and the unmanned vehicle; Comparing the motion time windows of the drone and the unmanned vehicle respectively according to the potential intersection information; Judging whether the potential intersection time is within the motion time windows of the drone and the unmanned vehicle; If not, determine the potential intersection as an invalid intersection; If so, determine the potential intersection as a valid intersection; Obtain path intersection information based on the spatial coordinates and intersection time of the valid intersection.

5. The control method of an unmanned system for a smart city according to claim 4, characterized in that, The steps of determining a potential conflict area according to the path intersection information and performing a conflict risk assessment on the potential conflict area by combining the environmental data and the path intersection information to obtain a conflict risk level include: Calculate the relative distance of each valid intersection according to the path intersection information; Respectively determine whether the relative distance of each valid intersection is less than a preset safety distance threshold. If so, determine the area where the valid intersection is located as a potential conflict area; Obtain the path intersection duration, relative distance, and relative speed difference of the drone and the unmanned vehicle in the potential conflict area; Calculate the corresponding environmental correction factor according to the environmental data; Correct the relative distance and the relative speed difference based on the environmental correction factor to obtain the corrected relative distance and relative speed difference; Based on a preset risk assessment algorithm, calculate a conflict risk score according to the path intersection duration, environmental correction factor, corrected relative distance, and relative speed difference; Based on a preset level mapping table, determine the corresponding conflict risk level according to the conflict risk score.

6. The control method of an unmanned system for a smart city according to claim 5, wherein The calculation formula of the preset risk assessment algorithm is: Risk_score = w1×T + w2×(1 / D′) + w3×V′ + w4×α enu ; Among them, w1 is the weight of the intersection duration, T is the path intersection duration, D′ is the corrected relative distance, w2 is the relative distance weight, V′ is the corrected relative speed difference, w3 is the relative speed difference weight, α enu is the environmental correction factor, and w4 is the environmental weight.

7. A control system for an unmanned system in a smart city, characterized in that, The control system includes: A state data receiving module, configured to receive the real-time state data of the drone and the unmanned vehicle collected by sensors; An acquisition module, configured to acquire urban traffic flow data and environmental data; A drone trajectory prediction module, configured to predict the operation trajectory of the drone according to the real-time state data to obtain a drone prediction trajectory; An unmanned vehicle trajectory prediction module, configured to predict the operation trajectory of the unmanned vehicle according to the real-time state data and urban traffic flow data to obtain an unmanned vehicle prediction trajectory; A path intersection analysis module, configured to perform a path intersection judgment on the drone prediction trajectory and the unmanned vehicle prediction trajectory to obtain corresponding path intersection information; A conflict risk assessment module, configured to determine a potential conflict area according to the path intersection information, and perform a conflict risk assessment on the potential conflict area by combining the environmental data and the path intersection information to obtain a conflict risk level; A conflict warning module, configured to generate corresponding conflict warning information according to the conflict risk level; A path strategy adjustment module, configured to generate a corresponding path adjustment strategy based on the conflict warning information and send it to the unmanned system; wherein, the unmanned system is configured to perform path adjustment on the drone and the unmanned vehicle respectively according to the path adjustment strategy.

8. The control system of an unmanned system for a smart city according to claim 7, characterized in that, The path intersection analysis module includes: A trajectory path conversion unit, configured to convert the drone prediction trajectory and the unmanned vehicle prediction trajectory into a drone trajectory path and an unmanned vehicle trajectory path respectively based on geometric modeling; An intersection calculation unit, configured to perform an intersection calculation on the drone trajectory path and the unmanned vehicle trajectory path to determine the potential intersection information of the drone and the unmanned vehicle; the potential intersection information includes the potential intersection position and the potential intersection time; A time window acquisition unit for acquiring the motion time windows of the drone and the unmanned vehicle; A time comparison unit for comparing the motion time windows of the drone and the unmanned vehicle respectively according to the potential intersection information; A judgment unit for judging whether the potential intersection time is within the motion time windows of the drone and the unmanned vehicle; if so, outputting an intersection valid result and determining the potential intersection as a valid intersection; A path intersection information generation unit for obtaining path intersection information according to the spatial coordinates and intersection time of the valid intersection in response to the intersection valid result.

9. A computer device, characterized in that: It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method described in any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium, characterized in that: A computer program capable of being loaded and executed by a processor for the method described in any one of claims 1 to 6 is stored.

Images