Data processing method, data processing platform, storage medium and computer product

Abstract

The invention discloses a data processing method, a data processing platform, a storage medium and a computer product, and the method comprises the steps: obtaining flight data reported when a movable platform flies according to a target route, the target route being a route obtained by carrying out track segmentation decision making through a path planning model; obtaining sensing data obtained by detecting the movable platform by the communication and sensing integrated base station; and according to the flight data and the sensing data, working parameters of the communication and sensing integrated base station are calibrated.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a data processing method, a data processing platform, a storage medium and a computer product. Background Art

[0002] At present, when a base station is newly built or expanded, the calibration of the working parameters of the base station antenna is too dependent on manual work. Factors such as antenna workers' skills, proficiency, and measurement tools can cause large errors. The current manual calibration method is inefficient. Summary of the invention

[0003] The embodiments of the present application provide a data processing method, a data processing platform, a storage medium and a computer product to solve the problem of low calibration efficiency when the working parameters of the base station antenna are calibrated by manual calibration. The present application can improve the calibration efficiency and calibration accuracy.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] The present application provides a data processing method, the method comprising:

[0006] Acquiring flight data reported by the mobile platform when flying along a target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model;

[0007] Acquire the perception data obtained by the synaesthesia integrated base station detecting the mobile platform;

[0008] The working parameters of the synaesthesia integrated base station are calibrated according to the flight data and the perception data.

[0009] In the above solution, before obtaining the flight data reported by the movable platform when flying along the target route, the process includes:

[0010] Taking the optimal estimation accuracy of the working parameters calibrated under each designed route as the optimization goal and satisfying the flight area and flight distance as the constraints, the route design problem of the movable platform is established;

[0011] Converting the route design problem into a Markov decision process problem, wherein the Markov decision process problem takes the movable platform as an intelligent agent and the flight strategy of the movable platform as an action;

[0012] Solve the Markov decision process problem and find the optimal solution for the target route.

[0013] In the above solution, solving the Markov decision process problem and finding the optimal solution for the target route includes:

[0014] Solving the Markov decision process problem to obtain constructed candidate trajectories, wherein each of the candidate trajectories satisfies the requirement of being within the estimated coverage area of ​​the synaesthesia integrated base station and outside the no-fly zone of the mobile platform;

[0015] Using the trajectory in the candidate trajectory as the initial particle to complete the initialization of the particle group;

[0016] The particle swarm is iteratively updated using a particle swarm algorithm until an iteration termination condition is met, and the optimal solution obtained is the target route.

[0017] In the above solution, the iteration termination condition includes any of the following:

[0018] The number of iterations reaches the threshold;

[0019] The similarity between the optimal solutions obtained from two adjacent iterations is less than the similarity threshold.

[0020] In the above scheme, the working parameters include one or more of the following: the position, height and angle of the antenna of the synesthesia integrated base station; wherein the angle includes one or more of the following: pitch angle, roll angle, horizontal angle.

[0021] In the above solution, the movable platform and the synaesthesia integrated base station maintain clock synchronization.

[0022] The present application provides a data processing device, including:

[0023] An acquisition module, used to acquire flight data reported by the mobile platform when flying along a target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model;

[0024] The acquisition module is used to acquire the perception data obtained by the synaesthesia integrated base station detecting the mobile platform;

[0025] The processing module is used to calibrate the working parameters of the synaesthesia integrated base station according to the flight data and the perception data.

[0026] The embodiment of the present application also provides a data processing platform, including: a processor and a memory for storing a computer program that can be run on the processor; wherein:

[0027] The processor is used to execute the steps of any one of the above methods when running the computer program.

[0028] An embodiment of the present application further provides a storage medium on which a computer program is stored, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0029] An embodiment of the present application further provides a computer product, including a computer program, which implements the steps of any of the above methods when executed by a processor.

[0030] A data processing method, a data processing platform, a storage medium and a computer product provided by an embodiment of the present application include: obtaining flight data reported by a movable platform when flying according to a target route, wherein the target route is a route obtained by using a path planning model to make a trajectory segmentation decision; obtaining the perception data obtained by detecting the movable platform by a synesthesia integrated base station; and calibrating the working parameters of the synesthesia integrated base station according to the flight data and the perception data. In the calibration of working parameters, the present application controls the movable platform to fly according to the target route, and then combines the flight data reported by the movable platform and the perception data detected in real time by the synesthesia integrated base station to calculate the working parameters of the synesthesia integrated base station, and completes the calibration of the working parameters of the synesthesia integrated base station. Under the trajectory corresponding to the target route, the calibrated working parameters have the optimal estimation accuracy under statistical significance. Thus, the problem of low calibration efficiency when calibrating the working parameters of the base station antenna using the current manual calibration method is solved, and the calibration efficiency and calibration accuracy are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A schematic diagram of a data processing method according to an embodiment of the present application Figure 1 ;

[0032] Figure 2 A schematic diagram of a data processing method according to an embodiment of the present application Figure 2 ;

[0033] Figure 3 A schematic diagram of a data processing method according to an embodiment of the present application Figure 3 ;

[0034] Figure 4 A schematic diagram of the process flow of the hierarchical optimization algorithm of the embodiment of the present application;

[0035] Figure 5 This is a schematic diagram of the structure of a data processing device according to an embodiment of the present application;

[0036] Figure 6 This is a schematic diagram of the structure of the data processing platform of the embodiment of the present application. DETAILED DESCRIPTION

[0037] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0038] In the related art, when a base station is newly built or expanded, the calibration of the base station antenna position, height and angle information is too dependent on manual work. Factors such as antenna workers' skills, proficiency and measurement tools can cause large errors. Due to the huge amount of base station data, manual calibration is inefficient, costly and the calibration accuracy is usually insufficient.

[0039] Integrated Sensing and Communication (ISAC), as a key technology for 5G-A and 6G, realizes the collaborative work of radar perception and communication through shared waveforms and hardware, improves spectrum efficiency, meets perception needs, and promotes the development of wireless communication technology. The low-altitude economy has an increasing demand for low-altitude networks and supervision, and ISAC is a new technology that can meet the communication and perception needs of drones.

[0040] The accuracy of the engineering parameters of the integrated base station antenna is the basis for network optimization and business development. When the network is newly built or optimized, the engineering parameters of the integrated base station antenna need to be accurately calibrated. Compared with traditional communication base stations, ISAC base stations have higher accuracy requirements for operating parameters in order to achieve high-precision perception. Therefore, during the initialization phase of the base station, the actual physical installation parameters of the base station need to be accurately calibrated.

[0041] Compared with traditional communication base stations, communication and perception integrated base stations have higher requirements for the accuracy of their working parameters in order to achieve high-precision perception capabilities. In related technologies, the function of parameter calibration can be achieved based on the comparison between the return data and the detection data of the drone. However, in general trajectory design, there is a lack of clear performance indicators to evaluate the parameter estimation results, and it still relies solely on the experience of the staff.

[0042] The data processing platform of the present application can be implemented as any terminal with a screen display function, such as a laptop computer, a tablet computer, a desktop computer, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated messaging device, a portable gaming device), an intelligent robot, or the like, and can also be implemented as a server.

[0043] The present application embodiment provides a data processing method, which is applied to a data processing platform, such as Figure 1 As shown, the method includes:

[0044] Step 101: Acquire flight data reported by the mobile platform when flying along a target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model.

[0045] In actual application, the movable platform can be a UAV (Unmanned Aerial Vehicle), an unmanned vehicle (or a movable car), an unmanned ship, a mobile robot or other movable devices. A communication connection is established between the data processing platform (also called the solution platform) and the movable platform, and the data processing platform controls and transmits data to the movable platform. For ease of description, the following description takes the movable platform as an example of a UAV. The flight data reported by the UAV includes but is not limited to RTK real-time dynamic carrier phase difference technology data.

[0046] In practical application, the target route of this application is an important basis for the flight of the UAV. The target route is the route obtained by using the path planning model to make trajectory segmentation decisions. It is the optimal route in a statistical sense. Under the trajectory data corresponding to the optimal route, the calibrated working parameters have the optimal estimation accuracy in a statistical sense.

[0047] Step 102: Acquire the perception data obtained by the integrated interawareness base station detecting the movable platform.

[0048] In actual application, the integrated telepathic base station detects and senses the UAV, and the obtained perception data includes but is not limited to the detection trajectory.

[0049] In actual application, drones are used as detection targets to calibrate the working parameters of the synaesthesia integrated base station. When collecting detection perception data, the drones are controlled to be within the coverage area estimated when the synaesthesia integrated base station is installed, so as to further improve the accuracy of calibration.

[0050] Step 103: Calibrate the working parameters of the telepathic integrated base station according to the flight data and the perception data.

[0051] In actual application, the working parameters of the synesthesia integrated base station are calculated according to the flight data and the perception data, and then the working parameters of the synesthesia integrated base station are calibrated.

[0052] A data processing method provided by an embodiment of the present application includes: obtaining flight data reported by a movable platform when flying according to a target route, wherein the target route is a route obtained by using a path planning model to make a trajectory segmentation decision; obtaining the perception data obtained by the synesthesia integrated base station detecting the movable platform; and calibrating the working parameters of the synesthesia integrated base station according to the flight data and the perception data. In the calibration of working parameters, the present application controls the movable platform to fly according to the target route, and then combines the flight data reported by the movable platform and the perception data detected in real time by the synesthesia integrated base station to calculate the working parameters of the synesthesia integrated base station, and completes the calibration of the working parameters of the synesthesia integrated base station. Under the trajectory corresponding to the target route, the calibrated working parameters have the optimal estimation accuracy under statistical significance. Thus, the problem of low calibration efficiency when calibrating the working parameters of the base station antenna using the current manual calibration method is solved, and the calibration efficiency and calibration accuracy are improved.

[0053] In some embodiments, before step 101 obtains the flight data reported by the mobile platform when flying along the target route, the target route can be determined by Figure 2 The steps shown achieve:

[0054] Step 201: Taking the optimal estimation accuracy of the calibrated working parameters under each designed route as the optimization goal and satisfying the flight area and flight distance as the constraints, a route design problem for a movable platform is established.

[0055] In practical applications, the flight distance can be understood as the total trajectory length that the drone can support with its battery life. The flight area can be understood as the flight trajectory should not pass through any no-fly zones.

[0056] In actual application, the goal of this application is to allow the UAV to fly within a certain operating distance, compare the flight trajectory reported by the UAV with the detection trajectory, realize the calibration of the physical installation parameters of the integrated base station, and ensure that the UAV does not fly into the no-fly zone during the flight, nor does it leave the preset ISAC base station coverage too far.

[0057] Without loss of generality, the flight route of a drone is a combination of multiple segments of straight lines connected end to end. This application regards the drone as an intelligent agent and the flight strategy executed by the drone as an action, and the goal is how to design the route of each segment of the drone to achieve the optimal parameter estimation accuracy. Based on this, this application can describe the drone's trajectory design problem, so as to optimize the working parameters calibrated under each designed route with the optimal estimation accuracy as the optimization goal, and to meet the flight area and flight distance as constraints, and establish the route design problem of the movable platform.

[0058] It can be seen that this application takes into account the energy, obstacle avoidance and other constraint information during actual UAV flight, so that the constructed model can better adapt to the actual flight environment and also facilitate the subsequent trajectory design.

[0059] In a feasible scenario, in order to describe the trajectory design problem of a UAV, several quantities related to trajectory planning are first defined.

[0060] (1) State: The position state vector of the drone in the rectangular coordinate system can be defined as:

[0061] s=[x,y,z] T

[0062] Among them, x, y, and z represent the coordinates in three dimensions in the rectangular coordinate system.

[0063] (2) Behavior: The drone will have certain behaviors at the starting point of each segment. The behavior vector is defined as:

[0064] a=[θ,φ,r] T

[0065] Among them, φ and θ represent the azimuth and pitch angle respectively, and r represents the distance of the stage operation. Each action of the drone is independent of each other.

[0066] (3) Objective: In the calibration of physical working parameters of base stations, based on the rigid body rotation theory in the Cartesian system:

[0067]

[0068] Among them, Y is an m×4 matrix, representing the observation values ​​reported by the base station, where m represents the number of points, and its mth row represents the mth point on the trajectory in the rectangular world coordinate system.

[0069] Where X is an m×4 matrix, representing the RTK reference value reported by the drone in the homogeneous coordinate system. For the sake of convenience, it is assumed here that the time of the drone reference value and the reported value are matched. In actual use, the drone reference value and the detection value can be conveniently associated using technologies in related technologies, such as timestamp synchronization. The position reported by the drone and the detected drone position information reported by the integrated base station are both based on the world coordinate system.

[0070] in, is an m×4 matrix representing the observation error. During the calibration of the drone parameters, errors will occur in both the reported position and the detected position of the drone. This part of the error can be included in the above noise matrix.

[0071] Among them, A is a 4×4 matrix A represents the homogeneous four-dimensional rigid body rotation matrix, and its expression is:

[0072]

[0073] Where t = [Δx, Δy, Δz] T It represents the difference between the base station in the world coordinate system and the installation position preset by the construction; R represents the rotation matrix of the rigid body, and its expression is:

[0074]

[0075] The above problem is a typical least squares problem, which is solved by making the square error Minimize to estimate the model parameters A. Among them, represents the Frobenius norm of the matrix. Without loss of generality, the above process can be assumed to be an unbiased estimate. Then, an excellent estimation result should make the estimated error matrix A as accurate as possible, that is, it has the smallest variance in a statistical sense. The Cramer-Rao bound refers to the lower bound of the variance of the estimated value of the model parameter A, and the expression is:

[0076] Var(A)>=(X T X) -1 ΣΣ T (X T X) -1

[0077] where Var(A) is the variance co-matrix of the estimated values ​​of the model parameters A.

[0078] Among them, (X T X) -1 is the inverse matrix of the information matrix of the design matrix X.

[0079] Where Σ is the observation error The covariance matrix of .

[0080] In addition, the matrix condition number is also an important indicator for measuring trajectory. The condition number of a problem is a measure of the ease of numerical calculation of the quantity, that is, the well-posedness of the problem. A problem with a low condition number is called well-posed, while a problem with a high condition number is called ill-posed (or ill-posed). The condition number is defined as:

[0081] κ(X)=||X -1 ||·||X||

[0082] It is easy to prove that the Cramer-Rao bound and the condition number are equivalent under the assumption that the noise is uniform Gaussian white noise.

[0083] It is worth noting that in this application, whether the Cramer-Rao bound or the condition number is used as the objective function for evaluating the performance of parameter estimation, both are estimates with optimal performance in a statistical sense.

[0084] In actual use, due to the drone reporting rate, clutter points also exist, but the use of data clock synchronization based on drones and perception platforms, robust data registration and other technologies can greatly solve this problem. This application does not make specific restrictions on this.

[0085] In addition, during the test, it is necessary to consider that the amount of electricity carried by the drone is certain. In order to conduct the test efficiently, the total length needs to be limited. An objective function is introduced as follows:

[0086]

[0087] Among them, β represents the coefficient of control weight, r represents the total trajectory length, which is calculated as follows:

[0088]

[0089] Among them, r0 represents the flight distance of the drone model used when 80% of the power is consumed; s t and t+1 They represent the rectangular coordinate positions of the t-th and t+1-th drones when they take action control. It is assumed that in multiple trajectories, the hovering time of the drone when taking action can be ignored.

[0090] During the deployment of ISAC base stations, it is often perceived that there are certain no-fly zones / obstacle zones within their coverage. These zones may be mountains, tall buildings, or other artificially defined areas that do not have flight conditions. With the support of the 3D map of the flight management control platform, the no-fly zone can be represented as a set of fine cubes Ξ. The flight trajectory should not pass through any no-fly zone. This constraint is

[0091] d min >d0

[0092] Among them, d min represents the minimum distance from a point in the trajectory matrix X to the obstacle set Ξ; d0 represents the minimum safe distance for the UAV to fly.

[0093] Step 202: Convert the route design problem into a Markov decision process problem, wherein the Markov decision process problem takes the movable platform as the intelligent agent and the flight strategy of the movable platform as the action.

[0094] In practical application, the present application describes the route design problem using the Markov decision problem (MDP) in mathematics. A test trajectory can be decomposed into a set of T sub-straight line trajectories, and the decision process of each sub-straight line trajectory is relatively independent and ultimately affects each other. Then the optimization problem of the present application can be described as a Markov decision process problem.

[0095] Here, the transformed Markov decision process problem can be:

[0096]

[0097] Among them, d min,t represents the minimum distance from the segmented trajectory to the obstacle; Ω represents the expected coverage of ISAC, which is generally smaller than the actual coverage area of ​​ISAC to ensure the robustness of the algorithm; f() represents the function of converting the state in the spherical coordinate system into the Cartesian system, and its expression is:

[0098]

[0099] g() is a function that gets the value from s t to t+1 The function of the trajectory points generated during the state is expressed as:

[0100] g(s t ,s t+1 )=s t +(s t+1 -s t )([1:N t ] / N t )

[0101] in:

[0102] N t =round(||s t+1 -s t || / v)

[0103] Among them, v represents the average flight state of the drone during the test. In practice, it is generally between 3m / s and 8m / s. Through the above function, the endpoints of the straight sub-trajectory can be converted into trajectory points. It is worth noting that if the sampling rate is consistent during the process, the deviation of the sampling position will not affect the performance of the entire measurement trajectory when performing parameter estimation.

[0104] Step 203: Solve the Markov decision process problem and find the optimal solution for the target route.

[0105] In practical applications, after obtaining the converted Markov decision process problem, that is, completing the model construction, the Markov decision process problem is solved to find the optimal solution for the target route. At this time, the target route determined is the flight route of the UAV when calibrating the working parameters.

[0106] This application establishes a model for base station initialization trajectory planning, taking into account the constraint information during actual UAV flight. This application proposes an innovative base station initialization trajectory planning model that fully takes into account the constraint information during actual UAV flight. This model can not only better adapt to the actual flight environment, but also effectively improve the efficiency and accuracy of base station initialization, providing more reliable support for UAV flight.

[0107] In some embodiments, clock synchronization is maintained between the mobile platform and the telepathic base station.

[0108] In actual application, after planning the target route, the drone will fly manually or mark the target route. Before taking off, the drone and the integrated base station need to be synchronized. The clock synchronization can be completed by network synchronization or Global Positioning System (GPS) and Beidou timing.

[0109] In some embodiments, step 203 solves the Markov decision process problem to find the optimal solution for the target route, which can be done by Figure 3 The steps shown achieve:

[0110] Step 301: Solve the Markov decision process problem to obtain constructed candidate trajectories, wherein each of the candidate trajectories satisfies the requirement of being within the estimated coverage area of ​​the synaesthesia integrated base station and outside the no-fly zone of the movable platform.

[0111] In practical application, the above modeling has high nonlinearity, and the multi-segment parameter space is large, and the solution is complex. In order to further improve the solution efficiency, this application adopts a hierarchical optimization algorithm. The hierarchical optimization algorithm includes: executing a particle pre-initialization phase; and executing a particle swarm optimization phase; thereby finding the optimal solution for the target route.

[0112] In practical applications, the particle pre-initialization phase is performed: a test trajectory can be decomposed into a set of multiple sub-trajectories. For each sub-trajectory, it is necessary to meet the conditions of being in the ISAC estimated coverage area and not intersecting with the no-fly zone. In each iteration of the sub-trajectory, random sampling is performed in the drone's action space until the current sub-trajectory satisfies the constraints. Finally, when all sub-trajectories meet the constraints, a total trajectory is obtained.

[0113] Step 302: Use the trajectory in the candidate trajectory as the initial particle to complete the initialization of the particle swarm.

[0114] In practical applications, the candidate trajectories found above are used as initial particles, and a certain degree of randomness is added, and then the trajectories are optimized using heuristic algorithms, such as particle swarm algorithm, genetic algorithm, etc. Taking particle swarm algorithm as an example, the trajectory can be optimized.

[0115] Step 303: The particle swarm algorithm is used to iteratively update the particle swarm until the iteration termination condition is met, and the optimal solution obtained is the target route.

[0116] In practical applications, the particle swarm optimization (PSO) is a meta-heuristic algorithm that simulates the behavior of groups of organisms such as bird flocks or fish schools. In the particle swarm algorithm, each "particle" represents a solution, and the optimal solution is found by continuously updating the position and velocity of the particles.

[0117] In some embodiments, the iteration termination condition includes any of the following:

[0118] The number of iterations reaches the threshold;

[0119] The similarity between the optimal solutions obtained from two adjacent iterations is less than the similarity threshold.

[0120] A hierarchical deterministic optimization method designed in this application accelerates the convergence process. Through hierarchical design, the convergence speed and efficiency are effectively improved. Experiments have shown that this optimization method has achieved remarkable results in trajectory design and is more accurate than the trajectory designed by traditional experience. Compared with traditional high-dimensional search algorithms, it is better in convergence speed and solution effect. This method provides a reliable foundation for high-precision automated parameter calibration and future positioning of communication-sensing integrated base stations, and has important practical application significance.

[0121] In a feasible solution scenario, first, the initialization phase:

[0122] (1) Initialize the size of the particle swarm N and the position of each particle Q i and speed V i , and the individual optimal position P of each particle i And the overall optimal position G. The position of each particle is assigned by the result of the previous stage to complete the initialization.

[0123] (2) Initialize the velocity range and position range of the particles.

[0124] (3) Initialize the fitness value of the particle.

[0125] Second, the iterative update process:

[0126] (1) For each particle i:

[0127] Calculate the fitness value of the particle, that is, the objective function value in the overall optimization objective function.

[0128] If it is better than the individual's optimal fitness value, update P i =Q i .

[0129] If it is better than the overall optimal fitness value, update G = Q i .

[0130] Update the particle's velocity and position:

[0131] V i =w·V i +c1·rand(P i -Q i )+c2·rand(GQ i )

[0132] Q i =Q i +V i

[0133] Among them, w is the inertia weight, c1 and c2 are learning factors, and rand(·) is the random number generation function.

[0134] (2) Update the global optimal position G.

[0135] The termination conditions set for this application are:

[0136] When the maximum number of iterations is reached or the stopping condition is met, the final result is the trajectory designed by this proposal when the optimization algorithm reaches the maximum number of iterations or the optimal solution of two consecutive iterations has almost no change.

[0137] For example, see Figure 4 As shown, the hierarchical optimization algorithm is implemented by executing steps 401 to 405:

[0138] Step 401: candidate trajectory construction;

[0139] Here, step 401 can be implemented through steps 4011 to 4016;

[0140] Among them, step 4011: trajectory initialization;

[0141] Step 4012: Generate segmented trajectories;

[0142] Step 4013: Determine whether the condition is met, if yes, execute step 4014, otherwise execute step 4012;

[0143] Step 4014: add the current trajectory set, and the number of segmented trajectories in the trajectory set increases by 1;

[0144] Step 4015: Determine whether the number of segmented trajectories in the trajectory set is equal to T; if yes, execute step 4016; otherwise, execute step 4012;

[0145] Step 4016: adding candidate trajectory set;

[0146] Step 402: Determine whether the number of segmented trajectories in the candidate trajectory set is sufficient; if yes, execute step 403; otherwise, execute step 402;

[0147] Step 403: Initialize the particle swarm;

[0148] Step 404: Particle Swarm Optimization (PSO) iterative optimization;

[0149] Here, step 404 can be implemented through steps 4041 to 4045;

[0150] Among them, step 4041: update particle Q i ;

[0151] Step 4042: Calculate fitness;

[0152] Step 4043: If the fitness is better, update the particle optimal P i ;

[0153] Step 4044: Update the global optimal G;

[0154] Step 4045: All particles are updated;

[0155] Step 405: Determine whether the maximum number of iterations has been reached; if so, end; otherwise, execute step 404.

[0156] It should be noted that the solution obtained by this application may be a local optimal solution, and it can be run several times to ensure the adaptability of the trajectory designed by the algorithm. In actual use, as long as the designed trajectory reaches a certain target value, using a suboptimal trajectory can still achieve a better ISAC parameter calibration result.

[0157] In some embodiments, the operating parameters include one or more of the following: position, height and angle of the antenna of the telepathic base station; wherein the angle includes one or more of the following: pitch angle, roll angle, horizontal angle.

[0158] In actual application, the trajectory designed by this application, i.e., the target route, will be input into the flight control platform (e.g., the remote control device of the UAV), which will convert it into a platform-standard trajectory problem and issue a flight control command to the UAV.

[0159] During the flight of the UAV, the calibration UAV reports the flight data to the calibration and solution platform in real time through the communication module, including at least the associated timestamp, location, and other situation information. At the same time, the synaesthesia detection base station reports the detected UAV data to the calibration and solution platform. In this proposal, it is believed that the UAV, synaesthesia equipment, and solution platform can be calibrated with high progress through the calibration method in the relevant technology.

[0160] In practical applications, after obtaining the least squares solution of matrix A, the difference t between the base station's installation position in the world coordinate system and the preset installation position can be obtained from the expression of A, and the values ​​of the offset angles α, β, and γ of the actual value and design value of the antenna in the pitch angle, roll angle, and horizontal angle are obtained as follows:

[0161]

[0162] From the above content, it can be seen that the data processing method provided by this application realizes the optimal trajectory design in the parameter calibration of the synaesthesia integrated base station. By designing the statistically optimal test trajectory, it provides a basis and method for the high-precision calibration of base station parameters, reduces dependence on manpower, improves calibration accuracy and efficiency, reduces calibration costs, and fills the gap in intelligent and automated methods in the initialization process of the synaesthesia integrated base station. Its core idea and working method is to propose a drone trajectory design method with phased decision-making to obtain the optimal flight trajectory data in a statistical sense. The solution platform uses drone data and perception data to solve the matrix containing base station working parameter information.

[0163] The present application also provides a data processing device, such as Figure 5 As shown, the data processing device includes:

[0164] The acquisition module 501 is used to acquire the flight data reported by the mobile platform when flying along the target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model;

[0165] An acquisition module 501 is used to acquire the perception data obtained by the synaesthesia integrated base station detecting the movable platform;

[0166] The processing module 502 is used to calibrate the working parameters of the interawareness integrated base station according to the flight data and the perception data.

[0167] In some embodiments, the processing module 502 is used to establish a route design problem for a movable platform with the optimal estimation accuracy of the calibrated working parameters under each designed route as the optimization goal and to satisfy the flight area and flight distance as constraints; convert the route design problem into a Markov decision process problem, wherein the Markov decision process problem takes the movable platform as the intelligent agent and the flight strategy of the movable platform as the action; solve the Markov decision process problem to find the optimal solution for the target route.

[0168] In some embodiments, the processing module 502 is used to solve the Markov decision process problem to obtain constructed candidate trajectories, wherein each trajectory in the candidate trajectories satisfies the requirement of being within the estimated coverage area of ​​the synaesthesia integrated base station and outside the no-fly zone of the movable platform; the trajectories in the candidate trajectories are used as initial particles to initialize the particle swarm; the particle swarm is iteratively updated using the particle swarm algorithm until the iteration termination condition is met, and the optimal solution obtained is the target route.

[0169] In some embodiments, the iteration termination condition includes any of the following:

[0170] The number of iterations reaches the threshold;

[0171] The similarity between the optimal solutions obtained from two adjacent iterations is less than the similarity threshold.

[0172] In some embodiments, the operating parameters include one or more of the following: position, height and angle of the antenna of the telepathic base station; wherein the angle includes one or more of the following: pitch angle, roll angle, horizontal angle.

[0173] In some embodiments, clock synchronization is maintained between the mobile platform and the telepathic base station.

[0174] In order to implement the data processing method of the embodiment of the present application, the embodiment of the present application also provides a data processing platform, such as Figure 6 As shown, the data processing platform 600 includes: a communication interface 601 and a processor 602; wherein,

[0175] Communication interface 601;

[0176] The processor 602 is connected to the communication interface 601 and is used to execute the above-mentioned method for processing information services when running a computer program;

[0177] The memory 603 stores computer programs that can be executed on the processor 602 .

[0178] The communication interface 601 is used to: obtain the flight data reported by the mobile platform when it flies along the target route, wherein the target route is the route obtained by using the path planning model to make trajectory segmentation decisions; obtain the perception data obtained by the integrated interaesthesia base station detecting the mobile platform

[0179] The processor 602 is used to calibrate the working parameters of the interawareness integrated base station according to the flight data and the perception data.

[0180] In some embodiments, the processor 602 is used to: establish a route design problem for a movable platform with the optimal estimation accuracy of the calibrated working parameters under each designed route as the optimization goal and satisfy the flight area and flight distance as constraints; convert the route design problem into a Markov decision process problem, wherein the Markov decision process problem takes the movable platform as the intelligent agent and the flight strategy of the movable platform as the action; solve the Markov decision process problem to find the optimal solution for the target route.

[0181] In some embodiments, the processor 602 is used to: solve the Markov decision process problem to obtain constructed candidate trajectories, wherein each trajectory in the candidate trajectories satisfies the requirement of being within the estimated coverage area of ​​the synaesthesia integrated base station and outside the no-fly zone of the movable platform; use the trajectory in the candidate trajectories as the initial particle to complete the initialization of the particle swarm; use the particle swarm algorithm to iteratively update the particle swarm until the iteration termination condition is met, and the optimal solution obtained is the target route.

[0182] In some embodiments, the iteration termination condition includes any of the following:

[0183] The number of iterations reaches the threshold;

[0184] The similarity between the optimal solutions obtained from two adjacent iterations is less than the similarity threshold.

[0185] In some embodiments, the operating parameters include one or more of the following: position, height and angle of the antenna of the telepathic base station; wherein the angle includes one or more of the following: pitch angle, roll angle, horizontal angle.

[0186] In some embodiments, clock synchronization is maintained between the mobile platform and the telepathic base station.

[0187] The method disclosed in the above embodiment of the present application can be applied to the processor 602, or implemented by the processor 602. The processor 602 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 602. The above processor 602 may be a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 602 can implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 603, and the processor 602 reads the information in the memory 603 and completes the steps of the above method in combination with its hardware.

[0188] In an exemplary embodiment, the data processing platform 600 can be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned method.

[0189] It can be understood that the memory of the embodiment of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory (FlashMemory), a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Synchronous Static Random Access Memory (SSRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Sync Link Dynamic Random Access Memory (SLDRAM), and Direct Rambus Random Access Memory (DRRAM).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0190] In an exemplary embodiment, the present application also provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, a memory 603 storing a computer program, and the computer program can be executed by a processor 602 of a data processing platform 600 to complete the steps of the aforementioned method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0191] In an exemplary embodiment, the present application also provides a computer product, including a computer program, which can be executed by the processor 602 of the data processing platform 600 to complete the steps of the aforementioned method.

[0192] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0193] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0194] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Acquiring flight data reported by the mobile platform when flying along a target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model; Acquire the perception data obtained by the synaesthesia integrated base station detecting the mobile platform; The working parameters of the synaesthesia integrated base station are calibrated according to the flight data and the perception data.

2. The method according to claim 1, characterized in that Before obtaining the flight data reported by the movable platform when flying along the target route, the method includes: Taking the optimal estimation accuracy of the working parameters calibrated under each designed route as the optimization goal and satisfying the flight area and flight distance as the constraints, the route design problem of the movable platform is established; Converting the route design problem into a Markov decision process problem, wherein the Markov decision process problem takes the movable platform as an intelligent agent and the flight strategy of the movable platform as an action; Solve the Markov decision process problem and find the optimal solution for the target route.

3. The method according to claim 2, characterized in that The step of solving the Markov decision process problem and finding the optimal solution for the target route includes: Solving the Markov decision process problem to obtain constructed candidate trajectories, wherein each of the candidate trajectories satisfies the requirement of being within the estimated coverage area of ​​the synaesthesia integrated base station and outside the no-fly zone of the mobile platform; Using the trajectory in the candidate trajectory as the initial particle to complete the initialization of the particle group; The particle swarm is iteratively updated using a particle swarm algorithm until an iteration termination condition is met, and the optimal solution obtained is the target route.

4. The method according to claim 3, characterized in that The iteration termination condition includes any of the following: The number of iterations reaches the threshold; The similarity between the optimal solutions obtained from two adjacent iterations is less than the similarity threshold.

5. The method according to claim 1, characterized in that The working parameters include one or more of the following: the position, height and angle of the antenna of the synesthesia integrated base station; wherein the angle includes one or more of the following: pitch angle, roll angle, horizontal angle.

6. The method according to claim 1, characterized in that The movable platform and the synaesthesia integrated base station maintain clock synchronization.

7. A data processing device, characterized in that: include: An acquisition module, used to acquire flight data reported by the mobile platform when flying along a target route, wherein the target route is a route obtained by performing trajectory segmentation decision using a path planning model; The acquisition module is used to acquire the perception data obtained by the synaesthesia integrated base station detecting the mobile platform; The processing module is used to calibrate the working parameters of the synaesthesia integrated base station according to the flight data and the perception data.

8. A data processing platform, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory, and execute the steps of the data processing method as claimed in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the data processing method according to any one of claims 1 to 6.

10. A computer product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the data processing method according to any one of claims 1 to 6 are implemented.

Images