Trajectory data optimization method, device, terminal device and storage medium

Abstract

The present application is applicable to the field of computer application technology, and provides a method, device, terminal device and storage medium for optimizing trajectory data, the method comprising: receiving current driving data corresponding to a target object; predicting the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through a physical constraint model and a feasible domain mathematical model according to the current driving data; determining the corrected position data corresponding to the current driving data according to the data feasible domain, predicted position data and current driving data at the current moment; when the current moment is the data processing moment of the current data window, smoothing each corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object. Thus, the data is predicted and optimized through physical constraints and mathematical models, and the optimized data is smoothed, thereby improving the accuracy of trajectory data optimization.

Description

Technical Field

[0001] The present application belongs to the field of computer application technology, and in particular, relates to a trajectory data optimization method, device, terminal device and computer-readable storage medium. Background Art

[0002] With the development of intelligent transportation systems, the requirements for data quality are getting higher and higher. Therefore, the collection and processing of vehicle trajectory data is becoming more and more important. Due to the physical environment of the road or the low accuracy of the sensing equipment, the data perceived by the IoT devices has errors. Therefore, optimizing the perceived trajectory data is necessary to ensure high-quality data. Summary of the invention

[0003] The purpose of the present application is to provide a trajectory data optimization method, apparatus, terminal device and computer-readable storage medium, which can solve the problem in the related art that due to the physical environment of the road or the low accuracy of the sensing device, the data perceived by the Internet of Things device has errors, resulting in poor trajectory data quality and the need for optimization processing.

[0004] In a first aspect, an embodiment of the present application provides a method for optimizing trajectory data, including: receiving current driving data corresponding to a target object, wherein the current driving data is driving data of the target object collected at the current moment; predicting the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through a physical constraint model and a feasible domain mathematical model according to the current driving data, and storing the data feasible domain and predicted position data of the next receiving moment in a feasible domain cache; determining the corrected position data corresponding to the current driving data according to the data feasible domain, predicted position data and current driving data at the current moment, and storing the corrected position data in a current data window corresponding to the current moment, wherein the data feasible domain and predicted position data at the current moment are determined based on the driving data received at the previous receiving moment corresponding to the current moment and stored in the feasible domain cache; when the current moment is the data processing moment of the current data window, smoothing each corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object.

[0005] In a possible implementation of the first aspect, the current driving data includes at least one of current position data, current heading angle, current speed, current acceleration and current heading angle change rate; the physical constraint model includes kinematic constraints, acceleration constraints and environmental factor constraints; the feasible domain mathematical model includes a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation; and the data feasible domain includes a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain.

[0006] Optionally, in another possible implementation of the first aspect, predicting the data feasible domain and predicted position data at the next receiving time corresponding to the current time through the physical constraint model and the feasible domain mathematical model according to the current driving data includes:

[0007] According to the kinematic constraints, the current speed, the current heading angle change rate and the heading angle feasible domain model, the heading angle feasible domain corresponding to the current moment is predicted;

[0008] According to kinematic constraints, current position data, current speed, current acceleration and position feasible domain model, predict the position feasible domain of the next receiving time corresponding to the current time;

[0009] According to the acceleration constraint, environmental factor constraint, current speed and longitudinal speed constraint equation, the feasible domain of longitudinal speed at the next receiving time corresponding to the current time is predicted;

[0010] According to the current position data, current heading angle, current speed, current acceleration, current heading angle change rate and the prediction value calculation equation, the predicted position data of the next receiving time corresponding to the current time is predicted.

[0011] Optionally, in another possible implementation manner of the first aspect, determining the corrected position data corresponding to the current driving data according to the data feasible domain at the current moment, the predicted position data, and the current driving data includes:

[0012] According to the data feasible domain at the current moment and the current position data, determine whether the current position data is within the data feasible domain;

[0013] When the current position data is within the data feasible domain, the current position data is determined as the corrected position data;

[0014] When the current position data is not within the data feasible domain, the deviation value of the current position data is determined based on the predicted position data and the current position data, and the corrected position data is determined based on the deviation value.

[0015] Optionally, in another possible implementation manner of the first aspect, the step of determining the corrected position data according to the deviation value includes:

[0016] When the deviation value is less than or equal to the deviation threshold, the current position data is projected to the feasible domain of the position data at the current moment to determine the corrected position data;

[0017] When the deviation value is greater than the deviation threshold, the predicted position data at the current moment is determined as the corrected position data.

[0018] Optionally, in another possible implementation of the first aspect, the smoothing of each corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object includes:

[0019] According to each corrected position data in the current data window and each corrected position data in the previous adjacent data window corresponding to the current data window, each corrected position data in the current data window is smoothed to generate an optimized driving trajectory.

[0020] Optionally, in another possible implementation of the first aspect, before smoothing each corrected position data in the current data window according to each corrected position data in the current data window and each corrected position data in a previous adjacent data window corresponding to the current data window to generate an optimized driving trajectory, the method further includes:

[0021] If the amount of data in the data window is less than a preset amount threshold, interpolation processing is performed on each trajectory data correction value in the data window.

[0022] Optionally, in another possible implementation manner of the first aspect, the method further includes: predicting the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through the physical constraint model and the feasible domain mathematical model according to the current driving data, and storing the data feasible domain and predicted position data of the next receiving moment in the feasible domain cache.

[0023] Get the timestamp corresponding to the current driving data;

[0024] According to the timestamp, determine the delay time corresponding to the current driving data;

[0025] When the delay time is greater than a preset delay threshold, the current driving data is discarded.

[0026] Optionally, in another possible implementation manner of the first aspect, the data window is an adaptive window, and the window length of the data window can be dynamically adjusted.

[0027] In the second aspect, the present application also provides a trajectory data optimization device, including: a receiving module, used to receive current driving data corresponding to a target object, wherein the current driving data is the driving data of the target object collected at the current moment; a prediction module, used to predict the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through a physical constraint model and a feasible domain mathematical model according to the current driving data, and store the data feasible domain and predicted position data of the next receiving moment in a feasible domain cache; a first determination module, used to determine the corrected position data corresponding to the current driving data according to the data feasible domain, predicted position data and current driving data at the current moment, and store the corrected position data in a current data window corresponding to the current moment, wherein the data feasible domain and predicted position data at the current moment are determined according to the driving data received at the previous receiving moment corresponding to the current moment and stored in the feasible domain cache; a data processing module, used to smooth each corrected position data in the current data window when the current moment is the data processing moment of the current data window, so as to generate an optimized driving trajectory corresponding to the target object.

[0028] In a possible implementation of the second aspect, the current driving data includes at least one of current position data, current heading angle, current speed, current acceleration and current heading angle change rate; the physical constraint model includes kinematic constraints, acceleration constraints and environmental factor constraints; the feasible domain mathematical model includes a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation; and the data feasible domain includes a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain.

[0029] Optionally, in another possible implementation manner of the second aspect, the prediction module includes:

[0030] A first prediction unit is used to predict the feasible domain of the heading angle at the next receiving moment corresponding to the current moment according to the kinematic constraint, the current speed, the current heading angle change rate and the heading angle feasible domain model;

[0031] A second prediction unit is used to predict the position feasible domain of the next receiving time corresponding to the current time according to the kinematic constraints, the current position data, the current speed, the current acceleration and the position feasible domain model;

[0032] A third prediction unit is used to predict the feasible domain of the longitudinal speed at the next receiving time corresponding to the current time according to the acceleration constraint, the environmental factor constraint, the current speed and the longitudinal speed constraint equation;

[0033] The fourth prediction unit is used to predict the predicted position data of the next receiving time corresponding to the current time according to the current position data, the current heading angle, the current speed, the current acceleration, the current heading angle change rate and the prediction value calculation equation.

[0034] Optionally, in another possible implementation manner of the second aspect, the first determining module includes:

[0035] A judging unit, used to judge whether the current position data is within the data feasible domain according to the data feasible domain at the current moment and the current position data;

[0036] A first determining unit, configured to determine the current position data as the corrected position data when the current position data is within the data feasible domain;

[0037] The second determination unit is used to determine the deviation value of the current position data according to the predicted position data and the current position data when the current position data is not within the data feasible domain, and to determine the corrected position data according to the deviation value.

[0038] Optionally, in another possible implementation manner of the second aspect, the second determining unit is specifically configured to:

[0039] When the deviation value is less than or equal to the deviation threshold, the current position data is projected to the feasible domain of the position data at the current moment to determine the corrected position data;

[0040] When the deviation value is greater than the deviation threshold, the predicted position data at the current moment is determined as the corrected position data.

[0041] Optionally, in another possible implementation of the second aspect, the data processing module includes:

[0042] The data processing unit is used to smooth each corrected position data in the current data window according to each corrected position data in the current data window and each corrected position data in the previous adjacent data window corresponding to the current data window, so as to generate an optimized driving trajectory.

[0043] Optionally, in another possible implementation of the second aspect, the trajectory data optimization device further includes:

[0044] The interpolation module is used to perform interpolation processing on each trajectory data correction value in the data window if the amount of data in the data window is less than a preset amount threshold.

[0045] Optionally, in another possible implementation of the second aspect, the trajectory data optimization device further includes:

[0046] An acquisition module is used to obtain the timestamp corresponding to the current driving data;

[0047] A second determination module, used to determine the delay time corresponding to the current driving data according to the timestamp;

[0048] The discarding module is used to discard the current driving data when the delay time is greater than a preset delay threshold.

[0049] Optionally, in another possible implementation manner of the second aspect, the data window is an adaptive window, and the window length of the data window can be dynamically adjusted.

[0050] In a third aspect, the present application further provides a terminal device. The terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a method for implementing any one of the implementation modes of the first aspect is implemented.

[0051] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method of any one of the implementation modes of the first aspect is implemented.

[0052] In a fifth aspect, the present application further provides a computer program product, which, when executed on an electronic device, enables the electronic device to execute any one of the methods of the first aspect.

[0053] Compared with the prior art, the embodiments of the present application have the following beneficial effects: determining the data feasible domain and predicted position data through physical constraints and mathematical models, verifying and optimizing the received data according to the data feasible domain and preset position data, and smoothing the optimized data, thereby improving the optimization accuracy of trajectory data. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 It is a flowchart of a method for optimizing trajectory data provided by an embodiment of the present application;

[0056] Figure 2 is a flow chart of a method for optimizing trajectory data provided by another embodiment of the present application;

[0057] Figure 3 is a schematic diagram of the structure of a trajectory data optimization device provided in an embodiment of the present application;

[0058] Figure 4 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0060] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0061] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0062] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0063] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0064] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the sentences "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0065] The trajectory data optimization method, apparatus, terminal device, storage medium and computer program provided by the present application are described in detail below with reference to the accompanying drawings.

[0066] Figure 1 A schematic flow chart of a trajectory data optimization method provided in an embodiment of the present application is shown.

[0067] Step 101: Receive current driving data corresponding to a target object.

[0068] The current driving data may be driving data of the target object collected at the current moment.

[0069] It should be noted that the trajectory data optimization method of the embodiment of the present application can be executed by the trajectory data optimization device of the embodiment of the present application. The trajectory data optimization device of the embodiment of the present application can be configured in any terminal device to execute the trajectory data optimization method of the embodiment of the present application.

[0070] In one possible implementation, the target object may be a vehicle in an underground road that requires trajectory data optimization, and the current driving data may be driving data collected at the current moment. The driving data may be collected and uploaded by an IoT device carried by the target object, and may include the location, speed, etc. of the target object.

[0071] In one possible implementation, the collection frequency of driving data collected by IoT devices, the delay time range of a single data packet, the rendering lag time range, and the data window duration range can be set, and the window duration of the data window can be dynamically adjusted according to actual scenario requirements to ensure the stability and accuracy of data processing.

[0072] For example, the collection frequency of driving data can be 10Hz, and the delay time range of a single data packet is Can be 50ms to 100ms, rendering delay time range and data window length range It can be from 0.5s to 1s, and the default value can be 0.5s.

[0073] As a possible implementation of the present application, the received current driving data can be stored in real time in the real-time data cache layer, and the amount of data in each data window can be determined according to the window length of the data window, for example, the amount of data . A circular queue can be used as the underlying data structure in the real-time data cache layer. In this way, by cyclically using a fixed-size storage space, frequent memory allocation and release operations can be avoided, thereby improving memory utilization; supporting efficient first-in-first-out operations, which is more suitable for processing time series data streams; automatically overwriting the oldest data when the queue is full to ensure that the system always maintains the latest real-time data; supporting fast random access operations to facilitate data retrieval and processing.

[0074] Step 102, based on the current driving data, through the physical constraint model and the feasible domain mathematical model, predict the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment, and store the data feasible domain and predicted position data of the next receiving moment in the feasible domain cache.

[0075] In a possible implementation, the physical constraint model may be a feasibility constraint determined based on real data evaluation, and may be a constraint on the speed of the target object, a constraint on the heading angle, and a constraint on the road friction coefficient determined based on environmental factors. The feasible domain mathematical model may include mathematical calculation formulas for the feasible domain of various data, etc. The next receiving moment corresponding to the current moment may be the moment corresponding to a receiving time interval after the current moment, and the predicted position data refers to the position where the target object may appear. Based on the driving data at the current moment, the data feasible domain and predicted position data at the next receiving moment may be predicted through physical feasibility constraints and mathematical calculation formulas for the feasible domain of various data, and the predicted data feasible domain and predicted position data may be stored in the feasible domain cache for verification and optimization of the driving data received at the next receiving moment.

[0076] Furthermore, the physical constraint model may include kinematic constraints, acceleration constraints and environmental factor constraints, and the feasible domain mathematical model may include calculation equations for multiple heading angle feasible domains, position feasible domains, speed feasible domains, etc., so that the noise and error of the IoT device perception data can be removed according to various constraints and feasible domain calculation equations, and the robustness and accuracy of trajectory data optimization can be improved. Through the closed-form mathematical model, the data calculation efficiency is guaranteed. That is, in a possible implementation method of the embodiment of the present application, the above-mentioned current driving data may include at least one of the current position data, the current heading angle, the current speed, the current acceleration and the current heading angle change rate, the above-mentioned physical constraint model may include kinematic constraints, acceleration constraints and environmental factor constraints, the above-mentioned feasible domain mathematical model may include a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation, and the above-mentioned data feasible domain may include a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain.

[0077] In one possible implementation, at least one of the current position data, current heading angle, current speed, current acceleration and current heading angle change rate of the target object can be received. Accordingly, the data feasible domain can include the heading angle feasible domain, the position feasible domain and the longitudinal speed feasible domain.

[0078] As a possible implementation method, the physical constraint model can include kinematic constraints, acceleration constraints and environmental constraints. Among them, kinematic constraints include constraints on the heading angle, heading angle change rate and driving speed of the target object; acceleration constraints include constraints on the longitudinal acceleration of the target object, and the acceleration constraints can be dynamically adjusted according to the road friction coefficient and weather influence coefficient; environmental constraints can be quantified by the road friction coefficient and weather influence coefficient, and different coefficients can be set for different road conditions and weather conditions, so as to fully consider the impact of the actual driving environment on vehicle performance and improve the environmental adaptability of the trajectory data optimization method.

[0079] For example, the heading angle The constraints can be:

[0080] .

[0081] Assume that the current time is t At time , the heading angle change rate ( t ) can be expressed as:

[0082] .

[0083] Travel speed v The constraints can be expressed as:

[0084] .

[0085] The longitudinal acceleration constraint can be expressed as:

[0086] , .

[0087] Road friction coefficient for different road conditions Can be set to:

[0088] .

[0089] Weather influence coefficients for different weather conditions Can be set to:

[0090] .

[0091] As a possible implementation of the present application, the data feasible domain and predicted position data can be saved in the feasible domain cache, and the timestamp of the current moment can be saved for storing and indexing the results. The position feasible domain can save four boundary points. , , , ,Since the receiving time interval is small, the feasible region of the ,position is small, so it can be simplified by using a trapezoidal range to ,save computing and storage resources.

[0092] Furthermore, the data feasible domain and predicted position data can be determined according to the feasible domain mathematical calculation formula in the above physical constraint model and feasible domain mathematical model, thereby further reducing the error and noise impact of the trajectory data and further improving the accuracy of the trajectory data. That is, in a possible implementation of the embodiment of the present application, the above step 102 may include:

[0093] According to the kinematic constraints, the current speed, the current heading angle change rate and the heading angle feasible domain model, the heading angle feasible domain corresponding to the current moment is predicted;

[0094] According to kinematic constraints, current position data, current speed, current acceleration and position feasible domain model, predict the position feasible domain of the next receiving time corresponding to the current time;

[0095] According to the acceleration constraint, environmental factor constraint, current speed and longitudinal speed constraint equation, the feasible domain of longitudinal speed at the next receiving time corresponding to the current time is predicted;

[0096] According to the current position data, current heading angle, current speed, current acceleration, current heading angle change rate and the prediction value calculation equation, the predicted position data of the next receiving time corresponding to the current time is predicted.

[0097] As a possible implementation of this application, the current time is t The next receiving time corresponding to the current time is t t ,in t The time difference between the next reception time and the current time, that is, the time interval. The current driving data includes the current location data x ( t )and y ( t ), current heading angle ( t ), current speed v ( t ), current acceleration a ( t ) and the current heading angle change rate ( t ), based on the current driving data, the feasible domain of heading angle, position, longitudinal speed, lateral acceleration and predicted position data at the next receiving moment can be predicted.

[0098] In a possible implementation, the heading angle and heading angle change rate constraints in the kinematic constraints, the current speed v ( t ) and the current heading angle change rate ( t ), predict the heading angle at the next receiving moment through the heading angle feasible domain model ( t t ), the feasible domain of heading angle can be specifically expressed as:

[0099] ,

[0100] ,

[0101] ,

[0102] ,

[0103] .

[0104] in, L is the vehicle wheelbase of the target object.

[0105] In a possible implementation, after predicting the feasible domain of the heading angle based on the kinematic constraints, the feasible domain of the heading angle and the current position data can be used to predict the feasible domain of the heading angle. x ( t)and y ( t ), current speed v ( t ) and current acceleration a ( t ), predict the location of the next receiving time corresponding to the current time through the location feasible domain model x ( t t )and y ( t t ), for any , location feasible domain x ( t t )and y ( t t ) can be expressed as:

[0106] ,

[0107] .

[0108] in, and is the position uncertainty range. The common IoT device perception error is 0.5m. The final position feasible domain is a fan-shaped area plus a 0.5-meter buffer zone, and its range is determined by the heading angle feasible domain, current speed, current acceleration and time interval.

[0109] In a possible implementation, the acceleration constraint, the environmental factor constraint and the current speed can be used to v ( t ), through the longitudinal velocity constraint equation, predict the longitudinal velocity at the next receiving time corresponding to the current time v ( t t ), the feasible domain of longitudinal velocity can be specifically expressed as:

[0110] .

[0111] in, and It can be determined according to the acceleration constraint and environmental factor constraint, and can be expressed as:

[0112] ,

[0113] .

[0114] In a possible implementation, the current location data may be used to x ( t )and y ( t ), current heading angle ( t ), current speed v ( t ), current acceleration a ( t ) and the current heading angle change rate ( t ), predict the predicted position data of the next receiving time corresponding to the current time through the prediction value calculation equation ( t ), which can be specifically expressed as:

[0115] .

[0116] in:

[0117] ,

[0118] ,

[0119] .

[0120] Furthermore, before predicting the feasible domain of data and predicting the position data, the timestamp of the received current driving data can be checked to determine whether the current driving data needs to be discarded, thereby further improving the accuracy of the data and thus improving the accuracy of trajectory data optimization. That is, in a possible implementation of the embodiment of the present application, before the above step 102, it can also include:

[0121] Get the timestamp corresponding to the current driving data;

[0122] According to the timestamp, determine the delay time corresponding to the current driving data;

[0123] When the delay time is greater than a preset delay threshold, the current driving data is discarded.

[0124] As a possible implementation method, the real-time data cache layer can be equipped with a timestamp alignment mechanism, which can obtain the timestamp corresponding to the current driving data, that is, the receiving time of the current driving data, and determine the delay time corresponding to the current driving data based on the timestamp and the perception time of the current driving data. If the delay time is greater than the preset delay threshold, the current driving data is discarded and wait for the next driving data to be received.

[0125] Step 103, determining the corrected position data corresponding to the current driving data according to the data feasible domain at the current moment, the predicted position data and the current driving data, and storing the corrected position data in the current data window corresponding to the current moment.

[0126] The data feasible domain and predicted position data at the current moment may be determined based on the driving data received at the last receiving moment corresponding to the current moment and stored in the feasible domain cache.

[0127] As a possible implementation method, the data feasible domain and predicted position data at the current moment can be extracted from the feasible domain cache to determine whether the current driving data is within the current data feasible domain, and based on the predicted position data, determine the corrected position data after correcting the current driving data, and store the corrected position data in the current data window corresponding to the current moment.

[0128] Furthermore, the data window can adaptively extend the window duration, thereby improving the stability and accuracy of the driving data. That is, in a possible implementation of the embodiment of the present application, the data window is an adaptive window, and the window duration of the data window can be dynamically adjusted.

[0129] In a possible implementation, the window duration of the data window can be dynamically adjusted according to the traffic volume, system load, network delay, etc., and the above factors are positively correlated with the window duration. For example, when the traffic volume is dense and the processing time is prolonged, the data window duration can be automatically extended from 0.5s to 1s.

[0130] Furthermore, if the current position data is within the data feasible domain, it means that the error of the current position data is small and can be used directly. Otherwise, the current driving data needs to be processed to further improve the data quality and the accuracy of trajectory data optimization. That is, in a possible implementation of the embodiment of the present application, the above step 103 may include:

[0131] According to the data feasible domain at the current moment and the current position data, determine whether the current position data is within the data feasible domain;

[0132] When the current position data is within the data feasible domain, the current position data is determined as the corrected position data;

[0133] When the current position data is not within the data feasible domain, the deviation value of the current position data is determined based on the predicted position data and the current position data, and the corrected position data is determined based on the deviation value.

[0134] As a possible implementation method, the four feasible domain vertices of the location feasible domain corresponding to the current moment can be extracted from the feasible domain cache , , , , to form a trapezoidal feasible domain range and determine the current position data Is it in the feasible region of the trapezoid? , compute the vector cross product:

[0135] .

[0136] in, Indicates the trapezoidal i Vertices.

[0137] Determine the current location data Is it in the trapezoidal feasible region?

[0138] .

[0139] Among them, 1 means that the current position data is within the data feasible domain, and 0 means that the current position data is not within the data feasible domain.

[0140] As a possible implementation form, when the current position data is within the data feasible domain, the current position data can be determined as the corrected position data. When the current position data is not within the data feasible domain, the deviation value of the current position data can be determined based on the predicted position data and the current position data, and the corrected position data can be determined based on the deviation value, wherein the deviation value can be obtained by calculating the normalized deviation degree between the predicted position data and the current position data. Specifically, the Euclidean distance between the predicted position data and the current position data can be calculated:

[0141] .

[0142] in, is the current location data, To predict location data, is the location distance threshold, which can be based on the device perception error It is found that when the device perception error is 0.5m, It can be set to twice the device perception error, that is m.

[0143] Furthermore, different data processing strategies may be adopted according to different deviation values ​​corresponding to the current position data, thereby further improving the accuracy of trajectory optimization. That is, in a possible implementation of the embodiment of the present application, the above-mentioned determination of the corrected position data according to the deviation value may include:

[0144] When the deviation value is less than or equal to the deviation threshold, the current position data is projected to the feasible domain of the position data at the current moment to determine the corrected position data;

[0145] When the deviation value is greater than the deviation threshold, the predicted position data at the current moment is determined as the corrected position data.

[0146] In a possible implementation, when the deviation value is greater than the deviation threshold, the predicted position data at the current moment can be determined as the corrected position data. At this time, the current heading angle and current speed in the current driving data can be replaced by the heading angle prediction value and the speed prediction value. When the deviation value is less than or equal to the deviation threshold, the current position data can be projected onto the boundary of the feasible domain of the position data at the nearest moment, and the projection point can be determined as the corrected position data. Among them, based on the four vertices of the trapezoidal feasible domain , , , , projection point ( t ) can be expressed as:

[0147] ,

[0148] .

[0149] in, ( t ) is the current location data, represents the i-th side of the trapezoid, Represents a line segment connecting adjacent vertices.

[0150] In a possible implementation, the corrected position data may be expressed as:

[0151] .

[0152] in, ( t ) is the corrected position data, is the deviation threshold, which can be set to 1.5.

[0153] In this way, it is possible to effectively distinguish between slight deviations caused by random errors (deviation values ​​less than or equal to the deviation threshold) and severe deviations caused by systematic errors (deviation values ​​greater than the deviation threshold). For slight deviations, corrections are made by projecting to the nearest trapezoidal boundary; for severe deviations, predicted values ​​are used as replacements, thereby ensuring the reliability and stability of the data. While maintaining data continuity, data jumps caused by perception errors can be effectively avoided.

[0154] Step 104 , when the current moment is the data processing moment of the current data window, smoothing is performed on each corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object.

[0155] In a possible implementation, when the current moment is the last driving data collection moment in the current data window, or when the amount of data in the current data window reaches a preset quantity threshold, the current moment may be the data processing moment of the current data window, and each corrected position data in the current data window may be smoothed, and the preset quantity threshold may be determined according to the window duration of the data window. A third-order Bezier curve may be used to perform curve fitting on each corrected position data, and the corrected position data may be optimized considering the continuity of the data, so as to generate an optimized driving trajectory corresponding to the target object according to the optimized corrected position data.

[0156] Furthermore, the data in the current data window may be processed according to the data in the current data window and the data in the adjacent data windows, thereby improving the overall continuity and smoothness of the driving trajectory, avoiding sudden changes or sharp corners, and ensuring a good fit to the original data. That is, in a possible implementation of the embodiment of the present application, the above step 104 may include:

[0157] According to each corrected position data in the current data window and each corrected position data in the previous adjacent data window corresponding to the current data window, each corrected position data in the current data window is smoothed to generate an optimized driving trajectory.

[0158] As a possible implementation of the present application, a third-order Bezier curve may be used for curve fitting for the data in the current data window, thereby ensuring the optimization speed, robustness and smoothness and avoiding overfitting. The details are as follows:

[0159] When the window length of the data window =0.5s, the data length in the data window can be , assuming that the 5 corrected position data are , , , , , third-order Bezier curve B ( t ) can be expressed as:

[0160] .

[0161] Among them, the control point is: window starting point , window end point , intermediate control point , .

[0162] The position is adjusted by the optimization algorithm to minimize the fitting error. The fitting optimization goal is:

[0163] .

[0164] In a possible implementation, in order to avoid jitter in trajectory data rendering on the digital twin end, it is necessary to ensure the overall smoothness and accuracy of the driving trajectory. Therefore, the corrected position data in the current data window can be smoothed according to the corrected position data in the previous adjacent data window corresponding to the current data window. The curve of the adjacent data window can be made to meet Continuous. Specifically. For adjacent third-order Bezier curves ( t ) can use the previous curve ( t ) and its tangent information to satisfy the following continuity conditions:

[0165] Endpoint positions are continuous ( ):

[0166] .

[0167] Tangent direction continuity ( ):

[0168] ,

[0169] .

[0170] In order to achieve the above continuity requirements, when optimizing the control points of adjacent curve segments, Continuity constraints are added to the optimization objective:

[0171] .

[0172] Among them, the first term is the fitting error term, and the second term is the continuity constraint term. is the weight coefficient, , the weight coefficient can be adjusted according to the trajectory data smoothing target and fitting accuracy target. Through iterative optimization, an optimized smooth driving trajectory that satisfies position continuity and tangential continuity can be obtained.

[0173] Furthermore, the amount of data in the data window may be less than a preset amount threshold, so the data in the data window may be interpolated first, thereby improving the accuracy of driving trajectory optimization. That is, in a possible implementation of the embodiment of the present application, before the above step 104, it may also include:

[0174] If the amount of data in the data window is less than a preset amount threshold, interpolation processing is performed on each trajectory data correction value in the data window.

[0175] In a possible implementation, the preset quantity threshold is determined according to the window length. When the current moment is the data processing moment of the current data window, but the amount of data in the data window is less than the preset quantity threshold, interpolation processing can be performed on each trajectory data correction value in the data window.

[0176] For example, when the window length =0.5s, the preset quantity threshold can be , assuming that the current moment is the data processing moment of the current data window, but there are only 3 data in the data window, it is necessary to interpolate the trajectory data correction value in the data window to make the number of data reach 5.

[0177] As a possible implementation of the present application, the optimization method of trajectory data provided in the present application can be as follows: Figure 2 The process shown is as follows: first, the current driving data is received, and a timestamp check is performed on the current driving data. Data with excessive delay is discarded, and the current driving data with normal delay is used. The data feasible domain and predicted position data of the next moment are calculated through physical constraints and feasible domain mathematical models, and stored in the feasible domain cache. The data feasible domain of the current moment is queried from the feasible domain cache. Then, it is determined whether the current driving data is within the data feasible domain. If so, the original value is maintained. If not, the deviation of the current driving data is calculated. When the deviation is less than or equal to the deviation threshold, the current driving data is projected to the data feasible domain. When the deviation is greater than the deviation threshold, the pre-position data is used to replace the original driving data. After data processing, it is stored in an adaptive data window to determine whether the data in the data window reaches the quantity threshold. If so, a third-order Bezier curve fitting is performed. If not, interpolation processing is performed. Finally, the data curve is smoothed to generate an optimized driving trajectory.

[0178] The optimization method of trajectory data provided by the embodiment of the present application determines the data feasible domain and predicted position data through physical constraints and mathematical models, verifies and optimizes the received data according to the data feasible domain and preset position data, and smoothes the optimized data, thereby improving the accuracy of trajectory data optimization. In the physical constraints, environmental factor constraints and kinematic constraints are added to increase the environmental adaptability and robustness of the trajectory data optimization method; the closed-form mathematical model ensures the efficiency of trajectory data optimization; and for the current driving data, timestamp verification is performed, and data with excessive delay is discarded. When verifying the data feasible domain, the deviation is calculated for the data that is not in the data feasible domain, and different data optimization strategies are adopted according to the deviation. The data quantity in the adaptive data window is judged, and the data is smoothed according to the data in the window and the data in the adjacent window, respectively, which ensures the rationality and continuity of the data while further improving the real-time, accuracy and stability of trajectory data optimization.

[0179] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0180] Corresponding to the optimization method of trajectory data in the above embodiment, Figure 3 A structural block diagram of a trajectory data optimization device provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0181] Reference Figure 3 , the device 30 comprises:

[0182] The receiving module 31 is used to receive the current driving data corresponding to the target object, wherein the current driving data is the driving data of the target object collected at the current moment;

[0183] The prediction module 32 is used to predict the data feasible domain and predicted position data of the next receiving time corresponding to the current time according to the current driving data through the physical constraint model and the feasible domain mathematical model, and store the data feasible domain and predicted position data of the next receiving time in the feasible domain cache;

[0184] A first determination module 33 is used to determine the corrected position data corresponding to the current driving data according to the data feasible domain at the current moment, the predicted position data and the current driving data, and store the corrected position data in the current data window corresponding to the current moment, wherein the data feasible domain at the current moment and the predicted position data are determined according to the driving data received at the last receiving moment corresponding to the current moment and stored in the feasible domain cache;

[0185] The data processing module 34 is used to perform smoothing processing on each corrected position data in the current data window when the current moment is the data processing moment of the current data window, so as to generate an optimized driving trajectory corresponding to the target object.

[0186] In actual use, the trajectory data optimization device provided in the embodiment of the present application can be configured in any terminal device to execute the above-mentioned trajectory data optimization method.

[0187] The trajectory data optimization device provided in the embodiment of the present application determines the data feasible domain and predicted position data through physical constraints and mathematical models, verifies and optimizes the received data according to the data feasible domain and preset position data, and smoothes the optimized data, thereby improving the accuracy of trajectory data optimization.

[0188] In a possible implementation form of the present application, the above-mentioned current driving data includes at least one of the current position data, the current heading angle, the current speed, the current acceleration and the current heading angle change rate, the above-mentioned physical constraint model includes kinematic constraints, acceleration constraints and environmental factor constraints, the above-mentioned feasible domain mathematical model includes a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation, and the above-mentioned data feasible domain includes a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain.

[0189] Furthermore, in another possible implementation form of the present application, the prediction module 32 includes:

[0190] A first prediction unit is used to predict the feasible domain of the heading angle at the next receiving moment corresponding to the current moment according to the kinematic constraint, the current speed, the current heading angle change rate and the heading angle feasible domain model;

[0191] A second prediction unit is used to predict the position feasible domain of the next receiving time corresponding to the current time according to the kinematic constraints, the current position data, the current speed, the current acceleration and the position feasible domain model;

[0192] A third prediction unit is used to predict the feasible domain of the longitudinal speed at the next receiving time corresponding to the current time according to the acceleration constraint, the environmental factor constraint, the current speed and the longitudinal speed constraint equation;

[0193] The fourth prediction unit is used to predict the predicted position data of the next receiving time corresponding to the current time according to the current position data, the current heading angle, the current speed, the current acceleration, the current heading angle change rate and the prediction value calculation equation.

[0194] Furthermore, in another possible implementation form of the present application, the first determining module 33 includes:

[0195] A judging unit, used to judge whether the current position data is within the data feasible domain according to the data feasible domain at the current moment and the current position data;

[0196] A first determining unit, configured to determine the current position data as the corrected position data when the current position data is within the data feasible domain;

[0197] The second determination unit is used to determine the deviation value of the current position data according to the predicted position data and the current position data when the current position data is not within the data feasible domain, and to determine the corrected position data according to the deviation value.

[0198] Furthermore, in another possible implementation form of the present application, the second determining unit is specifically configured to:

[0199] When the deviation value is less than or equal to the deviation threshold, the current position data is projected to the feasible domain of the position data at the current moment to determine the corrected position data;

[0200] When the deviation value is greater than the deviation threshold, the predicted position data at the current moment is determined as the corrected position data.

[0201] Furthermore, in another possible implementation form of the present application, the data processing module 34 includes:

[0202] The data processing unit is used to smooth each corrected position data in the current data window according to each corrected position data in the current data window and each corrected position data in the previous adjacent data window corresponding to the current data window, so as to generate an optimized driving trajectory.

[0203] Furthermore, in another possible implementation form of the present application, the trajectory data optimization device 30 further includes:

[0204] The interpolation module is used to perform interpolation processing on each trajectory data correction value in the data window if the amount of data in the data window is less than a preset amount threshold.

[0205] Furthermore, in another possible implementation form of the present application, the trajectory data optimization device 30 further includes:

[0206] An acquisition module is used to obtain the timestamp corresponding to the current driving data;

[0207] A second determination module, used to determine the delay time corresponding to the current driving data according to the timestamp;

[0208] The discarding module is used to discard the current driving data when the delay time is greater than a preset delay threshold.

[0209] Furthermore, in another possible implementation form of the present application, the above-mentioned data window is an adaptive window, and the window length of the data window can be dynamically adjusted.

[0210] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0211] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0212] In order to implement the above embodiments, the present application also proposes a terminal device.

[0213] Figure 4 A schematic diagram of the structure of a terminal device according to an embodiment of the present application.

[0214] like Figure 4 As shown, the terminal device 200 includes:

[0215] The memory 210 and at least one processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), the memory 210 stores a computer program, and when the processor 220 executes the program, the trajectory data optimization method described in the embodiment of the present application is implemented.

[0216] Bus 230 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0217] The terminal device 200 typically includes a variety of electronic device readable media, which can be any available media that can be accessed by the terminal device 200, including volatile and non-volatile media, removable and non-removable media.

[0218] The memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. The terminal device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 260 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 230 via one or more data medium interfaces. The memory 210 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0219] A program / utility 280 having a set (at least one) of program modules 270 may be stored, for example, in the memory 210, such program modules 270 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 270 generally perform the functions and / or methods of the embodiments described herein.

[0220] The terminal device 200 can also communicate with one or more external devices 290 (such as keyboards, pointing devices, displays 291, etc.), and can also communicate with one or more devices that enable users to interact with the terminal device 200, and / or communicate with any device that enables the terminal device 200 to communicate with one or more other computing devices (such as network cards, modems, etc.). This communication can be carried out through an input / output (I / O) interface 292. In addition, the terminal device 200 can also communicate with one or more networks (such as local area networks (LANs), wide area networks (WANs) and / or public networks, such as the Internet) through a network adapter 293. As shown in the figure, the network adapter 293 communicates with other modules of the terminal device 200 through a bus 230. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the terminal device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0221] The processor 220 executes various functional applications and data processing by running the programs stored in the memory 210 .

[0222] It should be noted that the implementation process and technical principles of the terminal device of this embodiment refer to the aforementioned explanation of the trajectory data optimization method of the embodiment of the present application, which will not be repeated here.

[0223] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0224] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0225] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0226] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0227] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0228] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0229] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0230] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for optimizing trajectory data, characterized in that: include: Receiving current driving data corresponding to a target object, wherein the current driving data is driving data of the target object collected at a current moment; According to the current driving data, the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment are predicted through the physical constraint model and the feasible domain mathematical model, and the data feasible domain and the predicted position data of the next receiving moment are stored in the feasible domain cache; the current driving data includes current position data, current heading angle, current speed, current acceleration and current heading angle change rate, the physical constraint model includes kinematic constraints, acceleration constraints and environmental factor constraints, the feasible domain mathematical model includes a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation, and the data feasible domain includes a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain; Determine, according to the data feasible domain of the current moment, the predicted position data and the current driving data, the corrected position data corresponding to the current driving data, and store the corrected position data in the current data window corresponding to the current moment, wherein the data feasible domain of the current moment and the predicted position data are determined according to the driving data received at the last receiving moment corresponding to the current moment and stored in the feasible domain cache; In a case where the current moment is a data processing moment of the current data window, smoothing is performed on each of the corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object; The method of predicting the data feasible domain and predicted position data of the next receiving time corresponding to the current time by using a physical constraint model and a feasible domain mathematical model according to the current driving data includes: Predicting the heading angle feasible domain at the next receiving moment corresponding to the current moment according to the kinematic constraint, the current speed, the current heading angle change rate and the heading angle feasible domain model; Predicting the position feasible domain at the next receiving moment corresponding to the current moment according to the kinematic constraints, the current position data, the current speed, the current acceleration and the position feasible domain model; Predicting the longitudinal velocity feasible domain at the next receiving time corresponding to the current time according to the acceleration constraint, the environmental factor constraint, the current velocity and the longitudinal velocity constraint equation; The predicted position data at the next receiving moment corresponding to the current moment is predicted based on the current position data, the current heading angle, the current speed, the current acceleration, the current heading angle change rate and the prediction value calculation equation.

2. The method according to claim 1, characterized in that The determining, according to the data feasible domain at the current moment, the predicted position data and the current driving data, the corrected position data corresponding to the current driving data comprises: According to the data feasible domain at the current moment and the current position data, determining whether the current position data is within the data feasible domain; When the current position data is within the data feasible domain, determining the current position data as the corrected position data; When the current position data is not within the data feasible domain, a deviation value of the current position data is determined based on the predicted position data and the current position data, and the corrected position data is determined based on the deviation value.

3. The method according to claim 2, characterized in that The step of determining the corrected position data according to the deviation value comprises: When the deviation value is less than or equal to the deviation threshold, projecting the current position data to the feasible domain of the position data at the current moment to determine the corrected position data; When the deviation value is greater than the deviation threshold, the predicted position data at the current moment is determined as the corrected position data.

4. The method according to claim 1, characterized in that The smoothing process of each of the corrected position data in the current data window to generate an optimized driving trajectory corresponding to the target object includes: According to each of the corrected position data in the current data window and each of the corrected position data in the previous adjacent data window corresponding to the current data window, each of the corrected position data in the current data window is smoothed to generate the optimized driving trajectory.

5. The method according to claim 4, characterized in that Before smoothing each of the corrected position data in the current data window according to each of the corrected position data in the current data window and each of the corrected position data in the previous adjacent data window corresponding to the current data window to generate the optimized driving trajectory, the method further includes: If the amount of data in the data window is less than a preset amount threshold, interpolation processing is performed on each of the trajectory data correction values ​​in the data window.

6. The method according to claim 1, characterized in that The method further comprises: predicting the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through the physical constraint model and the feasible domain mathematical model according to the current driving data, and storing the data feasible domain and the predicted position data of the next receiving moment in the feasible domain cache. Obtaining a timestamp corresponding to the current driving data; Determining a delay time corresponding to the current driving data according to the timestamp; When the delay time is greater than a preset delay threshold, the current driving data is discarded.

7. The method according to any one of claims 1 to 6, characterized in that: The data window is an adaptive window, and the window length of the data window can be dynamically adjusted.

8. A trajectory data optimization device, characterized in that: include: A receiving module, configured to receive current driving data corresponding to a target object, wherein the current driving data is driving data of the target object collected at a current moment; A prediction module, used to predict the data feasible domain and predicted position data of the next receiving moment corresponding to the current moment through a physical constraint model and a feasible domain mathematical model according to the current driving data, and store the data feasible domain and the predicted position data of the next receiving moment in a feasible domain cache; the current driving data includes current position data, current heading angle, current speed, current acceleration and current heading angle change rate, the physical constraint model includes kinematic constraints, acceleration constraints and environmental factor constraints, the feasible domain mathematical model includes a heading angle feasible domain model, a position feasible domain model, a longitudinal speed constraint equation and a predicted value calculation equation, and the data feasible domain includes a heading angle feasible domain, a position feasible domain and a longitudinal speed feasible domain; A first determination module is used to determine the corrected position data corresponding to the current driving data according to the data feasible domain at the current moment, the predicted position data and the current driving data, and store the corrected position data in the current data window corresponding to the current moment, wherein the data feasible domain at the current moment and the predicted position data are determined according to the driving data received at the last receiving moment corresponding to the current moment and stored in the feasible domain cache; A data processing module, configured to perform smoothing processing on each of the corrected position data in the current data window when the current moment is the data processing moment of the current data window, so as to generate an optimized driving trajectory corresponding to the target object; The prediction module is specifically used to predict the feasible domain of the heading angle at the next receiving moment corresponding to the current moment according to the kinematic constraints, the current speed, the current heading angle change rate and the heading angle feasible domain model; predict the position feasible domain at the next receiving moment corresponding to the current moment according to the kinematic constraints, the current position data, the current speed, the current acceleration and the position feasible domain model; predict the longitudinal speed feasible domain at the next receiving moment corresponding to the current moment according to the acceleration constraints, environmental factor constraints, the current speed and the longitudinal speed constraint equation; predict the predicted position data at the next receiving moment corresponding to the current moment according to the current position data, the current heading angle, the current speed, the current acceleration, the current heading angle change rate and the predicted value calculation equation.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the terminal device implements the method according to any one of claims 1 to 6.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by an electronic device, the method according to any one of claims 1 to 6 is implemented.

Images