CN115507867A - Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium - Google Patents
Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium Download PDFInfo
- Publication number
- CN115507867A CN115507867A CN202210978882.3A CN202210978882A CN115507867A CN 115507867 A CN115507867 A CN 115507867A CN 202210978882 A CN202210978882 A CN 202210978882A CN 115507867 A CN115507867 A CN 115507867A
- Authority
- CN
- China
- Prior art keywords
- predicted
- data set
- error
- values
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a target track prediction method, a target track prediction device, an electronic device and a storage medium, wherein real track data of a target are collected at a preset frequency, n continuous sampling values recorded from a first historical moment to a current moment are obtained to obtain a first real track data set, a first predicted track data set used for predicting the track of the target from the first historical moment to the current moment is obtained, and the first predicted track data set comprises n continuous predicted values; comparing the first predicted trajectory data set with the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set; and compensating the second predicted track data group according to the first error result to obtain a predicted track of the target from the second historical moment to the next moment, wherein the second predicted track data group comprises n continuous predicted values, so that the problem of low accuracy of the predicted track of the target is solved, and the accuracy of the predicted track of the target is improved.
Description
Technical Field
The present disclosure relates to the field of automatic driving technologies, and in particular, to a target trajectory prediction method, a target trajectory prediction device, an electronic device, and a storage medium.
Background
Vehicle trajectory prediction is one of the key technologies for autonomous driving. The existing vehicle track prediction methods mainly comprise the following types: the first is a method based on vehicle dynamics and kinematics models; secondly, predicting the driving intention of the vehicle and then generating a predicted track, learning parameters of a track evaluation function by adopting a maximum likelihood method after generating a candidate predicted track by algorithms such as RRT (remote tracking) according to the driving intention and the like, so as to select the track with the minimum cost, learning the parameters of the model by training data by adopting models such as a Gaussian process and the like, and generating the predicted track, wherein the driving intention predicting method comprises the steps of learning the parameters of the model by adopting a cost function, machine learning, a hidden Markov model, a Bayesian network and the like; and thirdly, directly generating a track by a deep learning-based method, wherein the track comprises an interaction algorithm based on LSTM, an interaction algorithm based on Graph/Attention and the like.
However, the above three types of vehicle trajectory prediction methods all depend on the accuracy of offline data and the coverage rate of training scenes. For example, a method based on vehicle dynamics and a kinematics model requires offline vehicle parameters and vehicle state parameters at the current time, and a predicted trajectory calculated by parameter evolution may exceed the real trajectory of a real human driver under a complex working condition; for example, in the trajectory prediction method based on the intention of the driver, when the cost function cost is calculated, the real intention of the driver cannot be effectively measured in a complex scene, for example, under the condition that the target vehicle is on the rightmost ramp which can only be merged into the main road, but the target vehicle is close to the lane line of the right side where the target vehicle is located, the real intention of the driver is difficult to effectively evaluate by the method based on the intention of the driver, and the trajectory predicted by an algorithm is influenced; for example, in a method for predicting a trajectory based on a deep learning model, data that needs to be trained offline covers various scenes, and when the trained scene data does not include a special complex scene, the trajectory of a vehicle driven by a real driver cannot be obtained due to model prediction. Therefore, the above three types of vehicle trajectory prediction methods are limited by the accuracy of offline data and the coverage factor of a training scene in the actual application process, so that a small difference exists between the predicted trajectory and the actual trajectory.
Aiming at the problem that the accuracy of a target prediction track is low in the related technology, no effective solution is provided at present.
Disclosure of Invention
The embodiment provides a target trajectory prediction method, a target trajectory prediction device, an electronic device and a storage medium, so as to solve the problem of low accuracy of a target prediction trajectory in the related art.
In a first aspect, in this embodiment, a target trajectory prediction method is provided, where real trajectory data of a target is collected at a preset frequency, n consecutive sample values recorded from a first historical time to a current time are obtained to obtain a first real trajectory data set, and a first predicted trajectory data set used for predicting a trajectory of the target from the first historical time to the current time is obtained, where the first predicted trajectory data set includes n consecutive predicted values; comparing the first predicted trajectory data set with the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set; and compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from a second historical moment to a next moment, wherein the second predicted track data set comprises n continuous predicted values.
In some embodiments, n error values are obtained according to the sampling values in the first real trajectory data set and the corresponding predicted values in the first predicted trajectory data set; and carrying out validity judgment on each error value, and correcting the error value judged to be invalid.
In some embodiments, a first threshold value is set, the n error values are compared with the first threshold value, and an error value greater than the first threshold value is determined to be an invalid error value. In some embodiments, two error values adjacent to the invalid error value are obtained, and the average of the two adjacent error values replaces the invalid error value.
In some of these embodiments, the n error values are added to n consecutive predicted values in the second predicted trajectory data set.
In some embodiments, a second error result is obtained, where the second error result is obtained by comparing the second predicted trajectory data set with a second real trajectory data set, the second real trajectory data set includes n consecutive sample values of the target from the second historical time to a next time, and the second error result includes n error values; and respectively calculating the average value of the first error result and the average value of the second error result, comparing the average values of the first error result and the second error result, and determining whether to adopt the first error result to compensate the second predicted trajectory data set or not according to the obtained comparison result.
In some embodiments, the time interval between the generation of the first predicted trajectory data set and the generation of the second predicted trajectory data set is less than or equal to the time interval from the current time to the next time.
In a second aspect, there is provided in the present embodiment a target trajectory prediction apparatus, including:
the system comprises an acquisition module, a prediction module and a prediction module, wherein the acquisition module is used for acquiring real track data of a target at a preset frequency, acquiring n continuous sampling values recorded from a first historical moment to a current moment to obtain a first real track data group, and acquiring a first prediction track data group used for predicting the track of the target from the first historical moment to the current moment, and the first prediction track data group comprises n continuous prediction values;
a comparison module, configured to compare the first predicted trajectory data set with the first real trajectory data set, so as to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set;
and the compensation module is used for compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from a second historical moment to a next moment, wherein the second predicted track data set comprises n continuous predicted values.
In a third aspect, in the present embodiment, there is provided an electronic apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the target trajectory prediction method according to the first aspect when executing the computer program.
In a fourth aspect, in the present embodiment, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the target trajectory prediction method described in the first aspect above.
Compared with the related art, the target trajectory prediction method, the target trajectory prediction device, the electronic device and the storage medium provided in this embodiment collect real trajectory data of a target at a preset frequency, obtain n continuous sampling values recorded from a first historical time to a current time to obtain a first real trajectory data set, and obtain a first predicted trajectory data set used for predicting a trajectory of the target from the first historical time to the current time, where the first predicted trajectory data set includes n continuous predicted values; comparing the first predicted trajectory data set with the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set; and compensating the second predicted track data group according to the first error result to obtain a predicted track of the target from the second historical moment to the next moment, wherein the second predicted track data group comprises n continuous predicted values, so that the problem of low accuracy of the target predicted track in the related technology is solved, and the accuracy of the target predicted track is improved.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of a terminal hardware structure of a target trajectory prediction method according to an embodiment of the present application;
FIG. 2 is a flow chart of a target trajectory prediction method in an embodiment of the present application;
FIG. 3 is a schematic diagram of a vehicle trajectory data acquisition method in an embodiment of the present application;
FIG. 4 is a flow chart of a vehicle trajectory prediction method in an embodiment of the present application;
fig. 5 is a block diagram of a target trajectory prediction apparatus according to an embodiment of the present application.
Detailed Description
For a clearer understanding of the objects, aspects and advantages of the present application, reference is made to the following description and accompanying drawings.
Unless defined otherwise, technical or scientific terms used herein shall have the same general meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The use of the terms "a" and "an" and "the" and similar referents in the context of describing the invention (including a reference to the context of the specification and claims) are to be construed to cover both the singular and the plural, as well as the singular and plural. The terms "comprises," "comprising," "has," "having" and any variations thereof, as referred to in this application, are intended to cover non-exclusive inclusions; for example, a process, method, and system, article, or apparatus that comprises a list of steps or modules (elements) is not limited to the listed steps or modules, but may include other steps or modules (elements) not listed or inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" as referred to herein means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. In general, the character "/" indicates a relationship in which the objects associated before and after are an "or". The terms "first," "second," "third," and the like in this application are used for distinguishing between similar items and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the present embodiment may be executed in a terminal, a computer, or a similar computing device. For example, the target trajectory prediction method is executed on a terminal, and fig. 1 is a block diagram of a hardware structure of the terminal according to an embodiment of the present application. As shown in fig. 1, the terminal may include one or more processors (only one shown in fig. 1) and a memory for storing data, wherein the processors may include, but are not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA. The terminal may further include a transmission device for a communication function and an input-output device. It will be understood by those of ordinary skill in the art that the structure shown in fig. 1 is merely an illustration and is not intended to limit the structure of the terminal described above. For example, the terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory may be used to store a computer program, for example, a software program and a module of application software, such as a computer program corresponding to the target trajectory prediction method in the embodiment, and the processor executes various functional applications and data processing by running the computer program stored in the memory, so as to implement the method described above. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device is used to receive or transmit data via a network. The network described above includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In an embodiment, a target trajectory prediction method is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and fig. 2 is a flowchart of the target trajectory prediction method, as shown in fig. 2, where the flowchart includes the following steps:
step S101, real track data of a target are collected at a preset frequency, n continuous sampling values recorded from a first historical moment to a current moment are obtained to obtain a first real track data set, and a first predicted track data set used for predicting the track of the target from the first historical moment to the current moment is obtained, wherein the first predicted track data set comprises n continuous predicted values.
In the moving process of the target, on one hand, real track data of the target are collected through a sensor at a preset frequency, a data storage mode of first in and last out is adopted, and n continuous sampling values are recorded at intervals of a first period to serve as a first real track data set. On the other hand, a predicted trajectory data set is generated every second cycle, and each predicted trajectory data set includes n consecutive predicted values.
The target may be a vehicle such as an automobile or a motorcycle, or may be an intelligent device such as a robot or an unmanned airplane. The n continuous sampling values and the n continuous predicted values are in one-to-one correspondence, the sampling values and the predicted values both comprise space coordinates of the target, and the space coordinates comprise positions in the horizontal direction and/or positions in the vertical direction.
Step S102, comparing the first predicted trajectory data set with the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set.
And correspondingly subtracting the n continuous sampling values from the n continuous predicted values to obtain n error values, wherein the n error values can be directly used as a first error result, or the n error values can be processed and then used as the first error result.
And S103, compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from the second historical moment to the next moment, wherein the second predicted track data set comprises n continuous predicted values.
And correspondingly adding the n error values or the processed n error values with the n predicted values in the second predicted trajectory data set to realize the compensation of the second predicted trajectory data set.
In the related art, the trajectory prediction method is to directly give a predicted trajectory based on offline data, but when the trajectory is predicted in real time, errors between the predicted trajectory and a real trajectory are ignored. In this embodiment, through the steps S101 to S103, an error result between the actual trajectory data set recorded from the first historical time to the current time and the corresponding predicted trajectory data set is calculated, the calculated error result is compensated to the subsequent predicted trajectory data set, and the target trajectory at the future time is predicted based on the compensated predicted trajectory data set, so as to achieve the purpose of real-time online correction of the target predicted trajectory, solve the problem of low accuracy of the target predicted trajectory in the related art, and improve the accuracy of the target predicted trajectory. Meanwhile, the target track prediction method is low in algorithm complexity, small in CPU/memory resource occupation in the operation process, wide in application scene, high in matching performance and suitable for track correction of various prediction models or algorithms.
In some of these embodiments, comparing the first predicted trajectory data set to the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set comprises: obtaining n error values according to the sampling values in the first real track data group and the corresponding predicted values in the first predicted track data group; and carrying out validity judgment on each error value, and correcting the error value judged to be invalid.
The terminal sensor samples the real track data of the target at a preset frequency, and errors of the sensor in the sampling process can influence the accuracy of a sampling value, so that the magnitude of error values is influenced, therefore, validity judgment needs to be carried out on n error values, and invalid error values are corrected according to a judgment result. In some embodiments, the determining the validity of each error value includes: setting a first threshold value, comparing the n error values with the first threshold value respectively, and determining the error value larger than the first threshold value as an invalid error value.
And calculating the standard deviation of the n error values, and setting a first threshold value to be k times of the standard deviation in the group, wherein the k value is set according to the target track prediction requirement. And comparing the error values with a set first threshold value respectively, determining the error value larger than the first threshold value as an invalid error value, wherein the error value is required to be corrected, and determining the error value smaller than or equal to the first threshold value as a valid error value without correction.
In some embodiments, correcting the error value determined to be invalid includes: and acquiring two error values adjacent to the invalid error value, and replacing the invalid error value with the average value of the two adjacent error values.
For the invalid error value, the correction is performed by up-down sampling and adding, that is, the average value of two adjacent error values of the error value is selected to replace the error value.
In some embodiments, the first error result comprises n error values, and compensating the second predicted trajectory data set according to the first error result comprises: and correspondingly adding the n error values and n continuous predicted values in the second predicted track data group.
The second predicted track data group is a predicted track of the target from the second historical moment to the next moment, the error values are respectively accumulated into corresponding continuous predicted values in the second predicted track data group, errors of the track predicted by the real-time algorithm and the real track are reduced to correct the future predicted track, and the track prediction accuracy is improved.
In some embodiments, the error result comprises n error values, and compensating the second predicted trajectory data set based on the error result further comprises:
obtaining a second error result, wherein the second error result is obtained by comparing a second predicted trajectory data set with a second real trajectory data set, the second real trajectory data set comprises n continuous sampling values of the target from a second historical moment to a next moment, and the second error result comprises n error values; and calculating the average values of the first error result and the second error result respectively, comparing the average values of the first error result and the second error result, and determining whether to adopt the first error result to compensate the second predicted trajectory data set according to the obtained comparison result.
Respectively calculating the mean value of the first error result and the second error result, and comparing the relationship between the two mean values, wherein the mean value comparison method is not limited, and includes but is not limited to judging whether the mean value is within a unified threshold range, and compensating if the mean value is within a preset threshold range; and judging the magnitude relation between the difference of the average values and a certain fixed threshold point, and compensating if the difference of the average values is smaller than the fixed threshold point.
In some embodiments, the time interval between the generation of the first predicted trajectory data set and the generation of the second predicted trajectory data set is less than or equal to the time interval from the current time to the next time.
The generation time interval of the first predicted trajectory data set and the second predicted trajectory data set is set to ensure that future predicted trajectories can be corrected in real time according to the first error result.
In one embodiment, for example, a predicted vehicle trajectory, FIG. 3 provides a schematic diagram of a vehicle trajectory data acquisition method. As shown in fig. 3, during the moving process of the vehicle, on one hand, the real track data of the vehicle is collected by the sensor at the preset frequency, and if the collection starts from the time t, a data storage manner of first-in and last-out is adopted, and n continuous sampling values are recorded at intervals of τ as a real track data set. If the sensor starts to collect the real track data of the vehicle from t time, when the time reaches t + l, n points are recorded, wherein l = k multiplied by tau, the number of a first real track data group collected in the time from t to (t + l) is recorded as 1- (1), 1- (2), 1- (3), \8230;, 1- (n-1), 1- (n); after the interval time tau, the sensor starts to collect a second real track data group from the time of t + tau, when the time reaches t + tau + l, n points are recorded, and the number of the second real track data group collected in the time from t + tau to (t + tau + l) is recorded as 2- (1), 2- (2), 2- (3), \8230;, 2- (n-1), 2- (n); after the interval time tau, the sensor starts to collect the next group of real track data from the time t +2 tau, and so on. After the first real track data group is recorded with n points, the predicted track and the real track can be compared.
On the other hand, from time t, a set of initial predicted trajectory data sets is generated at time τ, each set of predicted trajectory data sets including n consecutive predicted values. Obtaining a first predicted track data group at the time t for predicting the vehicle track in the future time t to (t + l), wherein the predicted track data numbers are recorded as Tra1- (1), tra1- (2), tra1- (3), \8230 \ 8230;, tra1- (n-1) and Tra1- (n); obtaining a second predicted track data group at the time of t + tau, wherein the second predicted track data group is used for predicting tracks in vehicle track time in the future time of t + tau to (t + tau + l), and the predicted track data numbers are recorded as Tra2- (1), tra2- (2), tra2- (3), \ 8230; \ 8230;, tra2- (n-1) and Tra2- (n); and obtaining the next group of predicted track data at the time t +3 tau, and so on. The prediction time length corresponding to the predicted track data set is l, and l = k × τ. When the time reaches t + l, the sensor just acquires a first real track data set within the time from t to (t + l), and then the first predicted track data set acquired within the time from t to (t + l) can be obtained by comparing the first predicted track data set acquired at the time t with the first real track data set acquired within the time from t to (t + l).
In one embodiment, the algorithm for implementing the target trajectory prediction method in the present embodiment is deployed in a domain controller in a vehicle, which uses the target trajectory prediction method on urban roads and elevated highway sections, wherein the domain controller includes a domain master processor, an operating system, and application software and algorithms. Fig. 4 is a flowchart of a vehicle trajectory prediction method, which includes the following steps, as shown in fig. 4:
step S201, a predicted track data set and a real track data set are obtained, wherein the domain controller outputs a group of predicted tracks of the vehicles in the future within 4S every 25ms, the group of predicted tracks consists of 20 points (predicted values), the interval between every two points is 200ms, and continuous 20 predicted data are recorded every 1S, so that a predicted track data set is obtained; sampling a real track every 200ms, after recording 20 sampling values, storing the real track in a first-in first-out mode to obtain a real track data set.
Step S202, under the condition that each real trajectory data set is obtained, that is, every 1S, the first predicted trajectory data set and the first real trajectory data set are compared to obtain a first error result.
Step S203, calculate the standard deviation of the n error values in the first error result, and set the first threshold to be k times of the standard deviation. The standard deviation formula is as follows:
where δ (X) represents the standard deviation of the error value, X represents the group number of the error result, X i For the error value, μ is the average value of n error values, i is a natural number from 1 to n, n represents the serial number of the error value, and in this embodiment, n is 20.
Step S204, comparing the magnitude relation between the n error values and the first threshold value, wherein the error value larger than the first threshold value is an invalid error value, and replacing the invalid error value by the average value of the adjacent error values.
Step S205, obtaining the second error result, calculating the average of the first error result and the second error result, comparing the two average values, and determining the validity of the first error result according to the comparison result.
In step S206, if the first error result is determined to be valid, the first error result is used to compensate the second predicted trajectory data.
In an embodiment, a target trajectory prediction apparatus is further provided, and the apparatus is used to implement the foregoing embodiment and the preferred embodiment, which have already been described and are not described again. The terms "module," "unit," "subunit," and the like as used below may implement a combination of software and/or hardware for a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram showing the structure of the target trajectory prediction apparatus of the present embodiment, and as shown in fig. 5, the apparatus includes:
the system comprises an acquisition module, a processing module and a control module, wherein the acquisition module is used for acquiring real track data of a target at a preset frequency, acquiring n continuous sampling values recorded from a first historical moment to a current moment to obtain a first real track data group, and acquiring a first predicted track data group used for predicting the track of the target from the first historical moment to the current moment, wherein the first predicted track data group comprises n continuous predicted values;
the comparison module is coupled to the acquisition module and used for comparing the first predicted track data set with the first real track data set to obtain a first error result between the first predicted track data set and the first real track data set;
and the compensation module is coupled to the acquisition module and used for compensating the second predicted track data set according to the first error result to obtain a predicted track of the target from the second historical moment to the next moment, wherein the second predicted track data set comprises n continuous predicted values.
It should be noted that the above modules may be functional modules or program modules, and may be implemented by software or hardware. For a module implemented by hardware, the above modules may be located in the same processor; or the modules can be respectively positioned in different processors in any combination.
There is also provided in this embodiment an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s101, acquiring real track data of a target at a preset frequency, acquiring n continuous sampling values recorded from a first historical moment to a current moment to obtain a first real track data set, and acquiring a first predicted track data set for predicting the track of the target from the first historical moment to the current moment, wherein the first predicted track data set comprises n continuous predicted values;
s102, comparing the first predicted track data set with the first real track data set to obtain a first error result between the first predicted track data set and the first real track data set
And S103, compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from a second historical moment to a next moment, wherein the second predicted track data set comprises n continuous predicted values.
It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the foregoing embodiment and optional implementation manners, and details are not described in this embodiment again.
In addition, in combination with the target trajectory prediction method provided in the foregoing embodiment, a storage medium may also be provided to implement this embodiment. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the target trajectory prediction methods in the above embodiments.
It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to be limiting. All other embodiments, which can be derived by a person skilled in the art from the examples provided herein without any inventive step, shall fall within the scope of protection of the present application.
It is obvious that the drawings are only examples or embodiments of the present application, and it is obvious to those skilled in the art that the present application can be applied to other similar cases according to the drawings without creative efforts. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
The term "embodiment" is used herein to mean that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is to be expressly and implicitly understood by one of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the patent protection. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for predicting a target trajectory, comprising:
acquiring real track data of a target at a preset frequency, acquiring n continuous sampling values recorded from a first historical moment to a current moment to obtain a first real track data set, and acquiring a first predicted track data set for predicting a track of the target from the first historical moment to the current moment, wherein the first predicted track data set comprises n continuous predicted values;
comparing the first predicted trajectory data set with the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set;
and compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from a second historical moment to a next moment, wherein the second predicted track data set comprises n continuous predicted values.
2. The method of claim 1, wherein comparing the first predicted trajectory data set to the first real trajectory data set to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set comprises:
obtaining n error values according to the sampling values in the first real track data group and the corresponding predicted values in the first predicted track data group;
and carrying out validity judgment on each error value, and correcting the error value judged to be invalid.
3. The method of claim 2, wherein the determining the validity of each error value comprises:
setting a first threshold value, comparing the n error values with the first threshold value respectively, and determining the error value larger than the first threshold value as an invalid error value.
4. The method of claim 2, wherein modifying the error value determined to be invalid comprises:
and acquiring two adjacent error values from the invalid error value, and replacing the invalid error value with the average value of the two adjacent error values.
5. The method of claim 1, wherein the first error result comprises n error values, and compensating the second predicted trajectory data set according to the first error result comprises:
and correspondingly adding the n error values and n continuous predicted values in the second predicted track data group.
6. The method of claim 1, wherein the error result comprises n error values, and compensating the second predicted trajectory data set based on the error result comprises:
obtaining a second error result, wherein the second error result is obtained by comparing the second predicted trajectory data set with a second real trajectory data set, the second real trajectory data set includes n consecutive sample values of the target from the second historical time to the next time, and the second error result includes n error values;
and respectively calculating the average value of the first error result and the average value of the second error result, comparing the average values of the first error result and the second error result, and determining whether to adopt the first error result to compensate the second predicted trajectory data set or not according to the obtained comparison result.
7. The target trajectory prediction method according to any one of claims 1 to 6, wherein a time interval between generation of the first predicted trajectory data set and generation of the second predicted trajectory data set is less than or equal to a time interval from a current time to a next time.
8. A target trajectory prediction apparatus, comprising:
the system comprises an acquisition module, a prediction module and a processing module, wherein the acquisition module is used for acquiring real track data of a target at a preset frequency, acquiring n continuous sampling values recorded from a first historical moment to a current moment to obtain a first real track data set, and acquiring a first predicted track data set used for predicting the track of the target from the first historical moment to the current moment, wherein the first predicted track data set comprises n continuous predicted values;
a comparison module, configured to compare the first predicted trajectory data set with the first real trajectory data set, so as to obtain a first error result between the first predicted trajectory data set and the first real trajectory data set;
and the compensation module is used for compensating a second predicted track data set according to the first error result to obtain a predicted track of the target from a second historical moment to a next moment, wherein the second predicted track data set comprises n continuous predicted values.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is configured to execute the computer program to perform the target trajectory prediction method of any one of claims 1 to 7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the target trajectory prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210978882.3A CN115507867A (en) | 2022-08-16 | 2022-08-16 | Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210978882.3A CN115507867A (en) | 2022-08-16 | 2022-08-16 | Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115507867A true CN115507867A (en) | 2022-12-23 |
Family
ID=84501554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210978882.3A Pending CN115507867A (en) | 2022-08-16 | 2022-08-16 | Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115507867A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116125819A (en) * | 2023-04-14 | 2023-05-16 | 智道网联科技(北京)有限公司 | Track correction method, track correction device, electronic device and computer-readable storage medium |
| CN116767186A (en) * | 2023-07-18 | 2023-09-19 | 北京斯年智驾科技有限公司 | Vehicle control method, device, computer equipment and readable storage medium |
-
2022
- 2022-08-16 CN CN202210978882.3A patent/CN115507867A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116125819A (en) * | 2023-04-14 | 2023-05-16 | 智道网联科技(北京)有限公司 | Track correction method, track correction device, electronic device and computer-readable storage medium |
| CN116767186A (en) * | 2023-07-18 | 2023-09-19 | 北京斯年智驾科技有限公司 | Vehicle control method, device, computer equipment and readable storage medium |
| CN116767186B (en) * | 2023-07-18 | 2024-04-26 | 北京斯年智驾科技有限公司 | Vehicle control method, device, computer equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115507867A (en) | Target trajectory prediction method, target trajectory prediction device, electronic device, and storage medium | |
| CN110316193B (en) | Preview distance setting method, device, equipment and computer readable storage medium | |
| CN111009134A (en) | Short-term vehicle speed working condition real-time prediction method based on interaction between front vehicle and self vehicle | |
| CN109767619B (en) | Intelligent networking pure electric vehicle running condition prediction method | |
| CN109472251B (en) | Object collision prediction method and device | |
| CN113291321A (en) | Vehicle track prediction method, device, equipment and storage medium | |
| CN112319464B (en) | Automatic parking method, device, equipment and storage medium | |
| US20230228593A1 (en) | Method, device and system for perceiving multi-site roadbed network and terminal | |
| CN113219336B (en) | Battery degradation determination system, method, and non-transitory storage medium storing program | |
| US11703874B2 (en) | System and method for collection of performance data by a vehicle | |
| CN112001948B (en) | Target tracking processing method and device | |
| CN112977412A (en) | Vehicle control method, device and equipment and computer storage medium | |
| EP4060381A1 (en) | History-based identification of incompatible tracks | |
| CN114637770A (en) | Vehicle track prediction method and device | |
| CN110478911A (en) | The unmanned method of intelligent game vehicle and intelligent vehicle, equipment based on machine learning | |
| CN114676870A (en) | Vehicle speed prediction method, vehicle speed prediction model training method and related device | |
| CN109767638A (en) | Control method for vehicle, device, equipment and computer readable storage medium | |
| CN115115530B (en) | Image deblurring method, device, terminal equipment and medium | |
| CN114536326B (en) | Road sign data processing method, device and storage medium | |
| CN114104005B (en) | Decision-making method, device and equipment of automatic driving equipment and readable storage medium | |
| CN115146525A (en) | System for estimating deterioration state of secondary battery, method for estimating deterioration state of secondary battery, and storage medium | |
| CN115610435A (en) | Method and device for predicting object driving intention, storage medium and electronic device | |
| CN111142422A (en) | Sensor information processing method for ios system | |
| CN113447037A (en) | Stroke yaw detection method and device | |
| CN115578413A (en) | Pedestrian trajectory prediction method and device and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |