CN111626097A - A method, device, electronic device and storage medium for predicting the future trajectory of an obstacle - Google Patents

Abstract

The application discloses a method, a device, electronic equipment and a storage medium for predicting future trajectories of obstacles, wherein the method comprises the following steps: acquiring a scene map corresponding to an area where a vehicle is located; the scene map comprises traffic information of an area, historical tracks of obstacles in a certain range of a vehicle in the area are obtained, the historical tracks are projected to corresponding positions of the scene map to obtain a scene map to be predicted containing the historical tracks, the scene map to be predicted is input into a trained track prediction model, and future tracks of the obstacles are obtained. In this way, the accuracy of future trajectory prediction of the obstacle can be improved by introducing the scene map and the trajectory prediction model.

Description

A method, device, electronic device and storage medium for predicting the future trajectory of an obstacle

technical field

The present application relates to the field of Internet technologies, and in particular, to a method, device, electronic device and storage medium for predicting the future trajectory of an obstacle.

Background technique

The trajectory prediction of the obstacle refers to predicting the future trajectory of the obstacle based on the historical movement path of the obstacle. In an autonomous driving scenario, it is necessary to predict the trajectory of the obstacles around the unmanned vehicle that may affect it, and the obstacles include: motor vehicles, non-motor vehicles, and pedestrians. The specific difficulties faced mainly include the following aspects:

1) The motion trajectory needs to satisfy both traffic rules and physical constraints;

2) The motion state of the obstacle and the characteristic description of the surrounding traffic environment;

3) It needs to be able to provide a variety of possible reasonable trajectories for subsequent screening;

4) The traffic conditions in the intersection scene are complex, contain multiple possibilities, and there is no clear lane division range.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a method, device, electronic device, and storage medium for predicting a future trajectory of an obstacle, so as to improve the accuracy of predicting the future trajectory of an obstacle.

On the one hand, an embodiment of the present application provides a method for predicting a future trajectory of an obstacle, the method comprising:

Obtain the scene map corresponding to the area where the vehicle is located; wherein, the scene map includes the traffic information of the area;

Obtain the historical trajectory of obstacles within a certain range of the vehicle in the area;

Project the historical trajectory to the corresponding position of the scene map, and obtain the scene map to be predicted containing the historical trajectory;

Input the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle.

Optionally, the method further includes the step of obtaining a trajectory prediction model through training; the trajectory prediction model obtained through training includes:

Obtain a sample data set, where the sample data set includes multiple training scene maps and the actual future trajectory corresponding to each training scene map; each training scene map includes a training historical trajectory;

Build a preset machine learning model, and determine the preset machine learning model as the current machine learning model;

Based on the current machine learning model, the trajectory prediction operation is performed on the training scene map, and the predicted future trajectory corresponding to the training scene map is determined;

Determine the loss value based on the predicted future trajectory and the actual future trajectory corresponding to the training scene map;

When the loss value is greater than the preset threshold, backpropagation is performed based on the loss value, the current machine learning model is updated to obtain the updated machine learning model, and the updated machine learning model is re-determined as the current machine learning model; repeat the steps : Based on the current machine learning model, perform trajectory prediction operation on the training scene map, and determine the predicted future trajectory corresponding to the training scene map;

When the loss value is less than or equal to the preset threshold, the current machine learning model is determined as the trajectory prediction model.

Optionally, obtain the historical trajectories of obstacles within a certain range of the vehicle in the area, including:

Obtain the historical position information of obstacles at multiple consecutive time points in the area through sensors;

The historical trajectory is obtained by splicing the historical location information of multiple consecutive time points;

The sensors include one or more of cameras, lidars, and millimeter-wave radars.

Optionally, obtain a scene map corresponding to the area where the vehicle is located, including:

determine the area in which the vehicle is located;

Obtain the traffic information within the preset range of the vehicle based on the high-precision map corresponding to the area;

Project the traffic information to the corresponding position in the preset map under the overlook angle to obtain the scene map.

Optionally, after obtaining the future trajectory of the obstacle, it also includes;

Display the future trajectory in the scene map to be predicted, and display the scene map to be predicted, so that the vehicle can avoid obstacles according to the future trajectory.

Another aspect provides a device for predicting the future trajectory of an obstacle, the device comprising:

The first acquisition module is used to acquire the scene map corresponding to the area where the vehicle is located; wherein, the scene map includes the traffic information of the area;

The second acquisition module is used to acquire the historical trajectory of obstacles within a certain range of the vehicle in the area;

The projection module is used to project the historical trajectory to the corresponding position of the scene map, and obtain the scene map to be predicted including the historical trajectory;

The prediction module is used to input the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle.

Another aspect provides an electronic device, the electronic device includes a processor and a memory, the memory stores at least one instruction or at least a piece of program, the at least one instruction or at least a piece of program is loaded and executed by the processor to realize the above A prediction method for the future trajectory of obstacles.

Another aspect provides a computer-readable storage medium, the storage medium stores at least one instruction or at least one program, and the at least one instruction or at least one program is loaded and executed by a processor to realize the above-mentioned future trajectory of the obstacle. method of prediction.

The method, device, electronic device, and storage medium for predicting the future trajectory of an obstacle provided by the embodiments of the present application have the following technical effects:

Obtain the scene map corresponding to the area where the vehicle is located; wherein, the scene map includes the traffic information of the area, obtain the historical trajectory of the obstacles within a certain range of the vehicle in the area, project the historical trajectory to the corresponding position of the scene map, and obtain the historical trajectory containing the historical trajectory The scene map to be predicted is input into the trained trajectory prediction model to obtain the future trajectory of the obstacle. In this way, the accuracy of future trajectory prediction of obstacles can be improved by introducing a scene map and a trajectory prediction model.

Description of drawings

In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or in the prior art, the following briefly introduces the accompanying drawings used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description The drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without any creative effort.

1 is a schematic diagram of an application environment provided by an embodiment of the present application;

2 is a schematic flowchart of a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application;

3 is a schematic flowchart of a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application;

4 is a schematic flowchart of a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application;

5 is a schematic flowchart of a training trajectory prediction model provided by an embodiment of the present application;

6 is a schematic structural diagram of a device for predicting a future trajectory of an obstacle provided by an embodiment of the present application;

FIG. 7 is a hardware structural block diagram of a server for a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present application.

It should be noted that the terms "first", "second", etc. in the description and claims of the present application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that data so used may be interchanged under appropriate circumstances so that the embodiments of the application described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

Please refer to FIG. 1. FIG. 1 is a schematic diagram of an application environment provided by an embodiment of the present application. The schematic diagram includes a vehicle 101 and a server 102. In an optional implementation manner, the server 102 may be provided in the vehicle 101. The in-vehicle server contains the trajectory prediction model, and can obtain the desired data in real time, so that the future trajectory of the obstacle can be obtained in the future. In another optional embodiment, the vehicle 101 may be provided with its own on-board server, and the on-board server and the server 102 shown in FIG. 1 are not the same server, and the on-board server transmits the obtained data to the server 102 After that, the server can complete the subsequent steps, and finally get the future trajectory of the obstacle. The in-vehicle server involved in the first situation and the server involved in the second situation are collectively referred to as servers below.

Specifically, the server 102 obtains a scene map corresponding to the area where the vehicle 101 is located, wherein the scene map includes the traffic information of the area, and at the same time, the server 102 can obtain the historical trajectory of the obstacles within a certain range of the vehicle 101 in the area, and convert the historical trajectory Projecting to the corresponding position of the scene map to obtain the scene map to be predicted including the historical trajectory, and finally, the server 102 inputs the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle.

A specific embodiment of a method for predicting a future trajectory of an obstacle according to the present application is described below. FIG. 2 is a schematic flowchart of a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application. method operating steps, but may include more or less operating steps based on routine or non-creative labor. The sequence of steps enumerated in the embodiments is only one of the execution sequences of many steps, and does not represent the only execution sequence. When an actual system or server product is executed, it can be executed sequentially or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the embodiments or the methods shown in the accompanying drawings. Specifically, as shown in Figure 2, the method may include:

S201: Obtain a scene map corresponding to the area where the vehicle is located. Wherein, the scene map includes the traffic information of the area.

In this embodiment of the present application, the vehicle may be an unmanned vehicle.

In this embodiment of the present application, the content in step S201 may be specifically implemented by using part of the content in the method for predicting the future trajectory of an obstacle shown in FIG. 3 , and the specific method is as follows:

S2011: Determine the area where the vehicle is located.

In this embodiment of the present application, the server may determine the area where the vehicle is located according to the positioning system of the vehicle.

S2013: Acquire traffic information within a preset range of the vehicle based on the high-precision map corresponding to the area.

In an optional embodiment, the traffic information may include lane information, lane centerline information, pedestrian crossing information, traffic light information, stop line information, and the like. Specifically, it may be lane information of a certain intersection (three forks, intersection, etc.), lane center line information, pedestrian crossing information, traffic light information, stop line information, and so on.

S2015: Project the traffic information to a corresponding position in the preset map under the bird's-eye view angle to obtain a scene map.

The scene map can be saved in the form of a picture, and different traffic information on the scene map can be expressed in different colors, for example, the lane information can be expressed in dark red, and the crosswalk information can be expressed in light green.

S203: Obtain the historical trajectory of obstacles within a certain range of the vehicle in the area.

The obstacles in the embodiments of the present application may be motor vehicles, non-motor vehicles and pedestrians.

In an optional implementation manner, FIG. 4 may represent a specific example of a method for predicting the future trajectory of an obstacle in the present application. In this manner, the step of S203 may be represented by the following content:

S2031: Acquire historical position information of obstacles at multiple consecutive time points in the area through the sensor.

In the embodiment of the present application, the sensor includes one or more of a camera, a lidar, and a millimeter-wave radar, and the sensor can be arranged around the vehicle to obtain the trajectory of obstacles within a certain range of the vehicle.

其中，t＝1...t_obs。Since there may be multiple obstacles within a certain range of the vehicle, the motion trajectory of each obstacle can be represented as a series of historical positions of multiple consecutive time points

where t=1...t _obs .

S2033: splicing the historical location information of multiple consecutive time points to obtain a historical track.

S205: Project the historical track to a corresponding position of the scene map, and obtain a scene map to be predicted including the historical track.

The server projects the historical track to the corresponding position of the scene map, and the track track can be displayed in the scene map in a certain color, so as to obtain the scene map to be predicted including the historical track.

S207: Input the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle.

Among them, the trajectory prediction model is a machine learning model, and machine learning (ML) is a multi-domain interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in how computers simulate or realize human learning behaviors to acquire new knowledge or skills, and to reorganize existing knowledge structures to continuously improve their performance. Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications are in all fields of artificial intelligence. Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning, teaching learning and other technologies. Machine learning can be divided into supervised machine learning, unsupervised machine learning and semi-supervised machine learning. Optionally, the trajectory prediction model may use a convolutional neural network or other neural network structure with similar functions, and perform training, verification, and testing of the network model for data acquisition as required.

The following describes how to train a trajectory prediction model based on a supervised machine learning, as shown in Figure 5, including:

S501: Obtain a sample data set, where the sample data set includes a plurality of training scene maps and an actual future trajectory corresponding to each training scene map; each training scene map includes a training historical trajectory;

Since the training historical trajectories in the scene map come from different times, the pixel color is also used to distinguish the historical time. It can be understood that the closer the time to the current state, the brighter the color, and the darker the color of the state that is about farther away.

S503: Build a preset machine learning model, and determine the preset machine learning model as the current machine learning model;

S505: Based on the current machine learning model, perform a trajectory prediction operation on the training scene map, and determine the predicted future trajectory corresponding to the training scene map;

S507: Determine the loss value based on the predicted future trajectory and the actual future trajectory corresponding to the training scene map;

S509: determine whether the loss value is greater than the preset threshold, if so, go to step S511; otherwise, go to step S513;

S511: Back-propagating based on the loss value, updating the current machine learning model to obtain the updated machine learning model, and re-determining the updated machine learning model as the current machine learning model; then, go to step S505;

S513: Determine the current machine learning model as the trajectory prediction model.

The sample data set in the embodiment of the present application may be stored in a certain storage area, and the storage area may be a blockchain. Among them, blockchain is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

The underlying platform of the blockchain can include processing modules such as user management, basic services, smart contracts, and operation monitoring. Among them, the user management module is responsible for the identity information management of all blockchain participants, including maintenance of public and private key generation (account management), key management, and maintenance of the corresponding relationship between the user's real identity and blockchain address (authority management), etc. When authorized, supervise and audit the transactions of some real identities, and provide rule configuration for risk control (risk control audit); the basic service module is deployed on all blockchain node devices to verify the validity of business requests, After completing the consensus on valid requests, record them in the storage. For a new business request, the basic service first adapts the interface for analysis and authentication processing (interface adaptation), and then encrypts the business information through the consensus algorithm (consensus management), After encryption, it is completely and consistently transmitted to the shared ledger (network communication), and records are stored; the smart contract module is responsible for the registration and issuance of contracts, as well as contract triggering and contract execution. Developers can define contract logic through a programming language and publish to On the blockchain (contract registration), according to the logic of the contract terms, call the key or other events to trigger execution, complete the contract logic, and also provide the function of contract upgrade and cancellation; the operation monitoring module is mainly responsible for the deployment in the product release process , configuration modification, contract settings, cloud adaptation, and visual output of real-time status in product operation, such as: alarms, monitoring network conditions, monitoring node equipment health status, etc. The platform product service layer provides the basic capabilities and implementation framework of typical applications. Based on these basic capabilities, developers can superimpose business characteristics to complete the blockchain implementation of business logic. The application service layer provides application services based on blockchain solutions for business participants to use.

Optionally, the trajectory prediction model is a model of a neural convolutional network model CNN, including an input layer, multiple convolutional layers, multiple pooling layers, a fully connected layer, and an output layer.

In an optional implementation manner, multiple convolution layers, multiple pooling layers and fully connected layers are connected in series, and multiple convolution layers and multiple pooling layers are arranged at intervals.

In another optional embodiment, it may also include multiple mixing layers, and multiple mixing layers may be composed of multiple branches in parallel, multiple convolution layers, multiple pooling layers, multiple mixing layers, and fully connected layers. Layers are connected in series.

For example, suppose the structure of the joint model graph is input layer, attention mechanism layer, first convolutional layer, first pooling layer, second convolutional layer, second pooling layer... fully connected layer and output layer, the output layer includes the Softmax classification module.

In an optional embodiment, after the vehicle obtains the future trajectory of the obstacle, the future trajectory can also be displayed in the scene map to be predicted, and the scene map to be predicted can be displayed on the display screen of the vehicle, so that the vehicle can Avoid obstacles based on future trajectories.

The above-mentioned embodiments can be applied in various traffic scenarios, for example, in traffic intersections.

An embodiment of the present application also provides a device for predicting a future trajectory of an obstacle. FIG. 6 is a schematic structural diagram of a device for predicting a future trajectory of an obstacle provided by an embodiment of the present application. As shown in FIG. 6 , the device includes:

The first obtaining module 601 is used to obtain a scene map corresponding to the area where the vehicle is located; wherein, the scene map includes the traffic information of the area;

The second acquisition module 602 is used to acquire the historical trajectory of obstacles within a certain range of the vehicle in the area;

The projection module 603 is used for projecting the historical track to the corresponding position of the scene map to obtain the scene map to be predicted containing the historical track;

The prediction module 604 is configured to input the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle.

In an optional embodiment, the device further includes:

The second determining module is specifically configured to obtain historical position information of obstacles at multiple consecutive time points in the area through the sensor; and splicing the historical position information of the multiple continuous time points to obtain a historical trajectory.

In an optional embodiment, the apparatus further includes a model training module for:

Obtain a sample data set, where the sample data set includes multiple training scene maps and the actual future trajectory corresponding to each training scene map; each training scene map includes a training historical trajectory;

Build a preset machine learning model, and determine the preset machine learning model as the current machine learning model;

Based on the current machine learning model, the trajectory prediction operation is performed on the training scene map, and the predicted future trajectory corresponding to the training scene map is determined;

Determine the loss value based on the predicted future trajectory and the actual future trajectory corresponding to the training scene map;

When the loss value is greater than the preset threshold, backpropagation is performed based on the loss value, the current machine learning model is updated to obtain the updated machine learning model, and the updated machine learning model is re-determined as the current machine learning model; repeat the steps : Based on the current machine learning model, perform trajectory prediction operation on the training scene map, and determine the predicted future trajectory corresponding to the training scene map;

When the loss value is less than or equal to the preset threshold, the current machine learning model is determined as the trajectory prediction model.

In an optional implementation manner, the first acquisition module is used for:

determine the area in which the vehicle is located;

Obtain the traffic information within the preset range of the vehicle based on the high-precision map corresponding to the area;

Project the traffic information to the corresponding position in the preset map under the overlook angle to obtain the scene map.

In an optional implementation manner, the device further includes a display module for:

Display the future trajectory in the scene map to be predicted, and display the scene map to be predicted, so that the vehicle can avoid obstacles according to the future trajectory.

The apparatus and method embodiments in the embodiments of the present application are based on the same concept of the application.

The method embodiments provided by the embodiments of the present application may be executed in a computer terminal, a server, or a similar computing device. Taking running on a server as an example, FIG. 7 is a hardware structural block diagram of a server of a method for predicting a future trajectory of an obstacle provided by an embodiment of the present application. As shown in FIG. 7 , the server 700 may vary greatly due to different configurations or performances, and may include one or more central processing units (Central Processing Units, CPUs) 710 (the processors 710 may include but are not limited to microprocessors) MCU or programmable logic device FPGA, etc.), memory 730 for storing data, one or more storage media 720 (eg, one or more mass storage devices) storing application programs 723 or data 722. Among them, the memory 730 and the storage medium 720 may be short-term storage or persistent storage. The program stored in the storage medium 720 may include one or more modules, and each module may include a series of instructions to operate on the server. Furthermore, the central processing unit 710 may be configured to communicate with the storage medium 720 to execute a series of instruction operations in the storage medium 720 on the server 700 . Server 700 may also include one or more power supplies 760, one or more wired or wireless network interfaces 750, one or more input and output interfaces 740, and/or, one or more operating systems 721, such as Windows Server™, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM and so on.

Input-output interface 740 may be used to receive or transmit data via a network. The specific example of the above-mentioned network may include a wireless network provided by the communication provider of the server 700 . In one example, the I/O interface 740 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through the base station so as to communicate with the Internet. In one example, the input/output interface 740 may be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet in a wireless manner.

Those of ordinary skill in the art can understand that the structure shown in FIG. 7 is only a schematic diagram, which does not limit the structure of the above-mentioned electronic device. For example, server 700 may also include more or fewer components than shown in FIG. 7 , or have a different configuration than that shown in FIG. 7 .

Embodiments of the present application further provide a storage medium, where the storage medium can be set in a server to store at least one instruction and at least one piece of program related to implementing a method for predicting a future trajectory of an obstacle in the method embodiment , a code set or an instruction set, the at least one instruction, the at least one piece of program, the code set or the instruction set is loaded and executed by the processor to implement the above method for predicting the future trajectory of an obstacle.

Optionally, in this embodiment, the above-mentioned storage medium may be located in at least one network server among multiple network servers of a computer network. Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic Various media that can store program codes, such as discs or optical discs.

It can be seen from the above-mentioned embodiments of the method, device or storage medium for predicting the future trajectory of an obstacle provided in the present application that in the present application, the scene map corresponding to the area where the vehicle is located is obtained; The historical trajectory of the obstacles in the area, project the historical trajectory to the corresponding position of the scene map, obtain the scene map to be predicted including the historical trajectory, input the scene map to be predicted into the trained trajectory prediction model, get The future trajectory of the obstacle. In this way, the accuracy of future trajectory prediction of obstacles can be improved by introducing a scene map and a trajectory prediction model.

It should be noted that: the above-mentioned order of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference may be made to the partial descriptions of the method embodiments for related parts.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above embodiments can be completed by hardware, or can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, etc.

The above descriptions are only preferred embodiments of the present application, and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection of the present application. within the range.

Claims (10)

1. a prediction method of obstacle future trajectory, is characterized in that, described method comprises: Obtain a scene map corresponding to the area where the vehicle is located; wherein, the scene map includes the traffic information of the area; Obtain the historical trajectory of obstacles within a certain range of the vehicle in the area; Projecting the historical track to a corresponding position of the scene map to obtain a scene map to be predicted containing the historical track; Input the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle. 2. The method according to claim 1, wherein the method further comprises the step of obtaining the trajectory prediction model by training; The trajectory prediction model obtained by the training includes: Obtaining a sample data set, the sample data set includes a plurality of training scene maps and an actual future trajectory corresponding to each of the training scene maps; each training scene map includes a training historical trajectory; constructing a preset machine learning model, and determining the preset machine learning model as the current machine learning model; Based on the current machine learning model, a trajectory prediction operation is performed on the training scene map, and a predicted future trajectory corresponding to the training scene map is determined; determining a loss value based on the predicted future trajectory and the actual future trajectory corresponding to the training scene map; When the loss value is greater than a preset threshold, backpropagation is performed based on the loss value, the current machine learning model is updated to obtain an updated machine learning model, and the updated machine learning model is re-determined is the current machine learning model; repeating the steps: based on the current machine learning model, perform a trajectory prediction operation on the training scene map, and determine the predicted future trajectory corresponding to the training scene map; When the loss value is less than or equal to the preset threshold, the current machine learning model is determined as the trajectory prediction model. 3. The method according to claim 1, wherein the traffic information comprises: lane information, lane centerline information, pedestrian crossing information, traffic light information and stop line information. 4 . The method according to claim 1 , wherein the acquiring the historical trajectory of obstacles within a certain range of the vehicle in the area comprises: 5 . Acquiring historical position information of the obstacle at multiple consecutive time points in the area through a sensor; The historical track is obtained by splicing the historical position information of the multiple consecutive time points; Wherein, the sensor includes one or more of a camera, a lidar, and a millimeter-wave radar. 5. The method according to claim 1, wherein the acquiring the scene map corresponding to the area where the vehicle is located comprises: determine the area in which the vehicle is located; Obtain traffic information within the preset range of the vehicle based on the high-precision map corresponding to the area; Projecting the traffic information to a corresponding position in a preset map from an overlook angle to obtain the scene map. 6. The method according to claim 1, wherein after obtaining the future trajectory of the obstacle, further comprising: The future trajectory is displayed in the scene map to be predicted, and the scene map to be predicted is displayed, so that the vehicle avoids the obstacle according to the future trajectory. 7. A device for predicting a future trajectory of an obstacle, wherein the device comprises: a first obtaining module, configured to obtain a scene map corresponding to the area where the vehicle is located; wherein, the scene map includes traffic information of the area; a second acquisition module, configured to acquire the historical trajectory of obstacles within a certain range of the vehicle in the area; a projection module, configured to project the historical track to a corresponding position of the scene map to obtain a scene map to be predicted that includes the historical track; The prediction module is used for inputting the scene map to be predicted into the trained trajectory prediction model to obtain the future trajectory of the obstacle. 8. The device according to claim 7, wherein the second acquisition module is specifically used for: Acquiring historical position information of the obstacle at multiple consecutive time points in the area through a sensor; The historical track is obtained by splicing the historical location information of the multiple consecutive time points. 9. An electronic device, characterized in that the electronic device comprises a processor and a memory, and the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is processed by the The controller loads and executes the method for predicting the future trajectory of an obstacle according to any one of claims 1-6. 10. A computer storage medium, characterized in that, at least one instruction or at least one program is stored in the computer storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to realize the method as claimed in claim 1- 6. Any one of the methods for predicting the future trajectory of an obstacle.

Images