Vehicle trajectory estimation method, device, computer equipment and storage medium

Abstract

The present application relates to a vehicle trajectory estimation method, device, computer equipment and storage medium. The method includes: determining the target parking position of the target vehicle on the target road section according to the terminal traffic state of the target road section and the queue sequence of the target vehicle; determining the distance to be traveled of the target vehicle according to the target parking position, adjusting the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain the adjusted driving speed, and updating the distance to be traveled according to the adjusted driving speed to obtain the updated distance to be traveled, and determining the driving trajectory point of the target vehicle according to the updated distance to be traveled; iteratively calculating the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target road section; determining the target driving trajectory of the target vehicle according to each driving trajectory point, and the method can accurately realize the estimation of the vehicle trajectory with high reliability.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a vehicle trajectory estimation method, apparatus, computer equipment and storage medium. Background Art

[0002] With the development of science and technology, the number of vehicles on the road has also increased. In order to manage and control road traffic more effectively, artificial intelligence technology can be used to predict the driving trajectory of vehicles on the road.

[0003] Existing technologies can reconstruct vehicle trajectories by collecting road-related parameters and connected vehicle driving data. However, traditional vehicle trajectory reconstruction methods are not applicable in blind spots where road-related parameters cannot be obtained. Existing technologies have low accuracy and reliability in estimating the trajectories of vehicles traveling on the entire road. Summary of the invention

[0004] Based on this, it is necessary to provide a vehicle trajectory estimation method, device, computer equipment and storage medium that can be more accurate and reliable in order to solve the above technical problems.

[0005] In a first aspect, the present application provides a vehicle trajectory estimation method, comprising:

[0006] Determine the target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle;

[0007] Determine the distance to be traveled of the target vehicle according to the target parking position, adjust the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed, update the distance to be traveled according to the adjusted travel speed to obtain an updated distance to be traveled, and determine the travel trajectory point of the target vehicle according to the updated distance to be traveled;

[0008] Iteratively calculate the updated distance to be traveled until the travel trajectory point corresponding to the updated distance to be traveled is outside the target road section;

[0009] The target driving trajectory of the target vehicle is determined according to each driving trajectory point.

[0010] In one embodiment, determining a target parking position of a target vehicle on a target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle includes:

[0011] Judging whether the target vehicle is the first vehicle on the target road section according to the queue sequence, and obtaining a judgment result;

[0012] The target parking position is determined according to the terminal traffic status and the judgment result.

[0013] In one embodiment, determining the target parking position according to the terminal traffic status and the judgment result includes:

[0014] If the destination traffic status is allowed and the target vehicle is the first vehicle on the target road section, the target parking position is determined according to the road section length of the target road section;

[0015] If the destination traffic status is prohibited and the target vehicle is not the first vehicle on the target road section, the target parking position is determined according to the position of the vehicle preceding the target vehicle;

[0016] If the terminal traffic status is allowed and the target vehicle is not the first vehicle on the target road section, the target parking position is determined according to the number of vehicles ahead of the target vehicle.

[0017] In one embodiment, determining a target parking position according to the number of vehicles ahead of the target vehicle includes:

[0018] Obtain the initial number of vehicles entering the target road section at the initial time and the current number of vehicles leaving the target road section at the current time, and determine the number of vehicles ahead according to the initial number of vehicles entering the target road section and the current number of vehicles leaving the target road section;

[0019] The target parking position is determined based on the length of the target road section and the number of vehicles ahead.

[0020] In one embodiment, adjusting the travel speed of the target vehicle according to the distance to be traveled to obtain the adjusted travel speed includes:

[0021] Obtain the current speed and speed prediction model of the target vehicle;

[0022] The current speed and the distance to be traveled are input into a speed prediction model to obtain an adjusted travel speed, wherein the speed prediction model is trained based on historical vehicle travel trajectories of the target road section.

[0023] In one embodiment, the method further comprises:

[0024] Obtain the driving trajectory of the preceding vehicle of the target vehicle in the target road section;

[0025] Obtain an intelligent driving model, and determine the predicted driving trajectory of the target vehicle on the target road section based on the driving trajectory of the preceding vehicle and the intelligent driving model;

[0026] The target driving trajectory and the predicted driving trajectory are combined to obtain the output driving trajectory.

[0027] In one embodiment, the preceding vehicle driving trajectory includes the preceding vehicle speed and the preceding vehicle position, and determining the predicted driving trajectory of the target vehicle on the target road section according to the preceding vehicle driving trajectory and the intelligent driving model includes:

[0028] Obtain the driving speed and vehicle position of the target vehicle at any time, and determine the speed and position of the preceding vehicle at any time according to the preceding vehicle's driving trajectory;

[0029] The driving speed, vehicle position, front vehicle speed and front vehicle position are input into the intelligent driving model to obtain the acceleration of the target vehicle;

[0030] The vehicle-to-vehicle distance between the target vehicle and the preceding vehicle is determined based on the acceleration, and the predicted driving trajectory is obtained based on the vehicle-to-vehicle distance.

[0031] In one embodiment, combining the target driving trajectory and the predicted driving trajectory to obtain an output driving trajectory includes:

[0032] The target driving trajectory and the predicted driving trajectory are fused based on the particle filtering method, and the fused driving trajectory is used as the output driving trajectory.

[0033] In a second aspect, the present application also provides a vehicle trajectory estimation device, comprising:

[0034] A parking position determination module is used to determine a target parking position of a target vehicle on a target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle;

[0035] A driving speed prediction module is used to determine the distance to be traveled of the target vehicle according to the target parking position, adjust the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain the adjusted driving speed, update the distance to be traveled according to the adjusted driving speed to obtain the updated distance to be traveled, and determine the driving trajectory point of the target vehicle according to the updated distance to be traveled;

[0036] A driving trajectory iterative calculation module, used for iteratively calculating the updated distance to be traveled, until the driving trajectory point corresponding to the updated distance to be traveled is outside the target road section;

[0037] The target driving trajectory determination module is used to determine the target driving trajectory of the target vehicle according to each driving trajectory point.

[0038] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Determine the target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle;

[0040] Determine the distance to be traveled of the target vehicle according to the target parking position, adjust the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed, update the distance to be traveled according to the adjusted travel speed to obtain an updated distance to be traveled, and determine the travel trajectory point of the target vehicle according to the updated distance to be traveled;

[0041] Iteratively calculate the updated distance to be traveled until the travel trajectory point corresponding to the updated distance to be traveled is outside the target road section;

[0042] The target driving trajectory of the target vehicle is determined according to each driving trajectory point.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Determine the target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle;

[0045] Determine the distance to be traveled of the target vehicle according to the target parking position, adjust the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed, update the distance to be traveled according to the adjusted travel speed to obtain an updated distance to be traveled, and determine the travel trajectory point of the target vehicle according to the updated distance to be traveled;

[0046] Iteratively calculate the updated distance to be traveled until the travel trajectory point corresponding to the updated distance to be traveled is outside the target road section;

[0047] The target driving trajectory of the target vehicle is determined according to each driving trajectory point.

[0048] The above-mentioned vehicle trajectory estimation method, device, computer equipment and storage medium determine the target parking position of the target vehicle on the target section according to the terminal traffic status of the target section and the queuing sequence of the target vehicles; determine the distance to be traveled of the target vehicle according to the target parking position, adjust the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain the adjusted driving speed, and update the distance to be traveled according to the adjusted driving speed to obtain the updated distance to be traveled, and determine the driving trajectory point of the target vehicle according to the updated distance to be traveled; iteratively calculate the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target section; and determine the target driving trajectory of the target vehicle according to each driving trajectory point. The present application estimates the target parking position of the target vehicle on the target road section based on the traffic status of the target road section and the queue sequence of the target vehicle, and dynamically adjusts the driving speed of the target vehicle according to the distance relationship between the target vehicle and the target parking position and the real-time driving speed of the target vehicle, and finally realizes the real-time estimation of the driving trajectory of the target vehicle on the target road section. It has been verified that the vehicle trajectory estimated by the present application has high accuracy and small error. The vehicle driving trajectory estimated by the present application almost coincides with the actual driving trajectory of the target vehicle, and has strong reliability. In addition, the vehicle trajectory method of the present application does not need to collect complex data on the target road section, and can realize accurate estimation of the driving trajectory of the target vehicle, with low cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are 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 creative work.

[0050] Figure 1 A diagram showing an application environment of a vehicle trajectory estimation method in one embodiment;

[0051] Figure 2 A schematic diagram of a process flow of a vehicle trajectory estimation method in one embodiment;

[0052] Figure 3 A schematic diagram of a process for determining a target parking position in one embodiment;

[0053] Figure 4 is a flow chart of a vehicle trajectory estimation method in another embodiment;

[0054] Figure 5 A schematic diagram of a target driving trajectory in an embodiment;

[0055] Figure 6is a structural block diagram of a vehicle trajectory estimation device in one embodiment;

[0056] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] The vehicle trajectory estimation method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 determines the target parking position of the target vehicle on the target section according to the terminal traffic status of the target section and the queuing sequence of the target vehicle; determines the distance to be traveled of the target vehicle according to the target parking position, adjusts the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle, obtains the adjusted driving speed, and updates the distance to be traveled according to the adjusted driving speed to obtain the updated distance to be traveled, and determines the driving trajectory point of the target vehicle according to the updated distance to be traveled; iteratively calculates the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target section; determines the target driving trajectory of the target vehicle according to each driving trajectory point.

[0059] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0060] In an exemplary embodiment, Figure 2 As shown, a vehicle trajectory estimation method is provided, which is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps 202 to 206. Among them:

[0061] Step 202, determining a target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle.

[0062] The target road section represents the road section used for vehicle trajectory estimation, and the target road section can be distinguished by a road section identifier, which can be a road section name, road section ID, etc. The target road section includes two ends. For the convenience of description, this embodiment takes the vehicle's driving direction as the positive direction, defines the port where the vehicle enters the target road section as the starting point of the target road section, and defines the port where the vehicle exits the target road section as the end point of the target road section.

[0063] The terminal traffic state of the target section is used to characterize whether the target section is passable. If the terminal traffic state is in the allowed state, it means that the vehicles on the target section can drive out of the target section normally. If the terminal traffic state is in the prohibited state, it means that the vehicles on the target section cannot drive out of the target section normally and need to wait for the terminal traffic state to be allowed. The terminal traffic state is associated with a time parameter. For example, the terminal traffic state of the target section can be in the prohibited state at the first moment and in the terminal traffic state at the second moment. The first moment and the second moment can be consecutive moments or have no association.

[0064] Exemplarily, the terminal traffic state can be determined by the signal mark at the end of the road section, or by the state of the vehicle in the road section. Taking the signal mark as a traffic light as an example, when the traffic light is red, it means that the terminal traffic state of the road section is prohibited; when the traffic light is green, it means that the terminal traffic state of the road section is allowed; when the traffic light is yellow, it can be said that the terminal traffic state of the road section is allowed or prohibited. If the terminal traffic state of the target road section is determined by the state of the vehicle in the road section, the speed of the vehicle in the road section can be judged. When the vehicle speed is less than the speed threshold, the terminal traffic state of the road section can be considered to be prohibited. When the vehicle speed is not less than the speed threshold, the terminal traffic state of the road section can be considered to be allowed.

[0065] The queue sequence of the target vehicle is used to characterize the position of the target vehicle in the target section, that is, the position of the target vehicle in the fleet in the target section. In this embodiment, the number of vehicles in front of the target vehicle is determined by the queue sequence of the target vehicle. Further, when the number of vehicles in front of the target vehicle is zero, the target vehicle is determined to be the first vehicle in the target section. When a vehicle is traveling on a section, the driving speed of the vehicle is affected not only by the traffic status at the end of the section, but also by the driving status of the preceding vehicle, such as the speed of the preceding vehicle. In this embodiment, the number of vehicles in front of the target vehicle is determined by the queue sequence, so that the speed of the target vehicle can be estimated and predicted more accurately, thereby obtaining a more accurate driving trajectory.

[0066] For example, the queue sequence can be directly acquired by setting an image acquisition device, or can be calculated by using data acquisition devices at both ends of the target road section. For example, fixed detectors are set at both ends of the target road section to collect the total number of vehicles traveling on the target road section and the number of vehicles behind the target vehicle, and then the number of vehicles in front of the target vehicle is obtained through data calculation, thereby determining the queue sequence of the target vehicle on the target road section.

[0067] The target parking position is used to characterize the parking position of the target vehicle in the target section. Generally speaking, it can be considered that the target vehicle will maintain a uniform and constant speed while traveling in the target section. However, due to the change of the terminal traffic state of the target section, the driving speed of the target vehicle also changes accordingly. Therefore, the present embodiment predicts the target parking position that the target vehicle may appear in the target section according to the terminal traffic state of the target section and the queue sequence of the target vehicle, and then estimates the driving speed of the target vehicle, so as to achieve the estimation of the driving trajectory of the target vehicle.

[0068] Step 204, determining the distance to be traveled of the target vehicle according to the target parking position, adjusting the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed, and updating the distance to be traveled according to the adjusted travel speed to obtain an updated distance to be traveled; determining the travel trajectory point of the target vehicle according to the updated distance to be traveled.

[0069] Among them, the distance to be traveled represents the distance that the target vehicle needs to travel before parking, and the analysis of the driving trajectory of the target vehicle is realized by analyzing the distance to be traveled. When the target parking position is determined, the distance to be traveled can be obtained by calculating the distance between the initial position of the target vehicle and the target parking position. The current speed represents the driving speed of the vehicle at the current moment. The driving trajectory point is a trajectory point determined according to the driving distance of the target vehicle. By connecting all the driving trajectory points, the driving trajectory of the target vehicle can be obtained. Exemplarily, the target vehicle is currently traveling at a speed V on the target section, and it is expected to stop at point A of the target section according to the above steps. The driving speed of the target vehicle at the next moment is adjusted according to the distance between the current position of the target vehicle and the parking point A and the current speed V, and then the distance between the target vehicle and the parking point A at the next moment is updated in real time according to the adjusted driving speed at the next moment. This distance is the updated distance to be traveled, and the driving trajectory point of the target vehicle can be determined according to the updated distance to be traveled.

[0070] Step 206, iteratively calculating the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target road section.

[0071] The iterative calculation of the target vehicle's travel speed is stopped when the travel trajectory point is outside the target section. When the travel trajectory point is outside the target section, it indicates that the target vehicle has left the target section. In this embodiment, only the travel trajectory of the target section vehicle is predicted, and the iterative prediction is stopped after the target vehicle leaves the target section.

[0072] Step 208, determining the target driving trajectory of the target vehicle according to each driving trajectory point.

[0073] By connecting the driving trajectory points obtained by iterative calculation, the target driving trajectory of the target vehicle on the target road section can be obtained.

[0074] It should be noted that the present embodiment may determine multiple target parking positions for the target vehicle on the target section, that is, the target vehicle may experience multiple stops on the target section, that is, the target parking position of the present embodiment is also updated in real time while the target vehicle iteratively calculates the distance to be traveled and the driving speed, and the specific number of stops is determined according to the driving status of the target vehicle in the application scenario.

[0075] In the above vehicle trajectory estimation method, according to the terminal traffic state of the target road section and the queue sequence of the target vehicle, the target parking position of the target vehicle in the target road section is determined; according to the target parking position, the distance to be traveled of the target vehicle is determined, and the driving speed of the target vehicle is adjusted according to the distance to be traveled and the current speed of the target vehicle to obtain the adjusted driving speed, and the distance to be traveled is updated according to the adjusted driving speed to obtain the updated distance to be traveled, and the driving trajectory point of the target vehicle is determined according to the updated distance to be traveled; iteratively calculate the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target road section; determine the target driving trajectory of the target vehicle according to each driving trajectory point. The present application predicts the target parking position of the target vehicle in the target road section based on the traffic state of the target road section and the queue sequence of the target vehicle, and dynamically adjusts the driving speed of the target vehicle according to the distance relationship between the target vehicle and the target parking position and the real-time driving speed of the target vehicle, and finally realizes the real-time estimation of the driving trajectory of the target vehicle in the target road section. It has been verified that the vehicle trajectory estimated by the present application has high accuracy and small error, and the vehicle driving trajectory estimated by the present application almost coincides with the actual driving trajectory of the target vehicle, and has strong reliability. In addition, the vehicle trajectory method of the present application can achieve accurate estimation of the target vehicle's driving trajectory without collecting complex data on the target road section, and the cost is low.

[0076] In one embodiment, Figure 3As shown, according to the terminal traffic state of the target road section and the queue sequence of the target vehicle, determining the target parking position of the target vehicle on the target road section includes steps 302 to 304. Among them:

[0077] Step 302, judging whether the target vehicle is the first vehicle of the target road section according to the queuing sequence, and obtaining a judgment result.

[0078] Among them, the judgment result is used to characterize whether the target vehicle is the first vehicle of the target section. The first vehicle of the target section is the first vehicle traveling on the target section. When the target vehicle is the first vehicle of the target section, the driving state of the target vehicle is independent of the driving states of other vehicles and can be regarded as only the target vehicle on the target section. When the target vehicle is not the first vehicle of the target section, the driving state of the target vehicle needs to be associated with the driving state of the vehicle in front of the target vehicle. Therefore, when determining the target parking position, this embodiment first determines whether the target vehicle is the first vehicle of the target section.

[0079] The first vehicle on the target section can be determined by acquiring an image of the target section and further analyzing the image; it can also be determined by performing mathematical operations on the number of vehicles traveling on the target section, such as collecting the number of vehicles ahead of the target vehicle before it enters the target section and the number of vehicles exiting the target section. If the number of vehicles entering and exiting the target section before the target vehicle is equal, the target vehicle can be considered to be the first vehicle on the target section.

[0080] It should be noted that in actual applications, other methods can be used to determine whether the target vehicle is the first vehicle on the target section. This embodiment has no limitation on the judgment method, as long as it can be used to determine whether the target vehicle is the first vehicle on the target section.

[0081] Step 304, determining the target parking position according to the terminal traffic status and the judgment result.

[0082] As can be seen from the above examples, the terminal passable state of the target road section is used to indicate whether the target road section is passable. In this embodiment, whether the target road section is passable and whether the target vehicle is the first vehicle on the target road section are combined to determine the target parking position.

[0083] Further analysis shows that if the target vehicle is the first vehicle traveling on the target section, the target vehicle will stop when it reaches the end of the target section and the traffic status at the end is prohibited, and the target vehicle can pass smoothly when the traffic status at the end is allowed; if the target vehicle is not the first vehicle traveling on the target section, the target parking position of the target vehicle can be determined by the position of the vehicle preceding the target vehicle, and the position of the vehicle preceding the vehicle can be repeatedly determined based on the position of the vehicle preceding the vehicle until the vehicle preceding the vehicle becomes the first vehicle on the section.

[0084] In one embodiment, the target parking position is determined according to the terminal traffic status and the judgment result, including: if the terminal traffic status is an allowed state and the target vehicle is the first vehicle of the target section, the target parking position is determined according to the section length of the target section; if the terminal traffic status is a prohibited state and the target vehicle is not the first vehicle of the target section, the target parking position is determined according to the position of the vehicle in front of the target vehicle; if the terminal traffic status is an allowed state and the target vehicle is not the first vehicle of the target section, the target parking position is determined according to the number of vehicles in front of the target vehicle.

[0085] For example, if the destination traffic status is allowed and the target vehicle is the first vehicle on the target road section, it can be considered that the target parking position is not within the range of the target road section, and the target parking position is determined based on the road section length of the target road section. In this case, the target parking position is represented by Q i It can be expressed as:

[0086]

[0087] Wherein, L represents the length of the target road section, and 50 is an adjustable parameter, which means that the target vehicle can smoothly drive out of the target road section and will not stop on the target road section.

[0088] If the destination traffic status is prohibited and the target vehicle is not the first vehicle on the target road section, the target parking position is related to the position of the vehicle in front of the target vehicle. At this time, the target parking position Q i It can be expressed as:

[0089]

[0090] Among them, Q i-1 (t) represents the parking position of the front vehicle, d0 represents the distance between the vehicles when stationary, which can be the distance between the front ends of the vehicles, the distance between the rear ends of the vehicles, etc. In this embodiment, d0 can be set to 7.5m.

[0091] If the terminal traffic status is allowed and the target vehicle is not the first vehicle on the target road section, the target parking position changes dynamically according to the number of vehicles in front of the target vehicle. The distance from the target vehicle to the end of the target road section is proportional to the number of vehicles in front. When the vehicles in front of the target vehicle exit the target road section one after another, the target parking distance of the target vehicle is also adjusted accordingly. At this time, the target parking position Q i It can be expressed as:

[0092]

[0093] Among them, Ni front (t) represents the number of vehicles in front of the target vehicle.

[0094] Combining the above three situations, the target parking position Q i It can be expressed as:

[0095]

[0096] in, represents the position of the target vehicle at time t, represents the speed of the target vehicle at time t, represents the speed of the target vehicle at time t-1, Indicates the state of traffic lights as signal indicators. It means the traffic light is green, which means the destination is allowed to pass.

[0097] It should be noted that the description of the number of vehicles in front of or behind the target vehicle in this embodiment is based on the target road section, which refers to the vehicles that are still traveling on the target road section. Vehicles that have left the target road section or have not yet entered the target road section are not within the range of the number of vehicles in front of or behind the target vehicle.

[0098] In an exemplary embodiment, a target parking position is determined based on the number of vehicles ahead of a target vehicle, including: obtaining an initial number of vehicles entering a target road section at an initial moment and a current number of vehicles leaving a target road section at a current moment, and determining the number of vehicles ahead based on the initial number of vehicles entering and the current number of vehicles leaving the target road section; and determining the target parking position based on the length of the target road section and the number of vehicles ahead.

[0099] The number of vehicles ahead can be calculated by collecting the initial number of vehicles entering the target section and the current number of vehicles leaving the target section. First, the cumulative number of vehicles on the target section is determined based on the number of vehicles entering and leaving the target section. The cumulative number of vehicles on the target section N(t) is expressed as:

[0100]

[0101] in, and are the number of vehicles entering and exiting the target road section respectively, and the number of vehicles can be obtained by a fixed detector.

[0102] The number of vehicles behind the target vehicle Ni behind(t) is expressed as:

[0103]

[0104] in, It indicates the number of vehicles entering the road section at time t0. Time t0 can be considered as the initial time when the target vehicle enters the target road section.

[0105] In summary, the number of vehicles ahead of the target vehicle Ni front(t) can be expressed as:

[0106] This embodiment only requires fixed detection equipment at both ends of the target road section. By calculating the initial number of vehicles entering the target road section at the initial moment and the current initial number at the current moment, the parking position of the target vehicle in the target road section can be determined. The data source is simple and does not require a complicated data collection process. It can be applied to any road section where detection equipment is not deployed in the middle of the road section. It has good adaptability, high reliability and low cost.

[0107] In one embodiment, the driving speed of the target vehicle is adjusted according to the distance to be traveled to obtain the adjusted driving speed, including: obtaining the current speed and a speed prediction model of the target vehicle; inputting the current speed and the distance to be traveled into the speed prediction model to obtain the adjusted driving speed, wherein the speed prediction model is trained according to the historical vehicle driving trajectory of the target section.

[0108] Since the running trajectories of vehicles on the same road section roughly present similar changing characteristics, the trajectory of the vehicle can be estimated by a speed prediction model. The speed prediction model can be obtained by collecting historical vehicle driving trajectories and training based on the historical vehicle driving trajectories.

[0109] Optionally, the historical vehicle driving trajectory can be obtained by setting up a networked vehicle on the target road section and collecting the vehicle trajectory of the networked vehicle. A networked vehicle refers to a vehicle that connects and interacts with the Internet, other vehicles or devices through vehicle-mounted communication technology. The networked vehicle can realize information sharing and intelligent traffic management between vehicles. The speed prediction model can be obtained based on the training of the long short-term memory (LSTM) neural network, or it can be obtained based on other neural network training. This embodiment has no restrictions on the training network of the model.

[0110] Taking LSTM network training as an example, the input parameters of LSTM are the current speed and the distance to be traveled of the target vehicle, which are expressed as:

[0111]

[0112] in, represents the speed of the target vehicle at time t, It refers to the position x of the target vehicle at time t. i (t) and the target parking position Q i The distance between At the beginning of the prediction, that is, the initial position of the target vehicle, It is expressed as:

[0113]

[0114] Using the historical connected vehicle trajectories as training data, we can build an LSTM model to predict the speed of the next time step, which can be expressed as:

[0115]

[0116] When the speed prediction model predicts the speed of the target vehicle at the next moment, that is, the adjusted driving speed, the position of the vehicle is updated according to the adjusted driving speed, and then the distance to be traveled of the vehicle is updated. It is related to the position at the previous moment and the speed at the current moment, expressed as:

[0117]

[0118] in, Indicates the position of the target vehicle at the last moment.

[0119] In one embodiment, the method further includes: obtaining a preceding vehicle driving trajectory of the target vehicle in the target section; obtaining an intelligent driving model, and determining a predicted driving trajectory of the target vehicle in the target section based on the preceding vehicle driving trajectory and the intelligent driving model; and combining the target driving trajectory with the predicted driving trajectory to obtain an output driving trajectory.

[0120] Among them, the intelligent driving model, also known as IDM (Intelligent Driver Model), is an analytical model for analyzing the interaction between vehicles. The model is based on the interaction between vehicles and the behavior pattern of the driver, and describes the movement law of the vehicle by considering factors such as acceleration, following behavior, and road conditions. After obtaining the target driving trajectory of the target vehicle, this embodiment predicts the predicted driving trajectory of the target vehicle according to the intelligent driving model, and combines the aforementioned target driving trajectory and predicted driving trajectory to obtain the output driving trajectory, which can reduce the estimation errors of the target driving trajectory and the predicted driving trajectory, and improve the estimation precision and accuracy of the target vehicle's driving trajectory.

[0121] In one embodiment, the driving trajectory of the preceding vehicle includes the speed and position of the preceding vehicle, and the predicted driving trajectory of the target vehicle on the target road section is determined based on the driving trajectory of the preceding vehicle and the intelligent driving model, including: obtaining the driving speed and vehicle position of the target vehicle at any time, and determining the speed and position of the preceding vehicle at any time based on the driving trajectory of the preceding vehicle; inputting the driving speed, vehicle position, speed and position of the preceding vehicle into the intelligent driving model to obtain the acceleration of the target vehicle; determining the inter-vehicle distance between the target vehicle and the preceding vehicle based on the acceleration, and obtaining the predicted driving trajectory based on the inter-vehicle distance.

[0122] Among them, the intelligent driving model mainly predicts the safe acceleration of the target vehicle based on the speed of the vehicle in front of the target vehicle, the distance to the vehicle in front and the driving speed of the target vehicle. Therefore, when predicting the vehicle's driving trajectory based on the intelligent driving model, the driving speed and vehicle position of the target vehicle, as well as the speed and position of the vehicle in front of the target vehicle are first obtained, and the obtained driving speed, vehicle position, speed of the vehicle in front and position of the vehicle in front are input into the intelligent driving model to obtain the safe acceleration of the target vehicle.

[0123] For example, the safety acceleration a of the target vehicle i (t) is expressed as:

[0124]

[0125]

[0126]

[0127] in, represents the speed of the target vehicle at time t, represents the position of the target vehicle at time t, v0 represents the expected safe speed of the target road section, s* represents the expected safe distance between vehicles, c0 represents the average length of the vehicle, T s represents the driver's reaction time, a represents the safe acceleration, and b represents the comfortable deceleration.

[0128] Furthermore, since the intelligent driving model can take into account the interaction with the vehicle in front, the first-in-first-out principle is guaranteed. However, predictions made through the intelligent driving model easily transfer the error of the trajectory of the vehicle in front to the target vehicle. A small speed error in the trajectory of the vehicle in front may be continuously amplified in the subsequent traffic flow due to error accumulation. When this embodiment determines the predicted driving trajectory through the intelligent driving model, it can also be combined with the target parking position described above for prediction to effectively interrupt the transmission of accumulated errors. Unlike predictions based on the LSTM method, when determining the target parking position through the intelligent driving model, it is only necessary to calculate Q when the end state of the target road section is prohibited, such as when the traffic light is red. i That is, when SignalState(t)=R and x i (t)≥Q i When v i (t+1)=0. When the target vehicle stops at a green light due to a queue in front of it, the intelligent driving model will automatically adjust the acceleration and stop the vehicle according to the position and speed of the vehicle in front.

[0129] In one embodiment, the target driving trajectory and the predicted driving trajectory are combined to obtain the output driving trajectory, including: fusing the target driving trajectory and the predicted driving trajectory based on a particle filtering method, and using the fused driving trajectory as the output driving trajectory.

[0130] For example, the target driving trajectory and the predicted driving trajectory are sampled respectively, x t and z t Represent the discrete state vector and measurement vector respectively. The expression of particle filter (PF) is:

[0131]

[0132]

[0133] Among them, F(·) is the state transition function, which is used to characterize the state transition probability p(x t+1 |x t ); O(·) is the measurement function, which is used to characterize the conditional probability p(z t |x t ). t-1 represents the noise at time t-1, R t represents the measurement noise at time t. Specifically, assuming that the system noise is the acceleration a t , which is a normally distributed random number.

[0134] Based on the kinematic relationship, the discrete state dynamics can be established as follows:

[0135]

[0136] Where dt is the time interval. Based on LSTM and IDM, the measurement trajectories are estimated as and The measurement vector is expressed as:

[0137]

[0138] A series of weighted samples are used to approximate the posterior probability. When the number of samples is large enough, these samples can be used to replace the true posterior probability distribution, expressed as:

[0139]

[0140] in, Represents the position of the i-th sample at time t; Represents the measurement vector from time 0 to time t; is the Dirac function. The weight of sample i The recursive formula is as follows:

[0141]

[0142] in, represents the position of the i-th sample from time 0 to time t. According to the principle of sampling importance resampling (SIR), the system transition density is selected as the importance density The above formula can be simplified to:

[0143]

[0144] At each time step, there are two measurements for the state, the weight It can be obtained by weighted summation, expressed as:

[0145]

[0146] Among them, t and t The measurements are and The calculated weight, m ​​is the custom measurement weight coefficient based on the LSTM method.

[0147] Since the estimated trajectories obtained based on LSTM and IDM are not exactly the same, there are certain errors in both. In this embodiment, the two trajectory estimation results are merged by particle filtering to improve the estimation accuracy and reliability of the target vehicle's driving trajectory.

[0148] In an exemplary embodiment, Figure 4 As shown, a vehicle trajectory estimation method is provided, including the following steps 402 to 410. Among them:

[0149] Step 402, respectively obtain the signal timing data of the end point of the target road section, the detector data of the start point and the end point of the target road section, and the historical vehicle driving trajectory.

[0150] The signal timing data at the end point of the target road section is the signal identification state at the end point of the target road section, and is used to indicate the traffic state at the end point of the target road section.

[0151] The detector data at the starting point and the end point of the target section are the number of vehicles collected by the fixed detectors at the starting point and the end point of the target section. The number of vehicles entering the target section is determined by the number of vehicles collected at the starting point of the target section, and the number of vehicles leaving the target section is determined by the number of vehicles collected at the end point of the target section. Exemplarily, the fixed detector can be a geomagnetic coil detector, an RFID (Radio Frequency Identification) detector, a camera or other image acquisition detector, etc. The above-mentioned fixed detector can more accurately measure the trajectory information of the target vehicle at a certain position, but the cost is relatively high. In this embodiment, only the vehicle information at the starting point and the end point of the target section needs to be collected.

[0152] Historical vehicle driving trajectories are historical trajectory data obtained through connected vehicles. Connected vehicles perform mobile monitoring based on vehicle positioning, such as floating vehicles, and can record the complete running trajectory of vehicles.

[0153] This embodiment combines multiple data sources to estimate the target vehicle's driving trajectory, reduces the calculation cost and can obtain a higher-precision driving trajectory.

[0154] Step 404: estimate the driving trajectory of the target vehicle based on the LSTM to obtain a first driving trajectory.

[0155] When determining the driving trajectory of the target vehicle based on LSTM, the target parking position of the target vehicle is first determined according to the terminal traffic status of the target road section and the queuing sequence of the target vehicle.

[0156] Then, the distance to be traveled of the target vehicle is determined based on the target parking position, and the distance to be traveled and the current speed of the target vehicle are input into the speed prediction model to obtain the driving speed at the next moment, and the distance to be traveled is updated according to the driving speed at the next moment to obtain the updated distance to be traveled, and the iterative cycle is performed to finally obtain the first driving trajectory. Among them, the speed prediction model is based on the LSTM network and is obtained through training of historical vehicle driving trajectories.

[0157] It should be noted that when the traffic status at the end of the target section changes and the vehicles on the target section change from a stopped state to a driving state, the vehicles cannot start at the same time, so the state changes of the vehicles are not simultaneous. A delayed start time needs to be set. The delayed start time is used to indicate the interval time between the starts of the two vehicles, that is, the time difference between the starts of two adjacent vehicles.

[0158] Figure 5 is a schematic diagram of a target driving trajectory in an embodiment, Figure 5The dotted line in the figure represents the real-time trajectory collected by the target vehicle, and the solid line represents the target driving trajectory estimated based on LSTM. It can be obtained that the target driving trajectory estimated based on LSTM basically coincides with the actual trajectory, with high accuracy.

[0159] Step 406 , estimating the driving trajectory of the target vehicle based on the IDM to obtain a second driving trajectory.

[0160] When determining the driving trajectory of the target vehicle based on IDM, the driving speed and vehicle position of the target vehicle, as well as the preceding vehicle speed and preceding vehicle position of the target vehicle are first obtained, and the trajectory of the target vehicle is predicted based on the preceding vehicle trajectory of the target vehicle.

[0161] In one implementation, in order to improve the accuracy of driving trajectory prediction based on IDM, when estimating based on IDM, when the end traffic status of the target road section is prohibited from passing, the target parking position of the target vehicle is also determined based on the above-mentioned method to reduce the cumulative error caused by the error of the preceding vehicle trajectory when calculating based on the preceding vehicle trajectory.

[0162] Step 408: The target driving trajectory and the predicted driving trajectory are merged based on the particle filtering method.

[0163] Step 410: Use the fused driving trajectory as the output driving trajectory.

[0164] In a verification example, the driving trajectories predicted based on LSTM and IDM are compared and analyzed to obtain the trajectory estimation positioning errors of the two methods. The root mean square error (RMSE) and mean absolute error (MAE) are used as evaluation indicators. The calculation formulas are as follows:

[0165]

[0166]

[0167] Among them, E i represents the estimated value of the driving trajectory; J i Represents the true value of the driving trajectory. The RMSE and MAE of the positioning error based on IDM are 7.95m and 4.98m respectively, and the RMSE and MAE based on LSTM are 6.63m and 4.40m respectively. It can be seen that the estimation accuracy of the vehicle driving trajectory based on LSTM is improved.

[0168] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0169] Based on the same inventive concept, the embodiment of the present application also provides a vehicle trajectory estimation device for implementing the vehicle trajectory estimation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle trajectory estimation device embodiments provided below can refer to the limitations of the vehicle trajectory estimation method above, and will not be repeated here.

[0170] In an exemplary embodiment, Figure 6 As shown, a vehicle trajectory estimation device 600 is provided, comprising: a parking position determination module 602, a driving speed prediction module 604 and a driving trajectory estimation module 606, wherein:

[0171] The parking position determination module 602 is used to determine the target parking position of the target vehicle on the target road section according to the terminal traffic state of the target road section and the queue sequence of the target vehicle;

[0172] A driving speed prediction module 604 is used to determine the distance to be traveled of the target vehicle according to the target parking position, adjust the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted driving speed, and update the distance to be traveled according to the adjusted driving speed to obtain an updated distance to be traveled;

[0173] The driving trajectory estimation module 606 is used to determine the driving trajectory points of the target vehicle according to the updated distance to be traveled, iteratively calculate the updated distance to be traveled until the driving trajectory points corresponding to the updated distance to be traveled are outside the target road section, and determine the target driving trajectory of the target vehicle according to each driving trajectory point.

[0174] In one embodiment, the parking position determination module 602 is further used to: determine whether the target vehicle is the first vehicle of the target road section according to the queuing sequence, and obtain a determination result; and determine the target parking position according to the terminal traffic status and the determination result.

[0175] In one embodiment, the parking position determination module 602 is also used for: if the terminal traffic status is an allowed state and the target vehicle is the first vehicle of the target section, the target parking position is determined according to the section length of the target section; if the terminal traffic status is a prohibited state and the target vehicle is not the first vehicle of the target section, the target parking position is determined according to the position of the vehicle in front of the target vehicle; if the terminal traffic status is an allowed state and the target vehicle is not the first vehicle of the target section, the target parking position is determined according to the number of vehicles in front of the target vehicle.

[0176] In one embodiment, the parking position determination module 602 is also used to: obtain the initial number of vehicles entering the target road section at the initial moment and the current number of vehicles leaving the target road section at the current moment, determine the number of vehicles ahead based on the initial number of vehicles entering and the current number of vehicles leaving the target road section; determine the target parking position based on the length of the target road section and the number of vehicles ahead.

[0177] In one embodiment, the driving speed prediction module 604 is also used to: obtain the current speed and speed prediction model of the target vehicle; input the current speed and the distance to be traveled into the speed prediction model to obtain the adjusted driving speed, wherein the speed prediction model is trained based on the historical vehicle driving trajectory of the target section.

[0178] In one embodiment, the vehicle trajectory estimation device 600 is also used to: obtain the driving trajectory of the preceding vehicle of the target vehicle in the target section; obtain the intelligent driving model, and determine the predicted driving trajectory of the target vehicle in the target section according to the driving trajectory of the preceding vehicle and the intelligent driving model; combine the target driving trajectory and the predicted driving trajectory to obtain the output driving trajectory.

[0179] In one embodiment, the vehicle trajectory estimation device 600 is also used to: obtain the driving speed and vehicle position of the target vehicle at any time, and determine the speed and position of the preceding vehicle at any time according to the driving trajectory of the preceding vehicle; input the driving speed, vehicle position, preceding vehicle speed and preceding vehicle position into the intelligent driving model to obtain the acceleration of the target vehicle; determine the inter-vehicle distance between the target vehicle and the preceding vehicle according to the acceleration, and obtain the predicted driving trajectory according to the inter-vehicle distance.

[0180] In one embodiment, the vehicle trajectory estimation device 600 is further used to: merge the target driving trajectory and the predicted driving trajectory based on a particle filtering method, and use the merged driving trajectory as the output driving trajectory.

[0181] Each module in the above-mentioned vehicle trajectory estimation device 600 can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0182] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store vehicle driving data and road section collection data. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle trajectory estimation method is implemented.

[0183] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0184] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0185] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0186] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0187] It should be noted that the vehicle information (including but not limited to vehicle driving information, vehicle status information) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0188] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0189] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0190] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle trajectory estimation method, characterized in that: The method comprises: Determining a target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle; Determine the distance to be traveled of the target vehicle according to the target parking position, adjust the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed, update the distance to be traveled according to the adjusted travel speed to obtain an updated distance to be traveled, and determine the travel trajectory point of the target vehicle according to the updated distance to be traveled; Iteratively calculating the updated distance to be traveled until the travel trajectory point corresponding to the updated distance to be traveled is outside the target road section; The target driving trajectory of the target vehicle is determined according to each of the driving trajectory points.

2. The method according to claim 1, characterized in that Determining the target parking position of the target vehicle at the target road section according to the terminal traffic state of the target road section and the queue sequence of the target vehicle comprises: Determine whether the target vehicle is the first vehicle of the target road section according to the queuing sequence, and obtain a determination result; The target parking position is determined according to the terminal traffic status and the judgment result.

3. The method according to claim 2, characterized in that The determining the target parking position according to the terminal traffic state and the judgment result includes: If the terminal traffic status is a permitted status and the target vehicle is the first vehicle of the target road section, the target parking position is determined according to the road section length of the target road section; If the terminal traffic state is a prohibited state and the target vehicle is not the first vehicle of the target road section, the target parking position is determined according to the position of the preceding vehicle of the target vehicle; If the terminal passage state is a permitted state and the target vehicle is not the first vehicle of the target road section, the target parking position is determined according to the number of vehicles ahead of the target vehicle.

4. The method according to claim 3, characterized in that The step of determining the target parking position according to the number of vehicles ahead of the target vehicle comprises: Obtaining the initial number of vehicles entering the target road section at an initial time and the current number of vehicles leaving the target road section at a current time, and determining the number of vehicles ahead according to the initial number of vehicles entering the target road section and the current number of vehicles leaving the target road section; The target parking position is determined according to the length of the target road section and the number of vehicles ahead.

5. The method according to claim 1, characterized in that The step of adjusting the travel speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted travel speed includes: Obtaining the current speed and speed prediction model of the target vehicle; The current speed and the distance to be traveled are input into the speed prediction model to obtain the adjusted travel speed, wherein the speed prediction model is trained based on the historical vehicle travel trajectory of the target road section.

6. The method according to claim 1, characterized in that The method further comprises: Obtaining a preceding vehicle driving trajectory of the target vehicle in the target road section; Acquire an intelligent driving model, and determine a predicted driving trajectory of the target vehicle on the target road section according to the driving trajectory of the preceding vehicle and the intelligent driving model; The target driving trajectory and the predicted driving trajectory are combined to obtain an output driving trajectory.

7. The method according to claim 6, characterized in that The preceding vehicle driving trajectory includes the preceding vehicle speed and the preceding vehicle position, and determining the predicted driving trajectory of the target vehicle on the target road section according to the preceding vehicle driving trajectory and the intelligent driving model includes: Obtaining the driving speed and vehicle position of the target vehicle at any time, and determining the speed and position of the preceding vehicle at any time according to the preceding vehicle's driving trajectory; Inputting the driving speed, the vehicle position, the preceding vehicle speed and the preceding vehicle position into the intelligent driving model to obtain the acceleration of the target vehicle; The vehicle-to-vehicle distance between the target vehicle and the preceding vehicle is determined according to the acceleration, and a predicted driving trajectory is obtained according to the vehicle-to-vehicle distance.

8. The method according to claim 6, characterized in that The step of combining the target driving trajectory with the predicted driving trajectory to obtain an output driving trajectory includes: The target driving trajectory and the predicted driving trajectory are fused based on a particle filtering method, and the fused driving trajectory is used as the output driving trajectory.

9. A vehicle trajectory estimation device, characterized in that: The device comprises: A parking position determination module, used to determine a target parking position of the target vehicle on the target road section according to the terminal traffic status of the target road section and the queue sequence of the target vehicle; a driving speed prediction module, used to determine the distance to be traveled of the target vehicle according to the target parking position, adjust the driving speed of the target vehicle according to the distance to be traveled and the current speed of the target vehicle to obtain an adjusted driving speed, update the distance to be traveled according to the adjusted driving speed to obtain an updated distance to be traveled, and determine the driving trajectory point of the target vehicle according to the updated distance to be traveled; A driving trajectory iterative calculation module, used for iteratively calculating the updated distance to be traveled until the driving trajectory point corresponding to the updated distance to be traveled is outside the target road section; The target driving trajectory determination module is used to determine the target driving trajectory of the target vehicle according to each of the driving trajectory points.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images