A vehicle trajectory prediction method and device, a vehicle, and a storage medium

Abstract

The present application relates to the technical field of trajectory prediction, and particularly relates to a vehicle trajectory prediction method and device, a vehicle and a storage medium, the method comprising: acquiring instantaneous motion information of a target vehicle, determining an instantaneous motion state of the target vehicle based on the instantaneous motion information; acquiring cache trajectory information of the target vehicle, determining an expected motion state of the target vehicle based on the cache trajectory information; and determining prediction trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state. The present application can acquire the instantaneous motion state and the expected motion state of the target vehicle, and analyze the prediction trajectory information of the target vehicle in combination, thereby improving the accuracy of trajectory prediction.

Description

Technical Field

[0001] This invention relates to the field of trajectory prediction technology, and in particular to a vehicle trajectory prediction method, device, vehicle, and storage medium. Background Technology

[0002] With the continuous development of future technologies and the gradual advancement of autonomous driving technology, vehicle trajectory prediction has become a highly anticipated and important research project. As a crucial element in the realization of autonomous driving technology, the accuracy and timeliness of trajectory prediction directly impact the practicality of autonomous driving. Vehicle trajectory prediction primarily involves analyzing factors such as the vehicle's historical trajectory, environmental information, and driver behavior to deduce the vehicle's potential future movement trajectory, thereby providing guidance for autonomous driving decision-making and control.

[0003] However, current methods of determining a vehicle's trajectory by analyzing historical data are prone to errors, as there may be instances where the target has just appeared or suddenly appears without any historical trajectory cache, making it impossible to accurately predict the vehicle's future motion. Furthermore, due to the complex nature of vehicle movement, it is impossible to accurately define the vehicle's current state of motion based solely on its trajectory.

[0004] Therefore, existing technologies still need to be improved and enhanced. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a vehicle trajectory prediction method, device, vehicle and storage medium in view of the above-mentioned defects of the prior art, so as to solve the problem that the prior art cannot accurately predict the future motion state of the vehicle, and cannot accurately define the motion state of the vehicle through the motion trajectory.

[0006] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows: In a first aspect, the present invention provides a vehicle trajectory prediction method, wherein the method includes: Acquire instantaneous motion information of the target vehicle, and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information; Obtain the cached trajectory information of the target vehicle, and determine the expected motion state of the target vehicle based on the cached trajectory information; Based on the instantaneous motion state and the expected motion state, the predicted trajectory information of the target vehicle is determined.

[0007] According to the above technical solution, this invention can accurately analyze the instantaneous motion information of the target vehicle when it first appears, thereby analyzing its instantaneous motion state. Furthermore, it can analyze the expected motion state of the target vehicle based on cached trajectory information. By combining the instantaneous motion state with the expected motion state for analysis, the predicted trajectory information of the target vehicle can be accurately determined, improving the accuracy of trajectory prediction.

[0008] In one embodiment of this application, obtaining the instantaneous motion information of the target vehicle includes: Acquire a preset number of image frames corresponding to the appearance of the target vehicle; Based on the image frame, the heading angle, longitudinal velocity, and lateral velocity of the target vehicle are determined, and the heading angle, longitudinal velocity, and lateral velocity of the target vehicle are used as the instantaneous motion information.

[0009] According to the above technical solution, this embodiment can extract a preset number of image frames when the target vehicle suddenly appears to analyze the heading angle, longitudinal velocity and lateral velocity, so as to accurately analyze the instantaneous motion state in subsequent steps.

[0010] In one embodiment of this application, determining the instantaneous motion state of the target vehicle based on the instantaneous motion information includes: If the heading angle is less than 45° and the longitudinal speed is greater than a preset first threshold, then the instantaneous motion state of the target vehicle is determined to be a forward-moving state. If the heading angle is less than 45° and the longitudinal speed is less than the first threshold, then the instantaneous motion state of the target vehicle is determined to be a backward motion state. If the heading angle is greater than 45° and the lateral velocity is greater than a preset second threshold, then the instantaneous motion state of the target vehicle is determined to be a traversing state from left to right. If the heading angle is greater than 45° and the lateral velocity is less than the second threshold, then the instantaneous motion state of the target vehicle is determined to be a right-to-left traversing state.

[0011] According to the above technical solution, this embodiment accurately analyzes the instantaneous motion state of the target vehicle when it first appears based on the heading angle, longitudinal velocity, and lateral velocity, so as to make up for the lack of historical trajectory cache when the vehicle first appears and improve the accuracy of instantaneous motion state analysis.

[0012] In one embodiment of this application, obtaining the cached trajectory information of the target vehicle includes: Determine the lane centerline, and based on the initial position of the target vehicle and the lane centerline, determine the amount of movement change of the target vehicle relative to the lane centerline; Based on the changes in movement, the lateral movement, longitudinal movement, and angular change of the target vehicle relative to the current lane, the next lane, and the previous lane are determined. The lateral movement, the longitudinal movement, and the angle change are used as the cached trajectory information.

[0013] According to the above technical solution, this embodiment determines the lateral movement, longitudinal movement, and angular change based on the movement change of the target vehicle relative to the center line of the lane, and uses the lateral movement, longitudinal movement, and angular change as cached trajectory information so that the expected motion state of the target vehicle can be analyzed based on the cached trajectory information in subsequent steps.

[0014] In one embodiment of this application, determining the lane centerline includes: Obtain the curvature information of the lane line, and determine the corner points of the lane line based on the curvature information; Obtain the midpoint between the two corner points, and determine the lane centerline based on the midpoint.

[0015] According to the above technical solution, this embodiment can accurately analyze the lane centerline so that the target vehicle's cache trajectory information can be accurately analyzed in subsequent steps.

[0016] In one embodiment of this application, determining the expected motion state of the target vehicle based on the cached trajectory information includes: The lane boundaries on the left and right sides are obtained, and the lane location of the target vehicle is determined by combining the lateral movement, the longitudinal movement, and the angle change. If the target vehicle is in the same lane as this lane, then the relative motion of the target vehicle with respect to this lane is obtained, and the expected motion state is determined to be forward or backward. If the target vehicle is in the next lane, then the left-right relative motion of the target vehicle relative to the current lane is obtained, and the expected motion state is determined to be a lateral movement from left to right or a lateral movement from right to left.

[0017] According to the above technical solution, this embodiment can accurately analyze the expected motion state of the target vehicle based on the lateral movement, longitudinal movement, and angle change.

[0018] In one embodiment of this application, determining the predicted trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state includes: In one embodiment of this application, the method further includes: Obtain parking space information, and based on the parking space information, determine the positional relationship between the target vehicle and the parking space information, as well as the angle change information of the target vehicle relative to the lane; Based on the positional relationship and the angle change information, the parking motion state is determined, and the parking trajectory information corresponding to the parking motion state is determined, wherein the parking motion state includes the parking state and the parking entry state.

[0019] According to the above technical solution, this embodiment can also analyze parking trajectory information based on the positional relationship between the target vehicle and the parking space information and the angle change information of the target vehicle relative to the lane, so that this application can be applied to more scenarios.

[0020] Secondly, embodiments of the present invention also provide a vehicle trajectory prediction device, wherein the device includes: The instantaneous state determination module is used to acquire instantaneous motion information of the target vehicle and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information. The expected state determination module is used to acquire the cached trajectory information of the target vehicle and determine the expected motion state of the target vehicle based on the cached trajectory information. The trajectory information determination module is used to determine the predicted trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state.

[0021] According to the above technical solution, the vehicle trajectory prediction device of the present invention can accurately analyze the instantaneous motion information of the target vehicle when it first appears, and then analyze the instantaneous motion state. Furthermore, it can analyze the expected motion state of the target vehicle based on cached trajectory information. By combining the instantaneous motion state with the expected motion state for analysis, the predicted trajectory information of the target vehicle can be accurately determined, thus improving the accuracy of trajectory prediction.

[0022] In one embodiment of this application, the instantaneous state determination module includes: An image acquisition unit is used to acquire a preset number of image frames corresponding to the appearance of the target vehicle; The image analysis unit is used to determine the heading angle, longitudinal velocity, and lateral velocity of the target vehicle based on the image frame, and to use the heading angle, longitudinal velocity, and lateral velocity of the target vehicle as the instantaneous motion information.

[0023] In one embodiment of this application, the instantaneous state determination module includes: The first instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a forward-moving state if the heading angle is less than 45° and the longitudinal speed is greater than a preset first threshold. The second instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a backward driving state if the heading angle is less than 45° and the longitudinal speed is less than the first threshold. The third instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a cross-traverse state from left to right if the heading angle is greater than 45° and the lateral velocity is greater than a preset second threshold. The fourth instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a right-to-left traversing state if the heading angle is greater than 45° and the lateral velocity is less than the second threshold.

[0024] In one embodiment of this application, the expected state determination module includes: A centerline determination unit is used to determine the lane centerline and, based on the lane centerline and the initial position of the target vehicle, determine the amount of movement change of the target vehicle relative to the lane centerline. The parameter determination unit is used to determine the lateral movement, longitudinal movement, and angular change of the target vehicle relative to the current lane, the next lane, and the previous lane based on the movement change. The historical trajectory determination unit is used to use the lateral movement, the longitudinal movement, and the angle change as the cached trajectory information.

[0025] In one embodiment of this application, the centerline determining unit includes: The corner point determination subunit is used to acquire the curvature information of the lane line and determine the corner point of the lane line based on the curvature information. The corner analysis subunit is used to obtain the midpoint between two corner points and determine the lane centerline based on the midpoint.

[0026] In one embodiment of this application, the expected state determination module includes: The parameter analysis unit is used to obtain the lane boundaries on the left and right sides, and combine the lateral movement, longitudinal movement and angle change to determine the lane where the target vehicle is located. The first expected state determination unit is used to obtain the relative forward and backward motion of the target vehicle with respect to the lane if the lane in which the target vehicle is located is the current lane, and to determine the expected motion state as forward or backward. The second expected state determination unit is used to obtain the left-right relative motion of the target vehicle relative to the current lane if the lane in which the target vehicle is located is the next lane, and to determine the expected motion state as a lateral movement from left to right or a lateral movement from right to left.

[0027] In one embodiment of this application, the apparatus further includes: The information acquisition module is used to acquire parking space information and, based on the parking space information, determine the positional relationship between the target vehicle and the parking space information, as well as the angle change information of the target vehicle relative to the lane. The parking analysis module is used to determine the parking motion state based on the positional relationship and the angle change information, and to determine the parking trajectory information corresponding to the parking motion state, wherein the parking motion state includes the parking state and the parking entry state.

[0028] Thirdly, embodiments of the present invention also provide a vehicle, wherein the vehicle includes a memory, a processor, and a vehicle trajectory prediction program stored in the memory and executable on the processor, wherein when the processor executes the vehicle trajectory prediction program, it implements the steps of the vehicle trajectory prediction method of any of the above solutions.

[0029] Fourthly, embodiments of the present invention also provide a computer-readable storage medium, wherein a vehicle trajectory prediction program is stored on the computer-readable storage medium, and when the vehicle trajectory prediction program is executed by a processor, it implements the steps of the vehicle trajectory prediction method described in any of the above schemes.

[0030] Beneficial Effects: Compared with existing technologies, this invention provides a vehicle trajectory prediction method. First, it acquires the instantaneous motion information of a target vehicle and determines its instantaneous motion state based on this information. Then, it acquires the cached trajectory information of the target vehicle and determines its expected motion state based on this information. Finally, it determines the predicted trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state. This invention can accurately analyze the instantaneous motion information of a target vehicle when it first appears, thereby analyzing its instantaneous motion state, and can also analyze its expected motion state based on the cached trajectory information. By combining the instantaneous motion state and the expected motion state for analysis, the predicted trajectory information of the target vehicle can be accurately determined, improving the accuracy of trajectory prediction. Attached Figure Description

[0031] Figure 1 A flowchart illustrating a specific implementation of the vehicle trajectory prediction method provided in this application; Figure 2 This is a schematic diagram of the corner points in the vehicle trajectory prediction method of this application; Figure 3 This is a schematic diagram of the midpoint in the vehicle trajectory prediction method of this application; Figure 4 This is a schematic diagram illustrating the principle of the vehicle trajectory prediction method in this application; Figure 5 A functional schematic diagram of the vehicle trajectory prediction device provided in this application; Figure 6 A schematic diagram of the vehicle provided in this application. Detailed Implementation

[0032] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0033] Existing technologies suffer from limitations such as the inability to accurately predict a vehicle's future motion state when it first appears or suddenly without historical trajectory cache. Furthermore, the complexity of vehicle movement makes it difficult to accurately define a vehicle's motion state through its trajectory. This embodiment provides a vehicle trajectory prediction method that can accurately determine the predicted trajectory information of a target vehicle. In specific applications, this embodiment first acquires the instantaneous motion information of the target vehicle and determines its instantaneous motion state based on this information. Then, it acquires the cached trajectory information of the target vehicle and determines its expected motion state based on this information. Finally, it determines the predicted trajectory information of the target vehicle based on both the instantaneous and expected motion states. This embodiment can accurately analyze the instantaneous motion information of a target vehicle when it first appears, thereby determining its instantaneous motion state. It can also analyze the expected motion state of the target vehicle based on the cached trajectory information. By combining the instantaneous and expected motion states in the analysis, the predicted trajectory information of the target vehicle can be accurately determined, improving the accuracy of trajectory prediction.

[0034] The vehicle trajectory prediction method of this embodiment can be applied to a control terminal, which can be an in-vehicle controller, such as an in-vehicle central control computer. Alternatively, the control terminal can also be a user's mobile terminal, such as a mobile phone, which can connect to the in-vehicle terminal to receive data transmitted by the in-vehicle terminal and perform corresponding analysis and processing. Specifically, as shown... Figure 1 As shown in the figure, the vehicle trajectory prediction method of this embodiment includes the following steps: Step S100: Obtain the instantaneous motion information of the target vehicle, and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information.

[0035] In reality, there may be vehicles that have just appeared, and these newly appeared vehicles do not have cached trajectory data. Therefore, it is impossible to accurately analyze the trajectory prediction of these vehicles. To address this, this embodiment can acquire the instantaneous motion information of the target vehicle. This instantaneous motion information is the motion information collected when the target vehicle has just appeared. After acquiring this instantaneous motion information, the terminal device can determine the instantaneous motion state of the target vehicle based on this instantaneous motion information.

[0036] In practical applications, this embodiment can acquire images of the target vehicle based on a pre-set onboard forward-looking camera or radar sensor when the target vehicle first appears. Then, based on a pre-set number of image frames (e.g., the first 20 frames) corresponding to the target vehicle's appearance, the heading angle, longitudinal velocity, and lateral velocity of the target vehicle can be determined. These heading angle, longitudinal velocity, and lateral velocity of the target vehicle are used as instantaneous motion information so that the instantaneous motion state can be accurately analyzed in subsequent steps.

[0037] In one implementation, this embodiment includes the following steps when determining the instantaneous motion state: Step S101: If the heading angle is less than 45° and the longitudinal speed is greater than a preset first threshold, then the instantaneous motion state of the target vehicle is determined to be a forward-moving state. Step S102: If the heading angle is less than 45° and the longitudinal speed is less than the first threshold, then the instantaneous motion state of the target vehicle is determined to be a backward driving state. Step S103: If the heading angle is greater than 45° and the lateral velocity is greater than a preset second threshold, then the instantaneous motion state of the target vehicle is determined to be a traversing state from left to right. Step S104: If the heading angle is greater than 45° and the lateral velocity is less than the second threshold, then the instantaneous motion state of the target vehicle is determined to be a right-to-left traversing state.

[0038] Specifically, in this embodiment, after acquiring instantaneous motion information, the heading angle in the instantaneous motion information is compared with a preset angle. For example, the preset angle is 45°. If the heading angle is less than 45°, considering that the target vehicle is moving forward or backward, this embodiment compares the longitudinal velocity of the target vehicle with a preset first threshold. If the longitudinal velocity is greater than the preset first threshold, the instantaneous motion state of the target vehicle is determined to be forward. If the longitudinal velocity is less than the first threshold, the instantaneous motion state of the target vehicle is determined to be backward. When the heading angle is greater than 45° and less than 90°, considering that the target vehicle is moving laterally, this embodiment compares the lateral velocity of the target vehicle with a preset second threshold. If the lateral velocity is greater than the preset second threshold, the instantaneous motion state of the target vehicle is determined to be traversing from left to right. If the lateral velocity is less than the second threshold, the instantaneous motion state of the target vehicle is determined to be traversing from right to left. This embodiment uses heading angle, longitudinal velocity, and lateral velocity to accurately analyze the instantaneous motion state of the target vehicle when it first appears, thus compensating for the lack of historical trajectory cache when the vehicle first appears and improving the accuracy of instantaneous motion state analysis.

[0039] Step S200: Obtain the cached trajectory information of the target vehicle, and determine the expected motion state of the target vehicle based on the cached trajectory information.

[0040] For target vehicles that have been in operation for a long time or after a target vehicle has been running for a long time, this embodiment will cache historical trajectories in real time. When the terminal device performs trajectory prediction, it will obtain the cached trajectory information of the target vehicle and then determine the expected motion state of the target vehicle based on the cached trajectory information.

[0041] In this embodiment, when acquiring cached trajectory information, the terminal device first determines the lane centerline. This embodiment first acquires the curvature information of the lane line, divides the lane into several lanes, and simultaneously determines the curvature changes based on the curvature information, using the points of curvature change as the corner points of the lane line, specifically as follows: Figure 2 As shown in the diagram. Next, the midpoint between each pair of corner points is calculated using the indexed corner points. This midpoint is the midpoint of the center line of each lane, as shown in the diagram. Figure 3As shown in the diagram. Since most lanes in the garage are perpendicular to each other, the longest lane line is first indexed by the length of the line connecting each pair of corner points. Then, the next lane line is obtained by drawing a perpendicular line from the midpoint, and so on, to determine the lane centerline. After obtaining the lane centerline, this embodiment acquires a certain number of image frames and, based on the lane centerline and the initial position of the target vehicle, determines the amount of movement change of the target vehicle relative to the lane centerline. Then, based on the amount of movement change, this embodiment can determine the lateral movement, longitudinal movement, and angular change of the target vehicle relative to the current lane, the next lane, and the previous lane. The previous lane is the lane before the vehicle changes to the current lane, and the next lane is the target lane from the current lane to another lane. In specific applications, this embodiment can propose a variable called move_counter. This variable is defined as the change in movement of the target vehicle relative to the lane centerline during its journey. Considering only lateral distance, the calculation method is as follows: For each captured image frame, a distance difference is calculated. If the difference is greater than a preset threshold, it indicates the target vehicle is moving in the opposite direction of the lane, and `move_up_counter` is incremented by 1. If the difference is less than 0 and less than the preset threshold, it indicates the target vehicle is moving in the direction of the lane, and `move_down_counter` is incremented by 1. If the target vehicle's movement distance is within a certain threshold, it is considered to be laterally stationary, and `move_steady_counter` is incremented by 1. If the vehicle continuously moves towards or in the opposite direction of the lane, or remains stationary, the other two counters are set to 0. Using these counters, the lateral movement, longitudinal movement, and angular change of the target vehicle relative to its current lane, the next lane, and the previous lane are calculated. These lateral movement, longitudinal movement, and angular change are used as cached trajectory information to facilitate subsequent analysis of the target vehicle's expected motion state.

[0042] In one implementation, this embodiment includes the following steps when determining the expected motion state of the target vehicle: Step S201: Obtain the lane boundaries on the left and right sides, and combine the lateral movement, longitudinal movement and angle change to determine the lane where the target vehicle is located. Step S202: If the lane in which the target vehicle is located is the current lane, then obtain the relative forward and backward motion of the target vehicle relative to the current lane, and determine whether the expected motion state is forward or backward. Step S203: If the target vehicle is in the next lane, then obtain the left-right relative motion of the target vehicle relative to the current lane, and determine that the expected motion state is a lateral movement from left to right or a lateral movement from right to left.

[0043] Specifically, this embodiment first determines whether the target vehicle is in the current lane or the next lane. Therefore, this embodiment obtains the lane boundaries on both the left and right sides, and combines the lateral movement, longitudinal movement, and angle change to determine the lane where the target vehicle is located. If the target vehicle is in the current lane, then for a target vehicle in this lane, it is considered that the target vehicle may be traveling forward or backward. Therefore, this embodiment obtains the relative forward and backward movement of the target vehicle relative to the current lane, and determines that the expected movement state is forward or backward. Of course, for a target vehicle in the current lane, it is also possible to consider that the target vehicle may be moving left or right. Therefore, this embodiment can also obtain the relative left and right movement of the target vehicle relative to the current lane, and determine that the expected movement state is moving from left to right or from right to left.

[0044] If the target vehicle is located in the next lane, meaning only the left-right lateral movement of the target vehicle is considered, this embodiment acquires the left-right relative motion of the target vehicle with respect to the current lane and determines the expected motion state as either lateral movement from left to right or lateral movement from right to left. This embodiment can accurately analyze the expected motion state of the target vehicle based on the lateral movement, longitudinal movement, and angle change.

[0045] Step S300: Based on the instantaneous motion state and the expected motion state, determine the predicted trajectory information of the target vehicle.

[0046] After obtaining the instantaneous motion state and the expected motion state, this embodiment can combine the two for analysis. Since the instantaneous motion state reflects the motion state of the target vehicle when it first appears, and the expected motion state is the motion state of the target vehicle during its long-term movement, combining the two for analysis allows for accurate determination of the predicted trajectory information of the target vehicle. In specific applications, this embodiment can be as follows: Figure 4 As shown, the terminal device optimizes the vehicle's historical information (i.e., the cached trajectory information corresponding to this embodiment, and then analyzes the expected motion state) and the vehicle's instantaneous information (i.e., the instantaneous motion information corresponding to this embodiment), and then integrates the vehicle's lateral intention to generate the future trajectory. The generated future trajectory of the vehicle is the predicted trajectory information of this embodiment.

[0047] In one implementation, since the instantaneous motion state of this embodiment reflects the motion state of the target vehicle when it first appears, and the expected motion state is the motion state of the target vehicle during its long-term movement, when the two are analyzed together, the motion state is predicted based on the instantaneous motion state and the expected motion state. That is, by comprehensively analyzing the motion state of the target vehicle when it first appears and the motion state after a long period of movement, the target motion state of the target vehicle is determined, and then the predicted trajectory information of the target motion state is determined. For example, if the instantaneous motion state and the expected motion state are the same, it means that the motion state of the target vehicle has not changed. Therefore, the expected motion state can be taken as the target motion state, and then the predicted trajectory information is determined based on the cached trajectory information corresponding to the expected motion state. Thus, this embodiment combines the analysis of the instantaneous motion state and the expected motion state. Since the instantaneous motion state is the motion state of the target vehicle when it first appears, and the expected motion state is the motion state of the target vehicle during its long-term movement, combining the two for analysis can accurately predict the future motion trajectory, thereby providing beneficial guidance for the decision-making and control of autonomous driving.

[0048] In another implementation, the terminal device of this embodiment can also determine the parking status, which includes both a parking status and a parking-in status. For determining the parking status, this embodiment considers the situation where a parking space exists within the lane, the target is determined to be moving, and the target's angle relative to the lane continuously changes. If the target is exiting the parking space, it is a parking-out status; if it is moving into the parking space, it is a parking-in status. In specific applications, this embodiment can acquire parking space information and, based on this information, determine the positional relationship between the target vehicle and the parking space, as well as the angle change information of the target vehicle relative to the lane. Then, based on the positional relationship and the angle change information, the parking status is determined, and the corresponding parking trajectory information is determined, enabling this embodiment to be applied to more scenarios.

[0049] Based on the above embodiments, the present invention also provides a vehicle trajectory prediction device, such as... Figure 5 As shown, the vehicle trajectory prediction device 100 of this embodiment includes: an instantaneous state determination module 10, an expected state determination module 20, and a trajectory information determination module 30. Specifically, the instantaneous state determination module 10 is used to acquire instantaneous motion information of the target vehicle and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information. The expected state determination module 20 is used to acquire cached trajectory information of the target vehicle and determine the expected motion state of the target vehicle based on the cached trajectory information. The trajectory information determination module 30 is used to determine the predicted trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state.

[0050] In one embodiment of this application, the instantaneous state determination module 10 includes: An image acquisition unit is used to acquire a preset number of image frames corresponding to the appearance of the target vehicle; The image analysis unit is used to determine the heading angle, longitudinal velocity, and lateral velocity of the target vehicle based on the image frame, and to use the heading angle, longitudinal velocity, and lateral velocity of the target vehicle as the instantaneous motion information.

[0051] In one embodiment of this application, the instantaneous state determination module 10 includes: The first instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a forward-moving state if the heading angle is less than 45° and the longitudinal speed is greater than a preset first threshold. The second instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a backward driving state if the heading angle is less than 45° and the longitudinal speed is less than the first threshold. The third instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a cross-traverse state from left to right if the heading angle is greater than 45° and the lateral velocity is greater than a preset second threshold. The fourth instantaneous motion state analysis unit is used to determine that the instantaneous motion state of the target vehicle is a right-to-left traversing state if the heading angle is greater than 45° and the lateral velocity is greater than the second threshold.

[0052] In one embodiment of this application, the expected state determination module 20 includes: A centerline determination unit is used to determine the lane centerline and, based on the lane centerline and the initial position of the target vehicle, determine the amount of movement change of the target vehicle relative to the lane centerline. The parameter determination unit is used to determine the lateral movement, longitudinal movement, and angular change of the target vehicle relative to the current lane, the next lane, and the previous lane based on the movement change. The historical trajectory determination unit is used to use the lateral movement, the longitudinal movement, and the angle change as the cached trajectory information.

[0053] In one embodiment of this application, the centerline determining unit includes: The corner point determination subunit is used to acquire the curvature information of the lane line and determine the corner point of the lane line based on the curvature information. The corner analysis subunit is used to obtain the midpoint between two corner points and determine the lane centerline based on the midpoint.

[0054] In one embodiment of this application, the expected state determination module 20 includes: The parameter analysis unit is used to obtain the lane boundaries on the left and right sides, and combine the lateral movement, longitudinal movement and angle change to determine the lane where the target vehicle is located. The first expected state determination unit is used to obtain the relative forward and backward motion of the target vehicle with respect to the lane if the lane in which the target vehicle is located is the current lane, and to determine the expected motion state as forward or backward. The second expected state determination unit is used to obtain the left-right relative motion of the target vehicle relative to the current lane if the lane in which the target vehicle is located is the next lane, and to determine the expected motion state as a lateral movement from left to right or a lateral movement from right to left.

[0055] In one embodiment of this application, the apparatus further includes: The information acquisition module is used to acquire parking space information and, based on the parking space information, determine the positional relationship between the target vehicle and the parking space information, as well as the angle change information of the target vehicle relative to the lane. The parking analysis module is used to determine the parking motion state based on the positional relationship and the angle change information, and to determine the parking trajectory information corresponding to the parking motion state, wherein the parking motion state includes the parking state and the parking entry state.

[0056] The working principle of each module in the vehicle trajectory prediction device 100 of this embodiment is the same as that of each step in the above method embodiment, and will not be repeated here.

[0057] The vehicle trajectory prediction device 100 according to this embodiment can accurately analyze the instantaneous motion information of the target vehicle when it first appears, and then analyze the instantaneous motion state. Furthermore, it can analyze the expected motion state of the target vehicle based on cached trajectory information. By combining the instantaneous motion state with the expected motion state for analysis, the predicted trajectory information of the target vehicle can be accurately determined, improving the accuracy of trajectory prediction.

[0058] Figure 6 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: a memory 501, a processor 502, and a computer program stored in the memory 501 and executable on the processor 502. When the processor 502 executes the program, it implements the vehicle trajectory prediction method provided in the above embodiment.

[0059] Furthermore, the vehicle also includes: Communication interface 503 is used for communication between memory 501 and processor 502.

[0060] The memory 501 is used to store computer programs that can run on the processor 502.

[0061] The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0062] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0063] In practical implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface. The processor 502 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0064] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the vehicle trajectory prediction method described above.

[0065] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0066] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0067] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0068] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0069] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0070] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0071] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0072] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A vehicle trajectory prediction method, characterized in that, The method includes: Acquire instantaneous motion information of the target vehicle, and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information; Obtain the cached trajectory information of the target vehicle, and determine the expected motion state of the target vehicle based on the cached trajectory information; Based on the instantaneous motion state and the expected motion state, the predicted trajectory information of the target vehicle is determined; The step of obtaining the cached trajectory information of the target vehicle includes: Determine the lane centerline, and based on the initial position of the target vehicle and the lane centerline, determine the amount of movement change of the target vehicle relative to the lane centerline; Based on the changes in movement, the lateral movement, longitudinal movement, and angular change of the target vehicle relative to the current lane, the next lane, and the previous lane are determined. The lateral movement, the longitudinal movement, and the angle change are used as the cached trajectory information; Determining the expected motion state of the target vehicle based on the cached trajectory information includes: The lane boundaries on the left and right sides are obtained, and the lane location of the target vehicle is determined by combining the lateral movement, the longitudinal movement, and the angle change. If the target vehicle is in the same lane as this lane, then the relative motion of the target vehicle with respect to this lane is obtained, and the expected motion state is determined to be forward or backward. If the target vehicle is in the next lane, then the left-right relative motion of the target vehicle relative to the current lane is obtained, and the expected motion state is determined to be a lateral movement from left to right or a lateral movement from right to left.

2. The vehicle trajectory prediction method according to claim 1, characterized in that, The acquisition of the instantaneous motion information of the target vehicle includes: Acquire a preset number of image frames corresponding to the appearance of the target vehicle; Based on the image frame, the heading angle, longitudinal velocity, and lateral velocity of the target vehicle are determined, and the heading angle, longitudinal velocity, and lateral velocity of the target vehicle are used as the instantaneous motion information.

3. The vehicle trajectory prediction method according to claim 2, characterized in that, Determining the instantaneous motion state of the target vehicle based on the instantaneous motion information includes: If the heading angle is less than 45° and the longitudinal speed is greater than a preset first threshold, then the instantaneous motion state of the target vehicle is determined to be a forward-moving state. If the heading angle is less than 45° and the longitudinal speed is less than the first threshold, then the instantaneous motion state of the target vehicle is determined to be a backward motion state. If the heading angle is greater than 45° and the lateral velocity is greater than a preset second threshold, then the instantaneous motion state of the target vehicle is determined to be a traversing state from left to right. If the heading angle is greater than 45° and the lateral velocity is less than the second threshold, then the instantaneous motion state of the target vehicle is determined to be a right-to-left traversing state.

4. The vehicle trajectory prediction method according to claim 1, characterized in that, Determining the lane centerline includes: Obtain the curvature information of the lane line, and determine the corner points of the lane line based on the curvature information; Obtain the midpoint between the two corner points, and determine the lane centerline based on the midpoint.

5. The vehicle trajectory prediction method according to claim 1, characterized in that, The method further includes: Obtain parking space information, and based on the parking space information, determine the positional relationship between the target vehicle and the parking space information, as well as the angle change information of the target vehicle relative to the lane; Based on the positional relationship and the angle change information, the parking motion state is determined, and the parking trajectory information corresponding to the parking motion state is determined, wherein the parking motion state includes the parking state and the parking entry state.

6. A vehicle trajectory prediction device, characterized in that, The apparatus is used to implement the steps of the vehicle trajectory prediction method according to any one of claims 1-5, and the apparatus comprises: The instantaneous state determination module is used to acquire instantaneous motion information of the target vehicle and determine the instantaneous motion state of the target vehicle based on the instantaneous motion information. The expected state determination module is used to acquire the cached trajectory information of the target vehicle and determine the expected motion state of the target vehicle based on the cached trajectory information. The trajectory information determination module is used to determine the predicted trajectory information of the target vehicle based on the instantaneous motion state and the expected motion state.

7. A vehicle, characterized in that, The vehicle includes a memory, a processor, and a vehicle trajectory prediction program stored in the memory and executable on the processor. When the processor executes the vehicle trajectory prediction program, it implements the steps of the vehicle trajectory prediction method as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle trajectory prediction program, which, when executed by a processor, implements the steps of the vehicle trajectory prediction method as described in any one of claims 1-5.

Images