Trajectory prediction method, trajectory prediction device, and storage medium

Abstract

The present disclosure relates to a trajectory prediction method, device and storage medium. The trajectory prediction method comprises: acquiring a map image, the map image comprising a lane center line, the lane center line having a plurality of nodes arranged at equal intervals, each node having a distance feature, and the distance feature of the node fusing distance features of other lane center line nodes having different distances from the node; determining, based on a position of a vehicle in the map image, a lane center line node closest to the position of the vehicle as a target node; performing vector merging of the distance feature of the target node and a historical trajectory feature of the vehicle to obtain a trajectory prediction vector; and predicting, based on the trajectory prediction vector, a driving trajectory of the vehicle in the map image. By merging the distance feature and the historical trajectory of the vehicle to obtain the trajectory prediction vector, and predicting the driving trajectory of the vehicle based on the trajectory prediction vector, the topological structure of the lane line in the map image can be retained, and the accuracy of trajectory prediction can be improved.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent driving technology, and in particular to trajectory prediction methods, trajectory prediction devices and storage media. Background Technology

[0002] In fields such as robot navigation and autonomous driving, predictions are made in dynamically changing traffic environments to plan the driving routes of physical objects and guide their movement.

[0003] The movement trajectory of the current object is affected by the behavior of other entities in the traffic scene. Therefore, in guiding the driving behavior of an entity, it is necessary to predict the driving trajectories of surrounding entities as the basis for guiding the current object's driving and to reasonably avoid obstacles. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this disclosure provides a trajectory prediction method, a trajectory prediction device, and a storage medium.

[0005] According to a first aspect of the present disclosure, a trajectory prediction method is provided, the trajectory prediction method comprising: acquiring a map image, the map image including lane centerlines, the lane centerlines having a plurality of nodes equally spaced, each node having a distance feature, the distance features of the nodes being fused with distance features of other lane centerline nodes having different distances from the node; determining, based on the position of a vehicle in the map image, the lane centerline node closest to the vehicle's position as a target node; merging the distance features of the target node with the historical trajectory features of the vehicle to obtain a trajectory prediction vector; and predicting the driving trajectory of the vehicle in the map image based on the trajectory prediction vector.

[0006] In some embodiments, the distance features of each node are determined as follows: a first node is determined on the map image; a regional map image is determined based on the position of the first node, the regional map image including the first node and a plurality of second nodes with different distances from the first node; based on the distances between the plurality of second nodes and the first node, the distance features of the plurality of second nodes are extracted and merged to obtain the distance features of the first node.

[0007] In some embodiments, based on the distance between the plurality of second nodes and the first node, distance features of the plurality of second nodes are extracted, and the distance features of the plurality of second nodes are merged to obtain the distance features of the first node, including: dividing the plurality of second nodes into multiple categories according to their distance from the first node, wherein the distance between the second nodes in the same category and the first node is the same; extracting the distance features of the second nodes in the same category in the plurality of categories respectively, and concatenating the extracted distance features of different categories to obtain the distance features of the first node.

[0008] In some embodiments, determining a regional map image based on the location of the first node includes: determining a regional map image with a preset range centered on the first node, wherein the preset range includes at least a second node directly adjacent to the first node and a second node indirectly adjacent to the first node.

[0009] In some embodiments, extracting distance features of the plurality of second nodes includes: extracting distance features of the plurality of second nodes based on a deep learning model of point cloud data.

[0010] In some embodiments, the historical trajectory features of the vehicle are determined as follows: the historical trajectory of the vehicle is acquired; features of the historical trajectory are extracted based on a long short-term memory regression neural network to obtain the historical trajectory features of the vehicle.

[0011] According to a second aspect of the present disclosure, a trajectory prediction apparatus is provided, comprising: an acquisition unit for acquiring a map image, the map image including a lane centerline, the lane centerline having a plurality of nodes equally spaced, each node having a distance feature, the distance feature of the node being fused with distance features of other lane centerline nodes having different distances from the node; a determination unit for determining, based on the position of a vehicle in the map image, the lane centerline node closest to the vehicle's position as a target node, and merging the distance feature of the target node with the historical trajectory features of the vehicle to obtain a trajectory prediction vector; and a prediction unit for predicting the vehicle's driving trajectory in the map image based on the trajectory prediction vector.

[0012] In some embodiments, the distance features of each node are determined as follows: a first node is determined on the map image; a regional map image is determined based on the position of the first node, the regional map image including the first node and a plurality of second nodes with different distances from the first node; based on the distances between the plurality of second nodes and the first node, the distance features of the plurality of second nodes are extracted and merged to obtain the distance features of the first node.

[0013] In some embodiments, the determining unit extracts distance features of the plurality of second nodes based on the distance between the plurality of second nodes and the first node, and merges the distance features of the plurality of second nodes to obtain the distance features of the first node: the plurality of second nodes are divided into multiple categories according to their distance from the first node, wherein the distance between the second nodes in the same category and the first node is the same; the distance features of the second nodes in the same category are extracted from the plurality of categories respectively, and the extracted distance features of different categories are concatenated to obtain the distance features of the first node.

[0014] In some embodiments, the determining unit determines a regional map image based on the location of the first node in the following manner: taking the first node as the center, a regional map image with a preset range is determined, and the preset range includes at least a second node directly adjacent to the first node and a second node indirectly adjacent to the first node.

[0015] In some embodiments, the determining unit extracts the distance features of the plurality of second nodes in the following manner: the distance features of the plurality of second nodes are extracted based on a deep learning model of point cloud data.

[0016] In some embodiments, the historical trajectory features of the vehicle are determined as follows: the historical trajectory of the vehicle is acquired; features of the historical trajectory are extracted based on a long short-term memory regression neural network to obtain the historical trajectory features of the vehicle.

[0017] According to a third aspect of the present disclosure, a trajectory prediction apparatus is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the trajectory prediction method described in any one of the preceding embodiments.

[0018] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium is provided, which, when the instructions in the storage medium are executed by a processor of a mobile terminal, enables the mobile terminal to perform the trajectory prediction method described in any of the preceding claims.

[0019] The technical solutions provided by the embodiments of this disclosure can include the following beneficial effects: Through the embodiments of this disclosure, the target node where the vehicle is located is determined in the map image, and the distance feature of the target node is determined. The distance feature is fused with the features of other nodes with different distances from the node. The trajectory prediction vector obtained by merging the distance feature with the vehicle's historical trajectory is used to predict the vehicle's driving trajectory. This can preserve the topological structure of lane lines in the map image and improve the accuracy of trajectory prediction.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0021] The accompanying drawings, which are incorporated in and form a part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure.

[0022] Figure 1 This is a flowchart illustrating a trajectory prediction method according to an exemplary embodiment of the present disclosure.

[0023] Figure 2 This is a schematic diagram of lane center lines and nodes in a map image according to an exemplary embodiment of the present disclosure.

[0024] Figure 3 This is a flowchart illustrating a method for determining the distance characteristics of a node according to an exemplary embodiment of the present disclosure.

[0025] Figure 4 This is a flowchart illustrating an exemplary embodiment of the present disclosure of a method for extracting distance features of multiple second nodes based on the distance between multiple second nodes and a first node, and merging the distance features of multiple second nodes to obtain the distance features of a first node.

[0026] Figure 5 This is a schematic diagram illustrating the determination of distance features of a first node according to an exemplary embodiment of the present disclosure.

[0027] Figure 6 This is a flowchart illustrating a method for determining the distance characteristics of a node according to an exemplary embodiment of the present disclosure.

[0028] Figure 7 This is a flowchart illustrating a method for determining the historical trajectory characteristics of a vehicle according to an exemplary embodiment of the present disclosure.

[0029] Figure 8 This is a block diagram of a trajectory prediction device according to an exemplary embodiment of the present disclosure.

[0030] Figure 9This is a block diagram illustrating an apparatus for trajectory prediction according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0032] In the field of autonomous driving, motion prediction of both the vehicle itself and surrounding moving objects is necessary. Since autonomous vehicles inevitably interact with other road users during actual driving, their driving strategy planning is closely related to the driving behavior of surrounding vehicles. Driving strategy planning involves predicting the future intentions of moving objects within the surrounding area and transforming the predictions into trajectories in both time and space dimensions. Using the predicted trajectories of moving objects such as obstacles, pedestrians, and non-motorized vehicles as input, the autonomous vehicle can make reasonable driving decisions and plan rational and safe vehicle movement. For example, if it is predicted that another vehicle will merge into the current vehicle's lane, deceleration needs to be considered in advance. The higher the accuracy of the prediction, the more accurate the decision-making, and the higher the reliability of autonomous driving.

[0033] Motion prediction combines the attribute information of moving objects, historical trajectory information, and high-precision map information to predict the motion behavior of moving objects over a future period. Rendering the map as a top-down view will lose the map's topological structure and fail to distinguish between oncoming lanes and the lanes in which vehicles are located, affecting the accuracy of trajectory prediction.

[0034] Therefore, this disclosure provides a trajectory prediction method that can preserve the topological structure of lane lines in a map image of a vehicle's location, thereby improving the accuracy of trajectory prediction.

[0035] Figure 1 This is a flowchart illustrating a trajectory prediction method according to an exemplary embodiment of the present disclosure, such as... Figure 1 As shown, the trajectory prediction method includes the following steps.

[0036] In step S101, a map image is acquired. The map image includes a lane centerline and several nodes set at equal intervals on the lane centerline. Each node has a distance feature, and the distance feature of the node is fused with the distance features of other lane centerline nodes that have different distances from the node.

[0037] In step S102, based on the vehicle's position in the map image, the lane centerline node closest to the vehicle's position is determined as the target node.

[0038] In step S103, the distance features of the target node and the historical trajectory features of the vehicle are vector-merged to obtain the trajectory prediction vector.

[0039] In step S104, the vehicle's driving trajectory in the map image is predicted based on the trajectory prediction vector.

[0040] In this embodiment of the disclosure, when predicting the driving trajectory of a vehicle, a map image including the location of the vehicle is obtained. The map image can be a rendered map to obtain a top-down view image.

[0041] Figure 2 This is a schematic diagram of lane centerlines and nodes in a map image according to an exemplary embodiment of the present disclosure, such as... Figure 2 As shown, the map image includes multiple lanes, based on the vehicle's location. These lanes can include lanes traveling in the same direction as the vehicle and lanes traveling in the opposite direction. Each lane has a centerline, and several nodes are set along the centerline at preset intervals, with adjacent nodes being equidistant. Taking any node as the current node as an example, the current node is surrounded by other lane centerline nodes that are different from the current node. There can be multiple other lane centerline nodes, and the distances between these other lane centerline nodes and the current node can vary. The distance features of these other lane centerline nodes at different distances are fused together to form the distance feature of the current node.

[0042] Based on the vehicle's position in the map image, the lane centerline node closest to the vehicle's position is determined as the target node. The distance features at the target node are then vector-merged with the vehicle's historical trajectory features to obtain a trajectory prediction vector, which serves as the basis for predicting the vehicle's driving trajectory.

[0043] In this embodiment of the disclosure, a multilayer perceptron (MLP) neural network or similar device can be used to input the trajectory prediction vector of a vehicle and output the possible location of the vehicle and the probability of it appearing at that location, thereby enabling the prediction of the vehicle's driving trajectory in a map image.

[0044] According to embodiments of this disclosure, a target node is determined in a map image to indicate the location of a vehicle, and the distance features of the target node are determined. The distance features are fused with features of other nodes that have different distances from the target node. The trajectory prediction vector obtained by merging the distance features with the vehicle's historical trajectory is used to predict the vehicle's driving trajectory. This method can preserve the topological structure of lane lines in the map image and improve the accuracy of trajectory prediction.

[0045] Figure 3 This is a flowchart illustrating a method for determining the distance features of a node according to an exemplary embodiment of the present disclosure, such as... Figure 3 As shown, the method for determining the distance features of nodes includes the following steps.

[0046] In step S201, the first node is determined on the map image.

[0047] In step S202, a regional map image is determined based on the location of the first node. The regional map image includes the first node and multiple second nodes with different distances from the first node.

[0048] In step S203, based on the distances between multiple second nodes and the first node, the distance features of multiple second nodes are extracted, and the distance features of multiple second nodes are merged to obtain the distance features of the first node.

[0049] In this embodiment of the disclosure, when predicting the driving trajectory of a vehicle, the acquired map image includes a lane centerline, and the lane centerline has several nodes spaced at equal intervals. The distance features of each node are fused with the distance features of other lane centerline nodes that are at different distances from the node. When determining the distance features of each node in the map image, a certain area needs to be selected, and the node distance features within the corresponding area map image are determined. The area map image includes a first node and multiple second nodes that are at different distances from the first node.

[0050] Understandably, in this embodiment of the disclosure, the first node can be understood as the current node, that is, the current location of the vehicle. It has other vehicles around it relative to the current vehicle and predicts the driving trajectories of other vehicles around it in order to provide reasonable guidance and planning for the current vehicle's driving.

[0051] Still refer to Figure 2 , Figure 2 The diagram shows the current node, i.e., the first node. An elliptical region includes the first node and a second node directly adjacent to it (i.e., the distance between the second node and the first node in the elliptical region is 1). Outside the elliptical region, second nodes indirectly adjacent to the first node at a distance of 2, and second nodes indirectly adjacent to the first node at a distance of 3, etc., are shown sequentially. For multiple second nodes, distance features of the second nodes are extracted based on their distances to the first node. These distance features are then merged to obtain the distance features of the first node, thus incorporating the distance features of the second nodes with different distances to the first node.

[0052] According to an embodiment of this disclosure, a first node is determined in a map image, and a regional map image is determined. The distance features of multiple second nodes included in the regional map image are extracted, and the distance features of multiple second nodes are merged to obtain the distance features of the first node. The topological structure of the lane lines is preserved, thus providing a guarantee for vehicle trajectory prediction.

[0053] Figure 4 This is a flowchart illustrating an exemplary embodiment of the present disclosure of a method for extracting distance features of multiple second nodes based on the distances between multiple second nodes and a first node, and merging the distance features of the multiple second nodes to obtain the distance features of the first node, as shown in the flowchart. Figure 4 As shown, the method includes the following steps.

[0054] In step S301, multiple second nodes are divided into multiple categories according to their distance from the first node, wherein the distance between the second nodes and the first node is the same in the same category.

[0055] In step S302, the distance features of the second nodes of the same category in multiple categories are extracted respectively, and the extracted distance features of different categories are concatenated to obtain the distance features of the first node.

[0056] In this embodiment of the disclosure, when determining the distance features of each node in a map image, a regional map image including a first node and a plurality of second nodes with different distances from the first node is determined in the map image to determine the distance features of each node in the determined regional map image.

[0057] Multiple second nodes surrounding the first node are categorized into several classes based on their distance from the first node. Second nodes with the same distance from the first node are grouped into the same class. Distance features are extracted from the second nodes of the same class, and the extracted distance features from different classes are concatenated to obtain the distance features of the first node. In essence, the concatenated distance features of the first node incorporate the distance features of its adjacent second nodes.

[0058] Figure 5 This is a schematic diagram illustrating the determination of distance features of a first node according to an exemplary embodiment of the present disclosure, with reference to... Figure 2 ,as well as Figure 5 , Figure 2 The image shows a regional map containing a first node and second nodes directly adjacent to it. The distance between a directly adjacent second node and the first node is 1. There are also second nodes indirectly adjacent to the first node at a distance of 2, and second nodes indirectly adjacent to the first node at a distance of 3, etc. Multiple second nodes are categorized according to their distances from the first node.

[0059] Figure 5 The diagram shows that the second node is divided into three categories: second nodes with a distance of 1, 2, and 3 from the first node. Distance features are extracted for each of the three categories: the distance features of the second nodes with distances of 1, 2, and 3 from the first node. These extracted distance features from different categories are then concatenated to obtain the distance features of the first node. Understandably, the distance features of each category of the second node can be represented as a vector; concatenating the distance features from different categories involves merging the vectors corresponding to the distance features of different categories.

[0060] According to an embodiment of this disclosure, a first node is determined in a map image, and a regional map image is determined. The distance features of multiple second nodes included in the regional map image are extracted, and the distance features of multiple second nodes are merged to obtain the distance features of the first node. The topological structure of the lane lines is preserved, thus providing a guarantee for vehicle trajectory prediction.

[0061] Figure 6 This is a flowchart illustrating a method for determining the distance features of a node according to an exemplary embodiment of the present disclosure, such as... Figure 6 As shown, the method for determining the distance features of nodes includes the following steps.

[0062] In step S401, the first node is determined on the map image.

[0063] In step S402, a regional map image with a preset range is determined with the first node as the center. The preset range includes at least a second node that is directly adjacent to the first node and a second node that is indirectly adjacent to the first node.

[0064] In step S403, based on the distance between multiple second nodes and the first node, the distance features of multiple second nodes are extracted, and the distance features of multiple second nodes are merged to obtain the distance features of the first node.

[0065] In this embodiment, the regional map image can be an image corresponding to a region centered on a first node and having a preset range. The preset range includes the first node and multiple second nodes at different distances from the first node. The adjacency relationship between the second nodes and the first node can be direct or indirect. The preset range can be a regular or irregular shape formed by the first node and preset distances as side lengths. When determining the distance characteristics of each node in the map image, a regional map image including the first node and multiple second nodes at different distances from the first node is determined to define the distance characteristics of each node in the determined regional map image.

[0066] According to embodiments of this disclosure, a regional map image is determined in a map image. In the regional map image, distance features of the second nodes are extracted based on the distances between multiple second nodes and the first node, and then merged to obtain the distance features of the first node. This can improve the calculation speed and efficiency.

[0067] In this embodiment, multiple second nodes with different distances surround the first node. Based on the distances between the multiple second nodes and the first node, distance features of the multiple second nodes are extracted, and these distance features are merged to obtain the distance features of the first node. Extracting the distance features of the second nodes can be done using a deep learning model (PointNet) for point cloud data. Point cloud data is a collection of unordered data points; a certain number of spatially related point clouds constitute objects within a specific space. PointNet can extract the overall features of point cloud data, providing a guarantee for vehicle trajectory prediction.

[0068] Figure 7 This is a flowchart illustrating a method for determining the historical trajectory features of a vehicle according to an exemplary embodiment of this disclosure, such as... Figure 7 As shown, the method for determining the historical trajectory characteristics of a vehicle includes the following steps.

[0069] In step S501, the historical trajectory of the vehicle is acquired.

[0070] In step S502, features of the historical trajectory are extracted based on the long short-term memory regression neural network to obtain the historical trajectory features of the vehicle.

[0071] In this embodiment, based on the vehicle's position in the map image, the lane centerline node closest to the vehicle's position is determined as the target node. The distance features at the target node are then merged with the vehicle's historical trajectory features to obtain a trajectory prediction vector, which serves as the basis for predicting the vehicle's driving trajectory. Based on this trajectory prediction vector, the vehicle's driving trajectory in the map image is predicted. The vehicle's historical trajectory can be described by the movement trajectory formed by the vehicle's center position, and features of the historical trajectory are extracted using a Long Short-Term Memory (LSTM) regressive neural network. LSTM is a variant of Recurrent Neural Network (RNN), enabling the transfer of information from the previous time step to the next, while effectively solving the gradient vanishing and gradient exploding problems that occur during training.

[0072] According to embodiments of this disclosure, a target node is determined in a map image to indicate the location of a vehicle, and the distance features of the target node are determined. The distance features are fused with features of other nodes that have different distances from the target node. The trajectory prediction vector obtained by merging the distance features with the vehicle's historical trajectory is used to predict the vehicle's driving trajectory. This method can preserve the topological structure of lane lines in the map image and improve the accuracy of trajectory prediction.

[0073] Based on the same concept, embodiments of this disclosure also provide a trajectory prediction device.

[0074] Figure 8 This is a block diagram of a trajectory prediction device according to an exemplary embodiment of the present disclosure. (Refer to...) Figure 8 The trajectory prediction device 100 includes: an acquisition unit 101, a determination unit 102, and a prediction unit 103.

[0075] The acquisition unit 101 is used to acquire a map image, which includes a lane centerline and several nodes set at equal intervals on the lane centerline. Each node has a distance feature, and the distance feature of the node is fused with the distance features of other lane centerline nodes that have different distances from the node.

[0076] The determining unit 102 is used to determine the lane centerline node closest to the vehicle's position as the target node based on the vehicle's position in the map image, and to merge the distance features of the target node with the vehicle's historical trajectory features to obtain the trajectory prediction vector.

[0077] The prediction unit 103 is used to predict the driving trajectory of a vehicle in a map image based on the trajectory prediction vector.

[0078] In some embodiments, the distance features of each node are determined as follows: a first node is determined on a map image; a regional map image is determined based on the position of the first node, the regional map image including the first node and multiple second nodes with different distances from the first node; based on the distances between the multiple second nodes and the first node, the distance features of the multiple second nodes are extracted and merged to obtain the distance features of the first node.

[0079] In some embodiments, the determining unit 102 extracts distance features of multiple second nodes based on the distance between multiple second nodes and the first node in the following manner, and merges the distance features of multiple second nodes to obtain the distance features of the first node: the multiple second nodes are divided into multiple categories according to their distance from the first node, wherein the distance between the second nodes in the same category and the first node is the same; the distance features of the second nodes in the same category in the multiple categories are extracted respectively, and the distance features of the extracted different categories are concatenated to obtain the distance features of the first node.

[0080] In some embodiments, the determining unit 102 determines the regional map image based on the location of the first node in the following manner: taking the first node as the center, a regional map image with a preset range is determined, and the preset range includes at least a second node directly adjacent to the first node and a second node indirectly adjacent to the first node.

[0081] In some embodiments, the determining unit 102 extracts the distance features of multiple second nodes in the following manner: the distance features of multiple second nodes are extracted based on a deep learning model of point cloud data.

[0082] In some embodiments, the historical trajectory features of a vehicle are determined as follows: the historical trajectory of the vehicle is obtained; features of the historical trajectory are extracted based on a long short-term memory regression neural network to obtain the historical trajectory features of the vehicle.

[0083] It is understood that the apparatus provided in this disclosure includes hardware structures and / or software modules corresponding to each function in order to achieve the above-mentioned functions. In conjunction with the units and algorithm steps of the various examples disclosed in this disclosure, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solutions of this disclosure.

[0084] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0085] Figure 9 This is a block diagram illustrating an apparatus for trajectory prediction according to an exemplary embodiment of the present disclosure. For example, apparatus 200 may be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0086] Reference Figure 9 The device 200 may include one or more of the following components: a processing component 202, a memory 204, a power component 206, a multimedia component 208, an audio component 210, an input / output (I / O) interface 212, a sensor component 214, and a communication component 216.

[0087] Processing component 202 typically controls the overall operation of device 200, such as operations associated with display, telephone calls, data communication, camera operation, and recording. Processing component 202 may include one or more processors 220 to execute instructions to perform all or part of the steps of the methods described above. Furthermore, processing component 202 may include one or more modules to facilitate interaction between processing component 202 and other components. For example, processing component 202 may include a multimedia module to facilitate interaction between multimedia component 208 and processing component 202.

[0088] Memory 204 is configured to store various types of data to support the operation of device 200. Examples of such data include instructions for any application or method operating on device 200, contact data, phonebook data, messages, pictures, videos, etc. Memory 204 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0089] The power supply component 206 provides power to the various components of the device 200. The power supply component 206 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power to the device 200.

[0090] Multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 208 includes a front-facing camera and / or a rear-facing camera. When the device 200 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0091] Audio component 210 is configured to output and / or input audio signals. For example, audio component 210 includes a microphone (MIC) configured to receive external audio signals when device 200 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 204 or transmitted via communication component 216. In some embodiments, audio component 210 also includes a speaker for outputting audio signals.

[0092] I / O interface 212 provides an interface between processing component 202 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0093] Sensor assembly 214 includes one or more sensors for providing status assessments of various aspects of device 200. For example, sensor assembly 214 may detect the on / off state of device 200, the relative positioning of components such as the display and keypad of device 200, changes in the position of device 200 or a component of device 200, the presence or absence of user contact with device 200, the orientation or acceleration / deceleration of device 200, and temperature changes of device 200. Sensor assembly 214 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 214 may also include an accelerometer, a gyroscope, a magnetometer, a pressure sensor, or a temperature sensor.

[0094] Communication component 216 is configured to facilitate wired or wireless communication between device 200 and other devices. Device 200 can access wireless networks based on communication standards, such as WiFi, 2G, or 3G, or combinations thereof. In one exemplary embodiment, communication component 216 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 216 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0095] In an exemplary embodiment, the apparatus 200 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0096] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 204 including instructions, which can be executed by a processor 220 of the device 200 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0097] It is understood that in this disclosure, "multiple" refers to two or more, and other quantifiers are similar. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. The singular forms "a," "the," and "the" are also intended to include the plural forms unless the context clearly indicates otherwise.

[0098] It is further understood that the terms "first," "second," etc., are used to describe various types of information, but this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another, and do not indicate a specific order or degree of importance. In fact, the expressions "first," "second," etc., are completely interchangeable. For example, without departing from the scope of this disclosure, first information can also be referred to as second information, and similarly, second information can also be referred to as first information.

[0099] It can be further understood that, unless otherwise specified, "connection" includes both direct connections where no other components exist between the two parties and indirect connections where other components exist between them.

[0100] It is further understood that although operations are described in a specific order in the accompanying drawings in this disclosure, this should not be construed as requiring these operations to be performed in the specific order or serial order shown, or requiring all of the shown operations to obtain the desired result. In certain environments, multitasking and parallel processing may be advantageous.

[0101] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following scope of claims.

[0102] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A trajectory prediction method, characterized in that, The method includes: Acquire a map image, the map image including lane center lines, the lane center lines having a number of nodes set at equal intervals, each node having distance features, the distance features of the nodes being fused with the distance features of other lane center line nodes that have different distances from the node. Based on the vehicle's position in the map image, the lane centerline node closest to the vehicle's position is determined as the target node; The distance features of the target node and the historical trajectory features of the vehicle are vector-merged to obtain the trajectory prediction vector; Based on the trajectory prediction vector, predict the vehicle's driving trajectory in the map image; The distance feature of each node is determined in the following way: A first node is determined on the map image, the first node including the node where the current vehicle is located; Centered on the first node, a regional map image with a preset range is determined, and the preset range includes at least a second node directly adjacent to the first node and a second node indirectly adjacent to the first node; Based on the distances between the plurality of second nodes and the first node, the distance features of the plurality of second nodes are extracted, and the distance features of the plurality of second nodes are merged to obtain the distance features of the first node.

2. The trajectory prediction method according to claim 1, characterized in that, Based on the distances between the plurality of second nodes and the first node, distance features of the plurality of second nodes are extracted, and the distance features of the plurality of second nodes are merged to obtain the distance features of the first node, including: The plurality of second nodes are divided into multiple categories according to their distance from the first node, wherein the second nodes in the same category are equidistant from the first node; The distance features of the second nodes of the same category in the multiple categories are extracted respectively, and the distance features of the extracted different categories are concatenated to obtain the distance features of the first node.

3. The trajectory prediction method according to claim 1, characterized in that, Extracting distance features from the plurality of second nodes, including: The distance features of the multiple second nodes are extracted using a deep learning model based on point cloud data.

4. The trajectory prediction method according to claim 1, characterized in that, The historical trajectory characteristics of the vehicle are determined in the following way: Obtain the historical trajectory of the vehicle; The historical trajectory features of the vehicle are obtained by extracting features from the historical trajectory using a long short-term memory regression neural network.

5. A trajectory prediction device, characterized in that, The device includes: The acquisition unit is used to acquire a map image, which includes a lane centerline and a number of nodes that are equally spaced on the lane centerline. Each node has a distance feature, and the distance feature of the node is fused with the distance features of other lane centerline nodes that have different distances from the node. The determining unit is used to determine the lane centerline node closest to the vehicle's position as the target node based on the vehicle's position in the map image, and to vector-merge the distance features of the target node with the vehicle's historical trajectory features to obtain a trajectory prediction vector. The prediction unit is used to predict the driving trajectory of the vehicle in the map image based on the trajectory prediction vector; The distance feature of each node is determined in the following way: A first node is determined on the map image, the first node including the node where the current vehicle is located; Centered on the first node, a regional map image with a preset range is determined, and the preset range includes at least a second node directly adjacent to the first node and a second node indirectly adjacent to the first node; Based on the distances between the plurality of second nodes and the first node, the distance features of the plurality of second nodes are extracted, and the distance features of the plurality of second nodes are merged to obtain the distance features of the first node.

6. The trajectory prediction device according to claim 5, characterized in that, The determining unit extracts distance features of the plurality of second nodes based on the distances between the plurality of second nodes and the first node, and merges the distance features of the plurality of second nodes to obtain the distance features of the first node: The plurality of second nodes are divided into multiple categories according to their distance from the first node, wherein the second nodes in the same category are equidistant from the first node; The distance features of the second nodes of the same category in the multiple categories are extracted respectively, and the distance features of the extracted different categories are concatenated to obtain the distance features of the first node.

7. The trajectory prediction device according to claim 5, characterized in that, The determining unit extracts the distance features of the plurality of second nodes in the following manner: The distance features of the multiple second nodes are extracted using a deep learning model based on point cloud data.

8. The trajectory prediction device according to claim 5, characterized in that, The historical trajectory characteristics of the vehicle are determined in the following way: Obtain the historical trajectory of the vehicle; The historical trajectory features of the vehicle are obtained by extracting features from the historical trajectory using a long short-term memory regression neural network.

9. A trajectory prediction device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to execute the trajectory prediction method according to any one of claims 1 to 4.

10. A storage medium, characterized in that, The storage medium stores instructions that, when executed by the terminal's processor, enable the terminal to perform the trajectory prediction method according to any one of claims 1 to 4.

Images