Method and apparatus for determining relationship of motion behavior, electronic device and storage medium

Abstract

The application is suitable for the technical field of trajectory prediction, and provides a motion behavior relationship determination method and device, electronic equipment and a storage medium. The motion behavior relationship determination method comprises: obtaining participant information of each traffic participant and road information of a road; determining a future trajectory of each traffic participant according to the participant information and the road information; and determining motion behavior relationship information between traffic participants according to a relative position relationship between the future trajectories of different traffic participants, wherein the motion behavior relationship information is used for trajectory prediction of the traffic participants. The embodiments of the application can introduce the mutual relationship of future behaviors between traffic participants for trajectory prediction, and reduce the operation complexity.

Description

Technical Field

[0001] This application belongs to the field of trajectory prediction technology, and in particular relates to a method, apparatus, electronic device and storage medium for determining motion behavior relationships. Background Technology

[0002] Trajectory prediction can predict possible trajectories for given traffic participants, providing a reference for autonomous driving of mobile devices. Most existing trajectory prediction schemes consider current and past interactions, but cannot guarantee that future trajectories between traffic participants will not collide, resulting in some predicted trajectories being illogical. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and storage medium for determining motion behavior relationships, which can solve the problem of unreasonable trajectory prediction in the prior art.

[0004] The first aspect of this application provides a method for determining motion behavior relationships, comprising: acquiring participant information of each traffic participant and road information of a road, wherein the participant information includes the current position and current speed of the traffic participant on the road, and the road information includes traffic lane information on the road; determining the future trajectory of each traffic participant based on the participant information and the road information; and determining motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants, wherein the motion behavior relationship information is used to predict the trajectories of traffic participants.

[0005] In some implementations, determining the motion behavior relationship information between traffic participants based on the relative positional relationship between their future trajectories includes: constructing graph nodes that correspond one-to-one with each traffic participant; establishing a connection between the graph nodes corresponding to two traffic participants when their future trajectories intersect, based on the relative positional relationship between their future trajectories, to obtain a structure graph; and determining the motion behavior relationship information based on the structure graph.

[0006] In some implementations, determining the motion behavior relationship information based on the structure graph includes: for a target graph node in the structure graph, determining the intersection point between the future trajectory corresponding to the target graph node and the future trajectory corresponding to a target connected node, wherein the target connected node is a graph node connected to the target graph node; and determining the motion behavior relationship information between the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node based on a first estimated time for the traffic participant corresponding to the target graph node to reach the intersection point and a second estimated time for the traffic participant corresponding to the target connected node to reach the intersection point.

[0007] In some implementations, determining the motion behavior relationship information based on the structure graph further includes: if the future trajectory corresponding to the target graph node does not intersect with the future trajectory corresponding to the target connected node, then determining that the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node are unrelated.

[0008] In some implementations, determining the motion behavior relationship information based on the structure diagram includes: inputting the structure diagram into a graph neural network to obtain the motion behavior relationship information processed and output by the graph neural network on the structure diagram.

[0009] In some implementations, determining the future trajectory of each traffic participant based on the participant information and the road information includes: predicting the future position of each traffic participant after a preset time period based on the participant information and the road information; and determining the future trajectory of each traffic participant based on the current position and the future position of each traffic participant.

[0010] In some implementations, determining the future trajectory of each traffic participant based on its current location and future location includes: acquiring a target layer in a map, the target layer recording the lane lines and lane center lines of the lanes; and drawing a trajectory on the target layer based on the current location and future location of each traffic participant to obtain the future trajectory of each traffic participant.

[0011] A second aspect of this application provides an apparatus for determining motion behavior relationships, comprising: an acquisition unit for acquiring participant information of each traffic participant and road information of a road, wherein the participant information includes the current position and current speed of the traffic participant on the road, and the road information includes lane traffic information on the road; a trajectory determination unit for determining the future trajectory of each traffic participant based on the participant information and the road information; and a relationship determination unit for determining motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants, wherein the motion behavior relationship information is used to predict the trajectories of the traffic participants.

[0012] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for determining the above-described motion behavior relationship.

[0013] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method for determining the above-described motion behavior relationship.

[0014] The fifth aspect of this application provides a computer program product that, when run on an electronic device, causes the electronic device to perform the aforementioned method for determining motion behavior relationships.

[0015] In the embodiments of this application, by obtaining participant information of each traffic participant and road information, the future trajectory of each traffic participant can be determined by utilizing the current position and speed of the traffic participants on the road and the traffic information of the lanes on the road. Based on the relative positional relationship between the future trajectories of different traffic participants, the motion behavior relationship information between traffic participants can be determined. Using the motion behavior relationship information to predict the trajectory of traffic participants can introduce the mutual relationship of future behavior between traffic participants into the trajectory prediction. Furthermore, the process of determining the motion behavior relationship information does not require the introduction of the past trajectories of traffic participants, which can effectively reduce the computational complexity. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1This is a schematic diagram illustrating the implementation process of a method for determining motion behavior relationships provided in an embodiment of this application;

[0018] Figure 2 This is a schematic diagram illustrating the specific implementation process of determining the future trajectory provided in the embodiments of this application;

[0019] Figure 3 This is a schematic diagram illustrating the specific implementation process of determining the relationship information of movement behavior between traffic participants provided in the embodiments of this application;

[0020] Figure 4 This is a schematic diagram of traffic participants within a preset area provided in the embodiments of this application;

[0021] Figure 5 This is a schematic diagram of the structure provided in the embodiments of this application;

[0022] Figure 6 This is a schematic diagram of the structure of a device for determining motion behavior relationships provided in an embodiment of this application;

[0023] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are protected by this application.

[0025] To illustrate the technical solution of this application, specific embodiments are described below.

[0026] Figure 1 The illustration shows a flowchart of a method for determining motion behavior relationships provided in an embodiment of this application, which can be applied to electronic devices.

[0027] The aforementioned electronic devices can be self-moving devices with autonomous driving capabilities, such as robots, smart cars, drones, and driverless vehicles, or smart devices such as computers and smartphones; this application does not impose any restrictions on them.

[0028] Specifically, the method for determining the above-mentioned relationship of motion behavior may include the following steps S101 to S103.

[0029] Step S101: Obtain participant information for each traffic participant, as well as road information.

[0030] In the embodiments of this application, traffic participants can refer to objects with mobility capabilities such as pedestrians, vehicles, and robots. A road refers to the road where the traffic participants are located. Specifically, trajectory prediction can be used to predict the trajectories of various traffic participants within a specific area (e.g., within a certain distance range of an autonomous vehicle). Therefore, in some embodiments, the aforementioned road can specifically refer to all roads within that specific area, and the aforementioned traffic participants can be all traffic participants appearing within a preset area.

[0031] In embodiments of this application, participant information may include the current position and current speed of the traffic participant on the road, and road information may include the traffic information of the lanes on the road. The traffic information indicates the possible direction of movement of the traffic participant when driving in the lane, including but not limited to maintaining a straight line, turning, changing lanes, etc.

[0032] Participant information can be input through the traffic participant tracking module. For example, when a vehicle needs to perform trajectory prediction or autonomous driving, the vehicle's tracking module can collect participant information of each traffic participant based on the vehicle's cameras, radar, and other sensors. Of course, participant information can also be obtained through other methods, such as image analysis based on images captured by monitoring equipment in a specific area, or input by the user after viewing relevant information, etc. This application does not impose any restrictions on this.

[0033] Correspondingly, road information can be obtained from information recorded on high-precision maps, or it can be entered by users after viewing relevant information, etc. This application does not impose any restrictions on this.

[0034] Step S102: Determine the future trajectory of each traffic participant based on participant information and road information.

[0035] Specifically, based on the current location and speed of traffic participants on the road, as well as the traffic information of the lanes on the road, the future movement trends of traffic participants can be predicted, and thus the future trajectory of each traffic participant can be determined.

[0036] Step S103: Determine the motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants.

[0037] The motion behavior relationship information characterizes the relationship between the future motion behaviors of traffic participants, specifically indicating whether yielding occurred between them and who yielded. More specifically, the relative positional relationship between the future trajectories of different traffic participants can characterize the likelihood of a future collision. To avoid a collision, two traffic participants will influence each other during movement, causing at least one participant's motion behavior to change; for example, one participant might yield to another in a future movement. Therefore, in the embodiments of this application, the motion behavior relationship information between traffic participants can be determined based on the relative positional relationship between their future trajectories, thus describing the motion behavior relationship between traffic participants through this information.

[0038] Specifically, for an individual traffic participant, the behavioral relationship between them and another traffic participant can include yielders, passersby, and unrelated parties. A yielder indicates that the traffic participant yields to another traffic participant; a passerby indicates that another traffic participant yields to the yielder; and an unrelated party indicates that the two traffic participants do not need to yield to each other and do not affect each other. In the behavioral relationship information, unrelated parties, passersby, and yielders can be represented using a bag-of-words model, for example, 0 represents an unrelated party, 1 represents a passerby, and 2 represents a yielder.

[0039] In the embodiments of this application, motion behavior relationship information is related to the future behavior of traffic participants, and the future behavior of traffic participants is related to the future trajectory of traffic participants. Therefore, motion behavior relationship information can be used to predict the trajectory of traffic participants.

[0040] Specifically, in some embodiments, the electronic device can perform trajectory prediction for any one or more traffic participants after executing step S103. During trajectory prediction, future relationships can be used as a feature to introduce the interrelationships of future motion behaviors among traffic participants, making the predicted future trajectories more accurate. In other embodiments, the electronic device can also output motion behavior relationship information as feature data to the device requiring trajectory prediction. For example, when the electronic device is a server, it can output motion behavior relationship information to the vehicle, which then performs trajectory prediction based on the motion behavior relationship information. This application does not impose any limitations on this. It should be noted that the above steps S101 to S103 can be encapsulated as a plug-in and inserted into any existing trajectory prediction module to add motion behavior relationship information to the trajectory prediction module.

[0041] In the embodiments of this application, by obtaining participant information of each traffic participant and road information, the future trajectory of each traffic participant can be determined by utilizing the current position and speed of the traffic participants on the road and the traffic information of the lanes on the road. Based on the relative positional relationship between the future trajectories of different traffic participants, the motion behavior relationship information between traffic participants can be determined. Using the motion behavior relationship information to predict the trajectory of traffic participants can introduce the mutual relationship of future behavior between traffic participants into the trajectory prediction. Furthermore, the process of determining the motion behavior relationship information does not require the introduction of the past trajectories of traffic participants, which can effectively reduce the computational complexity.

[0042] Please refer to Figure 2 In some embodiments of this application, step S102 can be implemented by steps S201 to S202.

[0043] Step S201: Based on participant information and road information, predict the future location of each traffic participant after a preset time period.

[0044] The future location refers to the location of traffic participants after a preset time. The preset time can be set according to actual needs, such as 5 seconds, 8 seconds, etc.

[0045] Specifically, for each traffic participant, using their current location, current speed, and lane information, and assuming that they only switch states once within a preset time (e.g., turning, going straight, changing lanes and then going straight), the current location after moving for a preset time from the current location can be estimated.

[0046] Taking vehicle A as an example, assuming that based on the current position, the lane where vehicle A is currently located will extend into 3 lanes, namely lane D1 after turning left, lane D2 after changing lanes and going straight, and the current lane D3, then based on the current speed, the future position of vehicle A in lane D1, lane D2 and lane D3 can be predicted after a preset time.

[0047] For ease of calculation, this application assumes that both the current and future positions are located on the center line of the lane.

[0048] Step S202: Determine the future trajectory of each traffic participant based on their current and future locations.

[0049] Specifically, for a single traffic participant, its future trajectory can be determined based on its current location and each future location. When there are multiple future locations (for example, vehicle A mentioned above has a total of 3 future locations), multiple future trajectories can be determined.

[0050] Specifically, the aforementioned future trajectories can be determined using electronic maps. In particular, trajectories can be drawn on electronic maps based on the current and future locations of traffic participants, thus obtaining their future trajectories.

[0051] To make the future trajectory more accurate, the aforementioned electronic map can be a high-precision map. Considering that when using a high-precision map, the computational load of loading the high-precision map and drawing on the high-precision map by the electronic device is large, in some embodiments, the determination of the future trajectory may further include: obtaining the target layer in the map, and drawing the trajectory on the target layer according to the current and future positions of each traffic participant to obtain the future trajectory of each traffic participant.

[0052] Specifically, the aforementioned map, also known as an electronic map, can include several layers, such as a lane line layer corresponding to lane lines, a building layer corresponding to buildings, and so on. The electronic device can select a target layer from the map. This target layer records the lane lines and lane center lines. Then, based on the current and future positions of each traffic participant, and the lane lines and lane center lines recorded in the target layer, the electronic device can draw a trajectory on the target layer to obtain the future trajectory of each traffic participant. This ensures that the future trajectory lies within the lane lines, and that the current and / or future positions of the traffic participants are located on the lane center lines. In this case, the electronic device does not need to load other layers besides the target layer, reducing the computational load on the electronic device.

[0053] After obtaining the future trajectory, the electronic device can determine the relative positional relationship between the future trajectories of different traffic participants, and determine the motion behavior relationship information between traffic participants based on the relative positional relationship.

[0054] Specifically, such as Figure 3 As shown, determining the motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants may include the following steps S301 to S303.

[0055] Step S301: Construct graph nodes that correspond one-to-one with each traffic participant.

[0056] Specifically, based on the number of traffic participants, a graph node can be generated that is equal to the number of traffic participants, and each graph node can be associated with a different traffic participant. Each graph node can record relevant information about the corresponding traffic participant, such as current location, current lane number, current speed, future location, future lane number, and the action performed (e.g., staying in the current lane to go straight, changing lanes to go straight, turning, etc.).

[0057] Step S302: Based on the relative positional relationship between the future trajectories of different traffic participants, when two traffic participants have intersecting future trajectories, establish the connection between the corresponding graph nodes of the two traffic participants to obtain the structure graph.

[0058] Specifically, after obtaining the future trajectories, the relative positional relationships between the future trajectories of different traffic participants can be determined; that is, whether two traffic participants have intersecting future trajectories. If two traffic participants have intersecting future trajectories, connections need to be established between the graph nodes corresponding to the two traffic participants. After traversing each graph node, a structure graph can be obtained. This structure graph contains each graph node and the connections between graph nodes, which can reflect relevant information about traffic participants and the possibility of future collisions between traffic participants.

[0059] Step S303: Determine the motion behavior relationship information based on the structure diagram.

[0060] Based on the structure diagram, the relevant information of traffic participants and the probability of future collisions between them can be used to determine the relationship between their movement behaviors.

[0061] Specifically, in some implementations, for a target graph node in the structural graph, the electronic device can determine the intersection point between the future trajectory corresponding to the target graph node and the future trajectory corresponding to the target connected node, and determine the motion behavior relationship information between the traffic participants corresponding to the target graph node and the traffic participants corresponding to the target connected node based on the first estimated time for the traffic participants corresponding to the target graph node to reach the intersection point and the second estimated time for the traffic participants corresponding to the target connected node to reach the intersection point.

[0062] The target graph node can be any graph node in the structure graph, and the target connected node is a graph node that is connected to the target graph node.

[0063] When a target graph node has a target connected node, it indicates that the future trajectory of the traffic participant corresponding to the target graph node intersects with the future trajectory of the traffic participant corresponding to the target connected node. At this point, the location of the intersection point can be determined. Based on the current position and speed of the traffic participant corresponding to the target graph node, a first estimated time required for the traffic participant to reach the intersection point from its current position can be estimated. Similarly, based on the current position and speed of the traffic participant corresponding to the target connected node, a second estimated time required for the traffic participant to reach the intersection point from its current position can be estimated. Based on the first and second estimated times, the order in which the two traffic participants arrive at the intersection point can be analyzed, thereby determining the behavioral relationship between the traffic participants corresponding to the target graph node and the traffic participants corresponding to the target connected node.

[0064] Specifically, if the first estimated time is less than or equal to the second estimated time, it means that the traffic participant corresponding to the target graph node arrives at the intersection earlier. In this case, the traffic participant corresponding to the target graph node can be identified as a traveler, and the traffic participant corresponding to the target connected node is identified as a yielder. If the first estimated time is greater than the second estimated time, it means that the traffic participant corresponding to the target graph node arrives at the intersection later. In this case, the traffic participant corresponding to the target graph node can be identified as a yielder, and the traffic participant corresponding to the target connected node is identified as a traveler.

[0065] In other implementations, if the future trajectory corresponding to the target graph node does not intersect with the future trajectory corresponding to the target connected node, then the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node are determined to be unrelated to each other.

[0066] For ease of understanding, Figure 4 This diagram illustrates three vehicles traveling within a preset area. Solid lines represent the current position, and dashed lines represent future positions. Figure 4 It can be seen that vehicle A's future trajectory 41 intersects with vehicle B's future trajectory 42, while vehicle C's future trajectory does not intersect with either vehicle A's or vehicle B's future trajectory. Therefore, as Figure 5 As shown in the diagram, in the structure diagram between vehicles A, B, and C, the graph node corresponding to vehicle A is connected to the graph node corresponding to vehicle B, while the graph node corresponding to vehicle C is not connected to the graph node corresponding to vehicle A, nor is it connected to the graph node corresponding to vehicle B. Based on these connections, since vehicle A arrives at intersection position 43 later than vehicle B... Figure 4 (As shown at the intersection), therefore, between vehicle A and vehicle B, vehicle A is the one yielding, and vehicle B is the one proceeding. Correspondingly, vehicle C and vehicle A, and vehicle C and vehicle B are unrelated parties.

[0067] It should be understood that, for each traffic participant, when the total number of traffic participants in the preset area is N (N is a positive integer greater than 1), the movement behavior relationship information of each traffic participant can be represented as an N-1 one-dimensional vector, which is used to describe the relationship between the participant and other traffic participants in the preset area.

[0068] To facilitate processing, electronic devices can input the structure graph into a graph neural network (GCN) to obtain motion behavior relationship information output by the GCN after processing the structure graph. Here, the GCN can refer to a Graph Convolutional Network (GCN). The GCN can use convolution operations on the aforementioned structure graph to extract information, realizing the process of identifying traversers, courteous parties, and irrelevant parties. Using GCN to process graph nodes within the structure graph requires less computation and is more computationally efficient.

[0069] It should be noted that, for the sake of simplicity, the aforementioned method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders.

[0070] like Figure 6 The diagram shown is a schematic diagram of a motion behavior relationship determination device 600 provided in an embodiment of this application. The motion behavior relationship determination device 600 is disposed on an electronic device.

[0071] Specifically, the device 600 for determining the relationship of motion behavior may include:

[0072] The acquisition unit 601 is used to acquire participant information of each traffic participant and road information of the road. The participant information includes the current position and current speed of the traffic participant on the road, and the road information includes the traffic information of the lanes on the road.

[0073] The trajectory determination unit 602 is used to determine the future trajectory of each traffic participant based on the participant information and the road information;

[0074] The relationship determination unit 603 is used to determine the motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants. The motion behavior relationship information is used to predict the trajectory of traffic participants.

[0075] In some embodiments of this application, the relationship determination unit 603 described above can be specifically used to: construct graph nodes that correspond one-to-one with each traffic participant; based on the relative positional relationship between the future trajectories of different traffic participants, when two traffic participants have intersecting future trajectories, establish a connection between the graph nodes corresponding to the two traffic participants to obtain a structure graph; and determine the motion behavior relationship information based on the structure graph.

[0076] In some embodiments of this application, the relationship determination unit 603 described above can be specifically used to: for a target graph node in the structural graph, determine the intersection point of the future trajectory corresponding to the target graph node and the future trajectory corresponding to the target connected node, wherein the target connected node is a graph node connected to the target graph node; and determine the motion behavior relationship information between the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node based on a first estimated time for the traffic participant corresponding to the target graph node to reach the intersection point and a second estimated time for the traffic participant corresponding to the target connected node to reach the intersection point.

[0077] In some embodiments of this application, the relationship determination unit 603 described above can be specifically used to: if the future trajectory corresponding to the target graph node does not intersect with the future trajectory corresponding to the target connected node, then determine that the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node are unrelated to each other.

[0078] In some embodiments of this application, the relationship determination unit 603 described above can be specifically used to: input the structure graph into a graph neural network, and obtain the motion behavior relationship information that is processed by the graph neural network and output by the graph neural network.

[0079] In some embodiments of this application, the trajectory determination unit 602 described above can be specifically used to: predict the future position of each traffic participant after a preset time period based on the participant information and the road information; and determine the future trajectory of each traffic participant based on the current position and the future position of each traffic participant.

[0080] In some embodiments of this application, the trajectory determination unit 602 described above can be specifically used to: obtain a target layer in a map, wherein the target layer records the lane lines and lane center lines of the lane; and draw a trajectory on the target layer based on the current position and the future position of each traffic participant to obtain the future trajectory of each traffic participant.

[0081] It should be noted that, for the sake of convenience and brevity, the specific working process of the above-mentioned motion behavior relationship determination device 600 can be found in the following reference: Figures 1 to 5The corresponding process of the method will not be described in detail here.

[0082] like Figure 7 The diagram shown is a schematic representation of an electronic device provided in an embodiment of this application. Specifically, the electronic device 7 may include: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70, such as a program for determining motion behavior relationships. When the processor 70 executes the computer program 72, it implements the steps in the various embodiments of the methods for determining motion behavior relationships described above, for example... Figure 1 Steps S101 to S103 are shown. Alternatively, when the processor 70 executes the computer program 72, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 6 The functions of the acquisition unit 601, trajectory determination unit 602, and relationship determination unit 603 are shown.

[0083] The computer program can be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0084] For example, the computer program can be divided into: an acquisition unit, a trajectory determination unit, and a relationship determination unit. The specific functions of each unit are as follows: the acquisition unit is used to acquire participant information for each traffic participant and road information, wherein the participant information includes the current position and current speed of the traffic participant on the road, and the road information includes lane traffic information on the road; the trajectory determination unit is used to determine the future trajectory of each traffic participant based on the participant information and the road information; the relationship determination unit is used to determine the motion behavior relationship information between traffic participants based on the relative positional relationship between the future trajectories of different traffic participants, and the motion behavior relationship information is used to predict the trajectories of traffic participants.

[0085] The electronic device may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will understand that... Figure 7 This is merely an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than illustrated, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0086] The processor 70 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0087] The memory 71 can be an internal storage unit of the electronic device, such as a hard drive or RAM. The memory 71 can also be an external storage device of the electronic device, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card. Furthermore, the memory 71 can include both internal and external storage units. The memory 71 is used to store the computer program and other programs and data required by the electronic device. The memory 71 can also be used to temporarily store data that has been output or will be output.

[0088] It should be noted that, for the sake of convenience and brevity, the structure of the above-mentioned electronic device can also be referred to the specific description of the structure in the method embodiment, which will not be repeated here.

[0089] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0090] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0091] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software 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 various specific applications, but such implementations should not be considered beyond the scope of this application.

[0092] In the embodiments provided in this application, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0095] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0096] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining relationships of motion behaviors, characterized in that, include: Obtain participant information for each traffic participant, as well as road information, wherein the participant information includes the current position and current speed of the traffic participant on the road, and the road information includes the traffic information of the lanes on the road; Based on the participant information and the road information, determine the future trajectory of each traffic participant; Construct graph nodes that correspond one-to-one with each traffic participant; Based on the relative positional relationship between the future trajectories of different traffic participants, when at least two traffic participants have intersecting future trajectories, a connection is established between the graph nodes corresponding to the at least two traffic participants to obtain a structural graph. The structure graph is input into a graph neural network to obtain motion behavior relationship information processed and output by the graph neural network. The motion behavior relationship information includes information indicating whether two traffic participants are unrelated, passing, or yielding. Unrelated means that the future trajectories of the two traffic participants do not intersect and do not affect each other. Passing means that one traffic participant has priority to pass through the intersection of two future trajectories. Yielding means that one traffic participant yields to another traffic participant. The motion behavior relationship information is used to predict the trajectory of traffic participants.

2. The method for determining the relationship of motion behavior as described in claim 1, characterized in that, The step of determining the motion behavior relationship information based on the structure diagram includes: For a target graph node in the structure graph, determine the intersection point between the future trajectory corresponding to the target graph node and the future trajectory corresponding to the target connected node, where the target connected node is a graph node connected to the target graph node; Based on the first estimated time for the traffic participant corresponding to the target graph node to reach the intersection position, and the second estimated time for the traffic participant corresponding to the target connected node to reach the intersection position, the motion behavior relationship information between the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node is determined.

3. The method for determining the relationship of motion behavior as described in claim 1, characterized in that, The step of determining the motion behavior relationship information based on the structure diagram further includes: If the future trajectory corresponding to the target graph node does not intersect with the future trajectory corresponding to the target connected node, then the traffic participant corresponding to the target graph node and the traffic participant corresponding to the target connected node are determined to be unrelated.

4. The method for determining the relationship of motion behavior as described in any one of claims 1 to 3, characterized in that, The step of determining the future trajectory of each traffic participant based on the participant information and the road information includes: Based on the participant information and the road information, predict the future location of each traffic participant after a preset time period; The future trajectory of each traffic participant is determined based on its current location and its future location.

5. The method for determining the relationship of motion behavior as described in claim 4, characterized in that, Determining the future trajectory of each traffic participant based on their current location and future location includes: Obtain the target layer in the map, the target layer recording the lane lines and lane center lines of the lane; Based on the current and future locations of each traffic participant, a trajectory is drawn on the target layer to obtain the future trajectory of each traffic participant.

6. A device for determining the relationship of motion behavior, characterized in that, include: The acquisition unit is used to acquire participant information of each traffic participant and road information of the road. The participant information includes the current position and current speed of the traffic participant on the road, and the road information includes the traffic information of the lanes on the road. The trajectory determination unit is used to determine the future trajectory of each traffic participant based on the participant information and the road information; A relationship determination unit is used to construct graph nodes that correspond one-to-one with each traffic participant. Based on the relative positional relationships between the future trajectories of different traffic participants, when at least two traffic participants have intersecting future trajectories, a connection is established between the graph nodes corresponding to the at least two traffic participants to obtain a structure graph. The structure graph is input into a graph neural network to obtain motion behavior relationship information processed and output by the graph neural network. This motion behavior relationship information includes information indicating whether two traffic participants are unrelated, passing, or yielding. Unrelated means that the future trajectories of the two traffic participants do not intersect and do not affect each other. Passing means that one traffic participant has priority in passing through the intersection of two future trajectories. Yielding means that one traffic participant yields to another. This motion behavior relationship information is used to predict the trajectories of traffic participants.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for determining the motion behavior relationship as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for determining the motion behavior relationship as described in any one of claims 1 to 5.

Images