Vehicle trajectory prediction method, device and equipment based on V2X and automatic driving vehicle

Abstract

The present disclosure provides a vehicle trajectory prediction method and device based on V2X, equipment and storage medium, which relates to the technical field of artificial intelligence, specifically to the technical field of automatic driving, intelligent transportation and deep learning. The method comprises: obtaining position information and heading angle information of a target vehicle; determining road information of a target road where the target vehicle is located in a pre-constructed road map based on the position information; determining lane change intention information of the target vehicle based on the heading angle information and the road information; and predicting a driving route of the target vehicle based on the lane change intention information and a connection relationship at an intersection where the target road is located. The vehicle trajectory prediction method based on V2X provided by the present disclosure improves the accuracy of predicting the trajectory of the target vehicle in a long time in the future.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical fields of automatic driving, intelligent transportation and deep learning, and more particularly to a vehicle trajectory prediction method and device based on V2X, an equipment and an automatic driving vehicle. BACKGROUND

[0002] V2X (vehicle to X or Vehicle to Everything) is a key technology of future intelligent transportation systems, and vehicle trajectory prediction, as a key link in V2X technology, will directly affect the development and use of subsequent V2V (vehicle-to-vehicle communication) / V2P scenarios. SUMMARY

[0003] The present disclosure provides a vehicle trajectory prediction method and device based on V2X, and an equipment and an automatic driving vehicle.

[0004] According to a first aspect of the present disclosure, a vehicle trajectory prediction method based on V2X is provided, comprising: obtaining position information and heading angle information of a target vehicle; determining road information of a target road where the target vehicle is located in a pre-constructed road map based on the position information; determining lane-changing intention information of the target vehicle based on the heading angle information and the road information; and predicting a driving route of the target vehicle based on the lane-changing intention information and a connection relationship at an intersection where the target road is located.

[0005] According to a second aspect of the present disclosure, a vehicle trajectory prediction device based on V2X is provided, comprising: an acquisition module configured to obtain position information and heading angle information of a target vehicle; a first determination module configured to determine road information of a target road where the target vehicle is located in a pre-constructed road map based on the position information; a second determination module configured to determine lane-changing intention information of the target vehicle based on the heading angle information and the road information; and a prediction module configured to predict a driving route of the target vehicle based on the lane-changing intention information and a connection relationship at an intersection where the target road is located.

[0006] According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any implementation manner of the first aspect.

[0007] According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method as described in any implementation form of the first aspect.

[0008] According to a fifth aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the method as described in any implementation form of the first aspect.

[0009] According to a sixth aspect of the present disclosure, there is provided an autonomous vehicle comprising the electronic device as described in the third aspect.

[0010] It is to be understood that what is described in this section is not intended to identify any key or essential features of embodiments of the present disclosure, nor is it meant to limit the scope of the present disclosure. Other BRIEF DESCRIPTION OF DRAWINGS

[0011] The accompanying drawings are included to provide a better understanding of the present scheme, and not to limit the present disclosure. Among them:

[0012] Figure 1 is an exemplary system architecture diagram in which the present disclosure can be applied;

[0013] Figure 2 is a flowchart of one embodiment of the V2X-based vehicle trajectory prediction method according to the present disclosure;

[0014] Figure 3 is a flowchart of another embodiment of the V2X-based vehicle trajectory prediction method according to the present disclosure;

[0015] Figure 4 is a schematic diagram of the relationship between intersection, road and lane data structures;

[0016] Figure 5 is a schematic diagram of the lane centerline and the road centerline;

[0017] Figure 6 is a schematic diagram of the position points of the lane centerline and the position points of the road centerline;

[0018] Figure 7 is a schematic diagram of the lane change intention of the target vehicle;

[0019] Figure 8 is a flowchart of yet another embodiment of the V2X-based vehicle trajectory prediction method according to the present disclosure;

[0020] Figure 9 is a structural schematic diagram of one embodiment of the V2X-based vehicle trajectory prediction device according to the present disclosure;

[0021] Figure 10 This is a block diagram of an electronic device used to implement the V2X-based vehicle trajectory prediction method of an embodiment of the present disclosure. DETAILED DESCRIPTION

[0022] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0023] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0024] Figure 1 An exemplary system architecture 100 is shown to which an embodiment of a V2X-based vehicle trajectory prediction method or a V2X-based vehicle trajectory prediction device of the present disclosure may be applied.

[0025] like Figure 1 As shown, system architecture 100 may include device 101, network 102, and target vehicle 103. Network 102 is used to provide a medium for a communication link between device 101 and target vehicle 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0026] The device 101 may be a roadside device or a background of a roadside device, and may be hardware or software.

[0027] The target vehicle 103 can interact with the device 101 via the network 102 to receive or send messages, etc. For example, the target vehicle 103 can obtain real-time location information, vehicle heading angle information, and road map data from the device 101, and then analyze and process the real-time location information, vehicle heading angle information, and road map data to generate a processing result (e.g., the target vehicle's driving route).

[0028] It should be noted that the V2X-based vehicle trajectory prediction method provided in the embodiments of the present disclosure is generally executed by the target vehicle 103 , and accordingly, the V2X-based vehicle trajectory prediction device is generally provided in the target vehicle 103 .

[0029] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0030] With reference to both Figure 2 which shows a flow 200 of one embodiment of the V2X-based vehicle trajectory prediction method according to the present disclosure. The V2X-based vehicle trajectory prediction method comprises the following steps:

[0031] Step 201, obtaining the position information and the heading angle information of the target vehicle.

[0032] In the present embodiment, the execution subject of the V2X-based vehicle trajectory prediction method (for example Figure 1 The target vehicle 103 shown in the figure will obtain the position information and the heading angle information of the target vehicle. The target vehicle in the present embodiment can be an autonomous vehicle, or a common vehicle, which needs to be equipped with a V2X device to obtain the nearby map information broadcast by the nearby RSU (Road Side Unit). The road side device refers to the device installed on both sides of the road, which can be a road side unit RSU, a road test computing unit RSCU (Road Side Computing Unit), or a multi-access edge computing unit MEC (Multi-access Edge Computing). As a transmission intermediary of messages, the road side device realizes the transmission of road traffic and other road side messages collected by the road side device to assist vehicles in safe driving.

[0033] It should be noted that V2X refers to vehicle wireless communication technology, also known as vehicle-to-everything communication, which enables vehicles to obtain real-time road conditions, road information, pedestrian information, and other traffic information, improve driving safety, reduce congestion, and improve traffic efficiency. Among them, V represents a vehicle, and X represents any object interacting with the vehicle, and the current X mainly includes vehicles (Vehicle to Vehicle, V2V), pedestrians (Vehicle to Pedestrian, V2P), traffic road infrastructure (Vehicle to Infrastructure, V2I), and networks (Vehicle to Network, V2N). V2X technology can be applied to various vehicles, and vehicles equipped with V2X technology related devices can receive road side messages.

[0034] In addition, the common vehicle can also be equipped with a GNSS-IMU combined inertial navigation device, and the device parameters are calibrated in advance, so as to obtain the real-time position, speed, acceleration, yaw rate, heading angle and other information of the target vehicle during driving.

[0035] Here, in order to facilitate the calculation and representation of coordinate positions, the above execution subject will establish an ENU coordinate system (East-North-Sky coordinate system) with the target vehicle position as the origin, and convert the position information of the target vehicle in the WGS84 coordinate system (World Geodetic System 1984, Geodetic Coordinate System) to the ENU coordinate system.

[0036] Step 202, determining the road information of the target road where the target vehicle is located in the pre-constructed road map based on the position information.

[0037] In this embodiment, the above execution subject will determine the road information of the target road where the target vehicle is located in the pre-constructed road map based on the position information. The above execution subject will obtain the nearby map information broadcast by the nearby RSU based on the position information of the target vehicle, and the obtained map includes a plurality of rectangular regions. First, each intersection is a node (Node), and the node contains at least one road (Link) leading to the intersection. Each road contains at least one lane (Lane). The attributes of the node include node index (Node ID) and node center position. The attributes of the road include road index (Link ID), information connected to the upstream node, road width, and column position point information in the road. The attributes of the lane include lane index (Lane ID), lane width, information connected to the downstream lane, and some column position point information of the lane. A series of position points of the road are constructed into a rectangular region (Segment) by two position points and combined with the road width. A series of position points of the lane are constructed into a rectangular region by two position points and combined with the lane width.

[0038] Then, the position information of the target vehicle is matched with the obtained map. Specifically, the above execution subject will first obtain all the nodes in the map, calculate the distance between the position information of the target vehicle and the center position of the node, and determine the matching node list from all the nodes based on the distance value. Then, the nodes in the matching node list are traversed again to determine whether the position of the target vehicle is in the rectangular region of a certain road, and further determine whether the vehicle position is in the rectangular region of a certain lane. If so, the rectangular region is determined as the target road where the target vehicle is located, and the node index, road index and lane index information corresponding to the rectangular region are obtained.

[0039] Step 203, determining the lane change intention information of the target vehicle based on the heading angle information and the road information.

[0040] In the embodiment, the execution subject determines the lane-changing intention information of the target vehicle based on the heading angle information and the road information. First, the execution subject can obtain the heading angle information of the target vehicle through the GNSS-IMU integrated inertial navigation equipment installed on the target vehicle. The vehicle heading angle generally refers to the angle between the vehicle mass center velocity and the transverse axis in the ground coordinate system. Then, the execution subject calculates the direction angle of the position point based on the front and rear position points of the rectangular region where the target vehicle is located, and then calculates the included angle between the heading angle and the direction angle. If the included angle is less than a (a is the maximum angle threshold of whether to drive along the road), it is considered that the vehicle is driving along the road or lane, and if the included angle is greater than a and less than b (b is the maximum angle threshold of whether to change lanes), it is considered that the vehicle is changing lanes, wherein the lane changing can include left turn, right turn and U-turn.

[0041] In step 204, the driving route of the target vehicle is predicted based on the lane-changing intention information and the connection relationship of the target road at the intersection.

[0042] In the embodiment, the execution subject predicts the driving route of the target vehicle based on the lane-changing intention information and the connection relationship of the target road at the intersection. If the execution subject determines that the target vehicle is going to change lanes, it obtains the connection information of the target lane after changing lanes at the intersection, wherein the connection information includes upstream lane index and downstream lane index information. The upstream lane is the last lane that the target vehicle drives through, and the downstream lane is the next lane that the target vehicle is about to drive into. If the execution subject determines that the target vehicle will not change lanes, it obtains the connection information of the current lane at the intersection.

[0043] Then, the execution subject obtains the Lane ID of the lane where the target vehicle is located when entering the intersection, and obtains the turning attribute allowed by the lane. If the turning attribute allows straight driving, it is predicted that the lane-changing intention of the target vehicle is straight driving; if the turning attribute only allows left turn, it is predicted that the lane-changing intention of the target vehicle is left turn; if the turning attribute only allows right turn, it is predicted that the lane-changing intention of the target vehicle is right turn; if the turning attribute only allows U-turn, it is predicted that the lane-changing intention of the target vehicle is U-turn. By judging the turning behavior of the vehicle at the intersection, the downstream lane index that meets the condition is calculated, and the downstream lane with the same upstream lane index as the lane to be driven into is preferentially selected. According to the current lane index, the current lane route is obtained, whether the vehicle is currently changing lanes is judged, the lane route after changing lanes is obtained, the lane route in the intersection and the downstream lane route are obtained according to the predicted intention, and the predicted trajectory route of the target vehicle to be driven is calculated.

[0044] The V2X-based vehicle trajectory prediction method provided in the disclosed embodiment first obtains the target vehicle's location and heading information; then, based on the location information, determines the target vehicle's road information within a pre-built road map; then, based on the heading information and road information, determines the target vehicle's lane change intention; and finally, based on the lane change intention information and the connectivity at the intersection where the target road is located, predicts the target vehicle's route. The V2X-based vehicle trajectory prediction method in this embodiment, which references map information obtained from roadside equipment, can accurately predict the target vehicle's trajectory for the next 5 to 20 seconds, thereby improving the accuracy of predicting the target vehicle's trajectory over a longer period of time. It also serves as an early warning in V2X applications, effectively informing the driver of the route of vehicles near their blind spots and reducing the risk of collision.

[0045] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0046] Continue to refer Figure 3 , Figure 3 FIG3 shows a process 300 of another embodiment of a V2X-based vehicle trajectory prediction method according to the present disclosure. The V2X-based vehicle trajectory prediction method includes the following steps:

[0047] Step 301: Acquire the location information and heading angle information of the target vehicle.

[0048] Step 301 is basically the same as step 201 in the aforementioned embodiment. For the specific implementation method, please refer to the aforementioned description of step 201, which will not be repeated here.

[0049] Step 302: Calculate the distance between the location information and each road node in the road map.

[0050] In this embodiment, the execution subject of the V2X-based vehicle trajectory prediction method (e.g. Figure 1 The target vehicle 103 shown will calculate the distance between the location information and each road node in the road map.

[0051] Prior to this, the execution entity will pre-establish a data structure for describing the map content. Figure 4 It is a schematic diagram of the data structure relationship between intersections, roads and lanes, such as Figure 4As shown, the data structure includes: each intersection is a node (Node), the node contains at least one road (Link) leading to the intersection, and each road contains at least one lane (Lane). The attributes of the node include the node index (Node ID) and the node center position. The attributes of the road include the road index (Link ID), information about the connection to the upstream node, the road width, and the column position point information in the road. The attributes of the lane include the lane index (Lane ID), the lane width, information about the connection to the downstream lane, and some column position point information in the lane. A series of road position points are combined with the road width to construct a road rectangular area (Segment). The edges of the road rectangular area are the road boundaries, and the center line of the road rectangular area is the road center line. A series of lane position points are combined with the lane width to construct a lane rectangular area. The center line of the lane rectangular area is the lane center line. Figure 5 is a schematic diagram of the lane centerline and the road centerline, such as Figure 5 As shown, the road centerline divides the road into two lanes, and each lane has a lane centerline. Figure 6 It is a schematic diagram of the position points of the lane centerline and the road centerline, such as Figure 6 As shown, two consecutive position points of the lane combined with the lane width construct a lane rectangular area, and two consecutive position points of the road combined with the road width construct a road rectangular area. Here, the distance between two consecutive position points of the lane and two consecutive position points of the road can be set according to different situations, and this embodiment does not make specific limitations on this.

[0052] Here, the execution entity obtains all nodes in the map data structure and calculates the distance between the target vehicle's position and the center position of each node.

[0053] Step 303: Compare the distance with a preset value, and obtain a matching node list based on the comparison result.

[0054] In this embodiment, the execution entity compares the distance with a preset value and obtains a matching node list based on the comparison result. If the distance is less than the preset value, the node is added to the matching node list.

[0055] Step 304: traverse the nodes in the matching node list to determine the node information of the target road where the target vehicle is located.

[0056] In this embodiment, the execution entity traverses the nodes in the matching node list to determine the node information of the target road where the target vehicle is located. The node information includes node index information, road index information, and lane index information. Specifically, the execution entity traverses all nodes in the matching node list to determine whether the vehicle's position is within a rectangular area of ​​a road. If so, the road is identified as the target road. The execution entity then determines whether the vehicle's position is within a rectangular area of ​​a lane within the road. If so, the execution entity obtains the node index, road index, and lane index information corresponding to the rectangular area where the target vehicle is located.

[0057] Through the above steps, the road information of the target vehicle on the map is accurately determined.

[0058] Step 305 : Calculate the road direction angle based on the position points in the rectangular area corresponding to the target road.

[0059] In this embodiment, the execution entity calculates the road heading angle based on the points within the rectangular area corresponding to the target road. Since the road rectangular area is formed by combining two consecutive points with the road width, the execution entity can calculate the road heading angle based on the two points within the rectangular area corresponding to the target road. The road heading angle is the direction of the segment.

[0060] Step 306: Calculate the angle between the heading angle information and the road direction angle.

[0061] In this embodiment, the execution entity can calculate the angle between the heading angle information and the road direction angle. Specifically, the execution entity calculates the target vehicle's direction based on the heading angle of the target vehicle and the road direction based on the position points within the rectangular area corresponding to the target road. Subsequently, the execution entity can calculate the angle between these two vectors.

[0062] Step 307 : Determine lane change intention information of the target vehicle based on the included angle.

[0063] In this embodiment, the execution entity can determine the target vehicle's lane change intention based on the included angle. Specifically, the execution entity compares the calculated included angle with a preset value and, based on the comparison result, determines whether the target vehicle intends to change lanes. This accurately determines the target vehicle's lane change intention.

[0064] In some optional implementations of this embodiment, step 307 includes: if the angle is less than a first preset angle value, determining that the target vehicle has no intention to change lanes; if the angle is greater than the first preset angle value, determining that the target vehicle is about to change lanes.

[0065] In the present implementation, if the included angle is less than a first preset angle value a (a is a maximum angle threshold for whether to travel along the road), it is considered that the target vehicle travels along the road or lane where it is located, i.e., no lane-changing intention. If the included angle is greater than a, it is considered that the target vehicle is about to change lanes.

[0066] In some optional implementations of the present embodiment, if the included angle is greater than the first preset angle value, it is determined that the target vehicle is about to change lanes, including: if the included angle is greater than the first preset angle value and less than a second preset angle value, it is determined that the lane-changing intention of the target vehicle is left turn or right turn; and if the included angle is greater than the second preset angle value, it is determined that the lane-changing intention of the target vehicle is U-turn.

[0067] Figure 7 For the lane-changing intention of the target vehicle, as shown in Figure 7 if the included angle is greater than a and less than a second preset angle value b (b is a maximum angle threshold for whether to change lanes), it is considered that the lane-changing intention of the target vehicle is left turn or right turn; and if the included angle is greater than b, it is determined that the lane-changing intention of the target vehicle is U-turn. Thus, the lane-changing intention of the target vehicle is accurately determined.

[0068] Step 308, based on the lane-changing intention information and the connection relationship of the target road at the intersection, the driving route of the target vehicle is predicted.

[0069] Step 308 is basically the same as step 204 of the foregoing embodiment, and the specific implementation can refer to the foregoing description of step 204, which will not be described here again.

[0070] As can be seen from Figure 3 , compared with Figure 2 the corresponding embodiment, the vehicle trajectory prediction method based on V2X in the present embodiment highlights the steps of determining the road information of the target road where the target vehicle is located in the road map and determining the lane-changing intention of the target vehicle, and in the process, the map information obtained from the roadside device is referred to, thereby improving the accuracy of predicting the trajectory of the target vehicle in a longer future time.

[0071] Continuing to refer to Figure 8 , Figure 8 Fig. 800 shows a flow 800 of still another embodiment of the vehicle trajectory prediction method based on V2X according to the present disclosure. The vehicle trajectory prediction method based on V2X includes the following steps:

[0072] Step 801, obtaining the position information and the heading angle information of the target vehicle.

[0073] Step 802, respectively calculating the distance between the position information and each road node in the road map.

[0074] Step 803, compare the distance with a preset value, and obtain a matching node list based on a comparison result.

[0075] Step 804, traverse the nodes in the matching node list to determine node information of a target road where the target vehicle is located.

[0076] Step 805, calculate a road direction angle based on the position point in the rectangular region corresponding to the target road.

[0077] Step 806, calculate an included angle between the heading angle information and the road direction angle.

[0078] Step 807, determine the lane change intention information of the target vehicle based on the included angle.

[0079] Steps 801-807 are basically the same as steps 301-307 of the foregoing embodiment, and the specific implementation manner can be referred to the foregoing description of steps 301-307, which will not be described here again.

[0080] Step 808, in response to determining that the target vehicle is about to change lanes, obtain a connection relationship at a road intersection where the target road is located.

[0081] In the embodiment, the execution subject (for example, the target vehicle 103 shown in FIG. 1) of the vehicle trajectory prediction method based on V2X will obtain the connection relationship at the road intersection where the target road is located if it is determined that the target vehicle is about to change lanes, wherein the connection relationship includes index information of an upstream lane and index information of a downstream lane. Figure 1

[0082] Step 809, determine lane change information based on the lane change attribute information of the target road and the connection relationship at the road intersection where the target road is located.

[0083] In the embodiment, the execution subject will determine the lane change information based on the lane change attribute information of the target road and the connection relationship at the road intersection where the target road is located. That is, the execution subject will obtain a Lane ID of a lane where the target vehicle is located when entering the road intersection, and obtain a turning attribute (that is, a lane change attribute) allowed by the lane based on the Lane ID, for example, left turn allowed, right turn allowed, and straight ahead allowed. Then, the lane change information is determined based on the allowed turning attribute and the connection relationship at the road intersection where the target road is located. By calculating an included angle between a lane direction and a position vector of a connected downstream lane, the included angle can be divided into four ranges: when the included angle is less than 45 degrees, the corresponding downstream lane is considered as a straight ahead lane; when the included angle is greater than 45 degrees and less than 135 degrees, the corresponding downstream lane is considered as a left turn lane or a right turn lane; and when the included angle is greater than 135 degrees, the corresponding lane is considered as a U-turn lane.

[0084] ​In some optional implementations of the embodiment, step 809 includes: if the lane-changing attribute information is left turn, taking the left downstream lane at the intersection where the target road is located as the lane-changing lane of the target vehicle; if the lane-changing attribute information is right turn, taking the right downstream lane at the intersection where the target road is located as the lane-changing lane of the target vehicle; and if the lane-changing attribute information is U-turn, taking the upstream lane at the intersection where the target road is located as the lane-changing lane of the target vehicle.

[0085] In the implementation, if the turning attribute only allows left turn, the predicted intention is determined to be left turn, and at this time, the left downstream lane at the intersection where the target road is located is taken as the lane-changing lane of the target vehicle; if the turning attribute only allows right turn, the predicted intention is determined to be right turn, and at this time, the right downstream lane at the intersection where the target road is located is taken as the lane-changing lane of the target vehicle; and if the turning attribute only allows U-turn, the predicted intention is determined to be U-turn, and at this time, the upstream lane at the intersection where the target road is located is taken as the lane-changing lane of the target vehicle. The turning behavior of the vehicle at the intersection is determined according to the intention, indexes of all downstream lanes satisfying the condition are calculated, and a downstream lane with the same index as the index of the upstream lane is preferentially selected as the lane to be driven into. The current lane line of the vehicle is obtained according to the current lane index, whether the vehicle is currently changing lane is determined, the lane line after lane changing is obtained, the lane line in the intersection and the downstream lane line are obtained according to the predicted intention, and the predicted trajectory line of the target vehicle to be driven is calculated.

[0086] Step 810, predicting the driving route of the target vehicle based on the lane-changing lane information.

[0087] In the embodiment, the above execution subject can predict the driving route of the target vehicle based on the lane-changing lane information. That is, the above execution subject generates a drivable reference path according to the current lane information, the information whether the current lane-changing behavior exists, the turning intention information at the intersection, and the corresponding downstream lane information. Then, a driving trajectory of the vehicle is calculated based on the reference path as the predicted trajectory path of the vehicle.

[0088] In some optional implementations of the embodiment, step 810 includes: generating a reference driving route based on the lane-changing lane information; generating a lateral offset based on the distance between the position information and the center line of the lane-changing lane; and generating the driving route of the target vehicle based on the reference driving route and the lateral offset.

[0089] In the implementation, the execution subject can obtain a drivable reference path through the lane information where the execution subject is currently located, the information about whether the execution subject currently has a lane-changing behavior, the turning intention information at the intersection, and the corresponding downstream lane information. A lateral offset can be obtained by calculating the distance between the vehicle and the center line of the current lane. A driving trajectory of the vehicle can be calculated as a predicted trajectory path of the vehicle through the drivable reference path and the lateral offset value. Thus, the trajectory of the target vehicle can be accurately predicted.

[0090] It can be seen from Figure 8 that, compared with Figure 3 the corresponding embodiment, the vehicle trajectory prediction method based on V2X in the embodiment highlights the step of predicting the driving route of the target vehicle based on the lane-changing intention information and the connection relationship at the intersection where the target road is located, thereby improving the accuracy of predicting the trajectory of the target vehicle in a relatively long future time.

[0091] Further reference Figure 9 is made to the method shown in each of the above figures, the disclosure provides an embodiment of a vehicle trajectory prediction device based on V2X. The device embodiment corresponds to the method embodiment shown in Figure 2 , and the device can be specifically applied to various electronic devices.

[0092] As shown in Figure 9 , the vehicle trajectory prediction device 900 based on V2X in the embodiment includes an acquisition module 901, a first determination module 902, a second determination module 903, and a prediction module 904. The acquisition module 901 is configured to acquire position information and heading angle information of a target vehicle. The first determination module 902 is configured to determine road information of a target road where the target vehicle is located in a pre-constructed road map based on the position information. The second determination module 903 is configured to determine lane-changing intention information of the target vehicle based on the heading angle information and the road information. The prediction module 904 is configured to predict a driving route of the target vehicle based on the lane-changing intention information and a connection relationship at an intersection where the target road is located.

[0093] In the embodiment, in the vehicle trajectory prediction device 900 based on V2X: the specific processing of the acquisition module 901, the first determination module 902, the second determination module 903, and the prediction module 904 and the technical effects brought by the specific processing can be respectively referred to the related descriptions of steps 201-204 in the corresponding embodiment, which will not be repeated here. Figure 2

[0094] ​In some optional implementations of the present embodiment, the road map comprises at least one road node; and the first determining module is further configured to: calculate distances between the position information and respective road nodes in the road map respectively; compare the distances with a preset value, and obtain a matching node list based on a comparison result; traverse the nodes in the matching node list, and determine node information of a target road where the target vehicle is located, the node information comprising index information of the node, index information of the road, and index information of a lane.

[0095] In some optional implementations of the present embodiment, the second determining module comprises: a first calculating submodule configured to calculate a road direction angle based on the position point in the rectangular region corresponding to the target road; a second calculating submodule configured to calculate an included angle between the heading angle information and the road direction angle; and a first determining submodule configured to determine the lane-changing intention information of the target vehicle based on the included angle.

[0096] In some optional implementations of the present embodiment, the first determining submodule comprises: a first determining unit configured to determine that the target vehicle has no lane-changing intention if the included angle is less than a first preset angle value; and a second determining unit configured to determine that the target vehicle is about to change lanes if the included angle is greater than the first preset angle value.

[0097] In some optional implementations of the present embodiment, the second determining unit is further configured to: determine that the lane-changing intention of the target vehicle is to turn left or right if the included angle is greater than the first preset angle value and less than a second preset angle value; and determine that the lane-changing intention of the target vehicle is to make a U-turn if the included angle is greater than the second preset angle value.

[0098] In some optional implementations of the present embodiment, the prediction module comprises: an obtaining submodule configured to, in response to determining that the target vehicle is about to change lanes, obtain a connection relationship at a road intersection where the target road is located, the connection relationship comprising index information of an upstream lane and index information of a downstream lane; a second determining submodule configured to determine lane-changing lane information based on the lane-changing attribute information of the target road and the connection relationship at the road intersection where the target road is located; and a prediction submodule configured to predict a driving route of the target vehicle based on the lane-changing lane information.

[0099] In some optional implementations of the present embodiment, the second determining submodule is further configured to: take a left-side downstream lane at the road intersection where the target road is located as the lane-changing lane of the target vehicle if the lane-changing attribute information is to turn left; take a right-side downstream lane at the road intersection where the target road is located as the lane-changing lane of the target vehicle if the lane-changing attribute information is to turn right; and take an upstream lane at the road intersection where the target road is located as the lane-changing lane of the target vehicle if the lane-changing attribute information is to make a U-turn.

[0100] In some optional implementations of the present embodiment, the prediction submodule is further configured to: generate a reference travel route based on the lane-changing lane information; generate a lateral offset based on the distance between the position information and the center line of the lane-changing lane; and generate a travel route of the target vehicle based on the reference travel route and the lateral offset.

[0101] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, a computer program product, and an autonomous vehicle.

[0102] Figure 10 A schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0103] As shown in Figure 10 The electronic device 1000 includes a computing unit 1001 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a random access memory (RAM) 1003. Various programs and data required for the operation of the electronic device 1000 can also be stored in the RAM 1003. The computing unit 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0104] Various components in the electronic device 1000 are connected to the I / O interface 1005, including an input unit 1006, such as a keyboard, a mouse, and the like; an output unit 1007, such as various types of displays, speakers, and the like; the storage unit 1008, such as a magnetic disk, an optical disk, and the like; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1009 allows the electronic device 1000 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0105] The computing unit 1001 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, and the like. The computing unit 1001 performs various methods and processes described above, such as the V2X-based vehicle trajectory prediction method. For example, in some embodiments, the V2X-based vehicle trajectory prediction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1000 via the ROM 1002 and / or the communication unit 1009. When the computer program is loaded onto the RAM 1003 and executed by the computing unit 1001, one or more steps of the V2X-based vehicle trajectory prediction method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 can be configured to perform the V2X-based vehicle trajectory prediction method by any other appropriate means, such as by means of firmware.

[0106] The autonomous vehicle provided by the present disclosure can include the electronic device as shown above, which can be capable of implementing the V2X-based vehicle trajectory prediction method described in any of the embodiments above when executed by the processor thereof. Figure 10 The autonomous vehicle provided by the present disclosure can include the electronic device as shown above, which can be capable of implementing the V2X-based vehicle trajectory prediction method described in any of the embodiments above when executed by the processor thereof.

[0107] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0108] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package, or entirely on a remote machine or server.

[0109] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0110] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0111] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of these, such as client- server, peer-to-peer, or cloud computing. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0112] Cloud computing refers to a technology system that accesses elastic scalable shared physical or virtual resource pools through a network, the resources can include servers, operating systems, networks, software, applications or storage devices, etc., and the resources can be deployed and managed in a demand-driven and self-service manner. Through cloud computing technology, efficient and powerful data processing capabilities can be provided for artificial intelligence, blockchain and other technology applications and model training.

[0113] The computer system can include clients and servers. A client and a server are generally remote from each other and typically interact through a communication network. The relationship of client and server is one of communication and distribution, with the server generally providing communication and distribution services to the client. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0114] It should be understood that the various forms of flow shown above can be used to reorder, add or delete steps. For example, the steps described in the present disclosure can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solutions of the present disclosure can be achieved, which are not limited herein.

[0115] The above detailed description does not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent replacements and improvements within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A vehicle trajectory prediction method based on V2X, comprising: Obtain the target vehicle's location information and heading angle information; Determining, based on the position information, road information of a target road located in a pre-constructed road map of the target vehicle, wherein the road map is constructed based on map information broadcast by a roadside device, the road map includes at least one rectangular area, the rectangular area including a road rectangular area and a lane rectangular area, the road map includes at least one road node, and the road information includes index information of the node corresponding to the rectangular area where the target vehicle is located, road index information, and lane index information; determining lane change intention information of the target vehicle based on the heading angle information and the road information; Predicting a driving route of the target vehicle based on the lane change intention information and a connection relationship at the intersection where the target road is located; Wherein, determining the road information of the target road where the target vehicle is located in the pre-constructed road map based on the position information includes: respectively calculating the distance between the position information and each road node in the road map; Comparing the distance with a preset value, and obtaining a matching node list based on the comparison result; Traversing the nodes in the matching node list, determining the road rectangular area and lane rectangular area where the target vehicle is located according to the location information, and obtaining index information of the nodes and roads corresponding to the road rectangular area and index information of the lanes corresponding to the lane rectangular area; Wherein, determining the lane change intention information of the target vehicle based on the heading angle information and the road information includes: Calculating a road direction angle based on position points in a rectangular area corresponding to the target road; Calculating the angle between the heading angle information and the road direction angle; Lane change intention information of the target vehicle is determined based on the angle.

2. The method according to claim 1, wherein The determining the lane change intention information of the target vehicle based on the included angle includes: If the included angle is less than a first preset angle value, it is determined that the target vehicle has no intention to change lanes; If the included angle is greater than the first preset angle value, it is determined that the target vehicle is about to change lanes.

3. The method according to claim 2, wherein: If the included angle is greater than the first preset angle value, determining that the target vehicle is about to change lanes includes: If the included angle is greater than the first preset angle value and less than the second preset angle value, determining that the lane change intention of the target vehicle is to turn left or right; If the included angle is greater than the second preset angle value, it is determined that the lane change intention of the target vehicle is a U-turn.

4. The method according to claim 3, wherein: The predicting the driving route of the target vehicle based on the lane change intention information and the connection relationship at the intersection where the target road is located includes: In response to determining that the target vehicle is about to change lanes, obtaining a connection relationship at an intersection where the target road is located, the connection relationship including index information of an upstream lane and index information of a downstream lane; Determining lane change lane information based on the lane change attribute information of the target road and the connection relationship at the intersection where the target road is located; A driving route of the target vehicle is predicted based on the lane change lane information.

5. The method according to claim 4, wherein The determining of lane change lane information based on the lane change attribute information of the target road and the connection relationship at the intersection where the target road is located includes: If the lane change attribute information is a left turn, the left downstream lane at the intersection where the target road is located is used as the lane change lane for the target vehicle; If the lane change attribute information is a right turn, the right downstream lane at the intersection where the target road is located is used as the lane change lane of the target vehicle; If the lane change attribute information is a U-turn, the upstream lane at the intersection where the target road is located is used as the lane change lane of the target vehicle.

6. The method according to claim 5, wherein: The predicting the driving route of the target vehicle based on the lane change lane information includes: generating a reference driving route based on the lane change lane information; generating a lateral offset based on a distance between the position information and a center line of the lane change lane; A driving route of the target vehicle is generated based on the reference driving route and the lateral offset.

7. A vehicle trajectory prediction device based on V2X, comprising: an acquisition module, configured to acquire position information and heading angle information of a target vehicle; a first determining module configured to determine, based on the position information, road information of a target road located by the target vehicle in a pre-constructed road map, wherein the road map is constructed based on map information broadcast by a roadside device, the road map includes at least one rectangular area, the rectangular area includes a road rectangular area and a lane rectangular area, the road map includes at least one road node, and the road information includes index information of the node corresponding to the rectangular area where the target vehicle is located, index information of the road, and index information of the lane; a second determining module configured to determine lane change intention information of the target vehicle based on the heading angle information and the road information; a prediction module configured to predict a travel route of the target vehicle based on the lane change intention information and a connection relationship at the intersection where the target road is located; Wherein, the first determining module is further configured to: respectively calculating the distance between the position information and each road node in the road map; Comparing the distance with a preset value, and obtaining a matching node list based on the comparison result; Traversing the nodes in the matching node list, determining the road rectangular area and lane rectangular area where the target vehicle is located according to the location information, and obtaining index information of the nodes and roads corresponding to the road rectangular area and index information of the lanes corresponding to the lane rectangular area; The second determining module includes: A first calculation submodule is configured to calculate a road direction angle based on position points in a rectangular area corresponding to the target road; A second calculation submodule is configured to calculate the angle between the heading angle information and the road direction angle; The first determining submodule is configured to determine lane-changing intention information of the target vehicle based on the included angle.

8. The device according to claim 7, wherein The first determining submodule includes: a first determining unit configured to determine that the target vehicle has no lane change intention if the included angle is less than a first preset angle value; The second determining unit is configured to determine that the target vehicle is about to change lanes if the included angle is greater than the first preset angle value.

9. The device according to claim 8, wherein The second determining unit is further configured to: If the included angle is greater than the first preset angle value and less than the second preset angle value, determining that the lane change intention of the target vehicle is to turn left or right; If the included angle is greater than the second preset angle value, it is determined that the lane change intention of the target vehicle is a U-turn.

10. The device according to claim 9, wherein The prediction module includes: an acquisition submodule configured to, in response to determining that the target vehicle is about to change lanes, acquire a connection relationship at an intersection where the target road is located, the connection relationship including index information of an upstream lane and index information of a downstream lane; a second determining submodule, configured to determine lane change lane information based on the lane change attribute information of the target road and a connection relationship at an intersection where the target road is located; The prediction submodule is configured to predict the driving route of the target vehicle based on the lane change lane information.

11. The device according to claim 10, wherein The second determining submodule is further configured to: If the lane change attribute information is a left turn, the left downstream lane at the intersection where the target road is located is used as the lane change lane for the target vehicle; If the lane change attribute information is a right turn, the right downstream lane at the intersection where the target road is located is used as the lane change lane of the target vehicle; If the lane change attribute information is a U-turn, the upstream lane at the intersection where the target road is located is used as the lane change lane of the target vehicle.

12. The device according to claim 11, wherein The prediction submodule is further configured to: generating a reference driving route based on the lane change lane information; generating a lateral offset based on a distance between the position information and a center line of the lane change lane; A driving route of the target vehicle is generated based on the reference driving route and the lateral offset.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to cause the computer to execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 6.

16. An autonomous driving vehicle comprising the electronic device according to claim 13.

Images