CN113788015B - Method, device and equipment for determining vehicle track and storage medium - Google Patents
Method, device and equipment for determining vehicle track and storage medium Download PDFInfo
- Publication number
- CN113788015B CN113788015B CN202110889630.9A CN202110889630A CN113788015B CN 113788015 B CN113788015 B CN 113788015B CN 202110889630 A CN202110889630 A CN 202110889630A CN 113788015 B CN113788015 B CN 113788015B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- node
- edge
- tested
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000011218 segmentation Effects 0.000 claims abstract description 27
- 238000003062 neural network model Methods 0.000 claims description 43
- 238000012545 processing Methods 0.000 claims description 29
- 230000007613 environmental effect Effects 0.000 claims description 26
- 230000002776 aggregation Effects 0.000 claims description 21
- 238000004220 aggregation Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 239000002243 precursor Substances 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 12
- 238000013461 design Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000004931 aggregating effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/095—Predicting travel path or likelihood of collision
- B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/146—Display means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/404—Characteristics
- B60W2554/4041—Position
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/80—Spatial relation or speed relative to objects
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The method comprises the steps of determining a running track of a vehicle to be detected in second preset time and displaying the running track of the vehicle to be detected in the second preset time by acquiring vehicle characteristics of the vehicle to be detected and vehicle characteristics of other vehicles in first preset time and environment characteristics in a preset range with the vehicle to be detected as the center and based on a lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of the other vehicles and the environment characteristics. According to the technical scheme, the position data of the vehicle to be predicted and other vehicles in the preset range, the coordinate information of each section of the lane and the steering type of each section are used, so that the predicted track of the vehicle is more consistent with an actual scene, and the prediction accuracy of the track of the vehicle is improved.
Description
Technical Field
The present application relates to the field of automatic driving technologies, and in particular, to a method, an apparatus, a device, and a storage medium for determining a vehicle trajectory.
Background
Trajectory prediction is widely applied to the intelligent fields of robots, automatic driving automobile route planning and the like, and provides reference for the running changes of vehicles or robots and the like in future trajectories (for example, in the next seconds).
In the prior art, taking the prediction of the trajectory of the vehicle a as an example, the operation information (for example, operation and position data) of the vehicle B around the vehicle a is generally collected and analyzed to obtain the influence that the vehicle B may have on the trajectory of the vehicle a, so as to determine the operation trajectory of the vehicle a after the current time.
However, the prediction method in the prior art only starts from the operation information of the vehicle B and the vehicle a, and does not consider the actual vehicle operation scene and the like, so that the vehicle trajectory prediction result is inaccurate.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a storage medium for determining a vehicle track, which are used for solving the problem of inaccurate prediction of the vehicle track in the prior art.
In a first aspect, an embodiment of the present application provides a method for determining a vehicle trajectory, including:
the method comprises the steps of obtaining vehicle characteristics of a vehicle to be tested and vehicle characteristics of other vehicles within a first preset time, wherein the other vehicles are vehicles within a preset range with the vehicle to be tested as a center, and the vehicle characteristics of the vehicles comprise position data of the vehicles;
acquiring environmental characteristics within a preset range by taking the vehicle to be detected as a center, wherein the environmental characteristics comprise coordinate information of each section of the lane and steering types of each section;
determining a running track of the vehicle to be detected in a second preset time based on a lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles and the environment characteristics, wherein the first preset time is before the second preset time, and the lane segmentation heterogeneous graph is a vehicle-segmentation relational graph established by taking the vehicle to be detected, the other vehicles and each segment as a node;
and displaying the running track of the vehicle to be tested.
In a possible design of the first aspect, the determining a driving track of the vehicle to be tested within a second preset time based on the lane segmentation heterogeneous map, the vehicle characteristics of the vehicle to be tested, the vehicle characteristics of the other vehicles, and the environmental characteristics includes:
in the lane segmentation heterogeneous graph, determining an edge characteristic of the vehicle to be detected according to a node, a first node and a second node corresponding to the vehicle to be detected, where the first node is a node of a lane where the vehicle to be detected is located, the second node is a node of a lane adjacent to the first node, and the edge characteristic includes: an edge feature of a first edge type and an edge feature of a second edge type, the edge feature of the first edge type comprising at least one of: the relative angle of the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, the edge characteristics of the second edge type include at least one of the following: the relative angle of the second node to the first node, the relative distance of the second node to the first node, the edge type including: the first edge type is the type of an edge between the vehicle to be tested and the first node, and the second edge type is the type of an edge between the first node and the second node;
and determining the running track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics within the preset range and the side characteristics of the vehicle to be detected.
In this possible design, the determining a driving track of the vehicle to be tested within a second preset time according to the vehicle characteristics of the vehicle to be tested, the environmental characteristics corresponding to the first node and the second node, and the edge characteristics of the vehicle to be tested includes:
inputting the vehicle characteristics of the vehicle to be detected into a first preset neural network model to obtain the node characteristics of the vehicle to be detected, wherein the first preset neural network model is used for extracting initial characteristics in the vehicle characteristics;
inputting the environmental features corresponding to the first node and the second node into a second preset neural network model to obtain the node features of the first node and the second node, wherein the second preset neural network model is used for extracting initial features in the node features;
inputting the edge features of the vehicle to be detected into a third preset neural network model to obtain target edge features, wherein the third preset neural network model is used for extracting initial features in the target edge features;
and determining the running track of the vehicle to be detected in second preset time according to the node characteristics of the vehicle to be detected, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics.
Optionally, determining a driving track of the vehicle to be tested within a second preset time according to the node feature of the vehicle to be tested, the node feature of the first node, and the target edge feature, includes:
under each edge type, carrying out aggregation processing on the node characteristics of the vehicle to be tested, the node characteristics of the first node and the target edge characteristics to obtain an aggregation value corresponding to each edge type of the vehicle to be tested;
carrying out aggregation processing on the aggregation values corresponding to the edge types and the vehicle characteristics of the vehicle to be tested to obtain a predicted value of the vehicle to be tested;
and inputting the predicted value of the vehicle to be tested into a fourth preset neural network model to obtain the running track of the vehicle to be tested in a second preset time.
Optionally, the first edge type includes at least one of the following:
an upper side, the upper side including a side pointing from the vehicle to be tested to the first node;
a lower edge, the lower edge including an edge pointing from the first node to the vehicle under test.
Optionally, the second edge type includes at least one of:
the right side comprises a side which points to the second node from the vehicle to be tested when the vehicle to be tested can pass through the left lane change from the first node to the second node;
a left side comprising an edge pointing from the second node to the vehicle under test when the vehicle under test can make a right lane change from the first node to the second node;
a front edge, the front edge comprising an edge that points from the vehicle under test to a second node when the first node is a precursor of the second node;
and the rear edge comprises an edge which points to the vehicle to be tested from the second node when the first node is a rear drive of the second node.
In a second aspect, an embodiment of the present application provides a vehicle trajectory determination apparatus, including: the device comprises an acquisition module, a processing module and a display module;
the acquisition module is used for acquiring vehicle characteristics of a vehicle to be detected and vehicle characteristics of other vehicles within a first preset time, wherein the other vehicles are vehicles within a preset range taking the vehicle to be detected as a center, and acquiring environment characteristics within the preset range taking the vehicle to be detected as the center, the vehicle characteristics of the vehicle comprise position data of the vehicle, and the environment characteristics comprise coordinate information of each section of a lane and steering types of each section;
the processing module is used for determining a running track of the vehicle to be detected in a second preset time based on a lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles and the environment characteristics, wherein the first preset time is before the second preset time, and the lane segmentation heterogeneous graph is a vehicle-segmentation relational graph established by taking the vehicle to be detected, the other vehicles and all segments as nodes;
the display module is used for displaying the running track of the vehicle to be tested.
In a possible design of the second aspect, the processing module is specifically configured to:
in the lane segmentation heterogeneous graph, determining an edge characteristic of the vehicle to be detected according to a node, a first node and a second node corresponding to the vehicle to be detected, where the first node is a node of a lane where the vehicle to be detected is located, the second node is a node of a lane adjacent to the first node, and the edge characteristic includes: an edge feature of a first edge type and an edge feature of a second edge type, the edge feature of the first edge type comprising at least one of: the relative angle between the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, and the edge characteristics of the second edge type include at least one of the following: the relative angle of the second node to the first node, the relative distance of the second node to the first node, and the edge type includes: the first edge type is the type of an edge between the vehicle to be tested and the first node, and the second edge type is the type of an edge between the first node and the second node;
and determining the running track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics within the preset range and the side characteristics of the vehicle to be detected.
In this possible design, the processing module determines a driving track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environmental characteristics corresponding to the first node and the second node, and the edge characteristics of the vehicle to be detected, and is specifically configured to:
inputting the vehicle characteristics of the vehicle to be detected into a first preset neural network model to obtain the node characteristics of the vehicle to be detected, wherein the first preset neural network model is used for extracting initial characteristics in the vehicle characteristics;
inputting the environmental features corresponding to the first node and the second node into a second preset neural network model to obtain the node features of the first node, wherein the second preset neural network model is used for extracting initial features in the node features;
inputting the edge features of the vehicle to be detected into a third preset neural network model to obtain target edge features, wherein the third preset neural network model is used for extracting initial features in the target edge features;
and determining the running track of the vehicle to be tested in a second preset time according to the node characteristics of the vehicle to be tested, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics.
Optionally, the processing module determines a driving track of the vehicle to be detected within a second preset time according to the node feature of the vehicle to be detected, the node feature of the first node, the node feature of the second node, and the target edge feature, and is specifically configured to:
under each edge type, carrying out aggregation processing on the node characteristics of the vehicle to be tested, the node characteristics of the first node and the target edge characteristics to obtain an aggregation value corresponding to each edge type of the vehicle to be tested;
carrying out aggregation processing on the aggregation values corresponding to the edge types and the vehicle characteristics of the vehicle to be tested to obtain a predicted value of the vehicle to be tested;
and inputting the predicted value of the vehicle to be tested into a fourth preset neural network model to obtain the running track of the vehicle to be tested in a second preset time.
Optionally, the first edge type includes at least one of the following:
an upper side, including a side pointing from the vehicle to be tested to the first node;
a lower edge, the lower edge including an edge pointing from the first node to the vehicle under test.
Optionally, the second edge type includes at least one of:
the right side comprises a side which points to the second node from the vehicle to be tested when the vehicle to be tested can pass through the left lane change from the first node to the second node;
a left side comprising an edge pointing from the second node to the vehicle under test when the vehicle under test can make a right lane change from the first node to the second node;
a front edge, the front edge comprising an edge that points from the vehicle under test to a second node when the first node is a precursor of the second node;
the rear edge comprises an edge pointing from a second node to the vehicle under test when the first node is a rear drive of the second node.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, a memory;
the memory stores computer-executable instructions;
the processor executes the computer-executable instructions to cause the vehicle to perform the method of determining vehicle trajectory as described in the first aspect and various possible designs above.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is used for implementing the method for determining a vehicle trajectory as described in the first aspect and various possible designs.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a computer program, which when executed by a processor, is configured to implement the method for determining a trajectory of a vehicle as described in the first aspect and various possible designs.
According to the method, the device, the equipment and the storage medium for determining the vehicle track, the vehicle characteristics of the vehicle to be measured and the vehicle characteristics of other vehicles within the first preset time are obtained, the environment characteristics within the preset range with the vehicle to be measured as the center are obtained, the vehicle characteristics of the vehicle comprise position data of the vehicle, the environment characteristics comprise coordinate information of each section of the lane and steering types of each section, the running track of the vehicle to be measured within the second preset time is determined based on the lane section heterogeneous graph, the vehicle characteristics of the vehicle to be measured, the vehicle characteristics of other vehicles and the environment characteristics, and the running track of the vehicle to be measured is displayed. According to the technical scheme, the position data of the vehicle to be predicted and other vehicles in the preset range, the coordinate information of each section of the lane and the steering type of each section are used, so that the predicted track of the vehicle is more consistent with an actual scene, and the prediction accuracy of the track of the vehicle is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a schematic application scenario diagram of a vehicle trajectory determination method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a first method for determining a vehicle track according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of each section of a lane provided by an embodiment of the present application;
fig. 4 is a schematic flowchart of a second embodiment of a method for determining a vehicle track according to an embodiment of the present application;
FIG. 5 is a heterogeneous pictorial illustration of lane segmentation provided by an embodiment of the present application;
fig. 6 is a schematic structural diagram of a device for determining a vehicle track according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Before introducing the embodiments of the present application, the background of the present application is explained first:
trajectory prediction is widely applied to the fields of robot, automatic driving automobile route planning and the like. The method provides reference for the running changes of the robot and the automatic driving automobile in the future track, and is beneficial for the user to timely adjust the route to be traveled.
In the common prior art, the running track of the vehicle to be tested in the future time is obtained by collecting historical running data of the vehicle to be tested and historical running data of other vehicles in a scene and processing the historical running data.
However, the method ignores the factors that the vehicle to be tested and other vehicles need to follow the operation scene, for example, map traffic rules, when the vehicle to be tested and other vehicles run in different lanes in opposite directions, no influence exists between the two vehicles, and the method in the prior art can cause the prediction result of the vehicle to be tested to have larger deviation.
Based on the problems in the prior art, fig. 1 is a schematic view of an application scenario of a method for determining a vehicle track provided in an embodiment of the present application, so as to solve the above technical problems. As shown in fig. 1, the application scenario diagram includes: vehicle 1, vehicle 2, vehicle 3, and vehicle 4.
The vehicle 1 is a vehicle to be tested. The vehicle 2 is separated by a thicker line in fig. 1 on a different lane, opposite to the direction of travel of the vehicle 1 (line with crop) and represents a line in the map traffic rules that cannot be crossed. The vehicle 3 runs in the same direction as the vehicle 1, and the vehicle 4 turns into the intersection from the lane where the vehicle 3 is located on each lane.
In fig. 1, the broken lines at the positions where the vehicle 1, the vehicle 2, the vehicle 3, and the vehicle 4 run in opposite directions respectively indicate the historical running trajectories of the respective vehicles.
In one possible implementation, when the vehicle 1 runs, the running track of the vehicle 1 in a period of time after the current time is determined according to the collected historical track information of the vehicles 1, 2, 3 and 4, the coordinate information of the lanes in which the vehicles 1, 2, 3 and 4 are located and the segmentation information of the lanes (i.e. thin solid lines in fig. 1).
It should be understood that: the execution main body in the embodiment of the present application may be an Electronic device, and the Electronic device may be an Electronic Control Unit (ECU) of the vehicle to be tested, or may be a third-party device independent of the vehicle to be tested, for example, a technician terminal device.
In order to solve the technical problems, the technical conception process of the inventor is as follows: the inventor finds that in the prior art, only the influence between the vehicles is considered, so that the influence of the lane on the vehicles can be considered, namely, the influence of the vehicles on the cross reference map is increased, so that the vehicle to be tested is not influenced by the unrelated vehicles on the map, and the influence of other vehicles on the vehicle to be tested on the map is distinguished, so that the track of the vehicle to be tested can be more accurately predicted.
The technical solution of the present application is described in detail below with reference to an application scenario diagram shown in fig. 1 by specific embodiments. It should be noted that the following specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 2 is a schematic flowchart of a first embodiment of a method for determining a vehicle track provided in the embodiment of the present application. As shown in fig. 2, the method for determining the vehicle track may include the following steps:
and 21, acquiring the vehicle characteristics of the vehicle to be detected and the vehicle characteristics of other vehicles within the first preset time.
The other vehicles are vehicles within a preset range with the vehicle to be tested as the center, and the vehicle characteristics of the vehicles comprise position data of the vehicles.
In this step, when performing trajectory prediction for the vehicle to be tested, historical operation data of the vehicle to be tested before the current time and historical operation data of other vehicles that may affect the vehicle to be tested need to be considered, and then the historical operation data of the vehicle to be tested and the other vehicles are further processed.
Optionally, the selection range of the other vehicles affecting the vehicle to be tested may be a preset range centered on the vehicle to be tested. For example, within 100m centered on the vehicle under test, it should be understood that: as the operating speed of the vehicle under test increases, the range may increase accordingly.
Optionally, the first preset time is a period of time before the current time, for example, within 1min and 30s before the current time.
In one possible implementation, the position data of the vehicle to be detected acquired by the various sensors and the position data of the other vehicles acquired by the various sensors are acquired by the electronic device. That is, the current position of the vehicle (the vehicle to be measured and other vehicles) is taken as the origin of coordinates, and the historical track position of the position data of each vehicle relative to the vehicle is recorded as V i (position data of the ith vehicle).
Specifically, the collection frequency may be 1s with 10Hz sampling, and within 1s, the historical track length of each vehicle is 10, that is, within 1s (10 moments), there are 10 position data of the vehicle, that is, V i The expression of (c) is:
wherein the content of the first and second substances,
a point representing the position of the vehicle i relative to the vehicle at the moment l, namely a two-dimensional coordinate; />
Other information indicative of vehicle i at time i may include, but is not limited to, speed, acceleration, angular velocity, vehicle type, etc.
And step 22, obtaining the environmental characteristics within the preset range by taking the vehicle to be tested as the center.
Wherein the environmental characteristics include coordinate information of each segment of the lane and a steering type of each segment.
In this step, the vehicle characteristics of the vehicle to be detected and other vehicles are obtained, and in order to accurately obtain the running track of the vehicle to be detected, lane information of the vehicle to be detected within a preset range needs to be determined.
Alternatively, the environmental characteristics, i.e. the lane information, within the preset range may be acquired from a High Definition Map (HD Map) software, including: coordinate information of each segment of the lane and a steering type of each segment. It should be understood that the turning type can be an option, and can also be whether the segment is at the intersection, for example, the value can be 0,1.
As an example, fig. 3 is a schematic diagram of each segment of the lane provided in the embodiment of the present application. As shown in fig. 3, on the basis of fig. 1, the schematic diagram further includes: segment 1, segment 2, segment 3, segment 4, segment 5, segment 6, segment 7, segment 8, and segment 9.
Specifically, vehicle 2 is on segment 1, vehicle 1 is on segment 3, vehicle 3 is on segment 6, and vehicle 4 is on segment 9.
In one possible implementation, the environmental characteristic may be denoted as S j J is the jth lane in the preset range, and the expression is as follows:
S j ＝(s j ，e j ，o j )
wherein s is j Starting coordinates of the lane segment j, e j Representing the end coordinate, o, of the lane segment j j Other information indicative of lane segment j may include, but is not limited to, lane segment turn type, whether a lane segment is at an intersection, etc.
And step 23, determining the running track of the vehicle to be detected in the second preset time based on the lane segmentation heterogeneous map, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles and the environment characteristics.
The lane segmentation heterogeneous graph is a vehicle-segmentation relational graph established by taking a vehicle to be detected, other vehicles and all segments as nodes before the first preset time and the second preset time.
In the step, in order to facilitate analysis of influence of the vehicle to be tested on other vehicles and each segment, a vehicle-segment relation graph is established by taking the vehicle to be tested, other vehicles and each segment as nodes, and the relation indicates the relation of positions, angles and the like among the three vehicles to be tested, other vehicles and each segment.
Based on the lane segmentation heterogeneous graph, the driving track of the vehicle to be detected in the second preset time is determined by using the historical running data of the vehicle to be detected and other vehicles, the coordinate information of each segment of the lane, the steering type of each segment and the like, and the specific determination method is as follows.
Optionally, the second preset time is a period of time after the current time, for example, 1min, 30s and the like after the current time.
Alternatively, the travel locus may be a coordinate point at each time within the second preset time. For example, the second preset time is 1s, and may be 10 coordinate points of the vehicle to be measured at the time of 0.1 s.
And 24, displaying the running track of the vehicle to be tested.
In this step, after the driving track of the vehicle to be tested is obtained, the driving track may be displayed on a display screen of the electronic device.
In one possible design, the driving track may be a smooth line formed by connecting a plurality of coordinate points determined in the above steps, and is displayed in the possible movement direction of the vehicle to be measured at the current time in the image.
According to the method for determining the vehicle track, the vehicle characteristic of the vehicle to be measured and the vehicle characteristics of other vehicles within the first preset time are obtained, the environmental characteristic within the preset range with the vehicle to be measured as the center is obtained, and the running track of the vehicle to be measured within the second preset time is determined based on the lane segmentation heterogeneous graph, the vehicle characteristic of the vehicle to be measured, the vehicle characteristics of the other vehicles and the environmental characteristic, so that the running track is displayed. According to the technical scheme, the position data of the vehicle to be measured and other vehicles in the preset range, the coordinate information of each section of the lane and the steering type of each section are used, so that the predicted track of the vehicle is more in line with the actual scene, and the prediction accuracy of the track of the vehicle is improved.
On the basis of the foregoing embodiment, fig. 4 is a schematic flowchart of a second embodiment of a method for determining a vehicle track provided in the embodiment of the present application. As shown in fig. 4, step 23 may comprise the following steps:
and step 41, determining the edge characteristics of the vehicle to be detected according to the node, the first node and the second node corresponding to the vehicle to be detected in the lane segmentation heterogeneous graph.
Wherein, first node is the node in the lane that the vehicle place that awaits measuring is located, and the second node is the node in the adjacent lane of first node, and the limit characteristic includes: edge features of a first edge type and edge features of a second edge type, the edge features of the first edge type including at least one of: the relative angle of the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, and the edge characteristics of the second edge type include at least one of the following: the relative angle between the second node and the first node, and the relative distance between the second node and the first node, wherein the edge types comprise: the device comprises a first edge type and a second edge type, wherein the first edge type is the type of an edge between a vehicle to be tested and a first node, and the second edge type is the type of an edge between the first node and a second node.
Specifically, the first edge type includes at least one of: upper side on and lower side continin.
The upper side comprises an edge pointing to the first node from the vehicle to be detected; and the lower edge comprises an edge pointing to the vehicle to be measured from the first node.
The second edge type includes at least one of: left, right, leading pre, and trailing suc.
The right side comprises a side which points to the second node from the vehicle to be detected when the vehicle to be detected can change lanes from the first node to the second node through the left side; the left side comprises an edge which points to the vehicle to be tested from the second node when the vehicle to be tested can pass through the right lane change from the first node to the second node; the front edge comprises an edge which points to the second node from the vehicle to be tested when the first node is the precursor of the second node; the rear edge includes an edge that points from the second node to the vehicle under test when the first node is the rear drive of the second node.
In one possible implementation, based on the application scenario diagram shown in fig. 1, fig. 5 is a heterogeneous diagram illustrating lane segmentation provided by the embodiment of the present application. As shown in fig. 5: box 1 represents vehicle 1 (vehicle under test), box 2, box 3 and box 4 represent other vehicles, i.e. vehicle 2, vehicle 3 and vehicle 4, respectively; the circles represent lane segments, namely segment 1, segment 2, segment 3, segment 4, segment 5, segment 6, segment 7, segment 8 and segment 9. The points at which the vehicles and segments are located are collectively referred to as nodes.
Where vehicle 2 is on segment 1, vehicle 3 is on segment 6, vehicle 4 is on segment 9, and vehicle 1 is on segment 3.
Optionally, in this embodiment of the application, the first node is the segment 3, the second node is the segment 4 and the segment 5, and the vehicle 1 is a node corresponding to a vehicle to be tested.
Specifically, as shown in fig. 5: the sides of vehicle 2 and segments 1 and 2 include an upper side, a lower side, a front side, and a rear side due to non-traversable lines in map traffic regulations (the thicker lines in fig. 1 block off).
The upper side and the lower side are included between the vehicle 1 and the segment 3, between the vehicle 3 and the segment 6, and between the vehicle 4 and the segment 9.
Further, segments 3 and 5 and 4 contain left, right, front and back edges, segments 4 and 3, segments 6 and 7 contain left, right, front and back edges, segments 6 and 4, segments 5, segments 7 and 8 contain left, right, front and back edges, segments 8 and 6 and 9 contain left, right, front and back edges, segments 5 and 3 and 6 contain left, right, front and back edges, segments 7 and 4 and 6 contain left, right, front and back edges, and segments 9 and 8 contain front and back edges.
Optionally, in fig. 5, the edge of the vehicle to be tested indicates: the starting vehicle 1 points to segment 3, and segment 3 points to any edge generated by the characteristics of segment 4 and segment 5, i.e., the two edge types described above.
Further, edge feature E <i，j> The method can comprise the following steps: the relative angle of segment 3 to vehicle 1, the relative distance of segment 3 to vehicle 1, the relative angle of segments 4 and 5 to segment 3, and the relative distance of segments 4 and 5 to segment 3.
Wherein i is a vehicle to be tested, namely a vehicle 1; j are segments, segment 3, segment 4, and segment 5.
It should be understood that: heterogeneous maps of vehicle and road nodes and edges are shown in fig. 5, rather than representing true bearing relationships between nodes.
And 42, determining the running track of the vehicle to be detected in a second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics in the preset range and the side characteristics of the vehicle to be detected.
In this step, the characteristics of the other vehicles and the sections of the road, which affect the vehicle to be detected, and the side characteristics of the vehicle to be detected, the other vehicles and the sections are determined in the above steps, and the following processing is further performed, so that the driving track of the vehicle to be detected in the second preset time can be determined.
In one possible implementation, this can be achieved by:
step 1, inputting vehicle characteristics of a vehicle to be detected into a first preset neural network model to obtain node characteristics of the vehicle to be detected, wherein the first preset neural network model is used for extracting initial characteristics in the vehicle characteristics;
optionally, the vehicle feature of the vehicle to be tested is subjected to an initial feature extraction operation to obtain a node feature of the vehicle to be tested, and the formula may be:
V ii ＝Encode(V i )
wherein the extracting operation can be performed by comparing the vehicle characteristic V of the vehicle to be tested i Inputting the data into a first preset neural network model to obtain the data.
Step 2, inputting the environmental characteristics corresponding to the first node and the second node into a second preset neural network model to obtain the node characteristics of the first node and the second node, wherein the second preset neural network model is used for extracting initial characteristics in the environmental characteristics;
optionally, the initial feature extraction operation is performed on the environmental features of the first node and the second node, that is, the environmental features of the first node and the second node are respectively input into the second preset neural network model, so as to obtain the node features of the first node and the second node, where the formula may be:
S jj ＝Encode(S j )
it should be understood that in some scenarios, there is no second node, i.e. there are no other segments around the first node where the vehicle under test is located; or the second node is related to other vehicles, namely, other vehicles are arranged on the second node adjacent to the first node where the vehicle to be tested is located.
Step 3, inputting the edge characteristics of the vehicle to be detected into a third preset neural network model to obtain target edge characteristics, wherein the third preset neural network model is used for extracting initial characteristics in the target edge characteristics;
optionally, the initial feature extraction operation is performed on the edge features of the vehicle to be detected, that is, the edge features of the vehicle to be detected are respectively input into a third preset neural network model to obtain target edge features, and the formula may be:
E 1<i，j> ＝Encode(E <i，j> )
the first preset Neural network model, the second preset Neural network model and the third preset Neural network model may be any one of Recurrent Neural Networks (RNNs), convolutional Neural Networks (CNNs) and Multi-Layer Neural Networks (MLPs) trained in advance by a user.
And 4, determining the running track of the vehicle to be detected in the second preset time according to the node characteristics of the vehicle to be detected, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics.
In one possible implementation, this step may be implemented by:
firstly, under each edge type, carrying out aggregation processing on the node characteristics of the vehicle to be tested, the node characteristics of the first node and the target edge characteristics to obtain an aggregation value corresponding to each edge type of the vehicle to be tested;
optionally, in each edge type related to the vehicle to be tested, taking the vehicle 1 pointing to the segment 3 as an example, the related edge is an upper edge, that is, the aggregation value corresponding to the left side is:
wherein, V ii As a node characteristic of the vehicle under test, S jj Node characteristics for segment 3, E 1<i，j> Target edge feature, f, for the vehicle 1 pointing to segment 3 t () Can be arbitrarily input as V ii ，S jj ，E 1<i，j> Functions of (1), e.g. attention neural network, agg t () Can be any aggregation function, such as an attention neural network, a simple sum, etc.,
indicating other edge types than the left.
Further, the last step can obtain N of different types of edges i Set of values U i 。
Secondly, carrying out aggregation processing on the aggregation values corresponding to all edge types and the vehicle characteristics of the vehicle to be tested to obtain a predicted value of the vehicle to be tested;
in this step, the set U is processed i A plurality of N in i And aggregating the vehicle characteristics of the vehicle to be tested, namely the formula of the predicted value of the vehicle to be tested is as follows:
F i ＝Agg(V i ，N i )
optionally, the specific implementation process of this step is: 1. will be set U i 1 st N in (1) i And V i Input Agg function to obtain the 1 st F i (ii) a 2. Will be set U i 2 nd N in (1) i And 1 st F i Inputting Agg function to obtain 2 nd F i Loop execution to set U i Last 1N in i The last 1F obtained i The predicted value is the predicted value of the vehicle to be tested.
And finally, inputting the predicted value of the vehicle to be tested into a fourth preset neural network model to obtain the running track of the vehicle to be tested in a second preset time.
Optionally, the fourth preset neural network model is used for decoding the predicted value of the vehicle to be tested to obtain the vehicle to be testedTrack P i The formula is as follows:
P i ＝Decode(F i )
the Decode (fourth predetermined neural network model) may be a prediction model of any structure, such as RNNs, MLP, etc.
Optionally, after decoding, the obtained P i The plurality of tracks in the second preset time can be
And K is the number of the running tracks of the vehicle to be tested.
Further, for each trajectory
The formula is as follows:
therein is directed to
And the two-dimensional coordinates of the Kth running track of the vehicle to be detected at the moment C in the second preset time are represented, and the original point is the coordinate of the current moment of the vehicle to be detected.
According to the method for determining the vehicle track, the side characteristics of the vehicle to be measured are determined according to the nodes, the first nodes and the second nodes corresponding to the vehicle to be measured in the lane segmentation heterogeneous graph, and the running track of the vehicle to be measured in the second preset time is determined according to the vehicle characteristics of the vehicle to be measured, the environment characteristics corresponding to the first nodes and the second nodes in the environment characteristics within the preset range and the side characteristics of the vehicle to be measured.
On the basis of the above method embodiment, fig. 6 is a schematic structural diagram of a vehicle trajectory determination device provided in the embodiment of the present application. As shown in fig. 6, the vehicle trajectory determination device includes: an acquisition module 61, a processing module 62 and a display module 63.
The obtaining module 61 is configured to obtain a vehicle characteristic of a vehicle to be detected and vehicle characteristics of other vehicles within a first preset time, where the other vehicles are vehicles within a preset range with the vehicle to be detected as a center, and obtain an environmental characteristic within the preset range with the vehicle to be detected as the center, where the vehicle characteristic of the vehicle includes position data of the vehicle, and the environmental characteristic includes coordinate information of each segment of the lane and a steering type of each segment;
the processing module 62 is configured to determine a driving track of the vehicle to be detected within a second preset time based on the lane segmentation heterogeneous map, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles, and the environmental characteristics, where the first preset time is before the second preset time, and the lane segmentation heterogeneous map is a vehicle-segmentation relational map established by taking the vehicle to be detected, other vehicles, and each segment as a node;
and the display module 63 is used for displaying the running track.
In one possible design of the embodiment of the present application, the processing module 62 is specifically configured to:
in the lane segmentation heterogeneous graph, determining the edge characteristics of the vehicle to be detected according to the node, the first node and the second node corresponding to the vehicle to be detected, wherein the first node is the node of the lane where the vehicle to be detected is located, the second node is the node of the lane adjacent to the first node, and the edge characteristics comprise: an edge feature of a first edge type and an edge feature of a second edge type, the edge feature of the first edge type comprising at least one of: the relative angle of the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, and the edge characteristics of the second edge type include at least one of the following: the relative angle between the second node and the first node, and the relative distance between the second node and the first node, wherein the edge type comprises: the method comprises the following steps of a first edge type and a second edge type, wherein the first edge type is the type of an edge between a vehicle to be detected and a first node, and the second edge type is the type of an edge between the first node and a second node;
and determining the running track of the vehicle to be detected in the second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics in the preset range and the side characteristics of the vehicle to be detected.
In this possible design, the processing module 62 determines the driving track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environmental characteristics corresponding to the first node and the second node, and the edge characteristics of the vehicle to be detected, and is specifically configured to:
inputting the vehicle characteristics of the vehicle to be detected into a first preset neural network model to obtain the node characteristics of the vehicle to be detected, wherein the first preset neural network model is used for extracting initial characteristics in the vehicle characteristics;
inputting the environmental characteristics corresponding to the first node into a second preset neural network model to obtain node characteristics of the first node and the second node, wherein the second preset neural network model is used for extracting initial characteristics in the node characteristics;
inputting the edge characteristics of the vehicle to be detected into a third preset neural network model to obtain target edge characteristics, wherein the third preset neural network model is used for extracting initial characteristics in the target edge characteristics;
and determining the running track of the vehicle to be detected in second preset time according to the node characteristics of the vehicle to be detected, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics.
Optionally, the processing module 62 determines a driving track of the vehicle to be detected within a second preset time according to the node feature of the vehicle to be detected, the node feature of the first node, the node feature of the second node, and the target edge feature, and is specifically configured to:
under each edge type, carrying out aggregation processing on the node characteristics of the vehicle to be tested, the node characteristics of the first node and the target edge characteristics to obtain an aggregation value corresponding to each edge type of the vehicle to be tested;
aggregating the aggregation values corresponding to the edge types and the vehicle characteristics of the vehicle to be tested to obtain a predicted value of the vehicle to be tested;
and inputting the predicted value of the vehicle to be tested into a fourth preset neural network model to obtain the running track of the vehicle to be tested in the second preset time.
Optionally, the first edge type includes at least one of:
the upper side comprises an edge pointing to the first node from the vehicle to be detected;
and the lower edge comprises an edge pointing to the vehicle to be measured from the first node.
Optionally, the second edge type includes at least one of the following:
the right side comprises a side which points to the second node from the vehicle to be detected when the vehicle to be detected can change lanes from the first node to the second node through the left side;
the left side comprises an edge which points to the vehicle to be tested from the second node when the vehicle to be tested can pass through the right lane change from the first node to the second node;
the front edge comprises an edge which points to a second node from the vehicle to be tested when the first node is a precursor of the second node;
the rear edge includes an edge that points from the second node to the vehicle under test when the first node is the rear drive of the second node.
The device for determining the vehicle track provided by the embodiment of the application can be used for executing the technical scheme corresponding to the method for determining the vehicle track in the embodiment, the implementation principle and the technical effect are similar, and the details are not repeated herein.
It should be noted that the division of the modules in the vehicle trajectory determination device is only a logical division, and all or part of the modules may be integrated into one physical entity or may be physically separated in actual implementation. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in the form of software.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 7, the electronic device may include: a processor 70, a memory 71, and computer program instructions stored on the memory 71 and operable on the processor 70.
The processor 70 executes computer-executable instructions stored by the memory 71, causing the processor 70 to perform the aspects of the embodiments described above. The processor 70 may be a general-purpose processor including a central processing unit CPU, a Network Processor (NP), and the like; but also a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
Optionally, the electronic device may further include: a transceiver 72 and a display 73.
The memory 71, the transceiver 72 and the display 73 are connected to the processor 70 via the system bus and communicate with each other, and the memory 71 is used for storing computer program instructions.
The transceiver 72 is used for communication with its devices, which transceiver 72 constitutes a communication interface.
Optionally, in terms of hardware implementation, the obtaining module 61 in the embodiment shown in fig. 6 corresponds to the transceiver 72 in this embodiment. The display module 63 in the embodiment shown in fig. 6 described above corresponds to the display 73 in the present embodiment.
In one possible implementation, the electronic device may further include: and the display 73, wherein the display 73 is used for displaying the running track of the vehicle to be tested.
The system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.
It should be understood that the electronic device may be a computer, tablet, ECU, etc.
The electronic device provided by the embodiment of the application can be used for executing the technical scheme corresponding to the method for determining the vehicle track in the embodiment, the implementation principle and the technical effect are similar, and details are not repeated here.
The embodiment of the application further provides a chip of the operation instruction, and the chip is used for executing the technical scheme of the method for determining the vehicle track in the embodiment.
The embodiment of the present application further provides a computer-readable storage medium, where a computer instruction is stored in the computer-readable storage medium, and when the computer instruction runs on a computer, the computer is enabled to execute the technical solution of the method for determining a vehicle track in the foregoing embodiment.
The embodiment of the present application further provides a computer program product, which includes a computer program, and the computer program is used for executing the technical solution of the method for determining a vehicle trajectory in the foregoing embodiment when executed by a processor.
The computer-readable storage medium described above may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A readable storage medium may be any available medium that can be accessed by a general purpose or special purpose computer.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (8)
1. A method of determining a vehicle trajectory, comprising:
the method comprises the steps of obtaining vehicle characteristics of a vehicle to be tested and vehicle characteristics of other vehicles within a first preset time, wherein the other vehicles are vehicles within a preset range with the vehicle to be tested as a center, and the vehicle characteristics of the vehicles comprise position data of the vehicles;
acquiring environmental characteristics within a preset range by taking the vehicle to be detected as a center, wherein the environmental characteristics comprise coordinate information of each section of the lane and steering types of each section;
determining a running track of the vehicle to be detected in a second preset time based on a lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles and the environment characteristics, wherein the lane segmentation heterogeneous graph is a vehicle-segmentation relational graph established by taking the vehicle to be detected, the other vehicles and each segment as a node before the second preset time;
displaying the running track of the vehicle to be tested;
based on lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be tested, the vehicle characteristics of other vehicles and the environmental characteristics, the driving track of the vehicle to be tested in a second preset time is determined, and the method comprises the following steps:
in the lane segmentation heterogeneous graph, determining an edge characteristic of the vehicle to be detected according to a node, a first node and a second node corresponding to the vehicle to be detected, where the first node is a node of a lane where the vehicle to be detected is located, the second node is a node of a lane adjacent to the first node, and the edge characteristic includes: an edge feature of a first edge type and an edge feature of a second edge type, the edge feature of the first edge type comprising at least one of: the relative angle between the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, and the edge characteristics of the second edge type include at least one of the following: the relative angle of the second node to the first node, the relative distance of the second node to the first node, the edge type including: the first edge type is the type of an edge between the vehicle to be tested and the first node, and the second edge type is the type of an edge between the first node and the second node;
and determining the running track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics within the preset range and the side characteristics of the vehicle to be detected.
2. The method according to claim 1, wherein the determining the driving track of the vehicle to be tested within a second preset time according to the vehicle characteristics of the vehicle to be tested, the environment characteristics corresponding to the first node and the second node, and the edge characteristics of the vehicle to be tested comprises:
inputting the vehicle characteristics of the vehicle to be detected into a first preset neural network model to obtain the node characteristics of the vehicle to be detected, wherein the first preset neural network model is used for extracting initial characteristics in the vehicle characteristics;
inputting the environmental features corresponding to the first node and the second node into a second preset neural network model to obtain the node features of the first node and the second node, wherein the second preset neural network model is used for extracting initial features in the node features;
inputting the edge features of the vehicle to be detected into a third preset neural network model to obtain target edge features, wherein the third preset neural network model is used for extracting initial features in the target edge features;
and determining the running track of the vehicle to be tested in a second preset time according to the node characteristics of the vehicle to be tested, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics.
3. The method according to claim 2, wherein the determining the driving track of the vehicle to be tested within a second preset time according to the node characteristics of the vehicle to be tested, the node characteristics of the first node, the node characteristics of the second node and the target edge characteristics comprises:
under each edge type, carrying out aggregation processing on the node characteristics of the vehicle to be tested, the node characteristics of the first node and the target edge characteristics to obtain an aggregation value corresponding to each edge type of the vehicle to be tested;
carrying out aggregation processing on the aggregation values corresponding to the edge types and the vehicle characteristics of the vehicle to be tested to obtain a predicted value of the vehicle to be tested;
and inputting the predicted value of the vehicle to be tested into a fourth preset neural network model to obtain the running track of the vehicle to be tested in a second preset time.
4. The method of claim 1, wherein the first edge type comprises at least one of:
an upper side, the upper side including a side pointing from the vehicle to be tested to the first node;
a lower edge, the lower edge including an edge pointing from the first node to the vehicle under test.
5. The method of claim 1, wherein the second edge type comprises at least one of:
the right side comprises an edge which points to the second node from the vehicle to be tested when the vehicle to be tested can pass through the left lane change from the first node to the second node;
a left side comprising an edge pointing from the second node to the vehicle under test when the vehicle under test can make a right lane change from the first node to the second node;
the front edge comprises an edge which points to a second node from the vehicle to be tested when the first node is a precursor of the second node;
and the rear edge comprises an edge which points to the vehicle to be tested from the second node when the first node is a rear drive of the second node.
6. A vehicle trajectory determination device, characterized by comprising: the device comprises an acquisition module, a processing module and a display module;
the acquisition module is used for acquiring vehicle characteristics of a vehicle to be detected and vehicle characteristics of other vehicles within a first preset time, wherein the other vehicles are vehicles within a preset range taking the vehicle to be detected as a center, and acquiring environment characteristics within the preset range taking the vehicle to be detected as the center, the vehicle characteristics of the vehicle comprise position data of the vehicle, and the environment characteristics comprise coordinate information of each section of a lane and steering types of each section;
the processing module is used for determining a running track of the vehicle to be detected in a second preset time based on a lane segmentation heterogeneous graph, the vehicle characteristics of the vehicle to be detected, the vehicle characteristics of other vehicles and the environment characteristics, wherein the first preset time is before the second preset time, and the lane segmentation heterogeneous graph is a vehicle-segmentation relational graph established by taking the vehicle to be detected, the other vehicles and all segments as nodes;
the display module is used for displaying the running track of the vehicle to be tested;
the processing module is specifically configured to:
in the lane segmentation heterogeneous graph, determining edge characteristics of the vehicle to be detected according to a node, a first node and a second node corresponding to the vehicle to be detected, wherein the first node is a node above the node corresponding to the vehicle to be detected, the second node is an adjacent node of the first node, and the edge characteristics include: an edge feature of a first edge type and an edge feature of a second edge type, the edge feature of the first edge type comprising at least one of: the relative angle of the first node and the node corresponding to the vehicle to be tested, and the relative distance between the first node and the node corresponding to the vehicle to be tested, the edge characteristics of the second edge type include at least one of the following: the relative angle of the second node to the first node, the relative distance of the second node to the first node, the edge type including: the first edge type is the type of an edge between the vehicle to be tested and the first node, and the second edge type is the type of an edge between the first node and the second node;
and determining the running track of the vehicle to be detected within a second preset time according to the vehicle characteristics of the vehicle to be detected, the environment characteristics corresponding to the first node and the second node in the environment characteristics within the preset range and the side characteristics of the vehicle to be detected.
7. An electronic device, comprising: a processor, a memory and computer program instructions stored on the memory and executable on the processor, wherein the processor when executing the computer program instructions implements the method of determining a vehicle trajectory according to any one of the preceding claims 1 to 5.
8. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of determining a vehicle trajectory according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889630.9A CN113788015B (en) | 2021-08-04 | 2021-08-04 | Method, device and equipment for determining vehicle track and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110889630.9A CN113788015B (en) | 2021-08-04 | 2021-08-04 | Method, device and equipment for determining vehicle track and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113788015A CN113788015A (en) | 2021-12-14 |
| CN113788015B true CN113788015B (en) | 2023-04-18 |
Family
ID=79181379
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110889630.9A Active CN113788015B (en) | 2021-08-04 | 2021-08-04 | Method, device and equipment for determining vehicle track and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113788015B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112665590A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle track determination method and device, electronic equipment and computer storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102463720B1 (en) * | 2017-12-18 | 2022-11-07 | 현대자동차주식회사 | System and Method for creating driving route of vehicle |
| US11378961B2 (en) * | 2018-04-17 | 2022-07-05 | Baidu Usa Llc | Method for generating prediction trajectories of obstacles for autonomous driving vehicles |
| WO2021065735A1 (en) * | 2019-10-02 | 2021-04-08 | 株式会社デンソー | Display control device and display control program |
| CN111114543B (en) * | 2020-03-26 | 2020-07-03 | 北京三快在线科技有限公司 | Trajectory prediction method and device |
| CN112212874B (en) * | 2020-11-09 | 2022-09-16 | 福建牧月科技有限公司 | Vehicle track prediction method and device, electronic equipment and computer readable medium |
| CN112562328B (en) * | 2020-11-27 | 2022-02-18 | 腾讯科技（深圳）有限公司 | Vehicle behavior prediction method and device |
-
2021
- 2021-08-04 CN CN202110889630.9A patent/CN113788015B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112665590A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Vehicle track determination method and device, electronic equipment and computer storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113788015A (en) | 2021-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109444932B (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| WO2022056770A1 (en) | Path planning method and path planning apparatus | |
| CN113492851B (en) | Vehicle control device, vehicle control method, and computer program for vehicle control | |
| KR102424067B1 (en) | Information processing method and device and storage medium | |
| JP2022505759A (en) | Methods and equipment for testing driver assistance systems | |
| JP7115502B2 (en) | Object state identification device, object state identification method, computer program for object state identification, and control device | |
| CN113109783B (en) | Course angle acquisition method, device, equipment and storage medium | |
| CN111339802A (en) | Method and device for generating real-time relative map, electronic equipment and storage medium | |
| US20230278587A1 (en) | Method and apparatus for detecting drivable area, mobile device and storage medium | |
| CN111483464B (en) | Dynamic automatic driving lane changing method, equipment and storage medium based on road side unit | |
| JP7226368B2 (en) | Object state identification device | |
| CN113788015B (en) | Method, device and equipment for determining vehicle track and storage medium | |
| CN112232257A (en) | Traffic abnormity determining method, device, equipment and medium | |
| CN116295497A (en) | Path generation method, path generation device, robot and storage medium | |
| CN115393827A (en) | Traffic signal lamp state identification method and system, electronic equipment and storage medium | |
| US11386675B2 (en) | Device and method for generating vehicle data, and system | |
| CN114898332A (en) | Lane line identification method and system based on automatic driving | |
| CN116381698B (en) | Road remains detection method and device and electronic equipment | |
| CN111325869A (en) | Vehicle fatigue driving accurate judgment method, terminal device and storage medium | |
| CN114754778B (en) | Vehicle positioning method and device, electronic equipment and storage medium | |
| US20230025579A1 (en) | High-definition mapping | |
| CN115675472B (en) | Ramp port determining method and device, electronic equipment and storage medium | |
| CN117238125A (en) | Track prediction method and related device based on vehicle information and map information | |
| CN113034588B (en) | Vehicle positioning method, device, computer equipment and storage medium | |
| CN116363631B (en) | Three-dimensional target detection method and device and vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |