Track planning method and device and terminal equipment

Abstract

The invention is suitable for the technical field of automatic driving, and provides a trajectory planning method and device and terminal equipment, and the method comprises the steps: obtaining at least one reference prior trajectory in a current road range sent by roadside equipment; obtaining current first driving data of the target vehicle and current second driving data of at least one associated vehicle; according to each piece of second driving data and each reference prior track, determining a predicted driving track corresponding to each associated vehicle; according to the first driving data, the predicted driving track corresponding to each associated vehicle and the second driving data, determining a cost value between each predicted driving track and the target vehicle; and planning the driving track of the target vehicle according to the cost value between each predicted driving track and the target vehicle. Therefore, priori trajectory data statistics is carried out through the roadside equipment, and the vehicle end information and the roadside information are combined, so that the calculation complexity of trajectory planning by the vehicle end is reduced, and the accuracy of trajectory planning is improved.

Description

Technical Field

[0001] This application belongs to the technical field of autonomous driving, and particularly relates to a trajectory planning method, apparatus, terminal device, and computer-readable storage medium. Background Art

[0002] When an autonomous vehicle passes through complex traffic scenarios such as intersections, it is necessary to predict the driving intentions and driving trajectories of surrounding vehicles in order to plan its own driving trajectory and ensure the safety of vehicle driving.

[0003] In related technologies, the vehicle trajectories of surrounding vehicles are usually predicted by combining lane information in the map. However, due to the complex traffic conditions at intersection scenarios and the instability of the driving trajectories of surrounding vehicles, the prediction error is relatively large. If the trajectory is predicted through the real-time driving data of surrounding vehicles, not only is the computational complexity high, but also the short-term data obtained by sensors cannot be used for long-term trajectory prediction, resulting in low accuracy of trajectory prediction. Therefore, the existing trajectory planning methods not only have high computational complexity and long time consumption, but also have low reliability. Summary of the Invention

[0004] Embodiments of this application provide a trajectory planning method, apparatus, terminal device, and storage medium, which can solve the problems that the existing trajectory planning methods not only have high computational complexity, long time consumption, but also have low reliability.

[0005] In a first aspect, embodiments of this application provide a trajectory planning method, including: obtaining at least one reference prior trajectory within the current road range corresponding to a target vehicle sent by a roadside device; obtaining the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle; determining a predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory; determining a cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data; and planning the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0006] In a possible implementation manner of the first aspect, the obtaining at least one reference prior trajectory within the current road range corresponding to a target vehicle sent by a roadside device includes:

[0007] obtaining at least one initial prior trajectory within the current road range sent by the roadside device;

[0008] obtaining a reference driving trajectory of the target vehicle within the current road range;

[0009] Screen the initial prior trajectory according to the reference driving trajectory to determine the reference prior trajectory.

[0010] Optionally, in another possible implementation manner of the first aspect, the determining of the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory includes:

[0011] Determine the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory;

[0012] Determine the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

[0013] Optionally, in yet another possible implementation manner of the first aspect, the determining of the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory includes:

[0014] Determine the matching degree between the first associated vehicle and each reference prior trajectory according to the cost value between the first associated vehicle and each reference prior trajectory, where the first associated vehicle is any one of the associated vehicles;

[0015] Determine the predicted driving trajectory corresponding to the first associated vehicle according to the matching degree between the first associated vehicle and each reference prior trajectory.

[0016] Optionally, in still another possible implementation manner of the first aspect, the determining of the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory includes:

[0017] Taking the first reference prior trajectory as the reference line, establish the reference coordinate system corresponding to the first reference prior trajectory, where the first reference prior trajectory is any one of the reference prior trajectories;

[0018] Determine the deviation driving data between the first associated vehicle and the first reference prior trajectory according to the current second driving data of the first associated vehicle and the reference coordinate system, where the first associated vehicle is any one of the associated vehicles;

[0019] Input the deviation driving data into the first generation cost value model to determine the cost value between the first associated vehicle and the first reference prior trajectory.

[0020] Optionally, in another possible implementation of the first aspect, the above reference coordinate system includes a first coordinate direction and a second coordinate direction. The first coordinate direction is parallel to the first reference prior trajectory, and the second coordinate direction is perpendicular to the first reference prior trajectory. The above second driving data includes at least one of a real-time position, a real-time speed, and a real-time heading angle. The above deviation driving data includes at least one of the following data: a first deviation distance along the first coordinate direction, a second deviation distance along the second coordinate direction, a first speed along the first coordinate direction, a second speed along the second coordinate direction, and a first heading angle relative to the first coordinate direction.

[0021] Optionally, in another possible implementation of the first aspect, the above first-generation value model includes a position deviation value model, a first speed deviation value model, and a second speed deviation value model; correspondingly, the above inputting the deviation driving data into the first-generation value model to determine the value between the first associated vehicle and the first reference prior trajectory includes:

[0022] Substituting the first deviation distance, the second deviation distance, and the first heading angle into the position deviation value model to determine the first-generation value between the first associated vehicle and the first reference prior trajectory;

[0023] Substituting the first deviation distance and the first speed into the first speed deviation value model to determine the second-generation value between the first associated vehicle and the first reference prior trajectory;

[0024] Substituting the second deviation distance and the second speed into the second speed deviation value model to determine the third-generation value between the first associated vehicle and the first reference prior trajectory;

[0025] Determining the value between the first associated vehicle and the first reference prior trajectory according to the first-generation value, the second-generation value, and the third-generation value.

[0026] Optionally, in another possible implementation of the first aspect, the above first driving data of the target vehicle currently includes a reference driving trajectory of the target vehicle within the current road range. There is a first intersection point between the reference driving trajectory and the first predicted driving trajectory, where the first predicted driving trajectory is any predicted driving trajectory;

[0027] Correspondingly, the value between the above first predicted driving trajectory and the target vehicle includes the values between each vehicle gap in the first predicted driving trajectory and the target vehicle, where the number of second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1;

[0028] Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection point, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, the distance between the i-th second associated vehicle and the first intersection point is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection point, where i is greater than 1 and less than or equal to N.

[0029] Optionally, in another possible implementation manner of the first aspect, determining the cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data includes:

[0030] Determine the first intersection point according to the first driving data and the first predicted driving trajectory;

[0031] According to the current second driving data of the j-th second associated vehicle and the first predicted driving trajectory, determine the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, where j is an integer greater than or equal to 1 and less than or equal to N;

[0032] According to the current second driving data of the j-th and (j - 1)-th second associated vehicles and the first predicted driving trajectory, determine the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory. When j is 1, the (j - 1)-th second associated vehicle is the first intersection point;

[0033] Substitute the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second cost value model to determine the cost value between the j-th vehicle gap and the target vehicle.

[0034] Optionally, in another possible implementation manner of the first aspect, the above-mentioned second cost value model includes a first collision cost value model, a second collision cost value model, and a third collision cost value model; correspondingly, substituting the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second cost value model to determine the cost value between the j-th vehicle gap and the target vehicle includes:

[0035] Substitute the distance between the j-th second associated vehicle and the first intersection, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory into the first collision cost value model to determine the fourth cost value corresponding to the j-th vehicle gap;

[0036] Substitute the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory into the second collision cost value model to determine the fifth cost value corresponding to the j-th vehicle gap;

[0037] Substitute the distance between the j-th second associated vehicle and the first intersection, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, and j into the third collision cost value model to determine the sixth cost value corresponding to the j-th vehicle gap;

[0038] Determine the cost value between the j-th vehicle gap and the target vehicle according to the fourth cost value, the fifth cost value, and the sixth cost value.

[0039] Optionally, in another possible implementation manner of the first aspect, the above-mentioned planning of the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle includes:

[0040] Determine the target vehicle gap that meets the passing condition according to the cost value between each vehicle gap and the target vehicle;

[0041] Plan the driving trajectory and driving speed of the target vehicle according to the target vehicle gap.

[0042] In a second aspect, an embodiment of the present application provides a trajectory planning device, including: a first acquisition module, configured to acquire at least one reference prior trajectory within the current road range corresponding to a target vehicle sent by a roadside device; a second acquisition module, configured to acquire the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle; a first determination module, configured to determine the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory; a second determination module, configured to determine the cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data; a first planning module, configured to plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0043] In a possible implementation manner of the second aspect, the above-mentioned first acquisition module includes:

[0044] A first acquisition unit, configured to acquire at least one initial prior trajectory within the current road range sent by the roadside device;

[0045] A second acquisition unit, configured to acquire a reference driving trajectory of a target vehicle within a current road range;

[0046] A first determination unit, configured to screen an initial prior trajectory according to the reference driving trajectory to determine a reference prior trajectory.

[0047] Optionally, in another possible implementation manner of the second aspect, the above first determination module includes:

[0048] A second determination unit, configured to determine a cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory;

[0049] A third determination unit, configured to determine a predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

[0050] Optionally, in yet another possible implementation manner of the second aspect, the above third determination unit is specifically configured to:

[0051] Determine a matching degree between a first associated vehicle and each reference prior trajectory according to the cost value between the first associated vehicle and each reference prior trajectory, where the first associated vehicle is any one of the associated vehicles;

[0052] Determine a predicted driving trajectory corresponding to the first associated vehicle according to the matching degree between the first associated vehicle and each reference prior trajectory.

[0053] Optionally, in still another possible implementation manner of the second aspect, the above second determination unit is specifically configured to:

[0054] Taking a first reference prior trajectory as a reference line, establish a reference coordinate system corresponding to the first reference prior trajectory, where the first reference prior trajectory is any one of the reference prior trajectories;

[0055] Determine deviation driving data between a first associated vehicle and the first reference prior trajectory according to the current second driving data of the first associated vehicle and the reference coordinate system, where the first associated vehicle is any one of the associated vehicles;

[0056] Input the deviation driving data into a first cost value model to determine a cost value between the first associated vehicle and the first reference prior trajectory.

[0057] Optionally, in another possible implementation manner of the second aspect, the above reference coordinate system includes a first coordinate direction and a second coordinate direction. The first coordinate direction is parallel to the first reference prior trajectory, and the second coordinate direction is perpendicular to the first reference prior trajectory. The second driving data includes at least one of a real-time position, a real-time speed, and a real-time heading angle. The deviation driving data includes at least one of the following data: a first deviation distance along the first coordinate direction, a second deviation distance along the second coordinate direction, a first speed along the first coordinate direction, a second speed along the second coordinate direction, and a first heading angle relative to the first coordinate direction.

[0058] Optionally, in another possible implementation manner of the second aspect, the above first-generation value model includes a position deviation value model, a first speed deviation value model, and a second speed deviation value model; correspondingly, the above second determination unit is further configured to:

[0059] Substitute the first deviation distance, the second deviation distance, and the first heading angle into the position deviation value model to determine the first-generation value between the first associated vehicle and the first reference prior trajectory;

[0060] Substitute the first deviation distance and the first speed into the first speed deviation value model to determine the second-generation value between the first associated vehicle and the first reference prior trajectory;

[0061] Substitute the second deviation distance and the second speed into the second speed deviation value model to determine the third-generation value between the first associated vehicle and the first reference prior trajectory;

[0062] Determine the value between the first associated vehicle and the first reference prior trajectory according to the first-generation value, the second-generation value, and the third-generation value.

[0063] Optionally, in another possible implementation manner of the second aspect, the current first driving data of the target vehicle includes a reference driving trajectory of the target vehicle within the current road range, and there is a first intersection point between the reference driving trajectory and the first predicted driving trajectory, where the first predicted driving trajectory is any predicted driving trajectory;

[0064] Correspondingly, the value between the first predicted driving trajectory and the target vehicle includes the values between each vehicle gap in the first predicted driving trajectory and the target vehicle, where the number of second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1;

[0065] Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, the distance between the i-th second associated vehicle and the first intersection is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection, where i is greater than 1 and less than or equal to N.

[0066] Optionally, in another possible implementation manner of the second aspect, the above-mentioned second determination module includes:

[0067] A fourth determination unit, configured to determine a first intersection according to the first driving data and the first predicted driving trajectory;

[0068] A fifth determination unit, configured to determine the distance between the j-th second associated vehicle and the first intersection, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th second associated vehicle and the first predicted driving trajectory, where j is an integer greater than or equal to 1 and less than or equal to N;

[0069] A sixth determination unit, configured to determine the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th and (j - 1)-th second associated vehicles and the first predicted driving trajectory, where when j is 1, the (j - 1)-th second associated vehicle is the first intersection;

[0070] A seventh determination unit, configured to substitute the distance between the j-th second associated vehicle and the first intersection, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second-generation value model to determine the value of the j-th vehicle gap with respect to the target vehicle.

[0071] Optionally, in another possible implementation manner of the second aspect, the above-mentioned second-generation value model includes a first collision value model, a second collision value model, and a third collision value model; correspondingly, the above-mentioned seventh determination unit is specifically configured to:

[0072] Substitute the distance between the j-th second associated vehicle and the first intersection, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory into the first collision value model to determine the fourth value corresponding to the j-th vehicle gap;

[0073] Substitute the gap distance corresponding to the j-th vehicle gap and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory into the second collision cost value model to determine the fifth cost value corresponding to the j-th vehicle gap;

[0074] Substitute the distance between the j-th second associated vehicle and the first intersection, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, and j into the third collision cost value model to determine the sixth cost value corresponding to the j-th vehicle gap;

[0075] Determine the cost value between the j-th vehicle gap and the target vehicle according to the fourth cost value, the fifth cost value, and the sixth cost value.

[0076] Optionally, in another possible implementation manner of the second aspect, the above first planning module includes:

[0077] An eighth determination unit, configured to determine a target vehicle gap that meets the passing condition according to the cost values between each vehicle gap and the target vehicle;

[0078] A ninth determination unit, configured to plan the driving trajectory and driving speed of the target vehicle according to the target vehicle gap.

[0079] In a third aspect, an embodiment of the present application provides a terminal device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the trajectory planning method as described above is implemented.

[0080] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the trajectory planning method as described above is implemented.

[0081] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, the terminal device is enabled to execute the trajectory planning method as described above.

[0082] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: By pre-statistically analyzing the prior trajectory data of vehicles passing through the current road range by roadside devices and sending it to the target vehicle, and by matching the surrounding vehicles with the prior trajectory data, the long-term driving trajectories of the surrounding vehicles are predicted. Furthermore, based on the cost value between the driving trajectories of the surrounding vehicles and the target vehicle, the safety of the target vehicle passing through each area within the current road range is evaluated to perform trajectory planning for the target vehicle. Thus, by statistically analyzing the prior trajectory data by roadside devices and combining the vehicle-side and roadside information, not only the computational complexity of trajectory planning at the vehicle side is reduced, the computational time consumption and resource occupancy are reduced, but also the accuracy of trajectory planning is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following described drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0084] Figure 1 is a flowchart of a trajectory planning method provided by an embodiment of the present application;

[0085] Figure 2 is a schematic diagram of the current road range corresponding to a target vehicle provided by an embodiment of the present application;

[0086] Figure 3 is a schematic diagram of another current road range corresponding to a target vehicle provided by an embodiment of the present application;

[0087] Figure 4 is a schematic diagram of a Frenet coordinate system provided by an embodiment of the present application;

[0088] Figure 5 is a flowchart of a trajectory planning method provided by another embodiment of the present application;

[0089] Figure 6 is a flowchart of a trajectory planning method provided by still another embodiment of the present application;

[0090] Figure 7 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present application;

[0091] Figure 8 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0092] In the following description, specific details such as specific system architectures and technologies are presented for purposes of illustration and not limitation, so as to provide a thorough understanding of the embodiments of the present application. However, those skilled in the art should understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from obscuring the description of the present application.

[0093] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0094] It should also be understood that the term "and / or" used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0095] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" depending on the context. Similarly, the phrases "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" depending on the context.

[0096] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for differentiating descriptions and cannot be understood as indicating or implying relative importance.

[0097] The reference to "one embodiment" or "some embodiments" etc. described in the specification of the present application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in another way. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in another way.

[0098] The trajectory planning method, device, terminal device, storage medium, and computer program provided by the present application will be described in detail below with reference to the accompanying drawings.

[0099] Figure 1 The flowchart shows a trajectory planning method provided by an embodiment of the present application.

[0100] As Figure 1 shown, the trajectory planning method includes the following steps:

[0101] Step 101: Obtain at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device.

[0102] It should be noted that the trajectory planning method of the embodiment of the present application can be executed by the trajectory planning device of the embodiment of the present application. The trajectory planning device of the embodiment of the present application can be configured in any terminal device to execute the trajectory planning method of the embodiment of the present application. For example, the trajectory planning device of the embodiment of the present application can be configured in the on-board unit (OBU) of the vehicle to perform trajectory planning according to the current road conditions.

[0103] Among them, the target vehicle can refer to any vehicle that is currently driving on the road and is equipped with the trajectory planning device of the embodiment of the present application for trajectory planning.

[0104] Among them, the current road range corresponding to the target vehicle can refer to the road range where the target vehicle is currently driving. For example, when the target vehicle travels to a certain intersection, the intersection range is the current road range corresponding to the target vehicle.

[0105] It should be noted that in actual use, the current road range corresponding to the target vehicle can be determined according to actual trajectory planning requirements, and the embodiment of the present application does not limit this.

[0106] Among them, the roadside device can refer to a roadside device installed within the current road range corresponding to the target vehicle and capable of perceiving the driving states of various vehicles within the current road range. For example, when the current road range is a certain intersection, the roadside device can refer to a roadside device installed at the intersection and capable of perceiving all vehicles within the intersection range; the number of roadside devices can be one or more. The roadside device can be composed of a sensing device, a communication device, and a data processing device. Among them, the sensing device is used to collect monitoring data within the sensing range, which can include one or more of radar devices (such as lidar, millimeter-wave radar, etc.), cameras, and other devices, but is not limited to the above device types; the data processing device is used to process the collected monitoring data to generate the required sensing results; the communication device can be used to send the generated sensing results to the server and / or the vehicle end.

[0107] It should be noted that the above examples are only exemplary and should not be regarded as a limitation to this application. In actual use, appropriate types of roadside devices can be installed to monitor the traffic conditions on the road according to actual needs and specific application scenarios.

[0108] Among them, the reference prior trajectory can be the driving trajectory commonly used by vehicles when passing through the current road range, which is calculated and statistically analyzed by the roadside device based on long-term monitoring data of the current road range.

[0109] It should be noted that the above long-term monitoring data can be the data collected by the roadside device on the driving data of vehicles passing through the current road range within a relatively long period of time; the reference prior trajectory can reflect the driving trajectories of vehicles passing through the current road range statistically analyzed over a relatively long period of time. Among them, the reference prior trajectory can be determined by the roadside device based on the long-term monitoring data collected within time ranges such as the most recent 1 day, 1 week, 1 month, or 1 year. In actual use, the time range of the reference prior trajectory can be determined according to actual needs and specific application scenarios, and the embodiments of this application do not make any limitations in this regard.

[0110] In the embodiments of this application, before the target vehicle travels to the current road range and after entering the communication range of the roadside device, the target vehicle can send a signal to the roadside device through the OBU carried in the vehicle, so that the roadside device sends the reference prior trajectory statistically analyzed within a period of time before the current moment to the target vehicle, and the target vehicle can receive the reference prior trajectory sent by the roadside device through the OBU.

[0111] For example, after receiving the signal sent by the target vehicle, the roadside device can send the recently statistically analyzed prior trajectory as the reference prior trajectory to the target vehicle. For instance, the prior trajectories statistically analyzed 1 day, 1 week, or 1 month before the current moment can be sent to the target vehicle. In actual use, the time range corresponding to the reference prior trajectory sent by the roadside device can be determined according to actual needs and specific application scenarios, and the embodiments of this application do not make any limitations in this regard.

[0112] Furthermore, since the prior trajectory statistically analyzed by the roadside device includes the driving trajectories of all vehicles passing through the current road range over a long period of time, the data volume may be very large and may include driving trajectories that are completely irrelevant to the current driving state of the target vehicle. Therefore, the prior trajectory sent by the roadside device can also be preliminarily screened to remove the prior trajectories that are irrelevant to the current path planning requirements of the target vehicle, thereby further reducing the computational complexity of subsequent trajectory planning. That is, in a possible implementation manner of the embodiments of this application, the above step 101 may include:

[0113] Obtain at least one initial prior trajectory within the current road range sent by the roadside device;

[0114] Obtain the reference driving trajectory of the target vehicle within the current road range;

[0115] According to the reference driving trajectory, screen the initial prior trajectory to determine the reference prior trajectory.

[0116] Among them, the initial prior trajectory can be all the prior trajectories of the current road range currently counted by the roadside device.

[0117] Among them, the reference driving trajectory can be the driving trajectory of the target vehicle within the current road range determined according to the driving path pre-planned by the target vehicle.

[0118] For example, assume that the current road range is the range of an intersection. According to the driving path pre-planned by the target vehicle, the target vehicle needs to go straight at this intersection, and the target vehicle is currently in the straight lane. Then, the driving trajectory of going straight through the intersection from the current lane can be determined as the reference driving trajectory; another example is that the target vehicle needs to turn left at this intersection, and the target vehicle is currently in the left-turn lane. Then, the driving trajectory of turning left through the intersection from the current lane can be determined as the reference driving trajectory; another example is that the target vehicle needs to turn left at this intersection, and the target vehicle is currently in the straight lane. Then, the driving trajectory of changing lanes from the current lane to the left-turn lane and then turning left through the intersection from the left-turn lane can be determined as the reference driving trajectory.

[0119] It should be noted that the above examples are only exemplary and should not be regarded as a limitation of this application. In actual use, the reference driving trajectory can be determined according to the actual needs and specific application scenarios based on the driving path pre-planned by the target vehicle. The embodiments of this application do not make any limitations in this regard.

[0120] As a possible implementation manner, after obtaining the initial prior trajectory sent by the roadside device and the reference driving trajectory of the target vehicle, the correlation between the reference driving trajectory and each initial prior trajectory can be calculated, and according to the correlation between the reference driving trajectory and each initial prior trajectory, the initial prior trajectory related to the reference driving trajectory can be screened out as the reference prior trajectory.

[0121] As an example, since the embodiments of the present application can use the reference driving trajectory as a reference to determine whether there is a collision risk between the target vehicle and other vehicles within the current road range, so as to ensure the driving safety of the target vehicle. Therefore, the correlation between the reference driving trajectory and the initial prior trajectory can be determined according to whether there is an intersection point between the reference driving trajectory and the initial prior trajectory, so as to screen out the prior trajectory that may have an intersection point with the driving trajectory of the target vehicle as the reference prior trajectory. For example, if there is an intersection point between the reference driving trajectory and an initial prior trajectory, it can be determined that the reference driving trajectory is related to the initial prior trajectory, and thus the initial prior trajectory can be determined as the reference prior trajectory; if there is no intersection point between the reference driving trajectory and an initial prior trajectory, it can be determined that the reference driving trajectory is not related to the initial prior trajectory, and thus the initial prior trajectory can be removed.

[0122] For example, as Figure 2 shown, assume that two initial prior trajectories 12 and 13 sent by the roadside device are currently obtained, and these two initial prior trajectories have intersection points 14 and 15 with the reference driving trajectory corresponding to the target vehicle 111 respectively. Therefore, the initial prior trajectories 12 and 13 can both be determined as the reference prior trajectories.

[0123] As a possible implementation, since if the target vehicle has already passed through the intersection point with a certain prior trajectory, the target vehicle will not collide with the associated vehicle traveling on this prior trajectory during subsequent driving, so there is no need to consider such prior trajectories in subsequent trajectory planning. Therefore, the correlation between the reference driving trajectory and the initial prior trajectory can also be determined according to whether there is an intersection point between the reference driving trajectory and the initial prior trajectory, and whether the target vehicle has already passed through this intersection point, so as to screen out the prior trajectory related to the future driving trajectory of the target vehicle as the reference prior trajectory. For example, if there is an intersection point between the reference driving trajectory and an initial prior trajectory, and the reference driving trajectory has not passed through this intersection point yet, it can be determined that the reference driving trajectory is related to the initial prior trajectory, and thus the initial prior trajectory can be determined as the reference prior trajectory; if there is no intersection point between the reference driving trajectory and an initial prior trajectory, or although there is an intersection point between the reference driving trajectory and this initial prior trajectory, but the target vehicle has already passed through this intersection point, it can be determined that the reference driving trajectory is not related to the initial prior trajectory, and thus the initial prior trajectory can be removed.

[0124] For example, as Figure 2As shown in the figure, currently two initial prior trajectories 12 and 13 sent by the roadside device are obtained. There are intersection points 14 and 15 between these two initial prior trajectories and the reference driving trajectory corresponding to the target vehicle 111 respectively, and the target vehicle 111 has not passed through the intersection points 14 and 15 yet. Then, both the initial prior trajectories 12 and 13 can be determined as reference prior trajectories. For another example, as Figure 3 shown, currently the target vehicle 111 has traveled to a position between the intersection point 14 and the intersection point 15. Then, only the initial prior trajectory 12 can be determined as the reference prior trajectory, and the initial prior trajectory 13 can be removed.

[0125] Step 102: Obtain the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle.

[0126] Among them, the first driving data may include data such as the reference driving trajectory, current position, current speed, and current acceleration of the target vehicle within the current road range. In actual use, the first driving data may include but is not limited to the above data types, and the embodiments of the present application do not make limitations in this regard.

[0127] Among them, the associated vehicle may refer to each surrounding vehicle that can be currently sensed by the sensors installed in the target vehicle.

[0128] It should be noted that the sensors installed in the target vehicle may include various radar devices, vision sensors, etc., but are not limited thereto.

[0129] Among them, the second driving data may refer to the current driving data of the associated vehicle currently collected by the sensors in the target vehicle.

[0130] It should be noted that the second driving data may include data such as the current position, current speed, and current acceleration of the associated vehicle. In actual use, the second driving data may include but is not limited to the above data types, and the embodiments of the present application do not make limitations in this regard.

[0131] As a possible implementation manner, after the target vehicle enters the current road range and obtains the reference prior trajectory sent by the roadside device, the target vehicle can obtain its own current first driving data according to the OBU, positioning device, etc. installed on itself; and can collect the driving data of surrounding vehicles in real time through the sensors installed on itself to obtain the current second driving data of the associated vehicle.

[0132] As a possible implementation manner, since the roadside device can monitor the driving data of all vehicles within the current road range, the target vehicle can also communicate with the roadside device to enable the roadside device to send the currently collected first driving data of the target vehicle and the current second driving data of the associated vehicle to the target vehicle.

[0133] It should be noted that the above examples are only exemplary and should not be regarded as a limitation to this application. In actual use, the acquisition methods of the first driving data and the second driving data may be related to the functions of the target vehicle or roadside equipment. The acquisition methods of the first driving data and the second driving data can be selected according to actual needs and specific application scenarios.

[0134] Step 103: Determine the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory.

[0135] Among them, the predicted driving trajectory can be used to represent the driving trajectory of the associated vehicle within the current road range in the future for a period of time.

[0136] In the embodiment of this application, when the target vehicle passes through an intersection, it is necessary to predict the driving trajectories of surrounding vehicles, and then plan its own driving trajectory to ensure driving safety. However, if the vehicle trajectories of surrounding vehicles are predicted by combining the lane information in the map, due to the complex traffic conditions at the intersection scene and the instability of the driving trajectories of surrounding vehicles, the prediction error is relatively large; if the trajectory is predicted by using the real-time driving data of surrounding vehicles, not only is the computational complexity high, but also the short-term data obtained by the sensor cannot be used for long-term trajectory prediction, resulting in low accuracy of trajectory prediction. Therefore, in the embodiment of this application, by matching the associated vehicle with the reference prior trajectory according to the current second driving data of the associated vehicle and the reference prior trajectory obtained from the roadside equipment, a reference prior trajectory with a high matching degree with the associated vehicle is directly selected as the predicted driving trajectory of the associated vehicle, so that not only can the accurate predicted driving trajectory of the associated vehicle be predicted by using the real-time driving data of the associated vehicle, but also the computational complexity of the associated vehicle trajectory prediction can be reduced.

[0137] As a possible implementation manner, the matching degree between the second driving data and each reference prior trajectory can be determined according to the second driving data and each reference prior trajectory, and then the reference prior trajectory with a relatively high matching degree with the second driving data can be selected according to the matching degree threshold as the predicted driving trajectory corresponding to the associated vehicle. For example, if the matching degree between a reference prior trajectory and the second driving data is greater than or equal to the matching degree threshold, the reference prior trajectory can be determined as the predicted driving trajectory corresponding to the associated vehicle.

[0138] It can be understood that through the above process of matching associated vehicles with reference prior trajectories, each associated vehicle can be classified into each reference prior trajectory; for each associated vehicle included in a reference prior trajectory (i.e., the reference prior trajectory is the predicted driving trajectory corresponding to these associated vehicles), it can be considered that these associated vehicles will drive along the reference prior trajectory within the current road range.

[0139] For example, as Figure 2 shown, two reference prior trajectories 12 and 13 within the current road range have been determined, and the positional relationship between the reference driving trajectory 11 corresponding to the target vehicle 111 and the reference prior trajectories 12 and 13 is as Figure 2 shown. The associated vehicles within the current road range include associated vehicles 121, 122, 123, 131, and 132; after matching each associated vehicle with each reference prior trajectory through the above matching process, it is determined that the predicted driving trajectories corresponding to associated vehicles 121, 122, and 123 are the reference prior trajectory 12, and the predicted driving trajectories corresponding to associated vehicles 131 and 132 are the reference prior trajectory 13; the positional relationship between each associated vehicle and the reference prior trajectory is as Figure 2 shown. Thus, it can be considered that associated vehicles 121, 122, and 123 will drive along the reference prior trajectory 12 within the current road range, and associated vehicles 131 and 132 will drive along the reference prior trajectory 13 within the current road range.

[0140] Furthermore, the degree of matching between an associated vehicle and a reference prior trajectory can be measured by the cost value between the current second driving data of the associated vehicle and the reference prior trajectory. That is, in a possible implementation manner of the embodiments of the present application, step 103 described above may include:

[0141] Determine the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory;

[0142] Determine the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

[0143] Among them, the cost value between an associated vehicle and a reference prior trajectory can be used to measure the degree of matching between the current second driving data of the associated vehicle and the reference prior trajectory. The larger the cost value between an associated vehicle and a reference prior trajectory, the lower the degree of matching between the second driving data and the reference prior trajectory, that is, the lower the possibility that the associated vehicle drives along the reference prior trajectory within the current road range; the smaller the cost value between an associated vehicle and a reference prior trajectory, the higher the degree of matching between the second driving data and the reference prior trajectory, that is, the higher the possibility that the associated vehicle drives along the reference prior trajectory within the current road range.

[0144] As a possible implementation, after determining the cost values between each associated vehicle and each reference prior trajectory, the predicted driving trajectory corresponding to each associated vehicle can be determined according to the first cost value threshold. It can be understood that if the cost value between an associated vehicle and a reference prior trajectory is less than the first cost value threshold, it can be determined that the matching degree between the current second driving trajectory of the associated vehicle and the reference prior trajectory is relatively high, so that the reference prior trajectory can be determined as the predicted driving trajectory corresponding to the associated vehicle.

[0145] As a possible implementation, after determining the cost values between an associated vehicle and each reference prior trajectory, the reference prior trajectory with the minimum cost value between it and the associated vehicle can be determined as the predicted driving trajectory corresponding to the associated vehicle.

[0146] As a possible implementation, in order to further ensure the accuracy of the predicted driving trajectory of the associated vehicle, after determining the cost values between an associated vehicle and each reference prior trajectory, the reference prior trajectory with the minimum cost value between it and the associated vehicle and less than the first cost value threshold can be determined as the predicted driving trajectory corresponding to the associated vehicle.

[0147] Furthermore, in order to convert the cost value into the matching degree between the associated vehicle and the reference prior trajectory after determining the cost value between the associated vehicle and the reference prior trajectory, and then determine the predicted driving trajectory corresponding to the associated vehicle according to the matching degree, so as to further improve the accuracy of the predicted associated vehicle trajectory and further improve the reliability of the vehicle trajectory planning. That is, in a possible implementation manner of the embodiment of the present application, the above determining the predicted driving trajectory corresponding to each associated vehicle according to the cost values between each associated vehicle and each reference prior trajectory includes:

[0148] Determine the matching degrees between the first associated vehicle and each reference prior trajectory according to the cost values between the first associated vehicle and each reference prior trajectory, where the first associated vehicle is any associated vehicle;

[0149] Determine the predicted driving trajectory corresponding to the first associated vehicle according to the matching degrees between the first associated vehicle and each reference prior trajectory.

[0150] As a possible implementation, according to the principle that the matching degree between the associated vehicle and the reference prior trajectory is negatively correlated with the cost value therebetween, the matching degree between the associated vehicle and the reference prior trajectory can be determined according to the cost value between the associated vehicle and the reference prior trajectory. For example, the reciprocal of the cost value between the first associated vehicle and the reference prior trajectory can be determined as the matching degree between the first associated vehicle and the reference prior trajectory.

[0151] As a possible implementation, after determining the matching degrees between the associated vehicles and each reference prior trajectory, the predicted driving trajectories corresponding to each associated vehicle can be determined according to a matching degree threshold. It can be understood that if the matching degree between the first associated vehicle and a reference prior trajectory is greater than the matching degree threshold, it can be determined that the matching degree between the current second driving trajectory of the first associated vehicle and the reference prior trajectory is relatively high, and thus the reference prior trajectory can be determined as the predicted driving trajectory corresponding to the first associated vehicle.

[0152] As a possible implementation, after determining the matching degrees between the first associated vehicle and each reference prior trajectory, the reference prior trajectory with the maximum matching degree with the first associated vehicle can be determined as the predicted driving trajectory corresponding to the first associated vehicle.

[0153] As a possible implementation, in order to further ensure the accuracy of the predicted driving trajectories of the associated vehicles, after determining the matching degrees between the first associated vehicle and each reference prior trajectory, the reference prior trajectory with the maximum matching degree with the first associated vehicle and greater than the matching degree threshold can be determined as the predicted driving trajectory corresponding to the first associated vehicle.

[0154] It should be noted that in actual use, the specific values of the above-mentioned matching degree threshold or the first-generation value threshold can be determined according to actual needs and specific application scenarios, and the embodiments of the present application do not limit this.

[0155] Furthermore, since the deviation driving data between the associated vehicle and the reference prior trajectory can be used to measure the similarity between the second driving data and the reference prior trajectory, the deviation driving data between the associated vehicle and the reference prior trajectory can be processed by a pre-trained value model to determine the value between the associated vehicle and the reference prior trajectory. That is, in a possible implementation of the embodiments of the present application, the above-mentioned determination of the value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory may include:

[0156] Taking the first reference prior trajectory as a reference line, a reference coordinate system corresponding to the first reference prior trajectory is established, where the first reference prior trajectory is any reference prior trajectory;

[0157] According to the current second driving data of the first associated vehicle and the reference coordinate system, the deviation driving data between the first associated vehicle and the first reference prior trajectory is determined, where the first associated vehicle is any associated vehicle;

[0158] The deviation driving data is input into the first-generation value model to determine the value between the first associated vehicle and the first reference prior trajectory.

[0159] As a possible implementation, the current second driving data of the associated vehicle and the reference prior trajectory can be transformed into the same coordinate system to determine the deviation data between the associated vehicle and the reference prior trajectory.

[0160] Among them, the reference coordinate system can refer to the Frenet coordinate system established with the first reference prior trajectory as the reference line and the tangent vector and normal vector of the first reference trajectory as the two coordinate directions respectively.

[0161] Among them, the reference coordinate system can include a first coordinate direction and a second coordinate direction. The first coordinate direction is parallel to the first reference prior trajectory, and the second coordinate direction is perpendicular to the first reference prior trajectory.

[0162] Such as Figure 4 shown, the coordinate axes of this Frenet coordinate system are perpendicular to each other, and are divided into a first coordinate direction (i.e., the s direction in Figure 4 , along the direction of the first reference prior trajectory, usually referred to as longitudinal) and a second coordinate direction (i.e., the d direction in Figure 4 , along the normal direction of the current first reference prior trajectory, usually referred to as lateral). The Frenet coordinate system significantly simplifies the problem of representing the position of a vehicle when driving on a road. Because when a vehicle is driving on a road, it is easy to find the reference line of the road (i.e., the center line of the road) or the reference line of the vehicle driving trajectory, then the position based on the reference line can be simply described using the longitudinal distance (i.e., the distance along the road direction) and the lateral distance (i.e., the distance deviating from the reference line), and the speed based on the reference line can be simply described using the longitudinal speed (i.e., the speed along the reference line direction) and the lateral speed (i.e., the speed along the normal direction of the reference line).

[0163] Among them, the second driving data can include at least one of the real-time position, real-time speed, and real-time heading angle.

[0164] Among them, the deviation driving data can include at least one of the following data: the first deviation distance along the first coordinate direction, the second deviation distance along the second coordinate direction, the first speed along the first coordinate direction, the second speed along the second coordinate direction, and the first heading angle relative to the first coordinate direction.

[0165] As a possible implementation, after establishing the reference coordinate system (i.e., Frenet coordinate system) as described above with the first reference prior trajectory as the reference line, the first associated vehicle can be represented in the reference coordinate system according to its real-time position, and the speed representation of the first associated vehicle in the reference coordinate system can be determined according to its real-time speed, and the heading angle representation of the first associated vehicle in the reference coordinate system can be determined according to its real-time heading angle, so as to determine the deviation data between the first associated vehicle and the first reference prior trajectory according to the coordinate representation, speed representation and heading angle representation of the first associated vehicle in the reference coordinate system.

[0166] As an example, for the first associated vehicle, the coordinate of the first associated vehicle in the s direction can be determined as the first deviation distance of the trajectory of the first associated vehicle along the first coordinate direction; and the coordinate of the first associated vehicle in the d direction can be determined as the second deviation distance of the trajectory of the first associated vehicle along the second coordinate direction; and the speed representation of the first associated vehicle in the s direction can be determined as the first speed of the trajectory of the first associated vehicle along the first coordinate direction; and the speed representation of the first associated vehicle in the d direction can be determined as the second speed of the trajectory of the first associated vehicle along the second coordinate direction; and the angle between the first associated vehicle and the s direction in the reference coordinate system can be determined as the first heading angle of the first associated vehicle relative to the first coordinate direction. By analogy, the deviation driving data between each associated vehicle and each reference prior trajectory can be determined in turn.

[0167] As a possible implementation, a cost value model for determining the cost value between an associated vehicle and a reference prior trajectory according to the deviation driving data therebetween can be pre-trained. Therefore, after determining the deviation driving data between the first associated vehicle and the first reference prior trajectory, each deviation driving data (the first deviation distance along the first coordinate direction, the second deviation distance along the second coordinate direction, the first speed along the first coordinate direction, the second speed along the second coordinate direction, the first heading angle relative to the first coordinate direction) can be input into the first cost value model, and the cost value between the first associated vehicle and the first reference prior trajectory can be determined according to the output of the first cost value model.

[0168] For example, the cost value between the first associated vehicle and the first reference prior trajectory can be expressed by the following formula:

[0169] cost1 = Q1(s, l, g, v s , v l )

[0170] Among them, cost1 is the cost value between the first associated vehicle and the first reference prior trajectory, Q1 represents the first cost value model, s is the first deviation distance, l is the second deviation distance, h is the first heading angle, and v s is the first speed, and v l is the second speed.

[0171] Step 104: Determine the cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectories corresponding to each associated vehicle, and the second driving data.

[0172] Among them, the cost value between the predicted driving trajectory and the target vehicle can be used to measure the possibility of collision between the target vehicle and each associated vehicle corresponding to the predicted driving trajectory; that is to say, the cost value between the predicted driving trajectory and the target vehicle can be used to measure the traffic safety when the target vehicle travels to the position where it intersects with the predicted driving trajectory.

[0173] In the embodiment of the present application, after determining the predicted driving trajectories corresponding to each associated vehicle, the cost value between each predicted driving trajectory and the target vehicle can be determined according to the first driving data, the predicted driving trajectories corresponding to each associated vehicle, and the second driving data, so as to measure the safety of the target vehicle passing through each predicted driving trajectory through this cost value, and then plan the driving trajectory of the target vehicle according to this safety.

[0174] Furthermore, since there are intersection points between the reference driving data corresponding to the target vehicle and the predicted driving trajectories, and at least one associated vehicle can be corresponding to the predicted driving trajectories, these associated vehicles and the intersection points can form multiple vehicle gaps in the predicted driving trajectories. It can be understood that when the target vehicle passes through the predicted driving trajectories, it can select any one of the vehicle gaps in the predicted driving trajectories. Therefore, the cost value between the predicted driving trajectory and the target vehicle can be used to measure whether the collision time for the target vehicle to pass through each vehicle gap in the predicted driving trajectory is sufficient to allow the target vehicle to pass safely. That is, in a possible implementation manner of the embodiment of the present application, the above-mentioned first driving data of the target vehicle currently may include the reference driving trajectory of the target vehicle within the current road range, and there is a first intersection point between the reference driving trajectory and the first predicted driving trajectory, where the first predicted driving trajectory is any one of the predicted driving trajectories;

[0175] Correspondingly, the cost value between the above-mentioned first predicted driving trajectory and the target vehicle includes the cost values between each vehicle gap in the first predicted driving trajectory and the target vehicle, where the number of second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1;

[0176] Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection point, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, the distance between the i-th second associated vehicle and the first intersection point is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection point, where i is greater than 1 and less than or equal to N;

[0177] Correspondingly, step 104 above may include:

[0178] Determine the first intersection point according to the first driving data and the first predicted driving trajectory;

[0179] According to the current second driving data and the first predicted driving trajectory of the j-th second associated vehicle, determine the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, where j is an integer greater than or equal to 1 and less than or equal to N;

[0180] According to the current second driving data and the first predicted driving trajectory of the j-th and (j - 1)-th second associated vehicles, determine the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, where when j is 1, the (j - 1)-th second associated vehicle is the first intersection point;

[0181] Substitute the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second-generation value model to determine the value of the j-th vehicle gap and the target vehicle.

[0182] Among them, the second driving data may include the real-time position and the real-time speed.

[0183] For example, such as Figure 2As shown in the figure, the second associated vehicles 121, 122, and 123 are three associated vehicles corresponding to the predicted driving trajectory 12. The first intersection point between the predicted driving trajectory 12 and the reference driving trajectory 11 corresponding to the target vehicle 111 is 14. Therefore, the second associated vehicle 121 can be the first second associated vehicle in the predicted driving trajectory 12, the second associated vehicle 122 can be the second second associated vehicle in the predicted driving trajectory 12, and the second associated vehicle 123 can be the third second associated vehicle in the predicted driving trajectory 12; correspondingly, the vehicle gap between the second associated vehicle 121 and the first intersection point 14 can be the first vehicle gap in the predicted driving trajectory 12, the vehicle gap between the second associated vehicle 122 and the second associated vehicle 121 can be the second vehicle gap in the predicted driving trajectory 12, and the vehicle gap between the third associated vehicle 123 and the second associated vehicle 122 can be the third vehicle gap in the predicted driving trajectory 12.

[0184] For another example, as Figure 2 shown in the figure, the second associated vehicles 131 and 132 are two associated vehicles corresponding to the predicted driving trajectory 13. The first intersection point between the predicted driving trajectory 13 and the reference driving trajectory 11 corresponding to the target vehicle 111 is 15. Therefore, the second associated vehicle 131 can be the first second associated vehicle in the predicted driving trajectory 13, and the second associated vehicle 132 can be the second second associated vehicle in the predicted driving trajectory 13; correspondingly, the vehicle gap between the second associated vehicle 131 and the first intersection point 15 can be the first vehicle gap in the predicted driving trajectory 13, and the vehicle gap between the second associated vehicle 132 and the second associated vehicle 131 can be the second vehicle gap in the predicted driving trajectory 13.

[0185] As a possible implementation manner, it is possible to establish a Frenet coordinate system as shown in Figure 4 the figure, taking the first predicted driving trajectory as the reference line and the tangent vector and normal vector of the first predicted driving trajectory as the two coordinate directions in accordance with the aforementioned method of establishing a reference coordinate system; then, according to the first driving data corresponding to the target vehicle, represent the reference driving trajectory corresponding to the target vehicle in this Frenet coordinate system to determine the first intersection point between the reference driving trajectory and the first predicted driving trajectory; and represent each second associated vehicle in this Frenet coordinate system according to the real-time positions of each second associated vehicle, and determine the speed representation of each second associated vehicle in this Frenet coordinate system according to the real-time speeds of each second associated vehicle, so as to determine the real-time driving data of each second associated vehicle along the first predicted driving trajectory according to the coordinate representation and speed representation of each second associated vehicle in the reference coordinate system.

[0186] As an example, the absolute value of the difference in the coordinates of each second associated vehicle and the first intersection in the s direction can be respectively determined as the distance between each second associated vehicle and the first intersection; and the velocity representation of each second associated vehicle in the s direction can be respectively determined as the driving velocity of each second associated vehicle along the first predicted driving trajectory; and the absolute value of the difference in the coordinates of each second associated vehicle and the previous second associated vehicle in the s direction can be respectively determined as the gap distance corresponding to each vehicle gap; and the velocity difference between each second associated vehicle and the previous second associated vehicle in the s direction can be determined as the velocity difference of each adjacent second associated vehicle along the first predicted driving trajectory.

[0187] It should be noted that for the first vehicle gap in the first predicted driving trajectory, the corresponding gap distance refers to the absolute value of the difference in the coordinates of the first second associated vehicle and the first intersection in the s direction; and the velocity difference between the first second associated vehicle and the previous second associated vehicle along the first predicted driving trajectory is the driving velocity of the first second associated vehicle along the first predicted driving trajectory.

[0188] As a possible implementation, a cost value model for determining the cost value corresponding to each vehicle gap in the predicted driving trajectory according to the driving data differences of each associated vehicle in the predicted driving trajectory can be pre-trained. Therefore, after determining the above-mentioned driving data differences of each associated vehicle and each vehicle gap data, for the j-th vehicle gap, the distance between the j-th second associated vehicle and the first intersection, the driving velocity of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the velocity difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and the sequence number j of the j-th vehicle gap can be substituted into the second cost value model, and the cost value between the j-th vehicle gap and the target vehicle can be determined according to the output of the second cost value model. By analogy, in the same way, the cost values between each vehicle gap in each predicted driving trajectory and the target vehicle can be determined.

[0189] For example, the cost value between the j-th vehicle gap in the first predicted driving trajectory and the target vehicle can be expressed by the following formula:

[0190] cost2 = Q2(s, Δs, v, Δv, j)

[0191] Among them, cost1 is the cost value between the j-th vehicle gap in the first predicted driving trajectory and the target vehicle, Q12 represents the second cost value model, s is the distance between the j-th second associated vehicle and the first intersection, Δs is the gap distance corresponding to the j-th vehicle gap, v is the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, Δv is the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j is the serial number of the vehicle gap.

[0192] Step 105: Plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0193] In the embodiment of the present application, after determining the cost value between each predicted driving trajectory and the target vehicle, the safety of the target vehicle passing through each position in each predicted driving trajectory can be judged according to the cost value between each predicted driving trajectory and the target vehicle. If the cost value between a predicted driving trajectory and the target vehicle is relatively high, it can be determined that the collision time for the target vehicle to pass through a certain position in this predicted driving trajectory may not be sufficient for the target vehicle to pass, that is, the safety of the target vehicle passing through a certain position in this predicted driving trajectory is relatively low. Therefore, it can be selected not to pass from here, and the vehicle can temporarily decelerate or wait at a safe position. If the cost value between a predicted driving trajectory and the target vehicle is relatively low, it can be determined that the collision time for the target vehicle to pass through a certain position in this predicted driving trajectory may be sufficient for the target vehicle to pass, that is, the safety of the target vehicle passing through a certain position in this predicted driving trajectory is relatively high. Therefore, it can be selected to pass through this position as soon as possible, so as to realize the trajectory planning of the target vehicle.

[0194] Furthermore, when the cost value between the predicted driving trajectory and the target vehicle includes the cost value between each vehicle gap in this predicted driving trajectory and the target vehicle, the vehicle gaps with relatively high safety can be selected according to the cost value between each vehicle gap and the target vehicle, and the intersection can be passed through from the vehicle gaps with relatively high safety to realize the trajectory planning of the target vehicle, and further improve the reliability and rationality of the vehicle trajectory planning. That is, in a possible implementation manner of the embodiment of the present application, the above step 105 may include:

[0195] Determine the target vehicle gap that meets the passing condition according to the cost value between each vehicle gap and the target vehicle;

[0196] Plan the driving trajectory and driving speed of the target vehicle according to the target vehicle gap.

[0197] As a possible implementation, since the lower the cost value between the vehicle gap and the target vehicle, the higher the safety of the target vehicle passing through the vehicle gap, the safety of the target vehicle passing through each vehicle gap can be judged according to the second cost value threshold. It can be understood that if the cost value between the target vehicle and a vehicle gap is less than the second cost value threshold, it can be determined that the collision time for the target vehicle to pass through the vehicle gap is sufficient for the target vehicle to pass, that is, the safety of the target vehicle passing through the vehicle gap is relatively high, so that the target vehicle can pass through the vehicle gap.

[0198] It should be noted that if a predicted driving trajectory contains multiple vehicle gaps with cost values less than the second cost value threshold, one eligible vehicle gap can be randomly selected to pass through; or, the vehicle gap with the smallest cost value can also be selected from multiple eligible vehicle gaps to pass through, so as to ensure the safety of the target vehicle as much as possible; or, the vehicle gap closest to the intersection can also be selected from the eligible vehicle gaps to pass through, so that the target vehicle can pass through the intersection as soon as possible and improve the traffic efficiency of the vehicle.

[0199] As a possible implementation, after determining the cost values between each vehicle gap in a predicted driving trajectory and the target vehicle, the vehicle gap with the smallest cost value between the predicted driving trajectory and the target vehicle can also be selected to pass through.

[0200] It should be noted that in actual use, the specific value of the second cost value threshold can be determined according to actual needs and specific application scenarios, and the embodiments of the present application do not limit this.

[0201] The trajectory planning method provided by the embodiments of the present application pre-statistics the prior trajectory data of vehicles passing through the current road range by roadside equipment and sends it to the target vehicle, and predicts the long-term driving trajectories of surrounding vehicles by matching the surrounding vehicles with the prior trajectory data. Furthermore, according to the cost values between the driving trajectories of the surrounding vehicles and the target vehicle, the safety of the target vehicle passing through each area within the current road range is evaluated to perform the trajectory planning of the target vehicle. Thus, by the roadside equipment for pre-statistics of the prior trajectory data and combining the vehicle terminal and roadside information, not only the computational complexity of the vehicle terminal for trajectory planning is reduced, the computational time consumption and resource occupation are reduced, but also the accuracy of the trajectory planning is improved.

[0202] In a possible implementation form of the present application, since the deviation distances, speed deviations, and heading angle deviations of the associated vehicle in different directions relative to the reference prior trajectory can generally reflect the differences between the current driving state of the associated vehicle and the reference prior trajectory in different aspects, and have different data characteristics, different cost value models can be trained for these three types of data respectively to process these three types of data respectively, so as to further improve the accuracy of cost value calculation, and further improve the accuracy of surrounding vehicle trajectory prediction, and further improve the accuracy of vehicle trajectory planning.

[0203] The following Figure 5 is used to further illustrate the trajectory planning method provided in the embodiments of the present application.

[0204] Figure 5 shows a schematic flow chart of another trajectory planning method provided in the embodiments of the present application.

[0205] As Figure 5 shown, the trajectory planning method includes the following steps:

[0206] Step 501, obtain at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device.

[0207] Step 502, obtain the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle.

[0208] Step 503, taking the first reference prior trajectory as the reference line, establish a reference coordinate system corresponding to the first reference prior trajectory, where the first reference prior trajectory is any reference prior trajectory.

[0209] As a possible implementation manner, the current second driving data of the associated vehicle and the reference prior trajectory can be converted into the same coordinate system to determine the deviation data between the associated vehicle and the reference prior trajectory.

[0210] Among them, the reference coordinate system may refer to the Frenet coordinate system established with the first reference prior trajectory as the reference line and the tangent vector and normal vector of the first reference trajectory as the two coordinate directions respectively.

[0211] Among them, the reference coordinate system may include a first coordinate direction and a second coordinate direction, the first coordinate direction is parallel to the first reference prior trajectory, and the second coordinate direction is perpendicular to the first reference prior trajectory.

[0212] Step 504, according to the current second driving data of the first associated vehicle and the reference coordinate system, determine the deviation driving data between the first associated vehicle and the first reference prior trajectory, where the first associated vehicle is any associated vehicle.

[0213] Among them, the second driving data may include at least one of the real-time position, real-time speed, and real-time heading angle.

[0214] Among them, the deviation driving data may include at least one of the following data: the first deviation distance along the first coordinate direction, the second deviation distance along the second coordinate direction, the first speed along the first coordinate direction, the second speed along the second coordinate direction, and the first heading angle relative to the first coordinate direction.

[0215] For the specific implementation process and principle of the above steps 501-504, reference may be made to the detailed description of the above embodiments, which will not be elaborated here.

[0216] Step 505: Substitute the first deviation distance, the second deviation distance, and the first heading angle into the position deviation cost value model to determine the first generation value between the first associated vehicle and the first reference prior trajectory.

[0217] As an example, the first generation value between the first associated vehicle and the first reference prior trajectory can be expressed by the following formula:

[0218] cost11 = I(s, l, h)

[0219] Among them, cost11 is the first generation value between the first associated vehicle and the first reference prior trajectory, I represents the position deviation cost value model, s is the first deviation distance, l is the second deviation distance, and h is the first heading angle.

[0220] Step 506: Substitute the first deviation distance and the first speed into the first speed deviation cost value model to determine the second generation value between the first associated vehicle and the first reference prior trajectory.

[0221] As an example, the second generation value between the first associated vehicle and the first reference prior trajectory can be expressed by the following formula:

[0222] cost12 = J(s, v s )

[0223] Among them, cost12 is the second generation value between the first associated vehicle and the first reference prior trajectory, J represents the first speed deviation cost value model, s is the first deviation distance, and v s is the first speed.

[0224] Step 507: Substitute the second deviation distance and the second speed into the second speed deviation cost value model to determine the third generation value between the first associated vehicle and the first reference prior trajectory.

[0225] As an example, the third generation value between the first associated vehicle and the first reference prior trajectory can be expressed by the following formula:

[0226] cost13 = H(l, v l )

[0227] where cost13 is the third-generation value between the first associated vehicle and the first reference prior trajectory, H represents the second speed deviation cost value model, l is the second deviation distance, and v l is the second speed.

[0228] Step 508: Determine the cost value between the first associated vehicle and the first reference prior trajectory according to the first-generation value, the second-generation value, and the third-generation value.

[0229] As a possible implementation, after determining the first-generation value, the second-generation value, and the third-generation value between the first associated vehicle and the first reference prior trajectory, the sum of the first-generation value, the second-generation value, and the third-generation value can be determined as the cost value between the first associated vehicle and the first reference prior trajectory.

[0230] As a possible implementation, different weights can also be configured for the first-generation value, the second-generation value, and the third-generation value according to the importance of the first-generation value, the second-generation value, and the third-generation value between the first associated vehicle and the first reference prior trajectory, and the weighted sum of the first-generation value, the second-generation value, and the third-generation value can be determined as the cost value between the first associated vehicle and the first reference prior trajectory.

[0231] As a possible implementation, the cost value between the first associated vehicle and the first reference prior trajectory can also be determined in the following way:

[0232]

[0233] where cost1 is the cost value between the first associated vehicle and the first reference prior trajectory, and cost11, cost12, and cost13 are the first-generation value, the second-generation value, and the third-generation value between the first associated vehicle and the first reference prior trajectory respectively, is a constant.

[0234] It should be noted that in the various ways of determining the cost value listed above, the weights and constants involved can all be obtained through training during the process of training the preset cost value model.

[0235] Step 509: Determine the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

[0236] Step 510: Determine the cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectories corresponding to each associated vehicle, and the second driving data.

[0237] Step 511: Plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0238] For the specific implementation process and principle of the above steps 509 - 511, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0239] The trajectory planning method provided by the embodiments of the present application determines the deviation driving data between the first associated vehicle and the first reference prior trajectory according to the current second driving data of the first associated vehicle and the reference coordinate system, and respectively substitutes the deviation driving data into the position deviation cost value model, the first speed deviation cost value model, and the second speed deviation cost value model according to the type of the deviation driving data to determine the first cost value, the second cost value, and the third cost value between the first associated vehicle and the first reference prior trajectory, and determines the cost value between the first associated vehicle and the first reference prior trajectory according to the first cost value, the second cost value, and the third cost value. Furthermore, according to the cost values between each associated vehicle and each reference prior trajectory, the predicted driving trajectory corresponding to each associated vehicle is determined. Finally, the driving trajectory of the target vehicle is planned according to the cost value between each predicted driving trajectory and the target vehicle. Thus, since the deviation distances, speed deviations, and heading angle deviations of the associated vehicle in different directions relative to the reference prior trajectory can usually respectively reflect the differences between the current driving state of the associated vehicle and the reference prior trajectory in different aspects and have different data characteristics, different cost value models are respectively trained for these three types of data to process these three types of data respectively, thereby further improving the accuracy of cost value calculation, further improving the accuracy of surrounding vehicle trajectory prediction, and further improving the accuracy of vehicle trajectory planning.

[0240] In a possible implementation form of the present application, since the distance and speed differences of the associated vehicle relative to the intersection point in the predicted driving trajectory, the distance and speed differences of the associated vehicle relative to the vehicle in front in the predicted driving trajectory, and the arrangement order of the associated vehicles in the predicted driving trajectory can respectively reflect the safety of the vehicle gap from different aspects and have different data characteristics, different cost value models can be respectively trained for these three types of data to process these three types of data respectively, thereby further improving the accuracy of cost value calculation, further improving the accuracy of vehicle gap safety assessment, and further improving the accuracy of vehicle trajectory planning and vehicle driving safety.

[0241] Next, in combination with Figure 6, a further description of the trajectory planning method provided in the embodiments of the present application will be given.

[0242] Figure 6 Fig. shows a schematic flow chart of another trajectory planning method provided in the embodiments of the present application.

[0243] As Figure 6 shown, the trajectory planning method includes the following steps:

[0244] Step 601, obtain at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device.

[0245] Step 602, obtain the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle.

[0246] Step 603, determine the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory.

[0247] Among them, the current first driving data of the target vehicle may include the reference driving trajectory of the target vehicle within the current road range, and there is a first intersection point between the reference driving trajectory and the first predicted driving trajectory, where the first predicted driving trajectory is any predicted driving trajectory;

[0248] Correspondingly, the cost value between the above-mentioned first predicted driving trajectory and the target vehicle includes the cost value between each vehicle gap in the first predicted driving trajectory and the target vehicle, where the number of the second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1;

[0249] Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection point, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, and the distance between the i-th second associated vehicle and the first intersection point is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection point, and i is greater than 1 and less than or equal to N.

[0250] Step 604, determine the first intersection point according to the first driving data and the first predicted driving trajectory.

[0251] Step 605, determine the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th second associated vehicle and the first predicted driving trajectory.

[0252] Among them, j is an integer greater than or equal to 1 and less than or equal to N.

[0253] Step 606: Determine the gap distance corresponding to the j-th vehicle gap and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory according to the current second driving data and the first predicted driving trajectory of the j-th and (j - 1)-th second associated vehicles.

[0254] Where when j is 1, the (j - 1)-th second associated vehicle is the first intersection point.

[0255] For the specific implementation process and principle of the above steps 601 - 606, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0256] Step 607: Substitute the distance between the j-th second associated vehicle and the first intersection point and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory into the first collision cost value model to determine the fourth cost value corresponding to the j-th vehicle gap.

[0257] As an example, the fourth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory can be expressed by the following formula:

[0258] cost21 = E(s, v)

[0259] Where cost21 is the fourth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, E represents the first collision cost value model, s is the distance between the j-th second associated vehicle and the first intersection point, and v is the driving speed of the j-th second associated vehicle along the first predicted driving trajectory.

[0260] Step 608: Substitute the gap distance corresponding to the j-th vehicle gap and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory into the second collision cost value model to determine the fifth cost value corresponding to the j-th vehicle gap.

[0261] As an example, the fifth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory can be expressed by the following formula:

[0262] cost22 = F(Δs, Δv)

[0263] Where cost22 is the fifth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, F represents the second collision cost value model, Δs is the gap distance corresponding to the j-th vehicle gap, and Δv is the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory.

[0264] Step 609: Substitute the distance between the j-th second associated vehicle and the first intersection, the traveling speed of the j-th second associated vehicle along the first predicted driving trajectory, and j into the third collision cost value model to determine the sixth cost value corresponding to the j-th vehicle gap.

[0265] As an example, the sixth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory can be expressed by the following formula:

[0266] cost23 = K(s, v, i)

[0267] where cost23 is the sixth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, E represents the first collision cost value model, s is the distance between the j-th second associated vehicle and the first intersection, v is the traveling speed of the j-th second associated vehicle along the first predicted driving trajectory, and j is the serial number of the vehicle gap.

[0268] Step 610: Determine the cost value between the j-th vehicle gap and the target vehicle according to the fourth cost value, the fifth cost value, and the sixth cost value.

[0269] As a possible implementation, after determining the fourth cost value, the fifth cost value, and the sixth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, the sum of the fourth cost value, the fifth cost value, and the sixth cost value can be determined as the cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory. That is, the cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory can be determined by the following formula:

[0270] cost2 = cost21 + cost22 + cost23

[0271] where cost2 is the cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, and cost21, cost22, and cost23 are the fourth cost value, the fifth cost value, and the sixth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, respectively.

[0272] As a possible implementation, it is also possible to configure different weights for the fourth cost value, the fifth cost value, and the sixth cost value according to the importance of the fourth cost value, the fifth cost value, and the sixth cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory, and the weighted sum of the fourth cost value, the fifth cost value, and the sixth cost value can be determined as the cost value corresponding to the j-th vehicle gap in the first predicted driving trajectory.

[0273] It should be noted that the weights involved in the above-listed various methods for determining the cost value can all be obtained through training during the process of training the preset cost value model.

[0274] Step 611: Plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0275] For the specific implementation process and principle of the above step 611, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0276] The trajectory planning method provided by the embodiments of the present application determines the predicted driving trajectory corresponding to each associated vehicle according to the current first driving data of the target vehicle, the current second driving data of at least one associated vehicle, and each reference prior trajectory, and determines the cost value between each vehicle gap in each predicted driving trajectory and the target vehicle. Furthermore, according to the cost value between each predicted driving trajectory and the target vehicle, the driving trajectory of the target vehicle is planned. Thus, due to the distance and speed differences of the associated vehicles relative to the intersection point in the predicted driving trajectory, the distance and speed differences of the associated vehicles relative to the vehicle in front in the predicted driving trajectory, and the arrangement order of the associated vehicles in the predicted driving trajectory, which can respectively reflect the safety of the vehicle gap from different aspects and have different data characteristics, different cost value models can be trained for these three types of data respectively to process these three types of data respectively, thereby further improving the accuracy of cost value calculation, further improving the accuracy of vehicle gap safety evaluation, and further improving the accuracy of vehicle trajectory planning and the driving safety of the vehicle.

[0277] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0278] Corresponding to the trajectory planning method described in the above embodiments, Figure 7 The structural schematic diagram of the trajectory planning device provided by the embodiments of the present application is shown. For the convenience of description, only the parts related to the embodiments of the present application are shown.

[0279] Referring to Figure 7 , the device 70 includes:

[0280] A first acquisition module 71, configured to acquire at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device;

[0281] A second acquisition module 72, configured to acquire the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle;

[0282] A first determination module 73, configured to determine the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory;

[0283] A second determination module 74, configured to determine a cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectories corresponding to each associated vehicle, and the second driving data.

[0284] A first planning module 75, configured to plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

[0285] The trajectory planning device provided by the embodiment of the present application pre-statistics the prior trajectory data of vehicles passing through the current road range by the roadside device and sends it to the target vehicle, and predicts the long-term driving trajectories of surrounding vehicles by matching the surrounding vehicles with the prior trajectory data. Furthermore, according to the cost value between the driving trajectories of the surrounding vehicles and the target vehicle, the safety of the target vehicle passing through each area within the current road range is evaluated to perform the trajectory planning of the target vehicle. Thus, by the roadside device for pre-statistics of the prior trajectory data and combining the vehicle-side and roadside information, not only the computational complexity of the vehicle-side trajectory planning is reduced, the calculation time consumption and resource occupation are reduced, but also the accuracy of the trajectory planning is improved.

[0286] In a possible implementation form of the present application, the above-mentioned first acquisition module 71 includes:

[0287] A first acquisition unit, configured to acquire at least one initial prior trajectory within the current road range sent by the roadside device;

[0288] A second acquisition unit, configured to acquire the reference driving trajectory of the target vehicle within the current road range;

[0289] A first determination unit, configured to screen the initial prior trajectory according to the reference driving trajectory to determine the reference prior trajectory.

[0290] Further, in another possible implementation form of the present application, the above-mentioned first determination module 73 includes:

[0291] A second determination unit, configured to determine the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory;

[0292] A third determination unit, configured to determine the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

[0293] Further, in another possible implementation form of the present application, the above-mentioned third determination unit is specifically configured to:

[0294] Determine the matching degrees between the first associated vehicle and each reference prior trajectory respectively according to the cost values between the first associated vehicle and each reference prior trajectory, where the first associated vehicle is any one of the associated vehicles;

[0295] Determine the predicted driving trajectory corresponding to the first associated vehicle according to the matching degrees between the first associated vehicle and each reference prior trajectory respectively.

[0296] Further, in another possible implementation form of the present application, the above-mentioned second determination unit is specifically used for:

[0297] Taking the first reference prior trajectory as a reference line, establish a reference coordinate system corresponding to the first reference prior trajectory, where the first reference prior trajectory is any one of the reference prior trajectories;

[0298] Determine the deviation driving data between the first associated vehicle and the first reference prior trajectory according to the current second driving data of the first associated vehicle and the reference coordinate system, where the first associated vehicle is any one of the associated vehicles;

[0299] Input the deviation driving data into the first-generation cost value model to determine the cost value between the first associated vehicle and the first reference prior trajectory.

[0300] Further, in another possible implementation form of the present application, the above-mentioned reference coordinate system includes a first coordinate direction and a second coordinate direction, the first coordinate direction is parallel to the first reference prior trajectory, the second coordinate direction is perpendicular to the first reference prior trajectory, the above-mentioned second driving data includes at least one of real-time position, real-time speed and real-time heading angle, and the above-mentioned deviation driving data includes at least one of the following data: the first deviation distance along the first coordinate direction, the second deviation distance along the second coordinate direction, the first speed along the first coordinate direction, the second speed along the second coordinate direction, and the first heading angle relative to the first coordinate direction.

[0301] Further, in another possible implementation form of the present application, the above-mentioned first-generation cost value model includes a position deviation cost value model, a first speed deviation cost value model and a second speed deviation cost value model; correspondingly, the above-mentioned second determination unit is further used for:

[0302] Substitute the first deviation distance, the second deviation distance and the first heading angle into the position deviation cost value model to determine the first-generation cost value between the first associated vehicle and the first reference prior trajectory;

[0303] Substitute the first deviation distance and the first speed into the first speed deviation cost value model to determine the second-generation cost value between the first associated vehicle and the first reference prior trajectory;

[0304] Substitute the second deviation distance and the second speed into the second speed deviation cost value model to determine the third-generation cost value between the first associated vehicle and the first reference prior trajectory;

[0305] Determine the cost value between the first associated vehicle and the first reference prior trajectory according to the first-generation cost value, the second-generation cost value, and the third-generation cost value.

[0306] Further, in another possible implementation form of the present application, the current first driving data of the target vehicle includes a reference driving trajectory of the target vehicle within the current road range, and there is a first intersection point between the reference driving trajectory and the first predicted driving trajectory, where the first predicted driving trajectory is any predicted driving trajectory;

[0307] Correspondingly, the cost value between the first predicted driving trajectory and the target vehicle includes the cost values between each vehicle gap in the first predicted driving trajectory and the target vehicle, where the number of second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1;

[0308] Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection point, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, and the distance between the i-th second associated vehicle and the first intersection point is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection point, where i is greater than 1 and less than or equal to N.

[0309] Further, in another possible implementation form of the present application, the above-mentioned second determination module 74 includes:

[0310] A fourth determination unit, configured to determine the first intersection point according to the first driving data and the first predicted driving trajectory;

[0311] A fifth determination unit, configured to determine the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th second associated vehicle and the first predicted driving trajectory, where j is an integer greater than or equal to 1 and less than or equal to N;

[0312] A sixth determination unit, configured to determine the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th and (j - 1)-th second associated vehicles and the first predicted driving trajectory, where when j is 1, the (j - 1)-th second associated vehicle is the first intersection point;

[0313] A seventh determination unit, configured to substitute the distance between the j-th second associated vehicle and the first intersection, the traveling speed of the j-th second associated vehicle along the first predicted traveling trajectory, the clearance distance corresponding to the j-th vehicle clearance, the speed difference between the j-th second associated vehicle and the (j-1)-th second associated vehicle along the first predicted traveling trajectory, and j into a second-generation value model to determine the value between the j-th vehicle clearance and the target vehicle.

[0314] Further, in another possible implementation form of the present application, the above-mentioned second-generation value model includes a first collision value model, a second collision value model, and a third collision value model; correspondingly, the above-mentioned seventh determination unit is specifically configured to:

[0315] Substitute the distance between the j-th second associated vehicle and the first intersection, and the traveling speed of the j-th second associated vehicle along the first predicted traveling trajectory into the first collision value model to determine the fourth value corresponding to the j-th vehicle clearance;

[0316] Substitute the clearance distance corresponding to the j-th vehicle clearance, and the speed difference between the j-th second associated vehicle and the (j-1)-th second associated vehicle along the first predicted traveling trajectory into the second collision value model to determine the fifth value corresponding to the j-th vehicle clearance;

[0317] Substitute the distance between the j-th second associated vehicle and the first intersection, the traveling speed of the j-th second associated vehicle along the first predicted traveling trajectory, and j into the third collision value model to determine the sixth value corresponding to the j-th vehicle clearance;

[0318] Determine the value between the j-th vehicle clearance and the target vehicle according to the fourth value, the fifth value, and the sixth value.

[0319] Further, in another possible implementation form of the present application, the above-mentioned first planning module 75 includes:

[0320] An eighth determination unit, configured to determine a target vehicle clearance that meets the passing condition according to the values between each vehicle clearance and the target vehicle;

[0321] A ninth determination unit, configured to plan the traveling trajectory and traveling speed of the target vehicle according to the target vehicle clearance.

[0322] It should be noted that for the information interaction, execution process, etc. between the above-mentioned device / units, since it is based on the same concept as the method embodiment of the present application, the specific functions and the technical effects brought thereby can be specifically referred to in the method embodiment part, and will not be elaborated here.

[0323] Those skilled in the art can clearly understand that, for the convenience and conciseness of description, only the above division of each functional unit and module is used as an example. In practical applications, the above functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0324] To implement the above embodiment, this application also proposes a terminal device.

[0325] Figure 8 It is a schematic structural diagram of a terminal device according to an embodiment of this application.

[0326] As Figure 8 shown, the above terminal device 200 includes:

[0327] A memory 210 and at least one processor 220, a bus 230 connecting different components (including the memory 210 and the processor 220), and the memory 210 stores a computer program. When the processor 220 executes the program, it implements the trajectory planning method described in the embodiment of this application.

[0328] The bus 230 represents one or more of several types of bus structures, including a memory bus or a memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any bus structure in a variety of bus structures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0329] The terminal device 200 typically includes a variety of electronically readable media. These media can be any available media that can be accessed by the terminal device 200, including volatile and non-volatile media, removable and non-removable media.

[0330] The memory 210 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 240 and / or cache memory 250. The terminal device 200 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 260 may be used for reading and writing on a non-removable, non-volatile magnetic medium ( Figure 8 not shown, commonly referred to as a "hard disk drive"). Although Figure 8 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk") and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 230 through one or more data media interfaces. The memory 210 may include at least one program product having a set (such as at least one) of program modules configured to perform the functions of the embodiments of the present application.

[0331] A program / utilities 280 having a set (at least one) of program modules 270 may be stored, for example, in the memory 210. Such program modules 270 include - but are not limited to - an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples. The program modules 270 generally perform the functions and / or methods in the embodiments described in the present application.

[0332] The terminal device 200 may also communicate with one or more external devices 290 (such as a keyboard, a pointing device, a display 291, etc.), and may also communicate with one or more devices that enable a user to interact with the terminal device 200, and / or communicate with any device that enables the terminal device 200 to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication may be carried out through an input / output (I / O) interface 292. Also, the terminal device 200 may communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 293. As shown in the figure, the network adapter 293 communicates with other modules of the terminal device 200 through the bus 230. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in combination with the terminal device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0333] The processor 220 executes various functional applications and data processing by running the programs stored in the memory 210.

[0334] It should be noted that for the implementation process and technical principle of the terminal device in this embodiment, please refer to the foregoing explanation of the trajectory planning method in the embodiments of the present application, which will not be elaborated here.

[0335] The embodiments of the present application further provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented.

[0336] The embodiments of the present application provide a computer program product. When the computer program product runs on a terminal device, the terminal device can implement the steps in the foregoing method embodiments when executed.

[0337] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the foregoing method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the foregoing method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the photographing device / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0338] In the foregoing embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not elaborated or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0339] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0340] In the embodiments provided in the present application, it should be understood that the disclosed device / terminal device and method can be implemented in other ways. For example, the device / terminal device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0341] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0342] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A trajectory planning method, characterized in that, Including: Obtain at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device; Obtain the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle; Determine the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory; Determine the cost value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data; Plan the driving trajectory of the target vehicle according to the cost value between each predicted driving trajectory and the target vehicle.

2. The method according to claim 1, characterized in that, The obtaining at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device includes: Obtain at least one initial prior trajectory within the current road range sent by the roadside device; Obtain the reference driving trajectory of the target vehicle within the current road range; Filter the initial prior trajectory according to the reference driving trajectory to determine the reference prior trajectory.

3. The method according to claim 1, characterized in that, The determining the predicted driving trajectory corresponding to each associated vehicle according to each second driving data and each reference prior trajectory includes: Determine the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory; Determine the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory.

4. The method according to claim 3, wherein The determining the predicted driving trajectory corresponding to each associated vehicle according to the cost value between each associated vehicle and each reference prior trajectory includes: Determine the matching degree between the first associated vehicle and each reference prior trajectory according to the cost value between the first associated vehicle and each reference prior trajectory, where the first associated vehicle is any one of the associated vehicles; Determine the predicted driving trajectory corresponding to the first associated vehicle according to the matching degree between the first associated vehicle and each reference prior trajectory.

5. The method according to claim 3, wherein The determining the cost value between each associated vehicle and each reference prior trajectory according to each second driving data and each reference prior trajectory includes: Taking the first reference prior trajectory as a reference line, establish a reference coordinate system corresponding to the first reference prior trajectory, where the first reference prior trajectory is any one of the reference prior trajectories; Determine the deviation driving data between the first associated vehicle and the first reference prior trajectory according to the current second driving data of the first associated vehicle and the reference coordinate system, where the first associated vehicle is any one of the associated vehicles; Input the deviation driving data into the first generation cost model to determine the cost value between the first associated vehicle and the first reference prior trajectory.

6. The method according to claim 5, wherein The reference coordinate system includes a first coordinate direction and a second coordinate direction. The first coordinate direction is parallel to the first reference prior trajectory, and the second coordinate direction is perpendicular to the first reference prior trajectory. The second driving data includes at least one of a real-time position, a real-time speed, and a real-time heading angle. The deviation driving data includes at least one of the following data: a first deviation distance along the first coordinate direction, a second deviation distance along the second coordinate direction, a first speed along the first coordinate direction, a second speed along the second coordinate direction, and a first heading angle relative to the first coordinate direction.

7. The method according to claim 6, wherein The first-generation value model includes a position deviation value model, a first speed deviation value model, and a second speed deviation value model. Inputting the deviation driving data into the first-generation value model to determine the value between the first associated vehicle and the first reference prior trajectory includes: Substituting the first deviation distance, the second deviation distance, and the first heading angle into the position deviation value model to determine the first-generation value between the first associated vehicle and the first reference prior trajectory; Substituting the first deviation distance and the first speed into the first speed deviation value model to determine the second-generation value between the first associated vehicle and the first reference prior trajectory; Substituting the second deviation distance and the second speed into the second speed deviation value model to determine the third-generation value between the first associated vehicle and the first reference prior trajectory; Determining the value between the first associated vehicle and the first reference prior trajectory according to the first-generation value, the second-generation value, and the third-generation value.

8. The method according to any one of claims 1 to 7, characterized in that, The first driving data of the target vehicle currently includes a reference driving trajectory of the target vehicle within the current road range. There is a first intersection point between the reference driving trajectory and a first predicted driving trajectory, where the first predicted driving trajectory is any one of the predicted driving trajectories; The value between the first predicted driving trajectory and the target vehicle includes the values between each vehicle gap in the first predicted driving trajectory and the target vehicle. The number of second associated vehicles corresponding to the first predicted driving trajectory is N, and N is an integer greater than or equal to 1; Among them, the first vehicle gap is the gap between the first second associated vehicle and the first intersection point, the i-th vehicle gap is the gap between the i-th second associated vehicle and the (i - 1)-th second associated vehicle, and the distance between the i-th second associated vehicle and the first intersection point is greater than the distance between the (i - 1)-th second associated vehicle and the first intersection point, where i is greater than 1 and less than or equal to N.

9. The method according to claim 8, wherein Determining the value between each predicted driving trajectory and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data includes: Determining the first intersection point according to the first driving data and the first predicted driving trajectory; Determine the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th second associated vehicle and the first predicted driving trajectory, where j is an integer greater than or equal to 1 and less than or equal to N; Determine the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory according to the current second driving data of the j-th and (j - 1)-th second associated vehicles and the first predicted driving trajectory. When j is 1, the (j - 1)-th second associated vehicle is the first intersection point; Substitute the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second-generation value model to determine the value of the j-th vehicle gap with respect to the target vehicle.

10. The method according to claim 9, wherein The second-generation value model includes a first collision value model, a second collision value model, and a third collision value model. Substituting the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, the gap distance corresponding to the j-th vehicle gap, the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory, and j into the second-generation value model to determine the value of the j-th vehicle gap with respect to the target vehicle includes: Substitute the distance between the j-th second associated vehicle and the first intersection point, and the driving speed of the j-th second associated vehicle along the first predicted driving trajectory into the first collision value model to determine the fourth-generation value corresponding to the j-th vehicle gap; Substitute the gap distance corresponding to the j-th vehicle gap, and the speed difference between the j-th second associated vehicle and the (j - 1)-th second associated vehicle along the first predicted driving trajectory into the second collision value model to determine the fifth-generation value corresponding to the j-th vehicle gap; Substitute the distance between the j-th second associated vehicle and the first intersection point, the driving speed of the j-th second associated vehicle along the first predicted driving trajectory, and j into the third collision value model to determine the sixth-generation value corresponding to the j-th vehicle gap; Determine the value of the j-th vehicle gap with respect to the target vehicle according to the fourth-generation value, the fifth-generation value, and the sixth-generation value.

11. The method according to claim 8, characterized in that, The planning of the driving trajectory of the target vehicle according to the value of each predicted driving trajectory with respect to the target vehicle includes: Determine a target vehicle gap that meets the passing condition according to the cost value between each of the vehicle gaps and the target vehicle; Plan the driving trajectory and driving speed of the target vehicle according to the target vehicle gap.

12. A trajectory planning device, characterized in that, It includes: A first acquisition module, configured to acquire at least one reference prior trajectory within the current road range corresponding to the target vehicle sent by the roadside device; A second acquisition module, configured to acquire the current first driving data of the target vehicle and the current second driving data of at least one associated vehicle corresponding to the target vehicle; A first determination module, configured to determine the predicted driving trajectory corresponding to each associated vehicle according to each of the second driving data and each of the reference prior trajectories; A second determination module, configured to determine the cost value between each of the predicted driving trajectories and the target vehicle according to the first driving data, the predicted driving trajectory corresponding to each associated vehicle, and the second driving data; A first planning module, configured to plan the driving trajectory of the target vehicle according to the cost value between each of the predicted driving trajectories and the target vehicle.

13. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method described in any one of claims 1-11 is implemented.

14. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, the method described in any one of claims 1-11 is implemented.

Images