Track planning method and device and terminal equipment

Abstract

The present application is applicable to the technical field of automatic driving, and provides a trajectory planning method and device, and a terminal device, the method comprising: acquiring a reference trajectory corresponding to a target vehicle and at least one associated trajectory, the associated trajectory being a historical trajectory of at least one associated vehicle corresponding to the target vehicle within a reference time period; determining a cost value between each associated trajectory and the reference trajectory; and planning the driving track of the target vehicle according to the cost value between each associated track and the reference track. Therefore, according to the cost value between the historical tracks of other associated vehicles in the road and the reference track corresponding to the target vehicle, the driving behaviors and driving intentions of the associated vehicles are determined to assist in detecting undetectable or shielded obstacles in the road, an obstacle avoidance track is planned in advance, and the obstacle avoidance efficiency is improved. Therefore, the safety and comfort of automatic driving are improved.

Description

Technical Field

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

[0002] When an autonomous vehicle is driving on an actual road, when there are blind spots in the sensors, or there are obstacles that cannot be detected or are blocked by other vehicles on the road (such as, potholes on the ground, spilled objects, cones blocked by the vehicle in front, etc.), the autonomous vehicle may not be able to give feedback on the obstacle in advance and cannot plan the driving trajectory in advance to avoid obstacles. In this case, it is easy to cause sudden braking, sharp turning, emergency takeover, and even collisions with obstacles and other behaviors that affect autonomous driving, thereby reducing the safety and comfort of autonomous driving. Summary of the Invention

[0003] Embodiments of this application provide a trajectory planning method, apparatus, terminal device, and storage medium, which can solve the problem that when facing obstacles that cannot be detected or are blocked, the autonomous vehicle cannot plan the driving trajectory in advance to avoid obstacles, thereby reducing the safety and comfort of autonomous driving.

[0004] In a first aspect, embodiments of this application provide a trajectory planning method, including: obtaining a reference trajectory corresponding to a target vehicle and at least one associated trajectory, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within a reference period; determining the cost value between each associated trajectory and the reference trajectory; and planning the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory.

[0005] In a possible implementation manner of the first aspect, the determining the cost value between each associated trajectory and the reference trajectory includes:

[0006] determining deviation data between a first associated trajectory and the reference trajectory, where the first associated trajectory is any one of the associated trajectories;

[0007] determining the cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model.

[0008] Optionally, in another possible implementation manner of the first aspect, the determining the deviation data between the first associated trajectory and the reference trajectory includes:

[0009] establishing a first coordinate system according to the reference trajectory;

[0010] determining the deviation data between the first associated trajectory and the reference trajectory in the first coordinate system.

[0011] Optionally, in another possible implementation manner of the first aspect, each of the above-mentioned associated trajectories includes a plurality of trajectory points, and the deviation data includes at least one of deviation distance data, curvature difference data, and heading angle difference data; wherein, the deviation distance data includes the deviation distances between the respective first trajectory points included in the first associated trajectory and the reference trajectory, the curvature difference data includes the curvature differences between the first associated trajectory and the reference trajectory at the respective first trajectory points, the heading angle difference data includes the heading angle differences between the first associated trajectory and the reference trajectory at the respective first trajectory points, and the first trajectory points are the trajectory points included in the first associated trajectory.

[0012] Optionally, in another possible implementation manner of the first aspect, determining the cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model includes:

[0013] Determine the first-order derivative and second-order derivative corresponding to the deviation distance data, and the first-order derivative corresponding to the curvature difference data;

[0014] Input the deviation distance data, the first-order derivative and second-order derivative corresponding to the deviation distance data, the curvature difference data, the first-order derivative corresponding to the curvature difference data, and the heading angle difference data into the preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

[0015] Optionally, in another possible implementation manner of the first aspect, the preset cost value model includes a deviation distance cost value model, a curvature difference cost value model, and a heading angle cost value model; correspondingly, inputting the deviation distance data, the first-order derivative and second-order derivative corresponding to the deviation distance data, the curvature difference data, the first-order derivative corresponding to the curvature difference data, and the heading angle difference data into the preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory includes:

[0016] Input the deviation distance data, the first-order derivative and second-order derivative corresponding to the deviation distance data into the deviation distance cost value model to determine the first cost value between the first associated trajectory and the reference trajectory;

[0017] Input the curvature difference data and the first-order derivative corresponding to the curvature difference data into the curvature difference cost value model to determine the second cost value between the first associated trajectory and the reference trajectory;

[0018] Input the heading angle difference data into the heading angle cost value model to determine the third cost value between the first associated trajectory and the reference trajectory;

[0019] Determine the cost value between the first associated trajectory and the reference trajectory according to the first cost value, the second cost value, and the third cost value.

[0020] Optionally, in another possible implementation of the first aspect, the above-mentioned planning of the driving trajectory of the target vehicle according to the cost values between each associated trajectory and the reference trajectory includes:

[0021] Determine the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost values between each associated trajectory and the reference trajectory;

[0022] Plan the driving trajectory of the target vehicle according to the abnormal area recognition result.

[0023] Optionally, in yet another possible implementation of the first aspect, the above-mentioned determination of the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost values between each associated trajectory and the reference trajectory includes:

[0024] Judge whether there is an abnormal associated trajectory that meets the abnormal conditions according to the cost values between each associated trajectory and the reference trajectory and the abnormal conditions;

[0025] When there is an abnormal associated trajectory, determine that the abnormal area recognition result is that there is an abnormal area on the current road, and determine the abnormal area corresponding to the current road according to the abnormal associated trajectory;

[0026] When there is no abnormal associated trajectory, determine that the abnormal area recognition result is that there is no abnormal area on the current road.

[0027] Optionally, in yet another possible implementation of the first aspect, the above-mentioned planning of the driving trajectory of the target vehicle according to the abnormal area recognition result includes:

[0028] When the abnormal area recognition result is that there is no abnormal area on the current road, determine the driving trajectory of the target vehicle according to the reference trajectory;

[0029] When the abnormal area recognition result is that there is an abnormal area on the current road, determine the driving trajectory of the target vehicle according to the abnormal area.

[0030] Optionally, in yet another possible implementation of the first aspect, after the above-mentioned determination of the driving trajectory of the target vehicle according to the abnormal area, it further includes:

[0031] Correct the driving trajectory of the target vehicle according to the reference trajectory and the abnormal associated trajectory.

[0032] Second aspect, an embodiment of the present application provides a trajectory planning device, including: a first acquisition module, configured to acquire a reference trajectory corresponding to a target vehicle and at least one associated trajectory, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within a reference period; a first determination module, configured to determine the cost value between each associated trajectory and the reference trajectory; a first planning module, configured to plan the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory.

[0033] In a possible implementation manner of the second aspect, the above-mentioned first determination module includes:

[0034] A first determination unit, configured to determine the deviation data between a first associated trajectory and the reference trajectory, where the first associated trajectory is any one of the associated trajectories;

[0035] A second determination unit, configured to determine the cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model.

[0036] Optionally, in another possible implementation manner of the second aspect, the above-mentioned first determination unit is specifically configured to:

[0037] Establish a first coordinate system according to the reference trajectory;

[0038] In the first coordinate system, determine the deviation data between the first associated trajectory and the reference trajectory.

[0039] Optionally, in still another possible implementation manner of the second aspect, each of the above-mentioned associated trajectories includes a plurality of trajectory points, and the deviation data includes at least one of deviation distance data, curvature difference data, and heading angle difference data; wherein, the deviation distance data includes the deviation distances between each first trajectory point included in the first associated trajectory and the reference trajectory, the curvature difference data includes the curvature differences between the first associated trajectory and the reference trajectory at each first trajectory point, the heading angle difference data includes the heading angle differences between the first associated trajectory and the reference trajectory at each first trajectory point, and the first trajectory point is a trajectory point included in the first associated trajectory.

[0040] Optionally, in yet another possible implementation manner of the second aspect, the above-mentioned second determination unit is specifically configured to:

[0041] Determine the first derivative and the second derivative of the deviation distance data, and the first derivative of the curvature difference data;

[0042] Input the deviation distance data, the first derivative and the second derivative of the deviation distance data, the curvature difference data, the first derivative of the curvature difference data, and the heading angle difference data into a preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

[0043] Optionally, in another possible implementation manner of the second aspect, the above-mentioned preset cost value model includes a deviation distance cost value model, a curvature difference cost value model, and a heading angle cost value model; correspondingly, the above-mentioned second determination unit is further configured to:

[0044] Input the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data into the deviation distance cost value model to determine the first cost value between the first associated trajectory and the reference trajectory;

[0045] Input the curvature difference data and the first derivative corresponding to the curvature difference data into the curvature difference cost value model to determine the second cost value between the first associated trajectory and the reference trajectory;

[0046] Input the heading angle difference data into the heading angle cost value model to determine the third cost value between the first associated trajectory and the reference trajectory;

[0047] Determine the cost value between the first associated trajectory and the reference trajectory according to the first cost value, the second cost value, and the third cost value.

[0048] Optionally, in another possible implementation manner of the second aspect, the above-mentioned first planning module includes:

[0049] A third determination unit, configured to determine the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost value between each associated trajectory and the reference trajectory;

[0050] A first planning unit, configured to plan the driving trajectory of the target vehicle according to the abnormal area recognition result.

[0051] Optionally, in another possible implementation manner of the second aspect, the above-mentioned third determination unit is specifically configured to:

[0052] Judge whether there is an abnormal associated trajectory that meets the abnormal condition according to the cost value between each associated trajectory and the reference trajectory and the abnormal condition;

[0053] When there is an abnormal associated trajectory, determine that the abnormal area recognition result is that there is an abnormal area on the current road, and determine the abnormal area corresponding to the current road according to the abnormal associated trajectory;

[0054] When there is no abnormal associated trajectory, determine that the abnormal area recognition result is that there is no abnormal area on the current road.

[0055] Optionally, in another possible implementation manner of the second aspect, the above-mentioned first planning unit is specifically configured to:

[0056] When the abnormal area recognition result is that there is no abnormal area on the current road, determine the driving trajectory of the target vehicle according to the reference trajectory;

[0057] When the recognition result of the abnormal area indicates that there is an abnormal area on the current road, determine the driving trajectory of the target vehicle according to the abnormal area.

[0058] Optionally, in another possible implementation manner of the second aspect, the above first planning unit is further configured to:

[0059] Correct the driving trajectory of the target vehicle according to the reference trajectory and the abnormal associated trajectory.

[0060] 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 described above is implemented.

[0061] 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 described above is implemented.

[0062] 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 described above.

[0063] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: By determining the driving behavior and driving intention of associated vehicles based on the cost value between the historical trajectories of other associated vehicles in the road and the reference trajectory corresponding to the target vehicle, it is possible to assist in detecting obstacles that cannot be detected or are blocked in the road, and plan an obstacle avoidance trajectory in advance, thereby improving the safety and comfort of autonomous driving. Description of the Drawings

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0065] Figure 1 It is a flowchart of the trajectory planning method provided by an embodiment of the present application;

[0066] Figure 2 It is a schematic diagram of the Frenet coordinate system provided by an embodiment of the present application;

[0067] Figure 3 It is a flowchart of the trajectory planning method provided by another embodiment of the present application;

[0068] Figure 4 is a schematic structural diagram of a trajectory planning device provided by an embodiment of the present application;

[0069] Figure 5 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0070] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are proposed to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly 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 interfering with the description of the present application.

[0071] It should be understood that when used in the specification and appended claims of the present application, 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.

[0072] It should also be understood that the term "and / or" as used in the specification and appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0073] As used in the specification and appended claims of the present application, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "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]" according to the context.

[0074] In addition, in the description of the specification and appended claims of the present application, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0075] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that specific features, structures, or characteristics described in connection with that embodiment are included in one or more embodiments of this 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. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0076] The trajectory planning method, device, terminal device, storage medium, and computer program provided by this application will be described in detail below with reference to the accompanying drawings.

[0077] Figure 1 The flowchart of a trajectory planning method provided by an embodiment of this application is shown.

[0078] As Figure 1 shown, the trajectory planning method includes the following steps:

[0079] Step 101, obtain a reference trajectory corresponding to a target vehicle and at least one associated trajectory, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within a reference period.

[0080] It should be noted that the trajectory planning method of the embodiment of this application can be executed by the trajectory planning device of the embodiment of this application. The trajectory planning device of the embodiment of this application can be configured in any terminal device to execute the trajectory planning method of the embodiment of this application. For example, the trajectory planning device of the embodiment of this application can be configured in the on-board unit (OBU) of a vehicle to perform trajectory planning according to the current road conditions.

[0081] 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 this application for trajectory planning.

[0082] Among them, the reference trajectory corresponding to the target vehicle can be determined according to the pre-planned driving path of the target vehicle. It should be noted that the reference trajectory can be the driving trajectory of the target vehicle in a future period pre-planned; it can also include both a part of the historical trajectory of the target vehicle and the driving trajectory of the target vehicle in a future period pre-planned.

[0083] For example, assume that according to the pre-planned driving path of the target vehicle, the target vehicle is currently in a straight-ahead state. Then, the center line of the lane where the target vehicle is currently located can be determined as the reference trajectory corresponding to the target vehicle.

[0084] Among them, the associated vehicle can refer to a vehicle in front of the target vehicle sensed by a sensor in the target vehicle. For example, the associated vehicle can be the vehicle in front in the lane where the target vehicle is currently located, or the vehicle in front in the adjacent lane of the target vehicle, and so on.

[0085] As a possible implementation, vehicles related to the pre-planned driving path can be selected from all the sensed vehicles according to the pre-planned driving path of the target vehicle and determined as associated vehicles.

[0086] For example, if according to the pre-planned driving path of the target vehicle, the target vehicle is currently in a straight-ahead state, then the vehicle in front in the same lane as the target vehicle sensed by the target vehicle can be determined as the associated vehicle; or, if according to the pre-planned driving path of the target vehicle, the target vehicle is currently in a left lane-changing state, then the vehicle in the adjacent lane on the left side of the target vehicle sensed by the target vehicle can be determined as the associated vehicle.

[0087] It should be noted that the above examples are only exemplary and should not be regarded as a limitation of this application. The determination method of the associated vehicle can include but is not limited to the above-listed situations. In actual use, the associated vehicle corresponding to the target vehicle can be determined according to actual needs and the actual driving requirements of the target vehicle.

[0088] Among them, the reference period can refer to any period before the current moment. For example, the reference period can be 30 seconds, 1 minute, etc. before the current moment.

[0089] Among them, the historical trajectory of the associated vehicle within the reference period can refer to the driving trajectory of the associated vehicle collected by the target vehicle through the sensor within the reference period.

[0090] In the embodiments of this application, when a vehicle is driving on an actual road, when there are blind spots in the sensor or there are obstacles that cannot be detected or are blocked by other vehicles on the road (such as potholes on the ground, spilled objects, cones blocked by the vehicle in front, etc.), the autonomous vehicle may not be able to give feedback on the obstacle in advance and cannot plan the driving trajectory in advance to avoid the obstacle, thus reducing the safety and comfort of autonomous driving. Therefore, in this case, the road conditions ahead can be predicted according to the historical trajectories of the surrounding associated vehicles sensed by the target vehicle, so as to improve the rationality and reliability of vehicle trajectory planning and ensure driving comfort and safety.

[0091] As a possible implementation, the target vehicle can collect the driving data of surrounding vehicles through sensors at a certain frequency, determine associated vehicles according to a pre-planned driving path, and obtain the historical trajectories of the associated vehicles during a reference period, so as to perform path planning at the current moment based on this data.

[0092] Step 102: Determine the cost value between each associated trajectory and the reference trajectory.

[0093] Among them, the cost value between the associated trajectory and the reference trajectory can be used to measure the similarity between the associated trajectory and the reference trajectory. The smaller the cost value between the associated trajectory and the reference trajectory, the higher the similarity between the associated trajectory and the reference trajectory; the larger the cost value between the associated trajectory and the reference trajectory, the lower the similarity between the associated trajectory and the reference trajectory.

[0094] In the embodiments of the present application, since the reference trajectory can include the path that the target vehicle is about to drive in front, and the associated vehicle is in front of the target vehicle, the associated trajectory corresponding to the associated vehicle can reflect the actual driving situation of the associated vehicle on a section of the road in front of the target vehicle. It can be understood that if the similarity between the associated trajectory and the reference trajectory is high, it means that the associated vehicle is driving normally in front of the target vehicle, and there may be no obstacles ahead; if the similarity between the associated trajectory and the reference trajectory is low, it means that there is a large difference between the associated trajectory and the reference trajectory, which indicates that the associated vehicle may have encountered an obstacle on the road in front of the target vehicle and has taken detours and other operations. Therefore, the embodiments of the present application can use the cost values between each associated trajectory and the reference trajectory as a standard for measuring the similarity between the associated trajectory and the reference trajectory, and judge whether there is an abnormal situation on the front road according to the cost values between each associated trajectory and the reference trajectory, so as to perform vehicle trajectory planning in advance.

[0095] Furthermore, since the deviation data between the associated trajectory and the reference trajectory can be used to measure the similarity between the associated trajectory and the reference trajectory, the deviation data between the associated trajectory and the reference trajectory can be processed by a pre-trained cost value model to determine the cost value between the associated trajectory and the reference trajectory. That is, in a possible implementation of the embodiments of the present application, the above step 102 may include:

[0096] Determine the deviation data between the first associated trajectory and the reference trajectory, where the first associated trajectory is any associated trajectory;

[0097] According to the deviation data and the preset cost value model, determine the cost value between the first associated trajectory and the reference trajectory.

[0098] Each associated trajectory may include multiple trajectory points.

[0099] Among them, the deviation data may include at least one of deviation distance data, curvature difference data, and heading angle difference data;

[0100] Among them, the deviation distance data may include the deviation distances between each first trajectory point included in the first associated trajectory and the reference trajectory; the curvature difference data may include the curvature differences between the first associated trajectory and the reference trajectory at each first trajectory point; the heading angle difference data may include the heading angle differences between the first associated trajectory and the reference trajectory at each first trajectory point, and the first trajectory point is a trajectory point included in the first associated trajectory.

[0101] As a possible implementation, the first associated trajectory and the reference trajectory can be converted into the same coordinate system to determine the deviation data between the first associated trajectory and the reference trajectory. That is, in a possible implementation of the embodiments of the present application, the above determination of the deviation data between the first associated trajectory and the reference trajectory may include:

[0102] Establish a first coordinate system according to the reference trajectory;

[0103] In the first coordinate system, determine the deviation data between the first associated trajectory and the reference trajectory.

[0104] Among them, the first coordinate system may refer to a Frenet coordinate system established with the target vehicle as the origin, the reference trajectory as the reference line, and the tangent vector and normal vector of the reference trajectory as the two coordinate directions respectively.

[0105] As Figure 2 shown, this Frenet coordinate system takes the target vehicle itself as the origin, the coordinate axes are perpendicular to each other, and are divided into the s direction (i.e., the direction along the reference trajectory, usually referred to as the longitudinal direction) and the d direction (i.e., the normal direction of the reference trajectory at present, usually referred to as the transverse direction). 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 can easily find the reference line of the road (i.e., the center line of the road), then the position representation based on the reference line can be simply described using the longitudinal distance (i.e., the distance along the road direction) and the transverse distance (i.e., the distance deviating from the reference line).

[0106] As a possible implementation, after establishing the first coordinate system (i.e., the Frenet coordinate system) described above with the reference trajectory as the reference line, each first trajectory point in the first associated trajectory can be represented in the first coordinate system, and the deviation data between the first associated trajectory and the reference trajectory can be determined according to the coordinate representations of each first trajectory point in the first coordinate system.

[0107] As an example, for a first trajectory point in the first associated trajectory, the coordinate of the first trajectory point in the d direction can be determined as the deviation distance between the first trajectory point and the reference trajectory; and the curvature of the first trajectory point in the first coordinate system can be determined as the curvature difference between the first associated trajectory and the reference trajectory at the first trajectory point; and the angle between the first trajectory point and the s direction in the first coordinate system can be determined as the heading angle difference between the first associated trajectory and the reference trajectory at the first trajectory point. By analogy, the deviation data between the first associated trajectory and the reference trajectory at each first trajectory point can be determined in turn.

[0108] As a possible implementation, a cost value model for determining the cost value between two trajectories based on the deviation data between the two trajectories can be pre-trained. Therefore, after determining the deviation data between the first associated trajectory and the reference trajectory, each deviation data (such as deviation distance data, curvature difference data, and heading angle difference data) can be input into the preset cost value model, and the cost value between the first associated trajectory and the reference trajectory can be determined according to the output of the preset cost value model.

[0109] Step 103, plan the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory respectively.

[0110] In the embodiment of the present application, after determining the cost value between each associated trajectory and the reference trajectory, it can be determined whether there is an associated trajectory with abnormal driving behavior according to the cost value between each associated trajectory and the reference trajectory. If there is no associated trajectory with abnormal driving behavior, it can be determined that the road where the reference trajectory is located is normal, and the target vehicle can continue to drive along the path of the pre-trajectory, such as continuing to drive along the center line of the current lane; if there is an associated trajectory with abnormal driving behavior, it can be determined that there may be an abnormal area on the road where the reference trajectory is located, and the position of the abnormal area can be predicted according to the abnormal associated trajectory, so as to plan the subsequent driving trajectory of the target vehicle according to the position of the abnormal area.

[0111] As a possible implementation, the abnormal area in the road can be identified first according to the cost value between each associated trajectory and the reference trajectory respectively, and then the trajectory of the target vehicle can be planned according to the abnormal area identification result. That is, in a possible implementation of the embodiment of the present application, the above step 103 may include:

[0112] Determine the abnormal area identification result corresponding to the current road where the target vehicle is located according to the cost value between each associated trajectory and the reference trajectory respectively;

[0113] Plan the driving trajectory of the target vehicle according to the abnormal area identification result.

[0114] Among them, the abnormal area recognition result may include that there is an abnormal area on the current road and there is no abnormal area on the current road; when there is an abnormal area on the current road, the abnormal area recognition result may further include the location information of the abnormal area.

[0115] As a possible implementation, the abnormal area recognition result corresponding to the current road can be determined in the following way:

[0116] According to the cost value and abnormal conditions between each associated trajectory and the reference trajectory, determine whether there is an abnormal associated trajectory that meets the abnormal conditions;

[0117] When there is an abnormal associated trajectory, determine that the abnormal area recognition result is that there is an abnormal area on the current road, and determine the abnormal area corresponding to the current road according to the abnormal associated trajectory;

[0118] When there is no abnormal associated trajectory, determine that the abnormal area recognition result is that there is no abnormal area on the current road.

[0119] Among them, the abnormal condition may be that the cost value between the associated trajectory and the reference trajectory is greater than the cost value threshold. In actual use, the specific value of the 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.

[0120] It should be noted that since the cost value between the associated trajectory and the reference trajectory is negatively correlated with the similarity between the associated trajectory and the reference trajectory, the greater the cost value between the associated trajectory and the reference trajectory, the lower the similarity between the associated trajectory and the reference trajectory; and the lower the similarity between the associated trajectory and the reference trajectory, the more likely it indicates that the associated trajectory may have abnormal driving behaviors such as obstacle avoidance that do not follow the reference trajectory. Therefore, the abnormal area on the current road can be recognized according to the relationship between the cost value between the associated trajectory and the reference trajectory and the cost value threshold.

[0121] As a possible implementation, if the cost value between the associated trajectory and the reference trajectory is greater than the cost value threshold, it can be determined that the associated trajectory meets the abnormal conditions, and thus the associated trajectory can be determined as an abnormal associated trajectory; if the cost value between the associated trajectory and the reference trajectory is less than or equal to the cost value threshold, it can be determined that the associated trajectory does not meet the abnormal conditions, and thus there is no need to determine the associated trajectory as an abnormal associated trajectory.

[0122] It can be understood that if there is no abnormal associated trajectory, it can be indicated that each current associated vehicle is traveling along the reference trajectory or a trajectory parallel or similar to the reference trajectory. Thus, there is no abnormal area on the road where the reference trajectory is currently located, that is, it can be determined that the abnormal area recognition result is that there is no abnormal area on the road where the target vehicle is currently located. If there is an abnormal associated trajectory, it can be indicated that there are currently associated vehicles with driving trajectories significantly different from the reference trajectory, and these associated vehicles may be performing abnormal driving behaviors such as obstacle avoidance. Therefore, it can be determined that the abnormal area recognition result is that there is an abnormal area on the current road, and the abnormal area corresponding to the current road can be determined according to the location of the abnormal associated trajectory.

[0123] As a possible implementation, the trajectory planning of the target vehicle can be carried out according to the abnormal area recognition result in the following way:

[0124] When the abnormal area recognition result is that there is no abnormal area on the current road, determine the driving trajectory of the target vehicle according to the reference trajectory;

[0125] When the abnormal area recognition result is that there is an abnormal area on the current road, determine the driving trajectory of the target vehicle according to the abnormal area.

[0126] As a possible implementation, if the abnormal area recognition result is that there is no abnormal area on the current road, it can be determined that there are no obstacles on the current road that are blocked or cannot be detected. Therefore, the vehicle can continue to travel along the pre-planned path; and since the reference trajectory is determined according to the path of the target vehicle's pre-trajectory, the driving trajectory of the target vehicle can be determined according to the reference trajectory. For example, the driving trajectory of the target vehicle can be determined as the reference trajectory or a trajectory parallel to the reference trajectory. If the abnormal area recognition result is that there is an abnormal area on the current road, it can be determined that there may be obstacles on the current road that are blocked or cannot be detected in the corresponding abnormal area. Therefore, the driving trajectory of the target vehicle can be determined according to the location of the abnormal area, so as to plan in advance to make the target vehicle drive around the abnormal area and prevent the vehicle from being emergently intervened, thereby ensuring the driving safety and comfort of the vehicle.

[0127] Further, when there is an abnormal area in the current road, since the determined abnormal area may be a relatively large area, if the trajectory of the target vehicle is directly planned according to the position of the abnormal area, causing the target vehicle to directly bypass the abnormal area, it is likely to result in a large and uneven change in the trajectory of the target vehicle, thereby affecting the driving safety and comfort. Therefore, the driving trajectory of the target vehicle can also be corrected based on the abnormal associated trajectory and the reference trajectory to improve the rationality of trajectory planning and further enhance the driving safety and comfort. That is, in a possible implementation manner of the embodiments of the present application, after determining the driving trajectory of the target vehicle according to the abnormal area, the following may further be included:

[0128] Correct the driving trajectory of the target vehicle according to the reference trajectory and the abnormal associated trajectory.

[0129] As a possible implementation manner, since the reference trajectory can be the route that the target vehicle is currently traveling and is expected to travel, and the abnormal associated trajectory is the driving trajectory generated by the associated vehicle to avoid obstacles ahead, the abnormal associated trajectory can be used as a better trajectory for bypassing the abnormal area for reference, and based on the reference trajectory, the driving trajectory of the target vehicle determined according to the abnormal area is corrected. For example, after determining the driving trajectory of the target vehicle according to the abnormal area, the driving trajectory of the target vehicle can be corrected with the aim of making the driving trajectory of the target vehicle as close as possible to the reference trajectory and referring to the abnormal associated trajectory near the abnormal area; so that the corrected driving trajectory can be as consistent as possible with the reference trajectory outside the abnormal area and similar to the abnormal associated trajectory near the abnormal area, thereby ensuring that the abnormal area can be bypassed and driving safety can be guaranteed, while ensuring that the target vehicle will not have overly abrupt steering or lane changes, making the driving trajectory of the target vehicle smoother and more stable, and further enhancing the driving comfort and safety.

[0130] The trajectory planning method provided by the embodiments of the present application determines the driving behavior and driving intention of the associated vehicle by calculating the cost value between the historical trajectory of other associated vehicles in the road and the reference trajectory corresponding to the target vehicle, so as to assist in detecting obstacles that cannot be detected or are blocked in the road, and plan the obstacle avoidance trajectory in advance, thereby enhancing the safety and comfort of autonomous driving.

[0131] In a possible implementation form of the present application, when calculating the cost value between the associated trajectory and the reference trajectory, in addition to the deviation data between the associated trajectory and the reference trajectory, the first derivative and the second derivative corresponding to the deviation data can also be introduced to introduce richer deviation information, further improving the accuracy of cost value determination, and further enhancing the reliability of vehicle trajectory planning.

[0132] The following combinesFigure 3 This further describes the trajectory planning method provided in the embodiments of the present application.

[0133] Figure 3 Fig. shows a schematic flowchart of another trajectory planning method provided in the embodiments of the present application.

[0134] As Figure 3 shown, the trajectory planning method includes the following steps:

[0135] Step 301: Obtain the reference trajectory corresponding to the target vehicle and at least one associated trajectory, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within the reference period.

[0136] Step 302: Determine the deviation data between the first associated trajectory and the reference trajectory, where the first associated trajectory is any one of the associated trajectories.

[0137] Each associated trajectory may include multiple trajectory points.

[0138] The deviation data may include at least one of deviation distance data, curvature difference data, and heading angle difference data;

[0139] The deviation distance data may include the deviation distances between each first trajectory point included in the first associated trajectory and the reference trajectory; the curvature difference data may include the curvature differences between the first associated trajectory and the reference trajectory at each first trajectory point; the heading angle difference data may include the heading angle differences between the first associated trajectory and the reference trajectory at each first trajectory point, and the first trajectory point is a trajectory point included in the first associated trajectory.

[0140] For the specific implementation process and principle of the above steps 301 - 302, reference may be made to the detailed description of the above embodiments, which will not be elaborated here.

[0141] Step 303: Determine the first derivative and the second derivative of the deviation distance data, and the first derivative of the curvature difference data.

[0142] In the embodiments of the present application, since the deviation data between the associated trajectory and the reference trajectory can directly represent the deviation between the associated trajectory and the reference trajectory, and the derivative of the deviation data can also contain the deviation information between the associated trajectory and the reference trajectory, in order to further improve the accuracy of determining the cost value between the associated trajectory and the reference trajectory, the cost value between the associated trajectory and the reference trajectory can be jointly determined according to the deviation data between the associated trajectory and the reference trajectory, the first derivative and the second derivative of the deviation data.

[0143] As a possible implementation, since the first associated trajectory includes multiple first trajectory points, and different first trajectory points represent the positions of the associated vehicle at different times, the first associated trajectory can be regarded as a function that changes over time; and the deviation data between the first associated trajectory and the reference trajectory, including the deviation data between the first associated trajectory and the reference trajectory at each first trajectory point. Therefore, the deviation data between the first associated trajectory and the reference trajectory can also be regarded as a function that changes over time. Thus, the deviation distance data can be differentiated to determine the first derivative corresponding to the deviation distance data, and then the first derivative corresponding to the deviation distance data can be differentiated to determine the second derivative corresponding to the deviation distance data; and the curvature difference data can be differentiated to determine the first derivative corresponding to the curvature difference data.

[0144] Step 304: Input the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data, the curvature difference data, the first derivative corresponding to the curvature difference data, and the heading angle difference data into a preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

[0145] In the embodiment of the present application, after determining the first derivative and the second derivative corresponding to the deviation distance data between the first associated trajectory and the reference trajectory, and the first derivative corresponding to the curvature difference data, the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data, the curvature difference data, the first derivative corresponding to the curvature difference data, and the heading angle difference data can be jointly input into a preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

[0146] For example, the cost value between the first associated trajectory and the reference trajectory can be represented by the following formula:

[0147]

[0148] where cost is the cost value between the first associated trajectory and the reference trajectory, Q represents the preset cost value model, l is the deviation distance data between the first associated trajectory and the reference trajectory, i is the first derivative corresponding to the deviation distance data, is the second derivative corresponding to the deviation distance data, k is the curvature difference data between the first associated trajectory and the reference trajectory, is the first derivative corresponding to the curvature difference data, and θ is the heading angle difference data between the first associated trajectory and the reference trajectory.

[0149] Further, since the deviation distance data, curvature difference data, and heading angle difference data usually have different data characteristics and can respectively represent the differences between the associated trajectory and the reference trajectory in different aspects, 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 and further improving the accuracy of vehicle trajectory planning. That is, in a possible implementation manner of the embodiment of the present application, the above preset cost value model may include a deviation distance cost value model, a curvature difference cost value model, and a heading angle cost value model; correspondingly, the above step 304 may include:

[0150] Input the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data into the deviation distance cost value model to determine the first cost value between the first associated trajectory and the reference trajectory;

[0151] Input the curvature difference data and the first derivative corresponding to the curvature difference data into the curvature difference cost value model to determine the second cost value between the first associated trajectory and the reference trajectory;

[0152] Input the heading angle difference data into the heading angle cost value model to determine the third cost value between the first associated trajectory and the reference trajectory;

[0153] Determine the cost value between the first associated trajectory and the reference trajectory according to the first cost value, the second cost value, and the third cost value.

[0154] As an example, the first cost value between the first associated trajectory and the reference trajectory can be expressed by the following formula:

[0155]

[0156] Where cost1 is the first cost value between the first associated trajectory and the reference trajectory, I represents the deviation distance cost value model, l is the deviation distance data between the first associated trajectory and the reference trajectory, is the first derivative corresponding to the deviation distance data, is the second derivative corresponding to the deviation distance data.

[0157] And, the second cost value between the first associated trajectory and the reference trajectory can be expressed by the following formula:

[0158]

[0159] Where cost2 is the second cost value between the first associated trajectory and the reference trajectory, J represents the curvature difference cost value model, k is the curvature difference data between the first associated trajectory and the reference trajectory, is the first derivative corresponding to the curvature difference data.

[0160] Moreover, the third-generation value between the first associated trajectory and the reference trajectory can be expressed by the following formula:

[0161] cost3 = H(θ)

[0162] where cost3 is the third-generation value between the first associated trajectory and the reference trajectory, H represents the heading angle cost value model, and θ is the heading angle difference data between the first associated trajectory and the reference trajectory.

[0163] As a possible implementation, after determining the first-generation value, the second-generation value, and the third-generation value between the first associated trajectory and the reference 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 trajectory and the reference trajectory.

[0164] As a possible implementation, different weights can also be assigned to 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 trajectory and the reference 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 trajectory and the reference trajectory.

[0165] As a possible implementation, the cost value between the first associated trajectory and the reference trajectory can also be determined in the following way:

[0166] cost = cost1 + cost2 + cost3 + Φ

[0167] where cost is the cost value between the first associated trajectory and the reference trajectory, cost1, cost2, and cost3 are the first-generation value, the second-generation value, and the third-generation value between the first associated trajectory and the reference trajectory respectively, and Φ is a constant.

[0168] 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.

[0169] Step 305: Plan the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory.

[0170] For the specific implementation process and principle of the above step 305, reference can be made to the detailed description of the above embodiments, which will not be elaborated here.

[0171] The trajectory planning method provided by the embodiment of the present application obtains the reference trajectory corresponding to the target vehicle and at least one associated trajectory, determines the deviation data between each associated trajectory and the reference trajectory, determines the first derivative and the second derivative of the deviation distance data, and the first derivative of the curvature difference data, and then inputs the deviation distance data, the first derivative and the second derivative of the deviation distance data, the curvature difference data, the first derivative of the curvature difference data, and the heading angle difference data into a preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory. Finally, according to the cost value between each associated trajectory and the reference trajectory respectively, the driving trajectory of the target vehicle is planned. Thus, when calculating the cost value between the associated trajectory and the reference trajectory, in addition to the deviation data between the associated trajectory and the reference trajectory, the first derivative and the second derivative of the deviation data can be introduced to introduce richer deviation information, which not only improves the safety and comfort of autonomous driving, but also further improves the accuracy of cost value determination, and further improves the reliability of vehicle trajectory planning.

[0172] 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 order of execution 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.

[0173] Corresponding to the trajectory planning method described in the above embodiments, Figure 4 The structural schematic diagram of the trajectory planning device provided by the embodiment of the present application is shown. For the convenience of description, only the parts related to the embodiment of the present application are shown.

[0174] Referring to Figure 4 , the device 40 includes:

[0175] A first acquisition module 41, configured to acquire the reference trajectory corresponding to the target vehicle and at least one associated trajectory, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within a reference period;

[0176] A first determination module 42, configured to determine the cost value between each associated trajectory and the reference trajectory respectively;

[0177] A first planning module 43, configured to plan the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory respectively.

[0178] The trajectory planning device provided by the embodiment of the present application determines the driving behaviors and driving intentions of associated vehicles by the cost value between the historical trajectories of other associated vehicles in the road and the reference trajectory corresponding to the target vehicle, so as to assist in detecting obstacles that cannot be detected or are blocked in the road, and plan an obstacle avoidance trajectory in advance, thereby improving the safety and comfort of autonomous driving.

[0179] In a possible implementation form of the present application, the above-mentioned first determination module 42 includes:

[0180] A first determination unit, configured to determine deviation data between a first associated trajectory and a reference trajectory, where the first associated trajectory is any associated trajectory;

[0181] A second determination unit, configured to determine a cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model.

[0182] Further, in another possible implementation form of the present application, the above-mentioned first determination unit is specifically configured to:

[0183] Establish a first coordinate system according to the reference trajectory;

[0184] In the first coordinate system, determine the deviation data between the first associated trajectory and the reference trajectory.

[0185] Further, in yet another possible implementation form of the present application, each of the above-mentioned associated trajectories includes a plurality of trajectory points, and the deviation data includes at least one of deviation distance data, curvature difference data, and heading angle difference data; wherein, the deviation distance data includes the deviation distance between each first trajectory point included in the first associated trajectory and the reference trajectory, the curvature difference data includes the curvature difference between the first associated trajectory and the reference trajectory at each first trajectory point, the heading angle difference data includes the heading angle difference between the first associated trajectory and the reference trajectory at each first trajectory point, and the first trajectory point is a trajectory point included in the first associated trajectory.

[0186] Further, in yet another possible implementation form of the present application, the above-mentioned second determination unit is specifically configured to:

[0187] Determine the first derivative and the second derivative corresponding to the deviation distance data, and the first derivative corresponding to the curvature difference data;

[0188] Input the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data, the curvature difference data, the first derivative corresponding to the curvature difference data, and the heading angle difference data into a preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

[0189] Further, in yet another possible implementation form of the present application, the above-mentioned preset cost value model includes a deviation distance cost value model, a curvature difference cost value model, and a heading angle cost value model; correspondingly, the above-mentioned second determination unit is further configured to:

[0190] Input the deviation distance data, the first derivative and the second derivative corresponding to the deviation distance data into the deviation distance cost value model to determine the first generation cost value between the first associated trajectory and the reference trajectory;

[0191] Input the curvature difference data and the first derivative corresponding to the curvature difference data into the curvature difference cost value model to determine the second generation cost value between the first associated trajectory and the reference trajectory;

[0192] Input the heading angle difference data into the heading angle cost value model to determine the third generation cost value between the first associated trajectory and the reference trajectory;

[0193] Determine the cost value between the first associated trajectory and the reference trajectory according to the first generation cost value, the second generation cost value and the third generation cost value.

[0194] Further, in another possible implementation form of the present application, the above-mentioned first planning module 43 includes:

[0195] A third determination unit, configured to determine the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost value between each associated trajectory and the reference trajectory respectively;

[0196] A first planning unit, configured to plan the driving trajectory of the target vehicle according to the abnormal area recognition result.

[0197] Further, in another possible implementation form of the present application, the above-mentioned third determination unit is specifically configured to:

[0198] Judge whether there is an abnormal associated trajectory that meets the abnormal condition according to the cost value between each associated trajectory and the reference trajectory respectively and the abnormal condition;

[0199] When there is an abnormal associated trajectory, determine that the abnormal area recognition result is that there is an abnormal area on the current road, and determine the abnormal area corresponding to the current road according to the abnormal associated trajectory;

[0200] When there is no abnormal associated trajectory, determine that the abnormal area recognition result is that there is no abnormal area on the current road.

[0201] Further, in another possible implementation form of the present application, the above-mentioned first planning unit is specifically configured to:

[0202] When the abnormal area recognition result is that there is no abnormal area on the current road, determine the driving trajectory of the target vehicle according to the reference trajectory;

[0203] When the abnormal area recognition result is that there is an abnormal area on the current road, determine the driving trajectory of the target vehicle according to the abnormal area.

[0204] Further, in another possible implementation form of the present application, the above-mentioned first planning unit is further configured to:

[0205] Correct the driving trajectory of the target vehicle according to the reference trajectory and the abnormal correlation trajectory.

[0206] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units, due to being based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part specifically, and will not be elaborated here.

[0207] Those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, 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-mentioned 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 the present 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.

[0208] To implement the above embodiment, the present application also proposes a terminal device.

[0209] Figure 5 It is a schematic structural diagram of a terminal device according to an embodiment of the present application.

[0210] As Figure 5 shown, the above-mentioned terminal device 200 includes:

[0211] 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, and when the processor 220 executes the program, it implements the trajectory planning method described in the embodiment of the present application.

[0212] Bus 230 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, an Accelerated Graphics Port, a processor bus, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include 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.

[0213] Terminal device 200 typically includes a variety of computer-readable media. These media can be any available media that can be accessed by terminal device 200, including both volatile and nonvolatile media, removable and non-removable media.

[0214] 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. Terminal device 200 may further include other removable / non-removable, volatile / nonvolatile computer system storage media. By way of example only, storage system 260 can be used for reading from and writing to non-removable, nonvolatile magnetic media ( Figure 5 not shown, and typically called a "hard disk drive"). Although Figure 5 not shown in the figures, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from and writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) can be provided. In these instances, each drive can be connected to bus 230 by one or more data media interfaces. Memory 210 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of the embodiments of the present application.

[0215] A program / utility 280 having a set (at least one) of program modules 270 may be stored, for example, in 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, each of which examples or some combination thereof may include an implementation of a network environment. Program modules 270 typically carry out the functions and / or methods of the embodiments described in the present application.

[0216] The terminal device 200 can also communicate with one or more external devices 290 (such as a keyboard, a pointing device, a display 291, etc.), and can 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 can be carried out through an input / output (I / O) interface 292. Moreover, the terminal device 200 can also 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 a bus 230. It should be understood that although not shown in the figure, other hardware and / or software modules can 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.

[0217] The processor 220 executes various functional applications and data processing by running programs stored in the memory 210.

[0218] It should be noted that for the implementation process and technical principle of the terminal device in this embodiment, refer to the foregoing explanation of the trajectory planning method in the embodiments of the present application, and details are not described herein again.

[0219] The embodiments of the present application also provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0220] 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 execute the steps in the above-mentioned various method embodiments.

[0221] When 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 above-described embodiment methods of this 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 of the above-described 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.

[0222] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0223] 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. A professional technician 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 this application.

[0224] In the embodiments provided in this 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 only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can 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 couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0225] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or may be distributed across 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.

[0226] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; 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 described in the foregoing embodiments, or perform equivalent replacements on 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 a reference trajectory and at least one associated trajectory corresponding to a target vehicle, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle within a reference period; Determine the cost value between each of the associated trajectories and the reference trajectory; Plan the driving trajectory of the target vehicle according to the cost values between each of the associated trajectories and the reference trajectory.

2. The method according to claim 1, characterized in that, The determining the cost value between each of the associated trajectories and the reference trajectory includes: Determine the deviation data between a first associated trajectory and the reference trajectory, where the first associated trajectory is any one of the associated trajectories; Determine the cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model.

3. The method according to claim 2, characterized in that, The determining the deviation data between the first associated trajectory and the reference trajectory includes: Establish a first coordinate system according to the reference trajectory; In the first coordinate system, determine the deviation data between the first associated trajectory and the reference trajectory.

4. The method according to claim 2, wherein Each of the associated trajectories includes a plurality of trajectory points, and the deviation data includes at least one of deviation distance data, curvature difference data, and heading angle difference data; where the deviation distance data includes the deviation distances between each first trajectory point included in the first associated trajectory and the reference trajectory, the curvature difference data includes the curvature differences between the first associated trajectory and the reference trajectory at each of the first trajectory points, the heading angle difference data includes the heading angle differences between the first associated trajectory and the reference trajectory at each of the first trajectory points, and the first trajectory point is a trajectory point included in the first associated trajectory.

5. The method according to claim 4, characterized in that The determining the cost value between the first associated trajectory and the reference trajectory according to the deviation data and a preset cost value model includes: Determine the first derivative and the second derivative of the deviation distance data, and the first derivative of the curvature difference data; Input the deviation distance data, the first derivative and the second derivative of the deviation distance data, the curvature difference data, the first derivative of the curvature difference data, and the heading angle difference data into the preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory.

6. The method according to claim 5, characterized in that, The preset cost value model includes a deviation distance cost value model, a curvature difference cost value model, and a heading angle cost value model. The inputting the deviation distance data, the first derivative and the second derivative of the deviation distance data, the curvature difference data, the first derivative of the curvature difference data, and the heading angle difference data into the preset cost value model to determine the cost value between the first associated trajectory and the reference trajectory includes: Input the deviation distance data, the first derivative and the second derivative of the deviation distance data into the deviation distance cost value model to determine the first cost value between the first associated trajectory and the reference trajectory; Input the curvature difference data and the first derivative corresponding to the curvature difference data into the curvature difference cost value model to determine the second cost value between the first associated trajectory and the reference trajectory; Input the heading angle difference data into the heading angle cost value model to determine the third cost value between the first associated trajectory and the reference trajectory; Determine the cost value between the first associated trajectory and the reference trajectory according to the first cost value, the second cost value, and the third cost value.

7. The method according to any one of claims 1-6, characterized in that, The planning of the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory respectively includes: Determine the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost value between each associated trajectory and the reference trajectory respectively; Plan the driving trajectory of the target vehicle according to the abnormal area recognition result.

8. The method according to claim 7, wherein The determining the abnormal area recognition result corresponding to the current road where the target vehicle is located according to the cost value between each associated trajectory and the reference trajectory respectively includes: Judge whether there is an abnormal associated trajectory that meets the abnormal condition according to the cost value between each associated trajectory and the reference trajectory respectively and the abnormal condition; When there is the abnormal associated trajectory, determine that the abnormal area recognition result is that there is an abnormal area on the current road, and determine the abnormal area corresponding to the current road according to the abnormal associated trajectory; When there is no such abnormal associated trajectory, determine that the abnormal area recognition result is that there is no abnormal area on the current road.

9. The method according to claim 8, wherein The planning of the driving trajectory of the target vehicle according to the abnormal area recognition result includes: When the abnormal area recognition result is that there is no abnormal area on the current road, determine the driving trajectory of the target vehicle according to the reference trajectory; When the abnormal area recognition result is that there is an abnormal area on the current road, determine the driving trajectory of the target vehicle according to the abnormal area.

10. The method according to claim 9, characterized in that After determining the driving trajectory of the target vehicle according to the abnormal area, it further includes: Correct the driving trajectory of the target vehicle according to the reference trajectory and the abnormal associated trajectory.

11. A trajectory planning device, characterized in that, It includes: A first acquisition module, configured to acquire a reference trajectory and at least one associated trajectory corresponding to a target vehicle, where the associated trajectory refers to the historical trajectories of at least one associated vehicle corresponding to the target vehicle during a reference period; A first determination module, configured to determine the cost value between each associated trajectory and the reference trajectory respectively; A first planning module, configured to plan the driving trajectory of the target vehicle according to the cost value between each associated trajectory and the reference trajectory respectively.

12. 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 1-10 is implemented.

13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, the method described in any one of claims 1-10 is implemented.

Images