Target vehicle behavior prediction method and device, terminal equipment and storage medium

Abstract

The invention provides a target vehicle behavior prediction method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining current lane type information, and executing at least one of a first lane changing probability determination step, a second lane changing probability determination step, a third lane changing probability determination step and a fourth lane changing probability determination step according to the lane type information, and predicting the behavior of the target vehicle according to at least one determined lane changing probability in the four probabilities. According to the method provided by the invention, the behavior of the target vehicle at the future moment is predicted by determining the lane changing probability of the target vehicle, so that the problem that the behavior of the target vehicle is difficult to predict is solved to a certain extent, the accuracy of predicting the behavior of the target vehicle is improved, traffic accidents caused by lane changing of the target vehicle can be effectively reduced, and the user experience is improved. The driving safety is ensured.

Description

Technical Field

[0001] The present application belongs to the field of intelligent driving technology, and in particular, relates to a target vehicle behavior prediction method, device, terminal equipment and storage medium. Background Art

[0002] With the rapid increase in the number of cars, the driving environment is becoming more and more complex. During driving, not only do we need to avoid obstacles and pedestrians, but we also need to respond promptly and accurately to the lane changes of surrounding vehicles. When driving, people will subconsciously predict the behavior of other vehicles and determine the driving route of their own vehicle based on the lane change intentions of other vehicles. This can avoid possible dangers to a certain extent. However, when the vehicle suddenly changes lanes or a certain vehicle is in the driver's blind spot, the driver cannot predict the behavior of other vehicles. At the same time, even if the vehicle does not suddenly change lanes, or a certain vehicle is in the driver's field of vision, the driver's attention cannot be focused for a long time, and he may be temporarily distracted and unable to quickly predict the behavior of the vehicle. The above situations will lead to traffic accidents, so it is urgent to solve this problem. Summary of the invention

[0003] The embodiments of the present application provide a method and device for predicting the behavior of a target vehicle, which can solve the problem that the behavior of surrounding vehicles is difficult to predict.

[0004] In a first aspect, an embodiment of the present application provides a target vehicle behavior prediction method, comprising:

[0005] Get the current lane type information;

[0006] At least one of the following four steps is selected and performed according to the lane type information:

[0007] A first lane change probability determination step: determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the own vehicle;

[0008] A second lane change probability determination step: determining a second probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located;

[0009] A third lane-changing probability determination step: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the ego vehicle in the historical frame;

[0010] A fourth lane change probability determination step: determining a fourth probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame;

[0011] The target vehicle behavior is predicted according to at least one of the first probability, the second probability, the third probability, and the fourth probability.

[0012] In a possible implementation, if both the first lane change probability determination step and the third lane change probability determination step are performed, the predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability and the fourth probability includes:

[0013] Calculate a first average value according to the first probability and the third probability;

[0014] The target vehicle behavior is predicted according to the first average value.

[0015] In a possible implementation, if the second lane change probability determination step and the fourth lane change probability determination step are both performed, the predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability and the fourth probability includes:

[0016] Calculate a second average value according to the second probability and the fourth probability;

[0017] The target vehicle behavior is predicted according to the second average value.

[0018] In a possible implementation, if the first lane change probability determination step, the second lane change probability determination step, the third lane change probability determination step, and the fourth lane change probability determination step are all executed, then predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability, and the fourth probability includes:

[0019] Calculate a third average value according to the first probability, the second probability, the third probability and the fourth probability;

[0020] The target vehicle behavior is predicted according to the third average value.

[0021] In a possible implementation, determining the third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the vehicle in the historical frame includes:

[0022] A third probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the ego vehicle, and the corresponding accumulated generalized probability distribution.

[0023] In a possible implementation, determining the fourth probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame includes:

[0024] A fourth probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the center line of the lane where the vehicle is located, and the corresponding cumulative generalized probability distribution.

[0025] In a possible implementation, determining the first probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the own vehicle includes:

[0026] According to the positional relationship and lateral distance between the target vehicle and the self-vehicle, the lane change phase of the target vehicle is determined;

[0027] A first probability is determined according to the lane change phase of the target vehicle.

[0028] In a possible implementation, if the target vehicle is located on the left side of the own vehicle, determining the lane change phase of the target vehicle according to the distance between the target vehicle and the own vehicle includes:

[0029] If the lateral distance between the target vehicle and the own vehicle is within the first preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane;

[0030] If the lateral distance between the target vehicle and the own vehicle is within the second preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane;

[0031] If the lateral distance between the target vehicle and the own vehicle is within a third preset range, it is determined that the target vehicle is in a stage of completing a lane change from the left adjacent lane to the own lane;

[0032] If the lateral distance between the target vehicle and the ego vehicle is within a fourth preset range, it is determined that the target vehicle is in an initial stage of changing lanes from the ego lane to the left adjacent lane;

[0033] If the lateral distance between the target vehicle and the ego vehicle is within the fifth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the left adjacent lane;

[0034] If the lateral distance between the target vehicle and the own vehicle is within a sixth preset range, it is determined that the target vehicle is in a completion stage of changing lanes from the own lane to the left adjacent lane.

[0035] In a possible implementation, determining the first probability according to the lane change phase of the target vehicle includes:

[0036] If the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle;

[0037] If the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, a first probability is determined according to the first parameter, the second parameter, the third parameter, and the lateral distance between the target vehicle and the own vehicle;

[0038] If the target vehicle is in the completion phase of changing lanes from the left adjacent lane to the own lane, the first probability is zero;

[0039] If the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle;

[0040] If the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, a first probability is determined according to the fourth parameter, the fifth parameter, the sixth parameter, and the lateral distance between the target vehicle and the own vehicle;

[0041] If the target vehicle is in the completion phase of changing lanes from the vehicle's own lane to the left adjacent lane, the first probability is zero.

[0042] In a possible implementation, if the target vehicle is located on the right side of the own vehicle, determining the lane change phase of the target vehicle according to the distance between the target vehicle and the own vehicle includes:

[0043] If the lateral distance between the target vehicle and the own vehicle is within the first preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane;

[0044] If the lateral distance between the target vehicle and the own vehicle is within the second preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane;

[0045] If the lateral distance between the target vehicle and the own vehicle is within a third preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane;

[0046] If the lateral distance between the target vehicle and the ego vehicle is within a fourth preset range, it is determined that the target vehicle is in an initial stage of changing lanes from the ego lane to the right adjacent lane;

[0047] If the lateral distance between the target vehicle and the ego vehicle is within the fifth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the right adjacent lane;

[0048] If the lateral distance between the target vehicle and the own vehicle is within a sixth preset range, it is determined that the target vehicle is in a completion stage of changing lanes from the own lane to the right adjacent lane.

[0049] In a possible implementation, determining the first probability according to the lane change phase of the target vehicle includes:

[0050] If the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle;

[0051] If the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane, a first probability is determined according to the seventh parameter, the eighth parameter, the ninth parameter, and the lateral distance between the target vehicle and the own vehicle;

[0052] If the target vehicle is in the completion phase of changing lanes from the right adjacent lane to the own lane, the first probability is zero;

[0053] If the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle;

[0054] If the target vehicle is in the middle stage of changing lanes from the ego lane to the right adjacent lane, a first probability is determined according to the tenth parameter, the eleventh parameter, the twelfth parameter, and the lateral distance between the target vehicle and the ego vehicle;

[0055] If the target vehicle is in the completion phase of changing lanes from its own lane to the right adjacent lane, the first probability is zero.

[0056] In a possible implementation, determining the second probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0057] According to the azimuth relationship between the target vehicle and the ego vehicle and the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located, the lane change stage of the target vehicle is determined;

[0058] The second probability is determined according to the lane change phase of the target vehicle.

[0059] In a possible implementation, if the target vehicle is located on the left side of the own vehicle, determining the lane change stage of the target vehicle according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0060] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the seventh preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane;

[0061] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the eighth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane;

[0062] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within a ninth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the left adjacent lane to the own lane;

[0063] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the tenth preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the ego lane to the left adjacent lane;

[0064] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the eleventh preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the left adjacent lane;

[0065] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the twelfth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the own lane to the left adjacent lane.

[0066] In a possible implementation, determining the second probability according to the lane change phase of the target vehicle includes:

[0067] If the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0068] If the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, the second probability is determined according to the thirteenth parameter, the fourteenth parameter, the fifteenth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0069] If the target vehicle is in the stage of completing the lane change from the left adjacent lane to the own lane, the second probability is zero;

[0070] If the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, a second probability is determined based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0071] If the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, the second probability is determined according to the sixteenth parameter, the seventeenth parameter, the eighteenth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0072] If the target vehicle is in the completion phase of changing lanes from the target vehicle's own lane to the left adjacent lane, the second probability is zero.

[0073] In a possible implementation, if the target vehicle is located on the right side of the own vehicle, determining the lane change stage of the target vehicle according to the distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0074] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the seventh preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane;

[0075] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the eighth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane;

[0076] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within a ninth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane;

[0077] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the tenth preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the ego lane to the right adjacent lane;

[0078] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the eleventh preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the right adjacent lane;

[0079] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the twelfth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the own lane to the right adjacent lane.

[0080] In a possible implementation, determining the second probability according to the lane change phase of the target vehicle includes:

[0081] If the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0082] If the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane, the second probability is determined according to the nineteenth parameter, the twentieth parameter, the twenty-first parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0083] If the target vehicle is in the completion phase of changing lanes from the right adjacent lane to the own lane, the second probability is zero;

[0084] If the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0085] If the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane, the second probability is determined according to the twenty-second parameter, the twenty-third parameter, the twenty-fourth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located;

[0086] If the target vehicle is in the completion phase of changing lanes from the target vehicle's own lane to the right adjacent lane, the second probability is zero.

[0087] In a second aspect, an embodiment of the present application provides a target vehicle behavior prediction device, comprising:

[0088] An information acquisition module is used to obtain current lane type information;

[0089] A lane change probability determination module is used to select and execute at least one of the following four steps according to the lane type information:

[0090] A first lane change probability determination step: determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the own vehicle;

[0091] A second lane change probability determination step: determining a second probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located;

[0092] A third lane-changing probability determination step: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the ego vehicle in the historical frame;

[0093] A fourth lane change probability determination step: determining a fourth probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame;

[0094] Behavior prediction module: predicts the behavior of the target vehicle according to at least one of the first probability, the second probability, the third probability and the fourth probability.

[0095] In a third aspect, an embodiment of the present application provides a terminal device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described above when executing the computer program.

[0096] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described above is implemented.

[0097] Beneficial effects of this application

[0098] The present application provides a method, device, equipment and computer-readable storage medium for predicting the behavior of a target vehicle, wherein the method comprises: obtaining current lane type information, and executing at least one of a first lane change probability determination step, a second lane change probability determination step, a third lane change probability determination step and a fourth lane change probability determination step according to the lane type information, and predicting the behavior of the target vehicle according to at least one lane change probability determined among the above four probabilities. The method provided in the present application predicts the behavior of the target vehicle at a future moment by determining the probability of the target vehicle changing lanes, so the method provided in the present application can assist the driver in making predictions about the behavior of surrounding vehicles, thereby effectively reducing traffic accidents caused by lane changes of the target vehicle and ensuring driving safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0100] Figure 1 This is one of the flow charts of the target vehicle behavior prediction method provided in one embodiment of the present application;

[0101] Figure 2 This is the second flow chart of the target vehicle behavior prediction method provided in one embodiment of the present application;

[0102] Figure 3 This is the third flow chart of the target vehicle behavior prediction method provided in one embodiment of the present application;

[0103] Figure 4 This is a fourth flow chart of a target vehicle behavior prediction method provided in an embodiment of the present application;

[0104] Figure 5 is a schematic diagram of a first probability determination process provided by an embodiment of the present application;

[0105] Figure 6 is a schematic diagram of the structure of a target vehicle behavior prediction device provided in an embodiment of the present application;

[0106] Figure 7 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0107] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may 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 prevent unnecessary details from obstructing the description of the present application.

[0108] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0109] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0110] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0111] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0112] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0113] With the rapid increase in the number of cars, the driving environment has become more complex. During driving, not only do we need to avoid obstacles and pedestrians, but we also need to respond promptly and accurately to the behavior of surrounding vehicles. When driving, people will subconsciously predict the behavior of other vehicles to determine the driving route of their own vehicle based on the intentions of other vehicles. This can avoid possible dangers to a certain extent, but the external information that humans can capture is limited. When a vehicle suddenly changes lanes or a car is in the driver's blind spot, it is not easy to predict the behavior of other vehicles. In addition, it is difficult for drivers to concentrate for a long time, and they will inevitably be distracted by some external factors, and traffic accidents often occur at these moments.

[0114] The present application provides a method, device, equipment and computer-readable storage medium for predicting the behavior of a target vehicle, wherein the method comprises: obtaining current lane type information, and executing at least one of a first lane change probability determination step, a second lane change probability determination step, a third lane change probability determination step and a fourth lane change probability determination step according to the lane type information, and predicting the behavior of the target vehicle according to at least one lane change probability determined among the above four probabilities. The method provided by the present application predicts the behavior of the target vehicle at a future moment by determining the probability of the target vehicle changing lanes. Therefore, the present application solves the problem of the difficulty in predicting the behavior of the target vehicle to a certain extent, improves the accuracy of the prediction of the behavior of the target vehicle, and can effectively reduce traffic accidents caused by the lane change of the target vehicle and ensure driving safety.

[0115] In order to illustrate the technical solution of the present application, specific embodiments are provided below.

[0116] See also Figure 1 The process of an embodiment of the target vehicle behavior prediction method shown, as an example but not a limitation, includes the following steps:

[0117] Step S1: Obtain current lane type information;

[0118] Step S2: Select at least one of the following four steps to be performed according to the lane type information:

[0119] First lane change probability determination step S21: determining a first probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the own vehicle;

[0120] Second lane change probability determination step S22: determining a second probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the vehicle is located;

[0121] A third lane change probability determination step S23: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the vehicle in the historical frame;

[0122] Fourth lane change probability determination step S24: determining a fourth probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame.

[0123] Step S3: predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability and the fourth probability.

[0124] In step S1, the current lane type information includes: whether the lane currently traveled has a lane centerline, and whether the current traveled road is a straight road or a curved road. Exemplarily, the lane types include: a straight road with a lane centerline, a straight road without a lane centerline, and a curved road with a lane centerline. Because different lane types correspond to different lane change probability determination steps, it is necessary to distinguish lane types.

[0125] In order to better understand this solution, the lateral distance in step S2 is first explained. A coordinate system is established with the position of the ego vehicle as the origin and the driving direction of the ego vehicle as the positive direction of the X-axis. The lateral distance between the target vehicle and the ego vehicle refers to the distance from the midpoint of the rear axle of the target vehicle to the X-axis, and the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located refers to the distance from the midpoint of the rear axle of the target vehicle to the center line of the lane where the ego vehicle is located.

[0126] In step S2, at least one of the first lane change probability determination step S21, the second lane change probability determination step S22, the third lane change probability determination step S23 and the fourth lane change probability determination step S24 is selected to be executed according to the lane type. In step S2, the lateral distance is selected as the lane change probability calculation because the lateral distance between the target vehicle and the self-vehicle or the center line of the lane where the self-vehicle is located is constantly changing during the lane change process of the target vehicle. Therefore, this solution uses the lateral distance to determine the probability of the target vehicle changing lanes.

[0127] It should be noted that, depending on the lane type, we can choose to perform different lane change probability determination steps. Exemplarily, if the lane type is a straight road and there is no lane centerline, the target vehicle behavior cannot be predicted based on the lateral distance from the target vehicle to the centerline of the lane where the own vehicle is located. Therefore, it can only be predicted based on the lateral distance between the target vehicle and the own vehicle. Therefore, at this time, at least one of the first lane change prediction step S21 and the third lane change prediction step S23 can be executed; if the lane type is a curve and there is a lane centerline, it is more accurate to predict based on the lateral distance between the target vehicle and the centerline of the lane where the own vehicle is located. Therefore, at this time, at least one of the second lane change prediction step S22 and the fourth lane change prediction step S24 can be executed. It should be noted that in this case, the first lane change prediction step S21 and the third lane change prediction step S23 can also be executed, but in subsequent steps, different weights need to be given to the probabilities obtained after the above steps are executed; if the lane type is a straight road and there is a lane centerline, the first lane change probability determination step S21, the second lane change probability determination step S22, the third lane change probability determination step S23 and the fourth lane change probability determination step S24 can be executed simultaneously.

[0128] It should be noted that if only one lane change probability is determined in step S2, it is directly used to predict the target vehicle behavior. If multiple lane change probabilities are determined in step S2, the multiple probabilities need to be combined to jointly predict the target vehicle behavior.

[0129] Using the above method, that is, based on the current lane type information, and at least one of the lateral distance between the target vehicle and the own vehicle and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located, the probability of the target vehicle changing lanes can be determined, and then the behavior of the target vehicle can be predicted. Therefore, the method provided in this application can assist the driver in predicting the behavior of surrounding vehicles, thereby effectively reducing traffic accidents caused by lane changes and ensuring driving safety.

[0130] In one possible implementation, see Figure 2 , if both the first lane change probability determination step S21 and the third lane change probability determination step S23 are executed, then the target vehicle behavior is predicted according to at least one of the first probability, the second probability, the third probability and the fourth probability, including:

[0131] S311: Calculating a first average value according to the first probability and the third probability;

[0132] S312: Predicting the behavior of the target vehicle according to the first average value.

[0133] It should be noted that, in this embodiment, the first lane change probability determination step S21 and the third lane change probability determination step S23 are first performed. Further, the arithmetic mean is taken for the first probability determined in the first lane change probability determination step S21 and the third probability determined in the third lane change probability determination step S23. If the arithmetic mean is greater than the first preset threshold, it is predicted that the target vehicle will change lanes.

[0134] In this embodiment, the behavior of the target vehicle is predicted in combination with historical frame data. Since the lateral distance between the target vehicle and the own vehicle in the historical frame can reflect the movement trend of the target vehicle within a certain period of time, the real-time performance of the target vehicle behavior prediction is improved by combining the historical frame data, and the probability of the target vehicle changing lanes can be calculated more accurately.

[0135] In one possible implementation, see Figure 3 , if the second lane change probability determination step S22 and the fourth lane change probability determination step S24 are both executed, then the target vehicle behavior is predicted according to at least one of the first probability, the second probability, the third probability and the fourth probability, including:

[0136] S321: Calculate a second average value according to the second probability and the fourth probability;

[0137] S322: Predicting the behavior of the target vehicle according to the second average value.

[0138] It should be noted that, in this embodiment, the second lane change probability determination step S22 and the fourth lane change probability determination step S24 are first performed. Further, the arithmetic mean is taken for the second probability determined in the second lane change probability determination step S22 and the fourth probability determined in the fourth lane change probability determination step S24. If the arithmetic mean is greater than the second preset threshold, it is predicted that the target vehicle is about to change lanes.

[0139] In this embodiment, the behavior of the target vehicle is predicted by combining historical frame data. Since the lateral distance between the target vehicle and the vehicle in the historical frame can reflect the movement trend of the target vehicle within a certain period of time, combining historical frame data improves the real-time prediction of the target vehicle's behavior and can more accurately calculate the probability of the target vehicle changing lanes.

[0140] In one possible implementation, see Figure 4 , if the first lane change probability determination step, the second lane change probability determination step, the third lane change probability determination step and the fourth lane change probability determination step are all executed, then predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability and the fourth probability includes:

[0141] S331: Calculate a third average value according to the first probability, the second probability, the third probability and the fourth probability;

[0142] S332: Predicting the target vehicle behavior according to the third average value.

[0143] For more ideal road conditions, that is, the lane type is a straight road and there is a lane centerline, we can combine multiple calculation steps to more accurately determine the probability of the target vehicle changing lanes. Specifically, the first probability, the second probability, the third probability and the fourth probability can be calculated at the same time. Further, the arithmetic mean of the above four steps is taken as the final probability of the target vehicle changing lanes. If the arithmetic mean is greater than the third preset threshold, it is predicted that the target vehicle will change lanes. The target vehicle behavior prediction method of multi-rule fusion in this embodiment is used to better improve the accuracy and real-time performance of the target behavior prediction.

[0144] In a possible implementation, determining the third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the vehicle in the historical frame includes:

[0145] A third probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the ego vehicle, and the corresponding accumulated generalized probability distribution.

[0146] It should be noted that this embodiment provides a specific calculation method for the third probability, that is, by collecting the lateral distance between the target vehicle and the own vehicle in a certain number of historical frames, calculating the change in the lateral distance, and further combining the cumulative generalized probability distribution corresponding to the change, to determine the third probability of the target vehicle changing lanes.

[0147] In order to better understand this solution, we first briefly explain the process of obtaining the cumulative generalized probability distribution: the basis for obtaining the cumulative generalized probability distribution is a large amount of data collected from real vehicles. During the process of the target vehicle changing lanes, its historical trajectory points can be collected and stored. The data collected under the same working conditions are statistically analyzed to obtain the distribution trend of the historical points of the target vehicle's lane changing under the working conditions. This trend is the probability distribution of the target vehicle's lane changing behavior.

[0148] It should be noted that we can preset the number of interval frames in advance, for example, the preset number of interval frames is 20, then when the collected historical frame data is sufficient, the horizontal distance change at an interval of 20 frames can be directly calculated. In addition, in the actual collection process, it may happen that not enough historical frame data is collected, for example, only 10 frames of data are collected, in which case the horizontal distance change at an interval of 10 frames needs to be calculated.

[0149] In a possible implementation, determining the fourth probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame includes:

[0150] A fourth probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the center line of the lane where the vehicle is located, and the corresponding cumulative generalized probability distribution.

[0151] It should be noted that this embodiment provides a specific calculation method for the fourth probability, that is, by collecting the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located in a certain number of historical frames, calculating the change in the lateral distance, and further combining the cumulative generalized probability distribution corresponding to the change, to determine the fourth probability of the target vehicle changing lanes.

[0152] In one possible implementation, see Figure 5 , determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the vehicle includes:

[0153] S11: determining the lane change stage of the target vehicle according to the azimuth relationship and lateral distance between the target vehicle and the ego vehicle;

[0154] S12: Determine a first probability according to the lane change phase of the target vehicle.

[0155] In order to better understand this solution, the orientation relationship is first explained. For example, in one embodiment, a coordinate axis is established with the midpoint of the rear axle of the vehicle as the origin and the straight line where the median line of the rear axle of the vehicle is located as the axis, and the direction of travel of the vehicle is the positive direction. If the midpoint of the rear axle of the target vehicle is located on the left side of the coordinate axis, it is determined that the target vehicle is located on the left side of the vehicle. If the midpoint of the rear axle of the target vehicle is located on the right side of the coordinate axis, it is determined that the target vehicle is located on the right side of the vehicle.

[0156] It should be noted that, in this embodiment, the lane change of the target vehicle can be divided into multiple stages, and the probability algorithm corresponding to each stage is different. Therefore, it is necessary to first determine the lane change stage of the target vehicle, and then select the corresponding algorithm to calculate the probability of lane change. In addition, since this solution not only needs to determine whether the target vehicle is going to change lanes, but also needs to determine the direction of the target vehicle's lane change, it is necessary to combine the position relationship between the target vehicle and the self-vehicle when determining the lane change stage of the target vehicle.

[0157] In a possible implementation, if the target vehicle is located on the left side of the own vehicle, determining the lane change phase of the target vehicle according to the distance between the target vehicle and the own vehicle includes:

[0158] If the lateral distance between the target vehicle and the own vehicle is within the first preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane;

[0159] If the lateral distance between the target vehicle and the own vehicle is within the second preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane;

[0160] If the lateral distance between the target vehicle and the own vehicle is within a third preset range, it is determined that the target vehicle is in a stage of completing a lane change from the left adjacent lane to the own lane;

[0161] If the lateral distance between the target vehicle and the ego vehicle is within a fourth preset range, it is determined that the target vehicle is in an initial stage of changing lanes from the ego lane to the left adjacent lane;

[0162] If the lateral distance between the target vehicle and the ego vehicle is within the fifth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the left adjacent lane;

[0163] If the lateral distance between the target vehicle and the own vehicle is within a sixth preset range, it is determined that the target vehicle is in a completion stage of changing lanes from the own lane to the left adjacent lane.

[0164] It should be noted that, in the present embodiment, all preset ranges are determined through statistical analysis of a large amount of data collected from the actual vehicle under different working conditions and scenarios, wherein the first preset range to the third preset range do not overlap with each other, and the fourth preset range to the sixth preset range do not overlap with each other. The relationship between the first preset range to the sixth preset range is explained below with specific embodiments, and the process of determining the lane change stage of the target vehicle is explained.

[0165] In one possible scenario, the first preset range is a range where the lateral distance between the target vehicle and the own vehicle is greater than 3.5m, the second preset range is a range where the lateral distance between the target vehicle and the own vehicle is greater than 0.875m and less than 3.5m, and the third preset range is a range where the lateral distance between the target vehicle and the own vehicle is less than 0.875m. The first preset range to the third preset range do not overlap, so the lane change stage of the target vehicle can be determined based on the lateral distance between the target vehicle and the own vehicle. The purpose of determining the lane change stage is that when the lane change stage of the target vehicle is different, the corresponding lane change probability calculation method is different, so it is necessary to first determine the lane change stage, and then determine the lane change probability based on the lane change stage.

[0166] In a possible situation, the fourth preset range is a range where the lateral distance between the target vehicle and the vehicle is greater than 0m and less than 0.875m, the fifth preset range is a range where the lateral distance between the target vehicle and the vehicle is greater than 0.875m and less than 3m, and the sixth preset range is a range where the lateral distance between the target vehicle and the vehicle is greater than 3m. The fourth preset range to the sixth preset range do not overlap, so the lane change stage of the target vehicle can be determined based on the lateral distance between the target vehicle and the vehicle. The purpose of determining the lane change stage is that when the lane change stage of the target vehicle is different, the corresponding lane change probability calculation method is different, so it is necessary to first determine the lane change stage, and then determine the lane change probability according to the lane change stage. Since the lane change probability calculation methods corresponding to different lane change stages are different, it is necessary to determine the lane change stage of the target vehicle through the lateral distance between the target vehicle and the vehicle, and then further determine the probability calculation method according to the lane change stage of the target vehicle.

[0167] In a possible implementation, the determining of the first probability according to the lane change stage of the target vehicle includes: if the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, determining the first probability according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, determining the first probability according to the first parameter, the second parameter, the third parameter and the lateral distance between the target vehicle and the own vehicle; if the target vehicle is in the completion stage of changing lanes from the left adjacent lane to the own lane, the first probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, determining the first probability according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, determining the first probability according to the fourth parameter, the fifth parameter, the sixth parameter and the lateral distance between the target vehicle and the own vehicle; if the target vehicle is in the completion stage of changing lanes from the own lane to the left adjacent lane, the first probability is zero.

[0168] It should be noted that the first parameter, the second parameter and the third parameter are coefficients of the first quadratic curve fitted according to the process of the target vehicle changing lanes from the left adjacent lane to the own lane when the own vehicle is the reference system, wherein the first parameter is the quadratic term coefficient corresponding to the first quadratic curve, the second parameter is the linear term coefficient corresponding to the first quadratic curve, and the third parameter is the constant term corresponding to the first quadratic curve.

[0169] It should be noted that the fourth parameter, the fifth parameter and the sixth parameter are coefficients of the second quadratic curve fitted according to the process of the target vehicle changing lanes from the own lane to the left adjacent lane with the own vehicle as the reference system, wherein the fourth parameter is the quadratic term coefficient corresponding to the second quadratic curve, the fifth parameter is the linear term coefficient corresponding to the second quadratic curve, and the sixth parameter is the constant term corresponding to the second quadratic curve.

[0170] The determination of the above six coefficients needs to be obtained by fitting the trajectory points of the target vehicle changing lanes in the corresponding scenario. Commonly used fitting methods include least squares curve fitting method, etc. Polyfit can also be used to fit polynomials in MATLAB. Specifically, 1000 sets of trajectory points of the target vehicle changing lanes from the left adjacent lane to the own lane can be collected, and these 1000 sets of data can be fitted through polyfit to obtain the coefficients of the fitting curve. Similarly, for the case where the target vehicle changes lanes from the own lane to the left adjacent lane, 1000 sets of data also need to be collected and fitted.

[0171] It should be noted that this embodiment provides a specific calculation method for the first probability. Specifically, if the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, the first probability P1 is the difference between 1 and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, the first probability P1 is: the product of the first parameter a1 and the square of the lateral distance Dy from the target vehicle to the own vehicle, the product of the second parameter b1 and the lateral distance Dy from the target vehicle to the own vehicle, and the sum of the third parameter c1, that is, P1 = a1*Dy 2 +b1*Dy+c1; if the target vehicle is in the completion stage of changing lanes from the left adjacent lane to the own lane, the first probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, the first probability is the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, the first probability P1 is: the product of the fourth parameter a2 and the square of the lateral distance Dy from the target vehicle to the own vehicle, the product of the fifth parameter b2 and the lateral distance Dy from the target vehicle to the own vehicle, and the sum of the sixth parameter c2, that is, P1=a2*Dy 2 +b2*Dy+c2; if the target vehicle is in the completion stage of changing lanes from its own lane to the left adjacent lane, the first probability is zero.

[0172] It should be noted that different first probability determination methods correspond to different stages of the target vehicle's lane change, which is a rule summarized based on a large amount of target vehicle lane change data. In the initial stage of the target vehicle's lane change, since its lane change probability distribution is relatively concentrated and does not conform to a linear relationship, the cumulative generalized probability distribution is selected to determine the target vehicle's lane change probability; while in the middle stage of the target vehicle's lane change, its lane change intention conforms to a composite linear relationship, so the target vehicle's lane change probability can be determined based on the probability calculation formula corresponding to the parameters of the fitting curve. Therefore, the above-mentioned segmented probability determination method can more accurately determine the target vehicle's lane change probability.

[0173] In a possible implementation, if the target vehicle is located on the right side of the own vehicle, the determining of the lane change stage of the target vehicle based on the lateral distance between the target vehicle and the own vehicle includes: if the lateral distance between the target vehicle and the own vehicle is within a first preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane; if the lateral distance between the target vehicle and the own vehicle is within a second preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane; if the lateral distance between the target vehicle and the own vehicle is within a third preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane; if the lateral distance between the target vehicle and the own vehicle is within a fourth preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane; if the lateral distance between the target vehicle and the own vehicle is within a fifth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane; if the lateral distance between the target vehicle and the own vehicle is within a sixth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the own lane to the right adjacent lane.

[0174] It should be noted that, in this embodiment, all preset ranges are determined through statistical analysis of a large amount of data collected from the actual vehicle under different working conditions and scenarios, wherein the first preset range to the third preset range do not overlap with each other, and the fourth preset range to the sixth preset range do not overlap with each other.

[0175] Since the lane change probability calculation methods corresponding to different lane change stages are different, it is necessary to determine the lane change stage of the target vehicle through the lateral distance between the target vehicle and the center line of the lane where the vehicle is located, and then further determine the probability calculation method based on the lane change stage of the target vehicle.

[0176] In a possible implementation, the determining of the first probability according to the lane change stage of the target vehicle includes: if the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, determining the first probability according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane, determining the first probability according to the seventh parameter, the eighth parameter, the ninth parameter and the lateral distance between the target vehicle and the own vehicle; if the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane, the first probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, determining the first probability according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane, determining the first probability according to the tenth parameter, the eleventh parameter, the twelfth parameter and the lateral distance between the target vehicle and the own vehicle; if the target vehicle is in the completion stage of changing lanes from the own lane to the right adjacent lane, the first probability is zero.

[0177] Among them, the seventh parameter, the eighth parameter and the ninth parameter are the coefficients of the third quadratic curve fitted according to the process of the target vehicle changing lanes from the right adjacent lane to the own lane when the own vehicle is the reference system, wherein the seventh parameter is the quadratic term coefficient corresponding to the third quadratic curve, the eighth parameter is the linear term coefficient corresponding to the third quadratic curve, and the ninth parameter is the constant term corresponding to the third quadratic curve.

[0178] Among them, the tenth parameter, the eleventh parameter and the twelfth parameter are the coefficients of the fourth quadratic curve fitted according to the process of the target vehicle changing lanes from the self-lane to the right adjacent lane when the self-lane is the reference system, wherein the tenth parameter is the quadratic term coefficient corresponding to the fourth quadratic curve, the eleventh parameter is the linear term coefficient corresponding to the fourth quadratic curve, and the twelfth parameter is the constant term corresponding to the fourth quadratic curve. It should be noted that this embodiment provides a specific calculation method for the first probability. Specifically, if the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the self-lane, the first probability P1 is the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the self-lane; if the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the self-lane, the first probability P1 is: the product of the seventh parameter a3 and the square of the lateral distance Dy from the target vehicle to the self-lane, the product of the eighth parameter b3 and the lateral distance Dy from the target vehicle to the self-lane, and the sum of the ninth parameter c3, that is, P1 = a3*Dy 2+b3*Dy+c3; if the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane, the first probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, the first probability is the difference between 1 and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; if the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane, the first probability P1 is: the product of the tenth parameter a4 and the square of the lateral distance Dy from the target vehicle to the own vehicle, the product of the eleventh parameter b4 and the lateral distance Dy from the target vehicle to the own vehicle, and the sum of the twelfth parameter c4, that is, P1=a4*Dy 2 +b4*Dy+c4; if the target vehicle is in the completion stage of changing lanes from its own lane to the right adjacent lane, the first probability is zero.

[0179] It should be noted that different first probability determination methods correspond to different stages of the target vehicle's lane change, which is a rule summarized based on a large amount of target vehicle lane change data. In the initial stage of the target vehicle's lane change, since its lane change probability distribution is relatively concentrated and does not conform to a linear relationship, the cumulative generalized probability distribution is selected to determine the target vehicle's lane change probability; while in the middle stage of the target vehicle's lane change, its lane change intention complies with a linear relationship, so the target vehicle's lane change probability can be determined according to the corresponding probability calculation formula. Therefore, the above-mentioned segmented probability determination method can more accurately determine the target vehicle's lane change probability.

[0180] In a possible implementation, determining the second probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0181] According to the azimuth relationship between the target vehicle and the ego vehicle and the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located, the lane change stage of the target vehicle is determined;

[0182] The second probability is determined according to the lane change phase of the target vehicle.

[0183] It should be noted that, in this embodiment, the lane change of the target vehicle can be divided into multiple stages, and the probability algorithm corresponding to each stage is different. Therefore, it is necessary to first determine the lane change stage of the target vehicle, and then select the corresponding algorithm to calculate the probability of lane change. In addition, since this solution not only needs to determine whether the target vehicle is going to change lanes, but also needs to determine the direction of the target vehicle's lane change, when determining the lane change stage of the target vehicle, it is necessary to combine the position relationship between the target vehicle and the self-vehicle.

[0184] In a possible implementation, if the target vehicle is located on the left side of the own vehicle, determining the lane change stage of the target vehicle according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0185] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the seventh preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane;

[0186] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the eighth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane;

[0187] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within a ninth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the left adjacent lane to the own lane;

[0188] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the tenth preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the ego lane to the left adjacent lane;

[0189] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the eleventh preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the left adjacent lane;

[0190] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the twelfth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the own lane to the left adjacent lane.

[0191] It should be noted that, in this embodiment, all preset ranges are determined through statistical analysis of a large amount of data collected from the actual vehicle under different working conditions and scenarios, wherein the seventh preset range to the ninth preset range do not overlap with each other, and the tenth preset range to the twelfth preset range do not overlap with each other.

[0192] Since the lane change probability calculation methods corresponding to different lane change stages are different, it is necessary to determine the lane change stage of the target vehicle through the lateral distance between the target vehicle and the own vehicle, and then further determine the probability calculation method according to the lane change stage of the target vehicle.

[0193] In a possible implementation, the determining of the second probability according to the lane change stage of the target vehicle includes: if the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, determining the second probability according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the intermediate stage of changing lanes from the left adjacent lane to the own lane, determining the second probability according to the thirteenth parameter, the fourteenth parameter, the fifteenth parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; if the target vehicle is in the intermediate stage of changing lanes from the left adjacent lane to the own lane, determining the second probability according to the thirteenth parameter, the fourteenth parameter, the fifteenth parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the completion stage of lane change from the own lane to the left adjacent lane, the second probability is zero; if the target vehicle is in the initial stage of lane change from the own lane to the left adjacent lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the middle stage of lane change from the own lane to the left adjacent lane, the second probability is determined according to the sixteenth parameter, the seventeenth parameter, the eighteenth parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; if the target vehicle is in the completion stage of lane change from the own lane to the left adjacent lane, the second probability is zero.

[0194] Among them, the thirteenth parameter, the fourteenth parameter and the fifteenth parameter are coefficients of the fifth quadratic curve fitted according to the process of the target vehicle changing lanes from the left adjacent lane to the own lane with the lane line where the own vehicle is located as the reference system, wherein the thirteenth parameter is the quadratic term coefficient corresponding to the fifth quadratic curve, the fourteenth parameter is the linear term coefficient corresponding to the fifth quadratic curve, and the fifteenth parameter is the constant term corresponding to the fifth quadratic curve.

[0195] Among them, the sixteenth parameter, the seventeenth parameter and the eighteenth parameter are the coefficients of the sixth quadratic curve fitted according to the process of the target vehicle changing lanes from the self-lane to the left adjacent lane, with the lane line where the self-lane is located as the reference system, wherein the sixteenth parameter is the quadratic term coefficient corresponding to the sixth quadratic curve, the seventeenth parameter is the linear term coefficient corresponding to the sixth quadratic curve, and the eighteenth parameter is the constant term corresponding to the sixth quadratic curve. The determination of the above six coefficients needs to be obtained by fitting the trajectory points of the target vehicle changing lanes under the corresponding scene collected. Commonly used fitting methods include the least squares curve fitting method, etc. In MATLAB, polyfit can also be used to fit polynomials.

[0196] It should be noted that this embodiment provides a specific calculation method for the second probability. Specifically, if the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, the second probability P2 is the difference between 1 and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, the second probability P2 is: the product of the thirteenth parameter a5 and the square of the lateral distance CDy from the target vehicle to the center line of the lane where the own vehicle is located, the product of the fourteenth parameter b5 and the lateral distance CDy from the target vehicle to the center line of the lane where the own vehicle is located, and the sum of the fifteenth parameter c5, that is, P2 = a5*CDy 2 +b5*CDy+c5; if the target vehicle is in the completion stage of changing lanes from the left adjacent lane to the own lane, the second probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, the second probability is the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, the second probability P2 is: the product of the sixteenth parameter a6 and the square of the lateral distance CDy from the target vehicle to the center line of the lane where the own vehicle is located, the product of the seventeenth parameter b6 and the lateral distance CDy from the target vehicle to the center line of the lane where the own vehicle is located, and the sum of the eighteenth parameter c6, that is, P2=a6*CDy 2 +b6*CDy+c6; if the target vehicle is in the completion stage of changing lanes from its own lane to the left adjacent lane, the second probability is zero.

[0197] In a possible implementation, if the target vehicle is located on the right side of the own vehicle, determining the lane change stage of the target vehicle according to the distance between the target vehicle and the center line of the lane where the own vehicle is located includes:

[0198] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the seventh preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane;

[0199] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the eighth preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane;

[0200] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within a ninth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane;

[0201] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the tenth preset range, it is determined that the target vehicle is in the initial stage of changing lanes from the ego lane to the right adjacent lane;

[0202] If the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located is within the eleventh preset range, it is determined that the target vehicle is in the middle stage of changing lanes from the ego lane to the right adjacent lane;

[0203] If the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located is within the twelfth preset range, it is determined that the target vehicle is in the completion stage of changing lanes from the own lane to the right adjacent lane.

[0204] It should be noted that, in this embodiment, all preset ranges are determined through statistical analysis of a large amount of data collected from the actual vehicle under different working conditions and scenarios, wherein the seventh preset range to the ninth preset range do not overlap with each other, and the tenth preset range to the twelfth preset range do not overlap with each other.

[0205] Since the lane change probability calculation methods corresponding to different lane change stages are different, it is necessary to determine the lane change stage of the target vehicle through the lateral distance between the target vehicle and the center line of the lane where the vehicle is located, and then further determine the probability calculation method based on the lane change stage of the target vehicle.

[0206] In a possible implementation, the determining of the second probability according to the lane change stage of the target vehicle includes: if the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, determining the second probability according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the intermediate stage of changing lanes from the right adjacent lane to the own lane, determining the second probability according to the nineteenth parameter, the twentieth parameter, the twenty-first parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; if the target vehicle is in the intermediate stage of changing lanes from the right adjacent lane to the own lane, determining the second probability according to the nineteenth parameter, the twentieth parameter, the twenty-first parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the completion stage of lane change, the second probability is zero; if the target vehicle is in the initial stage of lane change from the own lane to the right adjacent lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the middle stage of lane change from the own lane to the right adjacent lane, the second probability is determined according to the twenty-second parameter, the twenty-third parameter, the twenty-fourth parameter and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; if the target vehicle is in the completion stage of lane change from the own lane to the right adjacent lane, the second probability is zero.

[0207] Among them, the nineteenth parameter, the twentieth parameter and the twenty-first parameter are coefficients of the seventh quadratic curve fitted according to the process of the target vehicle changing lanes from the right adjacent lane to the own lane with the lane line where the own vehicle is located as the reference system, wherein the nineteenth parameter is the quadratic term coefficient corresponding to the seventh quadratic curve, the twentieth parameter is the linear term coefficient corresponding to the seventh quadratic curve, and the twenty-first parameter is the constant term corresponding to the seventh quadratic curve.

[0208] Among them, the 22nd parameter, the 23rd parameter and the 24th parameter are the coefficients of the eighth quadratic curve fitted according to the process of the target vehicle changing lanes from the self-lane to the right adjacent lane, with the lane line where the self-lane is located as the reference system, wherein the 22nd parameter is the quadratic term coefficient corresponding to the eighth quadratic curve, the 23rd parameter is the linear term coefficient corresponding to the eighth quadratic curve, and the 24th parameter is the constant term corresponding to the eighth quadratic curve. It should be noted that this embodiment provides a specific calculation method for the second probability. Specifically, if the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the self-lane, the second probability P2 is the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the self-lane is located; if the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the self-lane, the second probability P2 is: the product of the square of the lateral distance CDy from the target vehicle to the center line of the lane where the self-lane is located, the product of the twentieth parameter b7 and the lateral distance CDy from the target vehicle to the center line of the lane where the self-lane is located, and the sum of the twenty-first parameter c7, that is, P2 = a7*CDy 2 +b7*CDy+c7; if the target vehicle is in the completion stage of changing lanes from the right adjacent lane to the own lane, the second probability is zero; if the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, the second probability is the difference between 1 and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the center line of the lane where the own vehicle is located; if the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane, the second probability P2 is: the product of the twenty-second parameter a8 and the square of the lateral distance CDy from the center line of the lane where the target vehicle is located, the product of the twenty-third parameter b8 and the lateral distance CDy from the center line of the lane where the target vehicle is located, and the sum of the twenty-fourth parameter c8, that is, P2=a8*CDy 2 +b8*CDy+c8; if the target vehicle is in the completion stage of changing lanes from its own lane to the right adjacent lane, the second probability is zero.

[0209] It should be noted that different second probability determination methods correspond to different stages of the target vehicle's lane change, which is a rule summarized based on a large amount of target vehicle lane change data. In the initial stage of the target vehicle's lane change, since its lane change probability distribution is relatively concentrated and does not conform to a linear relationship, the cumulative generalized probability distribution is selected to determine the target vehicle's lane change probability; while in the middle stage of the target vehicle's lane change, its lane change intention complies with a linear relationship, so the target vehicle's lane change probability can be determined according to the corresponding probability calculation formula. Therefore, the above-mentioned segmented probability determination method can more accurately determine the target vehicle's lane change probability.

[0210] The present application provides a target vehicle behavior prediction device, such as Figure 6 As shown, including:

[0211] The information acquisition module 601 is used to acquire the current lane type information;

[0212] The lane change probability determination module 602 is configured to select and execute at least one of the following four steps according to the lane type information:

[0213] A first lane change probability determination step: determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the own vehicle;

[0214] A second lane change probability determination step: determining a second probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located;

[0215] A third lane-changing probability determination step: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the ego vehicle in the historical frame;

[0216] A fourth lane change probability determination step: determining a fourth probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame;

[0217] The behavior prediction module 603 predicts the behavior of the target vehicle according to at least one of the first probability, the second probability, the third probability and the fourth probability.

[0218] Through the combined use of the above three modules, the probability of the target vehicle changing lanes can be determined based on the current lane type information and at least one of the lateral distance between the target vehicle and the own vehicle and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located, and the behavior of the target vehicle can be further predicted based on the probability of the target vehicle changing lanes. The use of this device solves the problem of the target vehicle's behavior being difficult to predict to a certain extent, thereby effectively reducing traffic accidents caused by the target vehicle's lane change and ensuring driving safety.

[0219] Figure 7 The terminal device 400 includes: at least one processor 401 ( Figure 7 Only one is shown in the figure) a processor, a memory 402, and a computer program 403 stored in the memory 402 and executable on the at least one processor 401, and when the processor 401 executes the computer program 403, the steps in the above-mentioned target vehicle behavior prediction method embodiment are implemented.

[0220] The terminal device 400 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 400 and does not constitute a limitation on the terminal device 400. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0221] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0222] In some embodiments, the memory 402 may be an internal storage unit of the terminal device 400, such as a hard disk or memory of the terminal device 400. In other embodiments, the memory 402 may also be an external storage device of the terminal device 400, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal device 400. Further, the memory 402 may also include both an internal storage unit of the terminal device 400 and an external storage device. The memory 402 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0223] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, 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 software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0224] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments can be implemented.

[0225] An embodiment of the present application provides a computer program product. When the computer program product runs on a mobile terminal, the mobile terminal can implement the steps in the above-mentioned method embodiments when executing the computer program product.

[0226] 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, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0227] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0228] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0229] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0230] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0231] The embodiments described above 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 aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions 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 target vehicle behavior prediction method, characterized in that: include: Get the current lane type information; At least one of the following four steps is selected and performed according to the lane type information: A first lane change probability determination step: determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the own vehicle; A second lane change probability determination step: determining a second probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located; A third lane-changing probability determination step: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the ego vehicle in the historical frame; A fourth lane change probability determination step: determining a fourth probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame; The target vehicle behavior is predicted according to at least one of the first probability, the second probability, the third probability, and the fourth probability.

2. The target vehicle behavior prediction method according to claim 1, characterized in that: If the first lane change probability determination step, the second lane change probability determination step, the third lane change probability determination step and the fourth lane change probability determination step are all performed, then predicting the target vehicle behavior according to at least one of the first probability, the second probability, the third probability and the fourth probability includes: Calculate a third average value according to the first probability, the second probability, the third probability and the fourth probability; The target vehicle behavior is predicted according to the third average value.

3. The target vehicle behavior prediction method according to claim 1, characterized in that: The determining, according to the lateral distance between the target vehicle and the vehicle in the historical frame, a third probability of the target vehicle changing lanes comprises: A third probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the ego vehicle, and the corresponding accumulated generalized probability distribution.

4. The target vehicle behavior prediction method according to claim 1, characterized in that: The determining, based on the lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame, a fourth probability of the target vehicle changing lanes includes: A fourth probability of the target vehicle changing lanes is determined according to the position of the target vehicle in at least two historical frames, the change in the lateral distance between the target vehicle and the center line of the lane where the vehicle is located, and the corresponding cumulative generalized probability distribution.

5. The target vehicle behavior prediction method according to claim 1, characterized in that: The determining, according to the lateral distance between the target vehicle and the vehicle, a first probability of the target vehicle changing lanes comprises: According to the positional relationship and lateral distance between the target vehicle and the self-vehicle, the lane change phase of the target vehicle is determined; A first probability is determined according to the lane change phase of the target vehicle.

6. The target vehicle behavior prediction method according to claim 5, characterized in that: The lane change phase includes: an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the left adjacent lane to the own lane, and an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the own lane to the left adjacent lane; The determining of the first probability according to the lane change phase of the target vehicle includes: If the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; If the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, a first probability is determined according to the first parameter, the second parameter, the third parameter, and the lateral distance between the target vehicle and the own vehicle; If the target vehicle is in the completion phase of changing lanes from the left adjacent lane to the own lane, the first probability is zero; If the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; If the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, a first probability is determined according to the fourth parameter, the fifth parameter, the sixth parameter, and the lateral distance between the target vehicle and the own vehicle; If the target vehicle is in the completion phase of changing lanes from the vehicle's own lane to the left adjacent lane, the first probability is zero.

7. The target vehicle behavior prediction method according to claim 5, characterized in that: The lane change phase includes: an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the right adjacent lane to the own lane, and an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the own lane to the right adjacent lane; The determining of the first probability according to the lane change phase of the target vehicle includes: If the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; If the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane, a first probability is determined according to the seventh parameter, the eighth parameter, the ninth parameter, and the lateral distance between the target vehicle and the own vehicle; If the target vehicle is in the completion phase of changing lanes from the right adjacent lane to the own lane, the first probability is zero; If the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, a first probability is determined according to the lateral distance between the target vehicle and the own vehicle and the cumulative generalized probability distribution based on the lateral distance from the target vehicle to the own vehicle; If the target vehicle is in the middle stage of changing lanes from the ego lane to the right adjacent lane, a first probability is determined according to the tenth parameter, the eleventh parameter, the twelfth parameter, and the lateral distance between the target vehicle and the ego vehicle; If the target vehicle is in the completion phase of changing lanes from its own lane to the right adjacent lane, the first probability is zero.

8. The target vehicle behavior prediction method according to claim 1, characterized in that: Determining the second probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the center line of the lane where the vehicle is located includes: According to the azimuth relationship between the target vehicle and the ego vehicle and the lateral distance between the target vehicle and the center line of the lane where the ego vehicle is located, the lane change stage of the target vehicle is determined; The second probability is determined according to the lane change phase of the target vehicle.

9. The target vehicle behavior prediction method according to claim 8, characterized in that: The lane change phase includes: an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the left adjacent lane to the own lane, and an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the own lane to the left adjacent lane; The determining the second probability according to the lane change phase of the target vehicle includes: If the target vehicle is in the initial stage of changing lanes from the left adjacent lane to the own lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the middle stage of changing lanes from the left adjacent lane to the own lane, the second probability is determined according to the thirteenth parameter, the fourteenth parameter, the fifteenth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the stage of completing the lane change from the left adjacent lane to the own lane, the second probability is zero; If the target vehicle is in the initial stage of changing lanes from the own lane to the left adjacent lane, a second probability is determined based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the middle stage of changing lanes from the own lane to the left adjacent lane, the second probability is determined according to the sixteenth parameter, the seventeenth parameter, the eighteenth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the completion phase of changing lanes from the target vehicle's own lane to the left adjacent lane, the second probability is zero.

10. The target vehicle behavior prediction method according to claim 8, characterized in that: The lane change phase includes: an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the right adjacent lane to the own lane, and an initial phase, an intermediate phase, and a completion phase of the target vehicle changing lanes from the own lane to the right adjacent lane; The determining the second probability according to the lane change phase of the target vehicle includes: If the target vehicle is in the initial stage of changing lanes from the right adjacent lane to the own lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the middle stage of changing lanes from the right adjacent lane to the own lane, the second probability is determined according to the nineteenth parameter, the twentieth parameter, the twenty-first parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the completion phase of changing lanes from the right adjacent lane to the own lane, the second probability is zero; If the target vehicle is in the initial stage of changing lanes from the own lane to the right adjacent lane, the second probability is determined according to the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located and the cumulative generalized probability distribution based on the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the middle stage of changing lanes from the own lane to the right adjacent lane, the second probability is determined according to the twenty-second parameter, the twenty-third parameter, the twenty-fourth parameter, and the lateral distance between the target vehicle and the center line of the lane where the own vehicle is located; If the target vehicle is in the completion phase of changing lanes from the target vehicle's own lane to the right adjacent lane, the second probability is zero.

11. A target vehicle behavior prediction device, characterized in that: include: An information acquisition module is used to obtain current lane type information; A lane change probability determination module is used to select and execute at least one of the following four steps according to the lane type information: A first lane change probability determination step: determining a first probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the own vehicle; A second lane change probability determination step: determining a second probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located; A third lane-changing probability determination step: determining a third probability of the target vehicle changing lanes according to the lateral distance between the target vehicle and the ego vehicle in the historical frame; A fourth lane change probability determination step: determining a fourth probability of the target vehicle changing lanes according to a lateral distance between the target vehicle and the center line of the lane where the vehicle is located in the historical frame; Behavior prediction module: predicts the behavior of the target vehicle according to at least one of the first probability, the second probability, the third probability and the fourth probability.

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 according to any one of claims 1 to 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 steps of the method according to any one of claims 1 to 10 are implemented.

Images