Following vehicle determination method and device, equipment and storage medium

Abstract

The invention discloses a following vehicle determination method, device and equipment and a storage medium, and the method comprises the steps: obtaining a center line of a lane where a current vehicle runs, and taking the center line as a reference line of a Frenet coordinate system, and building the Frenet coordinate system; determining predicted driving information of the obstacle vehicle under the Frenet coordinate system at the current moment based on historical driving information of the obstacle vehicle of the current vehicle at the previous moment; the current driving information of the obstacle vehicle at the current moment and the first lane changing probability of the obstacle vehicle at the previous moment are obtained; determining a second lane changing probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the predicted driving information, the current driving information and the first lane changing probability; and determining whether the obstacle vehicle is a following vehicle by using the second lane changing probability. Whether the obstacle vehicle is the following vehicle is predicted based on the driving information at the multiple moments in combination with the Gaussian distribution function, so that the accuracy of determining the following vehicle is relatively high.

Description

Technical Field

[0001] The present application belongs to the field of intelligent transportation technology, and in particular, relates to a method, device, equipment and storage medium for determining a following vehicle. Background Art

[0002] In scenarios where the road conditions are relatively simple and require long driving times, the current vehicle can turn on the automatic driving mode to appropriately free the driver's hands. For example, the current vehicle can turn on the automatic driving mode on the highway. In the automatic driving mode, the current vehicle detects the driving conditions of other vehicles around the current vehicle through the perception system. When it is detected that other vehicles may change lanes to the lane in front of the current vehicle, the current vehicle takes the other vehicles as the following target to avoid collision accidents. In the prior art, it is often predicted whether the other vehicles will change lanes to the current lane by detecting whether the lateral speed and heading angle of other vehicles meet a certain threshold. However, drivers with different styles control the lateral speed and heading angle of other vehicles during the lane change process differently, and when other vehicles deviate from the center line of the lane, the lateral speed and heading angle will also change. Therefore, the accuracy of determining whether other vehicles are going to change lanes to the current lane based solely on the lateral speed and heading angle of other vehicles at a certain moment is low. Other vehicles that need to change lanes to the current lane are dangerous vehicles for the current vehicle and may collide with the current vehicle, or the obstacle vehicle may also collide with the current vehicle after slowing down or braking after changing lanes to the lane where the current vehicle is located. Therefore, the other vehicles need to be regarded as following vehicles followed by the current vehicle, and the accuracy of determining the following vehicles through the solutions in the relevant technology is low. Summary of the invention

[0003] The embodiment of the present application provides an implementation scheme different from the prior art to solve the technical problem of low accuracy in determining a following vehicle.

[0004] In a first aspect, the present application provides a method for determining a following vehicle, comprising: obtaining a center line of a lane in which a current vehicle is traveling, and establishing the Frenet coordinate system with the center line as a reference line of the Frenet coordinate system; determining predicted driving information of the obstacle vehicle at the current moment in the Frenet coordinate system based on historical driving information of an obstacle vehicle of the current vehicle at a previous moment; obtaining current driving information of the obstacle vehicle at the current moment and a first lane change probability of the obstacle vehicle at the previous moment; determining a second lane change probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability; and determining whether the obstacle vehicle is a following vehicle using the second lane change probability.

[0005] In a second aspect, the present application provides a following vehicle determination device, comprising: an acquisition unit, used to acquire the center line of the lane in which the current vehicle is traveling, and establish the Frenet coordinate system with the center line as the reference line of the Frenet coordinate system; a determination unit, used to determine the predicted driving information of the obstacle vehicle in the Frenet coordinate system at the current moment based on the historical driving information of the obstacle vehicle of the current vehicle at the previous moment; the acquisition unit is also used to acquire the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment; the determination unit is also used to determine the second lane change probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability; the determination unit is also used to determine whether the obstacle vehicle is a following vehicle using the second lane change probability.

[0006] In a third aspect, the present application provides an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any method in the first aspect or any possible implementation manner of the first aspect by executing the executable instructions.

[0007] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the computer program implements any method in the first aspect or any possible implementation manner of the first aspect.

[0008] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in the first aspect or any possible implementation manner of the first aspect.

[0009] The present application provides a method for obtaining the center line of the lane in which the current vehicle is traveling, establishing the Frenet coordinate system with the center line as the reference line of the Frenet coordinate system; determining the predicted driving information of the obstacle vehicle at the current moment in the Frenet coordinate system based on the historical driving information of the obstacle vehicle of the current vehicle at the previous moment; obtaining the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment; determining the second lane change probability of the obstacle vehicle at the current moment based on the Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability; and determining whether the obstacle vehicle is a following vehicle using the second lane change probability. Based on the driving information at multiple moments and combined with the Gaussian distribution function, predicting whether the obstacle vehicle is a following vehicle makes the accuracy of determining the following vehicle higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0011] Figure 1 A schematic diagram of a flow chart of a method for determining a following vehicle provided in an embodiment of the present application;

[0012] Figure 2 A structural schematic diagram of a probability deviation interval correspondence relationship is provided for an embodiment of the present application;

[0013] Figure 3 A schematic diagram of another structure of a probability deviation interval correspondence relationship provided in an embodiment of the present application;

[0014] Figure 4 A schematic diagram of the structure of a following vehicle determination device provided in one embodiment of the present application;

[0015] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, but cannot be understood as limiting the present application.

[0017] The terms "first" and "second" etc. in the specification, claims and drawings of the embodiments of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein, for example. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, the process, method, system, product or equipment comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0018] Therefore, the accuracy of determining whether another vehicle is going to change lanes to the current lane based solely on the lateral speed and heading angle of another vehicle at a certain moment is low. For the current vehicle, another vehicle that needs to change lanes to the current lane is a dangerous vehicle that may collide with the current vehicle, or an obstacle vehicle that decelerates or brakes after changing lanes to the lane where the current vehicle is located may also collide with the current vehicle. Therefore, the other vehicle needs to be regarded as a following vehicle followed by the current vehicle. The accuracy of determining the following vehicle through the solution in the related art is low.

[0019] In the case of simple road conditions and long-term driving, the current vehicle can turn on the automatic driving mode to appropriately free the driver's hands. For example, the current vehicle can turn on the automatic driving mode on the highway. The automatic driving system of the current vehicle can detect the lane lines and surrounding obstacles through the perception system, and keep the vehicle in the lane by controlling the steering system. At the same time, according to the target speed and following time distance set by the driver, the current vehicle driving and braking system are controlled to make the current vehicle follow the front vehicle at a certain speed or keep a safe distance, thereby improving the comfort and safety of the driver. During the driving process of the current vehicle, other vehicles in adjacent lanes often cut into the front of the lane. In order to ensure that the current vehicle can drive safely, the current vehicle detects the driving conditions of other vehicles around the current vehicle through the perception system in the automatic driving mode. When it is detected that other vehicles may change lanes to the front of the lane where the current vehicle is driving, the current vehicle takes the other vehicles as the following target to avoid collision accidents. In the prior art, it is often predicted whether the other vehicles will change lanes to the current lane by detecting whether the lateral speed and heading angle of other vehicles meet a certain threshold. However, drivers with different styles control the lateral speed and heading angle of other vehicles during the lane change process differently, and other vehicles will also experience changes in lateral speed and heading angle when they deviate from the center line of the lane. If the accuracy of determining whether other vehicles are going to change lanes to the current lane is based only on a certain threshold and the lateral speed and heading angle at a certain moment, it is low, and other vehicles that need to change lanes to the current lane are dangerous vehicles that may collide with the current vehicle, or they may collide with the current vehicle if the obstacle vehicle decelerates or brakes after changing lanes to the lane where the current vehicle is located. Therefore, it is necessary to treat the other vehicles as the following vehicles followed by the current vehicle, and the accuracy of determining the following vehicles through the solutions in the related art is low.

[0020] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0021] Figure 1 A flowchart of a method for determining a following vehicle is provided for an exemplary embodiment of the present application. The execution subject of the method may be a server, wherein the server may be a cloud server or a vehicle-mounted server. The method at least includes the following steps S101-S105:

[0022] S101, obtaining the center line of the lane on which the current vehicle is traveling, and establishing the Frenet coordinate system using the center line as a reference line of the Frenet coordinate system;

[0023] Optionally, the center line of the lane may be a straight line or a curve. For relevant explanations of the Frenet coordinate system, please refer to the prior art.

[0024] S102, determining predicted driving information of the obstacle vehicle at the current moment in the Frenet coordinate system based on historical driving information of the obstacle vehicle of the current vehicle at the previous moment;

[0025] Optionally, the obstacle vehicle refers to a vehicle whose distance from the current vehicle is within a preset distance range, that is, the obstacle vehicle is a vehicle in an adjacent lane that may pose a danger to the current vehicle.

[0026] Optionally, the historical driving information includes a historical lateral position and a historical lateral speed of the obstacle vehicle in a vertical direction of a tangent line of the center line.

[0027] Optionally, the predicted driving information includes a predicted lateral position and a predicted lateral speed of the obstacle vehicle in a vertical direction of a tangent to the center line.

[0028] Optionally, the method further comprises the following steps S1-S5:

[0029] S1. Acquire at least one vehicle to be analyzed that can be detected by the current vehicle in an adjacent lane of the lane in which the current vehicle is traveling;

[0030] S2, obtaining at least one first current position of the at least one vehicle to be analyzed;

[0031] Optionally, the first current position is a position in a Frenet coordinate system. The first current position includes a first longitudinal position of the vehicle to be analyzed in the centerline direction and a first lateral position in the perpendicular direction of the tangent of the centerline, wherein the centerline direction parallel to the current vehicle's driving direction is regarded as a positive direction, and the left direction perpendicular to the current vehicle's driving direction is regarded as a positive direction.

[0032] Optionally, the obtaining of at least one first current position of the at least one vehicle to be analyzed in the aforementioned S2 includes the following steps S20-S21:

[0033] S20, obtaining at least one third current position and at least one heading angle of the at least one vehicle to be analyzed in the Cartesian coordinate system at the current moment:

[0034] Optionally, the third current position includes the coordinates of the X-axis and the Y-axis in a Cartesian coordinate system.

[0035] Optionally, the heading angle refers to the angle between the forward direction of the vehicle to be analyzed and the geographic north.

[0036] S21. Determine at least one first current position of the at least one vehicle to be analyzed in the Frenet coordinate system based on the at least one third current position and the at least one heading angle.

[0037] S3, obtaining a second current position of the current vehicle in the Frenet coordinate system at the current moment;

[0038] Optionally, the second current position includes a second longitudinal position of the current vehicle in the direction of the center line and a second lateral position in a direction perpendicular to a tangent line of the center line.

[0039] S4. Determine an obstacle position interval based on the second current position and a preset distance;

[0040] Optionally, the preset distance includes a first longitudinal distance, a second longitudinal distance, a first lateral distance, and a second lateral distance. Specifically, the above-mentioned step S4 of determining the obstacle position interval based on the second current position and the preset distance includes the following steps S41-S45:

[0041] S41, obtaining a first sum of the second longitudinal position and the first longitudinal distance;

[0042] S42, obtaining a first difference between the second longitudinal position and the second longitudinal distance;

[0043] S43, obtaining a second sum of the second lateral position and the first lateral distance;

[0044] S44, obtaining a second difference between the second lateral position and the second lateral distance;

[0045] S45: Consider a first range interval that is not less than the first difference and not greater than the first sum and a second range interval that is not less than the second difference and not greater than the second sum as the obstacle position interval.

[0046] The first longitudinal distance and the second longitudinal distance may be the same or different, and the first lateral distance and the second lateral distance may be the same or different.

[0047] S5. Determine, among the at least one vehicle to be analyzed, a vehicle to be analyzed whose first current position is located in the obstacle position interval as an obstacle vehicle.

[0048] Optionally, if the first lateral position is located in the second range interval, and the first longitudinal position is located in the first range interval, the first current position is deemed to be located in the obstacle position interval.

[0049] S103, obtaining the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment;

[0050] Optionally, the current driving information includes a first lateral position and a first lateral speed of the obstacle vehicle in a perpendicular direction to a tangent line of a center line.

[0051] Optionally, the first lateral velocity is determined based on a velocity, a heading angle and a yaw rate of the obstacle vehicle in a Cartesian coordinate system.

[0052] Optionally, the value of 1 minus the first lane change probability is the first lane change probability. Specifically, if the first lane change probability is denoted as P k-1 (θ=lc), the first lane-invariant probability is denoted as P k-1 (θ=lk), then the value of 1 minus the first lane change probability is the first lane change probability, which can be expressed as the following formula:

[0053] P k-1 (θ=lk)=1-P k-1 (θ=lc)

[0054] Wherein, k is the current moment, k-1 is the moment before the current moment, θ is the vehicle's lane change intention, if θ=lk it means the vehicle does not change lanes, if θ=lc it means the vehicle changes lanes.

[0055] Optionally, the current driving information and the predicted driving information conform to a Gaussian distribution. Specifically, the current driving information can be regarded as a Gaussian distribution with the predicted driving information as the mean.

[0056] Specifically, if the obstacle vehicle is regarded as a lane change, the current driving information is regarded as a Gaussian distribution with the predicted driving information as the mean, which can be expressed as the following formula:

[0057] Current driving information = predicted driving information + N(0,W lc )

[0058] Among them, W lc is the covariance matrix corresponding to the lane change of the obstacle vehicle. The covariance matrix is ​​used to describe the distribution and correlation of the predicted lateral position and predicted lateral speed of the obstacle vehicle.

[0059] If the obstacle vehicle is considered as a non-changing lane, the current driving information is considered as a Gaussian distribution with the predicted driving information as the mean, which can be expressed as the following formula:

[0060] Current driving information = predicted driving information + N(0,W lk )

[0061] Among them, W lk is the covariance matrix corresponding to the obstacle vehicle's unchanged lane. The covariance matrix is ​​used to describe the distribution and correlation of the predicted lateral position and predicted lateral velocity of the obstacle vehicle.

[0062] Optionally, the method further includes: obtaining a vehicle type of the obstacle vehicle, and determining the covariance matrix based on the vehicle type, wherein the covariance matrices corresponding to different vehicle types may be the same or different, and may be specifically set according to actual needs.

[0063] S104, determining a second lane-changing probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane-changing probability;

[0064] Optionally, the determining of the second lane-changing probability of the obstacle vehicle at the current moment based on the Gaussian distribution function, the predicted driving information, the current driving information, and the first lane-changing probability in the aforementioned S104 includes the following steps S1041-S1043:

[0065] S1041, acquiring deviation driving information of the obstacle vehicle based on the predicted driving information and the current driving information;

[0066] Optionally, in the aforementioned S1041, obtaining the deviation driving information of the obstacle vehicle based on the predicted driving information and the current driving information includes the following steps S10411-S10213:

[0067] S10411, determining position deviation information of the obstacle vehicle based on the predicted lateral position in the predicted driving information and the first lateral position in the current driving information;

[0068] Optionally, in the aforementioned S10411, determining the position deviation information of the obstacle vehicle based on the predicted lateral position in the predicted driving information and the first lateral position in the current driving information includes: taking the difference between the first lateral position in the current driving information and the predicted lateral position in the predicted driving information as the position deviation information of the obstacle vehicle, which can be specifically expressed as the following formula:

[0069]

[0070] Among them, e1 is the position deviation information, is the first lateral position, To predict the lateral position.

[0071] S10412, determining speed deviation information of the obstacle vehicle based on the predicted lateral speed in the predicted driving information and the first lateral speed in the current driving information;

[0072] Optionally, in the aforementioned S10412, determining the speed deviation information of the obstacle vehicle based on the predicted lateral speed in the predicted driving information and the first lateral speed in the current driving information includes: taking the difference between the first lateral speed in the current driving information and the predicted lateral speed in the predicted driving information as the speed deviation information of the obstacle vehicle, which can be specifically expressed as the following formula:

[0073]

[0074] Among them, e2 is the position deviation speed, is the first lateral velocity, To predict the lateral velocity.

[0075] S10413. Use the position deviation information and the speed deviation information as the deviation driving information.

[0076] Optionally, if the lane change intention of the obstacle vehicle is regarded as a lane change, the deviation driving information is recorded as e k,lc When the e k,lc =(e1, e2); if the intention of the obstacle vehicle to change lanes is regarded as not changing lanes, the deviation driving information is recorded as e k,lk , the e k,lk =(e1, e2).

[0077] S1042, using the deviation driving information as an input of a Gaussian distribution function to obtain a probability density value;

[0078] Specifically, in the aforementioned S1042, the deviation driving information is used as the input of the Gaussian distribution function to obtain the probability density value, including the following steps S10421-S10422:

[0079] S10421. If the lane-changing intention of the obstacle vehicle is regarded as a lane-changing intention, the deviation driving information is used as an input of a Gaussian distribution function to obtain a probability density value, which can be expressed as the following formula:

[0080] Y lc =N(e k,lc ,0,W lc )

[0081] Among them, Y lc is the probability density value corresponding to the lane change of the obstacle vehicle, N(X, 0, W lc ) is the Gaussian distribution function, X is the input value of the Gaussian distribution function, e k,lc The deviation driving information corresponding to the lane change of the obstacle vehicle.

[0082] S10422. If the lane-changing intention of the obstacle vehicle is regarded as not changing lanes, the deviation driving information is used as the input of the Gaussian distribution function to obtain a probability density value, which can be expressed as the following formula:

[0083] Y lk =N(e k,lk ,0,W lk )

[0084] Among them, Y lk is the probability density value corresponding to the obstacle vehicle not changing lane, N(X, 0, W lc ) is the Gaussian distribution function, X is the input value of the Gaussian distribution function, e k,lk It is the deviation driving information corresponding to the vehicle not changing lane due to obstacles.

[0085] S1043. Determine a second lane-changing probability of the obstacle vehicle at the current moment based on the probability density value and the first lane-changing probability.

[0086] Specifically, the probability density value includes a probability density value corresponding to the obstacle vehicle not changing lanes and a probability density value corresponding to the obstacle vehicle changing lanes.

[0087] Optionally, in the aforementioned S1043, determining the second lane-changing probability of the obstacle vehicle at the current moment based on the probability density value and the first lane-changing probability can be expressed as the following formula:

[0088]

[0089] Among them, P k (θ=lc) is the second lane change probability at the current moment, Y lc is the probability density value corresponding to the obstacle vehicle changing lanes, Y lk is the probability density corresponding to the obstacle vehicle not changing lane, P k-1 (θ=lc) is the first lane change probability, P k-1 (θ=lk) is the first lane-changing probability.

[0090] S105: Determine whether the obstacle vehicle is a following vehicle by using the second lane change probability.

[0091] Optionally, the following vehicle refers to an obstacle vehicle that the current vehicle needs to follow.

[0092] Optionally, 1 minus the second lane change probability is the second lane non-changing probability of the obstacle vehicle.

[0093] It should be understood that if the second probability of the obstacle vehicle changing lanes and entering the lane is high, then even if the obstacle vehicle has not entered the lane at a time after the current time, the obstacle vehicle should be considered as the following vehicle of the current vehicle in advance. This is to avoid the obstacle vehicle suddenly entering the lane, and then taking corresponding deceleration or braking actions, which will affect the driver's comfort due to excessive deceleration, or even cause a rear-end collision due to insufficient deceleration, endangering the driver's life safety.

[0094] Optionally, the determining whether the obstacle vehicle is a following vehicle by using the second lane change probability in the aforementioned S105 includes the following steps S1051-S1052:

[0095] S1051. Determine a target deviation interval corresponding to the second lane change probability based on a correspondence between the second lane change probability and the probability deviation interval;

[0096] Optionally, the probability deviation interval correspondence relationship refers to the correspondence relationship between the second lane change probability and the deviation distance interval of the vehicle in the vertical direction of the tangent to the center line. Specifically, the probability deviation interval correspondence relationship can be represented by the second lane change probability and the deviation distance of the vehicle in the vertical direction of the tangent to the center line, and the deviation distance corresponding to the second lane change probability is obtained, and the interval that is not less than the negative deviation distance and not greater than the deviation distance is used as the target deviation interval.

[0097] For example, see Figure 2 , the horizontal coordinate P (θ = lc) is the second lane change probability, and the vertical coordinate l thres is the deviation distance in m (meter). The corresponding relationship of the probability deviation interval can be a linear relationship. When the second lane change probability is 0.85, the target deviation interval is not less than -2.4 and not more than 2.4.

[0098] For example, see Figure 3 , the horizontal coordinate P (θ = lc) is the second lane change probability, and the vertical coordinate l thres is the deviation distance in m (meter). The corresponding relationship of the probability deviation interval can also be a nonlinear relationship. When the second lane change probability is 0.6, the target deviation interval is not less than -2.4 and not more than 2.4.

[0099] The probability deviation interval correspondence relationship may be set according to actual needs, which is only taken as an example here.

[0100] Optionally, the method further comprises the following steps S01-S02:

[0101] S01. Obtain the vehicle type of the obstacle vehicle, wherein the vehicle type includes a large truck, a bus, a motorcycle, and a car;

[0102] S02. Determine the probability deviation interval correspondence based on the vehicle type.

[0103] Optionally, the corresponding relationship of probability deviation intervals corresponding to different vehicle types may be the same or different. It should be understood that vehicles of different vehicle types have different characteristics when changing lanes, and at the same lateral position, the probability of lane change of different vehicles is different. Therefore, in order to improve the accuracy of the determined target deviation interval, the corresponding relationship of probability deviation intervals corresponding to vehicle types may be set according to actual needs, so that the obtained target deviation interval is more vehicle-specific and more accurate.

[0104] S1052: Determine whether the obstacle vehicle is a following vehicle according to the current driving position in the current driving information and the target deviation interval.

[0105] Optionally, the current driving position is the aforementioned first lateral position, and if the first lateral position is located in the target deviation interval, the obstacle vehicle located at the current position is regarded as a following vehicle. The following vehicle is a vehicle that follows the current vehicle.

[0106] Optionally, the current driving information includes a current driving position and a current driving speed, and the method further includes the following steps S0001-S0003:

[0107] S0001. If the obstacle vehicle is a following vehicle, obtaining first driving information of the obstacle vehicle in the Frenet coordinate system and a first driving acceleration of the obstacle vehicle at the current moment, wherein the first driving information includes a first driving speed and a first driving position, wherein the current driving speed is a component speed of the first driving speed in a direction perpendicular to a tangent of the center line, and the current driving position is a component position of the first driving position in the vertical direction;

[0108] S0002. Acquire second driving information of the current vehicle in the Frenet coordinate system at a current moment and a second driving acceleration of the current vehicle, wherein the second driving information includes a second driving speed and a second driving position;

[0109] S0003. Determine a driving plan of the current vehicle based on the first driving information, the first driving acceleration, the second driving information, and the second driving acceleration, so that the current vehicle performs automatic driving based on the driving plan.

[0110] Optionally, the driving scheme refers to a speed curve and a longitudinal control scheme planned for the current vehicle. How to determine the driving scheme of the current vehicle based on the first driving information, the first driving acceleration, the second driving information and the second driving acceleration can be referred to in the prior art, and will not be described in detail here.

[0111] Optionally, the method further comprises the following steps S001-S005:

[0112] S001. When there is no historical driving information of the obstacle vehicle at the previous moment, obtaining preset initial driving information;

[0113] Optionally, the initial driving information includes an initial lateral position and an initial lateral speed of the obstacle vehicle in a vertical direction of the tangent of the center line. The initial position and initial speed can be set to 0 or to other values ​​according to actual needs, which will not be elaborated here.

[0114] S002. Obtain the vehicle type of the obstacle vehicle;

[0115] S003. Determine a third lane-changing probability of the obstacle vehicle based on the vehicle type;

[0116] Optionally, the third lane change probability corresponding to vehicles of different vehicle types may be the same or different. The third lane change probability may be set according to actual needs, for example, it may be 0.05, 0.1, 0.2 or other values, which are not specifically limited here.

[0117] S004. Determine a second lane-changing probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the initial driving information, the current driving information, and the third lane-changing probability;

[0118] Optionally, in the aforementioned S004, the method for determining the second lane change probability of the obstacle vehicle at the current moment based on the Gaussian distribution function, the initial driving information, the current driving information, and the third lane change probability is the same as the aforementioned S1041, specifically, the initial driving information is used as the predicted driving information in the aforementioned S1041, the initial lateral position in the initial driving information can be used as the predicted lateral position in the predicted driving information in the aforementioned S1041, and the initial lateral speed in the initial driving information can be used as the predicted lateral speed in the predicted driving information in the aforementioned S1041. For more details, please refer to the aforementioned description related to S1041, which will not be repeated here.

[0119] S005. Determine whether the obstacle vehicle is a following vehicle by using the second lane change probability.

[0120] In summary, the present application provides a method for obtaining the center line of the lane in which the current vehicle is traveling, establishing the Frenet coordinate system with the center line as the reference line of the Frenet coordinate system; determining the predicted driving information of the obstacle vehicle at the current moment in the Frenet coordinate system based on the historical driving information of the obstacle vehicle of the current vehicle at the previous moment; obtaining the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment; determining the second lane change probability of the obstacle vehicle at the current moment based on the Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability; and determining whether the obstacle vehicle is a following vehicle using the second lane change probability. Predicting whether the obstacle vehicle is a following vehicle based on driving information at multiple moments and in combination with the Gaussian distribution function makes it possible to determine the following vehicle with a higher accuracy.

[0121] Specifically, the actual driving information of the obstacle vehicle is regarded as a Gaussian distribution with the predicted driving state as the mean. The state of the obstacle vehicle is continuously observed in multiple frames, and the Gaussian distribution function is used to estimate the probability of the obstacle vehicle changing lanes and the probability of the obstacle vehicle not changing lanes. Then, based on the lane change probability, it is determined whether the obstacle vehicle is a following vehicle, and whether it is necessary to regard the obstacle vehicle as a vehicle followed by the current vehicle, so as to plan the speed and longitudinal control of the current vehicle to avoid vehicle collision accidents. The safety and comfort of the current vehicle in autonomous driving are effectively improved. This scheme sets the corresponding covariance matrix, the corresponding probability deviation interval correspondence and the corresponding third lane change probability according to different vehicle types, and determines the following vehicle in combination with historical driving information. The randomness caused by the styles of different drivers when changing lanes and the differences in vehicle types when changing lanes are fully considered, so that the accuracy of the determined following vehicle is high.

[0122] Figure 4 A schematic diagram of a structure of a following vehicle determination device provided for an exemplary embodiment of the present application; wherein the device comprises:

[0123] An acquisition unit 21 is used to acquire the center line of the lane where the current vehicle is traveling, and establish the Frenet coordinate system by taking the center line as a reference line of the Frenet coordinate system;

[0124] A determination unit 22, configured to determine predicted driving information of the obstacle vehicle at a current moment in the Frenet coordinate system based on historical driving information of the obstacle vehicle of the current vehicle at a previous moment;

[0125] The acquisition unit 21 is further configured to acquire the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment;

[0126] The determining unit 22 is further configured to determine a second lane changing probability of the obstacle vehicle at a current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane changing probability;

[0127] The determining unit 22 is further configured to determine whether the obstacle vehicle is a following vehicle by using the second lane change probability.

[0128] Optionally, when the device is used to determine whether the obstacle vehicle is a following vehicle using the second lane change probability, it is specifically used to: determine a target deviation interval corresponding to the second lane change probability based on the correspondence between the second lane change probability and the probability deviation interval; and determine whether the obstacle vehicle is a following vehicle based on the current driving position in the current driving information and the target deviation interval.

[0129] Optionally, the device is also used to: obtain the vehicle type of the obstacle vehicle, wherein the vehicle type includes a large truck, a bus, a motorcycle and a car; and determine the corresponding relationship of the probability deviation interval based on the vehicle type.

[0130] Optionally, the device is also used to: obtain preset initial driving information when there is no historical driving information of the obstacle vehicle at the previous moment; obtain the vehicle type of the obstacle vehicle; determine the third lane change probability of the obstacle vehicle based on the vehicle type; determine the second lane change probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the initial driving information, the current driving information, and the third lane change probability; and use the second lane change probability to determine whether the obstacle vehicle is a following vehicle.

[0131] Optionally, when the device is used to determine the second lane change probability of the obstacle vehicle at the current moment based on the Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability, it is specifically used to: obtain the deviation driving information of the obstacle vehicle based on the predicted driving information and the current driving information; use the deviation driving information as the input of the Gaussian distribution function to obtain a probability density value; and determine the second lane change probability of the obstacle vehicle at the current moment based on the probability density value and the first lane change probability.

[0132] Optionally, the device is also used to: obtain at least one vehicle to be analyzed that can be detected by the current vehicle in an adjacent lane of the lane in which the current vehicle is traveling; obtain at least one first current position of the at least one vehicle to be analyzed; obtain a second current position of the current vehicle in the Frenet coordinate system at the current moment; determine an obstacle position interval based on the second current position and a preset distance; and determine, among the at least one vehicle to be analyzed, a vehicle to be analyzed whose first current position is located in the obstacle position interval as an obstacle vehicle.

[0133] Optionally, the current driving information includes a current driving position and a current driving speed, and the device is also used to: if the obstacle vehicle is a following vehicle, obtain the first driving information of the obstacle vehicle in the Frenet coordinate system at the current moment and the first driving acceleration of the obstacle vehicle, the first driving information including the first driving speed and the first driving position, the current driving speed being the component speed of the first driving speed in the vertical direction of the tangent of the center line, and the current driving position being the component position of the first driving position in the vertical direction; obtain the second driving information of the current vehicle in the Frenet coordinate system at the current moment and the second driving acceleration of the current vehicle, the second driving information including the second driving speed and the second driving position; determine the driving plan of the current vehicle based on the first driving information, the first driving acceleration, the second driving information and the second driving acceleration, so that the current vehicle performs automatic driving based on the driving plan.

[0134] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, no further description is given here. Specifically, the device may perform the above method embodiment, and the above and other operations and / or functions of each module in the device are the corresponding processes in each method in the above method embodiment, respectively, and no further description is given here for the sake of brevity.

[0135] The above describes the device of the embodiment of the present application from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0136] Figure 5 is a schematic block diagram of an electronic device provided in an embodiment of the present application, and the electronic device may include:

[0137] The memory 301 and the processor 302, the memory 301 is used to store the computer program and transmit the program code to the processor 302. In other words, the processor 302 can call and run the computer program from the memory 301 to implement the method in the embodiment of the present application.

[0138] For example, the processor 302 may be configured to execute the above method embodiments according to instructions in the computer program.

[0139] In some embodiments of the present application, the processor 302 may include but is not limited to:

[0140] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0141] In some embodiments of the present application, the memory 301 includes but is not limited to:

[0142] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0143] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 301 and executed by the processor 302 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0144] like Figure 5 As shown, the electronic device may also include:

[0145] The transceiver 303 may be connected to the processor 302 or the memory 301 .

[0146] The processor 302 may control the transceiver 303 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 303 may include a transmitter and a receiver. The transceiver 303 may further include an antenna, and the number of antennas may be one or more.

[0147] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0148] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.

[0149] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.

[0150] Those of ordinary skill in the art will appreciate that the modules 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.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules 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 modules, which can be electrical, mechanical or other forms.

[0152] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0153] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for determining a following vehicle, characterized in that: include: Obtaining the center line of the lane in which the current vehicle is traveling, and establishing the Frenet coordinate system using the center line as a reference line of the Frenet coordinate system; Determine the predicted driving information of the obstacle vehicle at the current moment in the Frenet coordinate system based on the historical driving information of the obstacle vehicle of the current vehicle at the previous moment; Acquire current driving information of the obstacle vehicle at the current moment and a first lane change probability of the obstacle vehicle at the previous moment; Determining a second lane-changing probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane-changing probability; The second lane change probability is used to determine whether the obstacle vehicle is a following vehicle.

2. The method according to claim 1, characterized in that: The determining whether the obstacle vehicle is a following vehicle by using the second lane change probability includes: determining a target deviation interval corresponding to the second lane change probability based on a correspondence between the second lane change probability and the probability deviation interval; Whether the obstacle vehicle is a following vehicle is determined according to the current driving position in the current driving information and the target deviation interval.

3. The method according to claim 2, characterized in that The method further comprises: Obtaining the vehicle type of the obstacle vehicle, wherein the vehicle type includes a large truck, a bus, a motorcycle, and a car; The probability deviation interval correspondence is determined based on the vehicle type.

4. The method according to claim 1, characterized in that: The method further comprises: When there is no historical driving information of the obstacle vehicle at the previous moment, obtaining the preset initial driving information; Obtaining the vehicle type of the obstacle vehicle; determining a third lane change probability of the obstacle vehicle based on the vehicle type; Determining a second lane-changing probability of the obstacle vehicle at the current moment based on a Gaussian distribution function, the initial driving information, the current driving information, and the third lane-changing probability; The second lane change probability is used to determine whether the obstacle vehicle is a following vehicle.

5. The method according to claim 1, characterized in that The determining, based on the Gaussian distribution function, the predicted driving information, the current driving information, and the first lane change probability, of a second lane change probability of the obstacle vehicle at the current moment includes: Acquire the deviation driving information of the obstacle vehicle based on the predicted driving information and the current driving information; Using the deviation driving information as an input of a Gaussian distribution function to obtain a probability density value; A second lane-changing probability of the obstacle vehicle at a current moment is determined based on the probability density value and the first lane-changing probability.

6. The method according to claim 1, characterized in that The method further comprises: Acquire at least one vehicle to be analyzed that can be detected by the current vehicle in an adjacent lane of the lane in which the current vehicle is traveling; Acquiring at least one first current position of the at least one vehicle to be analyzed; Obtaining a second current position of the current vehicle in the Frenet coordinate system at the current moment; determining an obstacle position interval based on the second current position and a preset distance; Among the at least one vehicle to be analyzed, a vehicle to be analyzed whose first current position is located in the obstacle position interval is determined as an obstacle vehicle.

7. The method according to claim 1, characterized in that The current driving information includes the current driving position and the current driving speed. The method further includes: If the obstacle vehicle is a following vehicle, first driving information of the obstacle vehicle in the Frenet coordinate system at the current moment and a first driving acceleration of the obstacle vehicle are obtained, wherein the first driving information includes a first driving speed and a first driving position, the current driving speed is a component speed of the first driving speed in a vertical direction of a tangent to the center line, and the current driving position is a component position of the first driving position in the vertical direction; Acquire second driving information of the current vehicle in the Frenet coordinate system at a current moment and a second driving acceleration of the current vehicle, wherein the second driving information includes a second driving speed and a second driving position; A driving plan of the current vehicle is determined based on the first driving information, the first driving acceleration, the second driving information, and the second driving acceleration, so that the current vehicle performs automatic driving based on the driving plan.

8. A following vehicle determination device, characterized in that: include: An acquisition unit, used for acquiring a center line of a lane on which the vehicle is currently traveling, and establishing the Frenet coordinate system by taking the center line as a reference line of the Frenet coordinate system; A determination unit, configured to determine predicted driving information of the obstacle vehicle at a current moment in the Frenet coordinate system based on historical driving information of the obstacle vehicle of the current vehicle at a previous moment; The acquisition unit is further used to acquire the current driving information of the obstacle vehicle at the current moment and the first lane change probability of the obstacle vehicle at the previous moment; The determining unit is further configured to determine a second lane changing probability of the obstacle vehicle at a current moment based on a Gaussian distribution function, the predicted driving information, the current driving information, and the first lane changing probability; The determining unit is further configured to determine whether the obstacle vehicle is a following vehicle by using the second lane change probability.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 7 by executing the executable instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images