Adjacent vehicle longitudinal intention prediction method and device, vehicle and readable storage medium

Abstract

The invention provides an adjacent vehicle longitudinal intention prediction method and device, a vehicle and a readable storage medium, and the method comprises the steps: obtaining a first driving state of a current vehicle in a lane changing process; determining a target judgment condition corresponding to the first driving state; determining an adjacent vehicle corresponding to the current vehicle in the lane changing process; acquiring a second driving state of the adjacent vehicle, and determining a longitudinal state value corresponding to the adjacent vehicle according to the second driving state and a target judgment condition; a longitudinal intent of the adjacent vehicle is determined from the longitudinal state value. The target judgment condition is determined on the basis of the first driving state of the current vehicle, so that the requirement for the state of the adjacent vehicle during lane changing can be determined on the basis of the state of the current vehicle, the longitudinal intention of the adjacent vehicle can be accurately determined on the basis of the target judgment condition, and possible actions of a rear target can be considered; and intelligent lane changing based on the longitudinal intention can be accurately completed.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a method, device, vehicle and readable storage medium for predicting the longitudinal intention of a neighboring vehicle. Background Art

[0002] In the field of autonomous driving, intelligent lane changing is an important implementation scenario for lateral control planning. In the current mass-produced lateral control solutions, traditional rule-based processing still occupies an important position. In the scenario of lateral lane change, the traditional processing method mainly calibrates the distance and speed from the target behind the destination lane to the vehicle, and then uses a table lookup to calculate whether the lane change can be performed. However, during the lane change process, the state of the vehicle and the target behind may change, and the existing technology is only based on the distance and speed calibration method. It is unable to consider the impact of the action to be performed by the target behind on the vehicle, and therefore, it may cause accidents when changing lanes. Summary of the invention

[0003] The main purpose of the present invention is to propose a method, device, vehicle and readable storage medium for predicting the longitudinal intention of a neighboring vehicle, aiming to solve the problem that the lane changing method in the prior art cannot consider the impact of the action to be performed by the rear target on the vehicle.

[0004] To achieve the above object, the present invention provides a method for predicting the longitudinal intention of a neighboring vehicle, the method comprising:

[0005] During the lane change process, obtaining a first driving state of the current vehicle;

[0006] determining a target judgment condition corresponding to the first driving state;

[0007] Determining an adjacent vehicle corresponding to the current vehicle during a lane change process;

[0008] Acquiring a second driving state of the neighboring vehicle, and determining a longitudinal state value corresponding to the neighboring vehicle according to the second driving state and the target judgment condition;

[0009] A longitudinal intention of the neighboring vehicle is determined based on the longitudinal state value.

[0010] Optionally, the target judgment condition includes a target judgment threshold, and the determining of the target judgment condition corresponding to the first driving state includes:

[0011] Acquiring a positional relationship between the current vehicle and a marking of a target lane change lane;

[0012] determining a first condition weight corresponding to the position relationship, wherein a lane change completion degree corresponding to the position relationship is positively correlated with the first condition weight;

[0013] Acquire the current driving speed of the vehicle, and determine a second condition weight corresponding to the driving speed, wherein the driving speed is positively correlated with the second condition weight;

[0014] An initial judgment threshold is obtained, and the product of the initial judgment threshold, the first condition weight, and the second condition weight is used as the target judgment threshold.

[0015] Optionally, determining the longitudinal state value corresponding to the adjacent vehicle according to the second driving state and the target judgment condition includes:

[0016] Acquiring a target judgment threshold in the target judgment condition, wherein the target judgment threshold includes a speed judgment threshold and a collision time judgment threshold;

[0017] determining a speed state value according to the speed judgment threshold and the second driving state;

[0018] determining a collision time state value according to the collision time judgment threshold and the second driving state;

[0019] The longitudinal state value is obtained based on the speed state value and the collision time state value.

[0020] Optionally, determining the speed state value according to the speed judgment threshold and the second driving state includes:

[0021] Determine the relative speed, relative distance, and acceleration / deceleration direction between the current vehicle and the neighboring vehicle according to the second driving state;

[0022] Calculating a target deceleration of the neighboring vehicle according to the relative speed, the relative distance, and the acceleration / deceleration direction;

[0023] Determining whether the absolute value of the target deceleration is greater than the speed determination threshold;

[0024] If the absolute value of the target deceleration is greater than the speed judgment threshold, the speed state value is determined to be a maximum state value and a minimum state value according to the acceleration and deceleration direction;

[0025] If the absolute value of the target deceleration is less than or equal to the speed judgment threshold, the speed state value is calculated according to the target deceleration and the speed judgment threshold.

[0026] Optionally, determining the collision time state value according to the collision time judgment threshold and the second driving state includes:

[0027] Determine the relative speed and relative distance between the current vehicle and the adjacent vehicle according to the second driving state;

[0028] Determining a target collision time between the current vehicle and the adjacent vehicle according to the relative speed and the relative distance;

[0029] Determining whether the target collision time is greater than the collision time determination threshold;

[0030] If the target collision time is greater than the collision time judgment threshold, a preset dangerous collision time threshold is obtained, and the collision time state value is calculated according to the relative speed, the relative distance, the preset dangerous collision time threshold and the collision time judgment threshold;

[0031] If the target collision time is less than or equal to the collision time judgment threshold, the collision time state value is determined to be a maximum state value.

[0032] Optionally, obtaining the longitudinal state value based on the speed state value and the collision time state value comprises:

[0033] determining a relative speed and a relative distance between the current vehicle and the neighboring vehicle according to the second driving state;

[0034] Determine a collision time weight corresponding to the relative speed and relative distance, and determine a speed weight corresponding to the collision time weight, wherein the sum of the collision time weight and the speed weight is 1;

[0035] The speed state value is associated with the speed weight, the collision time state value is associated with the collision time weight, and a weighted average calculation is performed to obtain the longitudinal state value.

[0036] Optionally, determining the longitudinal intention of the neighboring vehicle according to the longitudinal state value comprises:

[0037] Acquire a plurality of longitudinal state values ​​detected within a current time window;

[0038] Determine a state weight corresponding to each of the longitudinal state values, wherein a time difference between a collection time corresponding to the longitudinal state value and a current time is negatively correlated with the state weight;

[0039] The longitudinal state value is weighted averaged based on the corresponding state weight to obtain a final state value corresponding to the longitudinal intention.

[0040] To achieve the above object, the present invention further provides a device for predicting the longitudinal intention of a neighboring vehicle, the device comprising:

[0041] A first acquisition module, used for acquiring a first driving state of the current vehicle during a lane change process;

[0042] A first determination module, used to determine a target judgment condition corresponding to the first driving state;

[0043] A second determination module is used to determine an adjacent vehicle corresponding to the current vehicle during the lane change process;

[0044] A second acquisition module, used for acquiring a second driving state of the adjacent vehicle, and determining a longitudinal state value corresponding to the adjacent vehicle according to the second driving state and the target judgment condition;

[0045] The third determination module is configured to determine the longitudinal intention of the neighboring vehicle according to the longitudinal state value.

[0046] To achieve the above objectives, the present invention also provides a vehicle, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method for predicting the longitudinal intention of a neighboring vehicle as described above.

[0047] To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for predicting the longitudinal intention of a neighboring vehicle as described above are implemented.

[0048] The present invention proposes a method, device, vehicle and readable storage medium for predicting the longitudinal intention of an adjacent vehicle. During a lane change, the first driving state of the current vehicle is obtained; a target judgment condition corresponding to the first driving state is determined; the adjacent vehicle corresponding to the current vehicle during the lane change is determined; the second driving state of the adjacent vehicle is obtained, and the longitudinal state value corresponding to the adjacent vehicle is determined according to the second driving state and the target judgment condition; the longitudinal intention of the adjacent vehicle is determined according to the longitudinal state value. By determining the target judgment condition based on the first driving state of the current vehicle, the requirements for the state of the adjacent vehicle when changing lanes can be determined based on the state of the current vehicle, and then the longitudinal intention of the adjacent vehicle can be accurately determined based on the target judgment condition, so that the possible actions of the rear target can be considered, and then the intelligent lane change based on the longitudinal intention can be accurately completed. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0051] Figure 1 A schematic flow chart of a first embodiment of a method for predicting longitudinal intention of a neighboring vehicle according to the present invention;

[0052] Figure 2 It is an overall flow chart of the method for predicting the longitudinal intention of neighboring vehicles of the present invention;

[0053] Figure 3 A schematic diagram of the stages of a lane changing process in the method for predicting the longitudinal intention of a neighboring vehicle of the present invention;

[0054] Figure 4 It is a module structure diagram of the device for predicting the longitudinal intention of neighboring vehicles of the present invention;

[0055] Figure 5 It is a schematic diagram of the module structure of the vehicle of the present invention. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only embodiments of a part of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present application.

[0057] The present invention provides a method for predicting the longitudinal intention of adjacent vehicles, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a method for predicting the longitudinal intention of a neighboring vehicle according to the present invention. The method comprises the following steps:

[0058] Step S10, during the lane change process, obtaining a first driving state of the current vehicle;

[0059] In autonomous driving, some scenarios require the vehicle to change lanes; when the vehicle changes lanes, the current vehicle needs to take into account the driving status of adjacent vehicles; adjacent vehicles are vehicles that may affect the lane change of the current vehicle, or may be affected by the lane change of the current vehicle; targets can be screened mainly based on the relationship between the vehicle and the target lane and the distance information relative to the current vehicle; such as vehicles behind the current vehicle, vehicles in the target lane for lane change, and vehicles about to enter the target lane for lane change; adjacent vehicles will also move due to the driving status of the current vehicle, thereby affecting each other; therefore, in this embodiment, a first driving state reflecting the current vehicle state is obtained.

[0060] The first driving state is the real-time driving state of the current vehicle; it can be understood that the first driving state indicates relevant parameters of the current vehicle that have an impact on lane changing.

[0061] Step S20, determining a target judgment condition corresponding to the first driving state;

[0062] The target judgment condition is a parameter used to indicate the critical state of the second driving state in the longitudinal intention calculation; it can be understood that when the driving state of the current vehicle is different, the requirements for the driving state of the adjacent vehicle during the lane change process are also different; therefore, in this embodiment, the target judgment condition is set based on the first driving state, so that the target judgment condition can match the actual lane change needs.

[0063] Step S30, determining an adjacent vehicle corresponding to the current vehicle during the lane change process;

[0064] The specific identification method of neighboring vehicles can be set based on actual needs; it can be understood that the number of neighboring vehicles can be 0 or more. When the number is 0, the lane change can be performed without considering the neighboring vehicles. When the number of neighboring vehicles is one or more, subsequent steps are performed for each neighboring vehicle to determine the longitudinal intention of each neighboring vehicle.

[0065] Step S40, acquiring a second driving state of the neighboring vehicle, and determining a longitudinal state value corresponding to the neighboring vehicle according to the second driving state and the target judgment condition;

[0066] The second driving state is the real-time driving state of the neighboring vehicle; it can be understood that the second driving state indicates relevant parameters of the neighboring vehicle that have an impact on the lane change.

[0067] The longitudinal state value is used to indicate the longitudinal intention of neighboring vehicles.

[0068] In this embodiment, the larger the longitudinal state value, the stronger the longitudinal intention of the adjacent vehicle. It can be understood that the target judgment condition indicates the state requirement of the current vehicle for the adjacent vehicle, and the second driving state indicates the actual driving state of the adjacent vehicle. Therefore, the target judgment condition and the second driving state can be used to determine whether the adjacent vehicle will affect the lane change of the current vehicle, that is, to determine the longitudinal state value of the adjacent vehicle.

[0069] Step S50: determining the longitudinal intention of the neighboring vehicle according to the longitudinal state value.

[0070] Longitudinal intention refers to the intention of the neighboring vehicle to continue driving in the current direction. It is understandable that when the neighboring vehicle is behind the current vehicle, especially in the target lane of the lane change, if the longitudinal intention of the neighboring vehicle is too strong, it is easy to affect the lane change of the current vehicle. Therefore, the current vehicle needs to pay more attention when changing lanes, or avoid it. If the longitudinal intention of the neighboring vehicle is weak, it is not easy to affect the lane change of the current vehicle. Therefore, the current vehicle can complete the lane change based on its own driving needs when changing lanes. Therefore, after the longitudinal intention is determined, the current vehicle can be more aware of whether it will be affected by the neighboring vehicle when changing lanes, so as to implement a more robust lane change strategy.

[0071] This embodiment determines the target judgment condition based on the first driving state of the current vehicle, so that the requirement for the state of the adjacent vehicle when changing lanes can be determined based on the state of the current vehicle, and then the longitudinal intention of the adjacent vehicle can be accurately determined based on the target judgment condition, so that the possible actions of the rear target can be considered, and the intelligent lane change based on the longitudinal intention can be accurately completed.

[0072] Further, see also Figure 2 In the second embodiment of the method for predicting the longitudinal intention of a neighboring vehicle of the present invention proposed based on the first embodiment of the present invention, the target judgment condition includes a target judgment threshold, and the step S20 includes the steps of:

[0073] Step S21, obtaining a positional relationship between the current vehicle and a marking line of a target lane change lane;

[0074] Step S22, determining a first condition weight corresponding to the position relationship, wherein the lane change completion degree corresponding to the position relationship is positively correlated with the first condition weight;

[0075] Step S23, obtaining the current driving speed of the vehicle, and determining a second condition weight corresponding to the driving speed, wherein the driving speed is positively correlated with the second condition weight;

[0076] Step S24, obtaining an initial judgment threshold, and taking the product of the initial judgment threshold, the first condition weight, and the second condition weight as the target judgment threshold.

[0077] The lane change process can be divided into different stages based on driving characteristics, such as the lighting stage, the lane change execution stage, and the lane change completion stage. In this embodiment, the specific stage division is based on the positional relationship between the current vehicle and the target lane change lane. It can be understood that the target lane change lane is the lane to be reached after the lane change is completed, and the marking line of the target lane change lane is the marking line between the lane where the current vehicle is before the lane change and the target lane change lane. See Figure 3 ;

[0078] Stage 1: The current vehicle turns on the turn signal until it hits the line marking. At this time, the position relationship between the current vehicle and the line marking is not in contact;

[0079] Phase 2: The current vehicle presses against the line marking and changes sideways until the lane change is completed. At this time, the position relationship between the current vehicle and the line marking is in contact, and the vehicle changes sideways;

[0080] Stage 3: The current vehicle is driving along the line marking. At this time, the position relationship between the current vehicle and the line marking is maintained near the critical point of contact;

[0081] Stage 4: The current vehicle is traveling on the marking line. At this time, the position relationship between the current vehicle and the marking line is in contact, and the vehicle does not move laterally.

[0082] It should be noted that stages 2, 3, and 4 do not occur continuously. For example, when a lateral change is made after crossing the line in stage 2, if the lateral change is stopped, it will be converted to stage 4. On the basis of stage 4, when the lateral change is restarted, it will be converted to stage 2. For example, when a lateral change is made from stage 1, if the lateral change is stopped when the position of touching the line is reached, it will be converted to stage 3. On the basis of stage 3, if the lateral change to the target lane is restarted, it will be converted to stage 2.

[0083] It can be understood that stage 1 is the start-up stage of lane change. In this stage, the vehicle still maintains the lane before lane change, which is mainly used to play the role of adjacent vehicles. Stage 2 is the stage of formally executing lane change, and lateral changes are made to achieve lane change. Stages 3 and 4 are waiting stages in the process of lane change. It can be understood that in the process of lane change, adjacent vehicles may slow down to avoid the current vehicle, or may accelerate to overtake the current vehicle. Therefore, in actual lane change, it is often necessary to observe the status of adjacent vehicles. At the same time, adjacent vehicles will also determine their driving status based on the specific lane change stage of the current vehicle. For example, in stages 1 and 3, the current vehicle is still driving. When driving in the lane before changing lanes, the neighboring vehicles are more likely to accelerate and overtake, while in stages 2 and 4, the current vehicle has partially reached the target lane-changing vehicle, and the neighboring vehicles generally will not accelerate and overtake; therefore, in this embodiment, the first condition weight is determined based on the positional relationship between the current vehicle and the marking, that is, the specific stage of the current vehicle, so that the interaction relationship between the current vehicle and the neighboring vehicles can be introduced into the setting of the target judgment threshold, so that the target judgment threshold can accurately reflect the specific lane-changing scenario; the specific value of the first condition weight can be set based on actual needs, and the value range of the first condition weight is [0, 1].

[0084] It can be understood that the completion degree of stages 1, 3, 4, and 2 in the lane change process increases successively, and from the above description, it can be seen that the possibility of being overtaken by adjacent vehicles at stages 1 and 3 is higher. Relatively speaking, since stage 3 has begun to approach the target lane for lane change, stage 1 is more likely to be overtaken by adjacent vehicles at stage 3, and stage 2 is in continuous lateral change, so stage 4 is more likely to be overtaken by adjacent vehicles at stage 2. Therefore, in this embodiment, the lane change completion degree corresponding to the position relationship is positively correlated with the first condition weight; in other embodiments, the first condition weights corresponding to different stages can also be specifically set, such as setting stage 1 and stage 3 to the same smaller first condition weight, and setting stage 2 and stage 4 to the same larger first condition weight.

[0085] It can be understood that during the lane change process, the faster the current vehicle's speed is, the less likely the adjacent vehicle is to accelerate and overtake. Therefore, in this embodiment, the driving speed is set to be positively correlated with the second condition weight; by introducing the second condition weight, the target judgment threshold can accurately reflect the specific state of the current vehicle; when setting the second condition weight, the current vehicle's driving speed can be divided into intervals, each interval corresponds to a second condition weight, and after the current vehicle's driving speed is determined, the corresponding second condition weight can be determined by interval matching; the specific value of the second condition weight can be set based on actual needs, and the value range of the second condition weight is [0, 1].

[0086] After the first condition weight and the second condition weight are determined, a target judgment threshold corresponding to a specific lane change scenario can be determined based on the first condition weight and the second condition weight.

[0087] Specifically, the initial judgment threshold may include a speed judgment threshold and a collision time judgment threshold; the speed judgment threshold is used to determine the speed state value, and the collision time judgment threshold is used to determine the collision time state value.

[0088] Specifically, the speed judgment threshold thre a have:

[0089] thre a =Thre a ×W c ×W e

[0090] Among them, Thr a is the initial judgment threshold corresponding to the speed judgment threshold; W c is the first condition weight, W e is the weight of the second condition;

[0091] Collision time judgment threshold thre ttc have:

[0092] thre ttc =Thre ttc ×W c ×W e

[0093] Among them, Thr ttc is the initial judgment threshold corresponding to the collision time judgment threshold.

[0094] Further, in a third embodiment of the method for predicting the longitudinal intention of a neighboring vehicle of the present invention proposed based on the first embodiment of the present invention, step S40 includes the steps of:

[0095] Step S41, obtaining a target judgment threshold in the target judgment condition, wherein the target judgment threshold includes a speed judgment threshold and a collision time judgment threshold;

[0096] Step S42, determining a speed state value according to the speed judgment threshold and the second driving state;

[0097] The speed state value is used to indicate the longitudinal intention of the neighboring vehicle at the speed level;

[0098] Furthermore, the step S42 includes the steps of:

[0099] Step S421, determining the relative speed, relative distance, and acceleration / deceleration direction between the current vehicle and the adjacent vehicle according to the second driving state;

[0100] Step S422, calculating the target deceleration of the neighboring vehicle according to the relative speed, the relative distance and the acceleration / deceleration direction;

[0101] Step S423, determining whether the absolute value of the target deceleration is greater than the speed determination threshold;

[0102] Step S424, if the absolute value of the target deceleration is greater than the speed judgment threshold, determining the speed state value as a maximum state value and a minimum state value according to the acceleration and deceleration direction;

[0103] Step S425: If the absolute value of the target deceleration is less than or equal to the speed judgment threshold, the speed state value is calculated according to the target deceleration and the speed judgment threshold.

[0104] The relative speed and acceleration / deceleration direction can be determined by comparing the speed of the current vehicle with that of adjacent vehicles, and the relative distance can be determined by performing distance detection between the current vehicle and adjacent vehicles.

[0105] The target deceleration is the minimum deceleration of the neighboring vehicle at the current state to stop without colliding with the current vehicle; specifically, the target deceleration a' is:

[0106]

[0107] Among them, rel vel is the relative speed; rel posx is the relative distance; sign is the acceleration and deceleration direction, the sign is -1 when accelerating and 1 when decelerating;

[0108] After the target deceleration is determined, the target deceleration can be compared with the speed judgment threshold, specifically:

[0109]

[0110] Among them, LonStatus ref1 is the speed state value; abs() is the absolute value calculation;

[0111] When abs(a')>thre a When , if sign is -1, the speed state value is the maximum state value 1, and if sign is 1, the speed state value is the minimum state value -1;

[0112] When abs(a')≤thre a When:

[0113]

[0114] The speed state value is mapped to [-1, 1] by the above formula.

[0115] Step S43, determining a collision time state value according to the collision time judgment threshold and the second driving state;

[0116] The collision time refers to the time required for the two vehicles to maintain their current speed until a collision occurs, starting from the current moment.

[0117] The collision time state value is used to indicate the longitudinal intention of the adjacent vehicle at the collision time level;

[0118] Furthermore, the step S43 includes the steps of:

[0119] Step S431, determining a relative speed and a relative distance between the current vehicle and the adjacent vehicle according to the second driving state;

[0120] Step S432, determining a target collision time between the current vehicle and the adjacent vehicle according to the relative speed and the relative distance;

[0121] Step S433, determining whether the target collision time is greater than the collision time determination threshold;

[0122] Step S434, if the target collision time is greater than the collision time judgment threshold, obtaining a preset dangerous collision time threshold, and calculating the collision time state value according to the relative speed, the relative distance, the preset dangerous collision time threshold and the collision time judgment threshold;

[0123] Step S435: if the target collision time is less than or equal to the collision time judgment threshold, determining the collision time state value as a maximum state value.

[0124] The target collision time ttc is:

[0125]

[0126] After the target collision time is determined, the target collision time can be compared with the collision time judgment threshold, specifically:

[0127]

[0128] Among them, LonStatus ref2 is the collision time state value; ttc w To preset a dangerous collision time threshold;

[0129] It is understandable that, since there is no negative value for a collision event, in this embodiment, a preset dangerous collision time threshold is set to clarify the corresponding situation of the maximum state value of the collision time state value.

[0130] When ttc≤thre ttc When , the collision time state value is set to the maximum state value 1;

[0131] When ttc w >ttc>thre ttc When:

[0132]

[0133] The collision event state value is mapped to [0, 1) by the above formula.

[0134] Step S44: obtaining the longitudinal state value based on the speed state value and the collision time state value.

[0135] It can be understood that the speed state value only reflects the longitudinal intention of the neighboring vehicle at the speed level, and the collision time state value indicates the longitudinal intention of the neighboring vehicle at the collision time level; therefore, by combining the speed state value and the collision time state value, a longitudinal state value that reflects the longitudinal intention of the neighboring vehicle at multiple levels can be obtained.

[0136] Furthermore, the step S44 comprises the steps of:

[0137] Step S441, determining a relative speed and a relative distance between the current vehicle and the adjacent vehicle according to the second driving state;

[0138] Step S442, determining a collision time weight corresponding to the relative speed and relative distance, and determining a speed weight corresponding to the collision time weight, wherein the sum of the collision time weight and the speed weight is 1;

[0139] Step S443: Associating the speed state value with the speed weight, associating the collision time state value with the collision time weight, and performing weighted average calculation to obtain the longitudinal state value.

[0140] It is understandable that the collision time can only be accurately detected when the two vehicles maintain a certain relative speed and relative distance. Therefore, in order to avoid the impact of excessive deviation in the collision time on the determination of the longitudinal state value, a collision time weight and a speed weight are set in this embodiment, and the sum of the collision time weight and the speed weight is 1. Therefore, after the collision time is determined, the speed weight can be obtained.

[0141] Specifically, the collision time weight is determined based on the relative speed and the relative distance; the relative speed, relative distance and collision time can be associated and determined in advance based on the available range of the relative speed, relative distance and collision time, so as to obtain the corresponding relationship between the relative speed, relative distance and collision time weight; for example, a relative speed threshold and a relative distance threshold are set, when the relative speed is greater than the relative speed threshold and the relative distance is greater than the relative distance threshold, the collision time weight is set to 1, otherwise, the collision time weight is set to 0; for example, the relative speed and relative distance are divided into multiple intervals respectively, the smaller the relative speed and relative distance are, the smaller the corresponding collision time weight is.

[0142] After the collision time weight and speed weight are determined, the longitudinal status value LonStatus can be calculated:

[0143] LonStatus=LonStatus ref1 ×w′+LonStatus ref2 (1-w′)

[0144] Where w' is the velocity weight.

[0145] This embodiment can accurately calculate the longitudinal state value based on the actual available range of the collision time.

[0146] Further, in a fourth embodiment of the method for predicting the longitudinal intention of a neighboring vehicle of the present invention proposed based on the first embodiment of the present invention, step S50 includes the steps of:

[0147] Step S51, obtaining a plurality of longitudinal state values ​​detected within a current time window;

[0148] Step S52, determining a state weight corresponding to each of the longitudinal state values, wherein the time difference between the acquisition time corresponding to the longitudinal state value and the current time is negatively correlated with the state weight;

[0149] Step S53: performing weighted average calculation on the longitudinal state values ​​based on the corresponding state weights to obtain a final state value corresponding to the longitudinal intention.

[0150] The time window is used to indicate the value range of the longitudinal state value for determining the longitudinal intention; for example, if the time window is set to 2 seconds and a longitudinal state value is determined every 40 ms, 50 longitudinal state values ​​can be obtained within the time window; it can be understood that during driving, the driving state of the vehicle is not constant. Therefore, in order to avoid errors in the longitudinal intention caused by the vehicle state at a single moment, in this embodiment, multiple longitudinal state values ​​are obtained through the current time window to comprehensively determine the longitudinal intention.

[0151] The current time window is a time window of the current cycle. It can be understood that the time window is a sliding window, and the last longitudinal state value obtained in the time window is the latest longitudinal state value obtained.

[0152] It can be understood that the more recently acquired longitudinal state values ​​are more able to reflect the real-time intentions of neighboring vehicles. Therefore, in this embodiment, the longitudinal weight is associated with the distance of the longitudinal state value collection; the smaller the difference between the longitudinal state value collection time and the current time, the later the longitudinal state value is collected, the more the longitudinal state value can reflect the real-time intentions of neighboring vehicles, and the larger the corresponding state weight, and vice versa; in actual applications, the state weight can be set based on actual needs, such as dividing the time window into two intervals of length 1 second, and the weight corresponding to the longitudinal state value in the earlier interval is the same and smaller than the weight corresponding to the longitudinal state value in the later interval.

[0153] After the weights of each longitudinal state value are determined, a weighted average calculation can be performed to obtain the final state value corresponding to the longitudinal intention; it can be understood that the longitudinal intention can be expressed as a final state value, such as the closer the final state value is to 1, the greater the probability that the neighboring vehicle is close to the current vehicle in the longitudinal direction, and conversely, the closer the final state value is to 0, the smaller the probability that the neighboring vehicle is close to the current vehicle in the longitudinal direction; the specific application of the longitudinal intention can be set based on actual needs.

[0154] In this embodiment, the longitudinal intention is specifically determined by using multiple state weights within a time window, so that the intention of neighboring vehicles can be better predicted.

[0155] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0156] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0157] The present application also provides a neighboring vehicle longitudinal intention prediction device for implementing the neighboring vehicle longitudinal intention prediction method, see Figure 4 , the adjacent vehicle longitudinal intention prediction device comprises:

[0158] A first acquisition module, used for acquiring a first driving state of the current vehicle during a lane change process;

[0159] A first determination module, used to determine a target judgment condition corresponding to the first driving state;

[0160] A second determination module is used to determine an adjacent vehicle corresponding to the current vehicle during the lane change process;

[0161] A second acquisition module, used for acquiring a second driving state of the adjacent vehicle, and determining a longitudinal state value corresponding to the adjacent vehicle according to the second driving state and the target judgment condition;

[0162] The third determination module is configured to determine the longitudinal intention of the neighboring vehicle according to the longitudinal state value.

[0163] The device for predicting the longitudinal intention of adjacent vehicles determines the target judgment condition based on the first driving state of the current vehicle, so that the requirement for the state of the adjacent vehicle when changing lanes can be determined based on the state of the current vehicle, and then the longitudinal intention of the adjacent vehicle can be accurately determined based on the target judgment condition, so that the possible actions of the rear target can be considered, and then the intelligent lane change based on the longitudinal intention can be accurately completed.

[0164] It should be noted that the first acquisition module in this embodiment can be used to execute step S10 in the embodiment of the present application, the first determination module in this embodiment can be used to execute step S20 in the embodiment of the present application, the second determination module in this embodiment can be used to execute step S30 in the embodiment of the present application, the second acquisition module in this embodiment can be used to execute step S40 in the embodiment of the present application, and the third determination module in this embodiment can be used to execute step S50 in the embodiment of the present application.

[0165] Further, the target judgment condition includes a target judgment threshold, and the first determination module includes:

[0166] A first acquisition unit, used to acquire a positional relationship between the current vehicle and a marking line of a target lane change lane;

[0167] a first determining unit, configured to determine a first condition weight corresponding to the position relationship, wherein the lane change completion degree corresponding to the position relationship is positively correlated with the first condition weight;

[0168] a second acquisition unit, configured to acquire the current driving speed of the vehicle and determine a second condition weight corresponding to the driving speed, wherein the driving speed is positively correlated with the second condition weight;

[0169] The third acquisition unit is used to acquire an initial judgment threshold, and use the product of the initial judgment threshold, the first condition weight, and the second condition weight as the target judgment threshold.

[0170] Furthermore, the second acquisition module includes:

[0171] a fourth acquisition unit, configured to acquire a target judgment threshold in the target judgment condition, wherein the target judgment threshold includes a speed judgment threshold and a collision time judgment threshold;

[0172] a second determining unit, configured to determine a speed state value according to the speed judgment threshold and the second driving state;

[0173] a third determining unit, configured to determine a collision time state value according to the collision time judgment threshold and the second driving state;

[0174] The first execution unit is configured to obtain the longitudinal state value based on the speed state value and the collision time state value.

[0175] Further, the second determining unit includes:

[0176] a first determining subunit, configured to determine a relative speed, a relative distance, and an acceleration / deceleration direction between the current vehicle and the adjacent vehicle according to the second driving state;

[0177] A first calculation subunit, configured to calculate a target deceleration of the neighboring vehicle according to the relative speed, the relative distance, and the acceleration / deceleration direction;

[0178] A first judgment subunit, used to judge whether the absolute value of the target deceleration is greater than the speed judgment threshold;

[0179] a second determining subunit, configured to determine, if the absolute value of the target deceleration is greater than the speed judgment threshold, the speed state value as a maximum state value and a minimum state value according to the acceleration / deceleration direction;

[0180] The second calculation subunit is configured to calculate the speed state value according to the target deceleration and the speed judgment threshold if the absolute value of the target deceleration is less than or equal to the speed judgment threshold.

[0181] Further, the third determining unit includes:

[0182] a third determining subunit, configured to determine a relative speed and a relative distance between the current vehicle and the adjacent vehicle according to the second driving state;

[0183] a fourth determining subunit, configured to determine a target collision time between the current vehicle and the adjacent vehicle according to the relative speed and the relative distance;

[0184] A second judgment subunit, used to judge whether the target collision time is greater than the collision time judgment threshold;

[0185] A first acquisition subunit is used to acquire a preset dangerous collision time threshold if the target collision time is greater than the collision time judgment threshold, and calculate the collision time state value according to the relative speed, the relative distance, the preset dangerous collision time threshold and the collision time judgment threshold;

[0186] The fifth determining subunit is configured to determine that the collision time state value is a maximum state value if the target collision time is less than or equal to the collision time judgment threshold.

[0187] Furthermore, the first execution unit includes:

[0188] a sixth determining subunit, configured to determine a relative speed and a relative distance between the current vehicle and the adjacent vehicle according to the second driving state;

[0189] a seventh determining subunit, configured to determine a collision time weight corresponding to the relative speed and relative distance, and determine a speed weight corresponding to the collision time weight, wherein the sum of the collision time weight and the speed weight is 1;

[0190] The third calculation subunit is used to associate the speed state value with the speed weight, associate the collision time state value with the collision time weight, and perform weighted average calculation to obtain the longitudinal state value.

[0191] Furthermore, the third determination module includes:

[0192] A fifth acquisition unit, configured to acquire a plurality of longitudinal state values ​​detected within a current time window;

[0193] a fourth determining unit, configured to determine a state weight corresponding to each of the longitudinal state values, wherein a time difference between a collection time corresponding to the longitudinal state value and a current time is negatively correlated with the state weight;

[0194] The first calculation unit is used to perform weighted average calculation on the longitudinal state value based on the corresponding state weight to obtain a final state value corresponding to the longitudinal intention.

[0195] Reference Figure 5 In terms of hardware structure, the vehicle may include components such as a communication module 10, a memory 20, and a processor 30. In the vehicle, the processor 30 is connected to the memory 20 and the communication module 10 respectively, and a computer program is stored in the memory 20. The computer program is executed by the processor 30 at the same time, and the steps of the above method embodiment are implemented when the computer program is executed.

[0196] The communication module 10 can be connected to an external communication device through a network. The communication module 10 can receive requests from an external communication device, and can also send requests, instructions and information to the external communication device, which can be other vehicles, servers or IoT devices, such as televisions, etc.

[0197] The memory 20 can be used to store software programs and various data. The memory 20 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as obtaining the first driving state of the current vehicle), etc.; the data storage area can include a database, and the data storage area can store data or information created according to the use of the system, etc. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0198] The processor 30 is the control center of the vehicle. It uses various interfaces and lines to connect various parts of the entire vehicle. It executes various functions of the vehicle and processes data by running or executing software programs and / or modules stored in the memory 20, and calling data stored in the memory 20, so as to monitor the vehicle as a whole. The processor 30 may include one or more processing units; optionally, the processor 30 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 30.

[0199] although Figure 5 Although not shown, the above vehicle may further include a circuit control module, which is used to connect to a power source to ensure the normal operation of other components. Figure 5 The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0200] The present invention also provides a computer-readable storage medium on which a computer program is stored. The computer-readable storage medium may be Figure 5 The memory 20 in the vehicle may also be at least one of a ROM (Read-Only Memory) / RAM (Random Access Memory), a magnetic disk, and an optical disk. The computer-readable storage medium includes a number of instructions for enabling a terminal device with a processor (which may be a TV, a car, a mobile phone, a computer, a server, a terminal, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0201] In the present invention, the terms "first", "second", "third", "fourth" and "fifth" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0202] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0203] Although the embodiments of the present invention have been shown and described above, the scope of protection of the present invention is not limited thereto. It is understood that the above embodiments are exemplary and cannot be understood as limiting the present invention. A person of ordinary skill in the art can change, modify and replace the above embodiments within the scope of the present invention, and these changes, modifications and replacements should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A method for predicting the longitudinal intention of a neighboring vehicle, characterized in that: The method for predicting the longitudinal intention of a neighboring vehicle comprises: During the lane change process, obtaining a first driving state of the current vehicle; determining a target judgment condition corresponding to the first driving state; Determining an adjacent vehicle corresponding to the current vehicle during a lane change process; Acquiring a second driving state of the neighboring vehicle, and determining a longitudinal state value corresponding to the neighboring vehicle according to the second driving state and the target judgment condition; A longitudinal intention of the neighboring vehicle is determined based on the longitudinal state value.

2. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 1, characterized in that: The target judgment condition includes a target judgment threshold, and the determining of the target judgment condition corresponding to the first driving state includes: Acquiring a positional relationship between the current vehicle and a marking of a target lane change lane; determining a first condition weight corresponding to the position relationship, wherein a lane change completion degree corresponding to the position relationship is positively correlated with the first condition weight; Acquire the current driving speed of the vehicle, and determine a second condition weight corresponding to the driving speed, wherein the driving speed is positively correlated with the second condition weight; An initial judgment threshold is obtained, and the product of the initial judgment threshold, the first condition weight, and the second condition weight is used as the target judgment threshold.

3. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 1, characterized in that: The determining of the longitudinal state value corresponding to the adjacent vehicle according to the second driving state and the target judgment condition comprises: Acquiring a target judgment threshold in the target judgment condition, wherein the target judgment threshold includes a speed judgment threshold and a collision time judgment threshold; determining a speed state value according to the speed judgment threshold and the second driving state; determining a collision time state value according to the collision time judgment threshold and the second driving state; The longitudinal state value is obtained based on the speed state value and the collision time state value.

4. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 3, characterized in that: The determining of the speed state value according to the speed judgment threshold and the second driving state comprises: Determine the relative speed, relative distance, and acceleration / deceleration direction between the current vehicle and the neighboring vehicle according to the second driving state; Calculating a target deceleration of the neighboring vehicle according to the relative speed, the relative distance, and the acceleration / deceleration direction; Determining whether the absolute value of the target deceleration is greater than the speed determination threshold; If the absolute value of the target deceleration is greater than the speed judgment threshold, the speed state value is determined to be a maximum state value and a minimum state value according to the acceleration and deceleration direction; If the absolute value of the target deceleration is less than or equal to the speed judgment threshold, the speed state value is calculated according to the target deceleration and the speed judgment threshold.

5. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 3, characterized in that: The determining of the collision time state value according to the collision time judgment threshold and the second driving state comprises: Determine the relative speed and relative distance between the current vehicle and the adjacent vehicle according to the second driving state; Determining a target collision time between the current vehicle and the adjacent vehicle according to the relative speed and the relative distance; Determining whether the target collision time is greater than the collision time determination threshold; If the target collision time is greater than the collision time judgment threshold, a preset dangerous collision time threshold is obtained, and the collision time state value is calculated according to the relative speed, the relative distance, the preset dangerous collision time threshold and the collision time judgment threshold; If the target collision time is less than or equal to the collision time judgment threshold, the collision time state value is determined to be a maximum state value.

6. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 3, characterized in that: The obtaining of the longitudinal state value based on the speed state value and the collision time state value comprises: determining a relative speed and a relative distance between the current vehicle and the neighboring vehicle according to the second driving state; Determine a collision time weight corresponding to the relative speed and relative distance, and determine a speed weight corresponding to the collision time weight, wherein the sum of the collision time weight and the speed weight is 1; The speed state value is associated with the speed weight, the collision time state value is associated with the collision time weight, and a weighted average calculation is performed to obtain the longitudinal state value.

7. The method for predicting the longitudinal intention of a neighboring vehicle according to claim 1, characterized in that: The determining the longitudinal intention of the neighboring vehicle according to the longitudinal state value comprises: Acquire a plurality of longitudinal state values ​​detected within a current time window; Determine a state weight corresponding to each of the longitudinal state values, wherein a time difference between a collection time corresponding to the longitudinal state value and a current time is negatively correlated with the state weight; The longitudinal state value is weighted averaged based on the corresponding state weight to obtain a final state value corresponding to the longitudinal intention.

8. A device for predicting the longitudinal intention of a neighboring vehicle, characterized in that: The adjacent vehicle longitudinal intention prediction device comprises: A first acquisition module, used for acquiring a first driving state of the current vehicle during a lane change process; A first determination module, used to determine a target judgment condition corresponding to the first driving state; A second determination module is used to determine an adjacent vehicle corresponding to the current vehicle during the lane change process; A second acquisition module, used for acquiring a second driving state of the adjacent vehicle, and determining a longitudinal state value corresponding to the adjacent vehicle according to the second driving state and the target judgment condition; The third determination module is configured to determine the longitudinal intention of the neighboring vehicle according to the longitudinal state value.

9. A vehicle, characterized in that: The vehicle comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program implements the steps of the method for predicting the longitudinal intention of a neighboring vehicle as claimed in any one of claims 1 to 7 when executed by the processor.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for predicting the longitudinal intention of a neighboring vehicle according to any one of claims 1 to 7 are implemented.

Images