Intrusion assessment method, device and equipment and readable storage medium

Abstract

The invention discloses an intrusion assessment method, device and equipment and a readable storage medium in the technical field of intelligent driving, and the method comprises the steps: obtaining first probabilities corresponding to a current target lane and an adjacent lane of a vehicle; acquiring second probabilities corresponding to the target vehicle in the target lane and the adjacent lane; using the first probability and the second probability respectively corresponding to the target lane and the adjacent lane to determine combined probabilities respectively corresponding to the target vehicle in the target lane and the adjacent lane relative to the vehicle; and performing intrusion assessment on the target vehicle based on the change trend of the combination probability. According to the method, the target intrusion action is evaluated through the probability according to the change of the probability of the target vehicle relative to the own vehicle in the lane, and misjudgment caused by sensor detection errors can be reduced, so that the intrusion evaluation accuracy and quantification are improved, the control effect is improved, and the comfortable function experience is better.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to an intrusion assessment method, device, equipment and readable storage medium. Background Art

[0002] With the continuous development of autonomous driving and assisted driving technologies, cars are gradually entering the era of intelligence. However, how to accurately judge the intrusion behavior of target vehicles (for example, lane changing behaviors such as crossing and cutting in) to ensure the safety and comfort of autonomous driving is a problem worth exploring.

[0003] In response to the intrusion behavior of target vehicles, the current methods for evaluating the intrusion behavior of target vehicles include: evaluating the intrusion intention of the target vehicle through the lateral position of the target, the heading angle of the target vehicle, and the relative position relationship between the target vehicle and the lane boundary. This method is easily affected by the accuracy of the sensor and is prone to misjudgment; and this single description of the intrusion behavior through 0 or 1 affects the continuity of the control experience, which is likely to cause excessive braking and uncomfortable control effects.

[0004] In summary, how to improve the accuracy of vehicle intrusion assessment is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The purpose of this application is to provide an intrusion assessment method, device, equipment and readable storage medium, which can improve the accuracy of vehicle intrusion assessment.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] An intrusion assessment method, comprising:

[0008] Obtain the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle;

[0009] Obtain second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively;

[0010] Determine the combined probabilities of the target vehicle relative to the ego vehicle in the target lane and the adjacent lane respectively by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0011] Based on the changing trend of the combined probability, an intrusion assessment is performed on the target vehicle.

[0012] Preferably, obtaining the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively includes:

[0013] Obtaining a coordinate position sequence corresponding to the target vehicle in the current lane acquisition cycle;

[0014] Determining a probability density function of the target vehicle relative to a lane using the abscissa in the coordinate position sequence;

[0015] Acquire lane boundaries corresponding to the target lane and the adjacent lane respectively;

[0016] Based on the lane boundary, the probability density function is piecewise integrated to obtain the second probability.

[0017] Preferably, determining the probability density function of the target vehicle in the current lane acquisition cycle using the horizontal coordinate in the coordinate position sequence includes:

[0018] Calculate the mean and standard deviation of the horizontal coordinates;

[0019] The data expectation and standard deviation of the normal distribution function are determined according to the mean value and the standard deviation to obtain the probability density function.

[0020] Preferably, obtaining the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle includes:

[0021] Get the width of the vehicle;

[0022] Determining a probability distribution function of the ego-vehicle relative to the lane based on the width;

[0023] Obtain the interval distances corresponding to the target lane boundary and the adjacent lane boundary respectively;

[0024] The first probability is calculated based on the corresponding interval distance and in combination with a probability distribution function.

[0025] Preferably, the adjacent lanes include a left lane and a right lane, and using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively, determining the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively includes:

[0026] Determine each first probability group that the target vehicle is in the left lane relative to the self-vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0027] The first probability and the second probability corresponding to each first probability group are multiplied and superimposed to obtain a first combined probability that the target vehicle is equivalent to the vehicle being in the left lane;

[0028] Determine each second probability group of the target vehicle relative to the ego vehicle in the target lane by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0029] The first probability and the second probability corresponding to each second probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the target lane;

[0030] Determine each third probability group that the target vehicle is in the right lane relative to the ego vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0031] The first probability and the second probability corresponding to each third probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the right lane.

[0032] Preferably, the first probability group includes: a first probability that the ego vehicle is in the target lane, and a second probability that the target vehicle is in the left lane; a first probability that the ego vehicle is in the right lane, and a second probability that the target vehicle is in the target lane;

[0033] The second probability group includes: a first probability that the vehicle is in the left lane, and a second probability that the target vehicle is in the left lane; a first probability that the vehicle is in the target lane, and a second probability that the target vehicle is in the target lane; a first probability that the vehicle is in the right lane, and a second probability that the target vehicle is in the right lane;

[0034] The second probability group includes: a first probability that the vehicle is in the left lane and a second probability that the target vehicle is in the target lane; a first probability that the vehicle is in the target lane and a second probability that the target vehicle is in the right lane.

[0035] Preferably, based on the changing trend of the combined probability, performing intrusion assessment on the target vehicle includes:

[0036] If the combined probability drops to a cut-out threshold, it is determined that the target vehicle leaves the lane corresponding to the combined probability;

[0037] If the combined probability rises to the cut-in threshold, it is determined that the target vehicle cuts into the lane corresponding to the combined probability.

[0038] An intrusion assessment device, comprising:

[0039] A first probability acquisition module is used to obtain first probabilities corresponding to the current target lane and the adjacent lane of the vehicle;

[0040] A second probability acquisition module is used to acquire second probabilities of the target vehicle corresponding to the target lane and the adjacent lane respectively;

[0041] A combined probability acquisition module, used to determine the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0042] The intrusion assessment module is used to perform intrusion assessment on the target vehicle based on the change trend of the combined probability.

[0043] An electronic device, comprising:

[0044] Memory for storing computer programs;

[0045] A processor is used to implement the steps of the above-mentioned intrusion assessment method when executing the computer program.

[0046] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned intrusion assessment method are implemented.

[0047] By applying the method provided in the embodiment of the present application, the first probabilities corresponding to the current target lane and the adjacent lane of the ego vehicle are obtained; the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane are obtained; the combined probability of the target vehicle relative to the ego vehicle in the target lane and the adjacent lane is determined by using the first probability and the second probability corresponding to the target lane and the adjacent lane; and the target vehicle is evaluated for intrusion based on the changing trend of the combined probability.

[0048] In the present application, the target vehicle's choice of lane to drive is a random event, but at each fixed moment, the position of the target vehicle relative to the ego vehicle is determined. Therefore, in the present application, the first probabilities corresponding to the ego vehicle in the current lane and the adjacent lane, and the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane can be obtained respectively. Then, the first probability and the second lane are used to summarize and determine the combined probability of the target vehicle in the target lane and the adjacent lane relative to the ego vehicle. Then, with the help of the changing trend of the combined probability, the target vehicle can be evaluated for intrusion. By evaluating the target vehicle's intrusion action through the change in the probability of the target vehicle in the lane relative to the ego vehicle and the probability, it can reduce the misjudgment caused by sensor detection errors, thereby improving the accuracy of intrusion assessment.

[0049] In particular, when conducting intrusion assessment, by calculating the probability of the vehicle being in the lane, the intrusion action of the target vehicle is described based on the linear change of probability, which has good quantification. The comfortable deceleration during intrusion can be calculated based on this linear change, which improves the control effect and provides a better comfort function experience.

[0050] Accordingly, the embodiments of the present application also provide an intrusion assessment device, an apparatus and a readable storage medium corresponding to the above-mentioned intrusion assessment method, which have the above-mentioned technical effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] FIG1 is a flowchart of an implementation of an intrusion assessment method in an embodiment of the present application;

[0053] FIG2 is a schematic diagram of a vehicle probability function in an embodiment of the present application;

[0054] FIG3 is a schematic diagram of a probability distribution function of a self-vehicle in an embodiment of the present application;

[0055] FIG4 is a schematic diagram of a probability distribution function of a target vehicle in an embodiment of the present application;

[0056] FIG5 is a schematic diagram of a target vehicle cutting into a target lane in an embodiment of the present application;

[0057] FIG6 is a schematic diagram of a target vehicle cutting out of a target lane in an embodiment of the present application;

[0058] FIG7 is a schematic diagram of a target vehicle crossing a target lane in an embodiment of the present application;

[0059] FIG8 is a schematic diagram of a combination probability change in an embodiment of the present application;

[0060] FIG9 is a schematic diagram of the structure of an intrusion assessment device in an embodiment of the present application;

[0061] FIG10 is a schematic diagram of the structure of an electronic device in an embodiment of the present application;

[0062] FIG. 11 is a schematic diagram of the specific structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0064] Please refer to FIG. 1 , which is a flow chart of an intrusion assessment method in an embodiment of the present application. The method includes the following steps:

[0065] S101. Obtain first probabilities corresponding to the current target lane and the adjacent lane of the vehicle.

[0066] In this embodiment, considering that during the driving process of the vehicle, the conditions of the vehicles in the same lane as the vehicle and in the left and right adjacent lanes have the greatest impact on the vehicle, therefore, in this embodiment, the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle can be obtained.

[0067] Since the ego vehicle may also change lanes according to the road and vehicle conditions, and may drive to a certain area where the number of lanes will decrease, the number of adjacent lanes corresponding to the ego vehicle may be 0, 1, or 2. It is understandable that when there is no adjacent lane, the probability that the ego vehicle is in the adjacent lane can be set to 0. After the ego vehicle changes lanes, the target lane and adjacent lanes also change accordingly.

[0068] That is, there are three first probabilities, which are the probabilities corresponding to the vehicle being in the left lane, the target lane, and the right lane, respectively. The left lane and the right lane are adjacent lanes, and the target lane is the lane the vehicle is currently in. If Lane0, Lane1, and Lane2 are numbered to represent the left lane, the target lane, and the right lane, then the first probabilities are:

[0069] is the first probability that the vehicle is in lane 0;

[0070] is the first probability that the vehicle is in lane Lane1;

[0071] is the first probability that the vehicle is in lane Lane2.

[0072] When determining the first probability that the vehicle is in different lanes, it can be determined based on the width of the vehicle and the boundary of the lane. For example, when the vehicle completely falls into a lane, the lane is the target lane, and the corresponding first probability is 100%. When the vehicle does not completely fall into a lane, the first probability corresponding to the lane can be determined according to the proportion of the vehicle falling into the lane.

[0073] In a specific implementation of the present application, obtaining the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle includes:

[0074] Get the width of the vehicle;

[0075] Determine the probability distribution function of the ego vehicle relative to the lane based on the width;

[0076] Obtain the interval distances corresponding to the target lane boundary and the adjacent lane boundary respectively;

[0077] Based on the corresponding interval distances and in combination with the probability distribution function, a first probability is calculated.

[0078] For ease of description, the above steps are combined for explanation below.

[0079] After obtaining the width of the vehicle, use the interval To represent the width of the vehicle, They represent the negative half and positive half of the vehicle width respectively.

[0080] Please refer to Figure 2. Since the vehicle is in the interval It obeys continuous uniform distribution, so the probability density function of the vehicle is:

[0081] ;

[0082] Please refer to Figure 3, the probability distribution function of the ego vehicle relative to the lane is:

[0083] ;

[0084] Probability calculation of the ego vehicle in the three lanes: According to the distance between the ego vehicle and the boundaries of the left lane, right lane and middle lane, the above probability distribution function calculates the probability of the ego vehicle in the three lanes respectively: .

[0085] S102: Obtain second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively.

[0086] From the knowledge of statistics, we know that the lane a vehicle chooses to drive in is a random event, but its position relative to the vehicle at a certain moment is determined. Moreover, the distribution of lanes at a certain moment can be regarded as a normal distribution. Therefore, the probability density of the normal distribution can be used to solve the probability of the target vehicle existing in each lane (left lane, self lane (i.e. target lane) and right lane) at a certain moment.

[0087] In this embodiment, the target vehicle may be other vehicles within a set range that affect the driving of the vehicle (such as vehicles located in front of or behind the vehicle, traveling in the same lane or connected lanes). Such a target vehicle may not exist in a certain period of time (such as driving at night), or there may be multiple target vehicles in a certain period of time (such as peak hours).

[0088] In a specific implementation of the present application, obtaining the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively includes:

[0089] Obtain the coordinate position sequence corresponding to the target vehicle in the current lane acquisition cycle;

[0090] Determine the probability density function of the target vehicle relative to a lane using the abscissa in the coordinate position sequence;

[0091] Obtain the lane boundaries corresponding to the target lane and the adjacent lanes respectively;

[0092] Based on the lane boundary, the probability density function is piecewise integrated to obtain the second probability.

[0093] Among them, the probability density function of the target vehicle in the current lane acquisition cycle is determined by using the horizontal coordinate in the coordinate position sequence, including:

[0094] Calculate the mean and standard deviation of the horizontal axis;

[0095] The data expectation and standard deviation of the normal distribution function are determined based on the mean and standard deviation to obtain the probability density function.

[0096] For ease of description, the above steps are combined for explanation below.

[0097] Then the random variable (The horizontal axis of the target) obeys the mathematical expectation , the standard deviation is The Gaussian distribution of , then its probability density function is:

[0098] .

[0099] The coordinate position of the target vehicle obtained by the visual sensor within a certain lane sampling period is , according to the position of the target vehicle in the sampling period, calculate the average value and standard deviation of the horizontal coordinate of the target vehicle in the sampling period , , and then obtain the probability density function of the target vehicle in the sampling period.

[0100] Among them, the video sensor continuously collects the coordinates of the target vehicle based on the F1 frequency, and the lane collection cycle is F2. Within one F2, n coordinate positions can be collected based on F1, and these n coordinate positions are arranged in order as a coordinate position sequence.

[0101] Please refer to Figure 4 (ego), the probability distribution function of the target vehicle in the three lanes can be obtained by integrating its probability density function in the three lanes within the three lane boundaries. The three lane boundaries a, b, c and d are given by the visual sensor, where a is the left boundary of the target lane, b is the left boundary of the left lane, c is the right boundary of the target lane, and d is the right boundary of the right lane. From this, the second probability of the target vehicle in the three lanes can be calculated:

[0102] ;

[0103] ;

[0104] ;

[0105] In the above formula They represent the second probability of the target vehicle being in the three lanes respectively.

[0106] It should be noted that, in actual applications, step S101 and step S102 may be executed sequentially or in parallel, and there is no fixed order for their execution.

[0107] S103, using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively, determine the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively.

[0108] According to the probability of the target being in the three lanes and the probability of the ego vehicle being in the three lanes, the probability of the target being in the three lanes relative to the ego vehicle is finally determined as the probability combination superposition, that is, the combined probability.

[0109] In a specific implementation of the present application, the adjacent lanes include a left lane and a right lane, and the first probability and the second probability corresponding to the target lane and the adjacent lane are used to determine the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane, respectively, including:

[0110] Determine each first probability group that the target vehicle is in the left lane relative to the ego vehicle by using the first probabilities and the second probabilities corresponding to the target lane and the adjacent lane respectively;

[0111] The first probability and the second probability corresponding to each first probability group are multiplied and superimposed to obtain a first combined probability that the target vehicle is equivalent to the vehicle being in the left lane;

[0112] Determine each second probability group of the target vehicle relative to the ego vehicle in the target lane by using the first probabilities and the second probabilities corresponding to the target lane and the adjacent lane respectively;

[0113] The first probability and the second probability corresponding to each second probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the target lane;

[0114] Determine each third probability group that the target vehicle is in the right lane relative to the ego vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0115] The first probability and the second probability corresponding to each third probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the right lane.

[0116] The first probability group includes: a first probability that the vehicle is in the target lane, and a second probability that the target vehicle is in the left lane; a first probability that the vehicle is in the right lane, and a second probability that the target vehicle is in the target lane;

[0117] The second probability group includes: a first probability that the ego vehicle is in the left lane, a second probability that the target vehicle is in the left lane; a first probability that the ego vehicle is in the target lane, a second probability that the target vehicle is in the target lane; a first probability that the ego vehicle is in the right lane, a second probability that the target vehicle is in the right lane;

[0118] The second probability group includes: a first probability that the ego vehicle is in the left lane, a second probability that the target vehicle is in the target lane; a first probability that the ego vehicle is in the target lane, a second probability that the target vehicle is in the right lane.

[0119] Specifically, you can use , , , determine the combination probability;

[0120] Among them, Lane1 is the target lane, Lane0 and Lane2 are adjacent lanes;

[0121] is the combined probability that the target vehicle is equivalent to the ego vehicle in lane Lane0;

[0122] is the combined probability that the target vehicle is equivalent to the ego vehicle in lane Lane1;

[0123] The combined probability that the target vehicle is equivalent to the ego vehicle in lane Lane2;

[0124] is the second probability that the target vehicle is in lane Lane0;

[0125] is the second probability that the target vehicle is in lane Lane1;

[0126] is the second probability that the target vehicle is in lane Lane2;

[0127] is the first probability that the vehicle is in lane 0;

[0128] is the first probability that the vehicle is in lane Lane1;

[0129] is the first probability that the vehicle is in lane Lane2.

[0130] For ease of description, please refer to the following table to illustrate the combined probability calculation.

[0131]

[0132] As can be seen from the table above, there are two first probability groups, namely p1 and q0, p2 and q1. The first combined probability is the combined probability of the target vehicle in the left lane relative to the ego vehicle: ;

[0133] The second probability group has three, namely p0 and q0, p1 and q1, p2 and q2. The second combination probability is the combined probability of the target vehicle relative to the ego vehicle in the target lane: ;

[0134] The third probability group has two, namely p0 and q1, p1 and q2. The third combined probability is the combined probability of the target vehicle in the right lane relative to the ego vehicle: .

[0135] S104: Based on the changing trend of the combined probability, an intrusion assessment is performed on the target vehicle.

[0136] It can be understood that the higher the combination probability, the more likely the vehicle is in the corresponding lane, and the combination probability will change as the vehicle changes lanes. Specifically, when a vehicle cuts out of a lane, the combination probability corresponding to the lane will become smaller and smaller, and correspondingly, when a vehicle cuts into a lane, the combination probability corresponding to the lane will become larger and larger.

[0137] Therefore, based on the temporal trend of the combined probability, it can be determined that the target vehicle is equivalent to the target lane and the adjacent lane where the ego vehicle is located, such as cutting in (as shown in Figure 5, obj1 and obj2 are target vehicles at different positions), cutting out (as shown in Figure 6), crossing (as shown in Figure 7), and other lane change actions. That is, the target vehicle intrusion into the lane includes two situations: the target vehicle cuts into the ego vehicle's main lane from the adjacent lane (including the crossing situation perpendicular to the direction of movement of the ego vehicle) and cuts out from the main lane to the adjacent lane. By calculating the combined probability of the target vehicle in the three lanes respectively, according to the changing trend of the combined probability of the target vehicle in the three lanes, the intention of the target vehicle to invade the lane is evaluated.

[0138] In a specific implementation of the present application, based on the changing trend of the combined probability, an intrusion assessment is performed on the target vehicle, including:

[0139] If the combined probability drops to the cut-out threshold, it is determined that the target vehicle leaves the lane corresponding to the combined probability;

[0140] If the combined probability rises to the cut-in threshold, it is determined that the target vehicle cuts into the lane corresponding to the combined probability.

[0141] For ease of description, the above steps are combined for explanation below.

[0142] The cut-in threshold and the cut-out threshold can be set and adjusted according to actual needs, and are not specifically limited in this embodiment.

[0143] For example, when the combined probability decreases to 40%, it can be considered that the vehicle cuts out; when the combined probability increases to 60%, it can be considered that the vehicle cuts in.

[0144] The following uses different lanes as examples to explain the detection of lane changes in different situations where the target vehicle is equivalent to the self-vehicle:

[0145] The target vehicle cuts out from the target lane to the left lane: When the target vehicle cuts out from the target lane to the left lane, the probability of the target vehicle in lane 1 changes from large to small, which is in a decreasing process, and the probability of the target vehicle in lane 0 changes from small to large, which is in an increasing process.

[0146] Please refer to Figure 8. The target vehicle cuts out from the target lane to the left lane. The dotted line represents a downward trend: the target vehicle changes from the left lane to the target lane, and the corresponding combined probability change trend of the target vehicle in the left lane; the dotted line represents an upward trend: the target vehicle changes from the left lane to the target lane, and the corresponding combined probability change trend of the target vehicle in the target lane.

[0147] The target vehicle cuts out from the target lane to the right lane: When the target vehicle cuts out from the target lane to the right lane, the probability of the target vehicle in lane 1 is decreasing, showing a downward trend, and the probability of the target vehicle in lane 2 is increasing, showing an upward trend.

[0148] The target vehicle cuts into the target lane from the left side of the target lane: The target vehicle cuts into the target lane from the left side of the target lane. The probability of the target vehicle in lane 0 is decreasing, showing a downward trend, and the probability of the target vehicle in lane 1 is increasing, showing an upward trend.

[0149] The target vehicle cuts into the target lane from the right side of the target lane: The target vehicle cuts into the target lane from the right side of the target lane. The probability of the target vehicle in lane 2 is decreasing, showing a downward trend, and the probability of the target vehicle in lane 1 is increasing, showing an upward trend.

[0150] In a specific implementation of the present application, it also includes:

[0151] The speed and / or direction of the ego vehicle is controlled based on the quantitative results obtained from the intrusion assessment.

[0152] Considering that whether the target vehicle is in an intrusion state is judged by the target's lateral position, the heading angle between the target vehicle and the vehicle, and the distance between the target and the lane boundary, this method is easily affected by the accuracy of the sensor and may cause misjudgment; and this single description of the intrusion behavior by 0 or 1 affects the continuity of the control experience, which may easily cause excessive braking and uncomfortable control effect.

[0153] In this embodiment, by calculating the probability of the target being within the lane and describing the target's intrusion action based on the linear change of probability, the quantitative result of the intrusion assessment can be obtained with good quantification. The comfortable deceleration during intrusion can be calculated based on this linear change (i.e., speed and direction control), thereby improving the control effect and providing a better experience of the comfort function.

[0154] By applying the method provided in the embodiment of the present application, the first probabilities corresponding to the current target lane and the adjacent lane of the ego vehicle are obtained; the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane are obtained; the combined probability of the target vehicle relative to the ego vehicle in the target lane and the adjacent lane is determined by using the first probability and the second probability corresponding to the target lane and the adjacent lane; and the target vehicle is evaluated for intrusion based on the changing trend of the combined probability.

[0155] In the present application, the target vehicle's choice of lane to drive is a random event, but at each fixed moment, the position of the target vehicle relative to the ego vehicle is determined. Therefore, in the present application, the first probabilities corresponding to the ego vehicle in the current lane and the adjacent lane, and the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane can be obtained respectively. Then, the first probability and the second lane are used to summarize and determine the combined probability of the target vehicle in the target lane and the adjacent lane relative to the ego vehicle. Then, with the help of the changing trend of the combined probability, the target vehicle can be evaluated for intrusion. By evaluating the target vehicle's intrusion action through the change in the probability of the target vehicle in the lane relative to the ego vehicle and the probability, it can reduce the misjudgment caused by sensor detection errors, thereby improving the accuracy of intrusion assessment.

[0156] In particular, when conducting intrusion assessment, by calculating the probability of the vehicle being in the lane, the intrusion action of the target vehicle is described based on the linear change of probability, which has good quantification. The comfortable deceleration during intrusion can be calculated based on this linear change, which improves the control effect and provides a better comfort function experience.

[0157] Corresponding to the above method embodiment, the embodiment of the present application further provides an intrusion assessment device. The intrusion assessment device described below and the intrusion assessment method described above can refer to each other.

[0158] As shown in FIG9 , the device includes the following modules:

[0159] The first probability acquisition module 101 is used to obtain the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle;

[0160] The second probability acquisition module 102 is used to acquire the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively;

[0161] The combined probability acquisition module 103 is used to determine the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0162] The intrusion assessment module 104 is used to perform intrusion assessment on the target vehicle based on the change trend of the combined probability.

[0163] By using the device provided in the embodiment of the present application, the first probabilities corresponding to the current target lane and the adjacent lane of the own vehicle are obtained; the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane are obtained; the combined probability of the target vehicle relative to the own vehicle in the target lane and the adjacent lane is determined by using the first probability and the second probability corresponding to the target lane and the adjacent lane; and the intrusion assessment of the target vehicle is performed based on the changing trend of the combined probability.

[0164] In the present application, the target vehicle's choice of lane to drive is a random event, but at each fixed moment, the position of the target vehicle relative to the ego vehicle is determined. Therefore, in the present application, the first probabilities corresponding to the ego vehicle in the current lane and the adjacent lane, and the second probabilities corresponding to the target vehicle in the target lane and the adjacent lane can be obtained respectively. Then, the first probability and the second lane are used to summarize and determine the combined probability of the target vehicle in the target lane and the adjacent lane relative to the ego vehicle. Then, with the help of the changing trend of the combined probability, the target vehicle can be evaluated for intrusion. By evaluating the target vehicle's intrusion action through the change in the probability of the target vehicle in the lane relative to the ego vehicle and the probability, it can reduce the misjudgment caused by sensor detection errors, thereby improving the accuracy of intrusion assessment.

[0165] In particular, when conducting intrusion assessment, by calculating the probability of the vehicle being in the lane, the intrusion action of the target vehicle is described based on the linear change of probability, which has good quantification. The comfortable deceleration during intrusion can be calculated based on this linear change, which improves the control effect and provides a better comfort function experience.

[0166] In a specific implementation of the present application, the second probability acquisition module is specifically used to obtain a coordinate position sequence corresponding to the target vehicle in the current lane acquisition cycle;

[0167] Determine the probability density function of the target vehicle relative to a lane using the abscissa in the coordinate position sequence;

[0168] Obtain the lane boundaries corresponding to the target lane and the adjacent lanes respectively;

[0169] Based on the lane boundary, the probability density function is piecewise integrated to obtain the second probability.

[0170] In a specific implementation of the present application, the second probability acquisition module is specifically used to calculate the mean value and standard deviation of the horizontal coordinate;

[0171] The data expectation and standard deviation of the normal distribution function are determined based on the mean and standard deviation to obtain the probability density function.

[0172] In a specific implementation of the present application, the first probability acquisition module is specifically used to obtain the width of the vehicle;

[0173] Determine the probability distribution function of the ego vehicle relative to the lane based on the width;

[0174] Get the distance of the vehicle relative to the lane boundary;

[0175] Obtain the interval distances corresponding to the target lane boundary and the adjacent lane boundary respectively;

[0176] Based on the corresponding interval distances and in combination with the probability distribution function, a first probability is calculated.

[0177] In a specific implementation of the present application, the adjacent lanes include a left lane and a right lane, and the combined probability acquisition module is specifically used for

[0178] Determine each first probability group that the target vehicle is in the left lane relative to the ego vehicle by using the first probabilities and the second probabilities corresponding to the target lane and the adjacent lane respectively;

[0179] The first probability and the second probability corresponding to each first probability group are multiplied and superimposed to obtain a first combined probability that the target vehicle is equivalent to the vehicle being in the left lane;

[0180] Determine each second probability group of the target vehicle relative to the ego vehicle in the target lane by using the first probabilities and the second probabilities corresponding to the target lane and the adjacent lane respectively;

[0181] The first probability and the second probability corresponding to each second probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the target lane;

[0182] Determine each third probability group that the target vehicle is in the right lane relative to the ego vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively;

[0183] The first probability and the second probability corresponding to each third probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the right lane.

[0184] In a specific implementation of the present application, the first probability group includes: a first probability that the ego vehicle is in the target lane, and a second probability that the target vehicle is in the left lane; a first probability that the ego vehicle is in the right lane, and a second probability that the target vehicle is in the target lane;

[0185] The second probability group includes: a first probability that the ego vehicle is in the left lane, a second probability that the target vehicle is in the left lane; a first probability that the ego vehicle is in the target lane, a second probability that the target vehicle is in the target lane; a first probability that the ego vehicle is in the right lane, a second probability that the target vehicle is in the right lane;

[0186] The second probability group includes: a first probability that the ego vehicle is in the left lane, a second probability that the target vehicle is in the target lane; a first probability that the ego vehicle is in the target lane, a second probability that the target vehicle is in the right lane.

[0187] In a specific implementation of the present application, the intrusion assessment module is specifically used to determine that the target vehicle leaves the lane corresponding to the combined probability if the combined probability drops to the cut-out threshold;

[0188] If the combined probability rises to the cut-in threshold, it is determined that the target vehicle cuts into the lane corresponding to the combined probability.

[0189] In a specific implementation of the present application, it also includes:

[0190] The vehicle speed control module is used to control the speed and / or direction of the vehicle according to the quantitative results obtained by the intrusion assessment.

[0191] Corresponding to the above method embodiment, the embodiment of the present application further provides an electronic device. The electronic device described below and the intrusion assessment method described above can refer to each other.

[0192] As shown in FIG10 , the electronic device includes:

[0193] A memory 332, for storing computer programs;

[0194] The processor 322 is configured to implement the steps of the intrusion assessment method of the above method embodiment when executing a computer program.

[0195] Specifically, please refer to FIG. 11, which is a schematic diagram of the specific structure of an electronic device provided in this embodiment. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) (for example, one or more processors) and a memory 332, and the memory 332 stores one or more computer programs 342 or data 344. Among them, the memory 332 can be a temporary storage or a permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the data processing device. Furthermore, the processor 322 can be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the electronic device 301.

[0196] The electronic device 301 may further include one or more power supplies 326 , one or more wired or wireless network interfaces 350 , one or more input and output interfaces 358 , and / or one or more operating systems 341 .

[0197] The steps in the intrusion assessment method described above can be implemented by the structure of an electronic device.

[0198] Corresponding to the above method embodiment, the embodiment of the present application further provides a readable storage medium. The readable storage medium described below and the intrusion assessment method described above can refer to each other.

[0199] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intrusion assessment method of the above method embodiment are implemented.

[0200] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0201] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0202] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may 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.

[0203] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0204] Finally, it should be noted that, in this article, relationships such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms include, include or any other variations are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0205] Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An intrusion assessment method, characterized in that: include: Obtain the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle; Obtain second probabilities corresponding to the target vehicle in the target lane and the adjacent lane respectively; Determine the combined probabilities of the target vehicle relative to the ego vehicle in the target lane and the adjacent lane respectively by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively; Based on the changing trend of the combined probability, an intrusion assessment is performed on the target vehicle.

2. The method according to claim 1, characterized in that Obtaining second probabilities corresponding to the target vehicle in the target lane and the adjacent lane, respectively, includes: Obtaining a coordinate position sequence corresponding to the target vehicle in the current lane acquisition cycle; Determining a probability density function of the target vehicle relative to a lane using the abscissa in the coordinate position sequence; Acquire lane boundaries corresponding to the target lane and the adjacent lane respectively; Based on the lane boundary, the probability density function is piecewise integrated to obtain the second probability.

3. The method according to claim 2, characterized in that Determining the probability density function of the target vehicle in the current lane acquisition cycle using the horizontal coordinate in the coordinate position sequence includes: Calculate the mean and standard deviation of the horizontal coordinates; The data expectation and standard deviation of the normal distribution function are determined according to the mean value and the standard deviation to obtain the probability density function.

4. The method according to claim 1, characterized in that: Obtaining the first probabilities corresponding to the current target lane and the adjacent lane of the vehicle, including: Get the width of the vehicle; Determining a probability distribution function of the ego-vehicle relative to the lane based on the width; Obtain the interval distances corresponding to the target lane boundary and the adjacent lane boundary respectively; The first probability is calculated based on the corresponding interval distance and in combination with a probability distribution function.

5. The method according to claim 1, characterized in that: The adjacent lanes include a left lane and a right lane. Using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively, determining the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively includes: Determine each first probability group that the target vehicle is in the left lane relative to the self-vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively; The first probability and the second probability corresponding to each first probability group are multiplied and superimposed to obtain a first combined probability that the target vehicle is equivalent to the vehicle being in the left lane; Determine each second probability group of the target vehicle relative to the ego vehicle in the target lane by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively; The first probability and the second probability corresponding to each second probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the target lane; Determine each third probability group that the target vehicle is in the right lane relative to the ego vehicle by using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively; The first probability and the second probability corresponding to each third probability group are multiplied and superimposed to obtain a second combined probability that the target vehicle is equivalent to the vehicle being in the right lane.

6. The method according to any one of claim 5, characterized in that: The first probability group includes: a first probability that the vehicle is in the target lane, and a second probability that the target vehicle is in the left lane; a first probability that the vehicle is in the right lane, and a second probability that the target vehicle is in the target lane; The second probability group includes: a first probability that the vehicle is in the left lane, and a second probability that the target vehicle is in the left lane; a first probability that the vehicle is in the target lane, and a second probability that the target vehicle is in the target lane; a first probability that the vehicle is in the right lane, and a second probability that the target vehicle is in the right lane; The second probability group includes: a first probability that the vehicle is in the left lane and a second probability that the target vehicle is in the target lane; a first probability that the vehicle is in the target lane and a second probability that the target vehicle is in the right lane.

7. The method according to any one of claims 1 to 6, characterized in that: Based on the changing trend of the combined probability, an intrusion assessment is performed on the target vehicle, including: If the combined probability drops to a cut-out threshold, it is determined that the target vehicle leaves the lane corresponding to the combined probability; If the combined probability rises to the cut-in threshold, it is determined that the target vehicle cuts into the lane corresponding to the combined probability.

8. An intrusion assessment device, characterized in that: include: A first probability acquisition module is used to obtain first probabilities corresponding to the current target lane and the adjacent lane of the vehicle; A second probability acquisition module is used to acquire second probabilities of the target vehicle corresponding to the target lane and the adjacent lane respectively; A combined probability acquisition module, used to determine the combined probability of the target vehicle relative to the self-vehicle in the target lane and the adjacent lane respectively using the first probability and the second probability corresponding to the target lane and the adjacent lane respectively; The intrusion assessment module is used to perform intrusion assessment on the target vehicle based on the change trend of the combined probability.

9. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the intrusion assessment method according to any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intrusion assessment method according to any one of claims 1 to 7 are implemented.

Images