A method, device, equipment and medium for passing vehicles in a merging section

Abstract

The present application discloses a method, device, equipment and medium for vehicles passing through a merging section, which relates to the field of intelligent driving technology, including: when a merging section is detected in a first range in front of the vehicle, judging whether the first left lane change condition is currently met; if not, detecting whether there is a first vehicle in a second range of the branch lane; the branch lane merges into the main lane at the end of the merging section; if there is a first vehicle in the second range, decelerating the vehicle based on a pre-deceleration mechanism to obtain the first speed of the vehicle; determining the passing probability of the first vehicle according to the first speed of the vehicle and the second speed of the first vehicle, and controlling the vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the vehicle, and the second speed is the real-time speed of the first vehicle. The present application improves the safety and accuracy of vehicles passing through the merging section and reduces the calculation cost.

Description

Technical Field

[0001] The present invention relates to the field of intelligent driving technology, and in particular to a method, device, equipment and medium for vehicles passing through a merging section. Background Art

[0002] When passing through a high-speed merging section, smart driving vehicles often find it difficult to deal with the merging behavior of vehicles merging from the right, mainly because the speed difference between the two vehicles is too large, resulting in a great risk of collision.

[0003] The existing technology uses a neural network model to predict the driving trajectory of a vehicle merging from the right, but this method still has the following defects: (1) A vehicle merging from the right will inevitably change lanes to the left. The essence of using a neural network model to predict the driving trajectory is to predict the timing of the vehicle's lane change. However, the timing of the lane change mainly depends on the driver, so there may be a problem of poor prediction effect; (2) The neural network model needs to collect a large amount of training data and requires a certain amount of computing power support, resulting in a relatively expensive prediction cost.

[0004] Therefore, there is an urgent need for a low-cost, efficient and fast method to enable L2+ vehicles to pass through the merging section smoothly. Summary of the invention

[0005] In view of this, the object of the present invention is to provide a method, device, equipment and medium for vehicles passing through a merging section, which can improve the safety and accuracy of vehicles passing through a merging section and reduce the calculation cost. The specific scheme is as follows:

[0006] In a first aspect, the present application discloses a method for vehicles passing through a merging section, comprising:

[0007] When detecting that there is a merging section within a first range in front of the vehicle, determining whether a first left lane change condition is currently met;

[0008] If the first left lane change condition is not met at present, detecting whether there is a first vehicle within the second range of the branch lane; the branch lane merges into the main road lane at the end of the merging section;

[0009] If the first vehicle exists within the second range, decelerating the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle;

[0010] The passing probability of the first vehicle is determined according to the first speed of the self-vehicle and the second speed of the first vehicle, and the self-vehicle is controlled to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the self-vehicle, and the second speed is the real-time speed of the first vehicle.

[0011] Optionally, decelerating the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle includes:

[0012] Determining a first collision time between the self-vehicle and the first vehicle;

[0013] If the first collision time is not greater than a first collision time threshold, decelerating the vehicle based on a first deceleration model to obtain a first speed of the vehicle;

[0014] If the first collision time is greater than the first collision time threshold, decelerating the vehicle based on a second deceleration model to obtain a first speed of the vehicle;

[0015] Wherein, the second deceleration model includes:

[0016] ;

[0017] in, represents the second deceleration, V ego represents the speed of the vehicle before deceleration, V a represents a second speed of the first vehicle, Indicates the preset speed difference threshold.

[0018] Optionally, determining the passing probability of the first vehicle according to the first speed of the own vehicle and the second speed of the first vehicle includes:

[0019] determining a second collision time between the self-vehicle and the first vehicle;

[0020] If the second collision time is greater than a second collision time threshold, determining the longitudinal speed of the ego vehicle according to the first speed of the ego vehicle, and determining the lateral speed of the first vehicle and the longitudinal speed of the first vehicle according to the second speed of the first vehicle;

[0021] The passing probability of the first vehicle is determined according to the lane width of the branch lane, the longitudinal speed of the own vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point.

[0022] Optionally, determining the passing probability of the first vehicle according to the lane width of the branch lane, the longitudinal speed of the vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point includes:

[0023] Based on the target calculation model, the lane width of the branch lane, the longitudinal speed of the self-vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point are calculated to determine the passing probability of the first vehicle;

[0024] Wherein, the target calculation model includes:

[0025] ;

[0026] in, represents the lane width of the branch lane, represents the longitudinal velocity of the vehicle, represents the lateral velocity of the first vehicle, represents the longitudinal velocity of the first vehicle, represents the third collision time threshold, represents the distance between the vehicle and the first vehicle, represents the distance between the first vehicle and the end point, represents an estimated value of the lane change distance of the first vehicle, and is the proportionality coefficient;

[0027] in, ;

[0028] in, Indicates the minimum distance allowed between the vehicle and the first vehicle.

[0029] Optionally, after determining the second collision time between the vehicle and the first vehicle, the method further includes:

[0030] If the second collision time is not greater than the second collision time threshold, the ego vehicle is directly controlled to pass through the merging section according to the first speed of the ego vehicle.

[0031] Optionally, in the process of decelerating the ego vehicle based on the pre-deceleration mechanism to obtain the first speed of the ego vehicle or in the process of determining the passing probability of the first vehicle according to the first speed of the ego vehicle and the second speed of the first vehicle, the method further includes:

[0032] Determine whether the second left lane change condition is currently met;

[0033] If the second left lane change condition is currently met, the vehicle is directly controlled to change lanes to the left.

[0034] Optionally, controlling the vehicle to pass through the merging section according to the passing probability includes:

[0035] Determining whether the passing probability is greater than a preset passing probability;

[0036] If the passing probability is greater than the preset passing probability, taking the first vehicle as a following target of the ego vehicle, and controlling the ego vehicle to pass through the merging section based on the following target;

[0037] If the passing probability is not greater than the preset passing probability, the vehicle is directly controlled to pass through the merging section at the first speed of the vehicle.

[0038] In a second aspect, the present application discloses a merging section vehicle passing device, comprising:

[0039] A lane change judgment module, configured to judge whether a first left lane change condition is currently met when a merging section is detected in a first range in front of the vehicle;

[0040] a vehicle detection module, configured to detect whether there is a first vehicle within a second range of the branch lane if the first left lane change condition is not currently met; the branch lane merges into the main lane at the end of the merging section;

[0041] a pre-deceleration module, configured to decelerate the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle if the first vehicle exists within the second range;

[0042] A merging section passing module is used to determine the passing probability of the first vehicle according to the first speed of the ego vehicle and the second speed of the first vehicle, and control the ego vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the ego vehicle, and the second speed is the real-time speed of the first vehicle.

[0043] In a third aspect, the present application discloses an electronic device, comprising:

[0044] Memory, used to store computer programs;

[0045] A processor is used to execute the computer program to implement the above-disclosed method for vehicles passing through a merging section.

[0046] In a fourth aspect, the present application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed method for passing vehicles through a merging section is implemented.

[0047] It can be seen that the present application proposes a method for vehicles to pass through a merging section, including: when a merging section is detected to exist within a first range in front of the own vehicle, determining whether a first left lane change condition is currently met; if the first left lane change condition is not currently met, detecting whether a first vehicle exists within a second range of a branch lane; the branch lane merges into the main lane at the end of the merging section; if the first vehicle exists within the second range, decelerating the own vehicle based on a pre-deceleration mechanism to obtain a first speed of the own vehicle; determining a passing probability of the first vehicle according to the first speed of the own vehicle and the second speed of the first vehicle, and controlling the own vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the own vehicle, and the second speed is the real-time speed of the first vehicle.

[0048] Beneficial effect: When the present application detects that there is a merging section within the first range in front of the own vehicle, it is determined whether the first left lane change condition is currently met. It can be understood that if the first left lane change condition is met, the lane is changed to the left directly so that the own vehicle can pass through the merging section safely and efficiently. Further, if the first left lane change condition is not met, it is determined whether there is a first vehicle within the second range of the branch lane. It can be understood that if there is no first vehicle within the second range, the own vehicle can directly pass through the merging section safely and efficiently. Further, if there is a first vehicle within the second range, the own vehicle is first decelerated to avoid a large difference in speed between the own vehicle and the first vehicle, resulting in a high risk of collision. Further, considering that the timing of the first vehicle merging into the main road lane will affect the driving safety of the own vehicle, for this reason, the present application determines the merging timing of the first vehicle based on the first speed of the own vehicle and the second speed of the first vehicle to obtain the passing probability of the first vehicle, and finally controls the own vehicle to pass through the merging section based on the passing probability. In this way, the present application improves the safety and accuracy of the vehicle passing through the merging section, while greatly reducing the calculation cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] 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, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0050] Figure 1 A flow chart of a method for passing vehicles through a merging section disclosed in the present application;

[0051] Figure 2 A schematic diagram of a confluence section disclosed in this application;

[0052] Figure 3 A flowchart of a specific method for passing vehicles through a merging section disclosed in this application;

[0053] Figure 4 A flowchart of another specific method for passing vehicles through a merging section disclosed in the present application;

[0054] Figure 5 This is a schematic diagram of the structure of a merging section vehicle passing device disclosed in this application;

[0055] Figure 6 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] The existing technology uses a neural network model to predict the driving trajectory of a vehicle merging from the right, but this method still has the following defects: (1) A vehicle merging from the right will inevitably change lanes to the left. The essence of using a neural network model to predict the driving trajectory is to predict the timing of the vehicle's lane change. However, the timing of the lane change mainly depends on the driver, so there may be a problem of poor prediction effect; (2) The neural network model needs to collect a large amount of training data and requires a certain amount of computing power support, resulting in a relatively expensive prediction cost.

[0058] To this end, an embodiment of the present application proposes a vehicle passing solution for a merging section, which can improve the safety and accuracy of vehicles passing through the merging section and reduce calculation costs.

[0059] The present application embodiment discloses a method for vehicles passing through a merging section, see Figure 1 As shown, the method includes:

[0060] Step S11: when it is detected that there is a merging section within a first range in front of the vehicle, it is determined whether a first left lane change condition is currently satisfied.

[0061] In this embodiment, when the vehicle is traveling in the first right main road lane of the expressway and a merging section is detected within a first range in front of the vehicle, it is determined whether a first left lane change condition is currently satisfied.

[0062] In a specific implementation, assuming that the vehicle speed is v, when the high-precision map shows that there is a merging section v×t ahead, it is determined whether the first condition for changing lanes to the left is currently met. For example, when the high-precision map shows that there is a merging section v×15s ahead, it is determined whether the first condition for changing lanes to the left is currently met. It can be understood that 15s is only a value of t in a specific driving scenario. In different driving scenarios, t can have different values, which are not limited here.

[0063] In this embodiment, if there is no second vehicle in the left lane of the vehicle and the left lane line is not a solid line, the first left lane change condition is currently met, and the vehicle is immediately controlled to change lanes to the left to avoid the merging section. In this way, the present application ensures that the vehicle can pass through the merging section safely and efficiently.

[0064] Step S12: If the first left lane change condition is not currently met, detecting whether there is a first vehicle within a second range of the branch lane; the branch lane merges into the main road lane at the end of the merging section.

[0065] From the above analysis, it can be seen that if there is a second vehicle in the left lane of the own vehicle or the left lane line is a solid line, the first left lane change condition is not met at present, and it is detected whether there is a first vehicle in the second range of the branch lane. The branch lane merges into the main lane at the end of the merging section. Furthermore, if there is no first vehicle in the second range of the branch lane, the own vehicle is controlled to pass through the merging section at the current driving speed. In this way, it is further ensured that the own vehicle can pass through the merging section safely and efficiently.

[0066] In a specific implementation, the second range is 200 m from the end point of the merging section. Similarly, 200 m is only used as a value of the second range in a specific driving scenario. In different driving scenarios, the second range may have different values, which are not limited here.

[0067] Step S13: If the first vehicle exists within the second range, the vehicle is decelerated based on a pre-deceleration mechanism to obtain a first speed of the vehicle.

[0068] It should be pointed out that if the first vehicle exists within the second range, in order to prevent a large speed difference between the own vehicle and the first vehicle, thereby causing a high risk of collision, the present embodiment needs to pre-decelerate the own vehicle based on a pre-deceleration mechanism to obtain the first speed of the own vehicle. It can be understood that the first speed is the speed of the own vehicle after deceleration.

[0069] The pre-deceleration mechanism is explained below:

[0070] First, determining a first collision time between the ego vehicle and the first vehicle; if the first collision time is not greater than a first collision time threshold, decelerating the ego vehicle based on a first deceleration model to obtain a first speed of the ego vehicle; if the first collision time is greater than the first collision time threshold, decelerating the ego vehicle based on a second deceleration model to obtain a first speed of the ego vehicle;

[0071] In a specific implementation, the first collision time threshold is 7 seconds, and the first deceleration corresponding to the first deceleration model is 0.4 m / s 2 , so that if the first collision time is no more than 7s, based on 0.4 m / s 2 The vehicle is decelerated, and the deceleration time can be maintained for 5 seconds. If the first collision time is greater than 7 seconds, the vehicle is decelerated based on a second deceleration model, wherein the second deceleration model includes:

[0072] ;

[0073] in, represents the second deceleration, V ego represents the speed of the vehicle before deceleration, V a represents a second speed of the first vehicle, Indicates the preset speed difference threshold.

[0074] Specifically, The value range is usually 15~25km / h. For example, assuming The value is 15km / h. When the second deceleration is 0, When the second deceleration is the target value, the target value may be 1.2 m / s 2 .

[0075] Considering that the first collision time may change at different times, in order to avoid the first collision time changing and causing the deceleration to be at the first deceleration of 0.4 m / s 2 and the second deceleration 1.2 m / s 2 A jump occurs between the two. In this embodiment, a preset operation is added to solve the above problem, which specifically includes:

[0076] Assuming that the first collision time captured in the first frame is 5s, the deceleration at this time is the first deceleration, which is 0.4 m / s 2 Furthermore, if the second frame captures the first collision time of 8s, then the deceleration at this time is the second deceleration, that is, 1.2m / s 2, and the first collision time threshold is subtracted based on the target change interval. Assuming that the target change interval is 0.2, the first collision time threshold is 6.8. In this way, when the first collision time collected in the third frame is 6.9s, the corresponding deceleration is the second deceleration, that is, 1.2 m / s 2 It can be seen that after the first collision time threshold is modified, the deceleration does not jump. If the first collision time threshold is not modified, the deceleration is 0.4 m / s when the first collision time collected in the third frame is 6.9s. 2 ,It can be seen that if the first collision time threshold is not modified, the deceleration will jump significantly, resulting in unstable vehicle driving.

[0077] In this embodiment, when the first vehicle is detected in the branch lane, the vehicle is pre-decelerated until it reaches x meters before the intersection, then the vehicle is stopped from decelerating and the vehicle is maintained at the first speed. It should be noted that x can have different values ​​in different driving scenarios. For example, if x is 20, when the first vehicle is detected in the branch lane, the vehicle is pre-decelerated until it reaches 20 meters before the intersection, then the vehicle is stopped from decelerating. Figure 2 As shown, the intersection point and the end point are respectively the starting point and the end point where the main road lane and the branch lane intersect.

[0078] It should be pointed out that the specific values ​​involved in the above process can be set according to the actual driving scenario, and this application does not impose any restrictions on this.

[0079] Step S14: Determine the passing probability of the first vehicle according to the first speed of the self-vehicle and the second speed of the first vehicle, and control the self-vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the self-vehicle, and the second speed is the real-time speed of the first vehicle.

[0080] It should be pointed out that, considering that the timing when the first vehicle merges into the main road lane will affect the driving safety of the own vehicle, this application judges the merging timing of the first vehicle based on the first speed of the own vehicle and the second speed of the first vehicle to obtain the passing probability of the first vehicle, and the passing probability is the probability that the first vehicle passes the merging section before the own vehicle.

[0081] Specifically, this embodiment first determines the second collision time between the ego vehicle and the first vehicle. If the second collision time is greater than the second collision time threshold, the longitudinal speed of the ego vehicle is determined according to the first speed of the ego vehicle, and the lateral speed of the first vehicle and the longitudinal speed of the first vehicle are determined according to the second speed of the first vehicle. Then, based on the target calculation model, the lane width of the branch lane, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, the longitudinal speed of the ego vehicle, and the distance between the first vehicle and the end point are calculated to determine the passing probability of the first vehicle, wherein the target calculation model includes:

[0082] ;

[0083] in, Indicates the lane width of the branch lane, which can be obtained through high-precision map data; represents the lateral speed of the first vehicle; represents the longitudinal speed of the vehicle, which can be obtained by a wheel speed sensor; represents the longitudinal speed of the first vehicle, which can be obtained by millimeter wave radar or smart camera, represents the third collision time threshold, represents the distance between the vehicle and the first vehicle, represents the distance between the first vehicle and the end point, is an adjustable constant, which represents the estimated distance of the first vehicle preparing to change lanes, and is the proportionality coefficient.

[0084] in, ;

[0085] in, Indicates the minimum distance allowed between the vehicle and the first vehicle.

[0086] The following is an explanation of each item of the target calculation model:

[0087] The first item is used to detect whether the first vehicle has a tendency to change lanes. The second item is used to determine the collision time difference between the first vehicle and the ego vehicle to determine the probability that the first vehicle will change lanes under different collision time differences. The third item is used to determine the probability that the first vehicle is forced to change lanes when it is close to the end point.

[0088] Specifically, for the first item, when the first vehicle has a lane-changing tendency, a corresponding lateral displacement will occur, that is, , assuming that the vehicle is traveling in the middle of the road, when the lateral displacement is greater than half the lane width, it indicates that the first vehicle will change lanes. When the lateral displacement is close to half the lane width, it indicates that the first vehicle is likely to change lanes. Furthermore, when the first vehicle only makes normal left and right swaying in the lane, the value calculated by the first item will be very small, indicating that it will not change lanes.

[0089] For the second item, assume When the collision time between the own vehicle and the first vehicle is 100s, when the collision time between the own vehicle and the first vehicle is close to 0, the result calculated by the exponential function is 0, which means that the first vehicle is very close to the own vehicle and the first vehicle does not change lanes. When the collision time between the own vehicle and the first vehicle is relatively large, for example, 80s, it means that the speeds of the two vehicles are close, and the result calculated by the exponential function is close to 1, indicating a high probability of changing lanes.

[0090] Regarding the third item, the third item calculates the distance between the first vehicle and the end point. If the distance is too small, the probability of being forced to change lanes increases.

[0091] It should be pointed out that the first collision time and the second collision time of the present application are the collision times between the own vehicle and the first vehicle at different times, and are essentially the collision times between the two vehicles.

[0092] In addition, if the second collision time is not greater than the second collision time threshold, it is theoretically considered that the first vehicle gives priority to the ego vehicle to pass, and the ego vehicle is directly controlled to pass through the merging section according to the first speed of the ego vehicle.

[0093] Exemplarily, the second collision time threshold may be 5s. If the second collision time is greater than 5s, the passing probability is calculated according to the target calculation model. Further, this embodiment determines whether the passing probability is greater than a preset passing probability. If the passing probability is greater than the preset passing probability, the first vehicle is used as the following target of the self-vehicle, and the self-vehicle is controlled to pass through the merging section based on the following target. If the passing probability is not greater than the preset passing probability, the self-vehicle is directly controlled to pass through the merging section at the first speed of the self-vehicle. Exemplarily, assuming that the passing probability threshold is 0.5, if the passing probability is greater than 0.5, it indicates that the first vehicle has a greater probability of passing through the merging section before the self-vehicle, and the first vehicle is used as the following target of the self-vehicle to control the self-vehicle to pass through the merging section. If the passing probability is less than 0.5, it indicates that the first vehicle has a smaller probability of passing through the merging section before the self-vehicle, and the self-vehicle is controlled to pass through the merging section according to the first speed of the self-vehicle, and a reminder to pay attention to the right vehicle merging is broadcast.

[0094] It can be seen that the present application proposes a method for vehicles to pass through a merging section, including: when a merging section is detected to exist within a first range in front of the own vehicle, determining whether a first left lane change condition is currently met; if the first left lane change condition is not currently met, detecting whether a first vehicle exists within a second range of a branch lane; the branch lane merges into the main lane at the end of the merging section; if the first vehicle exists within the second range, decelerating the own vehicle based on a pre-deceleration mechanism to obtain a first speed of the own vehicle; determining a passing probability of the first vehicle according to the first speed of the own vehicle and the second speed of the first vehicle, and controlling the own vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the own vehicle, and the second speed is the real-time speed of the first vehicle.

[0095] Beneficial effect: When the present application detects that there is a merging section within the first range in front of the own vehicle, it is determined whether the first left lane change condition is currently met. It can be understood that if the first left lane change condition is met, the lane is changed to the left directly so that the own vehicle can pass through the merging section safely and efficiently. Further, if the first left lane change condition is not met, it is determined whether there is a first vehicle within the second range of the branch lane. It can be understood that if there is no first vehicle within the second range, the own vehicle can directly pass through the merging section safely and efficiently. Further, if there is a first vehicle within the second range, the own vehicle is first decelerated to avoid a large difference in speed between the own vehicle and the first vehicle, resulting in a high risk of collision. Further, considering that the timing of the first vehicle merging into the main road lane will affect the driving safety of the own vehicle, for this reason, the present application determines the merging timing of the first vehicle based on the first speed of the own vehicle and the second speed of the first vehicle to obtain the passing probability of the first vehicle, and finally controls the own vehicle to pass through the merging section based on the passing probability. In this way, the present application improves the safety and accuracy of the vehicle passing through the merging section, while greatly reducing the calculation cost.

[0096] The embodiment of the present application discloses a specific method for vehicles passing through a merging section. Compared with the previous embodiment, this embodiment further illustrates and optimizes the technical solution. Figure 3 As shown, specifically including:

[0097] Step S21: Determine whether the second lane change condition to the left is currently met.

[0098] Step S22: If the second lane-changing condition to the left is currently satisfied, directly control the vehicle to change lanes to the left.

[0099] From the above analysis, it can be seen that the present application judges the merging timing of the first vehicle to ensure that the own vehicle can safely pass through the merging section, but this process will reduce the driving efficiency of the own vehicle to a certain extent. In order to further optimize the method described in the present application, the present embodiment proposes to introduce a priority judgment, that is, to judge whether the second left lane change condition is currently met. If it is met, the own vehicle is controlled to change lanes to the left first. In this way, it is ensured that the own vehicle can avoid the merging section and the first vehicle can safely merge into the merging section. At the same time, it will not cause danger to the second vehicle on the left lane, thereby improving the driving efficiency of the own vehicle. See Figure 4 As shown, the vehicle is traveling in the right main road lane, and first determines whether the first left lane change condition is currently met. If so, it changes lanes directly to the left. If not, it determines whether there is a first vehicle in the branch lane. If not, it directly passes through the merging section. If so, it determines the first lateral collision time, and pre-decelerates the vehicle according to the first lateral collision time, and then determines the second lateral collision time to determine the passing probability, and determines whether to take the first vehicle as the following target based on the passing probability. Furthermore, in order to improve the driving efficiency of the vehicle, this embodiment determines in real time whether the second left lane change condition is currently met at any stage after determining whether there is a first vehicle in the branch lane, so as to determine the priority. If met, the vehicle is preferentially controlled to change lanes to the left.

[0100] Specifically, the second left lane change condition is that the speed of the vehicle in the left lane is greater than the speed of the vehicle itself, the speed of the vehicle in the left lane is greater than the speed of the first vehicle, and the left lane line is not a solid line.

[0101] From the above, it can be seen that the present application can improve the safety of vehicles passing through safe sections, and the present application does not require the use of a neural network model method, which reduces computing costs and is more competitive.

[0102] Correspondingly, the embodiment of the present application also discloses a merging section vehicle passing device, see Figure 5 As shown, the device comprises:

[0103] A lane change judgment module 11 is used to judge whether a first left lane change condition is currently met when a merging section is detected in a first range in front of the vehicle;

[0104] The vehicle detection module 12 is used to detect whether there is a first vehicle in the second range of the branch lane if the first left lane change condition is not currently met; the branch lane merges into the main road lane at the end of the merging section;

[0105] A pre-deceleration module 13 is configured to decelerate the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle if the first vehicle exists within the second range;

[0106] The merging section passing module 14 is used to determine the passing probability of the first vehicle according to the first speed of the ego vehicle and the second speed of the first vehicle, and control the ego vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the ego vehicle, and the second speed is the real-time speed of the first vehicle.

[0107] Among them, for more specific working processes of the above-mentioned modules, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0108] It can be seen that the present application proposes a method for vehicles to pass through a merging section, including: when a merging section is detected to exist within a first range in front of the own vehicle, determining whether a first left lane change condition is currently met; if the first left lane change condition is not currently met, detecting whether a first vehicle exists within a second range of a branch lane; the branch lane merges into the main lane at the end of the merging section; if the first vehicle exists within the second range, decelerating the own vehicle based on a pre-deceleration mechanism to obtain a first speed of the own vehicle; determining a passing probability of the first vehicle according to the first speed of the own vehicle and the second speed of the first vehicle, and controlling the own vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the own vehicle, and the second speed is the real-time speed of the first vehicle.

[0109] Beneficial effect: When the present application detects that there is a merging section within the first range in front of the own vehicle, it is determined whether the first left lane change condition is currently met. It can be understood that if the first left lane change condition is met, the lane is changed to the left directly so that the own vehicle can pass through the merging section safely and efficiently. Further, if the first left lane change condition is not met, it is determined whether there is a first vehicle within the second range of the branch lane. It can be understood that if there is no first vehicle within the second range, the own vehicle can directly pass through the merging section safely and efficiently. Further, if there is a first vehicle within the second range, the own vehicle is first decelerated to avoid a large difference in speed between the own vehicle and the first vehicle, thereby causing a high risk of collision. Further, considering that the timing of the first vehicle merging into the main road lane will affect the driving safety of the own vehicle, for this reason, the present application determines the merging timing of the first vehicle based on the first speed of the own vehicle and the second speed of the first vehicle to obtain the passing probability of the first vehicle, and finally controls the own vehicle to pass through the merging section based on the passing probability. In this way, the present application improves the safety and accuracy of the vehicle passing through the merging section, while greatly reducing the calculation cost.

[0110] Furthermore, an embodiment of the present application also provides an electronic device. Figure 6This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0111] Figure 6 The present invention provides a schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the vehicle passing method of the merging section disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0112] In this embodiment, the power supply 26 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 25 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 24 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0113] In addition, the memory 22, as a carrier for storing resources, may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include a computer program 221, and the storage method may be temporary storage or permanent storage. In addition to the computer program that can be used to complete the vehicle passing method of the merging section executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 221 may further include a computer program that can be used to complete other specific tasks.

[0114] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the above-disclosed method for passing vehicles through a merging section is implemented.

[0115] For the specific steps of the method, reference may be made to the corresponding contents disclosed in the aforementioned embodiments, which will not be described in detail here.

[0116] The various embodiments in this application are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced 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 description.

[0117] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in 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 the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians 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.

[0118] 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.

[0119] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used 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", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0120] The above is a detailed introduction to a method, device, equipment, and storage medium for passing vehicles in a merging section provided by the present application. Specific examples are used in this article 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 of the present application and its core idea; at the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for vehicles passing through a merging section, characterized in that: include: When detecting that there is a merging section within a first range in front of the vehicle, determining whether a first left lane change condition is currently met; If the first left lane change condition is not met currently, detecting whether there is a first vehicle within the second range of the branch lane; The branch lane merges into the main lane at the end of the merging section; If the first vehicle exists within the second range, decelerating the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle; Determine a passing probability of the first vehicle according to a first speed of the ego vehicle and a second speed of the first vehicle, and control the ego vehicle to pass through the merging section according to the passing probability; wherein the passing probability is a probability that the first vehicle passes through the merging section before the ego vehicle, and the second speed is a real-time speed of the first vehicle; wherein, based on the target calculation model, the lane width of the branch lane, the longitudinal speed of the self-vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point are calculated to determine the passing probability of the first vehicle; Wherein, the target calculation model includes: Among them, W 右 represents the lane width of the branch lane, V1 represents the longitudinal speed of the vehicle, V a横 represents the lateral speed of the first vehicle, V2 represents the longitudinal speed of the first vehicle, TTC a represents the third collision time threshold, d a represents the distance between the vehicle and the first vehicle, L 右a represents the distance between the first vehicle and the end point, η represents the estimated lane change distance of the first vehicle, and c and k are proportional coefficients; in, Wherein, ε represents the minimum distance allowed between the ego vehicle and the first vehicle.

2. The method for passing a vehicle through a merging section according to claim 1, characterized in that: The decelerating the vehicle based on the pre-deceleration mechanism to obtain the first speed of the vehicle includes: Determining a first collision time between the self-vehicle and the first vehicle; If the first collision time is not greater than a first collision time threshold, decelerating the vehicle based on a first deceleration model to obtain a first speed of the vehicle; If the first collision time is greater than the first collision time threshold, decelerating the vehicle based on a second deceleration model to obtain a first speed of the vehicle; Wherein, the second deceleration model includes: Wherein, a1 represents the second deceleration, V ego represents the speed of the vehicle before deceleration, V a represents the second speed of the first vehicle, and α represents a preset speed difference threshold.

3. The method for passing a vehicle through a merging section according to claim 1, characterized in that: The determining the passing probability of the first vehicle according to the first speed of the own vehicle and the second speed of the first vehicle includes: determining a second collision time between the self-vehicle and the first vehicle; If the second collision time is greater than a second collision time threshold, determining the longitudinal speed of the ego vehicle according to the first speed of the ego vehicle, and determining the lateral speed of the first vehicle and the longitudinal speed of the first vehicle according to the second speed of the first vehicle; The passing probability of the first vehicle is determined according to the lane width of the branch lane, the longitudinal speed of the own vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point.

4. The method for passing a vehicle through a merging section according to claim 3, characterized in that: After determining the second collision time between the vehicle and the first vehicle, the method further includes: If the second collision time is not greater than the second collision time threshold, the ego vehicle is directly controlled to pass through the merging section according to the first speed of the ego vehicle.

5. The method for passing a vehicle through a merging section according to claim 1, characterized in that: The process of decelerating the ego vehicle based on the pre-deceleration mechanism to obtain the first speed of the ego vehicle or determining the passing probability of the first vehicle according to the first speed of the ego vehicle and the second speed of the first vehicle also includes: Determine whether the second left lane change condition is currently met; If the second left lane change condition is currently met, the vehicle is directly controlled to change lanes to the left.

6. The method for passing a vehicle through a merging section according to claim 1, characterized in that: The controlling the vehicle to pass through the merging section according to the passing probability includes: Determining whether the passing probability is greater than a preset passing probability; If the passing probability is greater than the preset passing probability, taking the first vehicle as a following target of the ego vehicle, and controlling the ego vehicle to pass through the merging section based on the following target; If the passing probability is not greater than the preset passing probability, the vehicle is directly controlled to pass through the merging section at the first speed of the vehicle.

7. The method for passing a vehicle through a merging section according to claim 1, characterized in that: Also includes: The first item of the target calculation model is used to detect whether the first vehicle has a tendency to change lanes, the second item is used to determine the collision time difference between the first vehicle and the own vehicle to determine the probability that the first vehicle will change lanes under different collision time differences, and the third item is used to determine the probability that the first vehicle is forced to change lanes when it is close to the end point.

8. A vehicle passing device in a merging section, characterized in that: include: A lane change judgment module, configured to judge whether a first left lane change condition is currently met when a merging section is detected in a first range in front of the vehicle; a vehicle detection module, configured to detect whether there is a first vehicle within a second range of the branch lane if the first left lane change condition is not currently met; The branch lane merges into the main lane at the end of the merging section; a pre-deceleration module, configured to decelerate the vehicle based on a pre-deceleration mechanism to obtain a first speed of the vehicle if the first vehicle exists within the second range; a merging section passing module, used to determine the passing probability of the first vehicle according to the first speed of the ego vehicle and the second speed of the first vehicle, and control the ego vehicle to pass through the merging section according to the passing probability; wherein the passing probability is the probability that the first vehicle passes through the merging section before the ego vehicle, and the second speed is the real-time speed of the first vehicle; wherein, based on the target calculation model, the lane width of the branch lane, the longitudinal speed of the self-vehicle, the lateral speed of the first vehicle, the longitudinal speed of the first vehicle, and the distance between the first vehicle and the end point are calculated to determine the passing probability of the first vehicle; Wherein, the target calculation model includes: Among them, W 右 represents the lane width of the branch lane, V1 represents the longitudinal speed of the vehicle, V a横 represents the lateral speed of the first vehicle, V2 represents the longitudinal speed of the first vehicle, TTC a represents the third collision time threshold, d a represents the distance between the vehicle and the first vehicle, L 右a represents the distance between the first vehicle and the end point, η represents the estimated lane change distance of the first vehicle, and c and k are proportional coefficients; in, Wherein, ε represents the minimum distance allowed between the ego vehicle and the first vehicle.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor is used to execute the computer program to implement the vehicle passing method of the merging section according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program; wherein, when the computer program is executed by a processor, the method for vehicles passing through a merging section as claimed in any one of claims 1 to 7 is implemented.

Images