A method, device, electronic device and storage medium for selecting a lane gap

Abstract

The present application discloses a method, device, electronic device and storage medium for selecting a lane gap, relating to the field of artificial intelligence, and particularly to autonomous driving technology. The specific implementation solution is as follows: when the host vehicle meets the lane-changing condition, extract the characteristics of the driving environment where the host vehicle is located at the current moment; calculate the lane-changing costs corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; select the target gap of the host vehicle at the current moment according to the lane-changing costs corresponding to each candidate gap. The embodiments of the present application can adaptively select the optimal gap, increase the merging opportunity, enhance the lane-changing merging ability, and improve the intelligence of autonomous driving.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and further relates to autonomous driving technology, in particular to a method, apparatus, electronic device and storage medium for selecting a lane gap. Background Art

[0002] When an autonomous vehicle changes lanes, it needs to interact with obstacles in the target lane. Figure 1 It is a schematic diagram of the driving of an autonomous vehicle provided by the prior art. As Figure 1 shown, the left lane includes three social vehicles, which are, in order from front to back: social vehicle 1, social vehicle 2, and social vehicle 3. At this time, there are 4 gaps in the left lane, namely: the gap in front of social vehicle 1, the gap formed by social vehicle 1 and social vehicle 2, the gap formed by social vehicle 2 and social vehicle 3, and the gap behind social vehicle 3. According to the planned route, the host vehicle is going to turn to the left lane ahead. When the host vehicle changes lanes to the left, it needs to determine the target gap (the empty space formed by obstacles). In the prior art, the host vehicle will default to select the gap that is currently the closest to the host vehicle. Using the above lane-changing scheme, the host vehicle cannot adaptively select the target gap according to the traffic flow conditions of the current lane and the target lane, and the gap that is currently the closest to the host vehicle is not necessarily the optimal choice. This may cause insufficient lane-changing and merging ability of the autonomous vehicle, resulting in the situation that it cannot merge into the target lane, or even get stuck, blocking traffic and affecting vehicle passage. Summary of the Invention

[0003] The present disclosure provides a method, apparatus, electronic device and storage medium for selecting a lane gap.

[0004] In a first aspect, the present application provides a method for selecting a lane gap, the method comprising:

[0005] When the host vehicle meets the lane-changing condition, extracting the characteristics of the driving environment where the host vehicle is located at the current moment;

[0006] Calculating the lane-changing cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located;

[0007] Selecting the target gap of the host vehicle at the current moment according to the lane-changing cost corresponding to each candidate gap.

[0008] In a second aspect, the present application provides a device for selecting a lane gap, the device comprising: an extraction module, a calculation module, and a selection module; wherein,

[0009] The extraction module is configured to extract the characteristics of the driving environment where the host vehicle is located at the current moment when the host vehicle meets the lane-changing condition;

[0010] The calculation module is configured to calculate the lane change cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located.

[0011] The selection module is configured to select the target gap of the host vehicle at the current moment according to the lane change cost corresponding to each candidate gap.

[0012] In a third aspect, an embodiment of the present application provides an electronic device, including:

[0013] One or more processors;

[0014] A memory for storing one or more programs,

[0015] When the one or more programs are executed by the one or more processors, the one or more processors implement the method for selecting a lane gap according to any embodiment of the present application.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, the method for selecting a lane gap according to any embodiment of the present application is implemented.

[0017] In a fifth aspect, a computer program product is provided, and when the computer program product is executed by a computer device, the method for selecting a lane gap according to any embodiment of the present application is implemented.

[0018] The technology according to the present application solves the technical problem in the prior art that the host vehicle only defaults to select the gap closest to the host vehicle at present, but the gap closest to the host vehicle at present is not necessarily the optimal choice, which may cause insufficient lane change and merging ability of the autonomous vehicle, resulting in the situation that it cannot merge into the target lane, or even get stuck, blocking traffic and affecting vehicle traffic. The technical solution provided by the present application can adaptively select the optimal gap, increase the merging opportunity, enhance the lane change and merging ability, and improve the intelligence of autonomous driving.

[0019] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0021] Figure 1 is a schematic diagram of the driving of an autonomous vehicle provided by the prior art;

[0022] Figure 2It is the first process schematic diagram of the method for selecting lane gaps provided by an embodiment of the present application;

[0023] Figure 3 It is the second process schematic diagram of the method for selecting lane gaps provided by an embodiment of the present application;

[0024] Figure 4 It is the structural schematic diagram of the gap selection system provided by an embodiment of the present application;

[0025] Figure 5 It is the third process schematic diagram of the method for selecting lane gaps provided by an embodiment of the present application;

[0026] Figure 6 It is the structural schematic diagram of the device for selecting lane gaps provided by an embodiment of the present application;

[0027] Figure 7 It is the block diagram of the electronic device for implementing the method for selecting lane gaps in an embodiment of the present application. Specific Embodiments

[0028] The following describes exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0029] Embodiment 1

[0030] Figure 2 It is the first process schematic diagram of the method for selecting lane gaps provided by an embodiment of the present application. This method can be executed by a device for selecting lane gaps or an electronic device, which can be implemented in a software and / or hardware manner and can be integrated into any intelligent device with network communication functions. As Figure 2 shown, the method for selecting lane gaps may include the following steps:

[0031] S201. When the host vehicle meets the lane change condition, extract the characteristics of the driving environment where the host vehicle is located at the current moment.

[0032] In this step, when the host vehicle meets the lane-changing condition, the electronic device can extract the characteristics of the driving environment where the host vehicle is located at the current moment. Among them, the characteristics of the driving environment where the host vehicle is located include: the driving state of the first vehicle in front of the host vehicle; the driving state of the first vehicle behind the host vehicle; the distance of the host vehicle from the end of the lane-changing section on the current lane; the speed limit of the current lane where the host vehicle is located and the speed limit of the target lane where the host vehicle is located; the driving state of the host vehicle; the driving states of the respective candidate gaps in the target lane.

[0033] As Figure 1 shown, the left lane includes three social vehicles, which are, in order from front to back: Social Vehicle 1, Social Vehicle 2, and Social Vehicle 3. At this time, there are 4 gaps in the left lane, namely: the gap in front of Social Vehicle 1, the gap formed by Social Vehicle 1 and Social Vehicle 2, the gap formed by Social Vehicle 2 and Social Vehicle 3, and the gap behind Social Vehicle 3. According to the planned route, the host vehicle is to turn into the left lane ahead. When the host vehicle changes lanes to the left, it is necessary to determine the target gap (the empty space formed by obstacles). In a specific embodiment of the present application, the host vehicle no longer defaults to selecting the gap closest to the host vehicle at present. Instead, when it is determined that a lane change is needed, the electronic device first extracts the characteristics of the driving environment where the host vehicle is located at the current moment; then adaptively selects the optimal target gap based on the characteristics of the driving environment. This can solve the problem of insufficient lane-changing and merging ability of vehicles and avoid traffic jams.

[0034] S202. Calculate the lane-changing costs corresponding to the respective candidate gaps in the target lane according to the characteristics of the driving environment where the host vehicle is located.

[0035] In this step, the electronic device can calculate the lane-changing costs corresponding to the respective candidate gaps in the target lane according to the characteristics of the driving environment where the host vehicle is located. Specifically, the electronic device can first calculate the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; then calculate the lane-changing cost corresponding to each candidate gap according to the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane. Among them, the length cost is used to measure the cost of the host vehicle inserting into the corresponding length of each candidate gap; the longer the length of the candidate gap, the smaller the length cost, that is, the smaller the cost of the host vehicle inserting into the corresponding length of each candidate gap. The head cost is used to measure the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap; the greater the head cost, that is, the greater the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap. The tail cost is used to measure the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap; the greater the tail cost, that is, the greater the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap.

[0036] S203. Select the target gap of the host vehicle at the current moment according to the lane change costs corresponding to each candidate gap.

[0037] In this step, the electronic device can select the target gap of the host vehicle at the current moment according to the lane change costs corresponding to each candidate gap. Specifically, the electronic device can select the gap with the minimum lane change cost as the target gap of the host vehicle at the current moment. It should be noted that at different moments, the target gaps selected for the same host vehicle can be the same or different.

[0038] For the method for selecting a lane gap proposed in the embodiments of the present application, when the host vehicle meets the lane change condition, first extract the characteristics of the driving environment where the host vehicle is located at the current moment; then calculate the lane change costs corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; and then select the target gap of the host vehicle at the current moment according to the lane change costs corresponding to each candidate gap. That is to say, the present application can automatically calculate the lane change costs corresponding to each candidate gap; and then adaptively select the target gap according to the lane change costs corresponding to each candidate gap. In the existing method for selecting a lane gap, the host vehicle only defaults to select the gap closest to the host vehicle currently. Because the present application adopts the technical means of automatically calculating the lane change costs corresponding to each candidate gap and adaptively selecting the target gap according to the lane change costs corresponding to each candidate gap, it overcomes the technical problem in the prior art that the host vehicle only defaults to select the gap closest to the host vehicle currently, but the gap closest to the host vehicle currently is not necessarily the optimal choice, which may cause insufficient lane change and merging ability of the autonomous vehicle, resulting in the situation that it cannot merge into the target lane, or even get stuck, blocking traffic and affecting vehicle traffic. The technical solution provided by the present application can adaptively select the optimal gap, increase the merging opportunity, enhance the lane change and merging ability, and improve the intelligence of autonomous driving; moreover, the technical solution of the embodiments of the present application is simple and convenient to implement, easy to popularize, and has a wider application range.

[0039] Embodiment 2

[0040] Figure 3 It is the second process schematic diagram of the method for selecting a lane gap provided by the embodiments of the present application. Based on the above technical solution, it is further optimized and extended, and can be combined with each of the above optional implementation manners. As Figure 3 shown, the method for selecting a lane gap may include the following steps:

[0041] S301. When the host vehicle meets the lane change condition, extract the characteristics of the driving environment where the host vehicle is located at the current moment.

[0042] In this step, when the host vehicle meets the lane-changing condition, the electronic device can extract the characteristics of the driving environment where the host vehicle is located at the current moment. Among them, the characteristics of the driving environment where the host vehicle is located include: the driving state of the first vehicle in front of the host vehicle; the driving state of the first vehicle behind the host vehicle; the distance of the host vehicle from the end of the lane-changing section in the current lane; the road speed limit of the host vehicle in the current lane and the road speed limit of the host vehicle in the target lane; the driving state of the host vehicle; the driving states of the respective candidate gaps in the target lane. As Figure 1 shown, the main factors affecting the selection of the target gap are as follows: ① The driving state of the first vehicle in front of the host vehicle, which may include but is not limited to the speed, acceleration, and position of the vehicle at the current moment; ② The driving state of the first vehicle behind the host vehicle, which may include but is not limited to the speed, acceleration, and position of the vehicle at the current moment; ③ The distance of the host vehicle from the end of the lane-changing section in the current lane; ④ The speed limit of the current lane for the host vehicle and the speed limit of the target lane for the host vehicle; ⑤ The driving state of the host vehicle, which may include but is not limited to the speed, acceleration, and position of the host vehicle at the current moment; ⑥ The driving state of the target gap, which may include but is not limited to the speed, acceleration, and position of the first vehicle in front of the target gap and the speed, acceleration, and position of the first vehicle behind the target gap. Among the above influencing factors, for the first five factors, the influence on each gap is the same; for the last factor, since the driving states of the two vehicles forming the gap are different, the influence on different gaps is different. For example, as Figure 1 shown, the above first five factors are respectively: ① The driving state of social vehicle 4; ② The driving state of social vehicle 5; ③ The distance of the host vehicle from the end of the lane-changing section in the middle lane; ④ The speed limit of the middle lane for the host vehicle and the speed limit of the left lane for the host vehicle; ⑤ The driving state of the host vehicle. These five factors are common factors for the four gaps in the left lane, that is, the influence of these five factors on the gap in front of social vehicle 1, the gap formed by social vehicle 1 and social vehicle 2, the gap formed by social vehicle 2 and social vehicle 3, and the gap behind social vehicle 3 is the same. Therefore, for the first five factors, the influence on each gap is the same. For the last factor, for the gap in front of social vehicle 1, the driving state of this gap is determined by social vehicle 1; for the gap formed by social vehicle 1 and social vehicle 2, the driving state of this gap is jointly determined by social vehicle 1 and social vehicle 2; for the gap formed by social vehicle 2 and social vehicle 3, the driving state of this gap is jointly determined by social vehicle 2 and social vehicle 3; for the gap behind social vehicle 3, the driving state of this gap is determined by social vehicle 3. Therefore, for the last factor, since the driving states of the two vehicles forming the gap are different, the influence on different gaps is different.

[0043] In a specific embodiment of the present application, Figure 4 is a schematic structural diagram of a gap selection system provided by an embodiment of the present application. As Figure 4 shown, the gap selection system may include: a gap feature extraction module, a rough planner, a cost evaluation system module, and an optimal gap selection module; wherein, the number of the gap feature extraction module, the rough planner, and the cost evaluation system module may be N, and N is a natural number greater than or equal to 1; the number of the optimal gap selection module is 1. Specifically, the gap feature extraction module is used to extract the features of the driving environment where the host vehicle is located at the current moment; after the gap feature extraction module extracts the features of the driving environment where the host vehicle is located, it inputs them into the rough planner. The rough planner can be implemented by using a simple ST graph (Spatio-Temporal Graph) to express the driving trajectories of the first vehicle in front of each gap and / or the driving trajectory of the first vehicle behind the gap, the driving trajectory of the first vehicle in front of the host vehicle, and the driving trajectory of the first vehicle behind the host vehicle in the ST graph, and then the speed planning required for the host vehicle to merge behind the first vehicle in front of the gap and in front of the first vehicle behind the gap can be solved. For the prediction of the vehicle driving state, the driving state of the vehicle at the next moment can be predicted according to the driving state of the vehicle at the current moment. For the prediction of the vehicle driving trajectory, the driving trajectory of the vehicle in the next time period can be predicted according to the driving trajectory of the vehicle in the current time period. The cost evaluation system module is used to calculate the lane change costs corresponding to each candidate gap according to the features of the driving environment where the host vehicle is located; the optimal gap selection module is used to select the target gap of the host vehicle at the current moment according to the lane change costs corresponding to each candidate gap.

[0044] S302. Calculate the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane according to the features of the driving environment where the host vehicle is located; wherein, the length cost is used to measure the cost of the host vehicle inserting into the corresponding length of each candidate gap; the head cost is used to measure the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap; the tail cost is used to measure the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap.

[0045] In this step, the electronic device can calculate the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located. Specifically, when calculating the length cost corresponding to each candidate gap in the target lane, the electronic device can first calculate the actual length and expected length of each candidate gap in the target lane based on the position of the first vehicle in front of each candidate gap and the position of the first vehicle behind each candidate gap in the target lane; then, based on the actual length and expected length of each candidate gap in the target lane, and a preset reference length cost, calculate the length cost corresponding to each candidate gap in the target lane. Specifically, the electronic device can calculate the length cost corresponding to each candidate gap in the target lane according to the following formula: cost length = cos t base ×max(0, (1 - length gap / length desire )); where, cos t base represents the preset reference length cost; length gap represents the actual length of each candidate gap; length desire represents the expected length of each candidate gap.

[0046] In addition, when calculating the head cost corresponding to each candidate gap in the target lane, the electronic device can first calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it according to the characteristics of the driving environment where the host vehicle is located; then, based on the distance cost between the host vehicle and the vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it, calculate the head cost corresponding to each candidate gap in the target lane. Specifically, the electronic device can calculate the head cost corresponding to each candidate gap in the target lane according to the following formula: cos t lead = cos t dis1 + cos t brake + cost crtail ; where, cos t dis is used to measure the distance cost between the host vehicle and the first vehicle in front of the gap. Based on l lead calculated above as the expected value, the smaller the actual value is compared to the expected value, the larger cos t dis1 . As Figure 1 shown, taking the gap in front of social vehicle 1 as an example, there is no first vehicle in front of the gap at this time, so cos t lead is equal to 0. Taking the gap behind social vehicle 3 as an example, at this time social vehicle 3 is the first vehicle in front of the gap. The more the host vehicle exceeds the first vehicle in front of the gap, the larger costdis1 The larger it is; in terms of speed, the faster the host vehicle is compared to the speed of the first vehicle in front of the gap, the higher the cost for the host vehicle to brake and merge into the gap, that is, cost brake The larger it is. The greater the impact of the host vehicle on the social vehicle 5, that is, cost crtail The larger it is. The solution provided by the embodiment of the present application calculates the head costs corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle in front of the gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it. The considered factors are more comprehensive, and the calculated tail costs corresponding to each candidate gap are more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0047] In addition, when calculating the tail costs corresponding to each candidate gap in the target lane, the electronic device can first calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit according to the characteristics of the driving environment where the host vehicle is located; then calculate the tail costs corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit. Specifically, the electronic device can calculate the tail costs corresponding to each candidate gap in the target lane according to the following formula: cost tail = cost dis2 + cost acc + cost feasibility + cost overspeed ; where cost dis2 is used to measure the distance cost between the host vehicle and the first vehicle behind the gap; based on the calculated l tail as the expected value, the smaller the actual value is compared to the expected value, the larger cost dis2 is; cost acc is used to represent the acceleration cost of the host vehicle; cost feasibility is used to represent the acceleration feasibility cost of the host vehicle; cost overspeed is used to represent the penalty cost for the host vehicle exceeding the speed limit. It should be noted that the tail costs in the embodiment of the present application are used to measure the cost for the host vehicle to insert in front of the first vehicle behind each candidate gap. The tail costs can be jointly determined by the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit. The specific explanation is as follows. The distance cost between the host vehicle and the first vehicle behind each candidate gap can be represented by cost dis2It is indicated that the distance cost can be used to measure the cost for the host vehicle to insert into each candidate gap due to the first vehicle behind the gap. Assume that the host vehicle inserts into a certain gap. If the distance between the host vehicle and the first vehicle behind the gap is larger, then the distance cost between the host vehicle and the first vehicle behind the gap is smaller. The acceleration cost of the host vehicle can be represented by cost acc It is indicated that the acceleration cost can be used to measure the cost of the acceleration of the host vehicle at the current moment for the host vehicle to change lanes. The larger the acceleration of the host vehicle, the higher the acceleration cost. The acceleration feasibility cost of the host vehicle can be represented by cost feasibility It is indicated that the larger the acceleration of the host vehicle, the higher the acceleration possibility cost. The penalty cost for the host vehicle to exceed the speed limit can be represented by cost overspeed It is indicated that the more the host vehicle exceeds the speed limit of the current lane or the target lane, the higher the penalty cost for exceeding the speed limit. As Figure 1 shown, taking the gap behind the social vehicle 3 as an example, there is no first vehicle behind the gap at this time, then cost tail is equal to 0. Taking the gap in front of the social vehicle 1 as an example again, at this time the social vehicle 1 is the first vehicle behind the gap. The more the host vehicle lags behind the social vehicle 1 and the slower the speed, so cost dis2 is larger, and the higher the cost for the host vehicle to accelerate and catch up, that is, cost acc is larger. At the same time, based on the solution result of the rough planner, it may occur that the host vehicle needs to exceed the first vehicle in front of the host vehicle in the current lane or exceed the remaining passing length in order to accelerate and catch up with the first vehicle behind the gap. At this time, it will be considered that it is not feasible for the host vehicle to merge into the gap in front of the social vehicle 1, and at this time cost feasibility will be relatively large. Similarly, the more the solution result of the rough planner exceeds the speed limit, cost overspeed will be larger. The solution provided in the embodiment of the present application calculates the tail costs corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle behind the gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle to exceed the speed limit. The considered factors are more comprehensive, and the calculated tail costs corresponding to each candidate gap are more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0048] S303. Calculate the lane change costs corresponding to each candidate gap according to the length costs, head costs, and tail costs corresponding to each candidate gap in the target lane.

[0049] In this step, the electronic device can calculate the lane change cost corresponding to each candidate gap in the target lane according to the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane. Specifically, the electronic device can calculate the lane change cost corresponding to each candidate gap according to the following formula: cost = cost length + cost tail + cost lead ; where cost represents the lane change cost corresponding to each candidate gap; cost length represents the length cost corresponding to each candidate gap; cost lead represents the head cost corresponding to each candidate gap; cost tail represents the tail cost corresponding to each candidate gap. In the embodiment of the present application, the lane change cost corresponding to each candidate gap is calculated jointly by the length cost, head cost, and tail cost corresponding to each candidate gap, and the consideration factors are more comprehensive. Therefore, the tail cost corresponding to each candidate gap calculated therefrom is more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0050] S304. Select a target gap of the host vehicle at the current moment according to the lane change cost corresponding to each candidate gap.

[0051] For the method for selecting a lane gap proposed in the embodiment of the present application, when the host vehicle meets the lane change condition, first extract the characteristics of the driving environment where the host vehicle is located at the current moment; then calculate the lane change cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; and then select the target gap of the host vehicle at the current moment according to the lane change cost corresponding to each candidate gap. That is to say, the present application can automatically calculate the lane change cost corresponding to each candidate gap; and then adaptively select the target gap according to the lane change cost corresponding to each candidate gap. In the existing method for selecting a lane gap, the host vehicle only defaults to select the gap closest to the host vehicle currently. Because the present application adopts the technical means of automatically calculating the lane change cost corresponding to each candidate gap and adaptively selecting the target gap according to the lane change cost corresponding to each candidate gap, it overcomes the technical problem in the prior art that the host vehicle only defaults to select the gap closest to the host vehicle currently, but the gap closest to the host vehicle currently is not necessarily the optimal choice, which may cause insufficient lane change and merging ability of the autonomous driving vehicle, resulting in the situation that it cannot merge into the target lane, or even get stuck, blocking traffic and affecting vehicle traffic. The technical solution provided by the present application can adaptively select the optimal gap, increase the merging opportunity, enhance the lane change and merging ability, and improve the intelligence of autonomous driving; and, the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider application range.

[0052] Embodiment Three

[0053] Figure 5 It is the third process schematic diagram of the method for selecting a lane gap provided by an embodiment of the present application. It is further optimized and extended based on the above technical solution and can be combined with the above various optional implementation manners. As Figure 5 shown, the method for selecting a lane gap may include the following steps:

[0054] S501. When the host vehicle meets the lane-changing condition, extract the characteristics of the driving environment where the host vehicle is located at the current moment.

[0055] S502. According to the positions of the first vehicle in front of each candidate gap and the first vehicle behind each candidate gap in the target lane, calculate the actual length and expected length of each candidate gap in the target lane.

[0056] In this step, the electronic device may calculate the actual length and expected length of each candidate gap in the target lane according to the positions of the first vehicle in front of each candidate gap and the first vehicle behind each candidate gap in the target lane. The actual length of each candidate gap may be represented by the longitudinal length between the two vehicles before and after each candidate gap. As Figure 1 shown, the distance between the front of the second social vehicle and the rear of the first social vehicle is the length of the gap between social vehicle 1 and social vehicle 2. The expected length of each candidate gap represents the expected length of each candidate gap, which is related to the state of the host vehicle and the state of the vehicle in the gap, and can be calculated according to the speed and acceleration of the host vehicle, as well as the speed and acceleration of the first vehicle in front of the gap. To ensure driving safety, when the host vehicle merges behind the first vehicle in front of the gap, a certain distance should be maintained from it, and this distance can be represented as l lead ; similarly, l tail can be calculated, and in this way, length = l lead +l tail can be obtained.

[0057] S503. According to the actual length and expected length of each candidate gap in the target lane, and a preset reference length cost, calculate the length cost corresponding to each candidate gap in the target lane.

[0058] In this step, the electronic device may calculate the length cost corresponding to each candidate gap in the target lane according to the actual length and expected length of each candidate gap in the target lane, and a preset reference length cost. Specifically, the electronic device may calculate the length cost corresponding to each candidate gap according to the following formula: cost length = cost base × max(0, (1 - length gap / length desire )); where, cost base represents a preset reference length cost; length gap represents the actual length of each candidate gap; length desire represents the expected length of each candidate gap.

[0059] S504. According to the characteristics of the driving environment where the host vehicle is located, calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it, respectively.

[0060] In this step, the electronic device can calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it, respectively, according to the characteristics of the driving environment where the host vehicle is located; where, the distance cost between the host vehicle and the first vehicle in front of each candidate gap can be expressed as cost dis ; the braking cost of the host vehicle can be expressed as cost brake ; the impact cost of the host vehicle on the first vehicle behind it can be expressed as cost crtail . As Figure 1 shown, taking the gap in front of the social vehicle 1 as an example, there is no first vehicle in front of the gap at this time, and cost lead is equal to 0. Taking the gap behind the social vehicle 3 as an example, at this time, the social vehicle 3 is the first vehicle in front of the gap. The more the host vehicle exceeds the first vehicle in front of the gap, so cost dis1 is larger; in terms of speed, the faster the host vehicle is than the first vehicle in front of the gap, the higher the cost for the host vehicle to brake and merge into this gap, that is, cost brake is larger. The greater the impact of the host vehicle on the social vehicle 5, that is, cost crtail is larger. The solution provided by the embodiment of the present application calculates the head cost corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle in front of the gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it. The considered factors are more comprehensive, and the calculated tail cost corresponding to each candidate gap is more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0061] S505. Calculate the head cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it.

[0062] In this step, the electronic device can calculate the head cost corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it. Specifically, the electronic device can calculate the head cost corresponding to each candidate gap in the target lane according to the following formula: cost lead = cost dis1 + cost brake + cost crtail ; where cost dis1 is used to measure the distance cost between the host vehicle and the first vehicle in front of the gap. Based on the calculated l lead as the expected value, the smaller the actual value is compared to the expected value, the larger cost dis . According to the planning result of the rough planner, the planning information such as the acceleration and speed that the host vehicle needs to take to merge behind the first vehicle in front of the gap can be obtained. cost brake is used to measure the braking cost of the host vehicle, and cost crtail is used to measure the impact of the host vehicle's braking on the first vehicle behind in the current lane. As Figure 1 shows, taking the gap in front of social vehicle 1 as an example, there is no first vehicle in front of the gap at this time, so cost lead is equal to 0. Taking the gap behind social vehicle 3 as an example, at this time social vehicle 3 is the first vehicle in front of the gap. The more the host vehicle exceeds the first vehicle in front of the gap, the larger cost dis1 . In terms of speed, the faster the host vehicle is than the first vehicle in front of the gap, the higher the cost for the host vehicle to brake and merge into this gap, that is, the larger cost brake . The greater the impact of the host vehicle on social vehicle 5, that is, the larger cost crtail . The solution provided in the embodiment of the present application calculates the head cost corresponding to each candidate gap in the target lane jointly based on the distance cost between the host vehicle and the first vehicle in front of the gap, the braking cost of the host vehicle, and the impact cost of the host vehicle on the first vehicle behind it. The considered factors are more comprehensive, and the calculated tail cost corresponding to each candidate gap is more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0063] S506. Calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit respectively according to the characteristics of the driving environment where the host vehicle is located.

[0064] In this step, the electronic device can calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit according to the characteristics of the driving environment where the host vehicle is located. Among them, the distance cost between the host vehicle and the first vehicle in front of each candidate gap can be expressed as cost dis ; the acceleration cost of the host vehicle can be expressed as cost acc ; the acceleration feasibility cost of the host vehicle can be expressed as cost feasibility ; the penalty cost for the host vehicle exceeding the speed limit can be expressed as cost overspeed . As Figure 1 shown, taking the gap behind the social vehicle 3 as an example, there is no first vehicle behind the gap at this time, so cost tail is equal to 0. Taking the gap in front of the social vehicle 1 as an example, at this time the social vehicle 1 is the first vehicle behind the gap. The more the host vehicle lags behind the social vehicle 1 and the slower its speed, the greater cost dis2 is, and the higher the cost for the host vehicle to accelerate and catch up, that is, the greater cost acc . At the same time, based on the solution result of the rough planner, it may occur that the host vehicle needs to overtake the first vehicle in front of the host vehicle in the current lane or exceed the remaining passing length in order to accelerate and catch up with the first vehicle behind the gap. In this case, it is considered that it is not feasible for the host vehicle to merge into the gap in front of the social vehicle 1, and at this time cost feasibility will be relatively large. Similarly, the more the solution result of the rough planner exceeds the speed limit, the greater cost overspeed will be. The solution provided in the embodiment of the present application calculates the tail cost corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle behind the gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit. The considerations are more comprehensive, and the calculated tail cost corresponding to each candidate gap is more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0065] S507. Calculate the tail cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit.

[0066] In this step, the electronic device can calculate the tail cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit. Specifically, the electronic device can calculate the tail cost corresponding to each candidate gap in the target lane according to the following formula: costtail = cos t dis2 + cos t acc + cos t feasibility + cost overspeed ; where, cos t dis2 is used to measure the distance cost between the host vehicle and the first vehicle behind the gap. Based on the calculated l above tail as the expected value, the smaller the actual value is compared to the expected value, the larger cos t dis is. According to the results of the rough planner module, information such as the acceleration and speed planning that the host vehicle needs to take to merge behind the first vehicle in front of the gap can be obtained. cos t acc is used to measure the acceleration cost of the host vehicle, and cos t feasibility is used to measure the feasibility of the host vehicle's acceleration, and cos t overspeed is used to measure the penalty term for the host vehicle exceeding the speed limit. The acceleration cost of the host vehicle in the embodiments of the present application can be represented by cos t acc . This acceleration cost can be used to measure the acceleration of the host vehicle at the current moment and the cost of the host vehicle changing lanes. The greater the acceleration of the host vehicle, the higher the acceleration cost. The acceleration feasibility cost of the host vehicle can be represented by cos t feasibility . The greater the acceleration of the host vehicle, the higher the acceleration possibility cost; the penalty term cost for the host vehicle exceeding the speed limit can be represented by cos t overspeed . The more the host vehicle exceeds the speed limit of the current lane or the target lane, the higher the penalty term cost for exceeding the speed limit. As Figure 1 shown, taking the gap behind the social vehicle 3 as an example, there is no first vehicle behind the gap at this time, so cos t tail is equal to 0. Taking the gap in front of the social vehicle 1 as an example, at this time the social vehicle 1 is the first vehicle behind the gap. The more the host vehicle lags behind the social vehicle 1 and the slower the speed, the larger cost dis2 is, and the higher the cost for the host vehicle to accelerate and catch up, that is, the larger cos t acc is. At the same time, based on the solution results of the rough planner, it may occur that the host vehicle needs to exceed the first vehicle in front of the host vehicle in the current lane or exceed the remaining passing length in order to accelerate and catch up with the first vehicle behind the gap. In this case, it will be considered that it is not feasible for the host vehicle to merge into the gap in front of the social vehicle 1. At this time, cos t feasibility will be relatively large. Similarly, the more the solution results of the rough planner exceed the speed limit, the larger cost overspeeThe larger d is. The solution provided by the embodiment of the present application calculates the tail cost corresponding to each candidate gap in the target lane based on the distance cost between the host vehicle and the first vehicle behind the gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit. The considerations are more comprehensive, and the calculated tail cost corresponding to each candidate gap is more accurate, providing a more accurate data basis for the host vehicle to automatically select a gap, thereby improving the intelligence of autonomous driving.

[0067] S508. Select the target gap of the host vehicle at the current moment according to the lane-changing cost corresponding to each candidate gap.

[0068] For the method for selecting a lane gap proposed by the embodiment of the present application, when the host vehicle meets the lane-changing condition, first extract the characteristics of the driving environment where the host vehicle is located at the current moment; then calculate the lane-changing cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; and then select the target gap of the host vehicle at the current moment according to the lane-changing cost corresponding to each candidate gap. That is to say, the present application can automatically calculate the lane-changing cost corresponding to each candidate gap; and then adaptively select the target gap according to the lane-changing cost corresponding to each candidate gap. In the existing method for selecting a lane gap, the host vehicle only defaults to selecting the gap closest to the host vehicle currently. Because the present application adopts the technical means of automatically calculating the lane-changing cost corresponding to each candidate gap and adaptively selecting the target gap according to the lane-changing cost corresponding to each candidate gap, it overcomes the technical problem in the prior art that the host vehicle only defaults to selecting the gap closest to the host vehicle currently, but the gap closest to the host vehicle currently may not be the optimal choice, which may cause insufficient lane-changing and merging ability of the autonomous driving vehicle, resulting in the situation of being unable to merge into the target lane, or even getting stuck, blocking traffic, and affecting vehicle traffic. The technical solution provided by the present application can adaptively select the optimal gap, increase the merging opportunity, enhance the lane-changing and merging ability, and improve the intelligence of autonomous driving; moreover, the technical solution of the embodiment of the present application is simple and convenient to implement, easy to popularize, and has a wider application range.

[0069] Embodiment 4

[0070] Figure 6 is a schematic structural diagram of a device for selecting a lane gap provided by an embodiment of the present application. As Figure 6 shown, the device 600 includes: an extraction module 601, a calculation module 602, and a selection module 603; wherein,

[0071] The extraction module 601 is configured to extract the characteristics of the driving environment where the host vehicle is located at the current moment when the host vehicle meets the lane-changing condition;

[0072] The calculation module 602 is configured to calculate the lane change cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located;

[0073] The selection module 603 is configured to select the target gap of the host vehicle at the current moment according to the lane change cost corresponding to each candidate gap.

[0074] Further, the characteristics of the driving environment where the host vehicle is located include: the driving state of the first vehicle in front of the host vehicle; the driving state of the first vehicle behind the host vehicle; the distance of the host vehicle from the end point of the lane change section on the current lane; the road speed limit of the host vehicle on the current lane and the road speed limit of the host vehicle on the target lane; the driving state of the host vehicle; the driving states of the candidate gaps in the target lane.

[0075] Further, the calculation module 602 is specifically configured to calculate the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; wherein, the length cost is used to measure the cost of the host vehicle inserting into the corresponding length of each candidate gap; the head cost is used to measure the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap; the tail cost is used to measure the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap; and calculate the lane change cost corresponding to each candidate gap according to the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane.

[0076] Further, the calculation module 602 is specifically configured to calculate the actual length and expected length of each candidate gap in the target lane according to the position of the first vehicle in front of each candidate gap in the target lane and the position of the first vehicle behind each candidate gap in the target lane; and calculate the length cost corresponding to each candidate gap in the target lane according to the actual length and expected length of each candidate gap in the target lane and a preset reference length cost.

[0077] Further, the calculation module 602 is specifically configured to calculate the length cost corresponding to each candidate gap in the target lane according to the following formula: cost length = cost base × max(0, (1 - length gap / length desire )); where cost base represents the preset reference length cost; length gap represents the actual length of each candidate gap; length desire represents the expected length of each candidate gap.

[0078] Further, the calculation module 602 is specifically configured to calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it respectively according to the characteristics of the driving environment where the host vehicle is located; calculate the head cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it.

[0079] Further, the calculation module 602 is specifically configured to calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit respectively according to the characteristics of the driving environment where the host vehicle is located; calculate the tail cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit.

[0080] The above device for selecting a lane gap can execute the method provided in any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method for selecting a lane gap provided in any embodiment of the present application.

[0081] Embodiment 5

[0082] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0083] Figure 7 FIG. shows a schematic block diagram of an exemplary electronic device 700 that can be used to implement the embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0084] As Figure 7As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 702 or computer programs loaded from a storage unit 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0085] Multiple components in device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 707, such as various types of displays, speakers, etc.; a storage unit 708, such as a magnetic disk, an optical disc, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows device 700 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0086] The computing unit 701 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 701 executes the various methods and processes described above, such as the method for selecting a lane gap. For example, in some embodiments, the method for selecting a lane gap can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed onto device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the method for selecting a lane gap described above can be executed. Alternatively, in other embodiments, the computing unit 701 can be configured to execute the method for selecting a lane gap by any other appropriate means (e.g., by means of firmware).

[0087] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0088] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.

[0089] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0090] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0091] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected to each other by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0092] A computer system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0093] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in this disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved, and no limitation is imposed herein. In the technical solutions of this disclosure, the acquisition, storage, and application of the user's personal information involved all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0094] The above specific embodiments do not constitute a limitation on the protection scope of the present disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A method for selecting a lane gap, the method comprising: When the host vehicle meets the lane-changing condition, extracting the characteristics of the driving environment where the host vehicle is located at the current moment; wherein, the host vehicle meeting the lane-changing condition means that the host vehicle has a lane-changing requirement; Calculating the lane-changing cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; Selecting a gap with the minimum lane-changing cost as the target gap of the host vehicle at the current moment according to the lane-changing costs corresponding to each candidate gap; Wherein, the calculating the lane-changing cost corresponding to each candidate gap according to the characteristics of the driving environment where the host vehicle is located includes: Calculating the length cost, head cost and tail cost corresponding to each candidate gap in the target lane respectively according to the characteristics of the driving environment where the host vehicle is located; wherein, the length cost is used to measure the cost of the host vehicle inserting into the corresponding length of each candidate gap; the head cost is used to measure the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap; the tail cost is used to measure the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap. Wherein, the length cost is calculated according to the actual length and expected length of each candidate gap in the target lane and a preset reference length cost; the head cost is jointly calculated according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle and the influence cost of the host vehicle on the first vehicle behind it; the tail cost is jointly calculated according to the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle and the penalty item cost of the host vehicle exceeding the speed limit.

2. According to the method described in claim 1, the characteristics of the driving environment where the master vehicle is located include: The driving state of the first vehicle in front of the host vehicle; the driving state of the first vehicle behind the host vehicle; The distance of the host vehicle from the end point of the lane-changing section on the current lane; the road speed limit of the host vehicle on the current lane and the road speed limit of the host vehicle on the target lane; the driving state of the host vehicle; the states of each candidate gap in the target lane; wherein, the state of the candidate gap includes the speed, acceleration, position of the first vehicle in front of the candidate gap, and / or the speed, acceleration, position of the first vehicle behind the candidate gap.

3. The method according to claim 1, wherein, Calculating the length cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located, including: Calculating the actual length and expected length of each candidate gap in the target lane according to the position of the first vehicle in front of each candidate gap and the position of the first vehicle behind each candidate gap in the target lane; Calculating the length cost corresponding to each candidate gap in the target lane according to the actual length and expected length of each candidate gap in the target lane and a preset reference length cost.

4. According to the method described in claim 1, calculate the length cost corresponding to each candidate gap in the target lane according to the following formula: cost length = cost base × max(0, (1 - length gap / length desire )); where cost base represents a preset reference length cost; length gap represents the actual length of each candidate gap; length desire represents the desired length of each candidate gap.

5. The method according to claim 1, wherein Calculating the head cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located, including: According to the characteristics of the driving environment where the host vehicle is located, calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it respectively; According to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it, calculate the head cost corresponding to each candidate gap in the target lane.

6. The method according to claim 1, wherein According to the characteristics of the driving environment where the host vehicle is located, calculate the tail cost corresponding to each candidate gap in the target lane, including: According to the characteristics of the driving environment where the host vehicle is located, calculate the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit respectively; According to the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit, calculate the tail cost corresponding to each candidate gap in the target lane.

7. A device for selecting a lane gap, the device comprising: An extraction module, a calculation module, and a selection module; wherein, The extraction module is used to extract the characteristics of the driving environment where the host vehicle is located at the current moment when the host vehicle meets the lane change condition; wherein, the host vehicle meets the lane change condition means that the host vehicle has a lane change requirement; The calculation module is used to calculate the lane change cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; The selection module is used to select a gap with the minimum lane change cost as the target gap of the host vehicle at the current moment according to the lane change cost corresponding to each candidate gap; Wherein, the calculation module is specifically used to calculate the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane according to the characteristics of the driving environment where the host vehicle is located; wherein, the length cost is used to measure the cost of the host vehicle inserting into the corresponding length of each candidate gap; the head cost is used to measure the cost of the host vehicle inserting behind the first vehicle in front of each candidate gap; the tail cost is used to measure the cost of the host vehicle inserting in front of the first vehicle behind each candidate gap; calculate the lane change cost corresponding to each candidate gap according to the length cost, head cost, and tail cost corresponding to each candidate gap in the target lane; Wherein, the length cost is calculated according to the actual length and expected length of each candidate gap in the target lane, and a preset benchmark length cost; the head cost is jointly calculated according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it; the tail cost is jointly calculated according to the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit.

8. The device according to claim 7, wherein the characteristics of the driving environment where the master vehicle is located include: The driving state of the first vehicle in front of the host vehicle; the driving state of the first vehicle behind the host vehicle; The distance of the host vehicle from the end of the lane change interval on the current lane; the road speed limit on the current lane of the host vehicle and the road speed limit on the target lane of the host vehicle; the driving state of the host vehicle; the states of the respective candidate gaps in the target lane; wherein the state of the candidate gap includes the speed, acceleration, position of the first vehicle in front of the candidate gap, and / or the speed, acceleration, position of the first vehicle behind the candidate gap.

9. The device according to claim 7, wherein the calculation module is specifically configured to calculate the actual length and the expected length of the respective candidate gaps in the target lane according to the positions of the first vehicle in front of each candidate gap and the positions of the first vehicle behind each candidate gap in the target lane; and calculate the length cost corresponding to each candidate gap in the target lane according to the actual length and the expected length of the respective candidate gaps in the target lane and a preset reference length cost.

10. The apparatus according to claim 9, wherein the calculation module is specifically configured to calculate the length cost corresponding to each candidate gap in the target lane according to the following formula: cost length = cost base × max(0, (1 - length gap / length desire )); where cost base represents a preset reference length cost; length gap represents the actual length of each candidate gap; length desire represents the expected length of each candidate gap.

11. The device according to claim 7, wherein the calculation module is specifically configured to calculate the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it respectively according to the characteristics of the driving environment where the host vehicle is located; and calculate the head cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle in front of each candidate gap, the braking cost of the host vehicle, and the influence cost of the host vehicle on the first vehicle behind it.

12. The device according to claim 7, wherein the calculation module is specifically configured to calculate the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit respectively according to the characteristics of the driving environment where the host vehicle is located; and calculate the tail cost corresponding to each candidate gap in the target lane according to the distance cost between the host vehicle and the first vehicle behind each candidate gap, the acceleration cost of the host vehicle, the acceleration feasibility cost of the host vehicle, and the penalty cost for the host vehicle exceeding the speed limit.

13. An electronic device, comprising: At least one processor; And A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the method according to any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to execute the method according to any one of claims 1-6.

15. A computer program product, comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-6.

Images