Vehicle lane changing control method and device, equipment and medium

Abstract

The invention provides a vehicle lane changing control method and device, equipment and a medium. The method comprises the steps that under the condition that vehicles around a vehicle hinder lane changing of the vehicle, a target gap is selected from multiple candidate gaps at least based on the gap length of the candidate gaps and the distance between the vehicle and the candidate gaps; wherein the candidate gap is a gap on an adjacent lane of a current driving lane of the vehicle; based on the target gap, the vehicle is controlled to run to a lane-changeable position in a current driving lane; and controlling the vehicle to change the lane from the lane-changeable position to the target gap.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automobiles, in particular to a vehicle lane changing control method, device, equipment and medium. BACKGROUND

[0002] When changing lanes manually, the driver relies on driving experience, lacks a unified standardized process, and is prone to dangerous behaviors such as lane cutting and sudden braking. In particular, in peak congestion, bad weather, or high-speed highway driving scenarios, safety accidents often occur due to driver judgment errors or improper operation. The vehicle lane changing control method is born out of the dual needs of improving road safety and evolving autonomous driving technology. SUMMARY

[0003] The present application provides a vehicle lane changing control method, device, equipment and medium.

[0004] The technical solution adopted by the present application is as follows: In a first aspect, the present application provides a vehicle lane changing control method, the method comprising the following steps: in the case that the lane changing of the ego vehicle is hindered by the vehicles around the ego vehicle, selecting a target gap from a plurality of candidate gaps based at least on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap; wherein the candidate gap is a gap on the adjacent lane of the current driving lane of the ego vehicle; based on the target gap, controlling the ego vehicle to drive on the current driving lane to a lane-changing position; controlling the ego vehicle to change lanes from the lane-changing position to the target gap.

[0005] It can be understood that the scheme provided by the present application: since the length of the gap can reflect whether the ego vehicle will collide with the vehicles around the ego vehicle after switching, the length of the distance between the ego vehicle and the candidate gap can reflect the timeliness and stability of the lane changing action, therefore, the target gap selected based on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap can not only reduce the occurrence of collision after lane changing of the ego vehicle, but also improve the lane changing efficiency.

[0006] In some embodiments, the selecting a target gap from a plurality of candidate gaps based on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap comprises: determining a score of the candidate gap based on the gap length of the candidate gap and a corresponding first weight and the distance between the ego vehicle and the candidate gap and a corresponding second weight; wherein the first weight is greater than the second weight; or the first weight is less than the second weight; selecting a target gap from a plurality of candidate gaps based on the scores of the plurality of candidate gaps.

[0007] It can be understood that the scheme provided in the application: by determining the score of the candidate gap based on the gap length of the candidate gap and the corresponding first weight and the distance between the ego vehicle and the candidate gap and the corresponding second weight, the first weight and the second weight are used to indicate whether more attention is paid to the influence of the gap length on the candidate gap or more attention is paid to the influence of the distance on the candidate gap; if more attention is paid to the influence of the gap length on the candidate gap, it means that more attention is paid to whether it is safe after lane changing, so that the occurrence of the crash after lane changing can be further reduced, thereby improving the safety of lane changing; if more attention is paid to the influence of the distance on the candidate gap, it means that more attention is paid to whether it can be quickly changed lanes, so that the occurrence of lane deviation and the situation that the following vehicle occupies the target gap in advance can be reduced, thereby the ego vehicle can complete the lane changing as soon as possible.

[0008] In some embodiments, the candidate gap is obtained by: in the case that there is no vehicle on the side of the ego vehicle or the vehicle on the side of the ego vehicle has no intention of overtaking, the gap between the front and rear two vehicles on the adjacent lane of the current driving lane of the ego vehicle is removed if the gap length of the gap is outside the first distance range, and the remaining gap is the candidate gap; wherein the distance between the front adjacent vehicle of the ego vehicle and the ego vehicle is the upper limit value of the first distance range, and the distance between the rear vehicle of the ego vehicle and the ego vehicle is the lower limit value of the first distance range.

[0009] It can be understood that the scheme provided in the application: since the first distance range is determined according to the first distance between the front vehicle of the ego vehicle and the ego vehicle and the second distance between the rear vehicle of the ego vehicle and the ego vehicle, the front vehicle of the ego vehicle will limit the acceleration of the ego vehicle, and the rear vehicle of the ego vehicle will limit the deceleration of the ego vehicle, so that by using the first set to screen the gap, the gap that can ensure that there is no safety accident after the ego vehicle changes lanes but the ego vehicle cannot reach by acceleration / deceleration can be screened out, and the gap obtained is the gap that is beneficial to the ego vehicle to realize lane changing under the condition of ensuring the safety of the ego vehicle, so that the lane changing is easier.

[0010] In some embodiments, the control of the ego vehicle to drive on the current driving lane to the lane-changing position based on the target gap comprises: determining a target driving speed required for the ego vehicle to drive to the lane-changing position according to the motion information of the front and rear two vehicles of the target gap; obtaining a first acceleration according to the target driving speed and the current driving speed of the ego vehicle; and controlling the ego vehicle to shift gears according to the first acceleration to drive on the current driving lane to the lane-changing position.

[0011] It can be understood that the technical scheme provided by the present application: because the candidate gap obtained based on the first distance range is a gap that is conducive to the ego vehicle to realize lane changing under the condition of ensuring the driving safety of the ego vehicle; the target gap selected from the candidate gaps is a gap that is more conducive to the ego vehicle to realize lane changing; and the ego vehicle is driven to the lane-changing position in the current driving lane according to the first acceleration obtained based on the target gap, so that the ego vehicle can reach the lane-changing position as soon as possible to realize lane changing even when there are front and rear vehicles.

[0012] In some embodiments, the control of the ego vehicle to change lanes from the lane-changing position to the target gap comprises: obtaining a second acceleration corresponding to a current lane-changing scene from a plurality of pre-configured lane-changing scenes; and in the case that a safety condition is met, controlling the ego vehicle to change lanes from the lane-changing position to the target gap according to the second acceleration; wherein the safety condition comprises at least one of the following: the ego vehicle is in a lane-changing request stage or in a lane-changing control stage; a lane-changing time from the start of lane changing to the current time is less than a first time length; the ego vehicle has crossed a lane line; a current driving speed of the ego vehicle does not exceed a pre-configured speed threshold; and a minimum deceleration of the ego vehicle is greater than a pre-configured deceleration threshold; wherein the minimum deceleration is the minimum deceleration in decelerations of the ego vehicle in the driving process due to obstacle avoidance.

[0013] It can be understood that the technical scheme provided by the present application: the lane-changing time from the start of lane changing to the current time is less than the first time length, which indicates that the lane changing is not overdue; the ego vehicle has crossed the lane line, which indicates that the ego vehicle has completed lane changing; the current driving speed of the ego vehicle does not exceed the pre-configured speed threshold, which indicates that the ego vehicle is not currently speeding; and the minimum deceleration of the ego vehicle is greater than the pre-configured deceleration threshold, which indicates that the ego vehicle is not currently dangerous. In the process of lane changing of the ego vehicle to the target gap, the ego vehicle does not immediately change to the target gap, but enters the target gap when the safety condition is met, so that the lane changing of the ego vehicle is safer and faster; in addition, the safety condition is associated with the lane-changing request, whether the lane changing is overdue, whether the lane line is crossed, whether the speed is exceeded, and whether it is dangerous, so that the lane changing is safer and more efficient.

[0014] In some embodiments, the method further comprises: determining a first safety distance; wherein the first safety distance refers to a collision-preventing distance between the ego vehicle and vehicles around the ego vehicle; and determining, based on a size relationship between the first safety distance and a horizontal distance between the ego vehicle and the vehicles around the ego vehicle in the driving direction, that the vehicles around the ego vehicle hinder the lane changing of the ego vehicle.

[0015] It can be understood that the technical solution provided by the present application is to determine whether the vehicles around the vehicle pose an obstacle to the vehicle's lane change based on the first safety distance and the horizontal spacing between the vehicle and the vehicles around the vehicle in the driving direction. This allows for quick determination and places relatively low demands on the algorithm.

[0016] In some embodiments, the first safety distance includes a collision avoidance distance between the vehicle and the vehicle in front of the adjacent lane of the current lane of the vehicle; the vehicles around the vehicle hinder the vehicle's lane change, including: the vehicle in front of the adjacent lane hinders the vehicle's lane change; the determination of whether the vehicles around the vehicle hinder the vehicle's lane change based on the first safety distance and the horizontal distance between the vehicle and the vehicles around the vehicle in the driving direction includes: when the first safety distance is greater than the horizontal distance between the vehicle and the vehicle in front of the adjacent lane in the driving direction, determining that the vehicle in front of the adjacent lane hinders the vehicle's lane change.

[0017] It can be understood that the technical solution provided by the present application is: when the first safety distance is greater than the horizontal distance between the own vehicle and the vehicle in front of the adjacent lane in the driving direction, it means that the own vehicle will not collide with the vehicle in front of the adjacent lane during the lane change process. The first safety distance is simple and easy to calculate, and the horizontal distance between the own vehicle and the vehicle in front of the adjacent lane in the driving direction can be obtained through the sensor. Therefore, the entire process has relatively low requirements for the algorithm.

[0018] In some embodiments, the first safety distance includes the anti-collision distance between the self-vehicle and the rear vehicle on the adjacent lane relative to the current driving lane of the self-vehicle; the vehicles around the self-vehicle pose an obstacle to the lane change of the self-vehicle, including: the rear vehicle on the adjacent lane poses an obstacle to the lane change of the self-vehicle; the determination of the obstacles to the lane change of the self-vehicle by the vehicles around the self-vehicle based on the first safety distance and the horizontal distance between the self-vehicle and the vehicles around the self-vehicle in the driving direction includes: when the first safety distance is greater than the absolute value of the sum of the length of the rear vehicle on the adjacent lane and the horizontal distance between the self-vehicle and the rear vehicle on the adjacent lane in the driving direction, determining that the rear vehicle on the adjacent lane poses an obstacle to the lane change of the self-vehicle.

[0019] It can be understood that the technical solution provided by this application is: since the uncertainty of the vehicle behind is greater, in order to prevent the rear-end collision of the vehicle by the rear vehicle, in addition to considering the safety suppression distance and longitudinal distance, the body length of the rear vehicle is also considered. In this way, while obtaining the judgment result quickly, it can also improve safety.

[0020] In some embodiments, the first safety distance includes a collision avoidance distance between the ego vehicle and a rear vehicle on an adjacent lane of the ego vehicle's current lane; the vehicles surrounding the ego vehicle hindering the ego vehicle's lane change include: the rear vehicle on the adjacent lane hindering the ego vehicle's lane change; determining that the vehicles surrounding the ego vehicle hinder the ego vehicle's lane change based on the first safety distance and the horizontal distance between the ego vehicle and the vehicles surrounding the ego vehicle in the driving direction include: determining that the rear vehicle on the adjacent lane hinders the ego vehicle's lane change when the first safety distance is greater than the absolute value of the sum of the length of the rear vehicle on the adjacent lane and the horizontal distance between the ego vehicle and the rear vehicle on the adjacent lane in the driving direction, and when the probability of the rear vehicle on the adjacent lane changing to the adjacent lane of the ego vehicle's current lane is greater than a first lane change probability threshold, and when the amount by which the rear vehicle on the adjacent lane presses the lane line of the adjacent lane of the ego vehicle's current lane is greater than a first lane pressing amount threshold.

[0021] It can be understood that the technical solution provided by this application is: since the uncertainty of the rear vehicle is greater, in order to prevent the rear vehicle from rear-ending the vehicle, in addition to considering the first safety distance and the horizontal distance between the vehicle and the rear vehicle on the adjacent lane in the driving direction, the body length of the rear vehicle on the adjacent lane is also considered, and the lane changing probability and the amount of crossing the line of the rear vehicle on the adjacent lane are also considered. In this way, while obtaining the judgment result quickly, safety is further improved.

[0022] In some embodiments, the first safety distance includes a collision avoidance distance between the self-vehicle and the vehicle in front of the adjacent lane of the current lane of the self-vehicle; the vehicles around the self-vehicle hinder the lane change of the self-vehicle, including: the vehicle in front of the adjacent lane hinders the lane change of the self-vehicle; the determination of the vehicles around the self-vehicle hindering the lane change of the self-vehicle based on the first safety distance and the horizontal distance between the self-vehicle and the vehicles around the self-vehicle in the driving direction includes: when the first safety distance is less than the horizontal distance between the self-vehicle and the vehicle in front of the adjacent lane in the driving direction, and the probability of the vehicle in front of the adjacent lane changing to the adjacent lane of the current lane of the self-vehicle is greater than a second lane change probability threshold, and the amount by which the vehicle in front of the adjacent lane presses the lane line of the adjacent lane of the current lane of the self-vehicle is greater than a second lane pressing amount threshold, determines that the vehicle in front of the adjacent lane hinders the lane change of the self-vehicle.

[0023] It can be understood that the technical scheme provided in the application considers the lane changing probability and the line pressure of the front vehicle on the adjacent lane in addition to the first safety distance and the horizontal distance between the ego vehicle and the front vehicle on the adjacent lane in the driving direction, considers the safety problem of the ego vehicle after lane changing, and thus improves the safety while obtaining the judgment result at a fast speed.

[0024] In some embodiments, the determining the first safety distance comprises: determining the first safety distance according to at least one of the following parameters: a safety threshold corresponding to the current driving speed of the ego vehicle; a time distance between the vehicle around the ego vehicle and the ego vehicle; a distance to be traveled by the ego vehicle assuming that the ego vehicle drives off the current driving lane of the ego vehicle; a driving distance of the vehicle around the ego vehicle assuming that the ego vehicle drives at the same speed as the front vehicle after completing lane changing; a speed of the vehicle around the ego vehicle assuming that the vehicle around the ego vehicle completes lane changing; a distance to be traveled by the vehicle around the ego vehicle assuming that the vehicle around the ego vehicle drives off the current driving lane of the vehicle around the ego vehicle.

[0025] It can be understood that the technical scheme provided in the application: these parameters are easy to obtain and easy to calculate, and thus the demand for algorithm can be reduced.

[0026] In some embodiments, the method further comprises: determining the distance to be traveled by the ego vehicle assuming that the ego vehicle drives off the current driving lane of the ego vehicle according to the current driving speed of the ego vehicle, the lane changing time required by the ego vehicle assuming that the ego vehicle completes lane changing, the lane width of the current driving lane of the ego vehicle, and the sampling acceleration; wherein the sampling acceleration is obtained by sampling a preset acceleration range according to a preset sampling step.

[0027] It can be understood that the technical scheme provided in the application: these parameters are easy to obtain and easy to calculate, and thus the demand for algorithm can be reduced.

[0028] In some embodiments, the method further comprises: determining the driving distance of the ego vehicle assuming that the ego vehicle drives at the same speed as the front vehicle after completing lane changing according to the driving speed of the ego vehicle assuming that the ego vehicle completes lane changing, the target deceleration time, and the target deceleration; wherein the target deceleration refers to the deceleration required by the ego vehicle assuming that the ego vehicle completes lane changing and needs to reach the same speed as the front vehicle of the ego vehicle after lane changing; and the target deceleration time refers to the time required by the ego vehicle to reduce from the current driving speed to the target speed.

[0029] It can be understood that the technical scheme provided in the application: these parameters are easy to obtain and easy to calculate, and thus the demand for algorithm can be reduced.

[0030] In some embodiments, the method further comprises determining the target deceleration time according to the assumed driving speed of the ego vehicle when completing the lane change, the assumed speed of the vehicle around the ego vehicle when completing the lane change, and the target deceleration.

[0031] It can be understood that the technical solutions provided in the present application are easy to obtain and easy to calculate, and thus the demand for algorithms can be reduced.

[0032] In some embodiments, the method further comprises determining the driving distance of the vehicle around the ego vehicle from when the ego vehicle completes the lane change to when the driving speed of the vehicle around the ego vehicle is the same as the driving speed of the vehicle in front of the ego vehicle according to the assumed speed of the vehicle around the ego vehicle when completing the lane change and the target deceleration time.

[0033] It can be understood that the technical solutions provided in the present application are easy to obtain and easy to calculate, and thus the demand for algorithms can be reduced.

[0034] In a second aspect, the present application provides a control device for vehicle lane changing, comprising a selection module, a first control module and a second control module. The selection module is configured to select a target gap from a plurality of candidate gaps based on at least the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap, in a case where the vehicle around the ego vehicle hinders the lane changing of the ego vehicle, wherein the candidate gap is a gap on an adjacent lane of the current driving lane of the ego vehicle. The first control module is configured to control the ego vehicle to drive to a lane-changing position on the current driving lane based on the target gap. The second control module is configured to control the ego vehicle to change lanes from the lane-changing position to the target gap.

[0035] In a third aspect, the present application provides a vehicle device comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements the method of the first aspect when executing the program.

[0036] In a third aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor or a vehicle device to implement the method of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0037] The drawings in the accompanying drawings are incorporated into and form part of the specification, which show embodiments consistent with the present application, and together with the specification serve to explain the technical solutions of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0038] The flowchart shown in the drawings is only an exemplary description, and is not necessarily to include all contents and operations / steps, nor is it necessarily executed in the order described. For example, some operations / steps can be further decomposed, and some operations / steps can be combined or partially combined, so that the actual execution order can be changed according to the actual situation.

[0039] Figure 1 A flowchart of a vehicle lane changing control method provided for an embodiment of the present application; Figure 2 A flowchart of a vehicle numbering method provided for an embodiment of the present application; Figure 3 A schematic diagram of a vehicle gap formed between the ego vehicle and the vehicles around the ego vehicle provided for an embodiment of the present application; Figure 4 A schematic diagram of the ego vehicle driving to a lane changing position by speed change provided for an embodiment of the present application; Figure 5 Another schematic diagram of the ego vehicle driving to a lane changing position by speed change provided for an embodiment of the present application; Figure 6 A flowchart of another vehicle lane changing control method provided for an embodiment of the present application; Figure 7 A structural schematic diagram of a vehicle lane changing control device provided for an embodiment of the present application; Figure 8 A structural schematic diagram of a vehicle device provided for an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the specific technical solutions of the present application will be further described in detail below in combination with the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

[0042] In the following description, "some embodiments", "this embodiment", "embodiments of the present application", and the like, describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same or different from one another, and can be combined with one another, without conflicts.

[0043] The "first", "second", "third", and the like, appearing in the embodiments of the present application, do not have a specific meaning (such as no order, nor represent a specific limitation on the number of devices in the embodiments of the present application), and are only for the convenience of clearly describing the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.

[0044] Before further detailing the embodiments of the present application, the terms and terms possibly involved in the embodiments of the present application are described, and the terms and terms involved in the embodiments of the present application are applicable to the following explanations.

[0045] Longitudinal planning: In the process of lane changing of a vehicle, longitudinal planning refers to controlling the speed and speed strategy of the vehicle along the driving direction (i.e. the direction of the lane), the purpose is to safely, smoothly and efficiently complete the lane changing action, and harmoniously interact with the surrounding traffic flow. In short, longitudinal planning solves the problem of when to accelerate, when to decelerate, and how fast to complete lane changing.

[0046] Dynamic suppression requirement: refers to the requirement that the system needs to dynamically "suppress" or "give up" some otherwise feasible lane change goals (lane change intentions) according to the real-time changing traffic environment (such as the speed, position, acceleration, behavior intention of surrounding vehicles), in order to ensure driving safety and efficiency. This mechanism enables the vehicle to "flexibly respond" like a human driver, avoiding accidents caused by stubbornly executing pre-planned plans.

[0047] Backtracking: refers to the process of stopping the lateral lane changing action in the process of lane changing execution, and controlling the vehicle to back to the original lane or a safe state, when the original plan is unsafe due to sudden risks or environmental changes.

[0048] Unintended Departure Lane Change (UDLC): used to prevent the vehicle from unintentionally deviating from the lane due to driver distraction or operational error.

[0049] Auto Lane Change (ALC): after the driver turns on the turn signal, the system automatically completes the lane change operation without the need for the driver to manually control the steering wheel.

[0050] Integrated Adaptive Cruise Control (IACC): This includes both longitudinal and lateral control. Longitudinal control automatically adjusts the vehicle's speed to maintain a safe distance from the vehicle ahead, while lateral control actively and stably keeps the vehicle centered in the lane.

[0051] Headway: The time interval between adjacent vehicles (i.e., the leading and following vehicles) in the same lane passing the same location. Its core significance lies in quantifying the following safety margin between vehicles and directly determining the risk of collision. Headway = headway D / own vehicle speed V; headway D is the distance between the rear of the leading vehicle and the front of the own vehicle.

[0052] To facilitate understanding of the technical solutions of the embodiments of the present application, the following describes the relevant technologies or terms of the embodiments of the present application. The following relevant technologies or terms can be combined with the technical solutions of the embodiments of the present application as optional solutions, and all of them fall within the scope of protection of the embodiments of the present application.

[0053] With the rapid development of intelligent driving technology, lane changing, as a crucial component of a vehicle's lateral motion, requires a rational longitudinal planning process that directly impacts driving safety and ride comfort. In related technologies, longitudinal planning methods for lane changing fall into two main categories: optimization-based and rule-based.

[0054] A related technology provides a lane-changing control method that uses a nonlinear optimization algorithm to find the optimal acceleration and deceleration trajectory, ensuring that the vehicle meets longitudinal safety distance and comfort requirements during lane changes. However, due to the complex nonlinear optimization algorithm used, this method has a long computation time, making it difficult to apply in intelligent driving systems with high real-time requirements or low-cost hardware and low-computing-power platforms. Furthermore, this method does not consider the handling of dangerous situations during lane changes.

[0055] In another related technology, a lane-changing control method is provided. This method iteratively calculates the vehicle's lane-changing plan by considering the safe following distance between the front and rear vehicles in the same lane and the gap between adjacent lanes for lane changes. This method has the characteristics of clear control logic, easy programming, and the ability to meet real-time requirements. However, this method only solves a single scenario and is limited to the control method for lane changes of vehicles at intersections. When faced with the complex traffic scenarios of the entire driving scene, its flexibility is insufficient. Secondly, this method takes into account the small number of participating targets in the environment and does not consider the targets in the adjacent lanes. The actions of vehicles in the adjacent lanes during the lane change process will also affect the safety of the lane change. This method also does not deal with dangerous situations that occur during the lane change process.

[0056] Based on this, the inventors of the present application found through research and analysis that the existing lane changing control method has the problems of low calculation efficiency and poor planning quality.

[0057] Based on this, the present application provides a vehicle lane changing control method, device, equipment and medium, etc.

[0058] Figure 1 A flowchart of a vehicle lane changing control method provided by an embodiment of the present application is shown in Figure 1 As shown in the figure, the method comprises the following steps: S101, in the case that the vehicles around the ego vehicle hinder the lane changing of the ego vehicle, selecting a target gap from a plurality of candidate gaps based on at least the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap; wherein the candidate gap is a gap on the adjacent lane of the current driving lane of the ego vehicle; S102, based on the target gap, controlling the ego vehicle to drive on the current driving lane to a lane changing position; S103, controlling the ego vehicle to change lanes from the lane changing position to the target gap.

[0059] It can be understood that the scheme provided by the present application: since the length of the gap can reflect whether the ego vehicle will collide with the vehicles around the ego vehicle after switching, and the distance between the ego vehicle and the candidate gap can reflect the timeliness and stability of the lane changing action, the target gap selected based on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap can not only reduce the occurrence of the ego vehicle colliding after lane changing, but also improve the lane changing efficiency.

[0060] The further optional embodiments of each of the above steps and related terms are described below.

[0061] S101, in the case that the vehicles around the ego vehicle hinder the lane changing of the ego vehicle, selecting a target gap from a plurality of candidate gaps based on at least the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap.

[0062] Wherein the candidate gap is a gap on the adjacent lane of the current driving lane of the ego vehicle.

[0063] In the embodiments of the present application, the vehicles around the ego vehicle include the vehicle directly in front of the ego vehicle, the vehicle directly behind the ego vehicle, the vehicle on the side of the ego vehicle, the vehicle on the side in front of the ego vehicle, and the vehicle on the side behind the ego vehicle.

[0064] Further, in some optional embodiments, the vehicle on the side of the ego vehicle can be divided into: adjacent lane side vehicle and adjacent adjacent lane side vehicle; the vehicle on the side in front of the ego vehicle can be divided into: adjacent lane side front vehicle and adjacent adjacent lane side front vehicle; the vehicle on the side behind the ego vehicle can be divided into adjacent lane side rear vehicle and adjacent adjacent lane side rear vehicle.

[0065] Exemplarily, Figure 2 A schematic diagram for numbering vehicles around the ego vehicle is provided in the embodiments of the present application, as shown in Figure 2 The vehicle directly in front of the ego vehicle ego is numbered as 1; the vehicle directly behind the ego vehicle ego is numbered as 11; the vehicles on the side of the ego vehicle ego are numbered as 7, 8, 27 and 28; the vehicles on the side front of the ego vehicle ego are numbered as 3, 5, 4, 6, 23, 25, 24 and 26; the vehicles on the side rear of the ego vehicle ego are numbered as 9, 10, 29 and 30.

[0066] Among them, the No. 7 vehicle and the No. 8 vehicle belong to the adjacent lane side vehicles; the No. 27 vehicle and the No. 28 vehicle belong to the adjacent adjacent lane side vehicles; the No. 3 vehicle, the No. 5 vehicle, the No. 4 vehicle and the No. 6 vehicle belong to the adjacent lane side front vehicles; the No. 23 vehicle, the No. 25 vehicle, the No. 24 vehicle and the No. 26 vehicle belong to the adjacent adjacent lane side front vehicles; the No. 9 vehicle and the No. 10 vehicle belong to the adjacent lane side rear vehicles; the No. 29 vehicle and the No. 30 vehicle belong to the adjacent adjacent lane side rear vehicles.

[0067] The method for judging whether the vehicles around the ego vehicle hinder the lane change of the ego vehicle will be described in detail below.

[0068] The calculation of lane change inhibition refers to the judgment of the longitudinal relationship of the vehicles on both sides of the current lane of the ego vehicle, and whether the vehicles around the ego vehicle inhibit the lane change of the ego vehicle (i.e., whether they hinder the lane change). It can also include the detection of irregular obstacles, including but not limited to water barriers, cone barrels and stone piers. If it is judged that there is a risk of collision with irregular obstacles when changing lanes to the side, the lane change will also be inhibited.

[0069] Exemplarily, the detection of irregular obstacles can be achieved through automatic driving drivable space perception technology.

[0070] The following describes whether the vehicles around the ego vehicle inhibit the lane change of the ego vehicle.

[0071] The inhibition of the vehicles around the ego vehicle includes front vehicle inhibition, side front vehicle inhibition, side vehicle inhibition and side rear vehicle inhibition.

[0072] The following describes the front vehicle inhibition: The lane change inhibition of the front target is very important. If the distance to the front vehicle is very close or the collision time is very short, the lane change path cannot be avoided in time, so it is necessary to inhibit the lane change and slow down to increase the distance before changing lanes.

[0073] In some optional embodiments, whether the front vehicle of the ego vehicle hinders the lane change of the ego vehicle is judged according to the collision time of the front vehicle of the ego vehicle or the time distance of the front vehicle of the ego vehicle.

[0074] Exemplarily, in the case that the collision time TTC of the vehicle in front of the ego vehicle is less than a collision time threshold TTC Threshod , it is considered that the vehicle in front of the ego vehicle hinders the lane change of the ego vehicle. Or, in the case that the time distance of the vehicle in front of the ego vehicle is less than a time distance threshold, it is considered that the vehicle in front of the ego vehicle hinders the lane change of the ego vehicle.

[0075] The collision time TTC of the vehicle in front of the ego vehicle can be determined according to the current driving speed of the vehicle in front of the ego vehicle and the acceleration of the vehicle in front of the ego vehicle.

[0076] The side front vehicle and the side rear vehicle are introduced as follows: In some optional embodiments, the first safety distance LcDiS Threshold is determined according to the current driving speed of the ego vehicle.

[0077] The first safety distance LcDiS Threshold is a distance between the ego vehicle and the vehicle around the ego vehicle for preventing collision.

[0078] It can be understood that, based on the size relationship between the first safety distance and the horizontal distance between the ego vehicle and the vehicle around the ego vehicle in the driving direction, it is determined that the vehicle around the ego vehicle hinders the lane change of the ego vehicle, which can quickly obtain a judgment result and has a relatively low requirement on the algorithm.

[0079] Further, in some optional embodiments, the first safety distance LcDiS self can be determined according to at least one of the following parameters: a safety threshold SafeDis corresponding to the current driving speed of the ego vehicle, a time distance TimeGap between the vehicle around the ego vehicle and the ego vehicle, a distance LcDiS self required for the ego vehicle to drive away from the current driving lane of the ego vehicle assuming that the ego vehicle completes the lane change, a driving distance DecelDiS target of the vehicle around the ego vehicle assuming that the ego vehicle completes the lane change and the driving speed of the vehicle around the ego vehicle is the same as the driving speed of the vehicle in front of the ego vehicle, a speed Vt Finished of the vehicle around the ego vehicle when the vehicle around the ego vehicle completes the lane change, and a distance LcDiS target required for the vehicle around the ego vehicle to drive away from the current driving lane of the vehicle around the ego vehicle assuming that the vehicle around the ego vehicle completes the lane change. Threshold

[0080] It can be understood that, since these parameters are easy to obtain and easy to calculate, the requirement on the algorithm can be reduced.

[0081] ​To make the calculated first safety distance LcDiS Threshold more accurate, the first safety distance LcDiS Threshold may be calculated according to the following formula (1) for example: (1) The safety threshold SafeDis corresponding to the current driving speed of the ego vehicle may be obtained by looking up a first corresponding relationship table for example. The first corresponding relationship table is a list of corresponding relationships between the current driving speed of the ego vehicle and the safety threshold SafeDis, that is, the current driving speed of the ego vehicle is different, and the corresponding safety threshold SafeDis is different. For safety, in the embodiments of the present application, it is stipulated that the higher the current driving speed of the ego vehicle, the larger the minimum safety threshold SafeDis. It can be understood that those skilled in the art can set the corresponding relationship between the current driving speed of the ego vehicle and the safety threshold SafeDis according to actual conditions.

[0082] The safety threshold SafeDis refers to the distance between the ego vehicle and the vehicle directly in front of the ego vehicle on the current driving lane of the ego vehicle.

[0083] In some optional embodiments, the time gap TimeGap between the vehicle around the ego vehicle and the ego vehicle can be a value preset in advance. In other optional embodiments, it can also be determined according to the lane changing style, which is not particularly limited in the present application, and will be described below taking the time gap TimeGap between the vehicle around the ego vehicle and the ego vehicle as an example, which is determined according to the lane changing style. This can make the lane changing safer.

[0084] The relationship between the time gap TimeGap (which can also be referred to as the lane changing inhibition time gap) between the vehicle around the ego vehicle and the ego vehicle and the lane changing style will be described below.

[0085] The lane changing style may include at least one of an agile lane changing style, a standard lane changing style, and a gentle lane changing style for example.

[0086] The lane changing inhibition time gap in the agile lane changing style case is the smallest, the lane changing inhibition time gap in the gentle lane changing style case is the largest, and the lane changing inhibition time gap in the standard lane changing style case is larger than the lane changing inhibition time gap in the agile lane changing style case and smaller than the lane changing inhibition time gap in the gentle lane changing style case.

[0087] In some optional embodiments, the distance LcDiS width required for the ego vehicle to drive off the current driving lane of the ego vehicle can be determined according to the current driving speed Vi of the ego vehicle, the lane changing time LcTime required for the ego vehicle to complete lane changing, the lane width Lane self of the current driving lane of the ego vehicle, and the sampled acceleration Ai.

[0088] wherein the sampling acceleration Ai is obtained by sampling a preset acceleration range according to a preset sampling step.

[0089] Exemplarily, it is assumed that the distance LcDiS required for the ego vehicle to drive off the current driving lane of the ego vehicle is self The distance LcDiS can be calculated by the following formula (2): (2) wherein the current driving speed Vi of the ego vehicle can be obtained by a sensor; it is assumed that the lane changing time LcTime required for the ego vehicle to complete lane changing can be a preset value; the lane width Lane of the current driving lane of the ego vehicle can be obtained by a sensor. width The lane width Lane can be obtained by a sensor.

[0090] It can be understood that these parameters are easy to obtain and easy to calculate, and thus the requirement for the algorithm can be reduced.

[0091] In some optional embodiments, the driving distance DecelDiS from when the ego vehicle completes lane changing to when the speed of the ego vehicle is the same as the driving speed of the vehicle in front can be determined according to the assumed driving speed Vi of the ego vehicle when the ego vehicle completes lane changing, Finished the target deceleration time DecelTime and the target deceleration TgtDecel. self .

[0092] Exemplarily, it is assumed that the driving distance DecelDiS from when the ego vehicle completes lane changing to when the speed of the ego vehicle is the same as the driving speed of the vehicle in front is self The distance DecelDiS can be calculated by the following formula (3): (3) wherein the target deceleration TgtDecel refers to the deceleration required for the ego vehicle to reach the same speed as the vehicle in front of the ego vehicle after lane changing.

[0093] Further, in some optional embodiments, the target deceleration TgtDecel can be obtained by looking up a second relationship corresponding list, the second relationship corresponding list referring to a corresponding relationship list of the distance between the ego vehicle and the vehicles around the ego vehicle and the comfortable deceleration, the comfortable deceleration being obtained first, and then the ego vehicle drives at the comfortable deceleration to obtain the deceleration required for the ego vehicle to reach the same speed as the vehicle in front after lane changing, and driving at the comfortable deceleration can reduce the forward inclination feeling of the driver caused by sudden deceleration.

[0094] The target deceleration time DecelTime refers to the time required for the vehicle to decelerate from its current speed to the target speed; the comfortable deceleration refers to the deceleration that the driver or passengers can tolerate without obvious discomfort during the vehicle deceleration process.

[0095] In some optional embodiments, the vehicle can be assumed to have a driving speed Vi when the vehicle completes the lane change. Finished Assume that the speed of the vehicles around the vehicle when they complete the lane change is Vt Finished And the target deceleration rate TgtDecel determines the target deceleration time DecelTime.

[0096] For example, the target deceleration time DecelTime can be calculated by the following formula (4): (4) It can be understood that these parameters are easy to obtain and easy to calculate, thus reducing the requirements on the algorithm.

[0097] In some optional embodiments, the driving speed Vi when the vehicle completes the lane change can be determined based on the current driving speed Vi of the vehicle, the sampled acceleration Ai, and the lane change time LcTime required for the vehicle to complete the lane change. Finished .

[0098] For example, the driving speed Vi when the vehicle completes the lane change can be calculated by the following formula (5): Finished .

[0099] (5) In some optional embodiments, the speed Vt of the vehicles around the self-vehicle when the lane change is completed can be determined based on the current driving speed Vt of the vehicles around the self-vehicle, the acceleration At of the vehicles around the self-vehicle, and the lane change time LcTime required for the self-vehicle to complete the lane change. Finished .

[0100] For example, the speed Vt of the vehicles around the vehicle when the vehicle completes the lane change can be calculated by the following formula (6): Finished : (6) The current speed Vt of the vehicles around the vehicle can be obtained through sensors; the acceleration At of the vehicles around the vehicle can also be obtained through sensors.

[0101] It can be understood that these parameters are easy to obtain and easy to calculate, thus reducing the requirements on the algorithm.

[0102] In some optional embodiments, the speed Vt of the vehicles around the vehicle when completing the lane change can be assumed to beFinished The target deceleration time DecelTime is used to determine the distance DecelDiS that the vehicle around the vehicle will travel after the vehicle completes the lane change and changes its speed to the same speed as the vehicle directly in front. target .

[0103] For example, the distance traveled by the vehicles around the vehicle after the vehicle completes the lane change and changes its speed to the same speed as the vehicle directly in front can be calculated according to the following formula (7): target : (7) It can be understood that these parameters are easy to obtain and easy to calculate, thus reducing the requirements on the algorithm.

[0104] In some optional embodiments, the distance LcDiS that the vehicles around the ego vehicle need to travel to leave the current lane of the vehicles around the ego vehicle can be determined based on the acceleration At of the vehicles around the ego vehicle, the lane change time LcTime that the ego vehicle needs to complete the lane change, and the current speed Vt of the vehicles around the ego vehicle. target .

[0105] For example, the distance LcDiS that the vehicles around the vehicle need to travel to leave the current lane of the vehicles around the vehicle can be calculated by the following formula (8): target : (8) It can be understood that these parameters are easy to obtain and easy to calculate, thus reducing the requirements on the algorithm.

[0106] When the vehicle around the vehicle is the vehicle in front of the adjacent lane (for example, vehicle No. 3): the first safety distance includes the collision avoidance distance LcDiS between the vehicle and the vehicle in front of the adjacent lane. Threshold邻侧前 The vehicles around the vehicle are obstructing the vehicle's lane change, including: the vehicle in front of the adjacent lane is obstructing the vehicle's lane change.

[0107] Among them, the collision avoidance distance LcDiS between the vehicle and the vehicle in front of the adjacent lane is Threshold邻侧前 This is the LcDiS calculated when the vehicles around the vehicle are clearly identified as the vehicles in front of the adjacent lane. Threshold .

[0108] Based on the first safety distance and the horizontal distance between the ego vehicle and the vehicles around the ego vehicle in the driving direction, it is determined that the vehicles around the ego vehicle are obstructing the ego vehicle's lane change, including: based on the anti-collision distance LcDiS between the ego vehicle and the vehicle in front of the adjacent lane Threshold邻侧前 and the horizontal distance PosX between the vehicle and the vehicle in front of the adjacent lane in the driving directiontarget邻侧前 The relationship between the longitudinal distance (i.e., the longitudinal distance between the vehicle and the vehicle in front of the adjacent lane) determines that the vehicle in front of the adjacent lane is an obstacle to the vehicle's lane change.

[0109] Among them, the horizontal distance PosX between the vehicle and the vehicle in front of the adjacent lane in the driving direction target邻侧前 Can be obtained through sensors.

[0110] For example, in LcDiS Threshold邻侧前 >PosX target邻侧前 In the case of , it is considered that the vehicle in front of the adjacent lane is hindering the lane change of the own vehicle.

[0111] It can be understood that when the anti-collision distance between the ego vehicle and the vehicle in front of the adjacent lane is greater than the horizontal distance between the ego vehicle and the vehicle in front of the adjacent lane in the driving direction, it means that the ego vehicle will not collide with the vehicle in front of the adjacent lane during the lane change process. The anti-collision distance between the ego vehicle and the vehicle in front of the adjacent lane is simple and easy to calculate, and the horizontal distance between the ego vehicle and the vehicle in front of the adjacent lane in the driving direction can be obtained through the sensor. Therefore, the entire process has relatively low requirements for the algorithm.

[0112] When the vehicle around the vehicle is the vehicle in front of the adjacent lane (for example, vehicle No. 23): the first safety distance includes the collision avoidance distance LcDiS between the vehicle and the vehicle in front of the adjacent lane. Threshold邻邻侧前 The vehicles around the vehicle are obstructing the vehicle's lane change, including: the vehicle in front of the adjacent lane is obstructing the vehicle's lane change.

[0113] Among them, the collision avoidance distance LcDiS between the vehicle and the vehicle in front of the adjacent lane is Threshold邻邻侧前 This is the LcDiS calculated when the vehicles around the vehicle are clearly defined as the vehicles in front of the adjacent lane. Threshold .

[0114] Based on the first safety distance and the horizontal distance between the ego vehicle and the vehicles around the ego vehicle in the driving direction, determining whether the vehicles around the ego vehicle are obstructing the ego vehicle's lane change includes: based on the anti-collision distance LcDiS between the ego vehicle and the vehicle in front of the adjacent lane Threshold邻邻侧前 and the horizontal distance PosX between the vehicle and the vehicle in front of the adjacent lane in the driving direction target邻邻侧前 The relationship between the longitudinal distance (i.e., the longitudinal distance between the vehicle and the vehicle in front of the adjacent lane) determines that the vehicle in front of the adjacent lane is an obstacle to the vehicle's lane change.

[0115] Among them, the horizontal distance PosX between the vehicle and the vehicle in front of the adjacent lane in the driving direction target邻邻侧前 Can be obtained through sensors.

[0116] For example, in PosXtarget邻邻侧前 <LcDiS Threshold邻邻侧前 , and the probability that the vehicle in front of the adjacent lane changes lanes to the lane adjacent to the current lane of the own vehicle is greater than the second lane-changing probability threshold, and the amount by which the vehicle in front of the adjacent lane presses the lane line of the adjacent lane of the current lane of the own vehicle is greater than the second lane-pressing amount threshold, it is determined that the vehicle in front of the adjacent lane poses an obstacle to the lane change of the own vehicle.

[0117] It can be understood that in addition to considering the first safety distance and the horizontal distance between the vehicle and the vehicle in front on the adjacent lane in the driving direction, the lane changing probability and the amount of crossing the line of the vehicle in front on the adjacent lane are also considered. Taking into account the safety of the vehicle after changing lanes, it is possible to further improve safety while obtaining judgment results quickly.

[0118] When the vehicle around the vehicle is a vehicle behind the adjacent lane (e.g., vehicle No. 9): the first safety distance includes the collision avoidance distance LcDiS between the vehicle and the vehicle behind the adjacent lane. Threshold邻侧后 The vehicles around the vehicle are obstructing the vehicle's lane change, including: the vehicle behind the adjacent lane is obstructing the vehicle's lane change.

[0119] Among them, the collision avoidance distance LcDiS between the vehicle and the vehicle behind it in the adjacent lane is Threshold邻侧后 This is the LcDiS calculated when the vehicles around the vehicle are clearly defined as the vehicles behind the adjacent lane. Threshold .

[0120] Based on the first safety distance and the horizontal distance between the ego vehicle and the vehicles around it in the driving direction, determining whether the vehicles around it are obstructing the ego vehicle's lane change includes: based on the anti-collision distance LcDiS between the ego vehicle and the vehicle behind it in the adjacent lane Threshold邻侧后 and the horizontal distance PosX between the vehicle and the vehicle behind it in the adjacent lane in the direction of travel target邻侧后 The relationship between the longitudinal distance between the vehicle and the vehicle behind the adjacent lane is used to determine whether the vehicle behind the adjacent lane is hindering the vehicle's lane change.

[0121] Among them, the horizontal distance PosX between the vehicle and the vehicle behind the adjacent lane in the driving direction target邻侧后 Can be obtained through sensors.

[0122] For example, in LcDiS Threshold邻侧后 >|PosX target邻侧后 + the length of the vehicle behind the adjacent lane|, it is determined that the vehicle behind the adjacent lane is hindering the lane change of the own vehicle.

[0123] It is understandable that due to the greater uncertainty of the rear vehicle, in order to prevent the rear vehicle from rear-ending the vehicle, in addition to considering the safety suppression distance (i.e. the first safety distance) and the longitudinal distance (i.e. the horizontal distance between the vehicle and the rear vehicle on the adjacent lane in the driving direction), the body length of the rear vehicle (i.e. the length of the rear vehicle on the adjacent lane) is also considered. This can not only quickly obtain the judgment result, but also improve safety.

[0124] If the vehicle around the ego vehicle is the vehicle behind the adjacent lane (e.g., vehicle No. 29), the first safety distance includes the collision avoidance distance LcDiS between the ego vehicle and the vehicle behind the adjacent lane. Threshold邻邻侧后 The vehicles around the vehicle are obstructing the vehicle's lane change, including: the vehicle behind the adjacent lane is obstructing the vehicle's lane change.

[0125] Among them, the collision avoidance distance LcDiS between the vehicle and the vehicle behind it on the adjacent lane is Threshold邻邻侧后 This is the LcDiS calculated when the vehicles around the vehicle are clearly defined as the vehicles behind the adjacent lane. Threshold .

[0126] Based on the first safety distance and the horizontal distance between the ego vehicle and the vehicles around the ego vehicle in the driving direction, determining whether the vehicles around the ego vehicle are obstructing the ego vehicle's lane change includes: based on the anti-collision distance LcDiS between the ego vehicle and the rear vehicle on the adjacent lane Threshold邻邻侧后 and the horizontal distance PosX between the vehicle and the vehicle behind it in the adjacent lane in the driving direction target邻邻侧后 The relationship between the longitudinal distance (i.e. the longitudinal distance between the vehicle and the vehicle behind it in the adjacent lane) determines that the vehicle behind it in the adjacent lane is hindering the vehicle's lane change.

[0127] Among them, the horizontal distance PosX between the vehicle and the vehicle behind it on the adjacent road in the driving direction target邻邻侧后 Can be obtained through sensors.

[0128] For example, in LcDiS Threshold邻邻侧后 >|PosX target邻邻侧后 + the length of the rear vehicle on the adjacent lane|, and when the probability of the rear vehicle on the adjacent lane changing lanes to the adjacent lane of the current lane of the own vehicle is greater than the first lane-changing probability threshold, and the amount by which the rear vehicle on the adjacent lane presses the lane line of the adjacent lane of the current lane of the own vehicle is greater than the first lane-pressing amount threshold, it is determined that the rear vehicle on the adjacent lane poses an obstacle to the lane change of the own vehicle.

[0129] It can be understood that, in order to prevent the rear vehicle from colliding with the ego vehicle, in addition to considering the first safety distance and the horizontal distance between the ego vehicle and the rear vehicle on the adjacent lane side in the driving direction, the body length of the rear vehicle on the adjacent lane side is also considered, and the lane changing probability and the line pressure of the rear vehicle on the adjacent lane side are also considered, so that the judgment result can be obtained quickly and the safety can be further improved.

[0130] The side vehicle suppression is introduced as follows: In some optional embodiments, when the side vehicle is the adjacent lane side vehicle (for example, vehicle No. 7), the judgment method of the lane changing of the side vehicle to the ego vehicle is that: in the case that the adjacent lane side vehicle exists, it is determined that the lane changing of the adjacent lane side vehicle to the ego vehicle is hindered.

[0131] In some optional embodiments, when the side vehicle is the adjacent lane side vehicle (for example, vehicle No. 27), the judgment method of the lane changing of the side vehicle to the ego vehicle is that: in the case that the adjacent lane side vehicle exists, and the probability of the adjacent lane side vehicle changing lanes to the adjacent lane of the current driving lane of the ego vehicle is greater than a third lane changing probability threshold, it is determined that the lane changing of the adjacent lane side vehicle to the ego vehicle is hindered.

[0132] The first lane changing probability threshold, the second lane changing probability threshold and the third lane changing probability threshold can be the same or different, which is not particularly limited in the present application.

[0133] The method of selecting the target gap from the multiple candidate gaps based on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap is introduced in detail as follows.

[0134] In some optional embodiments, the method of selecting the target gap from the multiple candidate gaps based on the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap comprises: determining the score of the candidate gap based on the gap length of the candidate gap and the corresponding first weight and the distance between the ego vehicle and the candidate gap and the corresponding second weight; wherein the first weight is greater than the second weight; or the first weight is less than the second weight; selecting the target gap from the multiple candidate gaps based on the scores of the multiple candidate gaps.

[0135] Exemplarily, the sum of the first weight and the second weight can be 1. It can be understood that the sum of the first weight and the second weight can also be other numerical values, which is not particularly limited in the present application.

[0136] It can be understood that the score of the candidate gap is determined based on the gap length of the candidate gap and the corresponding first weight and the distance between the ego vehicle and the candidate gap and the corresponding second weight. The first weight and the second weight are used to indicate whether more emphasis is placed on the effect of the gap length on the candidate gap or the effect of the distance on the candidate gap. If the first weight is greater than the second weight, it means that more emphasis is placed on the effect of the gap length on the candidate gap, which means that more attention is paid to whether the lane change is safe. Therefore, the occurrence of collisions after the lane change can be further reduced, thereby improving the safety of the lane change. If the second weight is greater than the first weight, it means that more emphasis is placed on the effect of the distance on the candidate gap, which means that more attention is paid to whether the lane change can be done quickly. Therefore, lane departure and the occurrence of the following vehicle occupying the target gap in advance can be reduced, thereby allowing the ego vehicle to complete the lane change as soon as possible.

[0137] Exemplarily, the score of the candidate gap is determined based on the gap length of the candidate gap and the corresponding first weight and the distance between the vehicle and the candidate gap and the corresponding second weight, including: the score of each candidate gap is obtained according to the following method: a gap score value is obtained by multiplying the first weight and the gap length of the candidate gap, a distance score value is obtained by multiplying the second weight and the distance between the vehicle and the candidate gap, and the sum of the gap score value and the distance score value is determined as the score of the candidate gap; based on the scores of multiple candidate gaps, a target gap is selected from the multiple candidate gaps.

[0138] In order to select the candidate gap that the ego vehicle can reach fastest, in some optional embodiments, the product of the second weight and the distance between the ego vehicle and the candidate gap may be the product of the second weight and the shortest distance between the ego vehicle and the candidate gap.

[0139] In other optional embodiments, a target gap is selected from multiple candidate gaps based on the gap length of the candidate gap and the distance between the vehicle and the candidate gap, including: determining the score of the candidate gap based on the product of the score of the gap length of the candidate gap and a third weight, and based on the product of the score of the distance between the vehicle and the candidate gap and a fourth weight; wherein the third weight is greater than the fourth weight; or, the third weight is less than the fourth weight; and selecting the target gap from multiple candidate gaps based on the scores of the multiple candidate gaps.

[0140] Exemplarily, the sum of the third weight and the fourth weight may be 1. It is understandable that the sum of the third weight and the fourth weight may also be other values, which is not particularly limited in this application.

[0141] For example, the longer the gap length of the candidate gap is, the higher the score of the gap length of the candidate gap is; and the smaller the distance between the vehicle and the candidate gap is, the greater the score of the distance between the vehicle and the candidate gap is.

[0142] It can be understood that the method of determining the scores of candidate gaps based on the product of the score of the candidate gap length and the third weight, and based on the product of the score of the distance between the vehicle and the candidate gap and the fourth weight, can make the target gaps selected subsequently more accurate.

[0143] In some optional embodiments, based on the scores of the plurality of candidate slots, selecting the target slot from the plurality of candidate slots may include: considering the candidate slot with the highest score as the target slot.

[0144] In order to prevent misjudgment and make the selected target gap more accurate, in other optional embodiments, based on the scores of multiple candidate gaps, the target gap is selected from multiple candidate gaps, including: comparing the candidate gap with the highest score with a preset gap threshold; if the candidate gap with the highest score is greater than the preset gap threshold, the candidate gap with the highest score is regarded as the target gap; if the candidate gap with the highest score is ≤ the preset gap threshold, it is considered that there is no target gap.

[0145] Furthermore, in some other optional embodiments, when no target gap is selected, the vehicle is controlled to continue traveling in the gap between the vehicle directly in front of the vehicle and the vehicle directly behind the vehicle.

[0146] The following describes how to obtain candidate gaps: In some optional embodiments, candidate gaps are obtained by the following method: when there is no vehicle on the side of the vehicle or the vehicle on the side of the vehicle has no intention of overtaking, the gaps between the front and rear vehicles on the adjacent lane of the vehicle's current driving lane whose lengths are outside the first distance range are eliminated, and the remaining gaps are candidate gaps; wherein, the distance between the vehicle directly in front of the vehicle in the vehicle's current driving lane and the vehicle itself is the upper limit value of the first distance range, and the distance between the vehicle directly behind the vehicle in the vehicle's current driving lane and the vehicle itself is the lower limit value of the first distance range.

[0147] Furthermore, in other optional embodiments, the distance between the vehicle directly in front of the vehicle in the vehicle's current driving lane and the vehicle itself may be the lower limit value of the first distance range, and the distance between the vehicle directly behind the vehicle in the vehicle's current driving lane and the vehicle itself may be the upper limit value of the first distance range.

[0148] The following explanation will be given by taking as an example the distance between the vehicle directly in front of the vehicle in the current lane of the vehicle as the upper limit value of the first distance range, and the distance between the vehicle directly behind the vehicle in the current lane of the vehicle as the lower limit value of the first distance range.

[0149] Exemplarily, the first distance range can be formed with the ego vehicle as the origin, the distance between the ego vehicle and the vehicle in front of the ego vehicle as a positive value, and the distance between the ego vehicle and the vehicle behind the ego vehicle as a negative value. For example, the distance between the No. 1 vehicle and the ego vehicle ego is 50 meters (m), and the distance between the No. 11 vehicle and the ego vehicle ego is -100 meters (m), and the first distance range is [-100 m, 50 m]. It can be understood that the first distance range [-100 m, 50 m] is only an example, and the first distance range is not limited in the present application, and is subject to the actual situation.

[0150] Exemplarily, Figure 3 A schematic diagram of the gaps between the ego vehicle and the vehicles around the ego vehicle is provided for the embodiments of the present application, as shown in FIG. 1. Figure 3 As shown in FIG. 1, the gap between the No. 5 vehicle and the No. 3 vehicle is gap 1, the gap between the No. 3 vehicle and the No. 7 vehicle is gap 2, the gap between the No. 7 vehicle and the No. 11 vehicle is gap 3, and the gap between the No. 11 vehicle and the No. 39 vehicle is gap 4.

[0151] In the method, the gaps 1, 2, 3 and 4 are screened by using the first distance range, the gaps with a length outside the first distance range are excluded, and candidate gaps are obtained. Then, the candidate gaps are scored based on the first weight and the second weight, and the target gap is selected from the multiple scored candidate gaps.

[0152] It can be understood that since the first distance range is determined according to the first distance between the vehicle in front of the ego vehicle and the ego vehicle and the second distance between the vehicle behind the ego vehicle and the ego vehicle, the vehicle in front of the ego vehicle will limit the acceleration of the ego vehicle, and the vehicle behind the ego vehicle will limit the deceleration of the ego vehicle. Therefore, by screening the gaps using the first set, the gaps that the ego vehicle cannot reach by acceleration / deceleration although the safety accident can be avoided after the ego vehicle changes lanes can be screened out, and the gaps obtained are the gaps that are conducive to the ego vehicle to change lanes under the condition of ensuring the driving safety of the ego vehicle, so that the lane changing is easier.

[0153] In other optional embodiments, the candidate gaps are obtained by the following method: first, the vehicles on the adjacent lane of the ego vehicle are sorted from front to back, then all the gaps are calculated, and then the vehicles on the lane changing side (i.e., the adjacent lane) with a longitudinal distance outside the first distance range are excluded, and the gaps formed by the remaining vehicles are calculated respectively, and the gaps formed by the remaining vehicles are the candidate gaps.

[0154] S102, based on the target gap, controlling the ego vehicle to drive on the current driving lane to a lane changing position.

[0155] In some optional embodiments, based on the target gap, the control of the ego vehicle to drive in the current driving lane to the lane-changing position comprises: determining a target driving speed required for the ego vehicle to drive to the lane-changing position according to the motion information of the two vehicles before and after the target gap; obtaining a first acceleration according to the target driving speed and the current driving speed of the ego vehicle; and controlling the ego vehicle to shift gears according to the first acceleration to drive in the current driving lane to the lane-changing position.

[0156] The lane-changing position is a safe lane-changing position, and when the ego vehicle drives to the safe lane-changing position, a collision situation caused by sudden acceleration of the rear vehicle and / or sudden deceleration of the front vehicle can be avoided.

[0157] Exemplarily, the first acceleration can be obtained through cruise control: the target driving speed is set as a speed control target of the cruise control, and the cruise control controls the current driving speed of the ego vehicle to the speed control target to obtain the first acceleration.

[0158] It can be understood that, since the candidate gaps obtained based on the first distance range are gaps that are conducive to lane changing of the ego vehicle in the case of ensuring driving safety of the ego vehicle, the target gap selected from the candidate gaps is a gap that is more conducive to lane changing of the ego vehicle, and the first acceleration obtained based on the target gap causes the ego vehicle to drive in the current driving lane to the lane-changing position according to the first acceleration, so that the ego vehicle can reach the lane-changing position as soon as possible for lane changing even when there are front and rear vehicles.

[0159] It can be understood that, through the first acceleration for gear shifting, the ego vehicle drives to the lane-changing position, and then through the second acceleration for gear shifting, the ego vehicle drives from the lane-changing position to the target gap, on the one hand, in the process of driving to the lane-changing position according to the first acceleration, the vehicles around the ego vehicle can be reminded that the ego vehicle is changing lanes, so that the situation of sudden acceleration of the rear vehicle or sudden deceleration of the front vehicle is reduced, and the safety during lane changing is improved, on the other hand, in the whole process of driving from the lane-changing position to the target gap according to the second acceleration after driving to the lane-changing position according to the first acceleration, a buffer period is reserved, so that if the rear vehicle accelerates or the front vehicle decelerates, the ego vehicle can not change lanes first, further reducing the occurrence of safety accidents, on the third hand, when the ego vehicle is at the lane-changing position, the acceleration of the rear vehicle or the deceleration of the front vehicle can be inhibited to some extent, so that the situation of collision is reduced, and the safety is improved, on the fourth hand, when the ego vehicle is at the lane-changing position, the ego vehicle can also seize the opportunity to change lanes, that is, in the case that the front and / or rear vehicles of the ego vehicle have the same lane-changing demand as the ego vehicle (i.e., in the case that the front and / or rear vehicles of the ego vehicle want to change lanes to the same lane as the ego vehicle), since the ego vehicle has already changed lanes partially, and the vehicles that need to change lanes are just preparing to change lanes, the ego vehicle can change lanes faster, and the lane-changing rate is improved.

[0160] For example, when the first acceleration is negative, the vehicle decelerates (also referred to as decelerating) to the lane-changing position, and the vehicle can refer to Figure 4 , Figure 4 A schematic diagram of a vehicle driving to a lane-changing position by changing speed is provided in an embodiment of the present application, as shown in FIG. Figure 4 As shown in Figure 2, the target car ego reduces its speed and drives to a lane-changing position, making it easier for it to enter the target gap.

[0161] For example, when the first acceleration is positive, the vehicle accelerates (also called speed-up driving) to the lane-changing position, and the vehicle can refer to Figure 5 , Figure 5 Another schematic diagram of a vehicle driving to a lane-changing position by changing speed is provided in an embodiment of the present application, as shown in FIG. Figure 5 As shown in Figure 2, the target car ego accelerates to a lane-changing position to facilitate entering the target gap.

[0162] S103: Control the vehicle to change lanes from the lane-changing position to the target gap.

[0163] In some optional embodiments, controlling the vehicle to change lanes from a lane-changing position to a target gap includes: obtaining a second acceleration corresponding to a current lane-changing scenario from accelerations corresponding to a plurality of pre-configured lane-changing scenarios; and controlling the vehicle to change speed according to the second acceleration when safety conditions are met, thereby changing lanes from the lane-changing position to the target gap.

[0164] Among them, the safety conditions include at least one of the following: the vehicle is in the lane change request stage or the lane change control stage; the accumulated lane change time from the start of the lane change to the current moment is less than the first time length; the vehicle has currently crossed the lane line; the current driving speed of the vehicle does not exceed a preset speed threshold; the minimum deceleration of the vehicle is greater than a preset deceleration threshold.

[0165] The minimum deceleration is the minimum deceleration among the decelerations caused by the vehicle avoiding an obstacle during travel.

[0166] Furthermore, for example, the minimum deceleration may include, but is not limited to, cone deceleration, pedestrian deceleration, and cut-in deceleration, wherein the cut-in deceleration is used to indicate the acceleration of target vehicles around the vehicle when cutting into the target lane.

[0167] For example, in some optional embodiments, when the minimum deceleration of the vehicle is greater than a preset deceleration threshold, it is considered that the safety condition is met; when the minimum deceleration of the vehicle is greater than a preset deceleration threshold, it is considered that there is no danger.

[0168] In yet another example, the safety condition is considered to be met in a case that the ego vehicle is in the lane-changing request phase or in the lane-changing control phase, and that the time length required for the ego vehicle to change lanes to the target gap is determined based on the second acceleration to be less than the first time length, and that the ego vehicle has currently crossed the lane line, and that the current speed of the ego vehicle does not exceed the pre-set speed threshold, and that the minimum deceleration of the ego vehicle is greater than the pre-set deceleration threshold.

[0169] It can be understood that the accumulated lane-changing time from the start of the lane-changing to the current time being less than the first time length indicates that the ego vehicle does not exceed the time limit for the lane-changing at the current time; and that the current speed of the ego vehicle not exceeding the pre-set speed threshold indicates that the ego vehicle does not exceed the speed limit.

[0170] Exemplarily, the lane-changing time is generated in the process of the lane-changing, the whole system starts timing when the lane-changing is allowed, and then the lane-changing time is accumulated every frame. It is assumed that the accumulated lane-changing time is less than the first time length at the current frame, which indicates that the lane-changing has not exceeded the time limit at the current time.

[0171] Exemplarily, it is assumed that the first time length can be 10 seconds, each frame corresponds to 0.025 seconds, and the current frame is 100 frames. From the start of the lane-changing, the accumulated lane-changing time at the current time has been 2.5 seconds. Since 2.5 seconds is less than 10 seconds, it is indicated that the lane-changing has not exceeded the time limit at the current time. If the lane-changing time has exceeded 10 seconds and the lane-changing is still in progress, it is indicated that there is a problem in the lane-changing process. It can be understood that the consideration of whether the lane-changing exceeds the time limit can know whether there is a problem in the lane-changing process. In the case that there is a problem, the lane-changing is temporarily not performed, which can make the lane-changing process safer.

[0172] It can be understood that the whole system starts timing when the lane-changing is allowed, and whether the lane-changing is completed is determined every frame. Exemplarily, it is determined that the lane-changing is not completed at the current frame. If the accumulated lane-changing time from the start of the lane-changing to the current frame is less than the first time length, it is considered that the lane-changing does not exceed the time limit. If the accumulated lane-changing time is greater than the first time length, it is considered that the lane-changing exceeds the time limit. It is determined that the lane-changing is completed at the current frame. If the accumulated lane-changing time from the start of the lane-changing to the current frame is less than the first time length, it is indicated that the whole lane-changing time does not exceed the time limit, and it can also be considered that the lane-changing does not exceed the time limit. If the accumulated lane-changing time is greater than the first time length, it is indicated that the whole lane-changing time exceeds the time limit, and it can also be considered that the lane-changing exceeds the time limit.

[0173] It can be understood that the ego vehicle does not immediately change to the target gap, but enters the target gap under the condition that the safety condition is met. In this way, the lane-changing of the ego vehicle can be safer and faster. In addition, the safety condition is associated with the lane-changing request, whether the lane-changing exceeds the time limit, whether the lane line is crossed, whether the speed limit is exceeded, and whether it is dangerous, so that the lane-changing is safer and more efficient.

[0174] Furthermore, in some optional embodiments, the deceleration threshold is adaptively adjusted according to the deceleration scenario.

[0175] Among them, the deceleration scenario includes at least one of the following: a deceleration scenario for following a vehicle, a deceleration scenario for vehicles in the original lane during lane change, and a cruise control scenario.

[0176] For example, when the deceleration scenario is a vehicle-following deceleration scenario, the deceleration threshold is obtained by looking up a table based on the obtained time interval of the tracked vehicle.

[0177] It is understandable that different time intervals between tracked vehicles correspond to different deceleration thresholds. The deceleration threshold obtained based on the time interval between tracked vehicles can make lane changing safer in the following vehicle deceleration scenario.

[0178] For example, when the deceleration scenario is a deceleration scenario for a vehicle in the original lane during a lane change process, the deceleration threshold is dynamically adjusted according to the lane change completion time of the vehicle. The longer the lane change completion time, the greater the deceleration threshold.

[0179] It's understandable that the longer the lane change completion time, the higher the deceleration threshold. This trades time for safety redundancy, reducing the likelihood of misjudgments. If the deceleration threshold remains unchanged, a safe lane change could be misjudged as a dangerous maneuver. For example, a smooth merge onto a highway might take longer to complete, but it's still safe.

[0180] For example, when the deceleration scenario is a cruise control scenario, the deceleration threshold is a speed control target during cruise control.

[0181] It can be understood that aligning the deceleration threshold with the speed control target can avoid redundant braking triggered by a too low deceleration threshold, reduce acceleration fluctuations, and reduce the occupants' feeling of leaning forward.

[0182] The following describes the process of obtaining the second acceleration: Furthermore, in some optional embodiments, the second acceleration may be obtained by the following method: S1. Sampling a preset acceleration range according to a preset sampling step to obtain multiple sampled accelerations.

[0183] S2. After traversing all sampled accelerations, obtain a first sampled acceleration range within which vehicles in front of the vehicle will not hinder the vehicle's lane change, a second sampled acceleration range within which vehicles to the side of the vehicle will not hinder the vehicle's lane change, and a third sampled acceleration range within which vehicles behind the vehicle will not hinder the vehicle's lane change; take the intersection of the first sampled acceleration range, the second sampled acceleration range, and the third sampled acceleration range to obtain the lane change acceleration range.

[0184] Exemplarily, reference can be made to Table 1.

[0185] Table 1 Determination of lane-changing acceleration range

[0186] Exemplarily, the preset acceleration range is [-Maxccel, Maxccel]; -Maxccel is the minimum acceleration; Maxccel is the maximum acceleration; acc_i (which can also be Ai) is the sampled acceleration collected according to the preset sampling step accel_step.

[0187] Exemplarily, the vehicle in the side front of the ego vehicle is sampled according to the preset sampling step accel_step and the preset acceleration range [-Maxccel, Maxccel], to obtain a first sampled acceleration range [-Maxccel, acc_i+accel_step] in which the vehicle in the side front will not hinder the lane-changing of the ego vehicle; the vehicle in the side of the ego vehicle is sampled according to the preset sampling step accel_step and the preset acceleration range [-Maxccel, Maxccel], to obtain a second sampled acceleration range [-Maxccel, Maxccel] in which the vehicle in the side will not hinder the lane-changing of the ego vehicle; the vehicle in the side rear of the ego vehicle is sampled according to the preset sampling step accel_step and the preset acceleration range [-Maxccel, Maxccel], to obtain a third sampled acceleration range [acc_i, Maxccel] in which the vehicle in the side rear will not hinder the lane-changing of the ego vehicle.

[0188] Therefore, the intersection of the first sampled acceleration range, the second sampled acceleration range and the third sampled acceleration range is [acc_i, acc_i+accel_step], i.e., the lane-changing acceleration range is [acc_i, acc_i+accel_step].

[0189] Exemplarily, -Maxccel can be -1.6, Maxccel can be 1.6, and the sampling step has a value range of [0.2, 0.5]. It can be understood that -Maxccel can be -1.6, Maxccel can be 1.6, and the sampling step has a value range of [0.2, 0.5] is only an example, and the application does not limit the value range of -Maxccel, Maxccel and the sampling step.

[0190] It should be understood that -Maxccel represents the minimum acceleration and can be a number less than 0, 0, or greater than 0. This application does not impose any specific restrictions on the value of -Maxccel, which is subject to actual conditions. Maxccel represents the maximum acceleration and can be a number less than 0, 0, or greater than 0. This application does not impose any specific restrictions on the value of Maxccel, which is subject to actual conditions. In practical applications, it is sufficient to ensure that -Maxccel is smaller than Maxccel.

[0191] S3. Determine a second acceleration from the lane-changing acceleration range based on different lane-changing scenarios.

[0192] Among them, the lane changing scenarios include at least one of the following: there is a vehicle within the first preset range, there is a large vehicle to the side and rear of the vehicle, there is a large vehicle to the side and rear of the vehicle and there is a vehicle in the first preset range, the vehicle directly behind the vehicle cuts out in the same direction as the vehicle, and general lane changing scenarios.

[0193] Illustratively, in a lane-changing scenario where there is a vehicle within a first preset range, the second acceleration is: the smallest positive sampled acceleration in the lane-changing acceleration range.

[0194] For example, in a lane-changing scenario where there is a large vehicle to the side and rear of the vehicle, the second acceleration is the maximum sampled acceleration in the lane-changing acceleration range.

[0195] Illustratively, in a lane-changing scenario where there is a large vehicle to the side and rear of the vehicle, and there is a vehicle within the first preset range, the second acceleration is: any sampled acceleration that is less than the average value of the lane-changing acceleration range but greater than the smallest positive sampled acceleration in the lane-changing acceleration range.

[0196] For example, in a lane-changing scenario where the vehicle directly behind the vehicle cuts out in the same direction as the vehicle, the second acceleration is any sampled acceleration that is greater than the average value of the lane-changing acceleration range but less than the maximum sampled acceleration in the lane-changing acceleration range.

[0197] Exemplarily, when the lane changing scenario is a general lane changing scenario, the second acceleration is an average value of the lane changing acceleration range.

[0198] It is understandable that the second acceleration determined according to different lane changing scenarios can make lane changing safer and more efficient.

[0199] Furthermore, in some optional embodiments, when sampling a preset acceleration range according to a preset sampling step size, the sampling upper limit can be adjusted.

[0200] The sampling upper limit may be adjusted according to at least one of the lane changing style, the speeding limit, the time distance limit, and the lane changing mode.

[0201] Exemplarily, the sampling upper limit is adjusted according to the lane changing style, including: the sampling upper limit in the agile lane changing style is greater than the sampling upper limit in the standard lane changing style; the sampling upper limit in the standard lane changing style is greater than the sampling upper limit in the smooth lane changing style.

[0202] Exemplarily, the sampling upper limit is adjusted according to the speeding limit, including: when the current driving speed of the vehicle does not exceed the set first speed limit, the sampling upper limit is the upper limit of the preset acceleration range; when the current driving speed of the vehicle exceeds the first speed limit but does not exceed the preset speed threshold, the sampling upper limit is the difference obtained by subtracting the sampling step from the upper limit of the preset acceleration range; when the current driving speed of the vehicle is between the preset speed threshold and the speed range of the maximum vehicle speed, the sampling upper limit is the first preset sampling upper limit.

[0203] The first speed limit is less than a preset speed threshold, which is less than the maximum vehicle speed. The first speed limit is related to the speed limit of the current lane in which the vehicle is traveling.

[0204] The corresponding relationship between the sampling upper limit and the current speed of the vehicle can be seen in Table 2.

[0205] Table 2 Correspondence between the sampling upper limit and the current speed of the vehicle

[0206] As can be seen from Table 2, when the current vehicle speed is ≤ the first speed limit (SetSpd_mps), the upper sampling limit is the upper limit of the preset acceleration range (i.e., the maximum acceleration Maxaccel); when the first limit SetSpd_mps is less than the current vehicle speed ≤ the preset speed threshold (SetSpd_mps + spd_step), the upper sampling limit is the difference between the maximum acceleration Maxaccel and the sampling step size accel_step; when the preset speed threshold (SetSpd_mps + spd_step) is less than the current vehicle speed ≤ the maximum vehicle speed (OverSpdMax_mps), the upper sampling limit is the first preset upper sampling limit. In this embodiment, the first preset upper sampling limit is 0. It is understood that 0 is an example and can be other values ​​in actual applications, and this application does not specifically limit this.

[0207] The first speed limit SetSpd_mps is related to the specified speed limit of the current lane of the ego vehicle, that is, the specified speed limit of the current lane of the ego vehicle is equal to the first speed limit SetSpd_mps; the sampling speed spd_step can be a speed calculated according to a first percentage of the specified speed limit of the current lane of the ego vehicle allowed to be exceeded in advance, or the sampling speed spd_step can also be a preset speed in advance, which is not particularly limited in the present application, and the following will be exemplarily described by taking the sampling speed spd_step as a speed calculated according to a first percentage of the specified speed limit of the current lane of the ego vehicle allowed to be exceeded in advance.

[0208] Exemplarily, assuming that the specified speed limit of the current lane of the ego vehicle is 80 kilometers per hour (that is, the first speed limit SetSpd_mps is exemplarily 80 kilometers per hour), the maximum speed of the ego vehicle is 150 kilometers per hour, and 10% of the specified speed limit of the current lane is allowed to be exceeded (that is, the first percentage is exemplarily 10%), then the sampling speed spd_step = 80 + 80 * 10% = 88 (kilometers per hour), that is, the current driving speed of the ego vehicle is constrained not to exceed 88 kilometers per hour, therefore, when the current driving speed of the ego vehicle is less than or equal to 80 kilometers per hour, the sampling upper limit is the maximum acceleration; when the current driving speed of the ego vehicle exceeds 80 kilometers per hour but is less than or equal to 88 kilometers per hour, the sampling upper limit is 0.

[0209] Exemplarily, the adjustment of the sampling upper limit according to the time interval restriction includes: when the current time interval of the ego vehicle is less than the time interval threshold, the sampling upper limit is a second preset sampling upper limit.

[0210] The second preset sampling upper limit can be the same as the first sampling upper limit, or can be different, and the following will be exemplarily described by taking the second preset sampling upper limit as 0.

[0211] Exemplarily, the adjustment of the sampling upper limit according to the lane changing mode includes: the lane changing mode at least includes one of the following: obstacle avoidance lane changing mode, merging mode, navigation mode lane changing, and lever lane changing mode.

[0212] The sampling upper limit of the obstacle avoidance lane changing mode is greater than the sampling upper limit of the merging mode; the sampling upper limit of the merging mode is greater than the sampling upper limit of the navigation mode lane changing; the sampling upper limit of the navigation mode lane changing is greater than the sampling upper limit of the lever lane changing mode; and the sampling upper limit of the lever lane changing mode is greater than the sampling upper limit of the overtaking lane changing.

[0213] That is, the sampling range in the obstacle avoidance lane changing mode is greater than the sampling range in the merging lane changing mode, the sampling range in the merging lane changing mode is greater than the sampling range in the extended navigation lane changing mode, the sampling range in the extended navigation lane changing mode is greater than the sampling range in the lever lane changing mode, and the sampling range in the lever lane changing mode is greater than the sampling range in the overtaking lane changing mode.

[0214] In some optional embodiments, the vehicle lane changing control method provided by the embodiments of the present application further includes the following step S104.

[0215] S104, in the case that the lane changing of the vehicle around the ego vehicle does not hinder the lane changing of the ego vehicle and the ego vehicle will not back up, controlling the ego vehicle to shift gears based on the second acceleration obtained in advance to drive off the current driving lane of the ego vehicle.

[0216] The method for determining whether the vehicle around the ego vehicle will cause the ego vehicle to back up during the lane changing (which can also be referred to as lane changing back up) is similar to the method for determining whether the lane changing of the vehicle around the ego vehicle hinders the lane changing of the ego vehicle (which can also be referred to as lane changing inhibition), and thus will not be described herein.

[0217] The difference between the lane changing back up and the lane changing inhibition is that the requirement for the lane changing back up is more stringent, which is reflected in that the safety threshold SafeDis selected under the lane changing inhibition is greater than the safety threshold SafeDis selected under the lane changing back up, and the lane changing time LcTime required for the ego vehicle to complete the lane changing set under the lane changing inhibition is greater than the lane changing time LcTime required for the ego vehicle to complete the lane changing set under the lane changing back up.

[0218] It can be understood that, for those skilled in the art who know how to determine whether the vehicle around the ego vehicle will hinder the lane changing of the ego vehicle, how to determine whether the vehicle around the ego vehicle will cause the ego vehicle to back up during the lane changing can be easily inferred, and thus will not be described herein.

[0219] The present application designs a method for adjusting the back up strength with the back up preset time, the lane changing back up considers the time of the lane changing duration, the longer the lane changing process lasts, the shorter the collision prediction time is, and the fixed prediction time is prevented from causing the false back up when the lane changing is almost completed.

[0220] In other optional embodiments, the embodiments of the present application also provide a back up weakening method for mutual suppression between a target (i.e., a vehicle) and a target, taking the side rear vehicle back up calculation as an example, the side rear target is predicted to slow down by judging whether the front vehicle has the trend or action of the same direction lane changing, and thus the back up of the side rear vehicle is weakened.

[0221] In some optional embodiments, the embodiments of the present application also provide a method for optimizing a far-away quick target trigger false back-off. In a daily driving environment, a vehicle with a large speed difference is often encountered. A collision is predicted to occur, but the vehicle has a probability and time to change lanes, slow down, or follow the vehicle, so the vehicle should not trigger back-off. Therefore, the embodiments of the present application dynamically predict whether the vehicle will slow down according to the distance between the vehicle and the vehicle.

[0222] For example, a collision time is obtained according to the speed and distance of the vehicle around the ego vehicle, and a minimum safety distance threshold is obtained according to the collision time. The greater the collision time, the smaller the minimum safety distance threshold. Since the minimum safety distance threshold is decreasing, the probability of back-off triggering can be reduced.

[0223] After calculating the back-off signal of each vehicle around the ego vehicle, it is determined which target back-off signal needs to be output according to the lane changing control stage and whether the vehicle crosses the line. The back-off signal is output to the decision system, and then the decision system tells all modules to cancel the lane change and back off to the original lane to follow the vehicle.

[0224] It can be understood that when the ego vehicle is not hindered by the vehicle around the ego vehicle, the ego vehicle does not directly change lanes, but considers whether a collision with the vehicle around the ego vehicle will occur. When no collision occurs, the second acceleration obtained in advance is controlled to change the speed of the ego vehicle to drive away from the current driving lane of the ego vehicle. In this way, the lane changing is more secure on the basis of quick lane changing.

[0225] The following examples describe possible implementation schemes of the lane changing control method of one or more embodiments described above.

[0226] The embodiments provide a low-time-complexity acceleration and deceleration lane changing longitudinal planning calculation method (i.e., a vehicle lane changing control method), which includes lane changing safety distance calculation, lane changing suppression judgment, lane changing back-off calculation, lane changing condition creation, and lane changing acceleration decision method. The method ensures the safety and smoothness of the lane changing process through multi-target dynamic analysis and acceleration sampling, in combination with the kinematic characteristics of the vehicle, greatly reducing the algorithm complexity of the entire module.

[0227] The vehicle lane changing control method provided by the embodiments can refer to Figure 6 .

[0228] Figure 6 Another flowchart of the vehicle lane changing control method provided by the embodiments of the present application is shown in FIG. 6, which includes the following steps. Figure 6 S601, receiving a lane changing request.

[0229] ​S602, judge whether there is inhibition (obstruction), if there is obstruction, execute step S607, if there is no inhibition, execute step S603.

[0230] The ego vehicle judges whether there is inhibition after receiving the lane changing request, and calculates the lane changing acceleration.

[0231] S603, lane changing longitudinal decision.

[0232] In the absence of inhibition, the lane changing longitudinal decision is made, that is, the lane changing acceleration (i.e., the second acceleration) is decided.

[0233] S604, lane changing control.

[0234] The lane changing control is performed according to the decided lane changing acceleration.

[0235] S605, lane changing rollback.

[0236] After the lane changing acceleration is decided, the lane changing rollback is judged, and if there is no lane changing rollback, step S606 is performed, and if there is lane changing rollback, the lane changing is not performed.

[0237] S606, lane changing completion.

[0238] The ego vehicle performs lane changing according to the decided lane changing acceleration.

[0239] S607, based on the gap search, the ego vehicle reaches the lane changeable position by accelerating or decelerating.

[0240] The ego vehicle obtains the optimal gap (also referred to as the target gap) based on the gap search, and then calculates a suitable speed according to the information of the two vehicles before and after the optimal gap, and the ego vehicle can drive to the lane changeable position on the current lane by decelerating or accelerating at the calculated speed. After reaching the lane changeable position, the lane changing is performed to the optimal gap, so that the lane changing can be completed.

[0241] For safety considerations, as an optional embodiment, after reaching the lane changeable position, it is judged again whether the vehicles around the ego vehicle cause inhibition and rollback to the lane changing of the ego vehicle, and in the absence of inhibition and rollback, the lane changing is performed to the optimal gap, so that the lane changing can be completed.

[0242] After the lane changing task is activated, the safety distance (i.e., the first safety distance) of the lane changing is calculated first, and the safety distance of the lane changing is calculated by analyzing the speed, acceleration and distance of the ego vehicle and the vehicles around the ego vehicle, and considering the comfortable deceleration after the lane changing and the safety distance threshold. The method proposed in this embodiment is suitable for lane changing safety distance calculation in a multi-target dynamic scene.

[0243] The lane change suppression judgment module distinguishes and judges vehicles in adjacent lanes and adjacent adjacent lanes according to the calculated safety distance of lane change. For a side front target, whether lane change needs to be suppressed is judged in combination with the cut-in probability and the line pressure of the side front vehicle; for a side rear vehicle, judgment is made based on higher safety parameters and the length of the side rear vehicle. The method is suitable for the dynamic suppression needs of vehicles in different lanes, and the method is effective and the time consumption of the algorithm is low.

[0244] The lane change rollback calculation module adopts a similar idea as lane change suppression, but more conservatively considers lane change duration and vehicle mutual influence to avoid false rollback. By dynamically predicting the behavior of the rear vehicle, the rollback strength is adjusted, and the method is suitable for lane change rollback optimization in complex traffic scenarios.

[0245] The lane change condition creation module drives to a lane changeable position through acceleration and deceleration operations in the current driving lane of the ego vehicle, handles complex gap scenarios, and selects the optimal gap for lane change operation. The module is suitable for lane change condition optimization under different traffic densities. The core of the embodiment is to simplify the method of circulating through complex gaps to a single scenario, anchor a gap for acceleration and deceleration, drive to a lane changeable position, create conditions for lane change, and then perform corresponding acceleration and deceleration operations according to different lane change modes. This method can avoid the frustration caused by changing instructions from day to night.

[0246] The acceleration and deceleration lane change decision module proposes a safe and smooth decision method that comprehensively judges lane change status, timeout, dangerous state, completion flag, and overspeed factors to determine whether to output lane change acceleration (i.e., second acceleration), ensuring the safety and smoothness of the lane change process. The module is suitable for safe and timely switching of lane change acceleration and following acceleration and deceleration in multi-target dynamic scenarios, ensuring the safety of lane change.

[0247] The use of the various methods proposed in the embodiment can effectively improve the efficiency and safety of lane change calculation on low-cost and low-computing-power platforms, meeting the lane change needs of the automatic driving system in complex traffic scenarios.

[0248] The lane change control method provided in the embodiment is described in detail below.

[0249] 1. Lane change suppression and lane change acceleration and deceleration calculation method.

[0250] The embodiment provides a method for calculating lane change inhibition and lane change acceleration and deceleration with low time complexity and safe use. In various functions of the auxiliary driving, the unintended departure lane change (UDLC) is a driver triggered lane change function, and the auto lane change (ALC) is an automatic triggered lane change system of the auxiliary driving system. When the driver toggles the turn signal or the decision system automatically requests a lane change request instruction in the integrated adaptive cruise control (IACC) mode or the pilot assist mode, the auxiliary driving system samples a plurality of accelerations and decelerations according to an expected lane change direction, judges which acceleration in a target lane meets safe lane change in combination with target attributes of a vehicle periphery and a self-vehicle driving state, and outputs a lane change inhibition signal of 0 if at least one sampled acceleration meets safe lane change. The decision system triggers a lane change control command to all downstream modules, including a longitudinal control module. The longitudinal control module also records all sampled accelerations meeting safe lane change and forwards a suitable acceleration to downstream control. If all sampled accelerations calculate that the space of the target lane cannot meet safe lane change, the lane change inhibition signal is output as a number greater than 0. The specific number represents which target inhibits the lane change. The entire lane change system is in a waiting stage until the lane change condition is met, and then the lane change is performed. Alternatively, the lane change is automatically cancelled when the waiting time is too long. The specific lane change acceleration sampling calculation and lane change inhibition calculation are as follows.

[0251] Exemplarily, the specific number representing which target inhibits the lane change includes: assuming that a flag of a front side vehicle is Front_lc_sts, a flag of a side vehicle is Side_lc_sts, and a flag of a rear side vehicle is Rear_lc_sts.

[0252] Exemplarily, the specific number representing which target inhibits the lane change includes: assuming that a flag of a front side vehicle is Front_lc_sts, a flag of a side vehicle is Side_lc_sts, and a flag of a rear side vehicle is Rear_lc_sts. Figure 2For example, if Front_lc_sts=1, it means that the vehicle in front of the adjacent lane (for example, vehicle No. 3) causes inhibition to the lane changing of the ego vehicle; if Front_lc_sts=2, it means that the vehicle in front of the adjacent lane (for example, vehicle No. 23) causes inhibition to the lane changing of the ego vehicle; if Side_lc_sts=1, it means that the vehicle in the adjacent lane causes inhibition to the lane changing of the ego vehicle; if Side_lc_sts=2, it means that the vehicle in the adjacent lane (for example, vehicle No. 27) causes inhibition to the lane changing of the ego vehicle; if rear_lc_sts=1, it means that the vehicle in the rear of the adjacent lane (for example, vehicle No. 9) causes inhibition to the lane changing of the ego vehicle; if Rear_lc_sts=2, it means that the vehicle in the rear of the adjacent lane (for example, vehicle No. 29) causes inhibition to the lane changing of the ego vehicle.

[0253] 1.1, Lane changing acceleration sampling calculation.

[0254] Due to the limitation of hardware resources and computing power, and the requirement of the entire system's calculation cycle time is 0.025s, the density of the lane changing acceleration sampling (i.e., sampling acceleration) cannot be too dense, otherwise it will lead to high time complexity of the algorithm, so the acceleration step is set to 0.2 gradient (i.e., assuming the sampling step is 0.2).

[0255] The upper and lower limits of the lane changing acceleration sampling are determined by the lane changing style (for example, agile, standard and soft), the speed limit, the target time interval limit and the lane changing mode (for example, the lever lane changing mode, the overtaking lane changing mode, the obstacle avoidance lane changing mode, the merging lane changing mode and the navigation lane changing mode), etc. It is not necessary to calculate all the sampling accelerations every time the lane changing inhibition and the lane changing acceleration are calculated, and the number of calculations needs to be reduced. The embodiment provides a method of dynamically adjusting and reducing the number of calculations by scene and function.

[0256] Firstly, the lane changing style determines the maximum acceleration of the acceleration sampling array (i.e., the sampling upper limit). Three lane changing styles are designed in the embodiment, which are agile lane changing style, standard lane changing style and soft lane changing style, wherein the sampling upper limit is from large to small, i.e., the sampling upper limit under the agile lane changing style is greater than that under the standard lane changing style; the sampling upper limit under the standard lane changing style is greater than that under the soft lane changing style.

[0257] Taking the agile lane changing style as an example, the upper limit of the acceleration is MaxAccel, and then the acceleration sampling is sequentially subtracted from the basis to obtain a cyclically traversed acceleration array.

[0258] Exemplarily, assuming that the preset acceleration range is [0.6, 1.6], that is, the minimum acceleration MaxAccel is 0.6, the maximum acceleration MaxAccel is 1.6, and the sampling step is 0.2, the obtained sampling accelerations are respectively: 1.6, 1.6-0.2=1.4, 1.4-0.2=1.2, …, 0.6.

[0259] Secondly, the embodiment provides a solution to accelerate the lane change. The speed limit determines the maximum value of the acceleration sampling (i.e., the upper limit of the sampling), and exemplarily, the system allows the speed to exceed the set speed by 10% during the acceleration lane change, for example, the road speed limit is 80 kilometers per hour, and the speed during the acceleration lane change is limited to 88 kilometers per hour. Based on the above speed limit, the sampling acceleration is limited, and the corresponding relationship between the upper limit of the sampling and the current speed of the vehicle can be seen from Table 2, and the specific related description can also be seen from the description of Table 2. Through this method, the problem of accelerating and exceeding the speed by 10% can be avoided. There is a dangerous scene during the acceleration lane change, the front vehicle quickly leaves, the side rear vehicle quickly comes, and the acceleration lane change is calculated. During the acceleration process, the target in front suddenly brakes, and the vehicle is outputting the execution acceleration. Since the execution mechanism needs time to change from acceleration to deceleration or the system has a delay, this scene often leads to a risk of rear-end collision or a feeling of acceleration compression. The embodiment provides a method for optimizing this scene, which adopts a time interval and maximum acceleration mapping method, that is, when the time interval is less than the time interval threshold, the upper limit of the sampling is limited to a second preset upper limit of the sampling (for example, 0). The time interval threshold can be calibrated in advance according to the actual situation.

[0260] In the ALC automatic lane change auxiliary driving system, the lane change request issued by the decision system has multiple types, referred to as lane change modes, including the lever lane change mode, the overtaking lane change mode, the obstacle avoidance lane change mode, the merging lane change mode, and the navigation lane change mode. The requirements for the lane change acceleration in different lane change modes are also different, for example, the overtaking lane change mode tries to avoid large deceleration (i.e., the lane change acceleration is less than 0), the deceleration range of the lever lane change is allowed to be wider than that of the overtaking lane change, and the obstacle avoidance lane change mode allows large deceleration lane change. The innovative method of the embodiment takes the overtaking lane change as a reference, first calculates whether the vehicles around the vehicle hinder the lane change of the vehicle according to the sampling acceleration of the overtaking lane change, directly outputs if at least one sampling acceleration can cancel all inhibitions, and continues to calculate according to the expansion of the sampling range according to different lane change modes if all the sampling accelerations of the overtaking lane change are inhibited. Especially in the ALC mode, most of the lane change modes are automatic overtaking lane change, so the embodiment can achieve the lowest complexity calculation in most of the calculations.

[0261] That is, the sampling upper limit of the obstacle avoidance lane changing mode is greater than the sampling upper limit of the merging lane changing mode; the sampling upper limit of the merging mode is greater than the sampling upper limit of the extended navigation lane changing mode; the sampling upper limit of the extended navigation lane changing mode is greater than the sampling upper limit of the lever lane changing mode; and the sampling upper limit of the lever lane changing mode is greater than the sampling upper limit of the overtaking lane changing mode.

[0262] That is, the sampling range of the obstacle avoidance lane changing mode is greater than the sampling range of the merging lane changing mode, the sampling range of the merging lane changing mode is greater than the sampling range of the extended navigation lane changing mode; the sampling range of the extended navigation lane changing mode is greater than the sampling range of the lever lane changing mode; and the sampling range of the lever lane changing mode is greater than the sampling range of the overtaking lane changing mode.

[0263] 1.2, calculation of lane changing inhibition.

[0264] The calculation of lane changing inhibition refers to the judgment of the longitudinal relationship of the target on both sides of the current lane of the ego vehicle, and whether the lane changing of the ego vehicle is inhibited (i.e., whether the lane changing is hindered) by the vehicle around the ego vehicle. It can also include the detection of irregular obstacles, including but not limited to water barriers, cone barrels, and stone piers. If it is judged that there is a risk of collision with irregular obstacles when changing lanes to the side, the lane changing will also be inhibited.

[0265] Exemplarily, the detection of irregular obstacles can be achieved by automatic driving drivable space perception technology.

[0266] Wherein, the target refers to the vehicle around the ego vehicle, and the vehicles around the ego vehicle are numbered first. The vehicles on the left side are all odd numbers, and the vehicles on the right side are all even numbers, as shown in Figure 2 .

[0267] The inhibition of the vehicle around the ego vehicle includes front target (front vehicle) inhibition, side front target (side front vehicle) inhibition, side target (side vehicle) inhibition, and side rear target (side rear vehicle) inhibition.

[0268] 1.2.1, calculation method of front target inhibition.

[0269] The lane changing inhibition of the front vehicle is very important. If the distance to the front target is very close or the time to collision is very short, the lane changing path cannot be avoided in time, so it is necessary to inhibit the lane changing and slow down to increase the distance before changing lanes. Exemplarily, taking the front target with label 1, which is referred to as Target1, as an example.

[0270] This embodiment provides a practical and low complexity inhibition method. Condition 1 for triggering inhibition: the time to collision TTC of the front target is less than the threshold TTC ThreshodIn the case of the time to collision, the speed and acceleration are taken into account. Condition 2 for triggering inhibition: in the case of the time headway of the front target being less than the time headway threshold, the front target inhibits the lane change of the ego vehicle. Condition 1 for triggering inhibition and condition 2 for triggering inhibition are in an OR relationship.

[0271] 1.2.2. Calculation method of side front and side rear target inhibition.

[0272] Taking the overtaking lane change agile lane change mode as an example, the core of calculating inhibition and is to calculate the lane change safety distance of the ego vehicle and the target vehicle. Since the lane change function can realize speed planning for the side front target of lane change, the safety distance is calculated in the calculation process of lane change inhibition, allowing the calculation of safety distance according to the acceleration in [-MaxAccel, MaxAccel].

[0273] 1.2.2.1 The calculation process is as follows: 1) Loop through each sampling acceleration Ai in [-MaxAccel, MaxAccel], and the speed of the ego vehicle when the lane change is completed (i.e., the driving speed of the ego vehicle when the lane change is assumed to be completed) Vi Finished Reference can be made to formula (5) above.

[0274] 2) Lane change driving distance of the ego vehicle (i.e., the distance required for the ego vehicle to drive away from the current driving lane of the ego vehicle) LcDiS self The calculation can refer to formula (2) above; 3) Speed of the target vehicle when the lane change is completed (i.e., the speed of the vehicle around the ego vehicle when the lane change is assumed to be completed) Vt Finished The calculation can refer to formula (6) above; 4) Lane change process driving distance of the target vehicle (i.e., the distance required for the vehicle around the ego vehicle to drive away from the current driving lane of the vehicle around the ego vehicle) LcDiS target The calculation can refer to formula (8) above; 5) Comfort deceleration lookup table: the deceleration required for the ego vehicle to reach the same speed as the front vehicle after the lane change is completed is obtained by looking up the target distance (i.e., the distance between the ego vehicle and the vehicle around the ego vehicle) and the set comfort deceleration two-dimensional table TgtDecel, and the calculation of the specific deceleration time (i.e., target deceleration time) DecelTime can refer to formula (4) above; 6) Driving distance of the ego vehicle during the deceleration process after the lane change (i.e., the driving distance of the ego vehicle after the lane change is completed to the time when the speed is changed to be the same as the driving speed of the front target vehicle) DecelDiS self The calculation can refer to formula (3) above; 7) The driving distance of the target vehicle during the deceleration process of the ego vehicle after changing lanes (i.e., the driving distance of the vehicle around the ego vehicle when the ego vehicle has the same driving speed as the vehicle in front after completing the lane change) DecelDiS target The calculation can refer to formula (7) above. 8) Obtain the additional minimum safety threshold (i.e., safety threshold) SafeDis through a vehicle speed lookup table; the higher the vehicle speed, the larger the minimum safety threshold. 9) The lane change safety inhibition distance (i.e., the first safety distance) LcDis Threshold The calculation can refer to formula (1) above.

[0275] In this embodiment, the lane change style is innovatively associated with the minimum safety threshold and the lane change inhibition distance; the softer the lane change style, the larger the lane change inhibition distance, the larger the minimum safety threshold, and also means that the lane change safety inhibition distance is larger, and the lane change is more conservative.

[0276] The target considered by the side front inhibition is limited to a total of 8 targets of Nos. 3 / 5 / 23 / 25 and 4 / 6 / 24 / 26, and the side front target No. 3 and the adjacent side front target No. 23 are taken as examples: 1.2.2.2 Inhibition judgment of the adjacent side front target (the vehicle in the adjacent side front): If LcDis Threshold is greater than the longitudinal distance PosX target of the target distance, the target will inhibit the lane change, otherwise it will not inhibit the lane change.

[0277] It can be understood that when the inhibition judgment of the adjacent side front target is performed, the calculated LcDis Threshold is LcDiS Threshold邻侧前 , that is, the anti-collision distance between the ego vehicle and the adjacent side front target; when the inhibition judgment of the adjacent side front target is performed, the longitudinal distance PosX target of the target distance obtained is PosX target邻侧前 , that is, the horizontal distance between the ego vehicle and the adjacent side front target in the driving direction.

[0278] 1.2.2.3 Inhibition judgment of the adjacent adjacent side front target (the vehicle in the adjacent adjacent side front): For the adjacent adjacent side front target, such as the No. 23 vehicle, the anti-collision distance between the ego vehicle and the adjacent adjacent side front target (also referred to as the longitudinal safety distance inhibition) is calculated in the same way as the calculation method of the adjacent lane No. 3 vehicle, and the inhibition of the No. 23 vehicle needs to be judged by means of the cut-in probability of the No. 23 vehicle into the adjacent lane; if the following conditions are met at the same time, the adjacent adjacent side front target inhibits the lane change: a. The distance between the vehicle and the target in the adjacent lane satisfies: PosX target <LcDis Threshold ; b. The probability of the target cutting into the adjacent lane is higher than the second lane change probability threshold CutIn Threshold2 ; c. The amount by which the object ahead in the adjacent lane exceeds the lane line is greater than the second lane line pressure threshold DisToLane2; It is understandable that when performing the suppression judgment of the front target on the adjacent lane, the calculated LcDis Threshold LcDiS Threshold邻邻侧前 , that is, the anti-collision distance between the vehicle and the target in front of the adjacent lane; when making the suppression judgment of the target in front of the adjacent lane, the longitudinal distance PosX of the target distance is obtained target That is PosX target邻邻侧前 , that is, the horizontal distance between the vehicle and the target in front of the adjacent lane in the driving direction; the probability of the target in front of the adjacent lane cutting in refers to the probability that the target in front of the adjacent lane changes lanes to the adjacent lane of the vehicle's current lane; the amount by which the target in front of the adjacent lane exceeds the lane line refers to the amount by which the vehicle in front of the adjacent lane presses the lane line of the adjacent lane of the vehicle's current lane.

[0279] Lane Change Inhibition for Side and Rear Targets: Similar to side and front targets, side and rear targets are also classified into adjacent lanes and adjacent-adjacent lanes. These targets include 9 / 29 (left rear adjacent target / left rear adjacent-adjacent target) and 10 / 30 (right rear adjacent target / right rear adjacent-adjacent target).

[0280] The steps for calculating the lane change safety distance are as follows: The lane change safety distance calculation steps for the side rear target are the same as those for the side front target (steps 1-9). However, since the side rear target is located at the rear, the uncertainty at the rear is greater, so the calibration parameters need to be more stringent than those for the side front target to prevent dangerous lane changes with the risk of rear-end collisions.

[0281] 1.2.2.4 Suppression Judgment of Targets on the Side and Rear of Adjacent Lanes: Since the target is behind the vehicle, the longitudinal distance of the target is PosX targett The expression is different from the front and side front, and the target vehicle length Length Target Take it into consideration.

[0282] If the vehicle and the adjacent lane rear target satisfy |PosX target +Length Target | <LcDis ThresholdIf LcDis

[0283] It can be understood that when the inhibition judgment of the adjacent lane rear target is performed, the LcDis Threshold LcDis Threshold邻侧后 , that is, the anti-collision distance between the ego vehicle and the adjacent lane rear target; when the inhibition judgment of the adjacent lane rear target is performed, the longitudinal distance PosX target PosX target邻侧后 , that is, the horizontal spacing of the ego vehicle and the adjacent lane rear target in the driving direction.

[0284] 1.2.2.5 Inhibition of adjacent adjacent lane rear target: For the adjacent adjacent lane rear target, for example, the 29th target, the lane changing safety distance calculation steps of the adjacent adjacent lane rear target are the same as the calculation method of the adjacent lane rear target (for example, the 9th vehicle), but since the ego vehicle is located in front of the adjacent adjacent target, it has priority in lane changing, so the parameters of lane changing inhibition need to be slightly weaker than those of the adjacent target 9th target. At the same time, the cut-in probability of the 29th target into the adjacent lane is needed to judge whether to adopt the inhibition of the 29th target, and if the following conditions are met at the same time, the lane changing is inhibited: a. The distance between the ego vehicle and the target satisfies: |PosX target +Length Target |<LcDis Threshold ; b. The adjacent adjacent lane rear target cut-in probability is higher than the first cut-in probability threshold CutIn Threshold1 ; c. The adjacent adjacent lane target exceeds the lane line by a lane line exceeding amount greater than the first lane line exceeding amount threshold DisToLane1.

[0285] It can be understood that when the inhibition judgment of the adjacent adjacent lane rear target is performed, the LcDis Threshold LcDis Threshold邻邻侧后 , that is, the anti-collision distance between the ego vehicle and the adjacent adjacent lane rear target; when the inhibition judgment of the adjacent adjacent lane rear target is performed, the longitudinal distance PosX target PosX target邻邻侧后 , that is, the horizontal spacing of the ego vehicle and the adjacent adjacent lane rear target in the driving direction; the adjacent adjacent lane rear target cut-in probability refers to the probability of the adjacent adjacent lane rear target changing lanes to the adjacent lane of the current driving lane of the ego vehicle; the lane line exceeding amount of the adjacent adjacent lane rear target refers to the lane line exceeding amount of the adjacent adjacent lane rear target to the lane line of the adjacent lane of the current driving lane of the ego vehicle.

[0286] 1.2.3, Judgment of side target inhibition: The embodiment provides a simple, practical and safe side target inhibition method, and the specific method is as follows: 1.2.3.1 Judgment of adjacent lane side target inhibition: For the adjacent lane side target, exemplarily, it can be No. 7 vehicle or No. 8 vehicle.

[0287] Adjacent lane side target lane changing inhibition logic: when there is a target in the lane changing target lane corresponding to the side of the vehicle, inhibition is triggered.

[0288] Exemplarily, whether the adjacent lane side target exists or not is judged by judging the ID of the vehicle information, and when the ID of the vehicle information on the adjacent lane side is not 0, it is determined that the adjacent lane side target exists.

[0289] 1.2.3.2 Judgment of adjacent adjacent lane side target inhibition: For the adjacent adjacent lane side target, exemplarily, it can be No. 27 vehicle or No. 28 vehicle.

[0290] Adjacent adjacent lane side target lane changing inhibition logic: when there is a target in the adjacent adjacent lane side, and the cut-in probability of cutting into the adjacent lane is greater than the third cut-in threshold CutIn Threshold3 , inhibition is triggered.

[0291] 1.3, Integration of inhibition signal and lane changing acceleration.

[0292] After all the sampling accelerations are traversed in 1.2, the acceleration of all side front, side and side rear target inhibition is finally counted.

[0293] The embodiment provides a set of ideas to integrate inhibition signals and lane changing acceleration. As shown in the example shown in Table 1, the sampling range of the acceleration of all targets is [-MaxAccel, MaxAccel], the acceleration of the side front target in the range [-Maxccel, acc_i+accel_step] satisfies lane changing, and will not cause inhibition to the lane changing of the vehicle; when the side target does not exist, the acceleration of the side target in the range [-Maxccel, Maxccel] satisfies lane changing, and will not cause inhibition to the lane changing of the vehicle; the side rear target needs to accelerate lane changing or small deceleration lane changing to meet, so the acceleration of the side rear target in the range [acc_i, Maxccel] satisfies lane changing, and will not cause inhibition to the lane changing of the vehicle; finally, the intersection of the three acceleration ranges is the final lane changing acceleration range that meets all targets, and the intersection of the three feasible acceleration ranges is shown in Table 1, that is, the acceleration in the range [acc_i, acc_i+accel_step] satisfies.

[0294] After obtaining the acceleration range of all targets, the optimal acceleration of each frame needs to be calculated. The embodiment provides a method for determining the optimal acceleration (i.e., determination of the second acceleration) according to different lane-changing scenes.

[0295] Scenario one: if there is no target in the far range (i.e., the first preset range) of the lane-changing side, the smallest sampling acceleration with a positive value in the lane-changing acceleration range is outputted. In this way, acceleration overspeed after lane-changing and deceleration can be avoided, and longitudinal unevenness can be caused.

[0296] Exemplarily, the far range can be 80 m. It can be understood that 80 m is only an example of the far range, and in actual application, the far range can also be other numerical values, which are not particularly limited in comparison. Scenario two: if the side rear is a large vehicle with strong pressure, the largest sampling acceleration in the lane-changing acceleration range is outputted. In this way, the acceleration is large, and the confidence of lane-changing is stronger.

[0297] Exemplarily, whether the vehicle at the side rear is a large vehicle can be identified through a perception identification technology. The perception identification technology can identify whether the vehicle at the side rear is a large vehicle through the head style of the vehicle at the side rear, and further, the type of the large vehicle in the case that the vehicle at the side rear is a large vehicle can be known through the point cloud data of the head style. For example, the type of the large vehicle includes but is not limited to at least one of the following: a bus, a coach, a truck and a tanker.

[0298] Scenario three: on the basis of scenario two, if there is a close-range target at the side front, any sampling acceleration below the average value of the lane-changing acceleration range but larger than the smallest sampling acceleration with a positive value in the lane-changing acceleration range is outputted.

[0299] Exemplarily, whether there is a close-range target at the side front can be determined by judging the collision time between the ego vehicle and the target at the side front. For example, in the case that the collision time between the ego vehicle and the target at the side front is less than n seconds, it is considered that there is a close-range target at the side front.

[0300] Scenario four: if the target at the rear has a same-direction lane-changing action, pre-acceleration is needed to prevent the ego vehicle from retreating due to the rear vehicle changing lane first, and any sampling acceleration above the average value of the lane-changing acceleration range but smaller than the largest sampling acceleration in the lane-changing acceleration range is outputted.

[0301] The rest of the scene: because the acceleration range that the target of the three positions of side front, side and side rear meets respectively is intersected, a feasible range is represented, and too small acceleration will cause compression to the side rear target, and too large acceleration will cause compression to the side front target, so the mean of the lane changing acceleration range can be taken as the best acceleration output.

[0302] 1.4, Lane change rollback calculation method.

[0303] This embodiment designs a lane change rollback method similar to lane change suppression, both of which calculate whether to collide with the target after lane changing is completed, but the difference is that lane change suppression is more conservative than lane change rollback, and the safety distance of lane change suppression is larger.

[0304] The difference is that lane change rollback is more stringent than lane change suppression, which is reflected in that when the safety threshold SafeDis is selected, the safety threshold SafeDis selected under lane change suppression is greater than the safety threshold SafeDis selected under lane change rollback; when the lane changing time LcTime required for the ego vehicle to complete lane changing is set, the lane changing time LcTime set under lane change suppression is greater than the lane changing time LcTime set under lane change rollback.

[0305] This embodiment designs a method of adjusting the rollback intensity with the preset rollback time, and the lane change rollback considers the time of lane change duration. The longer the lane change process lasts, the shorter the collision prediction time is, so as to prevent the fixed prediction time from causing false rollback when the lane change is almost completed.

[0306] This embodiment designs a rollback weakening method of mutual suppression between targets and targets, taking the side rear target rollback calculation as an example, by judging whether the rear target has a tendency or action of same direction lane changing to predict that the side rear fast target will slow down, and then to weaken the rollback of the side rear target.

[0307] This embodiment designs a method of optimizing the triggering of false rollback of a far fast target. In the daily driving environment, a target with a large speed difference is often encountered, which is predicted to collide, but since the distance is still far, the target has a probability and time of lane changing or slowing down, and should not trigger rollback, so this embodiment dynamically predicts whether the target will slow down according to the distance between the target and the ego vehicle.

[0308] Exemplarily, specifically, the collision time is obtained according to the speed and distance of the target and the ego vehicle, and the minimum safety distance threshold is obtained according to the collision time, and the larger the collision time is, the smaller the minimum safety distance threshold is. Since the minimum safety distance threshold is decreasing, the probability of rollback triggering can be reduced.

[0309] After the fallback signal of each target is calculated, it is decided which target's fallback signal needs to be output according to the lane changing control stage and whether it is crossing the line. The fallback signal is output to the decision system, and then the decision system tells all modules to cancel the lane change and fallback to the original lane following driving.

[0310] Exemplarily, taking the No. 9 target as an example, if the ego vehicle has crossed the line and the No. 9 target falls back, the ego vehicle does not fall back. At each moment, whether each target falls back is calculated according to the above target fallback calculation method.

[0311] 1.5, the lane speed up and down to create a lane changing condition method.

[0312] Not every lane change request can be successful. When a lane change request is made, there is a target in at least one of the side or side front distance or side rear distance, and at least one inhibition is generated. Therefore, the lane change control command cannot be switched, and only lane change waiting is allowed. Since the decision system issues a lane change request, it should try to cancel the inhibition signal to complete the lane change longitudinal planning.

[0313] This embodiment designs a method for creating a lane changing space by speeding up and down in the ego lane with low time complexity. Due to limited hardware resources and computing power, the time complexity and space complexity of the algorithm are minimized. The method of looping through complex gaps is simplified to a single scenario, and then the corresponding speed up and down operation is performed according to the scenario.

[0314] For the target selected by the upstream target selection target module, map the target longitudinal distance to the longitudinal coordinate, and then according to the gap size on the lane change side, the target speed and acceleration on the lane change side, and the distance that should be inhibited at the current speed, form a target gap from multiple targets to determine a target gap, and then nail the gap to create a lane changing condition by speeding up and down. This can avoid the confusion caused by changing orders at different times, and can also reduce the complexity from m*n to m+n.

[0315] Method: Simplify the scenario. The target that is most likely to be inhibited during lane changing is the side target. Therefore, the scenario is simplified according to whether there is a side target.

[0316] Step 1: There is a vehicle on the side, and the side vehicle has a tendency to speed up and overtake the ego vehicle. Let the side vehicle go first.

[0317] Step 2: There is no car on the side, or the car on the side has no intention of overtaking. First, sort all targets from front to back, and then calculate all gaps. The gap between the ego vehicle and the target is shown in the following figure: Figure 3 .

[0318] Third step: Because the target 1 and target 11 in front and behind of ego vehicle will limit the acceleration and deceleration of ego vehicle, the distance between target 1 and ego vehicle and the distance between target 11 and ego vehicle form a set (i.e. the first distance range), and the target whose longitudinal distance is out of the set is excluded, that is, the gap formed by the first set is used to filter the gap on the lane-changing side.

[0319] Fourth step: Calculate the gap formed by the remaining targets to obtain the candidate gap.

[0320] Fifth step: Score the candidate gap according to the product of the first weight and the length of the candidate gap, and the product of the second weight and the shortest distance between the head of the ego vehicle and the candidate gap.

[0321] Fifth step: Select the target gap to calculate the acceleration by combining the gap score.

[0322] Sixth step: If the best insertion position (i.e. target gap) is not calculated: operate in the gap between target 1 and target 11 in front and behind of the current lane.

[0323] Seventh step: If the best insertion position (i.e. target gap) is calculated, plan the acceleration and deceleration method based on the front and back targets of the target gap: according to the obtained target gap, obtain the target information of the front and back targets of the gap, calculate a target speed according to the target information of the two targets, and then perform cruise control to obtain an acceleration. The schematic diagram of creating a lane-changing space by decelerating or accelerating in the current lane is shown in Figure 4 and Figure 5 .

[0324] The essence of accelerating or decelerating in the current lane to create a lane-changing space is that the ego vehicle can reach the lane-changing position by accelerating or decelerating in the current lane of the ego vehicle, and then change lanes from the lane-changing position to the target gap when reaching the lane-changing position.

[0325] 1.6, Lane-changing acceleration decision method (i.e. how to decide the second acceleration).

[0326] After the lane-changing acceleration and deceleration in the current lane have been calculated, they are not always executed, but are executed after being decided by safety.

[0327] Exemplarily, the flag indicating whether the execution can be output is called TtyOutInprocess Flag The embodiment proposes a safe and smooth decision method, which is determined by the lane-changing state, lane-changing timeout state, danger state, lane-changing completion flag and overspeed judgment.

[0328] 1) Exemplarily, the flag of the lane change state is AlcCmd, if the system is in the lane change request or lane change control stage, the flag of the lane change state AlcCmd is True, considering that it is in the lane change request stage or the lane change control stage.

[0329] 2) Exemplarily, the flag of the danger state is Danger Flag The embodiment provides a method for adjusting a danger state judgment threshold value according to a scene. First, the minimum value of all longitudinal accelerations except lane change acceleration is considered as a reference, and second, the deceleration threshold value is adjusted according to different deceleration scenes.

[0330] All longitudinal accelerations except lane change acceleration are all decelerations of the ego vehicle in the driving process due to obstacle avoidance, including but not limited to conical barrel deceleration, pedestrian deceleration and cut-in deceleration.

[0331] The following takes three deceleration scenes as examples to illustrate how to adjust the deceleration threshold value: 2.1) When the scene is a following vehicle deceleration scene, the deceleration threshold value is obtained based on the time interval table of the tracked vehicle.

[0332] 2.2) When the scene is a deceleration scene of the original lane target in the lane change process, the deceleration threshold value is dynamically adjusted according to the lane change completion time of the ego vehicle, and the longer the lane change completion time, the greater the deceleration threshold value.

[0333] 2.3) When the scene is a cruise control deceleration scene, the threshold value of the cruise deceleration (also referred to as the speed control target) is taken as the deceleration threshold value.

[0334] If the minimum value of all decelerations is less than one of the three deceleration threshold values, the danger state flag Danger Flag is True.

[0335] 3) Exemplarily, the flag of the lane change completion is LaneChange Flag Whether the lane change is completed can be judged by whether the lane change crosses the lane line.

[0336] Exemplarily, whether the lane change crosses the lane line can be judged by the constant term jump of the left and right lane lines, and in the case of crossing the lane line, it is considered that the lane change is completed, and the lane change completion flag LaneChange Flag is True.

[0337] 4) Exemplarily, the flag of the lane change timeout state is OverTime Flag If the lane change time is within the first time length, the flag of the lane change timeout state OverTime Flagis True, it is considered that the lane change is not overtime; wherein, the lane change time is a cumulative value, which is counted from the time when the whole system allows lane change to the current time, and the accumulated lane change time, or also can be called as the duration.

[0338] It can be understood that from the time when the whole system allows lane change, each frame uses a constant item jump to determine whether the lane change is completed, for example, if the lane change is not completed under the current frame, the accumulated lane change time from the time when the whole system allows lane change to the current frame is less than the first time length, it is considered that the lane change is not overtime, and if the accumulated lane change time is greater than the first time length, it is considered that the lane change is overtime; if the lane change is completed under the current frame, if the accumulated lane change time from the time when the whole system allows lane change to the current frame is less than the first time length, it is considered that the whole lane change time is overtime, and if the accumulated lane change time is greater than the first time length, it is considered that the whole lane change time is overtime.

[0339] 5) OverSpd is True Flag , the current speed of the vehicle does not exceed the pre-set speed threshold (for example, does not exceed 10% of the set speed in the acceleration lane change process), the OverSpd flag is True, if the speed reaches the highest limit speed, a flag of maintaining the highest speed uniform speed driving is output to be used for planning limit. Flag

[0340] When AlcCmd, OverTime Flag , LaneChange Flag and OverSpd Flag are all True and Danger Flag is False, TtyOutInprocess Flag is True, allowing the lane change acceleration (i.e. the second acceleration) to be output for execution, if a dangerous scene is encountered in the lane change process, for example, an obstacle is encountered in the acceleration lane change process and needs to be decelerated urgently, Danger Flag is True, TtyOutInprocess Flag is switched to False in time, and then a safe and smooth switching to safe deceleration is realized, so that the lane change is ensured to be smooth under the premise of safety and efficiency.

[0341] ​The vehicle lane change control method provided in this embodiment includes a lane change target suppression method, a lane change acceleration planning method, a lane change backoff calculation method, a method for accelerating and decelerating the current lane to create lane change conditions after the lane change target is suppressed, and a lane change acceleration and deceleration determination method. It is directly applied to a low-cost map-free intelligent assisted driving system, which can realize automatic lane changing on highways and expressways, lane changing to avoid obstacles, and delayed navigation lane changing, and has been mass-produced in multiple vehicle model projects.

[0342] In summary, the lane changing control method provided by this application can take into account both computational efficiency and planning quality to meet the real-time and safety requirements of the intelligent driving system. It has both lane changing suppression in dangerous lane changing scenarios and comfortable and safe lane changing longitudinal planning. At the same time, it considers the dynamic and static targets of the five lanes to ensure the safety of lane changing. It also provides a method for creating lane changing conditions in the lane when the lane change is stuck by the car next to it, and provides a method for lane changing fallback processing in dangerous scenarios that occur during the lane changing process. Moreover, these methods have low time complexity and can run on a low-cost and low-computing power platform.

[0343] It should be noted that although the steps of the method of the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all steps must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps; or steps in different embodiments may be combined to form a new technical solution.

[0344] Based on the same inventive concept as the aforementioned embodiments, an embodiment of the present application provides a vehicle lane changing control device, which includes the modules included and the units included in each module, and can be implemented by a processor; of course, it can also be implemented by a specific logic circuit; during implementation, the processor can be an AI acceleration engine (such as NPU, etc.), GPU, central processing unit (CPU), microprocessor (MPU), digital signal processor (DSP) or field programmable gate array (FPGA), etc.

[0345] Figure 7 A schematic diagram of a vehicle lane-changing control device provided in an embodiment of the present application is shown in FIG. Figure 7 As shown, the vehicle lane-changing control device 70 includes a selection module 701, a first control module 702, and a second control module 703, wherein: The selection module 701 is configured to select a target gap from a plurality of candidate gaps based on at least the gap length of the candidate gap and the distance between the ego vehicle and the candidate gap, when a vehicle surrounding the ego vehicle obstructs the ego vehicle's lane change; wherein the candidate gap is a gap in a lane adjacent to the ego vehicle's current lane; The first control module 702 is configured to control the vehicle to travel in the current lane to a lane-changing position based on the target gap; The second control module 703 is configured to control the vehicle to change lanes from the lane-changeable position to the target gap.

[0346] In some optional embodiments, the second control module 703 is further configured to control the vehicle to change speed based on a pre-obtained second acceleration to leave the current driving lane of the vehicle when the vehicles around the vehicle do not hinder the lane change of the vehicle and the vehicle will not back down.

[0347] The description of the above device embodiment is similar to the description of the above method embodiment and has similar beneficial effects as the method embodiment. For technical details not disclosed in the device embodiment of this application, please refer to the description of the method embodiment of this application for understanding.

[0348] It should be noted that the division of modules in the embodiments of the present application is schematic and is merely a logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units. They may also be implemented in the form of a combination of software and hardware.

[0349] It should be noted that in the embodiments of the present application, if the above-mentioned method is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the relevant technology. The computer software product is stored in a storage medium and includes a number of instructions for enabling the vehicle equipment to execute all or part of the methods of each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk or an optical disk. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0350] The embodiment of the present application provides a vehicle device, Figure 8 A schematic diagram of the structure of a vehicle device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the vehicle device 80 includes a memory 801 and a processor 802 . The memory 801 stores a computer program that can be run on the processor 802 . When the processor 802 executes the program, the steps in the method provided in the above embodiment are implemented.

[0351] It should be noted that the memory 801 is configured to store instructions and applications executable by the processor 802, and can also buffer data (for example, image data, audio data, voice communication data and video communication data) to be processed or having been processed by the processor 802 and various modules in the vehicle device 80, which can be implemented by FLASH or Random Access Memory (RAM).

[0352] The embodiments of the present application further provide a computer readable storage medium for storing a computer program.

[0353] Optionally, the computer readable storage medium can be applied to the vehicle device in the embodiments of the present application, and the computer program causes the processor or the vehicle device to perform the various methods of the embodiments of the present application, which will not be described herein for the sake of brevity.

[0354] The embodiments of the present application further provide a computer program product comprising computer program instructions.

[0355] Optionally, the computer program product can be applied to the vehicle device in the embodiments of the present application, and the computer program instructions cause the processor or the vehicle device to perform the various methods of the embodiments of the present application, which will not be described herein for the sake of brevity.

[0356] The embodiments of the present application further provide a computer program.

[0357] Optionally, the computer program can be applied to the vehicle device in the embodiments of the present application, and when the computer program runs on the processor or the vehicle device, causes the processor or the vehicle device to perform the various methods of the embodiments of the present application, which will not be described herein for the sake of brevity.

[0358] It should be noted that the above descriptions of the vehicle device, the storage medium, the computer program product and the computer program embodiments are similar to the descriptions of the method embodiments, and have similar beneficial effects. For technical details not disclosed in the vehicle device, the storage medium, the computer program product and the computer program embodiments of the present application, please refer to the description of the method embodiments for understanding.

[0359] It should be understood that the term "one embodiment" or "an embodiment" or "some embodiments" as used herein means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. Therefore, the appearances of the phrase "in one embodiment" or "in an embodiment" or "in some embodiments" in various places throughout the specification are not necessarily referring to the same embodiment. Furthermore, the particular features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that the sequence of steps in the above-described processes does not necessarily mean that the steps are executed in the order described, and the execution order of the steps should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the application. The sequence numbers of the above-described embodiments of the application are only for description, and do not represent the advantages or disadvantages of the embodiments. The above description of each embodiment tends to emphasize the differences between the embodiments, and the same or similar parts can be mutually referred to, and are not described herein for the sake of brevity.

[0360] The term "and / or", as used herein, merely describes association between associated objects, and can mean that three relationships exist, for example, object A and / or object B can mean that object A exists alone, object A and object B exist together, and object B exists alone.

[0361] It should be noted that the terms "comprising", "including", or any other variant are intended to cover a non-exclusive inclusion, such that processes, methods, articles, or devices that comprise a list of elements not only include those elements, but also include other elements not expressly listed or inherent to such processes, methods, articles, or devices. Without more limitations, an element defined by the statement "comprising a" does not exclude the existence of additional identical elements in the process, method, article, or device including the element.

[0362] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The above-described embodiments are only illustrative, for example, the division of the modules is only a logical functional division, and actual implementation can have another division manner, such as: multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0363] The modules described above as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; they can be located in one place or distributed on multiple network units; and part or all of the modules can be selected as needed to achieve the purposes of the embodiments.

[0364] In addition, all the functional modules in the embodiments of the present application can be integrated in one processing unit, or each module can be a separate unit, or two or more modules can be integrated in one unit; the integrated modules can be realized in the form of hardware or in the form of hardware plus software functional units.

[0365] Those skilled in the art can understand that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware, and the aforementioned program can be stored in a computer readable storage medium, and the program executes the steps including the above-mentioned method embodiments when executed; and the aforementioned storage medium includes mobile storage devices, read only memory (ROM), magnetic discs or optical discs and various storage medium that can store program codes.

[0366] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products, and the computer software products are stored in a storage medium, including a number of instructions to make the vehicle device execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes mobile storage devices, ROM, magnetic discs or optical discs and various storage medium that can store program codes.

[0367] The methods disclosed in the several method embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments.

[0368] The features disclosed in the several product embodiments provided by the present application can be combined arbitrarily without conflict to obtain new product embodiments.

[0369] The features disclosed in the several method or device embodiments provided by the present application can be combined arbitrarily without conflict to obtain new method embodiments or device embodiments.

[0370] The above merely provides the implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of the change or replacement within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A method for controlling a vehicle lane change, characterized in that: The method comprises the following steps: In a case where vehicles surrounding the ego vehicle present an obstacle to the ego vehicle's lane change, selecting a target gap from a plurality of candidate gaps based at least on the gap lengths of the candidate gaps and the distance between the ego vehicle and the candidate gaps; wherein the candidate gaps are gaps in a lane adjacent to the ego vehicle's current lane; Based on the target gap, controlling the vehicle to travel in the current lane to a lane-changing position; Controlling the vehicle to change speed at a second acceleration from the lane-changing position to change lanes to the target gap; The controlling the vehicle to travel in the current lane to a lane-changing position based on the target gap includes: Determining a target driving speed required for the vehicle to reach the lane-changing position based on motion information of two vehicles before and after the target gap; Obtaining a first acceleration according to the target driving speed and the current driving speed of the vehicle; The vehicle is controlled to change speed according to the first acceleration so as to travel to a lane-changing position in the current lane.

2. The method according to claim 1, characterized in that The step of selecting a target gap from a plurality of candidate gaps based on the gap lengths of the candidate gaps and the distance between the vehicle and the candidate gaps includes: Determining a score for the candidate gap based on a gap length of the candidate gap and a corresponding first weight and a distance between the vehicle and the candidate gap and a corresponding second weight; wherein the first weight is greater than the second weight; or, the first weight is less than the second weight; A target slot is selected from the plurality of candidate slots based on the scores of the plurality of candidate slots.

3. The method according to claim 1, characterized in that The candidate gaps are obtained by the following method: When there is no vehicle on the side of the vehicle or the vehicle on the side of the vehicle has no intention of overtaking, gaps between the front and rear vehicles on the adjacent lane of the current lane of the vehicle are eliminated if the gap length is outside the first distance range, and the remaining gaps are candidate gaps; The distance between the vehicle directly in front of the vehicle and the vehicle itself is the upper limit of the first distance range, and the distance between the vehicle directly behind the vehicle and the vehicle itself is the lower limit of the first distance range.

4. The method according to claim 1, wherein The controlling the vehicle to change speed at a second acceleration from the lane-changeable position to the target gap includes: Obtaining a second acceleration corresponding to the current lane-changing scenario from accelerations corresponding to a plurality of pre-configured lane-changing scenarios; When a safety condition is satisfied, the vehicle is controlled to change speed according to the second acceleration, thereby changing lanes from the lane-changing position to the target gap; wherein the safety condition includes at least one of the following: The vehicle is in a lane change request phase or a lane change control phase; The accumulated lane changing time from the start of the lane changing to the current moment is less than the first time duration; The vehicle has currently crossed the lane line; The current speed of the vehicle does not exceed a preset speed threshold; The minimum deceleration of the vehicle is greater than a preset deceleration threshold; The minimum deceleration is the minimum deceleration among the decelerations caused by the vehicle avoiding obstacles during driving.

5. The method according to any one of claims 1 to 4, characterized in that The method further comprises: Determining a first safety distance; wherein the first safety distance refers to a collision avoidance distance between the vehicle and vehicles surrounding the vehicle; Based on the first safety distance and the horizontal distance between the vehicle and the vehicles surrounding the vehicle in the travel direction, it is determined that the vehicles surrounding the vehicle pose an obstacle to the lane change of the vehicle.

6. The method according to claim 5, characterized in that The first safety distance includes a collision avoidance distance between the vehicle and the vehicle in front of the adjacent lane of the current lane of the vehicle; the vehicles around the vehicle hindering the lane change of the vehicle include: the vehicle in front of the adjacent lane hindering the lane change of the vehicle; The determining, based on the first safety distance and the horizontal distance between the vehicle and the vehicles surrounding the vehicle in the travel direction, that the vehicles surrounding the vehicle are obstructing the lane change of the vehicle includes: When the first safety distance is greater than the horizontal distance between the own vehicle and the vehicle ahead in the adjacent lane in the traveling direction, it is determined that the vehicle ahead in the adjacent lane presents an obstacle to the lane change of the own vehicle.

7. The method according to claim 5, characterized in that The first safety distance includes a collision avoidance distance between the vehicle and a vehicle behind the vehicle in the adjacent lane of the current lane of the vehicle; the vehicles around the vehicle hindering the lane change of the vehicle include: the vehicle behind the vehicle in the adjacent lane hindering the lane change of the vehicle; The determining, based on the first safety distance and the horizontal distance between the vehicle and the vehicles surrounding the vehicle in the travel direction, that the vehicles surrounding the vehicle are obstructing the lane change of the vehicle includes: When the first safety distance is greater than the absolute value of the sum of the vehicle length of the rear vehicle in the adjacent lane and the horizontal distance between the own vehicle and the rear vehicle in the adjacent lane in the driving direction, it is determined that the rear vehicle in the adjacent lane poses an obstacle to the lane change of the own vehicle.

8. The method according to claim 5, characterized in that The first safety distance includes a collision avoidance distance between the vehicle and the vehicle behind the vehicle in the adjacent lane relative to the current lane of the vehicle; the vehicles around the vehicle hindering the lane change of the vehicle include: the vehicle behind the vehicle in the adjacent lane hindering the lane change of the vehicle; The determining, based on the first safety distance and the horizontal distance between the vehicle and the vehicles surrounding the vehicle in the travel direction, that the vehicles surrounding the vehicle are obstructing the lane change of the vehicle includes: When the first safety distance is greater than the absolute value of the sum of the length of the rear vehicle on the adjacent lane and the horizontal distance between the own vehicle and the rear vehicle on the adjacent lane in the driving direction, and the probability of the rear vehicle on the adjacent lane changing lanes to the adjacent lane of the current driving lane of the own vehicle is greater than the first lane changing probability threshold, and the amount by which the rear vehicle on the adjacent lane presses the lane line of the adjacent lane of the current driving lane of the own vehicle is greater than the first lane pressing amount threshold, it is determined that the rear vehicle on the adjacent lane poses an obstacle to the lane changing of the own vehicle.

9. The method according to claim 5, characterized in that The first safety distance includes a collision avoidance distance between the vehicle and the vehicle in front of the adjacent lane of the current lane of the vehicle; the vehicles around the vehicle hindering the lane change of the vehicle include: the vehicle in front of the adjacent lane hindering the lane change of the vehicle; The determining, based on the first safety distance and the horizontal distance between the vehicle and the vehicles surrounding the vehicle in the travel direction, that the vehicles surrounding the vehicle are obstructing the lane change of the vehicle includes: When the first safety distance is smaller than the horizontal spacing between the own vehicle and the vehicle in front of the adjacent lane in the driving direction, and the probability of the vehicle in front of the adjacent lane changing lanes to the adjacent lane of the current driving lane of the own vehicle is greater than the second lane changing probability threshold, and the amount by which the vehicle in front of the adjacent lane presses the lane line of the adjacent lane of the current driving lane of the own vehicle is greater than the second lane pressing amount threshold, it is determined that the vehicle in front of the adjacent lane poses an obstacle to the lane changing of the own vehicle.

10. The method according to claim 5, characterized in that Determining the first safety distance includes: The first safety distance is determined according to at least one of the following parameters: The safety threshold corresponding to the current driving speed of the vehicle; The time distance between the vehicles around the vehicle and the vehicle; Assume that the distance the vehicle needs to travel to leave the current lane of the vehicle; Assume that the distance traveled by the vehicle after completing the lane change until the vehicle's speed reaches the same speed as the vehicle directly ahead; Assume that the distance traveled by vehicles around the vehicle after the vehicle completes the lane change and changes its speed to the same speed as the vehicle directly in front; Assume the speed of the vehicles around the ego vehicle when they complete the lane change; Assume the distance that the vehicles around the own vehicle need to travel in order to leave the current lane of the vehicles around the own vehicle.

11. The method according to claim 10, characterized in that The method further comprises: Determining a distance the vehicle is assumed to need to travel to leave the current lane based on the current speed of the vehicle, a lane change time assumed to be required for the vehicle to complete the lane change, a lane width of the current lane of the vehicle, and the sampled acceleration; The sampled acceleration is obtained by sampling a preset acceleration range according to a preset sampling step size.

12. The method according to claim 10, characterized in that The method further comprises: Determining a travel distance from the time the ego vehicle completes the lane change until the speed reaches the same speed as the vehicle directly ahead, based on the assumed speed of the ego vehicle at the time the lane change is completed, the target deceleration time, and the target deceleration rate; The target deceleration refers to the deceleration required to achieve the same speed as the vehicle directly in front of the vehicle after the lane change, assuming that the vehicle has completed the lane change. The target deceleration time refers to the time required for the vehicle to decelerate from its current speed to the target speed.

13. The method according to claim 12, characterized in that The method further comprises: The target deceleration time is determined based on the assumed driving speed of the own vehicle when the lane change is completed, the assumed speeds of vehicles surrounding the own vehicle when the lane change is completed, and the target deceleration.

14. The method according to claim 12, characterized in that The method further comprises: The distance traveled by the vehicles surrounding the own vehicle after the assumed lane change is completed until the speed is changed to the same speed as the vehicle directly ahead is determined based on the assumed speed of the vehicles surrounding the own vehicle when the lane change is completed and the target deceleration time.

15. A vehicle lane-changing control device, characterized in that: It includes a judgment and selection module, a first control module and a second control module: The selection module is configured to select a target gap from a plurality of candidate gaps based on at least a gap length of the candidate gap and a distance between the ego vehicle and the candidate gap when a surrounding vehicle obstructs the ego vehicle's lane change; wherein the candidate gap is a gap in a lane adjacent to the ego vehicle's current lane; The first control module is configured to control the ego vehicle to travel in the current driving lane to a lane-changing position based on the target gap; The second control module is configured to control the vehicle to change lanes from the lane-changeable position to the target gap.

16. A vehicle device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein: When the processor executes the program, the method according to any one of claims 1 to 14 is implemented.

17. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor or a vehicle device, the method according to any one of claims 1 to 14 is implemented.

Images