Vehicle lane changing control method, device, equipment, automobile and storage medium

Abstract

Embodiments of the present application provide a vehicle lane changing control method, device, equipment, automobile and storage medium, and relate to the technical field of intelligent driving. The method comprises: obtaining a first space benefit and a second space benefit of a host vehicle in a preset time period; the first space benefit is a benefit obtained by simulating the host vehicle driving in a target lane changing planning trajectory; the target lane changing planning trajectory is a trajectory with the minimum total cost in a lane changing longitudinal planning trajectory in which the host vehicle can change lanes to a target position of a target lane, and the trajectory is determined based on a preset dynamic programming algorithm; the second space benefit is a benefit obtained by simulating the host vehicle driving in a target cruise planning trajectory; determining a lane changing benefit according to the first space benefit and the second space benefit; and controlling the host vehicle to change lanes according to the lane changing benefit. The method is used to improve the accuracy of lane changing decision and improve the passing efficiency of the vehicle in complex scenes such as low speed.

Description

TECHNICAL FIELD

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

[0002] In an automatic driving or an assisted driving system, vehicle lane changing is an important function. The ultimate goal of lane changing control technology is to ensure that a vehicle can safely and efficiently change lanes in a complex and changeable traffic environment.

[0003] In the prior art, common lane changing decisions usually rely on simple rules or algorithms based on fixed parameters, which are only applicable to relatively simple road scenes such as highways, and cannot be applied to complex and changeable urban traffic roads.

[0004] Due to the high irregularity of traffic flow in urban scenes, and the low speed of vehicles, vehicles are frequently started and stopped, especially during peak hours, the traffic flow is extremely large, and the distance between vehicles is small. It is difficult to quickly decide on a correct and safe lane changing scheme based on existing solutions. SUMMARY

[0005] The vehicle lane changing control method, device, equipment, automobile and storage medium provided by the embodiments of the present application can improve the intelligence and adaptability of lane changing decisions, and optimize the lane changing path of the vehicle in different traffic environments.

[0006] In a first aspect, the embodiments of the present application provide a vehicle lane changing control method, which comprises:

[0007] obtaining a first space benefit and a second space benefit of a host vehicle in a preset time period; wherein the first space benefit is a benefit obtained by simulating driving of the host vehicle in a target lane changing planning trajectory, the target lane changing planning trajectory being a trajectory with the minimum total cost in a target lane changing longitudinal planning trajectory in which the host vehicle can change lanes to a target position of a target lane, the target lane changing longitudinal planning trajectory being determined based on a preset dynamic programming algorithm; and the second space benefit is a benefit obtained by simulating driving of the host vehicle in a target cruise planning trajectory, the target cruise planning trajectory being a trajectory with the minimum total cost in a cruise longitudinal planning trajectory in which the host vehicle can cruise to a desired position in a current lane, the target cruise planning trajectory being determined based on the preset dynamic programming algorithm;

[0008] determining a lane changing benefit according to the first space benefit and the second space benefit;

[0009] controlling the host vehicle to change lanes according to the lane changing benefit.

[0010] In a possible implementation, the obtaining of the first space benefit and the second space benefit of the host vehicle in the preset time period comprises:

[0011] acquire data required for the lane-changing decision, wherein the data required for the lane-changing decision comprises at least lane perception information, self-vehicle positioning information, and map navigation information;

[0012] determine a target lane-changing planning trajectory and a target cruising planning trajectory of the self-vehicle within a preset time period according to the data required for the lane-changing decision and the preset dynamic programming algorithm;

[0013] determine a first space gain and a second space gain according to the target lane-changing planning trajectory and the target cruising planning trajectory.

[0014] In a possible implementation, the determining of the target lane-changing planning trajectory and the target cruising planning trajectory of the self-vehicle within a preset time period according to the data required for the lane-changing decision and the preset dynamic programming algorithm comprises:

[0015] determining an obstacle in each lane according to the data required for the lane-changing decision, and determining a long-time predicted trajectory of the obstacle;

[0016] determining the target position and the desired position according to a distribution of the obstacle in each lane;

[0017] generating, by the preset dynamic programming algorithm, a plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position and a plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position based on the self-vehicle positioning information and the long-time predicted trajectory of the obstacle, and calculating a total cost of each of the lane-changing longitudinal planning trajectories and a total cost of each of the cruising longitudinal planning trajectories;

[0018] determining, as the target lane-changing planning trajectory, a lane-changing longitudinal planning trajectory with the minimum total cost among the plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position;

[0019] determining, as the target cruising planning trajectory, a cruising longitudinal planning trajectory with the minimum total cost among the plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position.

[0020] In a possible implementation, the calculating of the total cost of each of the lane-changing longitudinal planning trajectories and the total cost of each of the cruising longitudinal planning trajectories comprises:

[0021] calculating the total cost of the lane-changing longitudinal planning trajectory according to a lane-changing parameter of the lane-changing longitudinal planning trajectory and a preset target function relationship;

[0022] calculating the total cost of the cruising longitudinal planning trajectory according to a cruising parameter of the cruising longitudinal planning trajectory and a preset target function relationship.

[0023] In a possible implementation, the determining the obstacles in each lane and the long-time predicted trajectories of the obstacles according to the data required for the lane-changing decision comprises:

[0024] analyzing and processing the lane perception information in the data required for the lane-changing decision to determine the obstacles in each lane and the short-time predicted trajectories of the obstacles;

[0025] determining the long-time predicted trajectories of the obstacles according to the map navigation information in the data required for the lane-changing decision and the short-time predicted trajectories of the obstacles in each lane.

[0026] In a possible implementation, the determining the first space gain and the second space gain according to the target lane-changing planning trajectory and the target cruise planning trajectory comprises:

[0027] simulating the driving of the ego vehicle according to the target lane-changing planning trajectory to determine the longitudinal displacement of the ego vehicle when the ego vehicle drives to the target position according to the target lane-changing planning trajectory, and the first space gain is determined;

[0028] simulating the driving of the ego vehicle according to the target cruise planning trajectory to determine the longitudinal displacement of the ego vehicle when the ego vehicle drives to the expected position according to the target cruise planning trajectory, and the second space gain is determined.

[0029] In a possible implementation, the determining the lane-changing gain according to the first space gain and the second space gain comprises:

[0030] determining the difference between the first space gain and the second space gain as the lane-changing gain.

[0031] In a possible implementation, the controlling the ego vehicle to change lanes according to the lane-changing gain comprises:

[0032] obtaining a lane-changing triggering threshold;

[0033] if the lane-changing gain is greater than or equal to the lane-changing triggering threshold, generating and executing lane-changing decision information, wherein the lane-changing decision information is used to instruct the ego vehicle to change lanes according to the target lane-changing planning trajectory.

[0034] In a possible implementation, the obtaining the lane-changing triggering threshold comprises:

[0035] obtaining a real-time distance between the ego vehicle and the target lane-changing point;

[0036] determining a lane-changing task of the ego vehicle according to the real-time distance and a first preset correspondence relationship, wherein the first preset correspondence relationship is a correspondence relationship between the real-time distance and the lane-changing task;

[0037] According to the lane-changing task and a second preset correspondence relationship, a lane-changing triggering threshold is determined, wherein the second preset correspondence relationship is a correspondence relationship between the lane-changing task and the lane-changing triggering threshold.

[0038] In a possible implementation, the execution of the lane-changing decision information includes:

[0039] The control unit controls the ego vehicle to turn on a lane-changing steering indicator.

[0040] After the light-on time of the lane-changing steering indicator reaches a preset time length, if it is determined that the ego vehicle meets a preset safety lane-changing requirement, the control unit controls the ego vehicle to perform lane-changing according to the target lane-changing planning trajectory.

[0041] In a possible implementation, after the control unit controls the ego vehicle to turn on the lane-changing steering indicator, before the light-on time of the lane-changing steering indicator reaches the preset time length, the method further includes:

[0042] The steps of obtaining the first space benefit and the second space benefit of the ego vehicle in a preset time period are repeatedly executed, and whether to change the lane-changing decision is determined according to the repeatedly obtained lane-changing benefits.

[0043] In a second aspect, an embodiment of the present application provides a vehicle lane-changing control device, and the device includes:

[0044] A processing unit is configured to obtain a first space benefit and a second space benefit of an ego vehicle in a preset time period, wherein the first space benefit is a benefit obtained by simulating driving of the ego vehicle according to a target lane-changing planning trajectory, the target lane-changing planning trajectory is a trajectory with the minimum total cost in a lane-changing longitudinal planning trajectory of a target position to which the ego vehicle can change lanes, and the target lane-changing planning trajectory is determined based on a preset dynamic programming algorithm; and the second space benefit is a benefit obtained by simulating driving of the ego vehicle according to a target cruise planning trajectory, the target cruise planning trajectory is a trajectory with the minimum total cost in a cruise longitudinal planning trajectory in which the ego vehicle can cruise to a desired position in a current lane, and the target cruise planning trajectory is determined based on a preset dynamic programming algorithm.

[0045] A determination unit is configured to determine a lane-changing benefit according to the first space benefit and the second space benefit.

[0046] A control unit is configured to control the ego vehicle to perform lane-changing according to the lane-changing benefit.

[0047] In a third aspect, an embodiment of the present application provides a vehicle lane-changing control device, and the vehicle lane-changing control device includes a memory and a processor.

[0048] The memory stores computer execution instructions.

[0049] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the first aspect and / or various possible implementation manners of the first aspect.

[0050] In a fourth aspect, an embodiment of the present application provides an automobile, which comprises the vehicle lane-changing control device according to the third aspect.

[0051] In a fifth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the first aspect and / or various possible implementation manners of the first aspect.

[0052] In a sixth aspect, an embodiment of the present application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to implement the first aspect and / or various possible implementation manners of the first aspect.

[0053] The vehicle lane-changing control method, device, equipment, automobile and storage medium provided by the embodiment of the present application, the method comprises: acquiring a first space benefit and a second space benefit of a vehicle in a preset time period; wherein the first space benefit is a benefit obtained by simulating the vehicle driving in a target lane-changing planning trajectory, the target lane-changing planning trajectory is a trajectory with the minimum total cost in a lane-changing longitudinal planning trajectory in which the vehicle can change lanes to a target position of a target lane, which is determined based on a preset dynamic programming algorithm; the second space benefit is a benefit obtained by simulating the vehicle driving in a target cruise planning trajectory, the target cruise planning trajectory is a trajectory with the minimum total cost in a cruise longitudinal planning trajectory in which the vehicle can cruise to a desired position in a current lane, which is determined based on a preset dynamic programming algorithm; determining a lane-changing benefit according to the first space benefit and the second space benefit; and controlling the vehicle to change lanes according to the lane-changing benefit. The embodiment of the present application selects the trajectory with the minimum total cost through the dynamic programming algorithm and the space benefit evaluation, significantly optimizes the path selection and lane-changing decision accuracy, and the vehicle can reach the destination faster and more efficiently, improves the lane-changing decision accuracy, reduces traffic congestion, improves road traffic capacity, can quickly initiate the lane-changing decision to change lanes in a complex traffic environment, and effectively improves the traffic efficiency of the vehicle in a complex low-speed scene. BRIEF DESCRIPTION OF DRAWINGS

[0054] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and serve to explain the principles of the present application together with the specification.

[0055] Figure 1 A flowchart of a vehicle lane-changing control method provided by an embodiment of the present application;

[0056] Figure 2 A distribution diagram of an obstacle provided for an embodiment of the present application;

[0057] Figure 3 A flowchart of another vehicle lane changing control method provided for an embodiment of the present application;

[0058] Figure 4 A schematic diagram of a lane changing scene provided for an embodiment of the present application;

[0059] Figure 5 A schematic diagram of another lane changing scene provided for an embodiment of the present application;

[0060] Figure 6 A structural schematic diagram of a vehicle lane changing control device provided for an embodiment of the present application;

[0061] Figure 7 A structural schematic diagram of a vehicle lane changing control device provided for an embodiment of the present application.

[0062] The specific embodiments of the present application have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and the written description are not intended to restrict the scope of the present application concept in any way, but to illustrate the present application concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0063] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same or similar components. The embodiments described in the following exemplary embodiments do not represent all the implementations consistent with the present application. Instead, they only represent examples of devices and methods consistent with some aspects of the present application, as detailed in the appended claims.

[0064] A highway has a relatively simple and straight linear layout, a relatively large number of fixed lanes, generally 2-4 or even more lanes, and a relatively wide width, providing a relatively spacious driving space for vehicles. The speed of vehicles on the highway is usually 60-120 kilometers per hour, and the distance between vehicles is relatively large, the traffic flow is relatively orderly, and the speed is high and stable. On the highway section, the vehicle can maintain a relatively stable high-speed driving state, and the lane changing demand on the highway is mainly to overtake or adjust to a more suitable lane. Based on this, in the actual scene, the calculation accuracy requirement of the lane changing benefit for the highway scene is relatively low, and only the ego vehicle needs to be controlled to complete the lane changing as required.

[0065] Unlike highways, urban roads present a complex grid-like layout, which usually contains numerous intersections, T-junctions, and various shapes and sizes of block roads, with relatively narrow road widths, limited number of lanes, and frequently changing passable states due to factors such as roadside parking, bus stops, construction areas, etc. Traffic flow on urban roads presents a high degree of irregularity, with vehicle speeds being relatively low, generally in the range of 0-60 km / h, and frequent start-stop situations. Especially during peak hours, traffic flow is extremely large, with small spacing between vehicles, and mixed traffic of different types of vehicles (such as cars, buses, taxis, motorcycles, bicycles, etc.). The main need for lane changing in urban road scenarios is to adjust to a more suitable lane for driving in order to have a better traffic plan.

[0066] Due to the environmental differences between highways and urban roads, vehicles face different difficulties and risks when making lane changing decisions. Existing lane changing decision-making techniques usually rely on simple rules or algorithms based on fixed parameters, which often fail to take into account these two completely different scenarios. Especially in complex low-speed urban scenarios, due to the high complexity and variability of the traffic environment, not only does it increase the difficulty of lane changing control, but it also requires accurate identification of lane changing benefits and accurate control of lane changing opportunities to improve traffic efficiency and driving safety.

[0067] To solve the above technical problems, the embodiments of the present application provide a vehicle lane changing control method. The scheme of the present application generates a lane changing longitudinal planning trajectory of the ego vehicle to the target position of the target lane and a cruising longitudinal planning trajectory of the ego vehicle cruising in the current lane to the desired position through a dynamic programming algorithm, considers the benefits of lane changing and cruising, and controls lane changing based on the determined lane changing benefits. Since the lane changing and cruising situations are considered comprehensively, the lane changing decision determined based thereon is more accurate, which can improve the accuracy and safety of lane changing execution.

[0068] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0069] It should be noted that the execution subject of the vehicle lane changing control method provided by the embodiments of the present application can be a vehicle lane changing control device, which can be deployed in an intelligent driving system of a vehicle. The intelligent driving system is located on a processor or control device of the vehicle, and the embodiments of the present application do not make any limitation. The embodiments of the present application will be described in detail taking the execution subject as the vehicle lane changing control device.

[0070] Figure 1 A flowchart of a vehicle lane changing control method provided by an embodiment of the present application is shown in FIG. 1. As shown in FIG. 1, the vehicle lane changing control method provided by the embodiment of the present application can include the following steps. Figure 1

[0071] S101, obtaining a first space benefit and a second space benefit of a host vehicle in a preset time period.

[0072] The first space benefit is a benefit obtained by simulating the host vehicle driving along a target lane changing planning trajectory, and the target lane changing planning trajectory is a trajectory with the minimum total cost among various lane changing longitudinal planning trajectories determined based on a preset dynamic planning algorithm and in which the host vehicle can change lanes to a target position of a target lane within the preset time period. The second space benefit is a benefit obtained by simulating the host vehicle driving along a target cruise planning trajectory, and the target cruise planning trajectory is a trajectory with the minimum total cost among various cruise longitudinal planning trajectories determined based on the preset dynamic planning algorithm and in which the host vehicle can cruise to a desired position in a current lane within the preset time period.

[0073] For example, the preset time period is a time period required for completing lane changing, and the embodiment of the present application does not limit the specific value of the preset time period, for example, the preset time period can be set to 10s or 15s, etc.

[0074] The first space benefit is a benefit obtained by simulating the host vehicle driving along a target lane changing planning trajectory. Optionally, the first space benefit can be represented by a longitudinal displacement of the host vehicle changing lanes from a current position of a current lane to a target position of a target lane, etc., and the embodiment of the present application does not limit the first space benefit. The target lane changing planning trajectory is a trajectory with the minimum total cost among various lane changing longitudinal planning trajectories determined based on a preset dynamic planning algorithm and in which the host vehicle can change lanes to a target position of a target lane from a current lane within a preset time period.

[0075] The second space benefit is a benefit obtained by simulating the host vehicle driving along a target cruise planning trajectory. Optionally, the second space benefit can be represented by a longitudinal displacement of the host vehicle cruising from a current position of a current lane to a desired position, etc., and the embodiment of the present application does not limit the second space benefit. The target cruise planning trajectory is a trajectory with the minimum total cost among various cruise longitudinal planning trajectories determined based on a preset dynamic planning algorithm and in which the host vehicle can cruise to a desired position in a current lane within a preset time period.

[0076] ​The preset dynamic programming algorithm is an algorithm for optimization problems, and can find an optimal solution in a multi-stage decision-making process by decomposing the problem into smaller sub-problems. In the embodiment of the application, the preset dynamic programming algorithm can generate multiple trajectories of the ego vehicle changing lanes from the current lane to the target position of the target lane, and the lane changing parameters such as speed, acceleration, trajectory of each trajectory are different, and therefore the cost is different. In order to achieve a better lane changing effect, the embodiment of the application selects the trajectory with the minimum cost as the target lane changing planning trajectory. Similarly, the preset dynamic programming algorithm can also generate multiple trajectories of the ego vehicle cruising in the current lane to the desired position. Since the lane changing parameters such as speed and acceleration of each trajectory are different, the cost is different. In order to achieve a better cruising effect, the embodiment of the application selects the trajectory with the minimum cost as the target cruising planning trajectory.

[0077] It should be noted that the total cost refers to the cost required by the ego vehicle during driving, which can be related to driving speed, acceleration, distance, time, energy consumption, safety, comfort, etc., and the embodiment of the application does not limit.

[0078] For example, the first and second space benefits can be calculated by other devices according to the lane changing decision required data, combined with the preset dynamic programming algorithm, and sent to the vehicle lane changing control device of the embodiment of the application; or the vehicle lane changing control device of the embodiment of the application can first select the target lane changing planning trajectory and the target cruising planning trajectory according to the lane changing decision required data combined with the preset dynamic programming algorithm, then simulate the ego vehicle driving along the target lane changing planning trajectory and the target cruising planning trajectory, and then calculate the corresponding space benefits combined with the benefit algorithm; and the like. The space benefits can be obtained in various ways.

[0079] Optionally, in a possible embodiment, obtaining the first and second space benefits of the ego vehicle in the preset time period can include:

[0080] S1, obtaining lane changing decision required data; wherein the lane changing decision required data at least includes lane perception information, ego vehicle positioning information and map navigation information;

[0081] S2, determining the target lane changing planning trajectory and the target cruising planning trajectory of the ego vehicle in the preset time period according to the lane changing decision required data and the preset dynamic programming algorithm;

[0082] S3, determining the first and second space benefits according to the target lane changing planning trajectory and the target cruising planning trajectory.

[0083] Exemplarily, in the embodiments of the present application, the first space benefit and the second space benefit of the ego vehicle in the preset time period are determined to determine the lane-changing benefit, so as to perform vehicle lane-changing control. For this purpose, when the first space benefit and the second space benefit are acquired, the data required for lane-changing decision can be acquired first, and then the target lane-changing planning track and the target cruise planning track of the ego vehicle are determined according to the data required for lane-changing decision and a preset dynamic programming algorithm, and the first space benefit and the second space benefit are determined.

[0084] The data required for lane-changing decision refers to data related to the determination of the lane-changing strategy. In the embodiments of the present application, the data required for lane-changing decision at least includes lane perception information, ego vehicle positioning information and map navigation information.

[0085] The lane perception information mainly includes environment-related information and lane-related information around the ego vehicle on the road traveled by the ego vehicle. The environment-related information includes but is not limited to obstacle information such as vehicles, pedestrians, cones, non-motor vehicles, etc. around the ego vehicle. The obstacles around the vehicle have basic information such as position, speed, acceleration, driving direction relative to the ego vehicle. The lane-related information includes but is not limited to the number, width of the lane, position and type (such as solid line, dashed line, etc.) of the lane line, etc. Optionally, the lane perception information can be acquired by a perception module deployed on the ego vehicle. The perception module can be a vehicle-mounted sensor such as a camera, a radar, etc. The embodiments of the present application do not make any limitation.

[0086] The ego vehicle positioning information can be acquired by a positioning module deployed on the ego vehicle. The positioning module can be implemented based on a global positioning system (GPS) or other positioning technologies. The embodiments of the present application do not make any limitation. The positioning module can be used to acquire accurate position, speed, direction, etc. of the ego vehicle, so as to manage the ego vehicle travel data.

[0087] The map navigation information can be acquired by a map module deployed on the ego vehicle. The map module can include a pre-stored high-precision map. The road shape, lane information, traffic signal information, intersection information, real-time traffic and navigation path information (such as the driving route of the ego vehicle to the destination based on the driving task of the ego vehicle) of the road where the ego vehicle is currently located can be acquired from the high-precision map according to the driving task of the ego vehicle.

[0088] Due to the fact that there are many buildings around urban roads, more greenery, and various traffic facilities (such as traffic lights, street lamp poles, billboards, etc.) blocking the road, in addition, due to the limitations of the perception module's sight distance, the self-vehicle's perception field of view is greatly limited, and there are a large number of blind spots, especially when turning at intersections, entering and exiting parking lots, and passing through narrow streets. Therefore, in order to improve the accuracy of the lane change benefit, the self-vehicle positioning information and map navigation information are also integrated into the lane change benefit calculation in the embodiments of the present application, so as to improve the accuracy of the lane change decision in the urban scenario.

[0089] Exemplarily, after obtaining the data required for the lane change decision, the target lane change planning trajectory and the target cruise planning trajectory of the self-vehicle within the preset time period can be determined based on the data required for the lane change decision and the preset dynamic programming algorithm. For example, a model using the preset dynamic programming algorithm is pre-constructed and trained, the input is the data required for the lane change decision, and the output is the target lane change planning trajectory and the target cruise planning trajectory of the self-vehicle within the preset time period, which is not limited in the embodiments of the present application.

[0090] Optionally, in a possible embodiment, step S2 of determining the target lane change planning trajectory and the target cruise planning trajectory of the self-vehicle within the preset time period according to the data required for the lane change decision and the preset dynamic programming algorithm can include:

[0091] S21, determining the obstacles in each lane according to the data required for the lane change decision, and determining the long-time prediction trajectory of the obstacles;

[0092] S22, determining the target position and the desired position according to the distribution of the obstacles in each lane;

[0093] S23, based on the self-vehicle positioning information and the long-time prediction trajectory of the obstacles, generating, through the preset dynamic programming algorithm, a plurality of lane change longitudinal planning trajectories in which the self-vehicle can change lanes to the target position, and a plurality of cruise longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position, and calculating the total cost of each lane change longitudinal planning trajectory and the total cost of each cruise longitudinal planning trajectory;

[0094] S24, determining the trajectory with the minimum total cost from the plurality of lane change longitudinal planning trajectories in which the self-vehicle can change lanes to the target position as the target lane change planning trajectory;

[0095] S25, determining the trajectory with the minimum total cost from the plurality of cruise longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position as the target cruise planning trajectory.

[0096] Exemplarily, there can be multiple obstacles around the ego vehicle, when the position, driving trajectory and the like of each obstacle are different, the target position that the ego vehicle can change lanes to and the expected position that the ego vehicle can cruise to are different, and correspondingly, the determined planning trajectory is also different. Therefore, it is necessary to first determine the obstacles in each lane according to the data required for the lane change decision, and determine the long-time prediction trajectory of each obstacle, and then determine the planning trajectory.

[0097] Optionally, in a possible embodiment, the step S21 of determining the obstacles in each lane and determining the long-time prediction trajectory of the obstacles according to the data required for the lane change decision can comprise:

[0098] S211, analyzing and processing the lane perception information in the data required for the lane change decision to determine the obstacles in each lane and the short-time prediction trajectory of the obstacles;

[0099] S212, determining the long-time prediction trajectory of the obstacles according to the map navigation information in the data required for the lane change decision and the short-time prediction trajectory of the obstacles in each lane.

[0100] Exemplarily, according to the position of each obstacle in the lane perception information, the obstacles in each lane can be calculated, and according to the basic information such as the position, driving speed, acceleration and driving direction of each obstacle, the short-time prediction trajectory of each obstacle can be determined. It should be noted that the initial data form of the lane perception information obtained by the vehicle-mounted sensor such as the camera and the radar can be image or point cloud data, etc. The initial data can be processed by the existing data processing method to determine the contained obstacles and the basic information, and then the lane attribution calculation is performed on each obstacle. The embodiments of the present application do not limit this, and details are not repeated here.

[0101] Exemplarily, when performing the lane attribution calculation, a Frenet coordinate system can be established, and all obstacles are projected based on the driving reference line, and then the coordinate value of the obstacle in the coordinate system is used to divide the belonging lane. It should be noted that the Frenet coordinate system is a coordinate system for describing curve motion, taking the starting position of the ego vehicle as the origin, the coordinate axes are perpendicular to each other, and are divided into S-axis direction and L-axis direction, and the coordinates are represented as (S, L). The Frenet coordinate system can project the trajectory of the vehicle at a certain moment onto the reference line, and decompose the motion into longitudinal and transverse two dimensions, S represents the longitudinal displacement based on the reference line, and L represents the transverse displacement deviating from the reference line.

[0102] In the embodiment of the present application, all obstacles in the region of interest in the lane of the ego vehicle can be set as a set obstacle{}, combined with obstacle attribution information, traffic facility information obtained from a navigation map and dynamic information, to calculate virtual stop lines of each lane, and to calculate the ranking of obstacles and interference of obstacles in front and behind the lane according to the longitudinal displacement S projected by the driving reference line from large to small. The ranked obstacle set can be recorded as obstacle{obs1, obs2, obs3, obs4…}. Alternatively, obstacles in front and behind the ego vehicle of each lane can also be counted separately, that is, obstacles in front of the current position of the ego vehicle on each lane are counted as one obstacle set, and obstacles behind the current position of the ego vehicle are counted as another obstacle set.

[0103] Exemplarily, Figure 2 A distribution diagram of obstacles is provided for the embodiment of the present application. As shown in the figure, Figure 2 In the left lane of the ego vehicle ego, obstacles obs1 and obs2 in front of the ego vehicle can be grouped into one obstacle set; in the current lane of the ego vehicle ego, obstacle obs3 in front of the ego vehicle can be grouped into another obstacle set.

[0104] It should be noted that the short-time predicted trajectory of the obstacle is obtained by predicting the trajectory of the obstacle in a short time based on a kinematics model or a short-time prediction model. The time range of the short-time prediction is generally within 3s, which can be set according to actual needs, and the embodiment of the present application does not make any limitation. The position, driving speed, acceleration, driving direction and other basic information of each obstacle can be input into the kinematics model or the short-time prediction model for prediction, so as to obtain the short-time predicted trajectory of each obstacle.

[0105] Further, the behavior of the obstacle is analyzed according to the map navigation information and the short-time predicted trajectory of the obstacle in each lane, and the driving intention of the obstacle is considered to determine the long-time predicted trajectory of each obstacle. It can be understood that the long-time predicted trajectory combines the intention prediction technology and can predict the trajectory of the obstacle in a longer time. The time range of the long-time prediction is generally more than 8s, which can be set according to actual needs, and the embodiment of the present application does not make any limitation, for example, it can be set as the time required for lane changing, such as 10s or 15s. The collected map navigation information and the calculated short-time predicted trajectory of the obstacle in each lane can be input into a pre-trained long-time prediction model for prediction, so as to obtain the long-time predicted trajectory of each obstacle.

[0106] It can be understood that the long-time predicted trajectory can provide more comprehensive path planning information, and through the long-time predicted trajectory, more optimal lane changing schemes can be generated, so as to improve the traffic efficiency and driving safety.

[0107] Exemplarily, after determining the obstacles in each lane, the target position and the desired position of each lane can be determined according to the distribution of the obstacles in each lane. The determination of the target position and the desired position should consider safety, traffic rules (such as prohibited lane-changing areas), navigation paths, and driving efficiency, etc. In combination with the above Figure 2 Taking left lane-changing as an example, the target space on the left lane can be initially screened out, which is the position that the ego vehicle can theoretically change lanes to. According to the left lane ownership, three lane-changing target spaces A1, A2, and A3 can be obtained, which are A1{-1, obs1}, A2{obs1, obs2}, and A3{obs2, -2} relative to the ego vehicle from front to back, wherein -1 represents no obstacle in front to limit lane-changing, and -2 represents no obstacle in back to limit lane-changing. Similarly, the ego vehicle can determine the desired position B while cruising on the current lane.

[0108] Further, in combination with the ego vehicle positioning information and the long-time predicted trajectories of the obstacles, through a preset dynamic programming algorithm, multiple lane-changing longitudinal planning trajectories of the ego vehicle changing lanes to the target space can be generated, and the longitudinal empty space pursuit capability of the ego vehicle can be determined, and it is determined in turn whether the ego vehicle can successfully change lanes to the target space within a preset time period based on the generated lane-changing longitudinal planning trajectories. If the determination fails, the next target space is calculated. When the target space is successfully selected, the target position can be determined, and then the target lane-changing planning trajectory can be selected through the total cost of each lane-changing longitudinal planning trajectory. Similarly, in combination with the ego vehicle positioning information and the long-time predicted trajectories of the obstacles, through a preset dynamic programming algorithm, multiple cruising longitudinal planning trajectories of the ego vehicle cruising to the desired position can also be generated, and the target cruising planning trajectory can also be selected through the total cost of each cruising longitudinal planning trajectory.

[0109] Optionally, in a possible embodiment, the calculation of the total cost of each lane-changing longitudinal planning trajectory and the total cost of each cruising longitudinal planning trajectory in step S23 can include:

[0110] S231, the total cost of the lane-changing longitudinal planning trajectory is calculated according to the lane-changing parameter of the lane-changing longitudinal planning trajectory and the preset target function relationship;

[0111] S232, the total cost of the cruising longitudinal planning trajectory is calculated according to the cruising parameter of the cruising longitudinal planning trajectory and the preset target function relationship.

[0112] Exemplarily, each lane-changing longitudinal planning trajectory has its corresponding lane-changing parameter, and each cruising longitudinal planning trajectory also has its corresponding cruising parameter. When the lane-changing parameters and the cruising parameters are different, the total costs corresponding to each lane-changing longitudinal planning trajectory and each cruising longitudinal planning trajectory are also different.

[0113] First, the main state variables involved in the driving process of a vehicle can be defined, including:

[0114] Longitudinal position: It can be represented by the distance of the vehicle in the driving direction relative to a certain fixed reference point (such as the current position of the ego vehicle), with the unit being meters (m). This variable describes the longitudinal position information of the vehicle on the road and is the basis for determining the driving path of the vehicle.

[0115] Speed: It refers to the driving speed of the vehicle, with the unit being meters per second (m / s), which reflects the speed of the vehicle and directly affects the driving time and energy consumption of the vehicle.

[0116] Acceleration: It represents the rate of change of the speed of the vehicle, with the unit being meters per square second (m / s 2 ), which is closely related to the dynamic performance and driving comfort of the vehicle.

[0117] Further, based on the principles of vehicle dynamics, state transition equations can be established to describe how the state of the vehicle changes over time or driving distance. Taking the movement of the vehicle in the longitudinal direction as an example, the state transition equations involved are as follows:

[0118] Regarding position update: where x t is the current position, v t is the current speed, a t is the current acceleration, is the time interval.

[0119] Regarding speed update:

[0120] It can be understood that in the state transition process, the vehicle dynamics constraints should be fully considered, i.e., the acceleration a t needs to meet the physical limitations of the vehicle, a min ≤ a t ≤ a max , where a min and a max are the minimum and maximum accelerations of the vehicle, respectively. At the same time, the constraints of changing lanes to the front and rear vehicles of the target empty should also be considered. If the position of the front vehicle is x front and the speed is v front , the safety distance d s between the vehicle and the front vehicle should meet certain conditions. For example, a simple safety distance model can be used as where d0 is the preset minimum safety distance and T is the preset minimum reaction time. Similarly, the safety distance between the vehicle and the rear vehicle should also meet certain conditions, which are not described here. Any vehicle needs to ensure that the vehicle does not violate the safety distance constraints during the state transition process to ensure driving safety.

[0121] Optionally, in order to reduce the amount of calculation, in the embodiment of the application, when the lane-changing longitudinal planning trajectory and the cruise longitudinal planning trajectory are generated by the preset dynamic programming algorithm, a sampling method of combing in front and combing in back can be adopted. For example, if the preset time period is 10s, when the lane-changing longitudinal planning trajectory is generated by the preset dynamic programming algorithm, the corresponding lane-changing parameters can be configured for the 1st second, the 2nd second, the 3rd second, the 5th second, the 7th second and the 10th second in turn, and the embodiment of the application does not limit this.

[0122] It can be understood that, in the trajectory generation method based on the preset dynamic programming algorithm in the embodiment of the application, since the problem is decomposed into smaller sub-problems at each sampling point to find the optimal solution, the cost related to state transition at each sampling point does not need to be calculated repeatedly, which greatly reduces the data processing amount and improves the data processing efficiency. In addition, in the process of decomposing the problem into smaller sub-problems at each sampling point to find the optimal solution, the planning trajectory that obviously does not meet the preset requirements (such as unable to meet the preset safety distance requirement, unable to meet the speed limit requirement, unable to meet the acceleration limit requirement, etc.) can be eliminated by the way of pruning to reduce the amount of calculation and improve the data processing efficiency, and the embodiment of the application does not limit this, and details are not described herein.

[0123] It can be understood that, in the trajectory generation method based on the preset dynamic programming algorithm in the embodiment of the application, since the problem is decomposed into smaller sub-problems at each sampling point to find the optimal solution, the cost related to state transition at each sampling point does not need to be calculated repeatedly, which greatly reduces the data processing amount and improves the data processing efficiency. In addition, in the process of decomposing the problem into smaller sub-problems at each sampling point to find the optimal solution, the planning trajectory that obviously does not meet the preset requirements (such as unable to meet the preset safety distance requirement, unable to meet the speed limit requirement, unable to meet the acceleration limit requirement, etc.) can be eliminated by the way of pruning to reduce the amount of calculation and improve the data processing efficiency, and the embodiment of the application does not limit this, and details are not described herein.

[0124] For example, the preset target function relationship can be the following formula (1):

[0125] Total cost cost = obstacle distance related cost + speed related cost + acceleration related cost + target longitudinal position related cost (1)

[0126] Wherein, the obstacle distance related cost cost: the difference between the longitudinal position s of the ego vehicle at each sampling point and the longitudinal position s of the front and rear obstacles is calculated first, then the difference between each distance difference and the expected safety distance is calculated, and the square of each difference is calculated respectively, then the sum of the squares is calculated, and finally the sum result is multiplied by the distance weight W_s to obtain the obstacle distance related cost cost.

[0127] The speed related cost cost: the difference between the speed of the ego vehicle at each sampling point and the speed of the previous sampling point is calculated first, then the square of each difference is calculated, then the sum of the squares is calculated, and finally the sum result is multiplied by the speed weight W_v to obtain the speed related cost cost.

[0128] Regarding the acceleration-related cost cost: the square of the acceleration of the ego vehicle at each sampling point of the solution can be calculated first, and then the sum of the squares is calculated, and then the sum is multiplied by the acceleration weight W a, thereby obtaining the acceleration-related cost cost.

[0129] Regarding the target longitudinal position-related cost cost: the difference between the end point (i.e., the corresponding target position or desired position) and the position s of each sampling point can be calculated first, and then the sum of the differences is calculated, and then the sum is multiplied by the position weight W target, thereby obtaining the target longitudinal position-related cost cost.

[0130] According to the lane change parameter of each lane change longitudinal planning trajectory and formula (1), the total cost of each lane change longitudinal planning trajectory can be calculated, and in the embodiments of the present application, the trajectory with the minimum total cost can be selected as the target lane change planning trajectory. Similarly, according to the cruise parameter of each cruise longitudinal planning trajectory and formula (1), the total cost of each cruise longitudinal planning trajectory can also be calculated, thereby selecting the trajectory with the minimum total cost to determine the target cruise planning trajectory.

[0131] The above-mentioned preset target function relationship accurately calculates the longitudinal empty-chasing capability of the ego vehicle, and comprehensively considers the influence of speed, acceleration, and longitudinal displacement on the empty-chasing capability. Based on this, the target lane change planning trajectory and the target cruise planning trajectory determined are more accurate, and the accuracy of subsequent lane change decision is improved.

[0132] Further, according to the target lane change planning trajectory and the target cruise planning trajectory, the first space yield and the second space yield can be determined. Alternatively, in a possible embodiment, step S3, determining the first space yield and the second space yield according to the target lane change planning trajectory and the target cruise planning trajectory, can include:

[0133] S31, simulating the ego vehicle driving along the target lane change planning trajectory, and determining the longitudinal displacement when the ego vehicle drives to the target position along the target lane change planning trajectory as the first space yield;

[0134] S32, simulating the ego vehicle driving along the target cruise planning trajectory, and determining the longitudinal displacement when the ego vehicle drives to the desired position along the target cruise planning trajectory as the second space yield.

[0135] Exemplarily, the computer simulation technology can be used to simulate the driving of the ego vehicle along the target lane change planning trajectory, and then the longitudinal displacement of the ego vehicle from the current position to the target position (the final position after the lane change is completed) along the target lane change planning trajectory can be calculated. The embodiments of the present application can determine that the longitudinal displacement is the first space yield, which can be denoted as Revenue LC, and is used to reflect the forward distance that the ego vehicle can reach on the lane change trajectory within a preset time period.

[0136] Similarly, the computer simulation technology can be used to simulate the situation that the ego vehicle drives along the target lane-changing planning trajectory, and then the longitudinal displacement of the ego vehicle from the current position to the desired position along the target lane-changing planning trajectory can be calculated. The embodiment of the present application can determine the longitudinal displacement as the second space benefit, which can be denoted as Revenue_LK, to reflect the forward distance that the ego vehicle can reach within the preset time period without changing lanes.

[0137] By simulating the driving trajectory of the ego vehicle, the first space benefit and the second space benefit can be quickly and accurately obtained, so that it is more accurate to evaluate which driving strategy is more beneficial to achieve the driving target.

[0138] In summary, by obtaining the data required for the lane-changing decision and combining the preset dynamic planning algorithm, the target lane-changing planning trajectory and the target cruise planning trajectory of the ego vehicle within the preset time period can be determined in a complex traffic environment, and more accurate first space benefit and second space benefit can also be calculated to provide an accurate data basis for subsequent determination of the lane-changing decision, and to improve driving efficiency and safety.

[0139] S102, determine the lane-changing benefit according to the first space benefit and the second space benefit.

[0140] Exemplarily, the lane-changing benefit provides a quantitative index to help evaluate the potential benefits of lane-changing. In the embodiment of the present application, the lane-changing benefit is used to evaluate whether lane-changing can bring additional benefits relative to not changing lanes, so as to determine whether to change lanes.

[0141] Optionally, in a possible embodiment, determining the lane-changing benefit according to the first space benefit and the second space benefit can include: determining the difference between the first space benefit and the second space benefit, and determining the difference as the lane-changing benefit.

[0142] Exemplarily, if the longitudinal displacement of the ego vehicle driving to the target position along the target lane-changing planning trajectory is determined as the first space benefit Revenue_LC, and the longitudinal displacement of the ego vehicle driving to the desired position along the target cruise planning trajectory is determined as the second space benefit Revenue_LK, then the difference between the first space benefit Revenue_LC and the second space benefit Revenue_LK can be calculated, which reflects the additional longitudinal displacement that lane-changing can bring relative to not changing lanes. The embodiment of the present application can determine that the difference is the lane-changing benefit. If the lane-changing benefit is positive, it means that lane-changing can make the vehicle advance further; if it is negative, it means that lane-changing can be less beneficial than keeping the current lane.

[0143] By calculating the difference between the first space benefit and the second space benefit to determine the lane-changing benefit, this intuitive method reduces the complex calculation process, making the decision-making process more concise and efficient.

[0144] S103, controlling the ego vehicle to change lanes according to the lane change benefit.

[0145] Exemplarily, the lane change benefit can be used as a quantitative indicator to quickly determine whether to change lanes. Since the dynamic programming fully considers the longitudinal execution capability of the ego vehicle, the lane change is often more decisive, and further avoids the problem of canceling the lane change after initiating due to changes in the environment caused by long waiting time for lane change, thereby greatly improving the traffic efficiency of the vehicle in urban scenarios.

[0146] Optionally, in a possible embodiment, controlling the ego vehicle to change lanes according to the lane change benefit can include:

[0147] S01, obtaining a lane change trigger threshold;

[0148] S02, if the lane change benefit is greater than or equal to the lane change trigger threshold, generating and executing lane change decision information; wherein the lane change decision information is used to instruct the ego vehicle to change lanes with a target lane change planning trajectory.

[0149] Exemplarily, the lane change trigger threshold is a pre-set value used to determine whether the lane change benefit is high enough to trigger the lane change operation. The lane change trigger threshold can be set according to various factors, such as traffic environment, vehicle performance, driving strategy, driving habit, and passenger preference, etc., which are not limited by the embodiments of the present application. In actual scenarios, the lane change trigger threshold can be dynamic and adjusted according to real-time traffic conditions, weather conditions, or driving modes, etc. For example, in high traffic or adverse weather conditions, the threshold can be increased to reduce the frequency of lane change, thereby improving safety.

[0150] Optionally, in a possible embodiment, step S01, obtaining a lane change trigger threshold, can include:

[0151] S011, obtaining a real-time distance between the ego vehicle and a target lane change point;

[0152] S012, determining a lane change task of the ego vehicle according to the real-time distance and a first preset correspondence relationship; wherein the first preset correspondence relationship is a correspondence relationship between the real-time distance and the lane change task;

[0153] S013, determining the lane change trigger threshold according to the lane change task and a second preset correspondence relationship; wherein the second preset correspondence relationship is a correspondence relationship between the lane change task and the lane change trigger threshold.

[0154] It can be understood that in the process of performing the lane change, there should be a corresponding target lane change point, and before reaching the target lane change point, the vehicle should complete the lane change preparation so as to perform the lane change when reaching the target lane change point. If the lane change preparation cannot be completed before reaching the target lane change point, it is possible that the lane change cannot be completed according to the predetermined lane change trajectory, and therefore different lane change triggering thresholds can be set according to the actual distance between the vehicle and the target lane change point, so as to accurately complete the lane change.

[0155] Specifically, during driving of the vehicle, the vehicle can use vehicle-mounted sensors (such as GPS, lidar, camera, etc.) to monitor the real-time distance between the vehicle and the target lane change point, and then determine the lane change task of the vehicle according to the real-time distance and a first preset corresponding relationship, and determine the lane change triggering threshold according to the lane change task and a second preset corresponding relationship.

[0156] The first preset corresponding relationship is a corresponding relationship between the real-time distance and the lane change task, which is a predefined rule or table for mapping different real-time distances to specific lane change tasks. The second preset corresponding relationship is a corresponding relationship between the lane change task and the lane change triggering threshold, which is also a predefined rule or table for mapping the lane change task to a specific lane change triggering threshold. In the embodiments of the present application, the first preset corresponding relationship and the second preset corresponding relationship can be set according to the driving habits of the user.

[0157] For example, if the road tasks of the left and right lanes are respectively recorded as lane_task_left and lane_task_right, according to the road tendency principle in the driving habits of the user, when the vehicle is a certain distance (such as 200 m) away from the latest lane change point, the user is more inclined to drive to the lane with only a single direction and in line with the navigation direction, for example, if the vehicle needs to go straight, and the front vehicle lane is a straight lane, and the right lane is a straight + right turn lane, the user will tend to drive to the vehicle lane, and at this time, the right lane task lane_task_right+1 of the vehicle can be set. For another example, according to the principle of avoiding driving on the left / right lane in the driving habits of the user, when the vehicle is 200 m away from the latest lane change point, the user will avoid driving on the left / right lane, for example, in a three-lane scene, the vehicle is in the middle lane, and at this time, the left lane task lane_task_left+1 and the right lane task lane_task_right+1 of the vehicle can be set. For another example, according to the principle of changing lanes to the direction of the navigation lane change task in the driving habits of the user, when the distance to the latest lane change point is within 200 m, the user will try to change lanes to the direction of the navigation lane change task, for example, the navigation task points to the right turn in front, and the vehicle is still on the straight lane, and at this time, the right lane task lane_task_right-1 of the vehicle can be set.

[0158] The first preset corresponding relationship is searched according to the real-time distance between the ego vehicle and the target lane-changing point, so as to determine the left lane-changing task and the right lane-changing task of the ego vehicle, and then according to the left lane-changing task and the right lane-changing task of the ego vehicle, the final lane-changing task lane task can be determined, for example, the task with a smaller task value between the left lane-changing task and the right lane-changing task is determined as the final lane-changing task lane task, and the present embodiment is not limited in this way.

[0159] Further, according to the determined lane-changing task, the second preset corresponding relationship is searched, so as to determine the lane-changing trigger threshold. Generally, a larger threshold is required for lane-changing to the lane with the lane-changing task lane task > 0, and only a smaller threshold is required for lane-changing to the lane with the lane-changing task lane task < 0, which can be set according to actual needs, and the present embodiment is not limited in this way.

[0160] By obtaining the real-time distance and using the preset corresponding relationship, the lane-changing trigger threshold can be dynamically adjusted. This method enables the ego vehicle to flexibly respond to different driving conditions and environmental changes, and improves the accuracy and adaptability of the lane-changing decision.

[0161] Exemplarily, after obtaining the lane-changing trigger threshold, the lane-changing benefit is compared with the lane-changing trigger threshold. If the lane-changing benefit is greater than or equal to the lane-changing trigger threshold, it means that the potential benefit of lane-changing is large enough to be worthy of performing the lane-changing operation, and the lane-changing decision information can be generated and executed. If the lane-changing benefit is less than the lane-changing trigger threshold, it means that the potential benefit of lane-changing is not large enough to be worthy of lane-changing.

[0162] By setting the lane-changing trigger threshold and making a lane-changing decision according to the lane-changing benefit, the ego vehicle can make a wise lane-changing selection in a complex traffic environment. This method ensures that the lane-changing operation is not only based on the potential efficiency benefit, but also considers safety and environmental adaptability, and has higher practicability.

[0163] Optionally, in a possible embodiment, the step S02 of executing the lane-changing decision information can include:

[0164] S021, controlling the ego vehicle to turn on a lane-changing steering indicator light;

[0165] S022, after the light-on time of the lane-changing steering indicator light reaches a preset time length, if it is determined that the ego vehicle meets a preset safety lane-changing requirement, the ego vehicle is controlled to perform lane-changing according to the target lane-changing planning track.

[0166] Exemplarily, the execution process of the lane change decision can be managed by a lane change state machine. Understandably, according to traffic rules, the turn signal of the vehicle needs to be turned on before lane changing to send a clear signal to other road users (such as vehicles and pedestrians, etc.) around the vehicle that the vehicle is about to change lanes. In the embodiments of the present application, when executing the lane change decision information, the turn signal of the ego vehicle also needs to be turned on, and the surrounding environment of the ego vehicle is continuously monitored during the lighting time of the turn signal reaching a preset time length (for example, 3s or 5s, etc.) to confirm whether the preset safety lane change requirement is met. If it is determined that the ego vehicle meets the preset safety lane change requirement, the ego vehicle is controlled to change lanes according to the target lane change planning trajectory.

[0167] In the embodiments of the present application, how to determine whether the ego vehicle meets the preset safety lane change requirement is not limited. Understandably, the safety of lane change has been fully considered when planning the lane change trajectory. The judgment of whether the ego vehicle meets the preset safety lane change requirement again is to re-evaluate the risk that may exist in the lane change process. If there is no risk, the lane change is normally executed according to the lane change parameters of the target lane change planning trajectory, and the corresponding steering wheel angle, driving or braking torque, etc. are output to perform trajectory control of the vehicle. If there is a risk, the lane change is cancelled and the vehicle returns to the original lane, so as to further improve the safety of lane change.

[0168] By using the turn signal and waiting for a preset time length, not only the requirements of the traffic regulations on the use of the turn signal are strictly followed to ensure the legality and compliance of the lane change operation, but also the transparency and predictability of the lane change operation are ensured, the risk of collision caused by sudden lane change is reduced, and the overall driving experience and road safety are improved.

[0169] Optionally, in a possible embodiment, after controlling the ego vehicle to turn on the turn signal, the step of obtaining the first space gain and the second space gain of the ego vehicle within a preset time period can also be repeatedly executed before the lighting time of the turn signal reaches the preset time length, and whether to change the lane change decision is determined according to the repeatedly obtained lane change gains.

[0170] Exemplarily, through real-time updated sensor data and environmental information, the lane change gain can be continuously recalculated to control the ego vehicle to dynamically evaluate the potential benefits of lane change according to the latest traffic conditions and vehicle state within the preset time length. If the repeatedly calculated lane change gains show significant changes (for example, from positive to negative or a significant reduction in gain, etc.) within the preset time length, the original lane change decision can be selected to be changed. The change decision can include delaying lane change, selecting a different lane change trajectory, or cancelling the lane change operation, etc. The embodiments of the present application are not limited.

[0171] By continuously monitoring and evaluating within the preset time length, potential safety hazards (such as suddenly appearing obstacles or rapidly approaching vehicles, etc.) can be identified in time, and the lane change plan can be adjusted accordingly, which can further improve the safety of lane change.

[0172] The vehicle lane changing control method provided by the embodiment of the application comprises: acquiring first space benefits and second space benefits of a host vehicle in a preset time period; the first space benefits are benefits obtained by simulating the host vehicle driving in a target lane changing planning trajectory, the target lane changing planning trajectory being a trajectory with minimum total cost in a lane changing longitudinal planning trajectory in which the host vehicle can change lanes to a target position of a target lane and being determined based on a preset dynamic programming algorithm; the second space benefits are benefits obtained by simulating the host vehicle driving in a target cruise planning trajectory, the target cruise planning trajectory being a trajectory with minimum total cost in a cruise longitudinal planning trajectory in which the host vehicle can cruise to a desired position in a current lane and being determined based on the preset dynamic programming algorithm; determining lane changing benefits according to the first space benefits and the second space benefits; and controlling the host vehicle to change lanes according to the lane changing benefits. The embodiment of the application selects a trajectory with minimum total cost through a dynamic programming algorithm and space benefit evaluation, significantly optimizes path selection and lane changing decision accuracy, and enables the vehicle to reach a destination faster and more efficiently, improves the accuracy of lane changing decisions, reduces traffic congestion, improves road traffic capacity, enables the vehicle to quickly initiate lane changing decisions to change lanes in a complex traffic environment, and effectively improves the traffic efficiency of the vehicle in a complex low-speed scene.

[0173] Exemplarily, Figure 3 A flowchart of another vehicle lane changing control method provided by the embodiment of the application is shown.

[0174] As Figure 3 shown, the vehicle lane changing control method provided by the embodiment of the application can comprise:

[0175] S301, acquiring data required for lane changing decisions.

[0176] The data required for lane changing decisions at least comprises lane perception information, host vehicle positioning information, and map navigation information.

[0177] S302, analyzing and processing the lane perception information in the data required for lane changing decisions to determine obstacles in each lane and short-time predicted trajectories of each obstacle.

[0178] S303, determining long-time predicted trajectories of each obstacle according to the map navigation information in the data required for lane changing decisions and the short-time predicted trajectories of the obstacles in each lane.

[0179] S304, determining a target position and a desired position according to the distribution of the obstacles in each lane.

[0180] S305, based on the self-vehicle positioning information and the long-time predicted trajectory of the obstacle, a plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position and a plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position are generated by a preset dynamic programming algorithm.

[0181] S306, the total cost of the lane-changing longitudinal planning trajectory is calculated according to the lane-changing parameter of the lane-changing longitudinal planning trajectory and the preset target function relationship, and the total cost of the cruising longitudinal planning trajectory is calculated according to the cruising parameter of the cruising longitudinal planning trajectory and the preset target function relationship.

[0182] S307, the lane-changing longitudinal planning trajectory with the minimum total cost among the plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position is determined as the target lane-changing planning trajectory, and the lane-changing longitudinal planning trajectory with the minimum total cost among the plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise in the current lane to the desired position is determined as the target cruising planning trajectory.

[0183] S308, the first space gain is determined by simulating the self-vehicle driving in the target lane-changing planning trajectory and determining the longitudinal displacement of the self-vehicle driving in the target lane-changing planning trajectory to the target position, and the second space gain is determined by simulating the self-vehicle driving in the target cruising planning trajectory and determining the longitudinal displacement of the self-vehicle driving in the target cruising planning trajectory to the desired position.

[0184] S309, the difference between the first space gain and the second space gain is determined, and the difference is determined as the lane-changing gain.

[0185] S310, the lane-changing trigger threshold is obtained.

[0186] S311, it is judged whether the lane-changing gain is greater than or equal to the lane-changing trigger threshold.

[0187] If yes, step S312 is executed, and if no, step S301 is executed.

[0188] S312, the self-vehicle is controlled to turn on the lane-changing turn signal.

[0189] S313, after the lighting time of the lane-changing turn signal reaches the preset length of time, it is judged whether the self-vehicle meets the preset safety lane-changing requirement.

[0190] If yes, step S314 is executed, and if no, step S315 is executed.

[0191] S314, the self-vehicle is controlled to change lanes in the target lane-changing planning trajectory.

[0192] S315, the lane change is cancelled.

[0193] It should be noted that the specific implementation of the above steps in this embodiment can refer to the specific description of other embodiments, which will not be repeated here. The process of vehicle lane change control may include some or all of the above steps, and this application embodiment does not impose any limitations.

[0194] The vehicle lane change control method of this application embodiment, compared with schemes that only make decisions based on visual maps and short-term obstacle prediction information, avoids problems such as false lane change initiation or failure to change lanes due to limited perception distance, unreasonable lane changes due to lack of obstacle intent information, and frequent lane change initiation and cancellation due to inaccurate lane change feasibility judgment and lane change benefit calculation. This application embodiment generates long-term predicted trajectories of obstacles based on navigation map information, short-term predicted trajectories of obstacles, and other auxiliary information, fully considering the intent of obstacles. It uses a dynamic programming algorithm to accurately calculate the vehicle's longitudinal tracking capability and the potential lane change benefits after the vehicle initiates a lane change decision. Lane change decisions based on this are often more decisive, avoiding lane change cancellation caused by environmental changes due to long waiting times, and greatly improving vehicle traffic efficiency in urban scenarios.

[0195] For example, Figure 4 This is a schematic diagram of a lane-changing scenario provided in an embodiment of this application. Figure 4 As shown, using the vehicle lane change control method provided in this application embodiment, when it is determined based on the long-term predicted trajectory 20 of the obstacle that the obstacle ahead wants to cut into the vehicle lane, and the left lane is passable, the vehicle ego can calculate the lane change process that can be executed by the vehicle according to the preset dynamic programming algorithm, and generate the lane change longitudinal planning trajectory 10 shown in the figure, which simulates the process of the vehicle ego changing to the left lane just when the obstacle ahead obs cuts into the vehicle lane, thereby obtaining a large lane change benefit, and finally initiating a lane change request to complete an efficient lane change.

[0196] For example, Figure 5 This is a schematic diagram illustrating yet another lane-changing scenario provided in an embodiment of this application. For example... Figure 5As shown, the vehicle lane changing control method provided by the embodiment of the present application can also deal with the scenario of approaching a red-green light intersection. It can be understood that, due to the limited field of view, the perception module of the ego vehicle cannot directly obtain the red light information in front, and if only the obstacle obs1 in front of the ego lane is identified to slow down and stop, and then the lane changing analysis is directly performed according to the speed information of the obstacle obs1 and the information that the left lane is passable, the lane changing result that the left lane changing can greatly improve the traffic efficiency will be obtained. However, according to the vehicle lane changing control method of the embodiment of the present application, the ego vehicle also obtains the map navigation information, and according to the map navigation information, it can be known that the red light stop is needed in front of a certain distance, so the lane changing may not have enough benefits, and it is more reasonable not to change lanes. According to the vehicle lane changing control method provided by the embodiment of the present application, the unreasonable lane changing situation can be avoided, and the accuracy of lane changing execution is improved.

[0197] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0198] Figure 6 A structural schematic diagram of a vehicle lane changing control device provided by an embodiment of the present application is shown in FIG. 6. As shown in the figure, the vehicle lane changing control device 60 provided by the embodiment of the present application includes a processing unit 601, a determination unit 602, and a control unit 603. Figure 6 The vehicle lane changing control device 60 provided by the embodiment of the present application includes a processing unit 601, a determination unit 602, and a control unit 603.

[0199] The processing unit 601 is configured to obtain a first space benefit and a second space benefit of the ego vehicle in a preset time period. The first space benefit is a benefit obtained by simulating the ego vehicle to travel in a target lane changing planning trajectory. The target lane changing planning trajectory is a trajectory with the minimum total cost in a target lane changing longitudinal planning trajectory in which the ego vehicle can change lanes to a target position of a target lane, which is determined based on a preset dynamic programming algorithm. The second space benefit is a benefit obtained by simulating the ego vehicle to travel in a target cruise planning trajectory. The target cruise planning trajectory is a trajectory with the minimum total cost in a cruise longitudinal planning trajectory in which the ego vehicle can cruise to a desired position in a current lane, which is determined based on a preset dynamic programming algorithm.

[0200] The determination unit 602 is configured to determine a lane changing benefit according to the first space benefit and the second space benefit.

[0201] The control unit 603 is configured to control the ego vehicle to change lanes according to the lane changing benefit.

[0202] The device provided by the embodiment of the present application can execute the method provided by the above-mentioned method embodiments, and the implementation principle and technical effects are similar, which will not be described here in detail.

[0203] On the basis of the above-mentioned embodiments, in some possible examples, the processing unit 601 is specifically configured to:

[0204] acquire data required for the lane-changing decision, wherein the data required for the lane-changing decision at least includes lane perception information, self-vehicle positioning information, and map navigation information;

[0205] determine a target lane-changing planning trajectory and a target cruising planning trajectory of the self-vehicle within a preset time period according to the data required for the lane-changing decision and a preset dynamic programming algorithm;

[0206] determine a first space gain and a second space gain according to the target lane-changing planning trajectory and the target cruising planning trajectory.

[0207] On the basis of the above-mentioned embodiments, in some possible examples, the processing unit 601 is specifically configured to:

[0208] determine an obstacle in each lane and a long-time prediction trajectory of the obstacle according to the data required for the lane-changing decision;

[0209] determine a target position and an expected position according to a distribution of the obstacle in each lane;

[0210] generate, based on the self-vehicle positioning information and the long-time prediction trajectory of the obstacle, a plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position and a plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise to the expected position in the current lane, and calculate a total cost of each lane-changing longitudinal planning trajectory and a total cost of each cruising longitudinal planning trajectory by using the preset dynamic programming algorithm;

[0211] determine a lane-changing longitudinal planning trajectory with the minimum total cost from the plurality of lane-changing longitudinal planning trajectories in which the self-vehicle can change lanes to the target position as the target lane-changing planning trajectory;

[0212] determine a cruising longitudinal planning trajectory with the minimum total cost from the plurality of cruising longitudinal planning trajectories in which the self-vehicle can cruise to the expected position in the current lane as the target cruising planning trajectory.

[0213] On the basis of the above-mentioned embodiments, in some possible examples, the processing unit 601 is specifically configured to:

[0214] calculate the total cost of the lane-changing longitudinal planning trajectory according to a lane-changing parameter of the lane-changing longitudinal planning trajectory and a preset target function relationship;

[0215] calculate the total cost of the cruising longitudinal planning trajectory according to a cruising parameter of the cruising longitudinal planning trajectory and a preset target function relationship.

[0216] On the basis of the above-mentioned embodiments, in some possible examples, the processing unit 601 is specifically configured to:

[0217] analyze and process the lane perception information in the data required for the lane-changing decision to determine an obstacle in each lane and a short-time prediction trajectory of the obstacle.

[0218] According to the map navigation information in the data required for the lane change decision and the short-time predicted trajectory of the obstacle in each lane, a long-time predicted trajectory of the obstacle is determined.

[0219] On the basis of the above-mentioned embodiments, in some possible examples, the processing unit 601 is specifically configured to:

[0220] simulate driving of the ego vehicle along the target lane change planning trajectory, and determine a longitudinal displacement of the ego vehicle when driving along the target lane change planning trajectory to the target position, as the first space gain;

[0221] simulate driving of the ego vehicle along the target cruise planning trajectory, and determine a longitudinal displacement of the ego vehicle when driving along the target cruise planning trajectory to the expected position, as the second space gain.

[0222] On the basis of the above-mentioned embodiments, in some possible examples, the determining unit 602 is specifically configured to:

[0223] determine a difference between the first space gain and the second space gain, and determine the difference as the lane change gain.

[0224] On the basis of the above-mentioned embodiments, in some possible examples, the control unit 603 is specifically configured to:

[0225] obtain a lane change triggering threshold;

[0226] if the lane change gain is greater than or equal to the lane change triggering threshold, generate and execute lane change decision information; wherein the lane change decision information is used to instruct the ego vehicle to change lanes along the target lane change planning trajectory.

[0227] On the basis of the above-mentioned embodiments, in some possible examples, the control unit 603 is specifically configured to:

[0228] obtain a real-time distance between the ego vehicle and the target lane change point;

[0229] determine a lane change task of the ego vehicle according to the real-time distance and a first preset correspondence relationship; wherein the first preset correspondence relationship is a correspondence relationship between the real-time distance and the lane change task;

[0230] determine the lane change triggering threshold according to the lane change task and a second preset correspondence relationship; wherein the second preset correspondence relationship is a correspondence relationship between the lane change task and the lane change triggering threshold.

[0231] On the basis of the above-mentioned embodiments, in some possible examples, the control unit 603 is specifically configured to:

[0232] control the ego vehicle to turn on a lane change steering indicator light;

[0233] After the lane change turn indicator light has been on for a preset duration, if it is determined that the vehicle meets the preset safe lane change requirements, the vehicle will be controlled to change lanes according to the target lane change plan trajectory.

[0234] Based on the above embodiments, in some possible examples, the control unit 603 is further specifically used for:

[0235] After the vehicle activates the lane change turn indicator, before the turn indicator light reaches a preset duration, the control processing unit 601 repeatedly executes the steps of acquiring the vehicle's first and second spatial benefits within a preset time period, and determines whether to change the lane change decision based on the repeatedly acquired lane change benefits.

[0236] The apparatus provided in this embodiment can be used to execute the methods of the above embodiments. Its implementation principle and technical effects are similar, and will not be described again here.

[0237] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. These modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented in software via processing element calls, while others are implemented in hardware. Furthermore, they can be stored as program code in the device's memory, and the data processing modules can be called and executed by a specific processing element. The implementation of other modules is similar. These modules can be fully or partially integrated together, or implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. During implementation, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0238] Figure 7 This is a schematic diagram of a vehicle lane change control device provided in an embodiment of this application. Figure 7 As shown, the vehicle lane change control device 70 provided in this embodiment includes at least one processor 701 and a memory 702. Optionally, the device 70 further includes a communication component 703. The processor 701, memory 702, and communication component 703 are connected via a bus 704.

[0239] In a specific implementation, at least one processor 701 executes computer execution instructions stored in memory 702, causing at least one processor 701 to perform the above-described method.

[0240] The specific implementation process of processor 701 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0241] In the above embodiments, it should be understood that the processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or can also be any conventional processor. The steps of the method disclosed in combination with the application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0242] The memory can include a random access memory (RAM), and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0243] The bus can be an industry standard architecture (ISA) bus, a peripheral component (PCI) bus, an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0244] The present application also provides an automobile, which comprises the vehicle lane changing control device as described above.

[0245] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method described above.

[0246] The present application also provides a computer readable storage medium, which stores computer execution instructions, and when a processor executes the computer execution instructions, the method described above is implemented.

[0247] The above-mentioned readable storage medium can be realized by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0248] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0249] The division of units is only a logical functional division, and in actual implementation, there can be another division manner, for example, multiple units or components can be combined or 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 units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0250] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the embodiment.

[0251] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0252] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the method of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0253] It can be understood by those skilled in the art that all or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The aforementioned program can be stored in a computer readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk, and various media that can store program codes.

[0254] Finally, it should be noted that: those skilled in the art will easily think of other embodiments of the present application after considering the specification and practicing the application disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application that follow the general principles of the present application and include common knowledge or conventional technical means in the art that are not disclosed in the present application, and is not limited to the precise structure described above and shown in the drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is only limited by the appended claims.

Claims

1. A vehicle lane change control method, characterized in that, The method includes: The system obtains the first spatial gain and the second spatial gain of the vehicle within a preset time period. The first spatial gain is the gain obtained by simulating the vehicle driving along a target lane change planning trajectory, where the target lane change planning trajectory is the trajectory with the minimum total cost among the longitudinal lane change planning trajectories determined by a preset dynamic programming algorithm, allowing the vehicle to change lanes to the target position in the target lane. The second spatial gain is the gain obtained by simulating the vehicle driving along a target cruise planning trajectory, where the target cruise planning trajectory is the trajectory with the minimum total cost among the longitudinal cruise planning trajectories determined by a preset dynamic programming algorithm, allowing the vehicle to cruise in the current lane to the desired position. Determine the lane change revenue based on the first space revenue and the second space revenue; Based on the lane change benefits, control the vehicle to change lanes.

2. The method according to claim 1, characterized in that, The process of obtaining the vehicle's first spatial gain and second spatial gain within a preset time period includes: Acquire the data required for lane change decision-making; wherein, the data required for lane change decision-making includes at least lane perception information, vehicle positioning information, and map navigation information; Based on the data required for the lane change decision and the preset dynamic programming algorithm, the target lane change planning trajectory and the target cruise planning trajectory of the vehicle within a preset time period are determined. Based on the target lane change planning trajectory and the target cruise planning trajectory, determine the first spatial gain and the second spatial gain.

3. The method according to claim 2, characterized in that, The step of determining the target lane change planning trajectory and target cruise planning trajectory of the vehicle within a preset time period based on the data required for the lane change decision and the preset dynamic programming algorithm includes: Based on the data required for the lane change decision, obstacles in each lane are identified, and the long-term predicted trajectory of the obstacles is determined. The target location and the desired location are determined based on the distribution of obstacles in each lane; Based on the vehicle's positioning information and the long-term predicted trajectory of the obstacle, the preset dynamic programming algorithm generates multiple lane-changing longitudinal planning trajectories that enable the vehicle to change lanes to the target location, and multiple cruise longitudinal planning trajectories that enable the vehicle to cruise in the current lane to the desired location. The total cost of each lane-changing longitudinal planning trajectory and the total cost of each cruise longitudinal planning trajectory are calculated. The trajectory with the minimum total cost among multiple longitudinal lane-change planning trajectories that allow the vehicle to change lanes to the target position is identified as the target lane-change planning trajectory. The trajectory with the minimum total cost among multiple longitudinal cruise planning trajectories that allow the vehicle to cruise to the desired position in the current lane is identified as the target cruise planning trajectory.

4. The method according to claim 3, characterized in that, The calculation of the total cost of each lane change longitudinal planning trajectory and the total cost of each cruise longitudinal planning trajectory includes: The total cost of the lane change longitudinal planning trajectory is calculated based on the lane change parameters and the preset objective function relationship of the lane change longitudinal planning trajectory. The total cost of the longitudinally planned cruise trajectory is calculated based on the cruise parameters and the preset objective function relationship.

5. The method according to claim 3, characterized in that, The step of determining obstacles in each lane based on the data required for the lane change decision, and determining the long-term predicted trajectory of the obstacles, includes: The lane perception information in the data required for the lane change decision is analyzed and processed to determine the obstacles in each lane and the short-term predicted trajectory of the obstacles; Based on the map navigation information and the short-term predicted trajectories of obstacles in each lane from the data required for the lane change decision, the long-term predicted trajectory of the obstacle is determined.

6. The method according to claim 2, characterized in that, The step of determining the first spatial gain and the second spatial gain based on the target lane change planning trajectory and the target cruise planning trajectory includes: Simulate the vehicle traveling along the target lane change planning trajectory, and determine the longitudinal displacement of the vehicle when it reaches the target position along the target lane change planning trajectory, which is the first spatial gain; The simulated vehicle travels along the target cruise planning trajectory, and the longitudinal displacement of the vehicle when it reaches the desired position along the target cruise planning trajectory is determined, which is the second spatial gain.

7. The method according to any one of claims 1-6, characterized in that, The step of determining lane-changing revenue based on the first spatial revenue and the second spatial revenue includes: Determine the difference between the first spatial gain and the second spatial gain, and determine the difference as the lane change gain.

8. The method according to any one of claims 1-6, characterized in that, The step of controlling the vehicle to change lanes based on the lane-changing benefit includes: Get the lane change trigger threshold; If the lane change benefit is greater than or equal to the lane change trigger threshold, then lane change decision information is generated and executed; wherein, the lane change decision information is used to instruct the vehicle to change lanes according to the target lane change planning trajectory.

9. The method according to claim 8, characterized in that, The process of obtaining the lane change trigger threshold includes: Obtain the real-time distance between the vehicle and the target lane change point; Based on the real-time distance and the first preset correspondence, the lane-changing task of the vehicle is determined; wherein, the first preset correspondence is the correspondence between the real-time distance and the lane-changing task; Based on the lane change task and the second preset correspondence, a lane change trigger threshold is determined; wherein, the second preset correspondence is the correspondence between the lane change task and the lane change trigger threshold.

10. The method according to claim 8, characterized in that, The lane change decision information includes: Control the vehicle to activate the lane change turn signal; After the lane change turn indicator light has been illuminated for a preset duration, if it is determined that the vehicle meets the preset safe lane change requirements, the vehicle is controlled to change lanes according to the target lane change planning trajectory.

11. The method according to claim 10, characterized in that, After the vehicle activates its lane change turn signal, before the turn signal's illumination time reaches a preset duration, the method further includes: Repeat the steps of obtaining the first and second spatial benefits of the vehicle within a preset time period, and determine whether to change the lane change decision based on the repeatedly obtained lane change benefits.

12. A vehicle lane change control device, characterized in that, The device includes: The processing unit is configured to obtain a first spatial gain and a second spatial gain for the vehicle within a preset time period; wherein, the first spatial gain is the gain obtained by simulating the vehicle traveling along a target lane change planning trajectory, and the target lane change planning trajectory is the trajectory with the minimum total cost among the longitudinal lane change planning trajectories determined based on a preset dynamic programming algorithm that allows the vehicle to change lanes to the target position in the target lane; the second spatial gain is the gain obtained by simulating the vehicle traveling along a target cruise planning trajectory, and the target cruise planning trajectory is the trajectory with the minimum total cost among the longitudinal cruise planning trajectories determined based on a preset dynamic programming algorithm that allows the vehicle to cruise to the desired position in the current lane. The determining unit is configured to determine the lane change benefit based on the first spatial benefit and the second spatial benefit; The control unit is used to control the vehicle to change lanes based on the lane change benefits.

13. A vehicle lane change control device, characterized in that, The vehicle lane change control device includes: a memory and a processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-11.

14. A car, characterized in that, The vehicle includes the vehicle lane change control device as described in claim 13.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-11.

16. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-11.

Images