Lane changing decision-making method, device, equipment and medium

Abstract

The invention relates to the technical field of automatic driving, in particular to a lane changing decision-making method, device, equipment and medium, and the method comprises the steps: determining a first distance when a vehicle body begins to intrude into a target lane and a second distance when the vehicle body completely intrudes into the target lane, defining a space range of a lane changing process of the vehicle by the two distances, and determining a lane changing decision-making result based on the first distance and the second distance. According to the method, the boundary line of the GAP area is determined, so that the GAP area is determined more accurately, and the lane changing time and the window duration of the GAP area are determined based on the intersection point in a curve graph formed by the ST graph and the boundary line of the GAP area; and calculating the lane changing cost corresponding to each GAP area according to the lane changing time and the window duration corresponding to each GAP area so as to determine a lane changing decision. By comprehensively considering the specific space requirement of lane change of the vehicle and the dynamic environment of the target lane, an accurate space reference is provided for the subsequent determination of the lane change time and the window duration, so that the accuracy and the safety of a lane change decision are improved, and the success rate of lane change is greatly improved.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a lane change decision method, device, equipment and medium. Background Art

[0002] Autonomous driving technology allows cars to perceive and understand the surrounding environment through their own equipment, automatically plan driving routes and perform motion control according to user needs, so as to achieve a safe, comfortable and efficient riding experience. Its basic principle is to integrate multiple sensors (such as lidar, cameras, millimeter-wave radar, etc.), high-performance computing platforms and advanced artificial intelligence algorithms to enable vehicles to drive safely and efficiently without human driver intervention.

[0003] In the scenario of autonomous driving, the mainstream lane change decision in the market is to determine whether the lane change is possible based on the current speed of the target vehicle and the absolute distance and TTC of the vehicle in front of the vehicle in the lane and the vehicles in front and behind the target lane to determine whether the lane change is met. The safety distance set during the lane change process is conservative, which may lead to a low lane change success rate when facing a large number of vehicles.

[0004] Therefore, how to improve the success rate of lane changing has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0005] The purpose of the application is to provide a lane changing decision method, device, equipment and medium that can improve the success rate of lane changing.

[0006] In a first aspect, a lane change decision method is provided, comprising:

[0007] Determine a first distance when the vehicle body begins to intrude into the target lane and a second distance when the vehicle body completely intrude into the target lane;

[0008] Acquire a curve graph, the curve graph comprising: ST graphs corresponding to each of the plurality of target vehicles, boundary lines of the GAP area corresponding to the plurality of target vehicles, and the ST graph of the vehicle; the lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, the plurality of target vehicles comprising: a plurality of first target vehicles in the target lane, and / or a second target vehicle ahead of the vehicle in the lane;

[0009] Determine the lane change time and window duration corresponding to each of the GAP areas according to the intersection points in the curve graph;

[0010] The lane changing cost corresponding to each of the GAP areas is calculated according to the lane changing time and the window duration corresponding to each of the GAP areas, and the lane changing cost is used to determine a lane changing decision.

[0011] In a preferred example, the present application may be further configured as follows: determining the first distance when the vehicle body begins to invade the target lane and the second distance when the vehicle body completely invades the target lane includes:

[0012] Construct the lane-changing trajectory of the ego vehicle;

[0013] The first distance when the vehicle body begins to invade the target lane and the second distance when the vehicle body completely invades the target lane are determined according to the lane change trajectory, the boundary line information of the target lane and the shape information of the vehicle.

[0014] In a preferred example, the present application can be further configured as follows: the acquisition curve graph includes:

[0015] Constructing an ST graph corresponding to each of the plurality of target vehicles and an ST graph corresponding to the self-vehicle;

[0016] Determine a boundary line of a GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to each of the plurality of target vehicles;

[0017] The curve graph is obtained according to the ST graphs corresponding to the plurality of target vehicles, the boundary line of the GAP area, and the ST graph of the vehicle.

[0018] In a preferred example, the present application may be further configured as follows: after determining the boundary line of the GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to the plurality of target vehicles, the present application may further include:

[0019] When there is a second target vehicle in the lane, the invalid GAP areas beyond the lower GAP line corresponding to the second target vehicle are removed from all GAP areas.

[0020] In a preferred example, the present application may be further configured as follows: constructing the ST graphs corresponding to the plurality of target vehicles and the ST graph corresponding to the self-vehicle includes:

[0021] Determine the first acceleration corresponding to each of the plurality of target vehicles within the prediction time by using the IDM model to obtain the ST graph corresponding to each of the plurality of target vehicles;

[0022] The acceleration of the vehicle within the prediction time is determined according to the vehicle speed, the maximum vehicle speed threshold and the minimum vehicle speed threshold, so as to obtain the ST diagram of the vehicle.

[0023] In a preferred example, the present application may be further configured as follows: the intersection points in the curve graph include: a first intersection point between the boundary lines of the GAP region, a second intersection point between the ST graph of the vehicle and the boundary line of the GAP region;

[0024] Correspondingly, determining the lane change time and window duration corresponding to each GAP area according to the intersection points in the curve graph includes:

[0025] Determine, according to the first intersection point, a window end time and a first start time corresponding to each of the GAP areas;

[0026] Determine a second starting point time corresponding to each of the GAP areas according to the second intersection point;

[0027] The maximum value of the first starting time corresponding to each of the GAP areas and the second starting time corresponding to the GAP areas is used as the window start time corresponding to each of the GAP areas;

[0028] The lane change time and window duration corresponding to the GAP area are determined according to the window end time corresponding to each GAP area and the window start time corresponding to each GAP area.

[0029] In a preferred example, the present application may be further configured as follows: determining the window end time and the first start time corresponding to each of the GAP areas according to the first intersection point, including:

[0030] Determine the initial window end time and the first start time corresponding to each of the GAP areas according to the first intersections; wherein, if there is no end intersection corresponding to any of the GAP areas among the first intersections, the end time is used as the initial window end time; if there is no start intersection corresponding to any of the GAP areas among the first intersections, the start time is used as the first start time;

[0031] Determine the time corresponding to the position of the second distance from the initial end position to the origin direction of the upper boundary line of each GAP area as the window end time, wherein the initial end position is the position corresponding to the initial window end time.

[0032] In a preferred example, the present application may be further configured as follows: the lane change cost corresponding to each GAP area is calculated according to the lane change time and window duration corresponding to each GAP area, including:

[0033] According to the window duration and a preset window duration threshold, removing a GAP area whose window duration is not greater than the preset window duration threshold from the plurality of GAP areas;

[0034] The lane changing cost corresponding to each remaining GAP area is determined according to the lane changing time, window duration and preset weight information corresponding to each remaining GAP area.

[0035] In a second aspect, a lane change decision device is provided, comprising:

[0036] A first determination module is used to determine a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane;

[0037] A curve graph acquisition module, used for acquiring a curve graph, the curve graph comprising: ST graphs corresponding to each of a plurality of target vehicles, boundary lines of a GAP area corresponding to a plurality of target vehicles, and an ST graph of the vehicle; a lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, the plurality of target vehicles comprising: a plurality of first target vehicles in a target lane, and / or a second target vehicle ahead of the vehicle in the lane;

[0038] A second determination module, configured to determine a lane change time and a window duration corresponding to each of the GAP areas according to the intersection points in the curve graph;

[0039] The third determination module is used to calculate the lane changing cost corresponding to each of the GAP areas according to the lane changing time and the window duration corresponding to each of the GAP areas, and the lane changing cost is used to determine the lane changing decision.

[0040] In a third aspect, an electronic device is provided, including:

[0041] one or more processors;

[0042] Memory;

[0043] One or more applications, wherein one or more applications are stored in a memory and configured to be executed by one or more processors, and the one or more programs are configured to: perform operations corresponding to the lane change decision method shown in any possible implementation of the first aspect.

[0044] In a fourth aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one instruction, at least one program, a code set or an instruction set, and the at least one instruction, at least one program, a code set or an instruction set is loaded by a processor and executed according to the steps of the lane change decision method shown in any possible implementation method of the first aspect.

[0045] In a fifth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements operations corresponding to the lane change decision method shown in any possible implementation manner in the first aspect.

[0046] In summary, the lane change decision method, device, equipment and medium provided by the present application have at least the following beneficial technical effects:

[0047] When the ego vehicle invades the target lane, it will affect the driving of the vehicles in the target lane. This application determines the first distance when the ego vehicle body begins to invade the target lane and the second distance when it completely invades. The two distances define the spatial range of the ego vehicle's lane changing process. Based on the first distance and the second distance, the boundary line of the GAP area is determined, making the GAP area determination more accurate, and then based on the intersection of the ST diagram and the curve diagram composed of the boundary line of the GAP area, the lane changing time and window duration of the GAP area are determined; according to the lane changing time and window duration corresponding to each GAP area, the lane changing cost corresponding to each GAP area is calculated to determine the lane changing decision. By comprehensively considering the specific spatial requirements of the ego vehicle's lane changing and the dynamic environment of the target lane, an accurate spatial reference is provided for the subsequent determination of the lane changing time and window duration, thereby improving the accuracy and safety of the lane changing decision and greatly improving the success rate of the lane changing. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions of the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0049] Figure 1 A schematic diagram of vehicle conditions in a lane during a lane change process provided by an embodiment of the present application;

[0050] Figure 2 A flowchart of a lane change decision method provided in an embodiment of the present application;

[0051] Figure 3 A schematic diagram of a lane-changing trajectory of a vehicle provided in an embodiment of the present application;

[0052] Figure 4 A schematic diagram of a process for determining a distance provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of an ST diagram of a target vehicle provided in an embodiment of the present application;

[0054] Figure 6 A schematic diagram of a boundary line of a target vehicle provided in an embodiment of the present application;

[0055] Figure 7 A schematic diagram of a curve graph provided in an embodiment of the present application;

[0056] Figure 8 A schematic diagram of a process for determining a lane change time and a window duration provided in an embodiment of the present application;

[0057] Fig. 9 A schematic diagram of another curve graph provided in an embodiment of the present application;

[0058] Fig.10 A schematic diagram of a decision-making solution flow chart provided for an embodiment of the present application;

[0059] Fig.11 A schematic structural diagram of a lane change decision device provided in an embodiment of the present application;

[0060] Fig.12 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application; DETAILED DESCRIPTION

[0061] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make modifications to the present embodiment without any creative contribution as needed, but such modifications are protected by the patent law as long as they are within the scope of the claims of the present application.

[0062] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained with the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information needs to obtain the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0063] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0064] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0065] The existing lane-changing decision scheme does not take into account the impact of the lateral movement of the vehicle before and after crossing the lane on the vehicles in the self-lane and the target lane during the lane-changing process. Therefore, the set safety distance is relatively conservative. The lane-changing success rate is very high when there are few vehicles. However, when there are many vehicles and the space available for lane-changing is relatively narrow, it is difficult to find a lane-changing position because the safety distance is relatively conservative, resulting in a lower lane-changing success rate.

[0066] For vehicles in the target lane for lane change, the future trajectory is predicted based on the rule of uniform speed driving, which is very different from the performance under actual working conditions when the traffic volume is large. When the lane change space is relatively small, lane change failure and cancellation are likely to occur.

[0067] Based on this, an embodiment of the present application provides a lane changing decision method, and the recommendation method relates to fields such as artificial intelligence and autonomous driving.

[0068] In order to better understand and illustrate the solutions of the embodiments of the present application, some technical terms involved in the embodiments of the present application are briefly explained below.

[0069] IDM model (Intelligent Driver Model): The intelligent driver model is a model that describes vehicle following behavior. It calculates the acceleration of the vehicle based on the relative distance and speed between vehicles, thereby simulating the driver's decision-making process in a dynamic traffic environment.

[0070] The reference line is the trajectory line that guides the vehicle on the road. For the condition of keeping straight in the lane, the reference line is the center line of the lane.

[0071] The SL coordinate system, also called the frenet coordinate system, takes the road centerline as a reference, S represents the direction of the road centerline, and L represents the direction perpendicular to the road centerline.

[0072] The DR coordinate system (Dead Reckoning coordinate system) is a coordinate system established based on the principle of dead reckoning. It is used to estimate the position and heading of objects (such as vehicles, aircraft, etc.). For autonomous vehicles, the origin of the coordinate system is the position of the IMU (inertial navigation unit) when the vehicle is powered on. At this time, the direction of the front of the vehicle is the positive direction of the X-axis, the left direction perpendicular to the X-axis in the plane of the vehicle body is the positive direction of the Y-axis, and the upward direction perpendicular to the plane of the vehicle body is the positive direction of the Z-axis.

[0073] Baseline: The trajectory points of the ego vehicle during the lane change process generated in the SL coordinate system.

[0074] ST diagram: Space-Time diagram is a graphical representation method that describes the relationship between the position of an object and time. The horizontal axis represents time, and the vertical axis represents the displacement (or distance, usually expressed in seconds) of the object along a specific direction (such as a planned path). Through this coordinate system, we can intuitively see the position of an object at different time points, as well as the changing trend of the object's position over time.

[0075] In one embodiment, reference Figure 1 , Figure 1 A schematic diagram of the vehicle situation in a lane during a lane change of a self-vehicle provided in an embodiment of the present application, wherein the self-vehicle needs to change lanes from the self-vehicle lane to the target lane.

[0076] The present application embodiment provides a lane change decision method, such as Figure 2 As shown, the method provided in the embodiment of the present application can be executed by an electronic device, and the electronic device is a server. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a vehicle-mounted device, etc., but is not limited to this. The terminal device and the electronic device can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes:

[0077] S101, determining a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane;

[0078] Among them, when the self-vehicle invades the target lane, it will affect the driving of the vehicle in the target lane. In the embodiment of the present application, the first distance is the lateral distance between the position at the starting moment of the lane change and the position when the self-vehicle body begins to invade the target lane, and the second distance is the lateral distance between the position at the starting moment of the lane change and the position when the self-vehicle body completely invades the target lane.

[0079] See also Figure 3 , Figure 3 A schematic diagram of a lane changing trajectory of an ego vehicle is provided in an embodiment of the present application, wherein the schematic diagram of the lane changing trajectory is a trajectory in the SL coordinate system, the position of the ego vehicle between the center line of the lane and the lane boundary line is the position when the ego vehicle body begins to invade the target lane, S1 is the first distance, the position of the ego vehicle between the lane boundary line and the center line of the target lane is the position where the ego vehicle body completely invades the target lane, and S2 is the second distance.

[0080] S102, constructing a curve graph, the curve graph including: ST graphs corresponding to each of the plurality of target vehicles, boundary lines of the GAP area corresponding to the plurality of target vehicles, and the ST graph of the ego vehicle; the lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, and the plurality of target vehicles include: a plurality of first target vehicles in the target lane, and / or a second target vehicle ahead of the ego vehicle in the ego lane;

[0081] In the embodiment of the present application, the curve graph shows the ST graphs corresponding to the multiple target vehicles, the boundary lines of the GAP areas corresponding to the multiple target vehicles, and the ST graph of the vehicle. When there is no vehicle ahead of the vehicle in the lane, the multiple target vehicles include: multiple first target vehicles in the target lane; when there is a vehicle ahead of the vehicle in the lane, the multiple target vehicles include: multiple first target vehicles in the target lane and a second target vehicle ahead of the vehicle in the lane.

[0082] When constructing the GAP areas corresponding to multiple target vehicles, the lower boundary line of the boundary line of the GAP area is calculated according to the set formula using the first distance and the second distance, and the actual impact of the intrusion of the own vehicle on the target lane is considered, making the final decision more accurate.

[0083] In the embodiment of the present application, the ST diagram of the vehicle includes a curve of the acceleration process and a curve of the deceleration process.

[0084] S103, determining the lane change time and window duration corresponding to each GAP area according to the intersection points in the curve graph;

[0085] The intersection points in the curve graph include: the first intersection point between the boundary lines of the GAP area, the second intersection point between the ST graph of the vehicle and the boundary line of the GAP area; furthermore, the lane changing time and window duration corresponding to the GAP area can be analyzed through the intersection points. The lane changing time includes the window end time and the window start time, and the window duration is the duration between the window end time and the window start time. The GAP area is the area between the boundary lines of two adjacent target vehicles. For example, if there is only the first target vehicle, the GAP area is the area between the boundary lines of the two adjacent first target vehicles; if there is a first target vehicle and a second target vehicle, the GAP area is the area between the boundary lines of the front and rear target vehicles, refer to Figure 1 The GAP area includes: the GAP area between vehicle 1 and vehicle 3, the GAP area between vehicle 2 and vehicle 3, the GAP area between vehicle 3 and vehicle 4, and the GAP area between vehicle 4 and vehicle 5.

[0086] S104. Calculate the lane changing cost corresponding to each GAP area according to the lane changing time and window duration corresponding to each GAP area. The lane changing cost is used to determine the lane changing decision.

[0087] According to the lane changing time and window length corresponding to each GAP area, the lane changing cost corresponding to each GAP area is calculated, and then the lane changing start time corresponding to the lane changing gap corresponding to the minimum lane changing cost is selected to generate the lane changing strategy.

[0088] In the embodiment of the present application, the lane changing decision includes but is not limited to: acceleration, deceleration, and lane changing time.

[0089] It can be seen that in the embodiment of the present application, only when the self-vehicle invades the target lane will it affect the driving of the vehicles in the target lane. The present application determines the first distance when the self-vehicle body begins to invade the target lane and the second distance when it completely invades. The two distances define the spatial range of the self-vehicle lane changing process. Based on the first distance and the second distance, the boundary line of the GAP area is determined, so that the GAP area is determined more accurately, and then based on the intersection of the ST diagram and the curve diagram composed of the boundary line of the GAP area, the lane changing time and window duration of the GAP area are determined; according to the lane changing time and window duration corresponding to each GAP area, the lane changing cost corresponding to each GAP area is calculated to determine the lane changing decision. By comprehensively considering the specific spatial requirements of the self-vehicle lane changing and the dynamic environment of the target lane, an accurate spatial reference is provided for the subsequent determination of the lane changing time and window duration, thereby improving the accuracy and safety of the lane changing decision and greatly improving the success rate of the lane changing.

[0090] A possible implementation method of the embodiment of the present application is as follows: Figure 4 As shown, S101 determines a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane, including: S1011, S1012, wherein:

[0091] S1011, constructing a lane-changing trajectory of the vehicle;

[0092] In an achievable manner, S1011 includes: obtaining a lateral state of the ego vehicle when the lane change is initiated in an SL coordinate system, wherein the SL coordinate system has the center line of the target lane as an S axis, and the direction from the center line of the target lane to the center line of the ego lane as an L axis, and the S coordinate of the ego vehicle when the lane change is initiated is 0, and the lateral state includes: lateral position, lateral velocity, and lateral acceleration;

[0093] Determining a lane change time parameter corresponding to the lateral speed from a preset correspondence relationship between the vehicle speed and the lane change time parameter according to the lateral speed when the lane change is initiated;

[0094] Determine the lateral position at the end of the lane change according to the lateral speed at the time of initiating the lane change and the lane change time parameter corresponding to the lateral speed, so as to obtain the lateral state at the end of the lane change;

[0095] The lane-changing trajectory of the ego vehicle is constructed based on the lateral state when the lane change is initiated and the lateral state when the lane change is completed.

[0096] In the embodiment of the present application, in the DR coordinate system, the lateral state of the vehicle at the time of lane change initiation in the SL coordinate system is calculated according to the motion posture of the vehicle relative to the reference line when the lane change is initiated. . According to the lateral speed when the lane change is initiated, the lane change time parameter corresponding to the lateral speed when the lane change is initiated is determined from the corresponding relationship between the preset vehicle speed and the lane change time parameter, wherein the lane change time parameter is related to the vehicle speed, and the greater the vehicle speed, the shorter the time; the lateral speed when the lane change is initiated and the lane change time parameter corresponding to the lateral speed are multiplied to obtain the lateral position at the end of the lane change, so as to obtain the corresponding lateral state at the end of the lane change, wherein at the end of the lane change, the vehicle is located on the reference line of the target lane, that is, the center line, the lateral position at the end of the lane change represents the lateral distance of the lane change, the corresponding lateral speed at the end of the lane change is 0, and the corresponding lateral acceleration at the end of the lane change is 0.

[0097] Furthermore, the quintic polynomial is: ;

[0098] According to the lateral state when the lane change is initiated ,get:

[0099]

[0100] ;

[0101] ;

[0102] According to the lateral state when the lane change is initiated ,get:

[0103] ;

[0104] ;

[0105] .

[0106] Through the above calculation, we can get , a lane-changing trajectory of a quintic polynomial is obtained, and this trajectory is used as the BaseLine of the lane-changing process. The embodiment of the present application proposes a method of obtaining a lane-changing trajectory that fits the desired characteristics through a solver by first designing a desired lane-changing trajectory, namely the BaseLine, based on a quintic polynomial, and using this as a reference line for the lane-changing trajectory solution process. This method can obtain the desired lane-changing trajectory with a small amount of parameter adjustment.

[0107] S1012: Determine a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane according to the lane change trajectory, the boundary line information of the target lane and the shape information of the vehicle.

[0108] In the embodiment of the present application, based on the lane change trajectory BaseLine and the boundary line information of the target lane (including but not limited to the lane width) and combined with the shape information of the vehicle, the first distance traveled by the vehicle body when it invades the target lane relative to the starting point of the lane change while the vehicle is driving along the lane change trajectory can be calculated, as well as the second distance traveled by the vehicle body relative to the starting point when it completely enters the target lane.

[0109] It can be seen that the embodiment of the present application first constructs a lane changing trajectory BaseLine to estimate the distance of the key position points of the vehicle during the lane changing process. The lane changing trajectory BaseLine can also be used for subsequent planning and generation of lane changing trajectories to more conveniently adjust the lane changing trajectory characteristics.

[0110] A possible implementation method of the embodiment of the present application, S102 obtains a curve graph, including: constructing an ST graph corresponding to each of the multiple target vehicles and an ST graph corresponding to the own vehicle; determining a boundary line of a GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to each of the multiple target vehicles; and obtaining a curve graph according to the ST graphs corresponding to each of the multiple target vehicles, the boundary line of the GAP area, and the ST graph of the own vehicle.

[0111] It can be seen that in the embodiment of the present application, in the process of constructing the curve graph, ST graphs of multiple target vehicles and the ego vehicle are first constructed respectively, providing the position and speed information of each vehicle changing over time; based on the spatial range of the ego vehicle's lane changing, combined with the ST graph of the target vehicle, the GAP area boundary line between every two adjacent target vehicles is determined, which not only takes into account the relative positions between the target vehicles, but also incorporates the actual needs of the ego vehicle's lane changing, so that the definition of the GAP area is more in line with the actual lane changing scenario.

[0112] Among them, constructing the ST graphs corresponding to multiple target vehicles and the ST graph corresponding to the self-vehicle includes:

[0113] Determine the first acceleration corresponding to each of the multiple target vehicles within the prediction time by using the IDM model, so as to obtain the ST graph corresponding to each of the multiple target vehicles;

[0114] According to the vehicle speed, the maximum vehicle speed threshold and the minimum vehicle speed threshold of the own vehicle, the acceleration of the own vehicle within the prediction time is determined to obtain the ST diagram of the own vehicle.

[0115] In the embodiment of the present application, the IDM model is used to predict the vehicle trajectory of the target vehicle, that is, the vehicle trajectory of the first target lane and / or the vehicle trajectory of the second target vehicle in the lane. The IDM model is used to predict the vehicle position under heavy traffic conditions, which improves the accuracy of the prediction relative to the uniform speed prediction, and also improves the accuracy of the prediction of the lane change feasible GAP, which is important in the lane change process.

[0116] The mathematical description of the IDM model is as follows: the acceleration of the target vehicle:

[0117] ;

[0118] in, is the maximum acceleration of the target vehicle, is the current speed of the target vehicle, is the expected speed of the target vehicle, is the acceleration index, which can be a calibration value. is the speed difference between the target vehicle and the preceding vehicle, is the distance between the current target vehicle and the preceding vehicle, is the expected following distance;

[0119] The expected vehicle distance can be calculated using the following formula:

[0120] ;

[0121] in, is the comfortable deceleration, T is the preset safety time, For safe time interval, The minimum vehicle distance.

[0122] Then, when preparing to change lanes, the first target vehicle in the target lane ~ (Subscript 1 is the first target vehicle in the front), where n can be set by the user according to actual needs. It should be noted that the relevant information of the nth first target vehicle can be collected by the vehicle. For the first first target vehicle, its target expected speed is the average speed of the target within the target tracking time, where the target tracking time can be set according to actual needs; for the first target vehicle behind ~ , set the first target speed , The calculation method is to find the closest speed limit value among multiple preset speeds according to the average speed of the target vehicle selected in the target lane. The multiple speeds can be set by the user according to actual needs. Exemplary multiple speeds include: {60km / h, 80km / h, 100km / h, 110km / h, 120km / h}. Then, the information of the first target vehicle and the first target vehicle is substituted into the IDM model to calculate the first target vehicle. The predicted acceleration of the first target vehicle under the IDM model is then calculated ~ The predicted acceleration of each vehicle. Based on the IDM model, the target vehicle in the adjacent lane is deduced from front to back, and the trajectory of each vehicle in a certain period of time under dynamic traffic flow is predicted to solve the problem of inaccurate prediction of the future trajectory of the vehicle using the uniform speed solution.

[0123] For the second target vehicle in front of the lane According to the average speed of the second target vehicle, the closest speed limit is found among the preset multiple speeds. Multiple speeds can be set by the user according to actual needs. Exemplary multiple speeds include: {60km / h, 80km / h, 100km / h, 110km / h, 120km / h}, which are set as the expected speed, and then the acceleration is calculated by the IDM model. For the first target vehicle and the second target vehicle, the preset multiple speeds can be the same or not completely the same, and the user can adjust them according to the actual situation.

[0124] After obtaining the predicted acceleration of all current target vehicles, the predicted acceleration of all target vehicles in the next cycle is derived according to the sampling period, and the predicted speed and position of the first target vehicle selected in the target lane and / or the second target vehicle in the self-lane within the prediction time are obtained, until the data corresponding to each of the multiple sampling points within the preset time are obtained, and the ST diagram is constructed. Exemplarily, the prediction time can be set to 8s, 10s or 12s or other values, and the sampling period can be 0.1s, 0.2s or 0.3s, etc.

[0125] The S value of the vehicle at the lane change start time 0 is 0. Figure 5 , Figure 5 A schematic diagram of an ST diagram of a target vehicle provided in an embodiment of the present application, wherein predict_time is the end time, and the target vehicles include: the first target vehicle in the target lane , and the second target car in the ego lane (obstacle_ego_f), which is just an example.

[0126] The ST diagram of the vehicle during lane change is further explained.

[0127] Among them, the maximum acceleration and deceleration accelerations for finding the lane changing gap during the lane changing process are set as follows: and , where the maximum acceleration and deceleration acceleration can be set according to the user's habits or actual needs; the maximum speed threshold is a preset multiple of the current road speed limit set , where the preset multiple is no longer limited in the embodiment of the present application, and the user can set it according to actual needs, for example, 1.08 times; the minimum speed threshold (current speed - preset speed value) and the maximum value of the minimum lane change speed allowed are set to The preset vehicle speed value can be set by the user according to actual needs, for example, 20km / h. The acceleration deduction formula of the vehicle during acceleration and deceleration is:

[0128] The acceleration of the vehicle during acceleration: ;

[0129] The vehicle acceleration during deceleration: ;

[0130] The acceleration of the vehicle is calculated according to the acceleration deduction formula of the vehicle. The position and speed information of the vehicle within the prediction time can be obtained according to the preset period, and the ST diagram of the vehicle can be generated.

[0131] It can be understood that the embodiments of the present application no longer limit the generation order of the first ST diagrams corresponding to each of the multiple first target vehicles, the second ST diagrams corresponding to each of the multiple second target vehicles, and the ST diagram of the own vehicle.

[0132] It can be seen that in the embodiment of the present application, when constructing the ST diagrams of the target vehicle and the ego vehicle, the IDM model is used to predict the acceleration of the target vehicle; for the ego vehicle, the acceleration within the prediction time is determined according to its current vehicle speed, the maximum vehicle speed threshold and the minimum vehicle speed threshold, ensuring that the speed change during the lane changing process is within a reasonable range; the constructed ST diagram has improved adaptability to complex traffic environments, making the lane changing process smoother and safer.

[0133] Further, according to the first distance, the second distance, and the ST graphs corresponding to the plurality of target vehicles, the boundary line of the GAP area formed between each two adjacent target vehicles is determined. In the embodiment of the present application, it is assumed that when changing lanes, the vehicle speed of the vehicle is quickly kept the same as that of the vehicle in front, and then the lane is changed. Under this condition, the safety distance is set. The safety distance when the lane change is allowed can be calculated according to the following formula:

[0134] ,

[0135] ,

[0136] in, is the safe vehicle distance corresponding to the upper boundary line of the GAP area, is the safe vehicle distance corresponding to the lower boundary line of the GAP area, is the minimum vehicle distance, T is the preset safety time, is the target vehicle’s ego speed, The speed of the vehicle behind the target vehicle, S2 is the second distance, S1 is the first distance, is the maximum acceleration of the target vehicle, Deceleration for comfort.

[0137] According to the above formula, the upper and lower safety boundaries of the GAP area formed by every two target vehicles can be drawn on the original target ST map.

[0138] In an achievable manner, after determining the boundary line of the GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to the plurality of target vehicles, the method further includes:

[0139] When there is a second target vehicle in the lane, the invalid GAP area beyond the lower GAP line corresponding to the second target vehicle is removed from all GAP areas.

[0140] Reference Figure 6 , Figure 6 A schematic diagram of a boundary line of a target vehicle provided in an embodiment of the present application.

[0141] Among them, when there is no second target vehicle obstacle_ego_f, the lower GAP line of obstacle1 and the upper GAP line of obstacle2 form a GAP area. When there is a second target vehicle obstacle_ego_f, the lower GAP line of obstacle1 and the upper GAP line of obstacle2 form a GAP area, and the lower GAP line of obstacle_ego_f and the upper GAP line of obstacle2 form a GAP area. However, because it is impossible to overtake the front vehicle, the target generates a safety boundary upper limit, which is the upper limit of the GAP area of ​​all target lanes. The GAP area of ​​lane change that exceeds this upper limit is an invalid GAP area, that is, the lower GAP line of obstacle1 and the upper GAP line of obstacle2 form an invalid GAP area.

[0142] Among them, if there is no second target vehicle, the GAP area includes: the GAP area formed by the lower GAP line of obstacle1 (the upper boundary line of the GAP area) and the upper GAP line of obstacle2 (the lower boundary line of the GAP area), the GAP area formed by the lower GAP line of obstacle2 and the upper GAP line of obstacle3, and the GAP area formed by the lower GAP line of obstacle3 and the upper GAP line of obstacle4.

[0143] If there is a second target vehicle obstacle_ego_f, because it cannot overtake the front vehicle, the second target vehicle generates a safety boundary upper limit, which is the upper limit of all target lane GAP areas. The GAP areas of lane changes exceeding this upper limit are invalid GAP areas. , then start_t_12 is and The starting point of the GAP area between When and No effective GAP area can be formed between them, but and An effective GAP area can be formed between them.

[0144] Furthermore, refer to Figure 7 , Figure 7 A schematic diagram of a curve graph provided for an embodiment of the present application, wherein Ego_acc and Ego_dec are ST graphs of the ego vehicle, which are merely examples given for a situation where there is no obstacle in front of the ego lane, and there may also be a corresponding curve for a second target vehicle in the ego lane.

[0145] In a possible implementation of the embodiment of the present application, the intersection points in the curve graph include: a first intersection point between the boundary lines of the GAP region, and a second intersection point between the ST graph of the vehicle and the boundary line of the GAP region;

[0146] Accordingly, refer to Figure 8 S103 determines the lane change time and window duration corresponding to each GAP area according to the intersection points in the curve graph, including: S1031-S1034, wherein:

[0147] S1031, determining the window end time and the first start time corresponding to each GAP area according to the first intersection point;

[0148] Specifically, based on the first intersection, the initial window end time and the first starting time corresponding to each GAP area are determined; wherein, if there is no end intersection corresponding to any GAP area in the first intersection, the end time is used as the initial window end time, and if there is no starting intersection corresponding to any GAP area in the first intersection, the start time is used as the first starting time; determine the time corresponding to the position on the upper boundary line of each GAP area that is the second distance from the initial end position in the direction of the origin as the window end time, wherein the initial end position is the position corresponding to the initial window end time.

[0149] In the embodiment of the present application, the window end point and start time are determined according to the first intersection of the upper and lower boundaries of the GAP area. If there is no intersection of the start time, the first start time is considered to be the start time 0. If there is no intersection of the end time, the end time is considered to be the window end time, recorded as and .based on Find the time corresponding to the second distance from the current point (the distance from the starting point of the lane change after the vehicle completely enters the target lane) along the upper boundary line of the GAP toward the origin, and record the time of the change as the actual end point of the lane change window .

[0150] S1032, determining a second starting point time corresponding to each GAP area according to the second intersection point;

[0151] For the case of ego vehicle acceleration, find the second intersection point where the ego vehicle acceleration trajectory first exceeds the GAP safety lower line and record it as ; For the case of the vehicle decelerating, find the second intersection point where the vehicle deceleration trajectory first falls below the GAP safety upper line and record it as ; If no point that meets the conditions is found, then Set as the window end time, The corresponding time is the second starting time.

[0152] For example, refer to Fig. 9 The second starting time of the gap formed by obstacle1 and obstacle2 is start_t_12, the second starting time of the gap formed by obstacle2 and obstacle3 is start_t_23, and the second starting time of the gap formed by obstacle3 and obstacle4 is start_t_34.

[0153] S1033, taking the maximum value of the first starting time corresponding to each GAP area and the second starting time corresponding to each GAP area as the window start time corresponding to each GAP area;

[0154] Window start time .

[0155] S1034. Determine the lane change time and window duration corresponding to each GAP area according to the window end time corresponding to each GAP area and the window start time corresponding to each GAP area.

[0156] It can be seen that in the embodiment of the present application, the first intersection is used to determine the window end time and the first starting time of the GAP area, ensuring that the end and possible start time of the lane change window are based on the spatial relationship between the actual target vehicles; considering the matching between the actual lane changing demand of the vehicle and the GAP area, the second intersection is used to determine the second starting time; by comparing the first starting time and the second starting time, the maximum value is selected as the window start time, ensuring that the opening of the lane change window not only meets the lane changing conditions of the vehicle, but also takes into account the dynamic changes of surrounding vehicles, so that the lane changing time and window duration corresponding to each GAP area are more accurate and reasonable.

[0157] A possible implementation of the embodiment of the present application is to calculate the lane change cost corresponding to each GAP area according to the lane change time and window duration corresponding to each GAP area, including:

[0158] According to the window duration and the preset window duration threshold, removing the GAP area whose window duration is not greater than the preset window duration threshold from the multiple GAP areas;

[0159] The lane changing cost corresponding to each remaining GAP area is determined according to the lane changing time, window duration and preset weight information corresponding to each remaining GAP area.

[0160] In an embodiment of the present application, when the window length is relatively small, it means that the stability of the GAP area is low and the implementation is difficult. Therefore, based on the window length and the preset window length threshold, the GAP area whose window length is not greater than the preset window length threshold is removed from multiple GAP areas.

[0161] The lane changing cost is calculated according to the lane changing time and window duration, and the lane changing decision is made. The cost function is used to screen the advantages and disadvantages of GAP, and an interface is reserved for the subsequent introduction of machine learning optimization weights.

[0162] Among them, the cost function of GAP is constructed:

[0163] ;

[0164] Where W1 is the weight of the lane change starting time, and W2 is the weight of the inverse of the lane change window time.

[0165] ;

[0166] ;

[0167] Calculate the GAP area of ​​each GAP area according to the cost function and cost value. >Preset window duration threshold The GAP area with the smallest cost is found in the GAP of the ego vehicle as the target GAP area; if there is no feasible GAP, the ego vehicle maintains the original longitudinal decision, otherwise, according to the optimal feasible GAP search method, it is determined whether the ego vehicle accelerates or decelerates, wherein the preset window duration threshold is the set minimum duration parameter.

[0168] Furthermore, an interface can be reserved for the subsequent introduction of machine learning optimization weights, and the weights can be continuously optimized to obtain the optimal solution.

[0169] It can be seen that in the embodiment of the present application, based on the window length and the preset window length threshold, the GAP areas whose window length is not greater than the preset window length threshold are removed from multiple GAP areas, and those GAP areas whose window length is too short and unsuitable for lane changing are removed, so that the options that do not meet the actual lane changing conditions are filtered out, thereby reducing the complexity of subsequent calculations; for the remaining GAP areas, the lane changing cost is determined in combination with their lane changing time, window length and preset weight information.

[0170] Based on any of the above embodiments, refer to Fig.10 , the decision-making process provided by the embodiment of the present application includes:

[0171] 1. Calculate BaseLine;

[0172] 2. Calculate the position and distance of the intrusion point during the lane change process;

[0173] 3. Use the IDM model to predict the trajectory of the vehicle in the target lane of the lane change;

[0174] 4. Generate the ST graph of the target of interest;

[0175] 5. Calculate the end point of the lane change window;

[0176] 6. Deducing the ST diagram of the lane change process of the vehicle;

[0177] 7. Calculate the time point and window duration for lane change on the ST diagram;

[0178] 8. Calculate the cost based on the lane changing time and window duration and make a lane changing decision.

[0179] In the embodiment of the present application, a lane-changing BaseLine is first constructed for estimating the distance of the key position points of the vehicle during the lane-changing process. At the same time, the subsequent planning of lane-changing trajectories based on the BaseLine can more conveniently adjust the characteristics of the lane-changing trajectories. The IDM model is used to predict the position of vehicles under conditions of heavy traffic, which improves the accuracy of the prediction compared to the uniform speed prediction, and also improves the accuracy of the prediction of the important lane-changing feasible GAP during the lane-changing process. A cost function is constructed to screen the pros and cons of the GAP, and an interface is reserved for the subsequent introduction of machine learning to optimize weights.

[0180] The embodiment of the present application provides a specific lane change decision method. In the lane change scenario, there is no preceding vehicle in the self-lane, and there is a first target vehicle in the target lane in a front-to-back order. ~ , the lane-changing decision method includes:

[0181] When receiving the lane change signal, construct the lane change trajectory of the ego vehicle Ego;

[0182] Determine a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane according to the lane change trajectory, the boundary line information of the target lane and the shape information of the vehicle;

[0183] Draw ST diagrams corresponding to multiple target vehicles and ST diagrams corresponding to the ego vehicle;

[0184] Determine a boundary line of a GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to each of the plurality of target vehicles;

[0185] According to the ST graphs corresponding to the multiple target vehicles, the boundary lines of the GAP area, and the ST graph of the vehicle, a curve graph is obtained; see Figure 7 ;

[0186] According to the intersection points in the curve graph, the lane change time and window length corresponding to each GAP area are determined;

[0187] According to the lane changing time and window duration corresponding to each GAP area, the lane changing cost corresponding to each GAP area is calculated, and the lane changing cost is used to determine the lane changing decision.

[0188] A lane changing decision device provided in an embodiment of the present application is introduced below. The lane changing decision device described below and the method described above can be referred to each other. The lane changing decision device of this embodiment is set in an electronic device. Fig.11 , Fig.11 : is a structural block diagram of a lane change decision device according to one embodiment of the present application, comprising:

[0189] A first determination module 210, for determining a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane;

[0190] The curve graph acquisition module 220 is used to acquire a curve graph, the curve graph including: ST graphs corresponding to each of the plurality of target vehicles, boundary lines of the GAP area corresponding to the plurality of target vehicles, and the ST graph of the vehicle; the lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, and the plurality of target vehicles include: a plurality of first target vehicles in the target lane, and / or a second target vehicle ahead of the vehicle in the lane;

[0191] A second determination module 230 is used to determine the lane change time and window duration corresponding to each GAP area according to the intersection points in the curve graph;

[0192] The third determination module 240 is used to calculate the lane changing cost corresponding to each GAP area according to the lane changing time and window duration corresponding to each GAP area, and the lane changing cost is used to determine the lane changing decision.

[0193] In an implementable manner, the first determining module 210 is specifically configured to:

[0194] Construct the lane-changing trajectory of the ego vehicle;

[0195] According to the lane-changing trajectory, the boundary line information of the target lane and the shape information of the own vehicle, a first distance when the own vehicle body begins to invade the target lane and a second distance when the own vehicle body completely invades the target lane are determined.

[0196] In one achievable manner, the curve graph acquisition module 220 is specifically configured to:

[0197] Construct ST graphs corresponding to multiple target vehicles and ST graphs corresponding to the ego vehicle;

[0198] Determine a boundary line of a GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to each of the plurality of target vehicles;

[0199] A curve graph is obtained based on the ST graphs corresponding to the multiple target vehicles, the boundary line of the GAP area, and the ST graph of the vehicle.

[0200] In one achievable manner, the construction module 220 is further configured to:

[0201] When there is a second target vehicle in the lane, the invalid GAP area beyond the lower GAP line corresponding to the second target vehicle is removed from all GAP areas.

[0202] In one achievable manner, the construction module 220 is specifically configured to:

[0203] Determine the first acceleration corresponding to each of the multiple target vehicles within the prediction time by using the IDM model, so as to obtain the ST graph corresponding to each of the multiple target vehicles;

[0204] According to the vehicle speed, the maximum vehicle speed threshold and the minimum vehicle speed threshold of the own vehicle, the acceleration of the own vehicle within the prediction time is determined to obtain the ST diagram of the own vehicle.

[0205] In one achievable manner, the intersection points in the curve graph include: a first intersection point between the boundary lines of the GAP region, and a second intersection point between the ST graph of the vehicle and the boundary line of the GAP region;

[0206] Accordingly, the second determining module 230 is specifically configured to:

[0207] According to the first intersection point, determine the window end time and the first starting time corresponding to each GAP area;

[0208] Determine the second starting point time corresponding to each GAP area according to the second intersection point;

[0209] The maximum value of the first starting time corresponding to each GAP area and the second starting time corresponding to each GAP area is used as the window start time corresponding to each GAP area;

[0210] The lane change time and window duration corresponding to each GAP area are determined according to the window end time corresponding to each GAP area and the window start time corresponding to each GAP area.

[0211] In an implementable manner, the second determining module 230 is specifically configured to:

[0212] According to the first intersection, determine the initial window end time and the first starting time corresponding to each GAP area; wherein, if there is no end intersection corresponding to any GAP area among the first intersections, the end time is used as the initial window end time; if there is no start intersection corresponding to any GAP area among the first intersections, the start time is used as the first starting time;

[0213] Determine the time corresponding to the position of the upper boundary line of each GAP area that is the second distance from the initial end position in the direction of the origin as the window end time, wherein the initial end position is the position corresponding to the initial window end time.

[0214] In an implementable manner, the third determining module 240 is specifically configured to:

[0215] According to the window duration and the preset window duration threshold, removing the GAP area whose window duration is not greater than the preset window duration threshold from the multiple GAP areas;

[0216] The lane changing cost corresponding to each remaining GAP area is determined according to the lane changing time, window duration and preset weight information corresponding to each remaining GAP area.

[0217] An electronic device is provided in an embodiment of the present application, such as Fig.12 As shown, Fig.12 The electronic device 300 shown includes: a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, such as through a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in actual applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0218] The processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 301 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0219] The bus 302 may include a path to transmit information between the above components. The bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig.12 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0220] The memory 303 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0221] The memory 303 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the contents shown in the above method embodiment.

[0222] Fig.12 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0223] An embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding content in the aforementioned method embodiment.

[0224] An embodiment of the present application provides a computer program product, including a computer program, which implements the corresponding contents of the aforementioned method embodiment when the computer program is executed by a processor.

[0225] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0226] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A lane-changing decision method, characterized in that: include: Determine a first distance when the vehicle body begins to intrude into the target lane and a second distance when the vehicle body completely intrude into the target lane; Acquire a curve graph, the curve graph comprising: ST graphs corresponding to each of the plurality of target vehicles, boundary lines of the GAP area corresponding to the plurality of target vehicles, and the ST graph of the vehicle; the lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, the plurality of target vehicles comprising: a plurality of first target vehicles in the target lane, and / or a second target vehicle ahead of the vehicle in the lane; Determine the lane change time and window duration corresponding to each of the GAP areas according to the intersection points in the curve graph; The lane changing cost corresponding to each of the GAP areas is calculated according to the lane changing time and the window duration corresponding to each of the GAP areas, and the lane changing cost is used to determine a lane changing decision.

2. The method according to claim 1, characterized in that The determining of the first distance when the vehicle body begins to invade the target lane and the second distance when the vehicle body completely invades the target lane includes: Construct the lane-changing trajectory of the ego vehicle; The first distance when the vehicle body begins to invade the target lane and the second distance when the vehicle body completely invades the target lane are determined according to the lane change trajectory, the boundary line information of the target lane and the shape information of the vehicle.

3. The method according to claim 1, characterized in that The obtaining curve graph comprises: Constructing an ST graph corresponding to each of the plurality of target vehicles and an ST graph corresponding to the self-vehicle; Determine a boundary line of a GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to each of the plurality of target vehicles; The curve graph is obtained according to the ST graphs corresponding to the plurality of target vehicles, the boundary line of the GAP area, and the ST graph of the vehicle.

4. The method according to claim 3, characterized in that After determining the boundary line of the GAP area formed between every two adjacent target vehicles according to the first distance, the second distance, and the ST graphs corresponding to the plurality of target vehicles, the method further includes: When there is a second target vehicle in the lane, the invalid GAP areas exceeding the lower GAP line corresponding to the second target vehicle are removed from all GAP areas.

5. The method according to claim 3, characterized in that: The step of constructing the ST graphs corresponding to the plurality of target vehicles and the ST graph corresponding to the vehicle includes: Determine the first acceleration corresponding to each of the plurality of target vehicles within the prediction time by using the IDM model to obtain the ST graph corresponding to each of the plurality of target vehicles; The acceleration of the vehicle within the prediction time is determined according to the vehicle speed, the maximum vehicle speed threshold and the minimum vehicle speed threshold, so as to obtain the ST diagram of the vehicle.

6. The method according to claim 1, characterized in that The intersection points in the curve graph include: a first intersection point between the boundary lines of the GAP region, and a second intersection point between the ST graph of the vehicle and the boundary line of the GAP region; Correspondingly, determining the lane change time and window duration corresponding to each GAP area according to the intersection points in the curve graph includes: Determine, according to the first intersection point, a window end time and a first start time corresponding to each of the GAP areas; Determine a second starting point time corresponding to each of the GAP areas according to the second intersection point; The maximum value of the first starting time corresponding to each of the GAP areas and the second starting time corresponding to the GAP areas is used as the window start time corresponding to each of the GAP areas; The lane change time and window duration corresponding to the GAP area are determined according to the window end time corresponding to each GAP area and the window start time corresponding to each GAP area.

7. The method according to claim 6, characterized in that The step of determining the window end time and the first start time corresponding to each of the GAP areas according to the first intersection point includes: Determine the initial window end time and the first start time corresponding to each of the GAP areas according to the first intersections; wherein, if there is no end intersection corresponding to any of the GAP areas among the first intersections, the end time is used as the initial window end time; if there is no start intersection corresponding to any of the GAP areas among the first intersections, the start time is used as the first start time; Determine the time corresponding to the position of the second distance from the initial end position to the origin direction of the upper boundary line of each GAP area as the window end time, wherein the initial end position is the position corresponding to the initial window end time.

8. The method according to any one of claims 1 to 7, characterized in that: Calculating the lane changing cost corresponding to each GAP area according to the lane changing time and the window duration corresponding to each GAP area includes: According to the window duration and a preset window duration threshold, removing a GAP area whose window duration is not greater than the preset window duration threshold from the plurality of GAP areas; The lane changing cost corresponding to each remaining GAP area is determined according to the lane changing time, window duration and preset weight information corresponding to each remaining GAP area.

9. A lane-changing decision device, characterized in that: include: A first determination module is used to determine a first distance when the vehicle body begins to invade the target lane and a second distance when the vehicle body completely invades the target lane; A curve graph acquisition module, used for acquiring a curve graph, the curve graph comprising: ST graphs corresponding to each of a plurality of target vehicles, boundary lines of a GAP area corresponding to a plurality of target vehicles, and an ST graph of the vehicle; a lower boundary line of the boundary line of the GAP area is determined according to the first distance and the second distance, the plurality of target vehicles comprising: a plurality of first target vehicles in a target lane, and / or a second target vehicle ahead of the vehicle in the lane; A second determination module, configured to determine a lane change time and a window duration corresponding to each of the GAP areas according to the intersection points in the curve graph; The third determination module is used to calculate the lane changing cost corresponding to each of the GAP areas according to the lane changing time and the window duration corresponding to each of the GAP areas, and the lane changing cost is used to determine the lane changing decision.

10. An electronic device, characterized in that: include: one or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, and the one or more applications are configured to: perform the steps of the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The storage medium stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded by the processor and executes the steps of the method according to any one of claims 1 to 8.

Images