Vehicle lane changing control method, device and equipment, medium and vehicle

Abstract

The invention discloses a vehicle lane changing control method and device, equipment, a medium and a vehicle, and the method comprises the steps: obtaining a target scene feature under the condition that a second vehicle located in front of a first vehicle is detected to have a lane changing behavior, and according to the target scene feature, determining the lane changing behavior of the first vehicle; target human driving experience information matched with the lane changing scene where the second vehicle is located is determined, a lane changing decision result is generated according to the target human driving experience information, and lane changing control over the first vehicle is executed according to the lane changing decision result. The experience of autonomous lane changing control of the vehicle can be improved, and the probability of invalid lane changing of the vehicle is reduced.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a vehicle lane change control method, device, equipment, medium and vehicle. Background Art

[0002] Advanced Driver Assistance Systems (ADAS) refers to a series of vehicle systems designed to improve driving safety, reduce driver burden and enhance the overall driving experience. Assisted driving systems use on-board sensors, cameras, radars, LiDAR and other sensor devices to obtain information about the vehicle's surroundings and take appropriate measures to assist the driver in better controlling the vehicle.

[0003] Autonomous Lane Change is a basic function in assisted driving. Autonomous lane change means that with the support of the assisted driving system, the vehicle can complete the lane change process without the intervention of the driver. In related technologies, the L2+ assisted driving function NOA (Navigation on Highway Assist) can realize autonomous lane change under certain road conditions.

[0004] Although current assisted driving technology can enable vehicles to change lanes autonomously, it is limited by the system's intelligence level, and the autonomous lane change control experience of existing vehicles is poor, which can easily lead to a bad experience of ineffective lane changes. Summary of the invention

[0005] The present application aims to propose a vehicle lane change control method, device, equipment, medium and vehicle, which can improve the experience of vehicle autonomous lane change control and reduce the probability of invalid lane changes.

[0006] In a first aspect, an embodiment of the present application provides a method for controlling a vehicle lane change, comprising the following steps:

[0007] When a second vehicle located in front of a first vehicle is detected to have changed lanes, a target scene feature is acquired, wherein the second vehicle is a vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate a lane change scene in which the second vehicle is located;

[0008] Determining target human driving experience information matching the lane change scenario of the second vehicle according to the target scenario characteristics, wherein the target human driving experience information is used to describe the target human driving experience that conforms to a preset driving logic;

[0009] generating a lane change decision result according to the target person's driving experience information, wherein the lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction when the lane change has occurred, based on the target person's driving experience;

[0010] Execute lane change control of the first vehicle according to the lane change decision result.

[0011] According to some embodiments of the present application, the acquiring target scene features includes:

[0012] Acquire scene recognition information associated with the first vehicle and the second vehicle, the scene recognition information including at least one of traffic rule information and map information;

[0013] The target scene features are determined according to the scene cognition information.

[0014] According to some embodiments of the present application, the second vehicle is a target type vehicle, and the scene recognition information includes traffic rule information for describing a lane change rule for the target type vehicle;

[0015] The determining the target scene feature according to the scene recognition information includes:

[0016] When the speed of the second vehicle during the lane change process is lower than the speed of the first vehicle, acquiring lane information of the lane in which the second vehicle was located before the lane change;

[0017] According to the lane information and the traffic rule information, a lane-changing scene feature is determined, and the target scene feature includes the lane-changing scene feature.

[0018] According to some embodiments of the present application, the second vehicle is a cargo vehicle;

[0019] The performing lane change control of the first vehicle according to the lane change decision result includes:

[0020] In the lane-changing scenario, when the cargo vehicle is located in the rightmost lane of the road before changing lanes, according to the lane-changing decision result, preventing the first vehicle from changing lanes to the lane before the cargo vehicle changes lanes; or

[0021] In the lane-changing scenario, when the cargo vehicle is not located in the rightmost lane of the road before changing lanes, the vehicle is controlled to change lanes to the lane before the cargo vehicle changed lanes according to the lane-changing decision result.

[0022] According to some embodiments of the present application, the acquiring scene recognition information associated with the first vehicle and the second vehicle includes:

[0023] When it is detected that the second vehicle changes lanes multiple times in a row toward a target direction, acquiring map information associated with the first vehicle and the second vehicle;

[0024] The determining the target scene feature according to the scene recognition information includes:

[0025] In a case where it is determined based on the map information that the lane change behavior of the second vehicle is to enter a ramp on the road side corresponding to the target direction, a down-ramp lane change scene is determined, wherein the target scene feature includes the down-ramp lane change scene,

[0026] The lane change decision result is used to instruct the first vehicle to change lanes in a direction opposite to the target direction based on the target human driving experience.

[0027] According to some embodiments of the present application, determining, based on the target scene feature, target human driving experience information that matches the lane change scene in which the second vehicle is located, includes:

[0028] Inputting the target scene feature into a preset driving experience database to obtain human driving experience information that has a corresponding relationship with the target scene feature in the driving experience database, wherein the driving experience database is a database including the corresponding relationship between different scene features and human driving experience information;

[0029] When the human driving experience information having a corresponding relationship with the target scene feature is obtained in the driving experience database, the obtained human driving experience information is determined as the target human driving experience information.

[0030] In a second aspect, an embodiment of the present application provides a vehicle lane change control device, comprising:

[0031] A scene feature acquisition module, configured to acquire a target scene feature when a second vehicle located in front of a first vehicle is detected to have changed lanes, wherein the second vehicle is a vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate a lane change scene in which the second vehicle is located;

[0032] A driving experience determination module, used to determine target human driving experience information that matches the lane change scenario in which the second vehicle is located according to the target scenario characteristics, wherein the target human driving experience information is used to describe the target human driving experience that conforms to a preset driving logic;

[0033] a lane change decision generating module, used to generate a lane change decision result according to the target person's driving experience information, wherein the lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction in the case of a lane change according to the target person's driving experience;

[0034] A lane change control execution module is used to execute lane change control of the first vehicle according to the lane change decision result.

[0035] In a third aspect, an embodiment of the present application provides an electronic device, the device comprising: a processor and a memory storing computer program instructions;

[0036] When the processor executes the computer program instructions, the vehicle lane changing control method as described in the first aspect is implemented.

[0037] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon, and when the computer program instructions are executed by a processor, the vehicle lane change control method as described in the first aspect is implemented.

[0038] In a fifth aspect, an embodiment of the present application provides a vehicle, which performs lane change control by the vehicle lane change control method as described in the first aspect.

[0039] The vehicle lane change control method, device, equipment, medium and vehicle of the embodiments of the present application have at least the following beneficial effects:

[0040] The present application firstly obtains the target scene feature when detecting that the second vehicle located in front of the first vehicle changes lanes; then determines the target person driving experience information matching the lane change scene of the second vehicle according to the target scene feature; then generates a lane change decision result according to the target person driving experience information; and finally executes the lane change control of the first vehicle according to the lane change decision result. The present application can improve the experience of the vehicle's autonomous lane change control and reduce the probability of invalid lane changes.

[0041] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present application is further described below with reference to the accompanying drawings and embodiments, wherein:

[0043] Figure 1 A schematic flow chart of an embodiment of a vehicle lane change control method provided by the present application;

[0044] Figure 2A schematic diagram of a first lane-changing scenario in a vehicle lane-changing control method;

[0045] Figure 3 is a schematic diagram of a second lane-changing scenario in a vehicle lane-changing control method;

[0046] Figure 4 A schematic diagram of a lane-changing scenario on an off-ramp in a vehicle lane-changing control method;

[0047] Figure 5 A schematic diagram of the structure of an embodiment of a vehicle lane change control device provided by the present application;

[0048] Figure 6 A schematic diagram of the structure of the electronic device provided in this application. DETAILED DESCRIPTION

[0049] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0050] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0051] In order to solve the problems of the prior art, the embodiments of the present application provide a vehicle lane change control method, device, equipment, medium and vehicle. The vehicle lane change control method provided by the embodiments of the present application is first introduced below.

[0052] Figure 1 A schematic flow chart of a vehicle lane change control method provided in an embodiment of the present application is shown. The method is applied to electronic equipment.

[0053] like Figure 1 As shown, the above-mentioned vehicle lane change control method includes the following steps:

[0054] S101, when a second vehicle located in front of a first vehicle is detected to have changed lanes, acquiring a target scene feature, wherein the second vehicle is a vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate a lane change scene in which the second vehicle is located;

[0055] S102, determining target person driving experience information that matches the lane change scenario in which the second vehicle is located according to the target scene characteristics, where the target person driving experience information is used to describe the target person driving experience that conforms to a preset driving logic;

[0056] S103, generating a lane change decision result according to the target person's driving experience information, where the lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction when the lane change has occurred, based on the target person's driving experience;

[0057] S104. Execute lane change control of the first vehicle according to the lane change decision result.

[0058] In this embodiment, when a second vehicle located in front of a first vehicle is detected to have changed lanes, the target scene feature is obtained; then, according to the target scene feature, the target person driving experience information matching the lane change scene of the second vehicle is determined; then, according to the target person driving experience information, a lane change decision result is generated; finally, according to the lane change decision result, the lane change control of the first vehicle is executed. This application can improve the experience of the vehicle's autonomous lane change control and reduce the probability of invalid lane changes.

[0059] In the above step S101, when it is detected that a second vehicle located in front of a first vehicle changes lanes, a target scene feature is acquired, wherein the second vehicle is a vehicle that changes lanes in front of the first vehicle, and the target scene feature is used to indicate the lane change scene in which the second vehicle is located.

[0060] The above-mentioned first vehicle refers to this vehicle, which is a vehicle equipped with an assisted driving system and can change lanes autonomously, and the second vehicle refers to other vehicles that change lanes in front of this vehicle.

[0061] The above-mentioned detection of the lane change behavior of the second vehicle located in front of the first vehicle refers to the surrounding environment information of the vehicle obtained by the vehicle through one or more of the front-view camera, side-view camera, lidar, millimeter-wave radar and other vehicle-mounted sensors. The surrounding environment information includes but is not limited to lane information, and vehicle information of lanes such as the own lane, adjacent lane, and adjacent lane. It also includes the vehicle's target type, target position, lateral and longitudinal speeds, lateral and longitudinal accelerations, collision time (Time To Collision-TTC), etc. This information can be directly obtained through the sensor or calculated based on the sensor data. The movement trajectory of nearby vehicles is then predicted based on this information, and whether lane change behaviors such as cutting in and out occur are predicted based on the movement trajectory.

[0062] As an example, an implementation method of lane change behavior prediction is introduced below, which is as follows:

[0063] First, the sensor is used to obtain the characteristics of the target vehicle, such as the initial distance, speed, and acceleration of the lane line. The target vehicle is any vehicle near the vehicle.

[0064] The above features are detected once every cycle;

[0065] The trajectory prediction method is used to calculate the motion trajectory of the target vehicle. The trajectory prediction method can use a Kalman filter algorithm or other trajectory prediction algorithms;

[0066] The lane change behavior of cutting in and out is determined by the relationship between the predicted motion trajectory and the lane line, such as the TTC and angle relationship with the lane line.

[0067] The following introduces a target trajectory calculation method to predict the trajectory of the target vehicle. The specific calculation process is as follows:

[0068] First, the target position and lateral and longitudinal speeds of nearby vehicles are obtained through on-board sensors;

[0069] Then according to the kinematic calculation formula, we can get:

[0070] At time T0, X0 = [Px0 Py0 Vx0 Vy0];

[0071] At time T1, X1 = [Px1 Py1 Vx1 Vy1];

[0072] At time T2, X2 = [Px2 Py2 Vx2 Vy2];

[0073] …

[0074] Furthermore, according to the kinematic calculation formula, we can get:

[0075] Xn=[Px(n-1)+Vx(n-1)*Δt Py(n-1)+Vy(n-1)*Δt Vx(n-1)Vy(n-1)]+[1 / 2ax(Δt) 2

[0076] 1 / 2ay(Δt) 2 ax*(Δt)ay*(Δt)].

[0077] Among them, X0 represents the position and speed variables of the vehicle at time T0, the lateral position relative to the vehicle coordinate system is Px0, the longitudinal position is Py0, the lateral speed is Vx0, and the longitudinal speed is Vy0; the same applies to X1 and X2; Xn represents the position and speed of the vehicle at time Tn, Px(n-1) is the lateral position of the vehicle at time T(n-1), ax is the lateral acceleration of the vehicle, ay is the longitudinal acceleration of the vehicle, and Δt is the system operation period.

[0078] The current position, lateral and longitudinal velocities, and acceleration of the target vehicle can be obtained based on the sensor data at each moment. The position of the next point is estimated based on the current lateral and longitudinal velocities and acceleration. The calculation is performed every 10ms to finally obtain the motion trajectory of the target vehicle.

[0079] The target scene feature refers to the lane change scene in which the second vehicle is located. The lane change behavior of the second vehicle can be predicted by the motion trajectory of the target vehicle, the surrounding environment information, etc., to determine which lane change scene the lane change behavior of the second vehicle belongs to, and then generate the target scene feature of the corresponding scene. The lane change scene may include but is not limited to the cut-in lane change scene, the cut-out lane change scene, the off-ramp lane change scene, the auxiliary lane lane change scene, the turning lane change scene, etc.

[0080] In the above step S102, according to the target scene characteristics, the target person driving experience information matching the lane change scene where the second vehicle is located is determined, and the target person driving experience information is used to describe the target person driving experience that conforms to the preset driving logic.

[0081] The above-mentioned target human driving experience information refers to the experience information that conforms to driving logic in a certain driving scenario, which is equivalent to the driving action prediction that an experienced virtual driver may make according to a certain scenario, such as controlling the vehicle to slow down or change lanes in a lane-cutting change scenario, or changing lanes to avoid obstacles in a scenario where there are obstacles ahead. The target human driving experience information that matches the lane-changing scenario refers to the driving action prediction that an experienced virtual driver may make in the lane-changing scenario.

[0082] The above-mentioned target human driving experience information can be obtained through a pre-built driving experience library, or through a driving experience model built by a neural network model or through other artificial intelligence methods such as AI.

[0083] In the above step S103, a lane change decision result is generated according to the target person's driving experience information. The lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction when the lane change occurs, based on the target person's driving experience.

[0084] The above-mentioned generation of the lane change decision result based on the target person's driving experience information refers to generating the lane change decision result in the current lane change scenario based on the target person's driving experience information obtained in step S102. The lane change decision result may indicate that the first vehicle changes lanes, or may indicate that the first vehicle does not change lanes, depending on whether an effective lane change is achieved. If it is judged based on the target person's driving experience information that the first vehicle changes lanes to improve the traffic efficiency, the lane change is performed. If it is judged based on the target person's driving experience information that the first vehicle changes lanes to reduce the traffic efficiency, the lane change is not performed.

[0085] The above lane change decision results include not only the decision results of whether to change lanes, but also the decision results of how to change lanes, such as cutting out to the left, cutting out to the right, continuous lane changes, etc.

[0086] In the above step S104, the lane change control of the first vehicle is performed according to the lane change decision result.

[0087] The above lane change control refers to the vehicle executing the corresponding lane change control according to the lane change decision result. The vehicle's lane change control can be realized by calling the autonomous lane change state machine. The autonomous lane change state machine refers to the state jump requirement and vehicle control and interaction process of the assisted driving system automatically triggering the lane change. It is a system-preset autonomous lane change process. When the lane change decision result triggers the lane change sign of the autonomous lane change state machine, the vehicle will automatically move laterally, turn on the turn signal to start changing lanes, and continuously detect the surrounding environment and target status during the lane change process, continuously perform risk assessment, and make decisions and actions to continue to complete the lane change or cancel the lane change.

[0088] In some implementations, obtaining target scene features may include:

[0089] Acquiring scene recognition information associated with the first vehicle and the second vehicle, the scene recognition information including at least one of traffic rule information and map information;

[0090] Determine the target scene characteristics based on the scene cognition information.

[0091] In this embodiment, by first acquiring scene recognition information associated with the first vehicle and the second vehicle, and then determining the target scene feature based on the scene recognition information, the target scene feature can be acquired more accurately, and the matching degree between the lane change scene indicated by the target scene feature and the actual lane change scene can be improved.

[0092] The above-mentioned acquisition of scene recognition information associated with the first vehicle and the second vehicle refers to acquiring traffic rule information and / or map information associated with the first vehicle and the second vehicle, and then more accurately acquiring the target scene characteristics of the second vehicle based on the traffic rule information and / or map information.

[0093] The above-mentioned scene recognition information includes at least one of traffic rule information and map information, wherein the traffic rule information is used to indicate the traffic rules that the vehicle should follow during driving, such as the maximum speed, minimum speed, lane type, traffic instruction information corresponding to different lane lines and signs, and different traffic rules corresponding to various vehicles, etc. For example, special vehicles such as ambulances and fire trucks need to give way first, and traffic rule information can help more accurately determine the characteristics of the target scene. Map information refers to prior map information, which refers to pre-loaded map information, including road layout, traffic signals, service areas, ramps, road signs, etc. On the one hand, map information provides the basic information required for the vehicle to locate and navigate in its environment, and on the other hand, map information can help more accurately determine the characteristics of the target scene. For example, if the map information indicates that there is an intersection ahead, the second vehicle on the left side ahead makes a continuous right turn, which may be a right turn scene, and if the second vehicle on the right side ahead makes a continuous left turn, it may be a left turn scene.

[0094] In some embodiments, the second vehicle is a target type of vehicle, and the scene awareness information includes traffic rule information for describing a lane change rule for the target type of vehicle;

[0095] Based on the scene cognition information, determine the characteristics of the target scene, including:

[0096] When the speed of the second vehicle during the lane change process is lower than the speed of the first vehicle, acquiring lane information of the lane in which the second vehicle was located before the lane change;

[0097] According to the lane information and traffic rule information, a lane-changing scene is determined, and the target scene feature includes the lane-changing scene.

[0098] In this embodiment, when the second vehicle is a target type of vehicle, first, when the speed of the second vehicle during the lane change process is lower than the speed of the first vehicle, the lane information of the lane where the second vehicle was before the lane change is obtained, and then the lane change scene is determined based on the lane information and traffic rule information, and the target scene feature includes the lane change scene. The matching degree between the lane change scene indicated by the target scene feature and the actual lane change scene can be improved.

[0099] The above-mentioned target type of vehicles refers to vehicles with specific traffic rules, such as cargo vehicles, large vehicles, and special vehicles such as ambulances and fire trucks.

[0100] In the case where the speed of the second vehicle during the lane change process is lower than that of the first vehicle, the lane information of the lane in which the second vehicle was located before the lane change is obtained, which means that the speed of the first vehicle and the speed of the second vehicle during the lane change process are first calculated by the vehicle-mounted sensor. If it is determined that the speed of the second vehicle during the lane change process is lower than that of the first vehicle, it is considered that the second vehicle may have a speed reduction behavior on the first vehicle, affecting the traffic efficiency of the first vehicle. In the case where it is determined that the second vehicle has a speed reduction behavior on the first vehicle, the lane information of the lane in which the second vehicle was located before the lane change is obtained, and then the lane change scene is determined based on the lane information and traffic rule information.

[0101] In the above lane change scenario determined based on lane information and traffic rule information, the lane change scenario is equivalent to the second vehicle cutting into the lane where the first vehicle is located and there is a speed reduction behavior. Usually, the logic judgment of the assisted driving is to directly request a lane change to the left or right to avoid the speed reduction behavior of the second vehicle. However, when the second vehicle is a cargo vehicle, a large vehicle, or a special vehicle such as an ambulance or a fire truck, it has specific traffic rules. For example, cargo vehicles and large vehicles need to drive on the right according to traffic rules. For example, special vehicles such as ambulances and fire trucks can drive in emergency lanes in emergencies. Therefore, simply requesting a lane change in the lane change scenario may result in an invalid lane change. In this application, the lane change scenario is determined based on lane information and traffic rule information, and the appropriate lane change scenario is determined based on the different types of second vehicles, lane information and traffic rules, so as to further improve the matching degree between the lane change scenario indicated by the target scene feature and the actual lane change scenario.

[0102] It should be understood that the above-mentioned lane change scenarios include many different types of situations. According to the different second vehicles, different lane information and different traffic rules of the corresponding vehicles, different lane change sub-scenarios can be obtained. According to the lane change scenarios in different situations, different target human driving experience information and lane change decision results can be obtained.

[0103] In some embodiments, the second vehicle is a cargo vehicle;

[0104] Executing lane change control of the first vehicle according to the lane change decision result may include:

[0105] In the case where the cargo vehicle is located in the rightmost lane of the road before changing lanes in the lane change scenario, according to the lane change decision result, the first vehicle is prevented from changing lanes to the lane before the cargo vehicle changes lanes; or

[0106] In the lane change scenario, when the cargo vehicle is not located in the rightmost lane of the road before changing lanes, the vehicle is controlled to change lanes to the lane before the cargo vehicle changed lanes according to the lane change decision result.

[0107] In this embodiment, when the second vehicle is a cargo vehicle, in the case where the cargo vehicle is located in the rightmost lane of the road before changing lanes in the cut-in lane change scenario, the first vehicle is prevented from changing lanes to the lane before the cargo vehicle changes lanes according to the lane change decision result; or, in the case where the cargo vehicle is not located in the rightmost lane of the road before changing lanes in the cut-in lane change scenario, the vehicle is controlled to change lanes to the lane before the cargo vehicle changes lanes according to the lane change decision result. The rationality of the lane change decision result can be improved, and the probability of invalid lane change can be further reduced.

[0108] The above-mentioned cargo vehicle refers to any large transport vehicle such as a truck, a van, a tanker, etc.

[0109] Because in the traffic regulations, cargo vehicles need to drive on the right, that is, the rightmost road is the default driving road for cargo vehicles. When a lane-cutting behavior occurs, the auxiliary driving logic in the relevant technology is to change lanes directly to the left or right. Since the rightmost road is the driving road for cargo vehicles, the cargo vehicle is on the rightmost road before changing lanes. At this time, the cargo vehicle cuts in and changes lanes to the left. Then, according to human driving experience, it can be determined that either there is a low-speed vehicle on the rightmost road and the cargo vehicle is overtaking at this time, or there are obstacles or other obstacles to traffic on the rightmost road, causing the cargo vehicle to change lanes to the left. At this time, if the first vehicle changes lanes to the right, it will not improve driving efficiency, resulting in an invalid lane change. In addition, when the cargo vehicle cuts in and changes lanes to the left, the on-board camera of the first vehicle that detects the right front will be blocked by the second vehicle, making it difficult to see the road conditions ahead of the right road. If there is a vehicle on the left road, a request to change lanes to the right will be made.

[0110] Therefore, in this embodiment, in the case where the cargo vehicle is located in the rightmost lane of the road before changing lanes in the lane change scenario, the target person's driving experience information can be used to make a judgment consistent with the driving experience, and a lane change decision result can be generated to prevent the first vehicle from changing lanes to the lane before the cargo vehicle changes lanes, thereby avoiding invalid lane changes in this situation.

[0111] Exemplary, reference Figure 2As shown, this is the first scenario of cutting in and changing lanes. At this time, the first vehicle is located in the second lane on the right, and there is a vehicle in the left lane of the first vehicle, and the traffic efficiency of the left lane is low. At this time, the cargo vehicle located in the rightmost lane cuts left into the lane where the first vehicle is located. Since the traffic efficiency of the left lane of the first vehicle is low, the auxiliary system of the first vehicle will default to request a lane change to the right due to the speed reduction behavior of the cargo vehicle when cutting in. At this time, there is a low-speed truck further ahead in the rightmost lane. If the lane is changed to the right, the traffic efficiency will be further reduced. Therefore, in this embodiment, a judgment consistent with the driving experience is made according to the driving experience information of the target person, and a lane change decision result is generated to prevent the first vehicle from changing lanes to the lane before the cargo vehicle changes lanes, so as to avoid invalid lane changes in this situation.

[0112] Therefore, in this embodiment, when the cargo vehicle is not located in the rightmost lane of the road before changing lanes in the lane change scenario, a lane change decision result that allows the lane change can be obtained based on the target human driving experience information, thereby controlling the vehicle to change lanes to the lane before the cargo vehicle changed lanes.

[0113] Exemplary, reference Figure 3 As shown, this is the second lane-changing scenario. At this time, the first vehicle is located in the leftmost lane, and there is no other vehicle on the right side of the first vehicle. When a cargo vehicle on the right slowly cuts into the own lane, if the driver waits for the cargo vehicle to completely cut into the own lane and triggers the acceleration before changing lanes to the right, it will lead to a poor lane-changing experience due to excessive deceleration. Therefore, a judgment consistent with the driving experience is made based on the target person's driving experience information, and a lane-changing decision result of changing lanes to the right in advance is generated, thereby improving the rationality of the lane-changing decision result.

[0114] It should be noted that, in addition to cargo vehicles, there may be other lane-changing scenarios for different second vehicles. For example, when the second vehicle is an ambulance, the first vehicle is in the slow lane, and the second vehicle cuts into the slow lane from the adjacent fast lane. According to driving experience, the ambulance cuts into the slow lane from the fast lane, and it can be considered that there is an obstacle on the fast lane in front of the ambulance. Then, the decision result of not changing lanes will be generated based on the target person's driving experience information. Or, if the ambulance cuts into the lane from the emergency lane, according to traffic regulations, except for special vehicles, other vehicles are not allowed to enter the emergency lane, then the decision result of not changing lanes will also be generated based on the target person's driving experience information.

[0115] In some implementations, obtaining scene recognition information associated with the first vehicle and the second vehicle may include:

[0116] When it is detected that the second vehicle changes lanes multiple times in a row toward the target direction, map information associated with the first vehicle and the second vehicle is obtained;

[0117] Based on the scene cognition information, the target scene characteristics are determined, which may include:

[0118] In the case where it is determined based on the map information that the lane change behavior of the second vehicle is to enter a ramp on the road side corresponding to the target direction, a down-ramp lane change scene feature is determined, the target scene feature including the down-ramp lane change scene,

[0119] The lane change decision result is used to instruct the first vehicle to change lanes in a direction opposite to the target direction based on the target human driving experience.

[0120] In this embodiment, when it is detected that the second vehicle changes lanes multiple times in a row toward the target direction, map information associated with the first vehicle and the second vehicle is obtained, and then when it is determined based on the map information that the second vehicle changes lanes to drive into the ramp on the road side corresponding to the target direction, the off-ramp lane change scene characteristics are determined, and the target scene characteristics include the off-ramp lane change scene, wherein the lane change decision result is used to instruct the first vehicle to change lanes in the direction opposite to the target direction based on the target person's driving experience. The rationality of the lane change decision result can be improved, and the traffic efficiency can be improved.

[0121] The above-mentioned obtaining of map information associated with the first vehicle and the second vehicle when it is detected that the second vehicle changes lanes multiple times in succession toward the target direction means that if the second vehicle changes lanes in succession in one direction at least twice, the map information is used to check whether there is a ramp ahead of the lane changing direction of the second vehicle.

[0122] The above-mentioned determination of the off-ramp lane change scenario in the case where the lane change behavior of the second vehicle is determined based on the map information to enter the ramp on the side of the road corresponding to the target direction means that if the second vehicle changes lanes in one direction at least twice in succession, and it is known through the map information that there is a ramp ahead of the lane change direction of the second vehicle, it is considered that the purpose of the second vehicle's lane change is to perform an off-ramp lane change, and the target scenario characteristics corresponding to the off-ramp lane change scenario are obtained. Since the off-ramp lane change is usually accompanied by a deceleration behavior, it will cause the ego vehicle to be affected and the traffic efficiency to become low. According to the target human driving experience information, after confirming that it is a off-ramp lane change scenario, a lane change decision result is generated to indicate that the first vehicle changes lanes in a direction opposite to the target direction, so as to avoid the speed reduction behavior of the second vehicle in advance, thereby improving the traffic efficiency.

[0123] The condition for determining whether multiple lane changes occur continuously is that the lanes are changed to the left or right at least twice in a row.

[0124] Exemplary, reference Figure 4As shown, the first vehicle is located in the second lane on the right, and the second vehicle is located in the leftmost lane. When the second vehicle continuously changes lanes to the right and the map information shows that there is a ramp exit in front of the right side of the road, a lane change decision result of changing lanes to the left in advance is generated based on the target person's driving experience information, which can avoid vehicles coming off the ramp more quickly and improve traffic efficiency.

[0125] It should be noted that, in the lane change decision result of changing lanes to the left in advance generated according to the target person's driving experience information, the lane change to the left may be performed once or multiple times in succession until the second vehicle is located in the right lane of the vehicle.

[0126] It should be noted that the above are only some of the implementation methods of the present application. In addition to the above-mentioned lane change scenarios and off-ramp lane change scenarios, other lane change scenarios can also be judged in accordance with the preset driving logic based on the target human driving experience to generate other lane change decision results with driving experience.

[0127] In some implementations, determining target human driving experience information matching the lane change scenario in which the second vehicle is located according to the target scenario characteristics may include:

[0128] Inputting the target scene feature into a preset driving experience database to obtain human driving experience information that has a corresponding relationship with the target scene feature in the driving experience database, wherein the driving experience database is a database including the corresponding relationship between different scene features and human driving experience information;

[0129] When human driving experience information having a corresponding relationship with the target scene feature is obtained in the driving experience database, the obtained human driving experience information is determined as the target human driving experience information.

[0130] In this embodiment, the target scene feature is first input into a preset driving experience database to obtain human driving experience information that corresponds to the target scene feature in the driving experience database. The driving experience database is a database including the correspondence between different scene features and human driving experience information. When human driving experience information that corresponds to the target scene feature is obtained in the driving experience database, the obtained human driving experience information is determined as the target human driving experience information. This application matches the target scene feature with the target human driving experience information through the driving experience database, which can improve the matching degree between the target human driving experience information and the corresponding scene, and further reduce the probability of invalid lane change.

[0131] The above-mentioned driving experience library refers to a scenario library based on driver behavior and driving experience, which may include some safety and comfort lane changes initiated by the driver's driving awareness, and may also include cooperation with other road users and predictive lane changes.

[0132] The driving experience database is a database including the correspondence between different scene features and human driving experience information, which means that the driving experience database stores various types of scenes and driving decision information that the driver may make based on experience in these scenes. According to the target scene features, the corresponding lane change scene in the driving experience database can be found, and then human driving experience information for the lane change scene can be output.

[0133] In the above case where the human driving experience information having a corresponding relationship with the target scene feature is obtained in the driving experience library, the obtained human driving experience information is determined as the target human driving experience information, which means that if the driving experience in the current corresponding scene exists in the driving experience library, it is output; if there is no corresponding driving experience in the current scene, it is not output or a prompt information is output.

[0134] The following introduces the construction process of the driving experience library related to the lane changing scenarios corresponding to this application: first, typical lane changing scenarios are extracted from a massive test scenario library, and then cognitive rules are extracted and designed for typical lane changing scenarios. After the scenario design is completed, labeling is performed according to the scene characteristics to obtain different target scene characteristics, and corresponding human driving experience information is constructed for typical lane changing scenarios. For example, what kind of judgments the driver may make and what kind of vehicle operations may be performed in a certain scenario. By digitizing these experiences, human driving experience information can be obtained, and then a driving experience library that gives human driving experience is obtained based on the target scene characteristics and the corresponding human driving experience information.

[0135] Based on the vehicle lane changing control method provided in the above embodiment, the present application also provides a specific implementation method of the vehicle lane changing control device.

[0136] like Figure 5 As shown, the vehicle lane change control device 200 provided in the embodiment of the present application may include:

[0137] A scene feature acquisition module 201 is used to acquire a target scene feature when a second vehicle located in front of the first vehicle is detected to have changed lanes, wherein the second vehicle is the vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate the lane change scene in which the second vehicle is located;

[0138] A driving experience determination module 202, for determining target human driving experience information that matches the lane change scenario in which the second vehicle is located according to the target scenario characteristics, where the target human driving experience information is used to describe the target human driving experience that conforms to a preset driving logic;

[0139] A lane change decision generating module 203, used to generate a lane change decision result according to the target person's driving experience information, the lane change decision result is used to indicate whether the first vehicle has a lane change behavior and the lane change direction in the case of a lane change behavior according to the target person's driving experience;

[0140] The lane change control execution module 204 is used to execute the lane change control of the first vehicle according to the lane change decision result.

[0141] The vehicle lane changing control device 200 of the embodiment of the present application is used to execute the vehicle lane changing control method in the above embodiment. Its specific processing process is the same as the vehicle lane changing control method in the above embodiment, and will not be repeated here.

[0142] Figure 6 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0143] The electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0144] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0145] The memory 302 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 302 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 302 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 302 is a non-volatile solid-state memory.

[0146] In some embodiments, the memory 302 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0147] The processor 301 implements any one of the vehicle lane change control methods in the above embodiments by reading and executing computer program instructions stored in the memory 302 .

[0148] In one example, the electronic device may further include a communication interface 303 and a bus 310. Figure 3 As shown, the processor 301, the memory 302, and the communication interface 303 are connected via a bus 310 and communicate with each other.

[0149] The communication interface 303 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0150] Bus 310 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 310 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0151] In addition, in combination with the vehicle lane change control method in the above embodiment, the embodiment of the present application can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the vehicle lane change control methods in the above embodiment is implemented.

[0152] The present application also relates to a vehicle, which is controlled to change lanes by the vehicle lane change control method in the above embodiment. Specifically, the vehicle can be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle can also be an operating vehicle, such as a van, a bus, a small truck or a large trailer. The vehicle can be a fuel vehicle or a new energy vehicle. When the vehicle is a new energy vehicle, it can be a hybrid vehicle or a pure electric vehicle. The vehicle lane change control method can be run in a vehicle-mounted terminal, or it can be run in other terminal devices connected to the vehicle via Bluetooth, a data cable or other communication methods, such as a mobile phone.

[0153] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0154] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0155] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0156] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0157] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A vehicle lane change control method, characterized in that: The following steps are involved: When a second vehicle located in front of a first vehicle is detected to have changed lanes, a target scene feature is acquired, wherein the second vehicle is a vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate a lane change scene in which the second vehicle is located; Determining target human driving experience information matching the lane change scenario of the second vehicle according to the target scenario characteristics, wherein the target human driving experience information is used to describe the target human driving experience that conforms to a preset driving logic; generating a lane change decision result according to the target person's driving experience information, wherein the lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction when the lane change has occurred, based on the target person's driving experience; Execute lane change control of the first vehicle according to the lane change decision result.

2. The vehicle lane change control method according to claim 1, characterized in that: The acquiring of target scene features comprises: Acquire scene recognition information associated with the first vehicle and the second vehicle, the scene recognition information including at least one of traffic rule information and map information; The target scene features are determined according to the scene cognition information.

3. The vehicle lane change control method according to claim 2, characterized in that: The second vehicle is a target type of vehicle, and the scene recognition information includes traffic rule information for describing a lane change rule for the target type of vehicle; The determining the target scene feature according to the scene recognition information includes: When the speed of the second vehicle during the lane change process is lower than the speed of the first vehicle, acquiring lane information of the lane in which the second vehicle was located before the lane change; A lane-changing scene is determined according to the lane information and the traffic rule information, and the target scene feature includes the lane-changing scene.

4. The vehicle lane change control method according to claim 3, characterized in that: The second vehicle is a cargo vehicle; The performing lane change control of the first vehicle according to the lane change decision result includes: In the cut-in lane change scenario, when the cargo vehicle is located in the rightmost lane of the road before changing lanes, according to the lane change decision result, preventing the first vehicle from changing lanes to the lane before the cargo vehicle changed lanes; or, In the lane-changing scenario, when the cargo vehicle is not located in the rightmost lane of the road before changing lanes, the vehicle is controlled to change lanes to the lane before the cargo vehicle changed lanes according to the lane-changing decision result.

5. The vehicle lane change control method according to claim 2, characterized in that: The acquiring scene recognition information associated with the first vehicle and the second vehicle includes: When it is detected that the second vehicle changes lanes multiple times in a row toward a target direction, acquiring map information associated with the first vehicle and the second vehicle; The determining the target scene feature according to the scene recognition information includes: In a case where it is determined based on the map information that the lane change behavior of the second vehicle is to enter a ramp on the road side corresponding to the target direction, a down-ramp lane change scene is determined, wherein the target scene feature includes the down-ramp lane change scene, The lane change decision result is used to instruct the first vehicle to change lanes in a direction opposite to the target direction based on the target human driving experience.

6. The vehicle lane change control method according to claim 1, characterized in that: The determining, according to the target scene feature, target human driving experience information matching the lane change scene in which the second vehicle is located, includes: Inputting the target scene feature into a preset driving experience database to obtain human driving experience information that has a corresponding relationship with the target scene feature in the driving experience database, wherein the driving experience database is a database including the corresponding relationship between different scene features and human driving experience information; When the human driving experience information having a corresponding relationship with the target scene feature is obtained in the driving experience database, the obtained human driving experience information is determined as the target human driving experience information.

7. A vehicle lane change control device, characterized in that: include: A scene feature acquisition module, configured to acquire a target scene feature when a second vehicle located in front of a first vehicle is detected to have changed lanes, wherein the second vehicle is a vehicle that has changed lanes in front of the first vehicle, and the target scene feature is used to indicate a lane change scene in which the second vehicle is located; A driving experience determination module, used to determine target human driving experience information that matches the lane change scenario in which the second vehicle is located according to the target scenario characteristics, wherein the target human driving experience information is used to describe the target human driving experience that conforms to a preset driving logic; a lane change decision generating module, used to generate a lane change decision result according to the target person's driving experience information, wherein the lane change decision result is used to indicate whether the first vehicle has changed lanes and the lane change direction in the case of a lane change according to the target person's driving experience; A lane change control execution module is used to execute lane change control of the first vehicle according to the lane change decision result.

8. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the vehicle lane change control method as described in any one of claims 1-6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the vehicle lane change control method according to any one of claims 1 to 6 is implemented.

10. A vehicle, characterized in that: The vehicle performs lane change control by using the vehicle lane change control method as described in any one of claims 1 to 6.

Images