Vehicle lane selection control method, device and equipment and storage medium

Abstract

The invention discloses a vehicle lane selection control method, device and equipment and a storage medium, and belongs to the technical field of vehicle control, and the method comprises the steps: determining the current lane center line information of each lane at the current moment according to the lane information of a road where a vehicle is located; for each lane, determining the clear state of the lane center line of the lane according to the historical lane center line information of the lane at the historical moment and the current lane center line information; for each lane, determining a current target preview point according to the clear state and the initial preview point; for each lane, determining the safety cost according to the position information of the vehicle, the center line information of the current lane and the current target preview point; wherein the safety cost is used for representing the risk degree of the vehicle entering the lane; and controlling the vehicle to enter the lane with the minimum safety cost. Due to the fact that the clear state of the lane center line of the vehicle in the scene with the limited view changes, the safety of the vehicle after lane selection in the scene can be guaranteed through the scheme.

Description

Technical Field

[0001] The present application belongs to the field of vehicle control technology, and in particular relates to a vehicle lane selection control method, device, equipment and storage medium. Background Art

[0002] When vehicles are driving on the road, they often need to change lanes to improve traffic efficiency or driving safety. In related technologies, when performing road search, the strategy adopted is: determine each vehicle's trajectory point based on the vehicle's global positioning system (GPS), determine a first radius based on the GPS positioning accuracy, and perform candidate road search and matching for each trajectory point according to the first radius; re-perform candidate road search and matching for trajectory points that do not match candidate roads according to the second radius; and for trajectory points that match candidate roads, calculate and determine whether the transfer route matrix between adjacent trajectory points is abnormal. If abnormal, re-perform candidate road search and matching for the corresponding abnormal trajectory point.

[0003] The above-mentioned multi-level radius search and matching strategy is more suitable for scenarios where the vehicle is driving on a road with unrestricted vision in front of it. However, when there is a scene with restricted vision such as occlusion in front of the vehicle, if the above-mentioned scheme is still used, the matching rate will be low and the lane selection will be unreasonable, which will lead to lower safety after the vehicle selects the lane. Summary of the Invention

[0004] The embodiments of the present application provide a vehicle lane selection control method, apparatus, device, and storage medium, which can, at least to a certain extent, ensure the safety of the vehicle after lane selection in a scenario with limited vision.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the present application.

[0006] According to a first aspect of an embodiment of the present application, a vehicle lane selection control method is provided, comprising:

[0007] Determine the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located;

[0008] For each lane, determining the lane centerline clarity status of the lane based on the lane centerline information at the historical moment and the current lane centerline information;

[0009] For each lane, determine the current target preview point based on the clear state and the initial preview point;

[0010] For each lane, a safety cost is determined based on the vehicle's position, the current lane centerline, and the current target preview point. The safety cost is used to represent the risk level of the vehicle entering the lane.

[0011] Control vehicles to enter the lane with the lowest safety cost.

[0012] In some embodiments, determining a lane centerline clarity state of a lane based on historical lane centerline information and current lane centerline information at a historical moment includes:

[0013] Determine the lateral offset and length change of the lane centerline based on the historical lane centerline information and the current lane centerline information at the historical moment;

[0014] The clarity of the lane centerline is determined based on the lateral offset and length change.

[0015] In some embodiments, the time difference between the historical moment and the current moment is less than or equal to a preset time length.

[0016] In some embodiments, the historical moment is the moment before the current moment, the historical lane centerline information includes the position of the initial preview point on the lane centerline at the previous moment and the length of the lane centerline at the previous moment, and the current lane centerline information includes the position of the initial preview point on the lane centerline at the current moment and the length of the lane centerline at the current moment. Based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information, determining the lateral offset and length change of the lane centerline includes:

[0017] Determine the lateral offset of the lane centerline based on the position of the initial preview point on the lane centerline at the previous moment and the position of the initial preview point on the lane centerline at the current moment;

[0018] The length change of the lane centerline is determined based on the length of the lane centerline at the previous moment and the length of the lane centerline at the current moment.

[0019] In some embodiments, the clear state includes a first state for indicating that the lane centerline is clear and a second state for indicating that the lane centerline is unclear. Determining the clear state of the lane centerline based on the lateral offset and the length change includes:

[0020] When the lateral offset is not greater than a first preset value and the length change is not greater than a second preset value, determining that the clear state of the lane centerline is the first state;

[0021] When the lateral offset is greater than a first preset value and / or the length change is greater than a second preset value, the clear state of the lane centerline is determined to be the second state.

[0022] In some embodiments, the clear state includes a first state for indicating that the lane centerline is clear and a second state for indicating that the lane centerline is unclear. Determining the current target preview point based on the clear state and the initial preview point includes:

[0023] When the clear state is the second state, the preview distance of the initial preview point is reduced to obtain the current target preview point.

[0024] In some embodiments, the safety cost is determined based on the vehicle's position information, the current lane centerline information, and the current target preview point, including:

[0025] Determine the lateral cost based on the vehicle's position information and the current lane centerline information;

[0026] Determine the lane curvature cost based on the current lane centerline information;

[0027] Determine the steering cost based on the position information and the current target preview point;

[0028] Determine the steering wheel consistency cost based on the position information, the current target preview point, and the lane's historical target preview points at historical moments.

[0029] The safety cost is determined based on the lateral cost, lane curvature cost, steering wheel turning cost and steering wheel consistency cost.

[0030] In some embodiments, the position information includes a first position representing the current position of the vehicle and a second position that is a preset distance away from the first position. The current lane centerline information includes a third position representing the current position of the lane centerline. Determining the lateral cost based on the vehicle position information and the current lane centerline information includes:

[0031] determining a first lateral deviation based on the first position and the third position;

[0032] determining a second lateral deviation based on the second position and the third position;

[0033] The first lateral deviation and the second lateral deviation are weighted and summed to obtain the lateral cost.

[0034] In some embodiments, the current lane centerline information includes the curvature of the lane centerline at the current moment. Determining the lane curvature cost based on the current lane centerline information includes:

[0035] The lane curvature cost is determined based on the curvature difference between the maximum curvature and the minimum curvature of the lane centerline of each lane at the current moment.

[0036] In some embodiments, the position information includes a first position representing the current position of the vehicle. Determining the steering cost based on the position information and the current target preview point includes:

[0037] Determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point;

[0038] The steering wheel steering cost is obtained by weighting the angle difference between the first steering wheel angle and the second steering wheel angle and summing it with the second steering wheel angle.

[0039] In some embodiments, the position information includes a first position representing a current position of the vehicle and a fourth position representing a historical position of the vehicle. Determining a steering wheel consistency cost based on the position information, the current target preview point, and the historical target preview points of the lane at historical moments includes:

[0040] Determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point;

[0041] Determining a third steering wheel angle corresponding to the fourth position and a fourth steering wheel angle corresponding to the historical target preview point;

[0042] determining a steering angle difference between the first steering wheel angle and the second steering wheel angle as a first steering angle difference;

[0043] determining a steering angle difference between the third steering wheel angle and the fourth steering wheel angle as a second steering angle difference;

[0044] The difference between the first steering angle difference and the second steering angle difference is multiplied by a preset weight to obtain a steering wheel consistency cost.

[0045] According to a second aspect of an embodiment of the present application, a vehicle lane selection control device is provided, comprising a processor and a memory, wherein the memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, the steps of any method of the first aspect described above are implemented.

[0046] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor is prompted to implement the steps of any method as described in the first aspect above.

[0047] According to a fourth aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program. When the computer program is executed by a processor, the processor is prompted to implement the steps of any one of the methods of the first aspect described above.

[0048] In this application, the current lane centerline information of each lane at the current moment is determined based on the lane information of the road where the vehicle is located; for each lane, the clarity state of the lane centerline is determined based on the historical lane centerline information of the lane at historical moments and the current lane centerline information; the current target preview point is determined based on the clarity state and the initial preview point; the safety cost is determined based on the vehicle's position information, the current lane centerline information, and the current target preview point; wherein the safety cost is used to characterize the risk level of the vehicle entering the lane; and the vehicle is controlled to enter the lane with the lowest safety cost. Since the clarity state of the lane centerline will change in scenarios with limited vision, after determining the target preview point using the clarity state of the lane centerline, the safety cost of each lane is calculated based on the target preview point, thereby ensuring the safety of the vehicle after selecting the lane in scenarios with limited vision.

[0049] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are incorporated into and constitute a part of the specification, illustrating embodiments consistent with the present application and, together with the specification, explaining the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can derive other drawings based on these drawings without inventive effort. In the drawings:

[0051] Figure 1 A schematic flow chart of a vehicle lane selection control method according to some embodiments of the present application is shown;

[0052] Figure 2 Shown Figure 1 Detailed schematic diagram of step 104;

[0053] Figure 3 Shown Figure 2 Schematic diagram of step 201;

[0054] Figure 4 A schematic diagram showing the calculation principle of the second steering wheel angle corresponding to the current target preview point is shown;

[0055] Figure 5 A schematic flow chart of a vehicle lane selection control method according to other embodiments of the present application is shown;

[0056] Figure 6 A block diagram of a vehicle lane selection control device according to some embodiments of the present application is shown;

[0057] Figure 7A structural schematic diagram of a vehicle lane selection control device according to some embodiments of the present application is shown. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0060] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0061] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0062] It should be noted that the lane selection control strategy in the related art is usually only applicable to scenarios where the vehicle is traveling on a road with unrestricted vision ahead. When there is a scenario with restricted vision such as an obstruction in front of the vehicle, if the existing lane selection control strategy is still used, it is easy to cause unreasonable lane selection, which in turn leads to lower safety after the vehicle selects the lane. The embodiment of the present application takes into account that the clarity state of the lane centerline of the vehicle in the scenario with restricted vision will change. First, based on the lane information of the road where the vehicle is located, the current lane centerline information of each lane at the current moment is determined. Then, for each lane, the clarity state of the lane centerline of the lane is determined based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information. Based on the clarity state and the initial preview point, the current target preview point is determined. Then, for each lane, the safety cost is determined based on the vehicle's position information, the current lane centerline information and the current target preview point. Finally, the vehicle is controlled to enter the lane with the smallest safety cost, thereby ensuring the safety of the vehicle after lane selection in the scenario with restricted vision.

[0063] Figure 1 FIG2 shows a flow chart of a vehicle lane selection control method according to some embodiments of the present application. Figure 1 As shown, a vehicle lane selection control method is provided, which may include the following steps 101 to 105.

[0064] In step 101, the current lane centerline information of each lane at the current moment is determined based on the lane information of the road where the vehicle is located.

[0065] It is understandable that the road where the vehicle is located may have two lanes, three lanes or more lanes. In order to select the most suitable lane from all lanes, it is necessary to determine the current lane centerline information of each lane at the current moment based on the lane information, and then perform lane selection control based on the current lane centerline information of each lane.

[0066] During the implementation process, the lane image of the road ahead of the vehicle can be collected in real time by the on-board camera, and the lane marking information, road boundary information, road environment information, etc. of each lane can be collected in real time by equipment such as millimeter wave radar and lidar, and this information can be used as the lane information of the road where the vehicle is located. After obtaining the lane information, the current lane centerline information of each lane can be determined based on the lane information at the current moment. For example, the initial lane centerline information can be determined based on the lane image and marking information in the lane information, and then the initial lane centerline information can be adjusted based on other information to obtain more accurate current lane centerline information. Of course, the historical lane line information of each lane can also be determined based on the lane information at historical moments, and then the historical lane centerline information can be determined based on the historical lane line information.

[0067] In step 102 , for each lane, a clear state of the lane centerline of the lane is determined based on historical lane centerline information of the lane at a historical moment and current lane centerline information.

[0068] The historical moment refers to a moment before the current moment. To ensure accurate determination of the clear state, the interval between the historical moment and the current moment cannot be too large. In some embodiments, the time difference between the historical moment and the current moment is less than or equal to a preset time length.

[0069] It is understood that when the vehicle's field of view is limited (e.g., when the lane centerline is blurred, or there is an obstruction or diversion ahead), the lane centerline may become blurred or jumpy, resulting in an unclear lane centerline. Therefore, the lane centerline clarity state in the embodiment of the present application may include a first state indicating that the lane centerline is clear and a second state indicating that the lane centerline is unclear.

[0070] In some embodiments, the clarity state of the lane centerline of the lane is determined based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information, including: determining the lateral offset and length change of the lane centerline based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information; determining the clarity state of the lane centerline based on the lateral offset and length change.

[0071] It's understood that the lateral offset represents the change in the lane centerline's lateral direction from a previous moment to the current moment, while the length change represents the change in the lane centerline's longitudinal direction from a previous moment to the current moment. If the vehicle's field of view is restricted, the lateral offset and length of the lane centerline can change significantly. For example, if the vehicle is temporarily obstructed, the current lane centerline length may be significantly reduced compared to the previous length.

[0072] During the implementation process, the historical moment may be the moment before the current moment, the historical lane centerline information includes the position of the initial preview point on the lane centerline at the previous moment and the length of the lane centerline at the previous moment, and the current lane centerline information includes the position of the initial preview point on the lane centerline at the current moment and the length of the lane centerline at the current moment. According to the historical lane centerline information of the lane at the historical moment and the current lane centerline information, the lateral offset and length change of the lane centerline are determined, including: determining the lateral offset of the lane centerline according to the position of the initial preview point on the lane centerline at the previous moment and the position of the initial preview point on the lane centerline at the current moment; determining the length change of the lane centerline according to the length of the lane centerline at the previous moment and the length of the lane centerline at the current moment.

[0073] It is understandable that the initial preview point is usually set on the center line of the lane, and its preview distance is usually the normal line of sight (for example, 3.6 times the line of sight). By comparing the position of the initial preview point at the current moment and the previous moment, the lateral offset of the lane center line can be accurately determined.

[0074] The length of a lane centerline can be determined by the number of valid pixels along the lane centerline. For example, the number of valid pixels along the lane centerline can be determined from the lane image and then converted to length. By comparing the lane centerline length at the current moment with the previous moment, the change in lane centerline length can be accurately determined.

[0075] In some embodiments, the clarity state of the lane centerline is determined based on the lateral offset and the length change, including: when the lateral offset is not greater than a first preset value and the length change is not greater than a second preset value, determining the clarity state of the lane centerline to be the first state; when the lateral offset is greater than the first preset value, and / or the length change is greater than the second preset value, determining the clarity state of the lane centerline to be the second state.

[0076] That is, as long as either the lateral offset or the length change is greater than a preset value, the clear state of the lane centerline is determined to be the second state; otherwise, the clear state of the lane centerline is determined to be the first state.

[0077] The first preset value and the second preset value can be designed according to actual conditions. For example, the first preset value can be 3m, and the second preset value can be 50%.

[0078] The first state and the second state can be represented by the confidence level of the lane centerline information. For example, a high confidence level represents the first state, and a low confidence level represents the second state. The embodiments of the present application do not limit the specific forms of expression of the first state and the second state.

[0079] Taking the first preset value of 3m and the second preset value of 50% as an example, if the lateral offset is greater than 3m, it means that the vehicle has switched lanes, and the confidence level of the lane centerline information can be determined to be low; if the length is reduced by 50% or more, it means that the vehicle may be temporarily obscured, and the confidence level of the lane centerline information can be determined to be low. Both situations indicate that the lane centerline is unclear.

[0080] In step 103, for each lane, a current target preview point is determined based on the clear state and the initial preview point.

[0081] It is understood that the preview distance of the initial preview point is usually the normal sight distance (for example, 3.6 times the sight distance). The clear state is the first state, indicating that the center line of the corresponding lane is clear. At this time, the initial preview point can be used as the current target preview point, and the current target preview point can be used to better determine the vehicle's driving direction.

[0082] In some embodiments, determining the current target preview point according to the clarity state and the initial preview point includes: when the clarity state is the second state, reducing the preview distance of the initial preview point to obtain the current target preview point.

[0083] It can be understood that the second state, when the clear state is clear, indicates that the centerline of the corresponding lane is unclear. The initial preview distance can be adjusted to a shorter sight distance (e.g., 1x sight distance) to facilitate determining the vehicle's direction of travel based on a preview point closer to the vehicle. This is similar to how, when a person is driving, if the road ahead is unclear, they can navigate based on the characteristics of the nearby lane. By adjusting the preview distance of the preview point, the accuracy of the subsequent safety cost calculation can be improved.

[0084] In step 104 , for each lane, a safety cost is determined based on the vehicle's position information, the current lane centerline information, and the current target preview point; wherein the safety cost is used to represent the risk level of the vehicle entering the lane.

[0085] In step 105 , the vehicle is controlled to enter a lane with the minimum safety cost.

[0086] Among them, the vehicle's location information may include a first location used to represent the vehicle's location at the current moment, a second location that is a preset distance away from the first location, a fourth location used to represent the vehicle's location at a historical moment, etc.

[0087] During the implementation process, a series of parameters related to the safety cost can be determined based on the vehicle's position information, the current lane centerline information and the current target preview point, such as lateral cost, lane curvature cost, steering wheel turning cost, steering wheel consistency cost and multiple other parameters, and then the safety cost can be calculated based on these parameters.

[0088] It can be understood that the safety cost is used to characterize the risk level of a vehicle entering a lane. The smaller the safety cost, the lower the risk level of the vehicle entering the lane, and the safer the vehicle is after selecting the lane.

[0089] The embodiment of the present application determines the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located; for each lane, the clarity state of the lane centerline is determined based on the lane's historical lane centerline information at historical moments and the current lane centerline information; the current target preview point is determined based on the clarity state and the initial preview point; the safety cost is determined based on the vehicle's position information, the current lane centerline information, and the current target preview point; wherein the safety cost is used to characterize the risk level of the vehicle entering the lane; and the vehicle is controlled to enter the lane with the lowest safety cost. Since the clarity state of the lane centerline will change in scenarios with limited field of view, after determining the target preview point using the clarity state of the lane centerline, the safety cost of each lane is calculated based on the target preview point, thereby ensuring the safety of the vehicle after selecting a lane in scenarios with limited field of view.

[0090] Figure 2 Shown Figure 1 Detailed diagram of step 104. Figure 2 As shown, in some embodiments, step 104 may include the following sub-steps:

[0091] Step 201, determining the lateral cost based on the vehicle's position information and the current lane centerline information;

[0092] Step 202: Determine the lane curvature cost based on the current lane centerline information;

[0093] Step 203, determining the steering cost based on the position information and the current target preview point;

[0094] Step 204: determining a steering wheel consistency cost based on the position information, the current target preview point, and the lane's historical target preview points at historical moments;

[0095] Step 205 : Determine the safety cost based on the lateral cost, the lane curvature cost, the steering wheel cost, and the steering wheel consistency cost.

[0096] In step 201, the position information includes a first position for representing the position of the vehicle at the current moment and a second position that is a preset distance away from the first position. The current lane centerline information includes a third position for representing the position of the lane centerline at the current moment. The lateral cost is determined based on the vehicle's position information and the current lane centerline information, including: determining a first lateral deviation based on the first position and the third position; determining a second lateral deviation based on the second position and the third position; and obtaining a lateral cost by weighted summation of the first lateral deviation and the second lateral deviation.

[0097] Figure 3 Shown Figure 2 Schematic diagram of step 201 in FIG. Figure 3As shown, the first lateral deviation is ego_dis, the second lateral deviation is heading_dis, and the lateral cost LatCost can be calculated according to the following formula 1:

[0098] LatCost=w_ego×ego_dis+w_heading×heading_dis Formula 1;

[0099] Among them, w_ego is the weight of the first lateral deviation, and w_heading is the weight of the second lateral deviation.

[0100] During implementation, the weight of the first lateral deviation may be greater than the weight of the second lateral deviation. For example, the weight of the first lateral deviation may be set to 0.6, and the weight of the second lateral deviation may be set to 0.4.

[0101] In step 202, the current lane centerline information includes the curvature of the lane centerline at the current moment. Determining the lane curvature cost based on the current lane centerline information includes: determining the lane curvature cost based on the curvature difference between the maximum curvature and the minimum curvature among the curvatures of the lane centerlines of each lane at the current moment.

[0102] It can be understood that the current lane centerline information of each lane includes the curvature of the corresponding lane centerline at the current moment. Taking the case where the vehicle is currently traveling on a three-lane road as an example, the three lanes correspond to the three current lane centerline curvatures respectively. The maximum curvature and the minimum curvature are selected from them, and then the lane curvature cost is determined based on the curvature difference between the maximum curvature and the minimum curvature.

[0103] The lane curvature cost CurveCost can be calculated according to the following formula 2:

[0104] CurveCost=w_curve×(max_curve–min_curve) Formula 2;

[0105] Among them, w_curve is the curvature weight, max_curve is the maximum curvature, and min_curve is the minimum curvature.

[0106] During implementation, considering that the curvature is usually small, the curvature weight needs to take a larger value, for example, it can be set to 1000.

[0107] In step 203, the position information includes a first position for representing the position of the vehicle at the current moment. The steering wheel steering cost is determined based on the position information and the current target preview point, including: determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; and weightedly summing the angle difference between the first steering wheel angle and the second steering wheel angle with the second steering wheel angle to obtain the steering wheel steering cost.

[0108] It can be understood that the first steering wheel angle represents the steering wheel angle of the vehicle when it is in the first position; the second steering wheel angle represents the steering wheel angle required to track the current target preview point on the center line of the lane from the first position, that is, the return cost; the angle difference between the first steering wheel angle and the second steering wheel angle is the required angle cost. The smaller the angle difference, the smaller the steering wheel must be turned to reach the lane where the current target preview point is located.

[0109] The steering wheel steering cost SteerCost can be calculated according to the following formula three:

[0110] SteerCost=w_steer_angle×pp_reference_steer+w_delta_steer×delta_steer Formula 3;

[0111] Among them, w_steer_angle is the weight of the second steering wheel angle, pp_reference_steer is the second steering wheel angle, w_delta_steer is the weight of the angle difference, and delta_steer is the angle difference.

[0112] During the implementation process, considering that it is more desirable for the vehicle to return to the center during driving, the weight of the second steering wheel angle can be greater than the weight of the angle difference. For example, the weight of the second steering wheel angle can be set to 0.6, and the weight of the angle difference can be set to 0.4.

[0113] The second steering wheel angle corresponding to the current target preview point can be calculated using the "Pure Pursuit method". The principle is that the vehicle can turn the steering wheel at a fixed angle to reach the preview point (regardless of the direction in which it reaches the preview point).

[0114] Figure 4 The figure shows the calculation principle of the second steering wheel angle corresponding to the current target preview point. Figure 4As shown in the figure, under the premise that the front wheel angle remains unchanged, the vehicle moves in a circle with the center of rotation as the center, and the radius of the circle is recorded as R. At this time, the center of rotation, the reference point of the vehicle (for example, the center of the rear axle), and the current target preview point (referred to as the preview point) form an isosceles triangle. The line between the reference point and the preview point is the base of the isosceles triangle, and its length is recorded as l. d The angle between the base of the isosceles triangle and the longitudinal axis of the vehicle is denoted by α. Since the longitudinal axis of the vehicle is always tangent to the arc, the angle opposite the base of the isosceles triangle is 2α.

[0115] According to the law of sine, we can get the following formula 4:

[0116]

[0117] Where R is the radius, l d is the distance from the reference point to the preview point, and α is the angle between the line between the reference point and the preview point and the longitudinal axis of the vehicle.

[0118] According to the bicycle model, the turning radius and the front wheel angle have the following relationship:

[0119]

[0120] Where φ is the front wheel turning angle and l is the wheelbase.

[0121] Combining Formula 4 and Formula 5, we can get the following Formula 6:

[0122]

[0123] Formula 6 can also be rewritten in terms of lateral error, as shown in Formula 7. This calculation form is suitable for the ego vehicle coordinate system, that is, all coordinates are expressed in the ego vehicle local coordinate system:

[0124]

[0125] Among them, y e It is the vertical distance from the center point of the front axle to the preview point.

[0126] In step 204, the position information includes a first position for representing the position of the vehicle at a current moment and a fourth position for representing the position of the vehicle at a historical moment. Based on the position information, the current target preview point and the historical target preview point of the lane at a historical moment, determining the steering wheel consistency cost includes: determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; determining a third steering wheel angle corresponding to the fourth position and a fourth steering wheel angle corresponding to the historical target preview point; determining the angle difference between the first steering wheel angle and the second steering wheel angle as a first angle difference; determining the angle difference between the third steering wheel angle and the fourth steering wheel angle as a second angle difference; and multiplying the difference between the first angle difference and the second angle difference by a preset weight to obtain the steering wheel consistency cost.

[0127] It is understandable that the steering wheel consistency cost can be obtained based on the current moment's steering angle difference and the previous moment's steering angle difference. In implementation, the previous moment can be the previous moment, and accordingly, the steering wheel consistency cost can be obtained based on the current moment's steering angle difference and the previous moment's steering angle difference.

[0128] As described above, the first steering wheel angle represents the steering wheel angle of the vehicle at the first position; the second steering wheel angle represents the steering wheel angle required to track the current target preview point on the lane centerline from the first position. Similarly, the third steering wheel angle represents the steering wheel angle of the vehicle at the fourth position; and the fourth steering wheel angle represents the steering wheel angle required to track the historical target preview point from the fourth position.

[0129] The steering wheel consistency cost CoherenceCost can be calculated according to the following formula 8:

[0130] CoherenceCost=w_coherence×(curr_steer-referenc_steer) Formula 8;

[0131] Where w_coherence is the consistency weight, curr_steer is the first turning angle difference, and referenc_steer is the second turning angle difference.

[0132] During implementation, considering that the angle difference of consistency is generally small, the consistency weight can be set to 2.

[0133] In step 205 , after obtaining the lateral cost LatCost, the lane curvature cost CurveCost, the steering wheel cost SteerCost, and the steering wheel consistency cost CoherenceCost, these four parameters may be normalized first and then summed to obtain the safety cost.

[0134] The safety cost of each lane is calculated using the same method. The lane with the smallest safety cost is the most suitable lane.

[0135] By dynamically calculating the safety cost of vehicle lane selection from multiple dimensions, the most suitable lane is determined in real time, which not only takes into account the safety of vehicle lane selection but also improves driving comfort.

[0136] Figure 5 FIG2 shows a flow chart of a vehicle lane selection control method according to other embodiments of the present application. Figure 5 As shown, another vehicle lane selection control method is provided, which may include the following steps:

[0137] Step 501, determining the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located;

[0138] Step 502: For each lane, determine the lateral offset and length change of the lane centerline based on the lane's historical lane centerline information at a historical moment and the current lane centerline information, and determine the clear state of the lane centerline based on the lateral offset and length change.

[0139] Step 503: For each lane, if the clear state is the second state indicating that the lane centerline is unclear, reduce the preview distance of the initial preview point to obtain a current target preview point.

[0140] Step 504: For each lane, determine the lateral cost, lane curvature cost, steering wheel turning cost, and steering wheel consistency cost based on the vehicle's position information, the current lane centerline information, and the current target preview point. Furthermore, determine the safety cost based on the lateral cost, lane curvature cost, steering wheel turning cost, and steering wheel consistency cost.

[0141] Step 505: Control the vehicle to enter the lane with the lowest safety cost.

[0142] The embodiment of the present application determines the current lane centerline information of each lane at the current moment based on the lane information of the road on which the vehicle is located; for each lane, determines the lateral offset and length change of the lane centerline based on the lane's historical lane centerline information at previous moments and the current lane centerline information, and determines the lane centerline clarity state based on the lateral offset and length change; when the clarity state is a second state representing an unclear lane centerline, reduces the preview distance of the initial preview point to obtain a current target preview point; determines the lateral cost, lane curvature cost, steering wheel turning cost, and steering wheel consistency cost based on the vehicle's position information, the current lane centerline information, and the current target preview point; and determines the safety cost based on the lateral cost, lane curvature cost, steering wheel turning cost, and steering wheel consistency cost; and controls the vehicle to enter the lane with the lowest safety cost. By adjusting the current target preview point in real time based on the lane centerline clarity state, the most suitable lane can be determined in real time. By calculating the safety cost from multiple dimensions, including the lateral cost, lane curvature cost, steering wheel turning cost, and steering wheel consistency cost, and selecting a lane based on the calculated safety cost, driving comfort during lane selection is improved.

[0143] The following describes an embodiment of the device of the present application, which can be used to execute the vehicle lane selection control method in the above-mentioned embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the vehicle lane selection control method in the above-mentioned embodiment of the present application.

[0144] See also Figure 6 , shows a block diagram of the vehicle lane selection control device in an embodiment of the present application.

[0145] like Figure 6 As shown, the vehicle lane selection control device of the embodiment of the present application includes: a centerline information determination module 601, a centerline state determination module 602, a preview point determination module 603, a safety cost determination module 604 and a lane updating module 605, wherein the centerline information determination module 601 is used to determine the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located; the centerline state determination module 602 is used to determine the clarity state of the lane centerline of the lane based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information; the preview point determination module 603 is used to determine the current target preview point for each lane based on the clarity state and the initial preview point; the safety cost determination module 604 is used to determine the safety cost for each lane based on the vehicle's position information, the current lane centerline information and the current target preview point; wherein the safety cost is used to characterize the risk level of the vehicle entering the lane; and the lane updating module 605 is used to control the vehicle to enter the lane with the minimum safety cost.

[0146] In some embodiments, based on the aforementioned scheme, the centerline state determination module 602 is also used to determine the lateral offset and length change of the lane centerline based on the historical lane centerline information and current lane centerline information of the lane at historical moments; and determine the clarity state of the lane centerline based on the lateral offset and length change.

[0147] In some embodiments, based on the aforementioned solution, the time difference between the historical moment and the current moment is less than or equal to a preset time length.

[0148] In some embodiments, based on the aforementioned scheme, the historical moment is the moment before the current moment, the historical lane centerline information includes the position of the initial preview point on the lane centerline at the previous moment and the length of the lane centerline at the previous moment, and the current lane centerline information includes the position of the initial preview point on the lane centerline at the current moment and the length of the lane centerline at the current moment. The centerline state determination module 602 is also used to determine the lateral offset of the lane centerline based on the position of the initial preview point on the lane centerline at the previous moment and the position of the initial preview point on the lane centerline at the current moment; and determine the length change of the lane centerline based on the length of the lane centerline at the previous moment and the length of the lane centerline at the current moment.

[0149] In some embodiments, based on the aforementioned scheme, the clear state includes a first state for characterizing that the lane centerline is clear and a second state for characterizing that the lane centerline is unclear. The centerline state determination module 602 is also used to determine that the clear state of the lane centerline is the first state when the lateral offset is not greater than a first preset value and the length change is not greater than a second preset value; and to determine that the clear state of the lane centerline is the second state when the lateral offset is greater than the first preset value and / or the length change is greater than the second preset value.

[0150] In some embodiments, based on the aforementioned scheme, the clear state includes a first state for characterizing that the lane centerline is clear and a second state for characterizing that the lane centerline is unclear. The preview point determination module 603 is also used to reduce the preview distance of the initial preview point when the clear state is the second state to obtain the current target preview point.

[0151] In some embodiments, based on the aforementioned scheme, the safety cost determination module 604 is also used to determine the lateral cost based on the vehicle's position information and the current lane centerline information; determine the lane curvature cost based on the current lane centerline information; determine the steering wheel steering cost based on the position information and the current target preview point; determine the steering wheel consistency cost based on the position information, the current target preview point and the historical target preview point of the lane at a historical moment; determine the safety cost based on the lateral cost, lane curvature cost, steering wheel steering cost and steering wheel consistency cost.

[0152] In some embodiments, based on the aforementioned scheme, the position information includes a first position for representing the position of the vehicle at the current moment and a second position that is a preset distance away from the first position, and the current lane centerline information includes a third position for representing the position of the lane centerline at the current moment. The safety cost determination module 604 is also used to determine a first lateral deviation based on the first position and the third position; determine a second lateral deviation based on the second position and the third position; and weightedly sum the first lateral deviation and the second lateral deviation to obtain a lateral cost.

[0153] In some embodiments, based on the aforementioned scheme, the current lane centerline information includes the curvature of the lane centerline at the current moment, and the safety cost determination module 604 is also used to determine the lane curvature cost based on the curvature difference between the maximum curvature and the minimum curvature among the curvatures of the lane centerlines of each lane at the current moment.

[0154] In some embodiments, based on the aforementioned scheme, the position information includes a first position used to characterize the position of the vehicle at the current moment, and the safety cost determination module 604 is also used to determine a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; the angle difference between the first steering wheel angle and the second steering wheel angle is weighted and summed with the second steering wheel angle to obtain the steering wheel steering cost.

[0155] In some embodiments, based on the aforementioned scheme, the position information includes a first position for representing the position of the vehicle at the current moment and a fourth position for representing the position of the vehicle at the historical moment. The safety cost determination module 604 is also used to determine a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; determine a third steering wheel angle corresponding to the fourth position and a fourth steering wheel angle corresponding to the historical target preview point; determine the angle difference between the first steering wheel angle and the second steering wheel angle as a first angle difference; determine the angle difference between the third steering wheel angle and the fourth steering wheel angle as a second angle difference; and multiply the difference between the first angle difference and the second angle difference by a preset weight to obtain a steering wheel consistency cost.

[0156] Based on the same inventive concept, the embodiment of the present application also provides a vehicle lane selection control device, referring to Figure 7 , shows a structural schematic diagram of a vehicle lane selection control device in an embodiment of the present application, wherein the vehicle lane selection control device includes one or more memories 704, one or more processors 702, and at least one computer program (computer program instruction) stored in the memory 704 and executable on the processor 702. When the processor 702 executes the computer program, the method described above is implemented.

[0157] Among them, Figure 7In the embodiment of the present invention, a bus architecture (represented by bus 700) is shown. Bus 700 may include any number of interconnected buses and bridges, and bus 700 links together various circuits including one or more processors represented by processor 702 and memory represented by memory 704. Bus 600 may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 705 provides an interface between bus 700 and receiver 701 and transmitter 703. Receiver 701 and transmitter 703 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 702 is responsible for managing bus 700 and general processing, while memory 704 may be used to store data used by processor 702 when performing operations.

[0158] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, in which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor is prompted to implement the steps of the method as described above.

[0159] Based on the same inventive concept, an embodiment of the present application provides a computer program product, including a computer program. When the computer program product is executed by a processor, it prompts the processor to implement the steps of the method described above.

[0160] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored as one or more instructions or codes on or transmitted via a computer-readable medium. Other examples and implementations are within the scope and spirit of this application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwiring, or a combination of any of these. Furthermore, the functional units may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit.

[0161] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0162] The units described as separate components may or may not be physically separate, and the components of the control device may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0163] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store computer program instructions.

[0164] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. Various modifications and variations are possible for those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of the claims of the present application.

Claims

1. A vehicle lane selection control method, characterized in that: include: Determine the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located; For each lane, determining a lane centerline clarity state of the lane based on historical lane centerline information of the lane at a historical moment and the current lane centerline information; For each lane, determining a current target preview point based on the clear state and the initial preview point; For each lane, a safety cost is determined based on the vehicle's position information, the current lane centerline information, and the current target preview point; wherein the safety cost is used to represent the risk level of the vehicle entering the lane; Control vehicles to enter the lane with the lowest safety cost.

2. The vehicle lane selection control method according to claim 1, characterized in that: The determining of a clear state of the lane centerline of the lane based on historical lane centerline information of the lane at a historical moment and the current lane centerline information includes: Determining a lateral offset and a length change of a lane centerline based on historical lane centerline information of the lane at a historical moment and the current lane centerline information; The clarity state of the lane centerline is determined based on the lateral offset and the length change.

3. The vehicle lane selection control method according to claim 2, characterized in that: The time difference between the historical moment and the current moment is less than or equal to a preset time length.

4. The vehicle lane selection control method according to claim 3, characterized in that: The historical moment is the moment before the current moment, the historical lane centerline information includes the position of the initial preview point on the lane centerline at the previous moment and the length of the lane centerline at the previous moment, the current lane centerline information includes the position of the initial preview point on the lane centerline at the current moment and the length of the lane centerline at the current moment, and determining the lateral offset and length change of the lane centerline based on the historical lane centerline information of the lane at the historical moment and the current lane centerline information includes: Determine the lateral offset of the lane centerline based on the position of the initial preview point on the lane centerline at the previous moment and the position of the initial preview point on the lane centerline at the current moment; The length change of the lane centerline is determined based on the length of the lane centerline at the previous moment and the length of the lane centerline at the current moment.

5. The vehicle lane selection control method according to claim 2, characterized in that: The clear state includes a first state for indicating that the lane centerline is clear and a second state for indicating that the lane centerline is unclear. The determining of the clear state of the lane centerline according to the lateral offset and the length change includes: When the lateral offset is not greater than a first preset value and the length change is not greater than a second preset value, determining that the clear state of the lane centerline is the first state; When the lateral offset is greater than the first preset value, and / or the length change is greater than the second preset value, the clear state of the lane centerline is determined to be the second state.

6. The vehicle lane selection control method according to claim 1, characterized in that: The clear state includes a first state for indicating that the lane centerline is clear and a second state for indicating that the lane centerline is unclear. The determining of the current target preview point based on the clear state and the initial preview point includes: When the clear state is the second state, the preview distance of the initial preview point is reduced to obtain the current target preview point.

7. The vehicle lane selection control method according to claim 1, characterized in that: The determining of the safety cost according to the vehicle position information, the current lane centerline information, and the current target preview point includes: Determining a lateral cost based on the vehicle's position information and the current lane centerline information; Determining a lane curvature cost based on the current lane centerline information; Determining a steering wheel steering cost based on the position information and the current target preview point; Determining a steering wheel consistency cost based on the position information, the current target preview point, and historical target preview points of the lane at historical moments; The safety cost is determined according to the lateral cost, the lane curvature cost, the steering wheel cost, and the steering wheel consistency cost.

8. The vehicle lane selection control method according to claim 7, characterized in that: The position information includes a first position for representing a current position of the vehicle and a second position that is a preset distance away from the first position. The current lane centerline information includes a third position for representing a current position of the lane centerline. Determining the lateral cost based on the vehicle position information and the current lane centerline information includes: determining a first lateral deviation based on the first position and the third position; determining a second lateral deviation based on the second position and the third position; The first lateral deviation and the second lateral deviation are weightedly summed to obtain the lateral cost.

9. The vehicle lane selection control method according to claim 7, characterized in that: The current lane centerline information includes the curvature of the lane centerline at the current moment. The determining of the lane curvature cost based on the current lane centerline information includes: The lane curvature cost is determined according to a curvature difference between a maximum curvature and a minimum curvature among curvatures of lane centerlines of each lane at a current moment.

10. The vehicle lane selection control method according to claim 7, characterized in that: The position information includes a first position for representing the position of the vehicle at a current moment, and determining the steering cost according to the position information and the current target preview point includes: Determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; The steering wheel steering cost is obtained by performing a weighted summation of a steering wheel angle difference between the first steering wheel angle and the second steering wheel angle and the second steering wheel angle.

11. The vehicle lane selection control method according to claim 7, characterized in that: The position information includes a first position for representing a current position of the vehicle and a fourth position for representing a historical position of the vehicle. Determining a steering wheel consistency cost based on the position information, the current target preview point, and historical target preview points of the lane at historical moments includes: Determining a first steering wheel angle corresponding to the first position and a second steering wheel angle corresponding to the current target preview point; determining a third steering wheel angle corresponding to the fourth position and a fourth steering wheel angle corresponding to the historical target preview point; determining a steering angle difference between the first steering wheel angle and the second steering wheel angle as a first steering angle difference; determining a steering angle difference between the third steering wheel angle and the fourth steering wheel angle as a second steering angle difference; The steering wheel consistency cost is obtained by multiplying the difference between the first steering angle difference and the second steering angle difference by a preset weight.

12. A vehicle lane selection control device, characterized in that: include: A centerline information determination module is used to determine the current lane centerline information of each lane at the current moment based on the lane information of the road where the vehicle is located; a centerline state determination module, configured to determine, for each lane, a lane centerline clear state of the lane based on historical lane centerline information of the lane at a historical moment and the current lane centerline information; A preview point determination module is used to determine, for each lane, a current target preview point based on the clear state and the initial preview point; a safety cost determination module, configured to determine, for each lane, a safety cost based on the vehicle's position information, the current lane centerline information, and the current target preview point; wherein the safety cost is used to represent the risk level of the vehicle entering the lane; The lane update module is used to control the vehicle to enter the lane with the lowest safety cost.

13. A vehicle lane selection control device, comprising a processor and a memory, characterized in that: The memory stores computer program instructions that can be executed by the processor, and when the processor executes the computer program instructions, the steps of the method according to any one of claims 1 to 11 are implemented.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer program instructions, which, when executed by a processor, prompt the processor to implement the steps of the method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, causes the processor to implement the steps of the method according to any one of claims 1 to 11.

Images