A method, apparatus, electronic device, and storage medium for determining the feasible lane-changing region.

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for determining a feasible lane-changing region. Relating to the field of road safety technology, the method includes: acquiring first and second motion information of the vehicle itself and surrounding vehicles within a preset future time period; determining at least one longitudinal displacement interval of the vehicle based on the first motion information, the vehicle's current speed, and road speed limit information; determining a lane-changing space based on the second motion information; and determining a target feasible lane-changing region based on the longitudinal displacement interval and the lane-changing space. The solution provided by this invention can accurately and safely determine the target feasible lane-changing region, thereby meeting the lane-changing needs of vehicles and effectively avoiding the problem of missing lane-changing opportunities.

Description

Technical Field

[0001] This invention relates to the field of road safety technology, and in particular to a method, apparatus, electronic device, and storage medium for determining lane-changing feasible regions. Background Technology

[0002] With the rapid development of communication and artificial intelligence technologies, connectivity and intelligence have become the future development direction of the automotive industry. Lane changing, as a common driving behavior, carries significant risks due to the need to consider the actual conditions of multiple lanes. Furthermore, unreasonable lane changing can not only affect the normal passage of other vehicles but may even cause serious traffic accidents, greatly impacting road efficiency and the safety of road users.

[0003] In existing research, vehicles can obtain information about surrounding vehicles through cameras, millimeter-wave radar, lidar, etc., and make a judgment on whether to perform a lane change operation based on the information of their own vehicle and the surrounding vehicles. If a lane change operation is to be performed, a smooth, collision-free trajectory that meets the vehicle dynamics constraints is planned, and the vehicle changes lanes according to the trajectory.

[0004] However, most existing studies simplify the motion of surrounding vehicles to uniform speed or uniform acceleration, which differs significantly from actual traffic flow. Furthermore, when a vehicle attempts to change lanes but the clearance in the target lane is too small to meet the lane-changing conditions, existing studies tend to abandon the lane-changing operation and passively wait for the next opportunity. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for determining lane-changing feasible regions, which can accurately and safely determine the target lane-changing feasible region, thereby meeting the lane-changing needs of vehicles and effectively avoiding the problem of missing lane-changing opportunities.

[0006] According to one aspect of the present invention, a method for determining the feasible region of lane changing is provided, comprising:

[0007] The vehicle acquires first and second motion information of its own vehicle and surrounding vehicles within a preset time period in the future.

[0008] Based on the first motion information, the vehicle's current speed, and the road speed limit information, determine at least one longitudinal displacement range for the vehicle.

[0009] Based on the second motion information, determine the lane-changing space;

[0010] Based on the longitudinal displacement range and the lane-changing space, the feasible domain for the target lane change is determined.

[0011] Optionally, the first motion information includes at least one set of motion data, each set of motion data including the final vehicle speed, acceleration, and deceleration;

[0012] Obtain the vehicle's initial motion information within a preset future time period, including:

[0013] Determine the vehicle's final speed range, acceleration range, and deceleration range within a preset time period in the future;

[0014] According to the preset accuracy, at least one end vehicle speed, at least one acceleration, and at least one deceleration are collected in the end vehicle speed range, acceleration range, and deceleration range, respectively, and motion data are generated.

[0015] Optionally, the first motion information includes the same number of motion data as the number of longitudinal displacement intervals; the road speed limit information includes the maximum and minimum road speeds; and the longitudinal displacement intervals include the upper and lower limits of longitudinal displacement.

[0016] For any set of motion data, based on the motion data, the vehicle's current speed, and road speed limit information, determine the longitudinal displacement range, including:

[0017] The upper limit of longitudinal displacement is determined based on the maximum speed of the road, the preset time period, acceleration, deceleration, the destination speed, and the current speed of the vehicle itself.

[0018] The lower limit of longitudinal displacement is determined based on the minimum road speed, the preset time period, acceleration, deceleration, the final speed, and the current speed of the vehicle itself.

[0019] Optional, upper limit of longitudinal displacement

[0020]

[0021] Lower limit of longitudinal displacement

[0022]

[0023] Among them, V max-lim V is the maximum speed limit on the road. min-lim The minimum speed on the road, t future For any point within a pre-defined future time period, a dec For deceleration, a acc For acceleration, V fin V0 represents the destination speed, and V0 represents the current speed of the vehicle itself.

[0024] Optionally, obtain secondary motion information of surrounding vehicles within a preset future time period, including:

[0025] Get the speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period;

[0026] The speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period are input into the pre-trained car-following model to obtain the current acceleration of surrounding vehicles.

[0027] Predict the second motion information based on the current acceleration of surrounding vehicles.

[0028] Optional methods for training the car-following model include:

[0029] Obtain the traffic dataset and filter the training dataset from it;

[0030] The long short-term memory (LSTM) neural network model was trained using the training dataset to obtain the car-following model.

[0031] Optionally, the surrounding vehicles include the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. The second motion information includes the motion information of the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. Among them, the first vehicle is the vehicle in front of the current vehicle in the current lane, the second vehicle is the vehicle in front of the current vehicle in the target lane, the third vehicle is the vehicle in front of the second vehicle in the target lane, the fourth vehicle is the vehicle behind the current vehicle in the target lane, and the fifth vehicle is the vehicle behind the fourth vehicle in the target lane. The lane-changing space includes the first space, the second space, and the third space.

[0032] Based on the second motion information, determine the lane-changing space, including:

[0033] The first space is determined based on the motion information of the first vehicle, the motion information of the second vehicle, and the motion information of the third vehicle;

[0034] The second space is determined based on the motion information of the first vehicle, the second vehicle, and the fourth vehicle;

[0035] The third space is determined based on the motion information of the fourth vehicle and the fifth vehicle.

[0036] Optional, first space

[0037] Second Space

[0038] Third Space

[0039] Where t0 is the current time, tfuture For any point within a pre-defined time period in the future For in t future First vehicle L c The achievable longitudinal position, For in t future Second vehicle L at time d The achievable longitudinal position, For in t future Third vehicle H at time d The achievable longitudinal position, For in t future Fourth vehicle F at time d The achievable longitudinal position, For in t future Fifth vehicle T at time d The achievable longitudinal position, When vehicle M arrives at the corresponding space, it should interact with the first vehicle L. c Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with the second vehicle L. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with a third vehicle H. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle F, the fourth vehicle. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle T, the fifth vehicle. d Maintain a safe distance.

[0040] Optionally, based on the longitudinal displacement range and the lane-changing space, the target lane-changing feasible region is determined, including:

[0041] Determine whether there is a longitudinal displacement interval that is entirely located within the lane-changing space among all longitudinal displacement intervals;

[0042] If it exists, the longitudinal displacement range that is completely within the lane-changing space will be taken as the candidate lane-changing feasible region.

[0043] The target lane-changing feasible region is determined from at least one candidate lane-changing feasible region.

[0044] Optionally, the target lane-changing feasible region is determined from at least one candidate lane-changing feasible region, including:

[0045] Construct at least one sub-function and determine the objective function based on the sub-function;

[0046] Solve the objective function for each candidate lane-changing feasible region, and take the candidate lane-changing feasible region with the smallest value that satisfies the objective function as the target lane-changing feasible region.

[0047] Optionally, the number of sub-functions is 3;

[0048] Objective function J = ω1J success +ω2J comfort +ω3J impact ;

[0049] Among them, J success Find a success rate subfunction for the feasible region. s max s represents the upper limit of the longitudinal displacement of the candidate lane-changing feasible region. min Let J be the lower limit of the longitudinal displacement of the candidate lane-changing feasible region, where ε is a constant. comfort For lane change comfort subfunction, V fin V0 is the destination speed, V0 is the current speed of the vehicle, and t is the destination speed. future For any point within a pre-defined future time period, J impact J is the traffic impact sub-function. impact =|V fin -V front |,V front To determine the speed of the vehicle ahead in the lane-changing space, ω1, ω2, and ω3 are the sub-functions J representing the success rate of finding the feasible region. success Lane change comfort subfunction J comfort Traffic impact sub-function J impact The weighting coefficients are ω1+ω2+ω3=1, and the values ​​of ω1, ω2, and ω3 are all greater than 0 and less than 1.

[0050] Optionally, after determining the feasible region for the target lane change, the following may also be included:

[0051] The vehicle speed-time curve is established based on a cubic polynomial, and the vehicle is controlled to change lanes within the target lane-changing feasible region according to the vehicle speed-time curve.

[0052] According to another aspect of the present invention, an apparatus for determining a lane-changing feasible region is provided, comprising: a data acquisition module, a prediction module, a calculation module, and a determination module; wherein,

[0053] The data acquisition module is used to obtain the first motion information of the vehicle within a preset time period in the future;

[0054] The prediction module is used to obtain the second motion information of surrounding vehicles within a preset time period in the future;

[0055] The calculation module is used to determine at least one longitudinal displacement range of the vehicle based on the first motion information, the vehicle's current speed and the road speed limit information; and to determine the lane-changing space based on the second motion information.

[0056] The determination module is used to determine the feasible domain of the target lane change based on the longitudinal displacement range and the lane change space.

[0057] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0058] At least one processor; and

[0059] A memory that is communicatively connected to at least one processor; wherein,

[0060] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the method for determining the lane-changing feasible region according to any embodiment of the present invention.

[0061] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute a method for determining the lane-switching feasible region according to any embodiment of the present invention.

[0062] The technical solution of this invention first acquires first and second motion information of the vehicle itself and surrounding vehicles within a preset future time period. Then, it combines this information with the vehicle's current speed and road speed limit information to determine at least one longitudinal displacement range and lane-changing space for the vehicle, thereby further determining the target lane-changing feasible region. Since the second motion information is based on predictions of the current acceleration of surrounding vehicles, it can more accurately reflect the motion state of surrounding vehicles, thus enabling a more accurate and safer determination of the target lane-changing feasible region to meet the vehicle's lane-changing needs. Simultaneously, by considering the influence of lane-changing space in the process of determining the target lane-changing feasible region, the problem of missing lane-changing opportunities can be effectively avoided.

[0063] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0064] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0065] Figure 1 This is a flowchart illustrating a method for determining the feasible region of lane changing according to Embodiment 1 of the present invention.

[0066] Figure 2This is a flowchart illustrating a method for determining a lane-changing feasible region according to Embodiment 2 of the present invention.

[0067] Figure 3 This is a schematic diagram of a longitudinal displacement range provided in Embodiment 2 of the present invention;

[0068] Figure 4 This is a basic structural diagram of an LSTM neural network model provided in Embodiment 2 of the present invention;

[0069] Figure 5 This is a schematic diagram of a vehicle, surrounding vehicles, and lane-changing space provided in Embodiment 2 of the present invention;

[0070] Figure 6 This is a schematic diagram of the structure of a lane-changing feasible region determination device provided in Embodiment 3 of the present invention;

[0071] Figure 7 This is a schematic diagram of another device for determining the feasible region of lane changing provided in Embodiment 3 of the present invention;

[0072] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0073] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0074] It should be noted that the terms "first," "second," "target," "candidate," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0075] Example 1

[0076] Figure 1This is a flowchart illustrating a method for determining a lane-changing feasible region according to Embodiment 1 of the present invention. This embodiment is applicable to situations where a lane-changing feasible region is determined during vehicle driving. The method can be executed by a lane-changing feasible region determining device, which can be implemented in hardware and / or software. This device can be configured in an electronic device (such as a processor or other computer equipment integrated in a vehicle). Figure 1 As shown, the method includes:

[0077] S110: Obtain the first motion information and the second motion information of the vehicle itself and surrounding vehicles within a preset time period in the future.

[0078] Surrounding vehicles refer to vehicles located around your vehicle, such as vehicles in front and behind you in your current lane (hereinafter referred to as the current lane), as well as vehicles in the lanes to the left and right of the current lane. The future preset time period is the period from the current moment to a future moment, representing the time during which your vehicle may perform a lane-changing operation. The length of the future preset time period can be set according to actual needs.

[0079] The first motion information includes at least one set of motion data, each set of motion data including the final vehicle speed, acceleration, and deceleration. Specifically, the method for "obtaining the first motion information of the vehicle within a preset future time period" in step S110 may include the following two steps:

[0080] Step a1: Determine the destination speed range, acceleration range, and deceleration range of your vehicle within a preset time period in the future.

[0081] Step a2: According to the preset accuracy, collect at least one end vehicle speed, at least one acceleration, and at least one deceleration in the end vehicle speed range, acceleration range, and deceleration range respectively, and generate motion data.

[0082] For example, suppose the vehicle's final speed range within a preset time period is 20 to 40 km / h, and its acceleration range is 1 to 10 m / s². 2 The deceleration range is -10 to -1 m / s². 2 The preset precision for the endpoint speed was 5, and the preset precision for acceleration and deceleration was 3. Five endpoint speeds were collected within the endpoint speed range: 20 km / h, 25 km / h, 30 km / h, 35 km / h, and 40 km / h. Four accelerations were collected within the acceleration range: 1 m / s². 2 4m / s 2 7m / s 2 and 10m / s 2 Four decelerations of -10 m / s were collected within the deceleration range.2 -7m / s 2 -4m / s 2 and -1m / s 2 The collected terminal vehicle speed, acceleration, and deceleration were arranged and combined to form a total of 80 sets of motion data (5*4*4). These 80 sets of motion data constitute the final first set of motion information.

[0083] Specifically, the method for "obtaining the second motion information of surrounding vehicles within a preset time period in step S110" may include the following three steps:

[0084] Step b1: Obtain the speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period.

[0085] The preset time period is the period from a certain point in the past to the current point. The length of the preset time period can be set according to actual needs.

[0086] Step b2: Input the speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period into the pre-trained car-following model to obtain the current acceleration of surrounding vehicles.

[0087] The car-following model is trained based on a Long Short-Term Memory (LSTM) neural network model. In one embodiment, the present invention can pre-train the LSTM neural network model, thereby directly obtaining the pre-trained car-following model in the process of determining the current acceleration of surrounding vehicles, so as to improve the efficiency of determining the lane-changing feasible region.

[0088] Specifically, methods for training a car-following model may include: acquiring a traffic dataset and selecting a training dataset from the traffic dataset; and using the training dataset to train an LSTM neural network model to obtain a car-following model.

[0089] Traffic datasets can be selected from open-source datasets, such as the Next Generation Simulation (NGSIM) traffic dataset. The speed of vehicles, the relative speed and relative distance between the vehicle and the vehicle in front are selected from the NGSIM traffic dataset to meet the criteria as training datasets. The LSTM neural network model is then trained using the training datasets to obtain the car-following model.

[0090] By inputting the speeds of surrounding vehicles over a preset time period, the relative speeds of surrounding vehicles to the vehicles in front over the preset time period, and the relative distances between surrounding vehicles and the vehicles in front, a pre-trained car-following model can be obtained to determine the current acceleration of surrounding vehicles.

[0091] Step b3: Predict the second motion information based on the current acceleration of surrounding vehicles.

[0092] In one embodiment, the second motion information can be predicted based on the current acceleration of the surrounding vehicles, combined with information such as the current position and speed of the surrounding vehicles.

[0093] S120. Based on the first motion information, the current speed of the vehicle and the road speed limit information, determine at least one longitudinal displacement range of the vehicle.

[0094] The first motion information includes the same number of motion data as the number of longitudinal displacement intervals. For example, in step S110 above, the first motion information includes 80 sets of motion data, and the final determined longitudinal displacement intervals also include 80.

[0095] Road speed limit information includes the maximum and minimum vehicle speeds on the road; the longitudinal displacement range includes the upper and lower limits of longitudinal displacement. Specifically, for any set of motion data, the method in step S120 of "determining the longitudinal displacement range based on the motion data, the vehicle's current speed, and the road speed limit information" can include the following two steps:

[0096] Step c1: Determine the upper limit of longitudinal displacement based on the maximum road speed, the preset time period, acceleration, deceleration, the destination speed, and the current speed of your own vehicle.

[0097] The method for determining the upper limit of longitudinal displacement is as follows: the vehicle accelerates uniformly from its current speed to the maximum speed on the road, and then travels at the maximum speed on the road for a period of time before decelerating uniformly from the maximum speed on the road to the final speed. This process lasts for a preset time period in the future.

[0098] Step c2: Determine the lower limit of longitudinal displacement based on the minimum road speed, the preset time period, acceleration, deceleration, the destination speed, and the current speed of the vehicle itself.

[0099] The method for determining the lower limit of longitudinal displacement is as follows: the vehicle decelerates uniformly from its current speed to the minimum speed on the road, and then travels at the minimum speed on the road for a period of time before accelerating uniformly from the minimum speed on the road to the final speed. This process lasts for a preset time period in the future.

[0100] S130. Determine the lane-changing space based on the second motion information.

[0101] Lane-changing space may include at least one space, and each space may be determined based on the motion relationship of surrounding vehicles associated with that space.

[0102] S140. Determine the feasible domain for the target lane change based on the longitudinal displacement range and the lane change space.

[0103] Specifically, the method for "determining the target lane-changing feasible region based on the longitudinal displacement range and lane-changing space" in step S140 may include the following four steps:

[0104] Step d1: Determine whether there is a longitudinal displacement interval that is completely located within the lane change space among all longitudinal displacement intervals.

[0105] Step d2: If it does not exist, then determine that the feasible domain for the target lane change is empty.

[0106] When the feasible region for lane changing is empty, it means that lane changing is not suitable and we need to wait for the next opportunity to change lanes.

[0107] Step d3: If it exists, the longitudinal displacement interval that is completely within the lane-changing space is taken as the candidate lane-changing feasible region.

[0108] Step d4: Determine the target lane-changing feasible region from at least one candidate lane-changing feasible region.

[0109] Thus, since the second motion information is based on the prediction of the current acceleration of surrounding vehicles, it can more accurately reflect the motion state of surrounding vehicles, thereby enabling a more accurate and safer determination of the target lane-changing feasible region to meet the lane-changing needs of vehicles. At the same time, the influence of lane-changing space on the determination of the target lane-changing feasible region is considered, which can effectively avoid the problem of missing the lane-changing opportunity.

[0110] Example 2

[0111] Figure 2 This is a flowchart illustrating a method for determining a lane-changing feasible region according to Embodiment 2 of the present invention. This embodiment uses an example where surrounding vehicles include a first vehicle, a second vehicle, a third vehicle, a fourth vehicle, and a fifth vehicle, and the lane-changing space includes a first space, a second space, and a third space to describe in detail the method for determining the lane-changing feasible region. Figure 2 As shown, the method includes:

[0112] S201, Obtain the first motion information of your own vehicle within a preset time period in the future.

[0113] The first set of motion information includes at least one set of motion data, each set of motion data including the final vehicle speed, acceleration, and deceleration.

[0114] Specifically, the method for obtaining the first motion information of one's own vehicle within a future preset time period may include: determining the final speed range, acceleration range, and deceleration range of one's own vehicle within the future preset time period; and, according to a preset precision, collecting at least one final speed, at least one acceleration, and at least one deceleration within the final speed range, acceleration range, and deceleration range, respectively, and generating motion data.

[0115] For example, suppose the vehicle's final speed range within a preset time period is 20 to 30 km / h, and its acceleration range is 6 to 10 m / s². 2 The deceleration range is -10 to -6 m / s². 2 The preset accuracy for the endpoint speed was 5, and the preset accuracy for acceleration and deceleration was 2. Within the endpoint speed range, three endpoint speeds were collected: 20 km / h, 25 km / h, and 30 km / h. Within the acceleration range, three accelerations were collected: 6 m / s². 2 8m / s 2 and 10m / s 2 Four decelerations of -10 m / s were collected within the deceleration range. 2 -8m / s 2 and -6m / s 2 The collected terminal vehicle speed, acceleration, and deceleration were arranged and combined to form a total of 27 sets of motion data (3*3*3). These 27 sets of motion data constitute the final first set of motion information.

[0116] S202. Based on the first motion information, the current speed of the vehicle and the road speed limit information, determine at least one longitudinal displacement range of the vehicle.

[0117] The first motion information includes the same number of motion data as the number of longitudinal displacement intervals. For example, in step S201 above, the first motion information includes 27 sets of motion data, and the final determined longitudinal displacement intervals also include 27.

[0118] Road speed limit information includes the maximum and minimum vehicle speeds on the road; the longitudinal displacement range includes the upper and lower limits of longitudinal displacement. Specifically, for any set of motion data, the method for determining the longitudinal displacement range may include: determining the upper limit of longitudinal displacement based on the maximum road speed, a preset future time period, acceleration, deceleration, the final speed, and the current speed of the vehicle; and determining the lower limit of longitudinal displacement based on the minimum road speed, a preset future time period, acceleration, deceleration, the final speed, and the current speed of the vehicle.

[0119] Specifically, Figure 3 This is a schematic diagram of a longitudinal displacement range provided in Embodiment 2 of the present invention. Figure 3 As shown, the upper limit of longitudinal displacement smax The method for determining this is as follows: the vehicle itself accelerates at a speed of a acc Accelerate uniformly from the vehicle's current speed V0 to the maximum road speed V. max-lim The duration is t2; then the maximum road speed V is used. max-lim After traveling at a constant speed to t4, it then decelerates at a speed of a. dec From the highest speed limit on the road V max-lim Decelerate uniformly to the final speed V fin This process will last for a predetermined period of time, duration t. future .

[0120] Lower limit of longitudinal displacement s min The method for determining this is as follows: the vehicle itself decelerates at a speed of a dec Based on the vehicle's current speed a dec Decelerate smoothly to the minimum road speed V min-lim The duration is t1; then the minimum road speed V min-lim After traveling at a constant speed to t3, it then accelerates at an acceleration a. acc From the minimum speed of vehicles on the road V min-lim Accelerate uniformly to the final speed V fin This process will last for a predetermined period of time, duration t. future .

[0121] In one embodiment, the upper limit of longitudinal displacement

[0122]

[0123] Lower limit of longitudinal displacement

[0124]

[0125] Among them, V max-lim V is the maximum speed limit on the road. min-lim The minimum speed on the road, t future For any point within a pre-defined future time period, a dec For deceleration, a acc For acceleration, V fin V0 represents the destination speed, and V0 represents the current speed of the vehicle itself.

[0126] S203. Obtain the traffic dataset and select the training dataset from the traffic dataset.

[0127] S204. Train the LSTM neural network model using the training dataset to obtain the car-following model.

[0128] Figure 4 This is a basic structural diagram of an LSTM neural network model provided in Embodiment 2 of the present invention. Figure 4As shown, by training the LSTM neural network model with the training dataset, various parameters of the LSTM neural network model can be continuously adjusted, thus ultimately obtaining the car-following model.

[0129] S205. Based on the car-following model, obtain the second motion information of surrounding vehicles within a preset time period in the future.

[0130] Specifically, the method for obtaining the second motion information of surrounding vehicles within a future preset time period may include: obtaining the vehicle speed of surrounding vehicles within a past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front within a past preset time period; inputting the vehicle speed of surrounding vehicles within a past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front within a past preset time period into a pre-trained car-following model to obtain the current acceleration of surrounding vehicles; and predicting the second motion information based on the current acceleration of surrounding vehicles.

[0131] Figure 5 This is a schematic diagram of the vehicle itself, surrounding vehicles, and lane-changing space provided in Embodiment 2 of the present invention. Figure 5 As shown, the vehicle itself is M, and the surrounding vehicles include the first vehicle L. c Second vehicle L d Third vehicle H d Fourth vehicle F d And the fifth vehicle T d Therefore, the second motion information includes the first vehicle L c Motion information, second vehicle L d Motion information, third vehicle H d Motion information, fourth vehicle F d Motion information and the fifth vehicle T d Motion information of the first vehicle L. c For vehicle M, the vehicle ahead in the current lane is the second vehicle L. d For vehicle M, the vehicle in front of it in the target lane, and the third vehicle H d For the second vehicle L d The vehicle ahead in the target lane, the fourth vehicle F d For vehicle M, which is behind another vehicle in the target lane, the fifth vehicle T d For the fourth vehicle F d Vehicles behind in the target lane. It is understood that the target lane can be at least one of the lanes to the left or right of the current lane. Figure 5 The target lane is the left lane of the current lane, which is used as an example for drawing.

[0132] S206. Determine the lane-changing space based on the second motion information.

[0133] Continue to refer to Figure 5 It can be seen that the lane-changing space includes a first space gap1, a second space gap2, and a third space gap3. The first space gap1 is adjacent to the first vehicle L. c Second vehicle L d and the third vehicle H d Related to; second space gap2 and first vehicle L c Second vehicle L d and the fourth vehicle F d Related to; third space gap3 and fourth vehicle F d And the fifth vehicle T d related.

[0134] Therefore, the method for determining lane-changing space based on the second motion information may include: determining a first space based on the motion information of the first vehicle, the second vehicle, and the third vehicle; determining a second space based on the motion information of the first vehicle, the second vehicle, and the fourth vehicle; and determining a third space based on the motion information of the fourth vehicle and the fifth vehicle.

[0135] Among them, the first space Second Space Third Space

[0136] t0 is the current time, t future For any point within a pre-defined time period in the future For in t future First vehicle L c The achievable longitudinal position, For in t future Second vehicle L at time d The achievable longitudinal position, For in t future Third vehicle H at time d The achievable longitudinal position, For in t future Fourth vehicle F at time d The achievable longitudinal position, For in t future Fifth vehicle T at time d The achievable longitudinal position, When vehicle M arrives at the corresponding space, it should interact with the first vehicle L. c Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with the second vehicle L. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with a third vehicle H. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle F, the fourth vehicle. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle T, the fifth vehicle. d Maintain a safe distance.

[0137] S207. Determine whether there is a longitudinal displacement interval that is completely located within the lane-changing space among all longitudinal displacement intervals. If yes, continue to step S208; otherwise, end the process of determining the feasible lane-changing region.

[0138] When there is no longitudinal displacement interval that is completely within the lane-changing space among all longitudinal displacement intervals, the target lane-changing feasible region is empty, indicating that it is not suitable to change lanes and it is necessary to wait for the next lane-changing opportunity.

[0139] S208. The longitudinal displacement range that is completely located within the lane-changing space is taken as the candidate lane-changing feasible region.

[0140] S209. Determine the target lane-changing feasible region from at least one candidate lane-changing feasible region.

[0141] To determine the target lane-changing feasible region, multiple factors can be considered, including the success rate of finding feasible regions, lane-changing comfort, and the degree of impact on traffic (such as traffic flow). Specifically, methods for determining the target lane-changing feasible region from at least one candidate lane-changing feasible region may include: constructing a sub-function for each factor and determining the objective function based on the sub-functions; solving the objective function for each candidate lane-changing feasible region and selecting the candidate lane-changing feasible region with the smallest value that satisfies the objective function as the target lane-changing feasible region.

[0142] In one embodiment, when multiple factors include feasible region search success rate, lane-changing comfort, and impact on traffic, the number of sub-functions is 3; the objective function J = ω1J success +ω2J comfort +ω3J impact .

[0143] Among them, J success To find a success rate subfunction for the feasible region, J comfort For the lane change comfort subfunction, J impact Let J be the traffic impact subfunction, and ω1, ω2, and ω3 be the feasible region search success rate subfunctions. success Lane change comfort subfunction J comfort Traffic impact sub-function J impact The weighting coefficients are ω1+ω2+ω3=1, and the values ​​of ω1, ω2, and ω3 are all greater than 0 and less than 1.

[0144] For the feasible region search success rate subfunction, the closer the upper and lower limits of the longitudinal displacement of the candidate lane-changing feasible region are, the fewer movement modes the vehicle can choose. Considering the controller's time delay, the difficulty of reaching the feasible region within the expected time also increases. Therefore, s max s represents the upper limit of the longitudinal displacement of the candidate lane-changing feasible region. min ε is the lower limit of longitudinal displacement in the candidate lane-changing feasible region, and ε is a constant, usually a non-zero minimum value.

[0145] For the lane-change comfort subfunction, in order to ensure that the vehicle reaches the candidate lane-change feasible region, it may engage in some rapid acceleration or deceleration behaviors, affecting driving comfort. Therefore, V fin V0 is the destination speed, V0 is the current speed of the vehicle, and t is the destination speed. future For any point in a future preset time period.

[0146] For the traffic impact sub-function, once the vehicle reaches the longitudinal position corresponding to the candidate lane-changing feasible region, the next step is to perform a lane-changing operation. If the speed difference between the vehicle and the vehicle constructing the lane-changing space is too large at this time, the vehicle needs to adjust its speed significantly during the lane-changing process. To avoid affecting subsequent vehicles in the target lane, this invention characterizes this impact by the difference between the vehicle's final speed in motion planning and the speed of the vehicle constructing the lane-changing space: J impact =|V fin -V front |,V front To determine the speed of the vehicle ahead in order to change lanes.

[0147] In addition, when solving the objective function for each candidate lane-changing feasible region, in order to ensure the efficiency of finding the optimal solution, the whale optimization algorithm can be selected to solve the relevant parameters, and the candidate lane-changing feasible region that satisfies the objective function with the smallest value is taken as the target lane-changing feasible region.

[0148] S210. Establish a vehicle speed-time curve based on a cubic polynomial, and control the vehicle to change lanes within the target lane-changing feasible region according to the vehicle speed-time curve.

[0149] After determining the feasible region for the target lane change, consider the vehicle's acceleration 'a' at the previous moment. pre Within the constraints on vehicle speed and acceleration within the target lane-changing feasible region, a smoothly varying desired vehicle speed curve is output in the form of a cubic polynomial. This ensures that the vehicle reaches the destination speed at the destination time and is within the target lane-changing feasible region. The solution is continuously iterated based on the actual situation at each sampling interval.

[0150] In one embodiment, the speed-time expression in the cubic polynomial is v = c0 + c1t + c2t. 2 +c3t 3 The acceleration-time expression is a = c1 + 2c2 + 3c3t 2 The polynomial parameters can be calculated using the following formula:

[0151]

[0152] This invention provides a method for determining a feasible lane-changing region, comprising: acquiring first motion information and second motion information of the vehicle itself and surrounding vehicles within a preset future time period; determining at least one longitudinal displacement interval of the vehicle itself based on the first motion information, the vehicle's current speed, and road speed limit information; determining a lane-changing space based on the second motion information; and determining a target feasible lane-changing region based on the longitudinal displacement interval and the lane-changing space. The technical solution of this invention first acquires first motion information and second motion information of the vehicle itself and surrounding vehicles within a preset future time period, then combines this information with the vehicle's current speed and road speed limit information to determine at least one longitudinal displacement interval and a lane-changing space, thereby further determining the target feasible lane-changing region. Since the second motion information is based on a prediction of the current acceleration of surrounding vehicles, it can more accurately reflect the motion state of surrounding vehicles, thus enabling a more accurate and safer determination of the target feasible lane-changing region to meet the vehicle's lane-changing needs. Simultaneously, the influence of the lane-changing space is considered in the process of determining the target feasible lane-changing region, effectively avoiding the problem of missing lane-changing opportunities.

[0153] Example 3

[0154] Figure 6 This is a schematic diagram of a device for determining the feasible region of lane changing according to Embodiment 3 of the present invention. Figure 6 As shown, the device includes: a data acquisition module 601, a prediction module 602, a calculation module 603, and a determination module 604.

[0155] The acquisition module 601 is used to acquire the first motion information of its own vehicle within a preset time period in the future;

[0156] Prediction module 602 is used to obtain the second motion information of surrounding vehicles within a preset time period in the future;

[0157] The calculation module 603 is used to determine at least one longitudinal displacement range of its own vehicle based on the first motion information, the current speed of its own vehicle and the road speed limit information; and to determine the lane-changing space based on the second motion information.

[0158] The determination module 604 is used to determine the target lane-changing feasible region based on the longitudinal displacement range and lane-changing space.

[0159] Optionally, the first motion information includes at least one set of motion data, each set of motion data including the final vehicle speed, acceleration, and deceleration;

[0160] The data acquisition module 601 is specifically used to determine the vehicle's final speed range, acceleration range, and deceleration range within a preset time period in the future; and to acquire at least one final speed, at least one acceleration, and at least one deceleration within the final speed range, acceleration range, and deceleration range according to a preset precision, and to generate motion data.

[0161] Optionally, the first motion information includes the same number of motion data as the number of longitudinal displacement intervals; the road speed limit information includes the maximum and minimum road speeds; and the longitudinal displacement intervals include the upper and lower limits of longitudinal displacement.

[0162] The calculation module 603 is specifically used to determine the upper limit of longitudinal displacement based on the maximum speed of the road, the future preset time period, acceleration, deceleration, the destination speed and the current speed of the vehicle itself; and to determine the lower limit of longitudinal displacement based on the minimum speed of the road, the future preset time period, acceleration, deceleration, the destination speed and the current speed of the vehicle itself.

[0163] Optional, upper limit of longitudinal displacement

[0164]

[0165] Upper limit of longitudinal displacement

[0166]

[0167] Among them, V max-lim V is the maximum speed limit on the road. min-lim The minimum speed on the road, t future For any point within a pre-defined future time period, a dec For deceleration, a acc For acceleration, V fin V0 represents the destination speed, and V0 represents the current speed of the vehicle itself.

[0168] Optionally, the prediction module 602 is used to obtain the speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period; input the speed of surrounding vehicles in the past preset time period, the relative speed and relative distance between surrounding vehicles and the vehicle in front in the past preset time period into a pre-trained car-following model to obtain the current acceleration of surrounding vehicles; and predict the second motion information based on the current acceleration of surrounding vehicles.

[0169] Optionally, the prediction module 602 is also used to train the car-following model. The method for training the car-following model includes: acquiring a traffic dataset and selecting a training dataset from the traffic dataset; and using the training dataset to train a long short-term memory (LSTM) neural network model to obtain the car-following model.

[0170] Optionally, the surrounding vehicles include the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. The second motion information includes the motion information of the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. Among them, the first vehicle is the vehicle in front of the current vehicle in the current lane, the second vehicle is the vehicle in front of the current vehicle in the target lane, the third vehicle is the vehicle in front of the second vehicle in the target lane, the fourth vehicle is the vehicle behind the current vehicle in the target lane, and the fifth vehicle is the vehicle behind the fourth vehicle in the target lane. The lane-changing space includes the first space, the second space, and the third space.

[0171] The calculation module 603 is specifically used to determine a first space based on the motion information of the first vehicle, the second vehicle, and the third vehicle; to determine a second space based on the motion information of the first vehicle, the second vehicle, and the fourth vehicle; and to determine a third space based on the motion information of the fourth vehicle and the fifth vehicle.

[0172] Optional, first space Second Space Third Space

[0173] Where t0 is the current time, t future For any point within a pre-defined time period in the future For in t future First vehicle L c The achievable longitudinal position, For in t future Second vehicle L at time d The achievable longitudinal position, For in t future Third vehicle H at time d The achievable longitudinal position, For in t future Fourth vehicle F at time d The achievable longitudinal position, For in t future Fifth vehicle T at time d The achievable longitudinal position, When vehicle M arrives at the corresponding space, it should interact with the first vehicle L. c Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with the second vehicle L. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with a third vehicle H. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle F, the fourth vehicle. d Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with vehicle T, the fifth vehicle. d Maintain a safe distance.

[0174] Optionally, the determining module 604 is specifically used to determine whether there is a longitudinal displacement interval that is completely located within the lane-changing space among all longitudinal displacement intervals; if so, the longitudinal displacement interval that is completely located within the lane-changing space is taken as a candidate lane-changing feasible region; and the target lane-changing feasible region is determined from at least one candidate lane-changing feasible region.

[0175] Optionally, module 604 is specifically used to construct at least one sub-function and determine the objective function based on the sub-function; solve the objective function for each candidate lane-changing feasible region, and take the candidate lane-changing feasible region with the smallest value that satisfies the objective function as the target lane-changing feasible region.

[0176] Optionally, the number of sub-functions is 3;

[0177] Objective function J = ω1J success +ω2J comfort +ω3J impact ;

[0178] Among them, J success Find a success rate subfunction for the feasible region. s max s represents the upper limit of the longitudinal displacement of the candidate lane-changing feasible region. min Let J be the lower limit of the longitudinal displacement of the candidate lane-changing feasible region, where ε is a constant. comfort For lane change comfort subfunction, V fin V0 is the destination speed, V0 is the current speed of the vehicle, and t is the destination speed. future For any point within a pre-defined future time period, J impact J is the traffic impact sub-function. impact =|V fin -V front |,V f r ont To determine the speed of the vehicle ahead in the lane-changing space, ω1, ω2, and ω3 are the sub-functions J representing the success rate of finding the feasible region. success Lane change comfort subfunction J comfort Traffic impact sub-function J impactThe weighting coefficients are ω1+ω2+ω3=1, and the values ​​of ω1, ω2, and ω3 are all greater than 0 and less than 1.

[0179] Optional, combined Figure 6 , Figure 7 This is a schematic diagram of another device for determining the feasible region of lane changing provided in Embodiment 3 of the present invention. Figure 7 As shown, it also includes: lane changing module 605.

[0180] The lane-changing module 605 is used to establish a vehicle speed-time curve based on a cubic polynomial, and to control its own vehicle to change lanes within the target lane-changing feasible region according to the vehicle speed-time curve.

[0181] The lane-changing feasible region determination device provided in the embodiments of the present invention can execute the lane-changing feasible region determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0182] Example 4

[0183] Figure 8 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0184] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0185] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0186] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining the feasible region of lane switching.

[0187] In some embodiments, the method for determining the lane-switching feasible region may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining the lane-switching feasible region described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining the lane-switching feasible region by any other suitable means (e.g., by means of firmware).

[0188] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0189] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0190] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0191] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0192] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0193] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0194] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0195] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining the feasible region of lane changing, characterized in that, include: Obtain the first motion information of its own vehicle within a preset future time period; The system acquires the speed of surrounding vehicles over a preset time period, the relative speed and relative distance between surrounding vehicles and the vehicles in front over the preset time period. The surrounding vehicles include a first vehicle, a second vehicle, a third vehicle, a fourth vehicle, and a fifth vehicle. The first vehicle is the vehicle in front of the current vehicle in the current lane, the second vehicle is the vehicle in front of the current vehicle in the target lane, the third vehicle is the vehicle in front of the second vehicle in the target lane, the fourth vehicle is the vehicle behind the current vehicle in the target lane, and the fifth vehicle is the vehicle behind the fourth vehicle in the target lane. The speed of the surrounding vehicles in the past preset time period, the relative speed and relative distance between the surrounding vehicles and the vehicles in front in the past preset time period are input into the pre-trained car-following model to obtain the current acceleration of the surrounding vehicles. Based on the current acceleration of the surrounding vehicles, predict the second motion information of the surrounding vehicles within a future preset time period, wherein the second motion information includes the motion information of the first vehicle, the motion information of the second vehicle, the motion information of the third vehicle, the motion information of the fourth vehicle, and the motion information of the fifth vehicle. Based on the first motion information, the vehicle's current speed, and the road speed limit information, determine at least one longitudinal displacement range of the vehicle. The first space is determined based on the motion information of the first vehicle, the motion information of the second vehicle, and the motion information of the third vehicle; The second space is determined based on the motion information of the first vehicle, the motion information of the second vehicle, and the motion information of the fourth vehicle; Based on the motion information of the fourth vehicle and the motion information of the fifth vehicle, a third space is determined, wherein the lane-changing space includes the first space, the second space and the third space; Determine whether there is a longitudinal displacement interval that is completely located within the lane-changing space among all the longitudinal displacement intervals; If it exists, the longitudinal displacement range that is completely located within the lane-changing space will be taken as the candidate lane-changing feasible region. Construct at least one sub-function, and determine the target function based on the sub-function; The objective function is solved for each candidate lane-changing feasible region, and the candidate lane-changing feasible region with the smallest value that satisfies the objective function is taken as the target lane-changing feasible region.

2. The method for determining the feasible region of lane changing according to claim 1, characterized in that, The first motion information includes at least one set of motion data, and each set of motion data includes the final vehicle speed, acceleration, and deceleration; The acquisition of the vehicle's first motion information within a preset future time period includes: Determine the destination speed range, acceleration range, and deceleration range of the vehicle within the preset future time period; According to the preset accuracy, at least one end vehicle speed, at least one acceleration, and at least one deceleration are collected in the end vehicle speed range, the acceleration range, and the deceleration range, respectively, and the motion data is generated.

3. The method for determining the feasible region of lane changing according to claim 2, characterized in that, The first motion information includes the same number of motion data as the number of longitudinal displacement intervals; the road speed limit information includes the maximum road speed and the minimum road speed; the longitudinal displacement interval includes the upper limit of longitudinal displacement and the lower limit of longitudinal displacement. For any set of motion data, determining the longitudinal displacement range based on the motion data, the vehicle's current speed, and road speed limit information includes: The upper limit of longitudinal displacement is determined based on the maximum speed of the road, the preset time period, the acceleration, the deceleration, the destination speed, and the current speed of the vehicle itself. The lower limit of longitudinal displacement is determined based on the minimum speed on the road, the preset time period, the acceleration, the deceleration, the destination speed, and the current speed of the vehicle itself.

4. The method for determining the feasible region of lane changing according to claim 3, characterized in that, The upper limit of longitudinal displacement The lower limit of longitudinal displacement Among them, V max-lim V represents the maximum vehicle speed on the road. min-lim t represents the minimum vehicle speed on the road. future For any time within the preset future time period, a dec Let a be the deceleration. acc For the acceleration, V fin V0 represents the destination vehicle speed, and V0 represents the current vehicle speed.

5. The method for determining the feasible region of lane changing according to claim 1, characterized in that, The method for training the car-following model includes: Obtain a traffic dataset and filter the training dataset from the traffic dataset; The long short-term memory (LSTM) neural network model is trained using the training dataset to obtain the car-following model.

6. The method for determining the feasible region of lane changing according to claim 1, characterized in that, First space Second space The third space Where t0 is the current time, t future For any time within the preset future time period, For in t future The first vehicle L at time c The achievable longitudinal position, For in t future The second vehicle L at time d The achievable longitudinal position, For in t future The third vehicle H at the specified time d The achievable longitudinal position, For in t future The fourth vehicle F at the specified time d The achievable longitudinal position, For in t future The fifth vehicle T at time T d The achievable longitudinal position, When vehicle M arrives at the corresponding space, it should interact with the first vehicle L. c Maintain a safe distance. When vehicle M arrives at the corresponding space, it should interact with the second vehicle L. d Maintain a safe distance. When the vehicle M arrives at the corresponding space, it should interact with the third vehicle H. d Maintain a safe distance. When the vehicle M arrives at the corresponding space, it should interact with the fourth vehicle F. d Maintain a safe distance. When the vehicle M arrives at the corresponding space, it should interact with the fifth vehicle T. d Maintain a safe distance.

7. The method for determining the feasible region of lane changing according to claim 1, characterized in that, The number of sub-functions is 3; The objective function J = ω1J success +ω2J comfort +ω3J impact ; Among them, J success Find a success rate subfunction for the feasible region. s max s represents the upper limit of the longitudinal displacement of the candidate lane-changing feasible region. min Let J be the lower limit of the longitudinal displacement of the candidate lane-changing feasible region, where ε is a constant. comfort For lane change comfort subfunction, V fin V0 is the destination speed, V0 is the current speed of the vehicle, and t is the destination speed. future For any time within the preset future time period, J impact J is the traffic impact sub-function. impact =|V fin -V front |,V front To determine the speed of the vehicle ahead in the lane-changing space, ω1, ω2, and ω3 are the sub-functions J representing the success rate of finding the feasible region. success Lane change comfort subfunction J comfort Traffic impact sub-function J impact The weighting coefficients are ω1+ω2+ω3=1, and the values ​​of ω1, ω2, and ω3 are all greater than 0 and less than 1.

8. The method for determining the feasible region of lane changing according to claim 1, characterized in that, After determining the feasible region for the target lane change, the following is also included: The vehicle speed-time curve is established based on a cubic polynomial, and the vehicle is controlled to change lanes within the target lane-changing feasible region according to the vehicle speed-time curve.

9. A device for determining the feasible region of lane changing, characterized in that, include: The module comprises an acquisition module, a prediction module, a calculation module, and a determination module; among which, The acquisition module is used to acquire the first motion information of its own vehicle within a preset time period in the future; The prediction module is used to acquire the speeds of surrounding vehicles over a preset time period, and the relative speeds and distances between surrounding vehicles and the vehicles in front over the same preset time period. The surrounding vehicles include a first vehicle, a second vehicle, a third vehicle, a fourth vehicle, and a fifth vehicle. The first vehicle is the vehicle in front of the current vehicle in the current lane, the second vehicle is the vehicle in front of the current vehicle in the target lane, the third vehicle is the vehicle in front of the second vehicle in the target lane, the fourth vehicle is the vehicle behind the current vehicle in the target lane, and the fifth vehicle is the vehicle behind the fourth vehicle in the target lane. The module inputs the speeds of the surrounding vehicles over the preset time period, and the relative speeds and distances between the surrounding vehicles and the vehicles in front over the same preset time period, into a pre-trained car-following model to obtain the current acceleration of the surrounding vehicles. Based on the current acceleration of the surrounding vehicles, the module predicts second motion information of the surrounding vehicles over a preset time period in the future. This second motion information includes the motion information of the first vehicle, the second vehicle, the third vehicle, the fourth vehicle, and the fifth vehicle. The calculation module is configured to determine at least one longitudinal displacement range of its own vehicle based on the first motion information, the current speed of its own vehicle, and the road speed limit information; and to determine a first space based on the motion information of the first vehicle, the motion information of the second vehicle, and the motion information of the third vehicle; to determine a second space based on the motion information of the first vehicle, the motion information of the second vehicle, and the motion information of the fourth vehicle; and to determine a third space based on the motion information of the fourth vehicle and the motion information of the fifth vehicle, wherein the lane-changing space includes the first space, the second space, and the third space; The determining module is used to determine whether there is a longitudinal displacement interval that is completely located within the lane-changing space among all the longitudinal displacement intervals; if so, the longitudinal displacement interval that is completely located within the lane-changing space is taken as a candidate lane-changing feasible region; at least one sub-function is constructed, and an objective function is determined based on the sub-function; the objective function is solved for each candidate lane-changing feasible region, and the candidate lane-changing feasible region that satisfies the objective function with the smallest value is taken as the target lane-changing feasible region.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, which enables the at least one processor to perform the method for determining the lane-changing feasible region according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the method for determining the lane-changing feasible region as described in any one of claims 1-8.

Images