Lane-changing trajectory planning method and apparatus, and vehicle and storage medium

Abstract

The present application relates to the technical field of vehicles, and in particular to a lane-changing trajectory planning method and apparatus, and a vehicle and a storage medium. The method comprises: acquiring the acceleration of a front vehicle in a target lane at a current moment and the acceleration of a rear vehicle in the target lane at the current moment; on the basis of the acceleration of the front vehicle in the target lane at the current moment and the acceleration of the rear vehicle in the target lane at the current moment, predicting a motion state of the front vehicle in the target lane at a future moment and a motion state of the rear vehicle in the target lane at the future moment; and on the basis of the motion state of the front vehicle in the target lane at the future moment and the motion state of the rear vehicle in the target lane at the future moment, determining a target lane-changing space, and on the basis of the target lane-changing space, planning a lane-changing trajectory for a current vehicle. Thus, the problems in the related art such as the risk of a traffic accident being increased due to insufficient consideration of changes in the speeds of surrounding vehicles and simultaneous lane-changing of vehicles in other lanes are solved.

Description

Lane-changing trajectory planning method, device, vehicle, and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is based on the Chinese patent application with application number 202410244819.6 and application date March 4, 2024, and claims the priority of the Chinese patent application. The entire content of the Chinese patent application is hereby introduced into this application as a reference. Technical Field

[0003] The present application relates to the field of vehicle technology, and in particular to a lane change trajectory planning method, device, vehicle, and storage medium. Background Art

[0004] While driving, drivers often intend to change lanes for the sake of efficiency or to comply with traffic regulations. This behavior involves complex interactions with vehicles in multiple lanes. Without proper planning, it can affect overall traffic flow and even cause accidents. The lane-changing process consists of three phases: intention generation, trajectory execution, and speed adjustment. Each stage places high demands on the driver's decision-making and the precision of the vehicle control system.

[0005] However, existing technologies often simplify the motion of surrounding vehicles as uniform, which is inaccurate in real traffic scenarios. When the speeds of surrounding vehicles vary, trajectories planned based on the uniform velocity assumption can cause the lane-changing vehicle to collide with other vehicles. Furthermore, they ignore the possibility of vehicles in other lanes simultaneously changing lanes into the target lane. This oversight is not uncommon in real traffic and can significantly increase the probability of an accident.

[0006] Summary of the Invention

[0007] The present application provides a lane-changing trajectory planning method, device, vehicle, and storage medium to address the problems in the related art of not fully considering the speed changes of surrounding vehicles and the simultaneous lane changes of vehicles in other lanes, thereby increasing the risk of traffic accidents.

[0008] An embodiment of the first aspect of the present application provides a lane change trajectory planning method, comprising the following steps: obtaining the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment; predicting the motion state of the front vehicle and the motion state of the rear vehicle in the target lane at the future moment based on the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment; determining the target lane change space based on the motion state of the front vehicle and the motion state of the rear vehicle in the target lane at the future moment, and planning the lane change trajectory of the current vehicle based on the target lane change space.

[0009] Optionally, the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment are obtained, including: obtaining the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at historical moments; inputting the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at historical moments into a vehicle following model, and the vehicle following model outputs the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment, wherein the vehicle following model is a neural network model, and the vehicle following model is trained using real traffic data.

[0010] Optionally, the motion state of the leading vehicle includes the speed and longitudinal position of the leading vehicle, and the motion state of the trailing vehicle includes the speed and longitudinal position of the trailing vehicle; determining the target lane changing space based on the motion state of the leading vehicle and the motion state of the trailing vehicle in the target lane at a future moment includes: obtaining a first safety distance and a second safety distance from the current vehicle to the leading vehicle and the trailing vehicle respectively; constructing the target lane changing space based on the speed and longitudinal position of the leading vehicle, the speed and longitudinal position of the trailing vehicle, the first safety distance, and the second safety distance.

[0011] Optionally, after planning the lane-changing trajectory of the current vehicle according to the target lane-changing space, it also includes: identifying whether there is a lane-changing vehicle that is expected to change lanes to the target lane within the target range; if a lane-changing vehicle is identified, predicting the lateral and longitudinal positions of the lane-changing vehicle at future times based on the lateral and longitudinal positions of the lane-changing vehicle at historical times; dividing the target lane-changing space into a first space and a second space according to the lateral and longitudinal positions of the lane-changing vehicle at future times, and replanning the lane-changing trajectory of the current vehicle based on the first space and the second space.

[0012] Optionally, identifying whether there is a lane-changing vehicle that is expected to change lanes to the target lane within the target range includes: identifying other vehicles within the target range that cross the lane line of the target lane; if the proportion of other vehicles crossing the lane line is greater than a lane-changing threshold, then determining that the other vehicles are lane-changing vehicles that are expected to change lanes to the target lane.

[0013] Optionally, the lateral and longitudinal positions of the lane-changing vehicle at a future moment are predicted based on the lateral and longitudinal positions of the lane-changing vehicle at a historical moment, including: inputting the lateral and longitudinal positions of the lane-changing vehicle at a historical moment into a trajectory prediction model, and inputting the lateral and longitudinal positions of the lane-changing vehicle at a future moment into the trajectory prediction model, wherein the trajectory prediction model is a neural network model, and the trajectory prediction model is trained using real lane-changing data.

[0014] Optionally, replanning the lane-changing trajectory of the current vehicle according to the first space and the second space includes: selecting the largest space between the first space and the second space; if the distance obtained by the largest space is greater than the preset safety distance, replanning the lane-changing trajectory of the current vehicle according to the largest space.

[0015] The second aspect of the present application provides a lane-changing trajectory planning device, including: an acquisition module for acquiring the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment; a prediction module for predicting the motion state of the front vehicle and the rear vehicle in the target lane at a future moment based on the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment; a planning module for determining a target lane-changing space based on the motion state of the front vehicle and the rear vehicle in the target lane at the future moment, and planning the lane-changing trajectory of the current vehicle according to the target lane-changing space.

[0016] The third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane change trajectory planning method as described in the above embodiment.

[0017] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the lane change trajectory planning method as described in the above embodiment.

[0018] Therefore, this application has at least the following beneficial effects:

[0019] By acquiring acceleration data from the preceding and following vehicles in the target lane in real time and predicting their future motion states, the embodiments of the present application can dynamically assess the safety of lane changes. This allows lane change decisions to be made while maintaining a safe distance between the current vehicle and the preceding and following vehicles. This effectively improves the accuracy and safety of lane change decisions and reduces the risk of traffic accidents caused by inadequate consideration of speed changes of surrounding vehicles. Furthermore, by rationally planning lane change trajectories, a smooth lane change process can be ensured and passenger comfort can be enhanced. This solves the technical issues in related technologies such as inadequate consideration of speed changes of surrounding vehicles and simultaneous lane changes by vehicles in other lanes, which increases the risk of traffic accidents.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] FIG1 is a flow chart of a lane change trajectory planning method according to an embodiment of the present application;

[0023] FIG2 is a schematic diagram of a target vehicle changing lanes according to one embodiment of the present application;

[0024] FIG3 is a schematic diagram of a target vehicle changing lanes according to another embodiment of the present application;

[0025] FIG4 is a flow chart of a lane change trajectory planning method according to one embodiment of the present application;

[0026] FIG5 is a schematic diagram of a safe lane-changing space provided according to one embodiment of the present application;

[0027] FIG6 is a schematic diagram of a safe lane-changing space provided according to another embodiment of the present application;

[0028] FIG7 is an example diagram of a lane change trajectory planning device according to an embodiment of the present application;

[0029] FIG8 is a schematic structural diagram of a vehicle according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] While driving, drivers may want to change lanes for various reasons, such as seeking higher driving efficiency or complying with road markings. Since lane changes involve the interaction of vehicles on multiple lanes, failure to properly plan these changes can negatively impact road efficiency and, in severe cases, even lead to traffic accidents.

[0032] Generally speaking, the lane-changing process can be divided into the intention generation phase, the execution phase, and the adjustment phase. During the intention generation phase, the target lane is selected and a safe lane-changing space is sought. If no suitable lane-changing space is found, the lane-changing attempt is abandoned. During the execution phase, trajectory planning is performed in real time based on the motion state of surrounding vehicles. The controller converts the trajectory into control variables such as steering wheel angle and throttle opening in real time to ensure that the vehicle can effectively follow the planned trajectory. During the adjustment phase, the vehicle should dynamically adjust its speed to follow the vehicle in front in the target lane.

[0033] In summary, both the intention generation and execution phases require a reasonable assessment of the motion state of surrounding vehicles to ensure lane-changing safety. In existing technologies, the motion of surrounding vehicles is typically assumed to be uniform. When vehicle speeds fluctuate, the planned trajectory could cause the lane-changing vehicle to collide with other vehicles. Furthermore, existing technologies fail to account for the possibility that vehicles in other lanes are simultaneously changing lanes into the target lane, potentially leading to traffic accidents.

[0034] The lane change trajectory planning method, device, vehicle and storage medium of the embodiment of the present application are described below with reference to the accompanying drawings. In response to the problem mentioned in the background technology above that it is impossible to reasonably predict the motion state of surrounding vehicles during the lane change process, the present application provides a lane change trajectory planning method. In this method, by acquiring the acceleration data of the front and rear vehicles in the target lane in real time and predicting their future motion states, the safety of lane change can be dynamically evaluated, so that lane change decisions can be made under the premise of maintaining a safe distance between the current vehicle and the front and rear vehicles. This can effectively improve the accuracy and safety of lane change decisions and reduce the risk of traffic accidents caused by not fully considering the speed changes of surrounding vehicles. At the same time, by reasonably planning the lane change trajectory, it is possible to ensure that the lane change process is smooth and improve the comfort of passengers. As a result, it solves the problems in the related art of not fully considering the speed changes of surrounding vehicles and the situation where vehicles in other lanes change lanes at the same time, which increases the risk of traffic accidents.

[0035] Specifically, FIG1 is a flow chart of a lane change trajectory planning method provided in an embodiment of the present application.

[0036] As shown in FIG1 , the lane change trajectory planning method includes the following steps:

[0037] In step S101 , the acceleration of the preceding vehicle and the acceleration of the following vehicle in the target lane at the current moment are obtained.

[0038] Among them, the current moment can be the current time point, the target lane can be the lane the vehicle plans to change into, the front vehicle acceleration can be the acceleration of the front vehicle in the target lane at the current moment, and the rear vehicle acceleration can be the acceleration of the rear vehicle in the target lane at the current moment.

[0039] It can be understood that the embodiments of the present application can collect acceleration data of the front and rear vehicles in the target lane in real time through on-board sensors, wherein the acceleration of the front and rear vehicles is dynamic and can reflect the speed of change of the front and rear vehicles, which is convenient for subsequent prediction of their future motion status.

[0040] It should be noted that the status and behavior of the leading and following vehicles will affect the lane-changing decision and safety of the current vehicle. The leading vehicle can be a vehicle in the target lane, located in front of the current vehicle, and traveling in the same direction as the current vehicle; the following vehicle can be a vehicle in the target lane, located behind the current vehicle, and traveling in the same direction as the current vehicle.

[0041] In an embodiment of the present application, obtaining the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment includes: obtaining the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at historical moments; inputting the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at historical moments into a vehicle following model, and the vehicle following model outputs the acceleration of the front vehicle and the acceleration of the rear vehicle in the target lane at the current moment, wherein the vehicle following model is a neural network model, and the vehicle following model is trained using real traffic data.

[0042] The historical moment can be a specific time point in the past, which is used to analyze or predict future traffic conditions; the speed of the leading vehicle can be the speed of the vehicle in the target lane that is ahead of the current vehicle and traveling in the same direction; the speed of the following vehicle can be the speed of the vehicle in the target lane that is behind the current vehicle and traveling in the same direction; the relative speed of the leading and following vehicles can be the difference in speed between the leading and following vehicles; and the relative distance between the leading and following vehicles can be the actual distance between the leading and following vehicles on the road.

[0043] A car-following model can be a mathematical model or algorithm that can be used to describe and predict the behavior of a vehicle following the vehicle in front on the road, such as a safety distance model. A neural network model can be a machine learning model based on an artificial neural network that can handle complex traffic conditions, such as an LSTM (Long Short-Term Memory) neural network. Real traffic data can be data collected in an actual road traffic environment, such as vehicle speed, acceleration, location, time, and other information.

[0044] It can be understood that the embodiments of the present application can establish a vehicle following model through a neural network combined with a large amount of real traffic data, which can predict the dynamic behavior of the vehicle on the road. Among them, the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at the historical moment are input into the vehicle following model to predict the acceleration of the front vehicle and the rear vehicle, providing the driver with more accurate and timely driving assistance information, thereby helping the driver make safer driving decisions.

[0045] For example, the LSTM neural network establishes a car-following model, and the input feature of the car-following model is the past period of time t past-cf The speed of the following car is 30m / s, the relative speed between the following car and the leading car is 10m / s, and the relative distance between the following car and the leading car is 5m. The output is the acceleration of the following car at the current moment. The training of the following model is completed based on real traffic data.

[0046] In step S102 , the motion state of the leading vehicle and the following vehicle in the target lane at a future moment is predicted based on the acceleration of the leading vehicle and the following vehicle in the target lane at a current moment.

[0047] Among them, the future moment can be one or more time points after the current moment, the movement state of the leading vehicle can include the speed and longitudinal position of the leading vehicle, wherein the longitudinal position can be the relative distance between a certain point in front of the current vehicle and itself, and the movement state of the following vehicle can include the speed and longitudinal position of the following vehicle, wherein the longitudinal position can be the relative distance between a certain point behind the current vehicle and the following vehicle.

[0048] It can be understood that the embodiments of the present application can predict the motion states of the front and rear vehicles in the target lane at a future moment based on their accelerations at the current moment, obtain more information about the dynamics of surrounding vehicles, help the driver maintain a safe following distance, avoid rear-end collisions, and reduce the possibility of traffic accidents.

[0049] In step S103, a target lane-changing space is determined based on the motion states of the preceding vehicle and the following vehicle in the target lane at a future moment, and a lane-changing trajectory of the current vehicle is planned based on the target lane-changing space.

[0050] Among them, the target lane change space can be the minimum space required for the vehicle to safely change lanes based on the future motion status of the leading and following vehicles; the lane change trajectory planning can be to calculate a driving trajectory for safely transitioning from the current lane to the target lane based on the target lane change space, the current status of the vehicle, and road environment information.

[0051] It can be understood that the embodiments of the present application can determine the optimal target lane changing space based on the motion states of the front and rear vehicles in the target lane at a future moment, accurately judge whether there is a collision risk during the lane changing process, improve driving safety, and plan the lane changing trajectory of the current vehicle according to the target lane changing space, avoid unnecessary waiting and tentative lane changing, significantly improve lane changing efficiency and road traffic capacity, ensure a smooth lane changing process and enhance passenger comfort.

[0052] In an embodiment of the present application, a target lane changing space is determined based on the motion states of the leading vehicle and the trailing vehicle in the target lane at a future moment, including: obtaining a first safety distance and a second safety distance between the current vehicle and the leading vehicle and the trailing vehicle, respectively; and constructing a target lane changing space based on the speed and longitudinal position of the leading vehicle, the speed and longitudinal position of the trailing vehicle, the first safety distance, and the second safety distance.

[0053] Among them, the current vehicle may be a vehicle that is currently changing lanes or is about to change lanes, the first safety distance may be the minimum safety distance that needs to be maintained between the current vehicle and the vehicle in front, and the second safety distance may be the minimum safety distance that needs to be maintained between the current vehicle and the vehicle behind.

[0054] It is understood that the embodiments of the present application can obtain the first and second safe distances between the current vehicle and the vehicle ahead and behind, respectively, to ensure that the vehicle does not collide with the vehicles ahead and behind during the lane change process. A virtual target lane change space is constructed based on the speed and longitudinal position of the leading vehicle, the speed and longitudinal position of the following vehicle, the first and second safe distances, so that the current vehicle can safely complete the lane change, ensuring the safety of the lane change process. By real-time monitoring and dynamic adjustment of the target lane change space, it is possible to more flexibly and efficiently respond to complex traffic environments, improving road capacity and driving safety.

[0055] In an embodiment of the present application, after planning the lane-changing trajectory of the current vehicle according to the target lane-changing space, it also includes: identifying whether there is a lane-changing vehicle that is expected to change lanes to the target lane within the target range; if a lane-changing vehicle is identified, predicting the lateral and longitudinal positions of the lane-changing vehicle at a future time based on the lateral and longitudinal positions of the lane-changing vehicle at a historical time; dividing the target lane-changing space into a first space and a second space according to the lateral and longitudinal positions of the lane-changing vehicle at a future time, and replanning the lane-changing trajectory of the current vehicle according to the first space and the second space.

[0056] Among them, the target range can be the area that the current vehicle perception system can cover and obtain information, the horizontal and vertical positions can be the specific coordinate points of the vehicle on the road, among which the horizontal position can be the offset of the vehicle relative to the lane line, and the longitudinal position can be the front and rear positions of the vehicle on the road. The first space can be the part of the current vehicle's lane changing trajectory close to the lane changing vehicle, and the second space can be the part away from the lane changing vehicle.

[0057] It is understandable that the embodiments of the present application can identify whether there is a lane-changing vehicle that is expected to change lanes to the target lane within the target range, ensuring that the lane-changing decision of the current vehicle is not only based on its own conditions and the surrounding environment, but also takes into account the dynamic behavior of other vehicles. When a lane-changing vehicle is identified, the historical position data of the vehicle is used to predict its trajectory. By analyzing the past horizontal and vertical movement patterns of the vehicle, the possible position in the future can be predicted. According to the prediction results, the originally continuous target lane-changing space is divided into a first space and a second space, ensuring that the current vehicle can avoid these areas when selecting a lane-changing path, thereby avoiding collisions. The lane-changing trajectory of the current vehicle is re-planned for the first space and the second space to ensure that the current vehicle's actions are both safe and effective, and that the lane-changing operation can be successfully completed without interfering with other vehicles.

[0058] In an embodiment of the present application, identifying whether there is a lane-changing vehicle that is expected to change lanes to the target lane within the target range includes: identifying other vehicles in the target range that have crossed the lane line of the target lane; if the proportion of other vehicles crossing the lane line is greater than a lane-changing threshold, then determining that the other vehicles are lane-changing vehicles that are expected to change lanes to the target lane.

[0059] Among them, the part that crosses the lane line can be a part of the vehicle, such as the tire, body, etc., which has crossed the lane boundary line that it should have remained within. The lane change threshold can be a preset value, such as 50% of the body width, etc., which is used to determine whether the vehicle is actually changing lanes.

[0060] It can be understood that the embodiment of the present application determines whether other vehicles are performing or preparing to change lanes by identifying the relative position relationship between other vehicles and lane lines within the target range, and whether these position relationships exceed the preset lane change threshold, thereby adjusting its own driving strategy to ensure safety.

[0061] For example, as shown in Figure 2 and Figure 3, in the past period of time t past Inside, vertical If a vehicle continuously crosses the lane line of the nearest target lane within the range, and the crossing ratio is greater than a certain threshold, it is considered that the vehicle is changing lanes into the target lane changing space. With the center of the vehicle as the origin, the forward direction is the positive direction of the x-axis, and the left direction perpendicular to the forward direction is the positive direction of the y-axis. When the vehicle takes the left lane as the target lane, if other lanes are in the longitudinal direction, There are cars in the range, in the past t past Time satisfies d1<0, and , it is considered that the vehicle is changing lanes to the target lane; when the vehicle takes the right lane as the target lane, if other lanes There are cars in the range, in the past t past Time satisfies d1>0, and , it is considered that the vehicle is changing lanes to the target lane.

[0062] Where d1 is the difference between the y coordinate value of the vertex of the lane-changing vehicle in its lane-changing direction and the y coordinate value of the point closest to the vertex across the lane line; d2 is the difference between the y coordinate value of the diagonal vertex of the lane-changing vehicle corresponding to d1 and the y coordinate value of the point closest to the vertex across the lane line; abs() means taking the absolute value, p thr is the set threshold.

[0063] In an embodiment of the present application, the lateral and longitudinal positions of the lane-changing vehicle at a future moment are predicted based on the lateral and longitudinal positions of the lane-changing vehicle at a historical moment, including: inputting the lateral and longitudinal positions of the lane-changing vehicle at a historical moment into a trajectory prediction model, and inputting the lateral and longitudinal positions of the lane-changing vehicle at a future moment into the trajectory prediction model, wherein the trajectory prediction model is a neural network model, and the trajectory prediction model is trained using real lane-changing data.

[0064] Among them, the trajectory prediction model can be an algorithm model used to predict the future driving position of a lane-changing vehicle.

[0065] It is understandable that the embodiments of the present application can use the lateral and longitudinal position information of lane-changing vehicles at historical moments as input, and use a neural network trajectory prediction model trained with real lane-changing data to predict the lateral and longitudinal positions of lane-changing vehicles at future moments. By continuously optimizing the parameters of the model through a large amount of data input, the model can more accurately predict future vehicle position changes, which helps the vehicle better understand the surrounding environment and make more reasonable and safe driving decisions.

[0066] In an embodiment of the present application, the lane change trajectory of the current vehicle is replanned according to the first space and the second space, including: selecting the largest space between the first space and the second space; if the distance obtained by the maximum space is greater than the preset safety distance, the lane change trajectory of the current vehicle is replanned according to the maximum space.

[0067] The preset safety distance may be a pre-set threshold value used to determine whether the distance between the current vehicle and surrounding obstacles is safe enough for lane changing operations.

[0068] It can be understood that the embodiment of the present application can select the largest and safest space as the lane changing target by comparing the size and safety of the first space and the second space, and re-plan the vehicle's lane changing trajectory based on the largest space to ensure that the entire lane changing process is smooth and smooth, thereby improving the riding comfort of passengers.

[0069] According to the lane change trajectory planning method proposed in the embodiment of the present application, by acquiring the acceleration data of the front and rear vehicles in the target lane in real time and predicting their future motion states, it is possible to dynamically evaluate the safety of lane changes, thereby making lane change decisions while maintaining a safe distance between the current vehicle and the front and rear vehicles. This can effectively improve the accuracy and safety of lane change decisions and reduce the risk of traffic accidents caused by not fully considering the speed changes of surrounding vehicles. At the same time, by rationally planning the lane change trajectory, it is possible to ensure a smooth lane change process and improve passenger comfort. This solves the problem that the related art does not fully consider the speed changes of surrounding vehicles and the situation where vehicles in other lanes change lanes at the same time, thereby increasing the risk of traffic accidents.

[0070] The lane change trajectory planning method provided by one embodiment of the present application will be specifically described below with reference to FIG4 . The description is as follows:

[0071] Step 1: Build a car-following model based on the LSTM neural network, with the input being the past period of time t past-cf The following car's speed, the relative speed between the following car and the preceding car, and the relative distance between the following car and the preceding car are output as the following car's current acceleration. The following model is trained based on real traffic data.

[0072] Step 2: Build a trajectory prediction model for lane-changing vehicles based on the LSTM neural network, with the input being the past period of time t past-lc The horizontal and vertical positions of the inner lane-changing vehicle are output as a time period t in the future. future The lateral position is the lateral position of the lane-changing vehicle relative to the lane line to be crossed, and the lane-changing data of real vehicles is used to train the model.

[0073] Step 3: When the vehicle intends to change lanes, the following model obtained in step 1 is used to predict the motion state of the vehicles in the target lane and ahead for a period of time in the future. That is, the following model is used to obtain the current vehicle acceleration a0, and the vehicle speed v1 and position s1 at the next moment are: v1 = v0 + a0Δt

[0074] Among them, v0 is the speed of the vehicle at the current moment, s0 is the position information, and Δt is the time step.

[0075] Calculate the vehicle L in the target lane at the next moment by using the above formula d 、F, the vehicle behind in the target lane d The speed and position of the object are calculated, and the relative speed and relative distance are calculated, and the past t is updated with the next moment as the origin. past-lc Input, by iterating in this loop, you can predict L d 、F d The lane change interval gap is constructed based on the movement state in the future period and the safety distance model as follows:

[0076] in, For the future future Time L d The vertical position that can be reached, For the future future Time F d The vertical position that can be reached, The vehicle M is the target space to be reached, and F d , L d The safe distance to be maintained. If a gap exists, it is set as the target lane-changing space and the lane-changing trajectory planning operation is performed.

[0077] Step 4: During the lane change process, step 3 is executed in real time to determine whether the target lane change space meets safety requirements. It is also necessary to determine whether other vehicles are changing into the target lane change space. If so, and the rear axle center of ego vehicle M does not cross the lane lines between the starting lane and the target lane, it is necessary to re-evaluate whether the newly created lane change space meets the requirements. If not, the ego vehicle abandons the lane change and returns to the original lane.

[0078] As shown in Figure 2 and Figure 3, in the past period of time t past Inside, vertical If a vehicle continuously crosses the lane line of the nearest target lane within the range, and the crossing ratio is greater than a certain threshold, it is considered that the vehicle is changing lanes into the target lane changing space. With the center of the vehicle as the origin, the forward direction is the positive direction of the x-axis, and the left direction perpendicular to the forward direction is the positive direction of the y-axis. When the vehicle takes the left lane as the target lane, if other lanes are in the longitudinal direction, There are cars in the range, in the past t past Time satisfies d1<0, and , it is considered that the vehicle is changing lanes to the target lane; when the vehicle takes the right lane as the target lane, if other lanes There are cars in the range, in the past t past Time satisfies d1>0, and , it is considered that the vehicle is changing lanes to the target lane.

[0079] Where d1 is the difference between the y coordinate value of the vertex of the lane-changing vehicle in its lane-changing direction and the y coordinate value of the point closest to the vertex across the lane line; d2 is the difference between the y coordinate value of the diagonal vertex of the lane-changing vehicle corresponding to d1 and the y coordinate value of the point closest to the vertex across the lane line; abs() means taking the absolute value, p thr is the set threshold.

[0080] As shown in Figure 5 and Figure 6, the model obtained in step 2 is used to predict the trajectory of other lane-changing vehicles. d 、F d , N are re-divided and a safe lane change zone is selected. d Lane changing space formed by N F d Lane changing space formed by N

[0081] Among them, x N (t0+t future ) is N in the future future The vertical position at the moment, For L d In the future future The vertical position at the moment, F d In the future future The vertical position at the moment, The safe distance between N and M, For M and L d Keep a safe distance between F d Keep a safe distance from M, The safe distance between M and N.

[0082] If both gap1 and gap2 are not satisfied, then the two lane-changing spaces cannot meet the safety requirements, and the vehicle abandons the lane change and returns to the original lane; otherwise, the larger gap between the two is selected as the target lane-changing space.

[0083] In summary, the embodiment of the present application uses an LSTM neural network to establish a vehicle following model, completes the motion state prediction of the vehicle in the target lane, and establishes a lane changing space based on the prediction results; based on the state of vehicles in other lanes relative to the lane line, it determines whether the vehicle has the intention to change lanes to the target lane; at the same time, considering the situation where vehicles in other lanes change lanes to the target lane changing space, the lane changing trajectory is predicted based on the LSTM model, and the target lane changing space is re-divided and selected to ensure that the vehicle can complete the lane changing operation smoothly and safely, while maximizing passenger comfort and driving efficiency.

[0084] Next, the lane change trajectory planning device proposed according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0085] FIG7 is a block diagram of a lane-changing trajectory planning device according to an embodiment of the present application.

[0086] As shown in FIG7 , the lane-changing trajectory planning device 10 includes: an acquisition module 100 , a prediction module 200 and a planning module 300 .

[0087] Among them, the acquisition module 100 is used to obtain the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment; the prediction module 200 is used to predict the motion state of the front vehicle and the rear vehicle in the target lane at the future moment based on the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment; the planning module 300 is used to determine the target lane changing space based on the motion state of the front vehicle and the rear vehicle in the target lane at the future moment, and plan the lane changing trajectory of the current vehicle according to the target lane changing space.

[0088] It should be noted that the above explanation of the lane-changing trajectory planning method embodiment is also applicable to the lane-changing trajectory planning device of this embodiment, and will not be repeated here.

[0089] According to the lane-changing trajectory planning device proposed in the embodiment of the present application, by acquiring the acceleration data of the front and rear vehicles in the target lane in real time and predicting their future motion states, it is possible to dynamically evaluate the safety of lane changes, thereby making lane-changing decisions while maintaining a safe distance between the current vehicle and the front and rear vehicles. This can effectively improve the accuracy and safety of lane-changing decisions and reduce the risk of traffic accidents caused by not fully considering the speed changes of surrounding vehicles. At the same time, by rationally planning the lane-changing trajectory, it is possible to ensure a smooth lane-changing process and improve passenger comfort. This solves the problem that the related art does not fully consider the speed changes of surrounding vehicles and the situation where vehicles in other lanes change lanes at the same time, thereby increasing the risk of traffic accidents.

[0090] FIG8 is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0091] A memory 801 , a processor 802 , and a computer program stored in the memory 801 and executable on the processor 802 .

[0092] When the processor 802 executes the program, the lane change trajectory planning method provided in the above embodiment is implemented.

[0093] Furthermore, the vehicle further comprises:

[0094] The communication interface 803 is used for communication between the memory 801 and the processor 802 .

[0095] The memory 801 is used to store computer programs that can be run on the processor 802.

[0096] The memory 801 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0097] If the memory 801, processor 802, and communication interface 803 are implemented independently, the communication interface 803, memory 801, and processor 802 can be interconnected via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. Buses can be divided into address buses, data buses, control buses, etc. For ease of illustration, FIG8 shows only one thick line, but this does not mean that there is only one bus or only one type of bus.

[0098] Optionally, in a specific implementation, if the memory 801, the processor 802 and the communication interface 803 are integrated on a chip, the memory 801, the processor 802 and the communication interface 803 can communicate with each other through an internal interface.

[0099] The processor 802 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0100] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the lane change trajectory planning method as described above.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0102] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0103] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0104] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0105] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0106] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A lane-changing trajectory planning method, characterized in that: The following steps are involved: Get the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment; Based on the acceleration of the front vehicle and the rear vehicle in the target lane at the current moment, the motion state of the front vehicle and the rear vehicle in the target lane at the future moment is predicted; A target lane-changing space is determined based on the motion states of the preceding and following vehicles in the target lane at a future moment, and a lane-changing trajectory of the current vehicle is planned based on the target lane-changing space.

2. The lane-changing trajectory planning method according to claim 1, characterized in that: The obtaining of the acceleration of the preceding vehicle and the following vehicle in the target lane at the current moment includes: Obtain the speed of the front vehicle, the speed of the rear vehicle, the relative speed of the front vehicle and the rear vehicle, and the relative distance between the front vehicle and the rear vehicle in the target lane at the historical moment; The speed of the leading vehicle, the speed of the following vehicle, the relative speed between the leading vehicle and the following vehicle, and the relative distance between the leading vehicle and the following vehicle in the target lane at historical moments are input into a vehicle-following model, which outputs the acceleration of the leading vehicle and the following vehicle in the target lane at the current moment. The vehicle-following model is a neural network model that is trained using real traffic data.

3. The lane-changing trajectory planning method according to claim 1, characterized in that: The motion state of the leading vehicle includes the speed and longitudinal position of the leading vehicle, and the motion state of the trailing vehicle includes the speed and longitudinal position of the trailing vehicle; Determining the target lane-changing space according to the motion state of the preceding vehicle and the following vehicle in the target lane at a future moment includes: Obtain the first safety distance and the second safety distance between the current vehicle and the vehicle in front and the vehicle behind respectively; The target lane-changing space is constructed according to the speed and longitudinal position of the leading vehicle, the speed and longitudinal position of the trailing vehicle, the first safety distance, and the second safety distance.

4. The lane-changing trajectory planning method according to claim 1, characterized in that: After planning the lane-changing trajectory of the current vehicle according to the target lane-changing space, the method further includes: Identify whether there is a lane-changing vehicle that desires to change lanes to the target lane within the target range; If the lane-changing vehicle is identified, predicting the future lateral and longitudinal positions of the lane-changing vehicle based on the historical lateral and longitudinal positions of the lane-changing vehicle; The target lane-changing space is divided into a first space and a second space according to the lateral and longitudinal positions of the lane-changing vehicle at a future moment, and the lane-changing trajectory of the current vehicle is replanned according to the first space and the second space.

5. The lane-changing trajectory planning method according to claim 4, characterized in that: The identifying whether there is a lane-changing vehicle in the target range that desires to change lanes to the target lane includes: Identifying other vehicles in a target range that cross a lane line of the target lane; If the ratio of the other vehicle crossing the lane line is greater than the lane-changing threshold, it is determined that the other vehicle is a lane-changing vehicle that desires to change lanes to the target lane.

6. The lane-changing trajectory planning method according to claim 4, characterized in that: The predicting of the lateral and longitudinal positions of the lane-changing vehicle at a future time based on the lateral and longitudinal positions of the lane-changing vehicle at a historical time includes: The lateral and longitudinal positions of the lane-changing vehicle at historical moments are input into a trajectory prediction model, and the trajectory prediction model inputs the lateral and longitudinal positions of the lane-changing vehicle at future moments. The trajectory prediction model is a neural network model, and is trained using real lane-changing data.

7. The lane-changing trajectory planning method according to claim 4, characterized in that: The replanning of the lane-changing trajectory of the current vehicle according to the first space and the second space includes: Selecting the largest space between the first space and the second space; If the maximum space obtained distance is greater than the preset safety distance, the lane change trajectory of the current vehicle is replanned according to the maximum space.

8. A lane-changing trajectory planning device, characterized in that: include: The acquisition module is used to obtain the acceleration of the preceding vehicle and the following vehicle in the target lane at the current moment; A prediction module is used to predict the motion state of the leading vehicle and the following vehicle in the target lane at a future moment based on the acceleration of the leading vehicle and the following vehicle in the target lane at a current moment; The planning module is used to determine the target lane-changing space based on the motion state of the leading vehicle and the following vehicle in the target lane at a future moment, and to plan the lane-changing trajectory of the current vehicle based on the target lane-changing space.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane change trajectory planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the lane change trajectory planning method according to any one of claims 1 to 7.

Images