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

Abstract

The invention discloses a vehicle lane changing control method and device, electronic equipment, a storage medium and a vehicle, and relates to the technical field of vehicle automatic drive.A first driving parameter, a second driving parameter and road information of the vehicle are obtained, the second driving parameter comprises a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles, and the road information of each vehicle is obtained; according to the first driving parameter, the second driving parameter and the road information, determining a planned lane changing track of the vehicle, predicted acceleration duration of the vehicle and predicted acceleration of the vehicle, and optimizing the planned lane changing track and the predicted acceleration of the vehicle through a nonlinear planning method to obtain a target lane changing track and a target acceleration, the target lane changing track and the target acceleration-time function are smooth curves, the vehicle is controlled to start acceleration, so that the vehicle runs from the original lane to the target lane according to the target lane changing track, and the lane changing track and the acceleration-time function are smooth curves, so that the acceleration of the vehicle is smoother, and the comfort of passengers is improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle automatic driving technology, and in particular to a vehicle lane changing control method, device, electronic equipment, storage medium and vehicle. Background Art

[0002] At present, point-to-point autonomous driving tasks on high-speed structured roads can already achieve point-to-point full-range autonomous driving. However, in addition to requiring the car to have adaptive cruise control capabilities, there are higher requirements for merging, converging, avoiding obstacles, etc., so as to complete the entire stage of driving. Typical merging and merging scenarios include: vehicles entering the secondary road from the main road, or entering the main road from the secondary road; on the highway, vehicles enter the highway from the ramp, or vehicles drive on high-grade roads with multiple lanes on the upper and lower levels. In scenarios such as merging, converging, and avoiding obstacles, changing lanes is the key to evaluating the level of autonomous driving.

[0003] The existing lane-changing scheme uses a large acceleration when overtaking, and the acceleration is constant, which will cause the vehicle to have very obvious acceleration oscillations, thereby resulting in poor passenger comfort.

[0004] Therefore, the existing lane changing methods still need to be improved in terms of driving comfort. Summary of the invention

[0005] One of the objects of the present invention is to provide a vehicle lane changing control method to solve the problem of acceleration oscillation when changing lanes, resulting in a poor user driving experience; the second object is to provide a vehicle lane changing control device; the third object is to provide an electronic device; the fourth object is to provide a readable storage medium; and the fifth object is to provide a vehicle.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows: A vehicle lane-changing control method, the method comprising: Acquire a first driving parameter, a second driving parameter, and road information of the vehicle, wherein the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; Determining a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; The planned lane-changing trajectory and the estimated acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration, wherein the target lane-changing trajectory and the target acceleration-time function are smooth curves; The vehicle is controlled to start accelerating according to the target acceleration within the estimated acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane changing trajectory.

[0007] According to the above technical means, by obtaining the first driving parameter, the second driving parameter and the road information of the vehicle, the planned lane changing trajectory of the vehicle, the expected acceleration time of the vehicle and the expected acceleration of the vehicle are determined according to the first driving parameter, the second driving parameter and the road information, and then the planned lane changing trajectory and the expected acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane changing trajectory and a target acceleration, and finally the vehicle is controlled to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle drives from the original lane to the target lane according to the target lane changing trajectory. On the one hand, a higher probability of lane changing success can be achieved to ensure driving safety, and on the other hand, the lane changing trajectory and acceleration can be appropriately adjusted. Since the lane changing trajectory and the acceleration-time function are both smooth curves, that is, the target lane changing trajectory and the target acceleration have a gentler slope, smoother transition, no sharp points, and no mutation points, which can make the acceleration of the vehicle smoother, avoid sudden acceleration or sudden deceleration of the vehicle, and thus improve the comfort of passengers.

[0008] Further, determining the lane change trajectory of the vehicle, the estimated acceleration time of the vehicle, and the estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information includes: Inputting the first driving parameter and the second driving parameter into a trajectory prediction model to obtain a motion state of the vehicle and motion states of multiple surrounding vehicles in a first future time period, wherein the motion states of the multiple surrounding vehicles include the motion state of each of the multiple surrounding vehicles; Determining the planned lane change trajectory according to the vehicle motion state, the motion states of the plurality of surrounding vehicles and the road information; Determining an estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameter, and the second driving parameter; The expected acceleration of the vehicle is determined according to the planned lane change trajectory, the first driving parameter and the expected acceleration time of the vehicle.

[0009] Further, determining the lane change trajectory according to the motion state of the vehicle, the motion states of the plurality of surrounding vehicles and the road information includes: Determine, according to the road information, a plurality of lane-changing spaces in a lane adjacent to the original lane, wherein the lane-changing spaces are gaps in the adjacent lane that can be used for lane-changing; Determine a target lane-changing space from the plurality of lane-changing spaces by using the motion state of the vehicle and the motion states of the plurality of surrounding vehicles; The planned lane changing trajectory is determined according to the vehicle motion state and the target lane changing space.

[0010] Further, the second driving parameter includes a driving parameter of a vehicle directly in front, a driving parameter of a vehicle in front of a side, and a driving parameter of a vehicle behind a side. The determining the estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameter, and the second driving parameter includes: Determining a maximum lane change duration according to the planned lane change trajectory, the first driving parameter, and the driving parameter of the vehicle directly in front, wherein the maximum lane change duration is a maximum time period during which the vehicle can accelerate; Inputting the vehicle motion state and the driving parameters of the side front vehicle into the lane changing game model to obtain a first lane changing duration; Inputting the motion state of the vehicle and the driving parameters of the side and rear vehicle into the lane-changing game model to obtain a second lane-changing duration; When the first lane changing duration is less than or equal to the limit lane changing duration, and the second lane changing duration is less than or equal to the limit lane changing duration, the larger of the first lane changing duration and the second lane changing duration is used as the estimated acceleration duration of the vehicle.

[0011] Further, the planned lane changing trajectory and the estimated acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane changing trajectory and a target acceleration, including: Projecting the driving trajectories of the plurality of surrounding vehicles onto a displacement-time graph to obtain a position constraint, wherein the driving trajectories of the plurality of surrounding vehicles include the driving trajectory of each of the plurality of surrounding vehicles, and the driving trajectories of the plurality of surrounding vehicles are obtained by inputting the second driving parameter into a trajectory prediction model; Determine speed constraint conditions according to a preset vehicle speed range; The planned lane-changing trajectory is optimized using a target cost function, the position constraint, and the speed constraint to obtain the target lane-changing trajectory and the target acceleration.

[0012] Further, projecting the driving trajectories of the plurality of surrounding vehicles into a displacement-time graph to obtain position constraints includes: Projecting the driving trajectory of the vehicle directly in front of the vehicle in the first time period and the driving trajectory of the vehicle in front of the vehicle inside the estimated acceleration time onto the displacement-time graph to obtain the upper boundary of the position constraint; The driving trajectory of the vehicle behind the vehicle inside the expected acceleration time is projected into the displacement-time graph to obtain the lower boundary of the position constraint.

[0013] Furthermore, the method further comprises: When the vehicle starts accelerating, obtaining a lane change start time, a current first driving parameter, and a current second driving parameter of the vehicle; Inputting the current first driving parameter and the current second driving parameter into a trajectory prediction model, obtaining a first distance between the vehicle and a vehicle directly in front, and a second distance between the vehicle and a target vehicle directly behind in a second time period in the future, wherein the second time period in the future is the difference between the estimated acceleration time of the vehicle and the lane change start time; When the vehicle meets the lane change back-off condition, the vehicle is controlled to give up the lane change and return to the original lane. The lane change back-off condition includes: the first distance is less than the first safety distance, or the second distance is less than the second safety distance.

[0014] Furthermore, the method further comprises: When a third distance between the vehicle and a target vehicle to the rear in the original lane is less than a third safety distance, or there is a lane-changing vehicle that desires to change lanes to the original lane, the vehicle is controlled to travel in the target lane and a prompt message is output, wherein the prompt message is used to prompt the driver that there is a risk of collision.

[0015] A vehicle lane changing device, the device comprising: An acquisition module, used to acquire a first driving parameter, a second driving parameter and road information of a vehicle, wherein the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; a determination module, configured to determine a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; A calculation module, used for optimizing the planned lane-changing trajectory and the estimated acceleration of the vehicle by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration, wherein the target lane-changing trajectory and the target acceleration-time function are smooth curves; The control module is used to control the vehicle to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane change trajectory.

[0016] An electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the vehicle lane change control method as described above.

[0017] A readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the vehicle lane change control method as described above are implemented.

[0018] A vehicle comprises the vehicle lane-changing control device as described above.

[0019] Beneficial effects of the present invention: In the embodiment of the present application, by acquiring the first driving parameter, the second driving parameter and the road information of the vehicle, the second driving parameter includes multiple driving parameters of each of the multiple surrounding vehicles, and then according to the first driving parameter, the second driving parameter and the road information, the planned lane changing trajectory of the vehicle, the expected acceleration time of the vehicle and the expected acceleration of the vehicle are determined, and then the planned lane changing trajectory and the expected acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane changing trajectory and a target acceleration, and finally the vehicle is controlled to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle drives from the original lane to the target lane according to the target lane changing trajectory. On the one hand, a higher probability of lane changing success can be achieved to ensure driving safety, and on the other hand, the lane changing trajectory and acceleration can be appropriately adjusted. Since the lane changing trajectory and the acceleration-time function are both smooth curves, that is, the target lane changing trajectory and the target acceleration have a gentler slope, smoother transition, no sharp points, and no mutation points, which can make the acceleration of the vehicle smoother, avoid sudden acceleration or sudden deceleration of the vehicle, thereby improving the comfort of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is a flow chart of the steps of a vehicle lane changing control method provided by an embodiment of the present application; Figure 2 is a flowchart of specific steps of a vehicle lane change control provided by an embodiment of the present application; Figure 3A is a schematic diagram of a lane-changing space provided in an embodiment of the present application; Figure 3B is a schematic diagram of another lane-changing space provided in an embodiment of the present application; Figure 4 is a flowchart of specific steps of a vehicle lane change control provided by an embodiment of the present application; Figure 5A is a schematic diagram of a lane changing trajectory of a vehicle provided in an embodiment of the present application; Figure 5B is a schematic diagram of the acceleration of a vehicle provided in an embodiment of the present application; Figure 6 is a block diagram of a vehicle lane change control device provided in an embodiment of the present application; Figure 7 It is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0021] The following will describe the embodiments of the present invention with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention, not for limiting the scope of protection of the present invention.

[0022] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention, and thus the drawings only show components related to the present invention rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0023] When a driver is driving a vehicle, for some reason, such as the pursuit of higher driving efficiency, the constraints of road traffic markings, etc., he or she may have the intention to change lanes (hereinafter referred to as "lane change"). Since lane change behavior involves the interaction of vehicles on multiple lanes, if the lane change cannot be reasonably planned, it may affect the traffic efficiency of the road, and even cause traffic accidents in serious cases. Generally speaking, the lane change process can be divided into the intention generation stage, the execution stage, and the adjustment stage. The purpose of the intention generation stage is to create a lane change. In the intention generation stage, the target lane is selected and a safe lane change space is found. If no suitable lane change space is found, the lane change behavior is abandoned; the purpose of the execution stage is to start acceleration to complete the lane change. In the execution stage, it is necessary to plan the trajectory in real time according to the motion status of multiple surrounding vehicles, and optimize the planned trajectory; the purpose of the adjustment stage is to determine whether to return to the original lane. In the adjustment stage, the vehicle should dynamically adjust the speed to follow the vehicle in front of the target lane.

[0024] In summary, reasonable judgments need to be made on the motion states of multiple surrounding vehicles during both the intention generation and execution stages to ensure the safety requirements of lane changing behavior. In the prior art, due to the use of a large acceleration when overtaking and the constant acceleration, the vehicle will experience very obvious acceleration oscillations, which will lead to poor passenger comfort. At the same time, the prior art does not take into account the scenario of retracting to the original lane after initiating the lane change, nor does it take into account the scenario of prohibiting retracting to the original lane when vehicles in other lanes are simultaneously changing lanes to the target lane, which may cause traffic accidents.

[0025] The vehicle lane changing control method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0026] Figure 1is a flow chart of the steps of a vehicle lane change control method provided by an embodiment of the present application, such as Figure 1 As shown, the method may include: Step 101: Acquire a first driving parameter, a second driving parameter, and road information of a vehicle.

[0027] In the embodiment of the present application, the second driving parameter includes a plurality of driving parameters of each vehicle among a plurality of surrounding vehicles.

[0028] Optionally, multiple surrounding vehicles may include: a vehicle directly in front, a vehicle directly behind, a vehicle in front to the side, and a vehicle to the side behind; driving parameters may include: position, speed, acceleration, etc., wherein acceleration may include lateral acceleration and / or longitudinal acceleration, and acceleration has magnitude and direction; the second driving parameters may include: driving parameters of the vehicle directly in front, driving parameters of the vehicle directly behind, driving parameters of the vehicle in front to the side, and driving parameters of the vehicle to the side behind, that is, the second driving parameters may include: the position, speed, acceleration, etc. of the vehicle directly in front, the position, speed, acceleration, etc. of the vehicle directly behind, the position, speed, acceleration, etc. of the vehicle in front to the side, and the position, speed, acceleration, etc. of the vehicle to the side behind.

[0029] It can be understood that the embodiment of the present application can collect the second driving parameter in real time through the vehicle-mounted sensor, wherein the second driving parameter is dynamic and can reflect the speed change of multiple surrounding vehicles and the distance from the own vehicle, so as to facilitate the subsequent prediction of the future movement status of multiple surrounding vehicles and the change of the distance from the own vehicle.

[0030] In some embodiments, before step 101, the above-mentioned vehicle lane changing control method may further include: when the trigger conditions are met, starting the vehicle's creative lane changing mode, wherein the creative lane changing mode may include: changing lanes with lights, changing lanes with voice requests, automatic overtaking lane changing, changing lanes on ramps, merging lanes, changing lanes to avoid obstacles, etc.

[0031] Step 102: Determine the planned lane change trajectory of the vehicle, the estimated acceleration time of the vehicle, and the estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information.

[0032] In the embodiment of the present application, the road information may include lane line information, and the lane line information includes the current lane, the left adjacent lane, and the right adjacent lane. The lane line information may also include lane line types, such as dashed line, solid line, dashed line to solid line, solid line to dashed line, etc. Among them, the current lane refers to the lane where the vehicle is located, and the current lane may also be called the "original lane". The target lane refers to the lane that the vehicle wants to change lanes to, and the target lane may be the left adjacent lane or the right adjacent lane of the current lane.

[0033] In some embodiments, the road information may also include obstacle information, where the obstacle information includes the location and size of the obstacle.

[0034] Exemplarily, in step 102, road information can be identified by an on-board visual sensor according to the current position of the vehicle; in step 102, road information can also be obtained by sending a road information acquisition request to a cloud server and processing information based on the road information request returned by the cloud server.

[0035] In some embodiments, the estimated acceleration time and acceleration of the vehicle can be comfort calibration parameters obtained after multiple lane change tests, and different creative lane change modes correspond to different coefficients. For example, in special scenarios such as merging, avoiding obstacles, and going down the ramp, the creative lane change completion time is limited to 4 seconds (s), the minimum deceleration coefficient is calibrated to -3, and the maximum acceleration coefficient is calibrated to +0.8.

[0036] Step 103: Optimize the planned lane-changing trajectory and the estimated acceleration of the vehicle by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration.

[0037] Among them, the target lane-changing trajectory and the target acceleration-time function are smooth curves.

[0038] In some embodiments, a time-dependent polynomial equation may be used to establish a lane-changing trajectory optimization model to ensure that the lane-changing trajectory and its derivative functions (speed, acceleration) are continuous and smooth.

[0039] It is understood that nonlinear programming is a method for solving optimization problems with one or more nonlinear functions in the objective function or constraints. Quadratic programming is a special type of mathematical programming problem in nonlinear programming. Its objective function is a quadratic function and the constraints are linear constraints, which are easier to solve.

[0040] For example, when solving the target lane-changing trajectory and the target acceleration, the target function is determined based on the preset optimization target, and then the multiple constraints that need to be followed when solving the parameters in the cost function are determined based on the first driving parameter and the target driving parameter. The constraints can be linear constraints or nonlinear constraints, so that the lane-changing trajectory optimization model based on quadratic programming is obtained. The planned lane-changing trajectory and the estimated acceleration of the vehicle are input into the lane-changing trajectory optimization model to obtain the output target lane-changing trajectory and target acceleration. Due to the characteristics of quadratic programming, the target lane-changing trajectory and the target acceleration-time function are smooth curves with a gentler slope, and the curve trajectory of the target lane-changing trajectory and the target acceleration has a smooth transition, no sharp points, and no mutation points. In this way, the acceleration of the vehicle can be smoother, avoiding sudden acceleration or deceleration of the vehicle, thereby improving the comfort of the passengers.

[0041] In some embodiments, step 103 may include: substituting the constraint conditions into a quadratic programming (QP) solver, optimizing the objective function, and obtaining an optimization result, thereby effectively improving the smoothness of the vehicle when changing lanes.

[0042] Step 104: Control the vehicle to start accelerating according to the target acceleration within the estimated acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane change trajectory.

[0043] In some embodiments, before step 104, the above-mentioned vehicle lane change control method further includes: when the vehicle does not start acceleration, judging whether the vehicle meets the lane change inhibition condition according to the current first driving parameter and the current second driving parameter; when the vehicle meets the lane change inhibition condition, controlling the vehicle to give up lane change; when the vehicle does not meet the lane change inhibition condition, controlling the vehicle to start acceleration so that the vehicle travels from the original lane to the target lane according to the target lane change trajectory. Among them, the lane change inhibition condition may include: the distance between the vehicle and the side front vehicle or the side rear vehicle is less than the minimum safety distance, or the speed difference between the vehicle and the side front vehicle or the side rear vehicle is less than the minimum safety speed. Optionally, the minimum safety distance and the minimum safety speed are determined based on the vehicle speed and the relative distance between the vehicle and the vehicle directly in front.

[0044] In summary, in the embodiment of the present application, by obtaining the first driving parameter, the second driving parameter and the road information of the vehicle, the second driving parameter includes multiple driving parameters of each vehicle in the multiple surrounding vehicles, and then according to the first driving parameter, the second driving parameter and the road information, the planned lane changing trajectory of the vehicle, the expected acceleration time of the vehicle and the expected acceleration of the vehicle are determined, and then the planned lane changing trajectory and the expected acceleration of the vehicle are optimized by the nonlinear programming method to obtain the target lane changing trajectory and the target acceleration, and finally the vehicle is controlled to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle drives from the original lane to the target lane according to the target lane changing trajectory. On the one hand, a higher probability of successful lane changing can be achieved to ensure driving safety, and on the other hand, the lane changing trajectory and acceleration can be appropriately adjusted. Since the lane changing trajectory and the acceleration-time function are both smooth curves, that is, the target lane changing trajectory and the target acceleration have a gentler slope, smoother transition, no sharp points, and no mutation points, which can make the acceleration of the vehicle smoother, avoid sudden acceleration or sudden deceleration of the vehicle, thereby improving the comfort of passengers.

[0045] In some embodiments, see Figure 2 , step 102 may include the following steps.

[0046] Step 201: Input the first driving parameter and the second driving parameter into a trajectory prediction model to obtain the motion state of the vehicle and the motion states of multiple surrounding vehicles in a first time period in the future.

[0047] In the embodiment of the present application, the motion states of the multiple surrounding vehicles include the motion state of each vehicle in the multiple surrounding vehicles.

[0048] Optionally, the motion state may include acceleration and driving trajectory.

[0049] In an embodiment of the present application, the trajectory prediction model may be a neural network model, and the trajectory prediction model is trained using real traffic data to obtain a trained trajectory prediction model.

[0050] Exemplarily, the trajectory prediction model can be a mathematical model or algorithm that can be used to describe and predict the behavior of a vehicle following a preceding vehicle on the road, such as a safety distance model; the neural network model can be a machine learning model based on an artificial neural network that can handle complex traffic conditions, such as a long short-term memory (LSTM) neural network; the real traffic data can be data collected in an actual road traffic environment, such as vehicle speed, acceleration, position, time and other information.

[0051] It can be understood that the embodiments of the present application can establish a vehicle trajectory prediction 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, wherein the first driving parameter and the second driving parameter are input into the trajectory prediction model to predict the acceleration of multiple surrounding vehicles, thereby providing the driver with more accurate and timely driving assistance information, thereby predicting the motion state of the vehicle and the motion state of multiple surrounding vehicles in the first time period in the future.

[0052] For example, the LSTM neural network establishes a vehicle trajectory prediction model, and the input features are the vehicle speed of the vehicle 30 meters per second (m / s), the relative speed between the vehicle and the vehicle in front 10m / s, and the relative acceleration between the vehicle and the vehicle in front 5m / s 2 , the output is the acceleration of the vehicle and the acceleration of the vehicle in front in the next 8 seconds. Optionally, the trajectory prediction model can also output the distance between the vehicle and the vehicle in front in the next 8 seconds, the driving trajectory of the vehicle, the driving trajectory of the vehicle in front, or other driving parameters, which are not limited in the embodiments of the present application.

[0053] Step 202: Determine a planned lane change trajectory based on the vehicle's motion state, the motion states of multiple surrounding vehicles, and road information.

[0054] In some embodiments, step 1022 may include the following steps: Determine, according to the road information, a plurality of lane-changing spaces in adjacent lanes of the original lane, where the lane-changing spaces are gaps in adjacent lanes that can be used for lane-changing; Determine a target lane-changing space from a plurality of lane-changing spaces by using a motion state of the vehicle and motion states of a plurality of surrounding vehicles; According to the vehicle's motion state and the target lane-changing space, the planned lane-changing trajectory is determined.

[0055] In an embodiment of the present application, the lane changing trajectory may be a driving trajectory for safely transitioning from the current lane to the target lane calculated based on the target lane changing space, the motion state of the vehicle, and the motion states of multiple surrounding vehicles.

[0056] For example, see Figure 3A and Figure 3B , the lane changing space in the embodiment of the present application can be diversified. When the current vehicle needs to change lanes to an adjacent lane, when the target lane is the left lane, multiple lane changing spaces such as Figure 3A As shown in the figure, when the target lane is the right lane, multiple lane change spaces are as follows Figure 3B shown.

[0057] In a possible implementation, determining a target lane changing space from a plurality of lane changing spaces based on a motion state of the vehicle and the motion states of a plurality of surrounding vehicles may include: establishing a cost calculation function, the cost calculation function being used to predict a real-time state of the vehicle within a preset lane changing time period at a preset acceleration or a preset deceleration; generating constraints based on the motion states of a plurality of surrounding vehicles; scoring a plurality of lane changing spaces based on the cost calculation function and the constraints; and determining a lane changing space with the highest score among the plurality of lane changing spaces as the target lane changing space.

[0058] Exemplarily, the specific method of establishing the cost calculation function is as follows: obtaining a preset acceleration unit and a cost calculation function formula; Initialize the cost calculation function formula corresponding to each acceleration unit; set a preset lane change creation time period according to the trajectory prediction model to obtain the speed and position state of the vehicle in front; use the preset evaluation function to determine whether the vehicle and the vehicle in front meet the safety distance at all times to support lane change during the lane change creation time period, and obtain the first score value of multiple lane change spaces; similarly, use the evaluation function to calculate the second score value of the vehicle in front and the third score value of the vehicle behind; use the lane change space with the highest score as the target lane change space.

[0059] In a possible implementation, before determining the planned lane change trajectory according to the vehicle's motion state and the target lane change space, the vehicle lane change control method may further include: determining whether the vehicle's lane change sign meets the activation condition; if the lane change sign meets the activation condition, determining the planned lane change trajectory according to the vehicle's motion state and the target lane change space, and recording the acceleration time; if the lane change sign does not meet the activation condition, abandoning the lane change. Optionally, the activation condition of the lane change sign includes: within a preset time period, the second score value is continuously greater than or equal to a preset second scoring threshold, and the third score value is continuously greater than or equal to a preset third scoring threshold.

[0060] In another possible implementation, determining a target lane changing space from multiple lane changing spaces based on the motion state of the vehicle and the motion states of multiple surrounding vehicles may also include: calculating an optimal lane changing speed for each lane changing space, where the optimal lane changing speed is a speed with minimum lane changing cost; determining an evaluation score for each lane changing space based on the optimal lane changing speed and the acceleration time, as well as a preset weight formula; and selecting the lane changing space with the highest score as the target lane changing space.

[0061] In a possible implementation, determining a planned lane-changing trajectory according to the vehicle's motion state and the target lane-changing space may include: sending a lane-changing request to a cloud server, the lane-changing request including the vehicle's motion state and the target lane-changing space; and receiving the planned lane-changing trajectory returned by the cloud server. Optionally, the cloud server may be a server corresponding to a navigation application software or a map application software.

[0062] In another possible implementation, the vehicle lane change control method may further include: when the number of the determined lane change spaces is one, using the lane change space as a target lane change space.

[0063] In some embodiments, the above-mentioned vehicle lane change control method may further include: exiting the lane change mode when the adjacent lane cannot determine the lane change space. For example, in a congested scene, before starting acceleration, it can be determined whether to exit the lane creation mode based on whether the lane change space meets the minimum safety distance, so as to avoid the overall uneven following caused by the acceleration switching of creation or straight driving.

[0064] Through the above-mentioned technical means, the optimal target lane changing space is determined according to the predicted motion state of the vehicle and the motion states of multiple surrounding vehicles, and whether there is a collision risk during the lane changing process is accurately judged to improve driving safety. The lane changing trajectory of the current vehicle is planned according to the target lane changing space to avoid unnecessary waiting and tentative lane changing, significantly improve lane changing efficiency and road capacity, ensure a smooth lane changing process and enhance passenger comfort.

[0065] Step 203: Determine an estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameter, and the second driving parameter.

[0066] In some embodiments, the second driving parameters include driving parameters of the vehicle directly in front, driving parameters of the vehicle in front of the side, and driving parameters of the vehicle behind the side. Step 203 may include the following steps: Determine a maximum lane change duration according to the planned lane change trajectory, the first driving parameter and the driving parameter of the vehicle directly in front, where the maximum lane change duration is a maximum time period during which the vehicle can accelerate; Input the motion state of the vehicle and the driving parameters of the vehicle in front and on the side into the lane-changing game model to obtain the first lane-changing duration; Input the motion state of the vehicle and the driving parameters of the side and rear vehicles into the lane-changing game model to obtain the second lane-changing duration; When the first lane changing duration is less than or equal to the limit lane changing duration, and the second lane changing duration is less than or equal to the limit lane changing duration, the larger of the first lane changing duration and the second lane changing duration is used as the estimated acceleration duration of the vehicle.

[0067] In one possible implementation, determining the maximum lane change duration based on the planned lane change trajectory, the first driving parameter and the driving parameter of the vehicle directly in front may include: obtaining a preset creative acceleration time; within the creative acceleration time, performing a finite number of cycles under the constraints of confirming suitability for lane change, and gradually increasing the creative acceleration time until the maximum lane change duration is found.

[0068] In an embodiment of the present application, the lane changing game model may be a neural network model, and the lane changing game model is trained using real traffic data to obtain a trained lane changing game model.

[0069] Exemplarily, the lane changing game model can be a mathematical model or algorithm that can be used to describe and predict whether a vehicle can meet a safe distance when changing lanes on the road, such as a Bayesian Stackelberg Game model; the optimal solution obtained by solving the payoff function of the Bayesian Stackelberg Game model is the first lane changing time or the second lane changing time.

[0070] It can be understood that the maximum lane change duration is the duration for the self-vehicle to meet the safe distance with the vehicle directly in front, the first lane change duration is the duration for the self-vehicle to meet the safe distance with the vehicle in front of it, and the second lane change duration is the duration for the self-vehicle to meet the safe distance with the vehicle behind it. When the first lane change duration is less than or equal to the maximum lane change duration, and the second lane change duration is less than or equal to the maximum lane change duration, it means that the self-vehicle meets the safe distance with the vehicle directly in front, the vehicle in front of it, and the vehicle behind it, and there is no risk of collision. In order to ensure the safety of vehicle lane changes, the larger of the first and second lane change durations is used as the estimated acceleration duration of the self-vehicle.

[0071] In some embodiments, the above-mentioned vehicle lane change control model may further include: when the first lane change time is longer than the limit lane change time, or the second lane change time is longer than the limit lane change time, giving up lane change.

[0072] Through the above-mentioned technical means, game theory is introduced into the lane changing trajectory planning method of autonomous driving vehicles. Autonomous driving vehicles can judge whether to continue changing lanes based on the motion status of themselves and multiple surrounding vehicles. The influence of multiple targets in the lane changing process can be effectively considered, which reduces the possibility of vehicle collision and improves lane changing safety.

[0073] Step 204: Determine the expected acceleration of the vehicle according to the planned lane change trajectory, the first driving parameter, and the expected acceleration time of the vehicle.

[0074] In some embodiments, step 204 may include: sending a lane change request to a cloud server, the lane change request including a planned lane change trajectory, a first driving parameter, and an estimated acceleration time of the vehicle; and receiving the estimated acceleration of the vehicle returned by the cloud server. Optionally, the cloud server may be a server corresponding to a navigation application software or a map application software.

[0075] In summary, the embodiment of the present application predicts the motion state of the ego vehicle and the motion states of multiple surrounding vehicles based on the trajectory prediction model, and then determines the planned lane change trajectory in combination with the road information. Finally, based on the obtained planned lane change trajectory, the estimated acceleration time of the ego vehicle and the estimated acceleration time of the ego vehicle are determined, and the estimated acceleration of the ego vehicle is determined, which can improve the consistency of autonomous driving decisions and control smoothness.

[0076] In some embodiments, see Figure 4 , step 103 may include the following steps.

[0077] Step 301: Project the driving trajectories of multiple surrounding vehicles into a displacement-time graph to obtain position constraints.

[0078] In the embodiment of the present application, the driving trajectories of the multiple surrounding vehicles include the driving trajectory of each of the multiple surrounding vehicles.

[0079] In the embodiment of the present application, the driving trajectories of multiple surrounding vehicles are obtained by inputting the second driving parameter into the trajectory prediction model.

[0080] In the embodiment of the present application, the method of obtaining the driving trajectories of multiple surrounding vehicles is similar to step 201 and will not be repeated here.

[0081] In some embodiments, step 301 may include: projecting the driving trajectory of the vehicle directly in front and the driving trajectory of the vehicle in front inside the expected acceleration time of the vehicle in the first time period into the displacement-time graph to obtain the upper boundary of the position constraint.

[0082] The driving trajectory of the vehicle behind the vehicle inside the expected acceleration time of the ego vehicle is projected into the displacement-time graph to obtain the lower boundary of the position constraint.

[0083] Exemplarily, the first time period may be 8 seconds.

[0084] In some embodiments, since the vehicle starts accelerating in the time period after the creative lane change is successful, the difference between the first time period and the estimated acceleration time of the vehicle is also called the creative lane change completion time, which is obtained by calibration, and different creative lane change modes correspond to different creative lane change completion times. In other words, the dividing line projected onto the displacement-time graph can be the creative lane change completion time.

[0085] For example, see Figure 5A , the creation of lane change completion time is 4s. During the creation of lane change completion time, only the vehicle in front is used as the upper boundary of the vehicle's driving trajectory. After the creation of lane change completion time, the vehicle needs to form the final upper and lower boundary constraints for the three targets of the vehicle in front, the vehicle in front of the side, and the vehicle behind the side. First, all 8s trajectories of the nearest vehicle in front (following target) are mapped into the ST graph. Starting from the 5th second, the driving trajectory of the vehicle in front of the side and the driving trajectory of the vehicle behind the side are mapped into the ST graph for processing. The vehicle in front of the lane change space, 4s is the estimated time for the vehicle to start after the creation of the lane. In this way, the number of surrounding vehicles that finally enter the ST graph does not exceed 3, and traverses from 8s to 0s with a sampling period of 0.1s to form a monotonous upper and lower boundary, which is used as the inequality position constraint of QP.

[0086] Through the above technical means, it is considered that the vehicle's lane change is divided into the intention generation stage and the actual execution stage. That is to say, it takes a certain amount of time for the vehicle to create a lane change. Projecting multiple surrounding vehicles in different directions in different time periods can improve the accuracy of lane change trajectory optimization and reduce the amount of calculation for the solution.

[0087] Step 302: Determine a speed constraint condition according to a preset vehicle speed range.

[0088] In the embodiment of the present application, different creative lane change modes correspond to different preset vehicle speed ranges, and comfortable acceleration and deceleration upper limits and slope upper limits are calibrated in different scenarios to form corresponding inequality constraints.

[0089] In a possible implementation, the vehicle speed range may also be obtained based on the vehicle speed before the lane change. For example, in a merging lane change scenario, the vehicle speed range is less than or equal to 115% of the set vehicle speed and greater than or equal to 40% of the vehicle speed before the lane change.

[0090] Step 303: Optimize the planned lane-changing trajectory using the target cost function, position constraints, and speed constraints to obtain a target lane-changing trajectory and a target acceleration.

[0091] In a possible implementation, the target cost function is a function expression of the plane curve of the current lane and the target lane that is fitted. Optionally, the road plane information is collected, and the curved road information is collected using high-precision maps, sensors, and global positioning system (GPS) equipment to obtain the horizontal and vertical coordinates x, y of the plane sample points of the curved road section and the curve length s between adjacent sample points, and the Chebyshev interpolation method is used to fit the function expression of the plane curve of the current lane and the target lane.

[0092] In the embodiment of the present application, since the position, speed and acceleration of the lane change trajectory need to be seamlessly connected, the constraint conditions may also include equality constraints of the starting point and the connection point.

[0093] Exemplarily, the expression of the target cost function is as follows: (1) In formula (1), H represents the matrix obtained by converting the optimization objective function into the QP formula form, and x and f both represent vectors in the feasible domain of the objective cost function.

[0094] The constraints are as follows: (2) (3) (4) Wherein, formula (2) represents the upper and lower bounds of S, st represents the valid set, LB represents the upper bound of S, and UB represents the lower bound of S; formula (3) represents the equality constraints of the starting point and the connection point, Indicates the starting point, represents the connection point; Formula (4) represents the speed constraint condition, Indicates the speed range, Represents the velocity boundary.

[0095] In some embodiments, step 303 may include: solving the target cost function to obtain the planned speed, planned acceleration and the derivative of the planned acceleration of each sampling point of the vehicle in the to-be-traveled trajectory, thereby obtaining the target lane change trajectory and the target acceleration. The algorithm used to solve the target cost function may include: Lagrangian method, interior point method, effective set method, ellipsoid algorithm, etc.

[0096] Optionally, the above-mentioned vehicle lane change control method may further include: performing a second check on the target acceleration solved by QP within the estimated acceleration time of the vehicle. For example, if the lane change time is 3s and the first time period is 7s, then the estimated acceleration time of the vehicle is 4s, and the target lane change trajectory is obtained from the 4th to 7th seconds and the upper and lower boundaries of the actual S are checked for safety distance.

[0097] In other embodiments, step 303 may also include: solving a target cost function that satisfies the constraint conditions, and taking the optimal solution as the target lane changing trajectory; and determining the target acceleration using an anchor point method based on the target lane changing trajectory.

[0098] In another possible implementation, see Figure 5B , multiple surrounding vehicles are only side and rear vehicles, and the speed of the side and rear vehicles is greater than the preset speed threshold; step 303 may also include: constructing the expected acceleration trajectory and deceleration trajectory of the vehicle within the first time period, wherein the expected acceleration trajectory of the vehicle is generated according to the maximum acceleration value, and the expected deceleration trajectory is generated according to the minimum acceleration value; using the acceleration correction reference trajectory to correct the original acceleration trajectory. Optionally, the maximum acceleration value can be obtained by looking up the speed difference between the vehicle and the side and rear vehicle. For example, when the side and rear vehicle is 3m / s faster than the vehicle, the maximum acceleration value is +130% of the acceleration calibration value, and the minimum acceleration value is -50% of the acceleration calibration value. In this way, unnecessary false acceleration or false deceleration experience can be generated, so that the vehicle remains in a small range of fluctuations on the uniform speed reference line.

[0099] In summary, in the embodiments of the present application, since the mathematical model based on quadratic programming is easier to solve, the amount of calculation during lane change planning is reduced, which can reduce the consumption of computing resources and improve computing efficiency. The real-time and applicability of the vehicle's position trajectory and acceleration control during lane change are improved, thereby enhancing the user's driving experience.

[0100] In some embodiments, the above vehicle lane changing control method may further include the following steps: When the vehicle starts accelerating, obtaining the vehicle's start lane change duration, current first driving parameter, and current second driving parameter; Inputting the current first driving parameter and the current second driving parameter into the trajectory prediction model, obtaining a first distance between the vehicle and the vehicle directly in front and a second distance between the vehicle and the target vehicle directly behind in a second time period in the future, wherein the second time period in the future is the difference between the estimated acceleration time of the vehicle and the lane change initiation time; When the vehicle meets the lane change back-off conditions, the vehicle is controlled to give up the lane change and return to the original lane. The lane change back-off conditions include: the first distance is less than the first safety distance, or the second distance is less than the second safety distance.

[0101] Among them, the first safety distance can be the minimum safety distance that needs to be maintained between the vehicle and the vehicle directly in front, and the second safety distance can be the minimum safety distance that needs to be maintained between the vehicle and the vehicle directly behind.

[0102] Exemplarily, the first safety distance is 6 m and the second safety distance is 3 m.

[0103] In one possible implementation, the first safety distance is determined based on the speed difference between the vehicle and the vehicle directly in front, and the relative distance between the vehicle and the vehicle directly in front, and the second safety distance is determined based on the speed difference between the vehicle and the vehicle directly in front, and the relative distance between the vehicle and the vehicle directly behind.

[0104] For example, after the vehicle starts changing lanes, the decision maker will uniformly arrange the time for lateral lane changes. Assuming that it takes 6 seconds to complete the lane change alignment, the timing starts from the start of the lane change. If it is 2 seconds after the start, it is only necessary to calculate in real time that the vehicle will not collide with the vehicle directly behind in the longitudinal position in the next 4 seconds. By analogy, the longer the time it takes to start the lane change, the lower the possibility of rolling back. This strategy can effectively avoid the overall poor lane change experience caused by erroneous rolling back.

[0105] In another possible implementation, the above-mentioned vehicle lane changing control method may also include: when the speed of the vehicle directly behind is greater than the speed of the own vehicle and the speed difference between the vehicle and the vehicle directly behind is less than a preset speed difference threshold, or when the lane changing mode is an on-ramp lane change, reducing the first safety distance and the second safety distance and increasing the current acceleration of the own vehicle.

[0106] For example, if the speed of the vehicle directly behind is much faster than the vehicle itself, the estimated driving distance L1 of the vehicle itself in the second time period in the future is calculated based on the real-time acceleration and real-time speed of the previous cycle, and the actual relative distance L2 between the vehicle itself and the vehicle directly behind is calculated at the same time. The minimum safety distance L3 that the vehicle directly behind and the vehicle itself need to maintain is calculated using the preset minimum safety distance judgment method. It can be seen that L1+L2-L3 is the maximum distance that the vehicle directly behind travels in the second time period in the future. The acceleration difference that needs to be reduced at least when the vehicle directly behind brakes is calculated based on the speed of the vehicle directly behind and the minimum safety distance. When the reduced acceleration difference is less than the preset acceleration threshold, it is determined that the vehicle meets the lane change back-off condition, that is, the vehicle is safe to change lanes and does not need to back off, and the fast car behind can avoid the vehicle; otherwise, the vehicle is controlled to give up the lane change and return to the original lane.

[0107] In another possible implementation, the above-mentioned vehicle lane change control method may also include: when the lane change mode is created as overtaking lane change, navigation lane change and lane change to avoid large vehicles, the vehicle uses a preset cruising acceleration to change lanes.

[0108] In another possible implementation, the above-mentioned vehicle lane changing control method may also include: when the speed difference between the vehicle and the vehicle directly behind is greater than or equal to a preset speed difference threshold, or when the lane changing mode is a down-ramp lane change, the vehicle uses a preset gentle acceleration to change lanes.

[0109] Through the above-mentioned technical means, when the vehicle meets the lane change retreat conditions, it will retreat to the original lane in time, re-plan the lane change trajectory of the current vehicle, and make a new lane change decision while maintaining a safe distance between the current vehicle and the vehicles in front and behind, ensuring that the current vehicle's actions are both safe and effective, and that the lane change operation can be completed smoothly without interfering with other vehicles.

[0110] In some embodiments, the above vehicle lane changing control method may further include the following steps: When the third distance between the vehicle and the target vehicle behind it in the original lane is less than the third safety distance, or there is a lane-changing vehicle that wishes to change lanes to the original lane, the vehicle is controlled to travel in the target lane and a prompt message is output, wherein the prompt message is used to remind the driver that there is a risk of collision.

[0111] Exemplarily, the third safety distance may be 2.5 m.

[0112] In a possible implementation, the above-mentioned vehicle control lane changing method may further include: identifying whether there is a lane-changing vehicle that is expected to change lanes to the original lane within a preset target range. Optionally, identifying whether there is a lane-changing vehicle that is expected to change lanes to the original lane within the preset target range may include: identifying other vehicles in the target range that cross the lane line of the original lane; when the proportion of other vehicles crossing the lane line is greater than the lane-changing threshold, determining that the other vehicle is a lane-changing vehicle that is expected to change lanes to the original lane. The crossed lane line may be a part of the vehicle, such as a tire, a body, etc., which has crossed the lane boundary line of the original lane, and the lane-changing threshold may be a preset value, such as 50% of the body width, etc., which is used to determine whether the vehicle is actually changing lanes. For example, a vehicle-mounted visual sensor may be used to identify whether there is a lane-changing vehicle that is expected to change lanes to the original lane.

[0113] Through the above-mentioned technical means, the third distance between the vehicle and the target vehicle behind it in the original lane, as well as the relative position relationship of other surrounding vehicles, is used to determine whether other vehicles are performing or preparing to change lanes, thereby adjusting its own driving strategy to ensure safety and outputting prompt information, which can improve the safety of vehicle driving and reduce the occurrence of accidents.

[0114] Figure 6 is a block diagram of a vehicle lane change control device provided in an embodiment of the present application, such as Figure 6 As shown, the device 30 comprises: An acquisition module 31 is used to acquire a first driving parameter, a second driving parameter and road information of a vehicle, wherein the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; A determination module 32, for determining a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; A calculation module 33 is used to optimize the planned lane-changing trajectory and the estimated acceleration of the vehicle by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration, wherein the target lane-changing trajectory and the target acceleration-time function are smooth curves; The control module 34 is used to control the vehicle to start acceleration according to the target acceleration within the estimated acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane change trajectory.

[0115] Optionally, the determination module 32 is specifically configured to: Inputting the first driving parameter and the second driving parameter into a trajectory prediction model to obtain a motion state of the vehicle and motion states of multiple surrounding vehicles in a first future time period, wherein the motion states of the multiple surrounding vehicles include the motion state of each of the multiple surrounding vehicles; Determine the planned lane change trajectory based on the vehicle's motion state, the motion states of multiple surrounding vehicles, and road information; Determining an estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameter, and the second driving parameter; An estimated acceleration of the vehicle is determined according to the planned lane change trajectory, the first driving parameter, and an estimated acceleration time of the vehicle.

[0116] Optionally, the determination module 32 is specifically configured to: Determine, according to the road information, a plurality of lane-changing spaces in adjacent lanes of the original lane, where the lane-changing spaces are gaps in adjacent lanes that can be used for lane-changing; Determine a target lane-changing space from a plurality of lane-changing spaces by using a motion state of the vehicle and motion states of a plurality of surrounding vehicles; According to the vehicle's motion state and the target lane-changing space, the planned lane-changing trajectory is determined.

[0117] Optionally, the second driving parameters include driving parameters of the vehicle directly in front, driving parameters of the vehicle in front of the side, and driving parameters of the vehicle behind the side. The determination module 32 is specifically used to: Determine a maximum lane change duration according to the planned lane change trajectory, the first driving parameter and the driving parameter of the vehicle directly in front, where the maximum lane change duration is a maximum time period during which the vehicle can accelerate; Input the motion state of the vehicle and the driving parameters of the vehicle in front and on the side into the lane-changing game model to obtain the first lane-changing duration; Input the motion state of the vehicle and the driving parameters of the side and rear vehicles into the lane-changing game model to obtain the second lane-changing duration; When the first lane changing duration is less than or equal to the limit lane changing duration, and the second lane changing duration is less than or equal to the limit lane changing duration, the larger of the first lane changing duration and the second lane changing duration is used as the estimated acceleration duration of the vehicle.

[0118] Optionally, the calculation module 33 is specifically configured to: The driving trajectories of the plurality of surrounding vehicles are projected onto the displacement-time graph to obtain position constraints; the driving trajectories of the plurality of surrounding vehicles include the driving trajectory of each of the plurality of surrounding vehicles, and the driving trajectories of the plurality of surrounding vehicles are obtained by inputting the second driving parameter into the trajectory prediction model; Determine speed constraint conditions according to a preset vehicle speed range; The planned lane-changing trajectory is optimized using the target cost function, position constraints, and speed constraints to obtain the target lane-changing trajectory and target acceleration.

[0119] Optionally, the calculation module 33 is further used for: Project the driving trajectory of the vehicle directly in front of you in the first time period and the driving trajectory of the vehicle in front of you within the estimated acceleration time onto the displacement-time graph to obtain the upper boundary of the position constraint; The driving trajectory of the vehicle behind the vehicle inside the expected acceleration time of the ego vehicle is projected into the displacement-time graph to obtain the lower boundary of the position constraint.

[0120] Optionally, the acquisition module 31 is further used to acquire the vehicle's start lane change duration, current first driving parameter and current second driving parameter when the vehicle starts accelerating; The determination module 32 is further used to input the current first driving parameter and the current second driving parameter into the trajectory prediction model to obtain a first distance between the vehicle and the vehicle directly in front and a second distance between the vehicle and the target vehicle directly behind in a future second time period, wherein the future second time period is the difference between the estimated acceleration time of the vehicle and the lane change start time; The control module 34 is further used to control the vehicle to give up lane change and return to the original lane when the vehicle meets the lane change back-off condition. The lane change back-off condition includes: the first distance is less than the first safety distance, or the second distance is less than the second safety distance.

[0121] Optionally, the control module 34 is specifically configured to: When the third distance between the vehicle and the target vehicle behind it in the original lane is less than the third safety distance, or there is a lane-changing vehicle that wishes to change lanes to the original lane, the vehicle is controlled to travel in the target lane and a prompt message is output, wherein the prompt message is used to remind the driver that there is a risk of collision.

[0122] The vehicle lane change control device in the embodiment of the present application can be a device, or a component, integrated circuit, or chip in a terminal. The device can be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device can be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a personal digital assistant (PDA), etc., and the non-mobile electronic device can be a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., which is not specifically limited in the embodiment of the present application.

[0123] The vehicle lane change control device in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, which are not specifically limited in the embodiment of the present application.

[0124] The vehicle lane change control device provided in the embodiment of the present application can achieve Figure 1 The various processes implemented by the vehicle lane changing control device in the method embodiment will not be described again here to avoid repetition.

[0125] An embodiment of the present application also provides a vehicle, comprising the vehicle lane changing control device as described above.

[0126] The specific implementation process of the vehicle lane changing control device in the vehicle also provided in the embodiment of the present application is similar to the aforementioned vehicle lane changing control device and will not be repeated here.

[0127] In the embodiment of the present application, by acquiring the first driving parameter, the second driving parameter and the road information of the vehicle, the second driving parameter includes multiple driving parameters of each of the multiple surrounding vehicles, and then according to the first driving parameter, the second driving parameter and the road information, the planned lane changing trajectory of the vehicle, the expected acceleration time of the vehicle and the expected acceleration of the vehicle are determined, and then the planned lane changing trajectory and the expected acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane changing trajectory and a target acceleration, and finally the vehicle is controlled to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle drives from the original lane to the target lane according to the target lane changing trajectory. On the one hand, a higher probability of lane changing success can be achieved to ensure driving safety, and on the other hand, the lane changing trajectory and acceleration can be appropriately adjusted. Since the lane changing trajectory and the acceleration-time function are both smooth curves, that is, the target lane changing trajectory and the target acceleration have a gentler slope, smoother transition, no sharp points, and no mutation points, which can make the acceleration of the vehicle smoother, avoid sudden acceleration or sudden deceleration of the vehicle, thereby improving the comfort of passengers.

[0128] Optionally, an embodiment of the present application further provides an electronic device, including a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, each process of the above-mentioned vehicle lane change control method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0129] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0130] Figure 7 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of the present application.

[0131] The electronic device 400 includes but is not limited to components such as a radio frequency unit 401 , a network module 402 , an audio output unit 403 , an input unit 404 , a sensor 405 , a display unit 406 , a user input unit 407 , an interface unit 408 , a memory 409 , and a processor 410 .

[0132] Those skilled in the art will appreciate that the electronic device 400 may also include a power source (such as a battery) for supplying power to various components, and the power source may be logically connected to the processor 410 through a power management system, thereby implementing functions such as managing charging, discharging, and power consumption management through the power management system. Figure 7 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be described in detail here.

[0133] The processor 410 is used to obtain a first driving parameter, a second driving parameter and road information of the vehicle, wherein the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; Determine a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; The planned lane-changing trajectory and the estimated acceleration of the vehicle are optimized by a nonlinear quadratic programming method to obtain the target lane-changing trajectory and the target acceleration. The target lane-changing trajectory and the target acceleration-time function are smooth curves. The vehicle starts accelerating according to the target acceleration within the estimated acceleration time of the vehicle, so that the vehicle moves from the original lane to the target lane according to the target lane changing trajectory.

[0134] It should be understood that in the embodiment of the present application, the input unit 404 may include a graphics processor (GPU) 4041 and a microphone 4042, and the graphics processor 4041 processes the image data of the static picture or video obtained by the image capture device (such as a camera) in the video capture mode or the image capture mode. The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 407 includes a touch panel 4071 and at least one of other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include two parts: a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, and a joystick, which will not be repeated here.

[0135] The memory 409 can be used to store software programs and various data. The memory 409 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data, wherein the first storage area may store an operating system, an application program or instructions required for at least one function (such as a sound playback function, an image playback function, etc.), etc. In addition, the memory 409 may include a volatile memory or a non-volatile memory, or the memory 409 may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDRSDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchronous link dynamic random access memory (SLDRAM) and a direct memory bus random access memory (DRRAM). The memory 409 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0136] The processor 410 may include one or more processing units; optionally, the processor 410 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It is understandable that the modem processor may not be integrated into the processor 410.

[0137] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, each process of the above-mentioned vehicle lane change control method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0138] The processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0139] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the above-mentioned vehicle lane change control method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0140] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0141] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises one..." does not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the method and device in the embodiment of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0142] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0143] The above embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent substitution or change made by a person skilled in the art based on the present invention is within the protection scope of the present invention.

Claims

1. A vehicle lane-changing control method, characterized in that: The method comprises: Acquire a first driving parameter, a second driving parameter and road information of the vehicle; the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; Determining a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; The planned lane-changing trajectory and the estimated acceleration of the vehicle are optimized by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration, wherein the target lane-changing trajectory and the target acceleration-time function are smooth curves; The vehicle is controlled to start accelerating according to the target acceleration within the estimated acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane changing trajectory.

2. The method according to claim 1, characterized in that The determining, according to the first driving parameter, the second driving parameter and the road information, the planned lane change trajectory of the vehicle, the estimated acceleration time of the vehicle and the estimated acceleration of the vehicle comprises: Inputting the first driving parameter and the second driving parameter into a trajectory prediction model to obtain a motion state of the vehicle and motion states of multiple surrounding vehicles in a first future time period, wherein the motion states of the multiple surrounding vehicles include the motion state of each of the multiple surrounding vehicles; Determining the planned lane change trajectory according to the vehicle motion state, the motion states of the plurality of surrounding vehicles and the road information; Determining an estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameter, and the second driving parameter; The expected acceleration of the vehicle is determined according to the planned lane change trajectory, the first driving parameter and the expected acceleration time of the vehicle.

3. The method according to claim 2, characterized in that The step of determining the planned lane change trajectory according to the motion state of the vehicle, the motion states of the plurality of surrounding vehicles and the road information includes: Determine, according to the road information, a plurality of lane-changing spaces in a lane adjacent to the original lane, wherein the lane-changing spaces are gaps in the adjacent lane that can be used for lane-changing; Determine a target lane-changing space from the plurality of lane-changing spaces by using the motion state of the vehicle and the motion states of the plurality of surrounding vehicles; The planned lane changing trajectory is determined according to the vehicle motion state and the target lane changing space.

4. The method according to claim 2, characterized in that: The second driving parameters include driving parameters of a vehicle directly in front, driving parameters of a vehicle in front of the side, and driving parameters of a vehicle behind the side. The determining of the estimated acceleration time of the vehicle according to the planned lane change trajectory, the first driving parameters, and the second driving parameters includes: Determining a maximum lane change duration according to the planned lane change trajectory, the first driving parameter, and the driving parameter of the vehicle directly in front, wherein the maximum lane change duration is a maximum time period during which the vehicle can accelerate; Inputting the vehicle motion state and the driving parameters of the side front vehicle into the lane changing game model to obtain a first lane changing duration; Inputting the motion state of the vehicle and the driving parameters of the side and rear vehicle into the lane-changing game model to obtain a second lane-changing duration; When the first lane changing duration is less than or equal to the limit lane changing duration, and the second lane changing duration is less than or equal to the limit lane changing duration, the larger of the first lane changing duration and the second lane changing duration is used as the estimated acceleration duration of the vehicle.

5. The method according to claim 1, characterized in that The step of optimizing the planned lane-changing trajectory and the estimated acceleration of the vehicle by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration includes: Projecting the driving trajectories of the plurality of surrounding vehicles onto a displacement-time graph to obtain position constraints; the driving trajectories of the plurality of surrounding vehicles include the driving trajectory of each of the plurality of surrounding vehicles, and the driving trajectories of the plurality of surrounding vehicles are obtained by inputting the second driving parameter into a trajectory prediction model; Determine speed constraint conditions according to a preset vehicle speed range; The planned lane-changing trajectory is optimized using a target cost function, the position constraint, and the speed constraint to obtain the target lane-changing trajectory and the target acceleration.

6. The method according to claim 5, characterized in that The projecting the driving trajectories of the plurality of surrounding vehicles into the displacement-time graph to obtain the position constraint comprises: Projecting the driving trajectory of the vehicle directly in front of the vehicle in the first time period and the driving trajectory of the vehicle in front of the vehicle inside the estimated acceleration time onto the displacement-time graph to obtain the upper boundary of the position constraint; The driving trajectory of the vehicle behind the vehicle inside the expected acceleration time is projected into the displacement-time graph to obtain the lower boundary of the position constraint.

7. The method according to claim 1, characterized in that The method further comprises: When the vehicle starts accelerating, obtaining a lane change start time, a current first driving parameter, and a current second driving parameter of the vehicle; Inputting the current first driving parameter and the current second driving parameter into a trajectory prediction model, obtaining a first distance between the vehicle and a vehicle directly in front, and a second distance between the vehicle and a target vehicle directly behind in a second time period in the future, wherein the second time period in the future is the difference between the estimated acceleration time of the vehicle and the lane change start time; When the vehicle meets the lane change back-off condition, the vehicle is controlled to give up the lane change and return to the original lane. The lane change back-off condition includes: the first distance is less than the first safety distance, or the second distance is less than the second safety distance.

8. The method according to claim 7, characterized in that The method further comprises: When a third distance between the vehicle and a target vehicle to the rear in the original lane is less than a third safety distance, or there is a lane-changing vehicle that desires to change lanes to the original lane, the vehicle is controlled to travel in the target lane and a prompt message is output, wherein the prompt message is used to prompt the driver that there is a risk of collision.

9. A vehicle lane-changing control device, characterized in that: The device comprises: An acquisition module, used to acquire a first driving parameter, a second driving parameter and road information of a vehicle, wherein the second driving parameter includes a plurality of driving parameters of each vehicle in a plurality of surrounding vehicles; a determination module, configured to determine a planned lane change trajectory of the vehicle, an estimated acceleration time of the vehicle, and an estimated acceleration of the vehicle according to the first driving parameter, the second driving parameter, and the road information; A calculation module, used for optimizing the planned lane-changing trajectory and the estimated acceleration of the vehicle by a nonlinear programming method to obtain a target lane-changing trajectory and a target acceleration, wherein the target lane-changing trajectory and the target acceleration-time function are smooth curves; The control module is used to control the vehicle to start acceleration according to the target acceleration within the expected acceleration time of the vehicle, so that the vehicle travels from the original lane to the target lane according to the target lane change trajectory.

10. An electronic device, characterized in that: The method comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the lane changing method as claimed in any one of claims 1 to 8.

11. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by a processor, the steps of the vehicle lane change control method as described in any one of claims 1 to 8 are implemented.

12. A vehicle, characterized in that: It comprises the vehicle lane changing control device as claimed in claim 9.

Images