Vehicle lane changing method and lane changing device

Abstract

The present application provides a vehicle lane-changing method and lane-changing device, the method comprising: obtaining future motion state information, the future motion state information including motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment; establishing a planning model for a gap, and obtaining constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle; inputting the future motion state information into the planning model, and calculating the optimal lane-changing motion state information of the vehicle to be changed based on the constraints and the loss function; and controlling the vehicle to be changed to change lanes to a target gap during the lane-changing process based on at least the optimal lane-changing motion state information, wherein the target gap is the gap corresponding to the optimal lane-changing motion state information. The present application solves the problem in the prior art that autonomous driving vehicles lack the ability to determine an optimal lane-changing environment when changing lanes.

Description

Technical Field

[0001] The present application relates to the field of vehicle trajectories, and more specifically, to a vehicle lane changing method, a lane changing device, a computer-readable storage medium, a processor, an electronic device, and a vehicle system. Background Art

[0002] An autonomous vehicle is one that can sense its environment and navigate without human input. Autonomous vehicles use various technologies to detect their surroundings, such as radar, lasers, GPS (Global Positioning System), odometry, and computer vision. Advanced control systems interpret this sensory information to identify appropriate navigation paths, obstacles, and relevant road signs.

[0003] In the existing technology, autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes.

[0004] The above information disclosed in the background technology section is only used to enhance the understanding of the background technology of the technology described in this article. Therefore, the background technology may contain certain information that does not form the prior art known in this country to those skilled in the art. Summary of the Invention

[0005] The main purpose of this application is to provide a vehicle lane changing method, lane changing device, computer-readable storage medium, processor, electronic device and vehicle system to solve the problem in the prior art that autonomous driving vehicles lack the ability to determine a better lane changing environment when changing lanes.

[0006] According to one aspect of an embodiment of the present invention, a vehicle lane-changing method is provided, comprising: obtaining future motion state information, wherein the future motion state information includes motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, wherein the motion state information includes at least one of position information, speed, and acceleration; the first target vehicle is a vehicle located in a first lane, adjacent to a vehicle to be changed lanes, and in front of the vehicle to be changed lanes in the direction of travel; the second target vehicle and the third target vehicle are two adjacent vehicles located in a second lane, and in the direction of travel, the second target vehicle is in front of the third target vehicle; the first lane is the location of the vehicle to be changed lanes. the lane where the second target vehicle is located, and the second lane is the lane that the vehicle to be changed lanes is to merge into; a planning model for the gap is established, and constraints and a loss function corresponding to the planning model are obtained, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variable of the planning model is the motion state information of the vehicle to be changed lanes; the future motion state information is input into the planning model, and the optimal lane-changing motion state information of the vehicle to be changed lanes is calculated based on the constraints and the loss function; and the vehicle to be changed lanes is controlled to change lanes to a target gap during the lane-changing process based at least on the optimal lane-changing motion state information, where the target gap is the gap corresponding to the optimal lane-changing motion state information.

[0007] Optionally, the future motion state information is input into the planning model, and the optimal lane-changing motion state information of the vehicle to be lane-changing is calculated based on the constraints and the loss function, including: inputting the future motion state information into the planning model, and calculating the feasible solutions corresponding to each future moment based on the constraints, the feasible solutions including at least one of the speed, acceleration and position information of the vehicle to be lane-changing; determining the optimal solutions corresponding to each future moment that satisfies the loss function based on the feasible solutions corresponding to each future moment and the loss function, and obtaining the optimal lane-changing motion state information.

[0008] Optionally, the feasible solution includes the speed and / or the acceleration, and controls the vehicle to be lane-changed to change lanes to a target gap during the lane-changing process at least according to the optimal lane-changing motion state information, including: performing predetermined processing on the speed and / or the acceleration corresponding to each future moment to obtain the position information of the vehicle to be lane-changed corresponding to each future moment, the predetermined processing including integration; generating a motion trajectory of the vehicle to be lane-changed based on each position information; and controlling the vehicle to be lane-changed to move according to the motion trajectory so that the vehicle to be lane-changed changes lanes to the target gap.

[0009] Optionally, obtaining future motion state information includes: obtaining current motion state information in real time, the current motion state information being the position information, the speed and the acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each current moment; obtaining the position information, the speed and the acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment based on the current motion state information; and determining the gaps of each second target vehicle and the corresponding third target vehicle at each future moment based on the position information at each future moment.

[0010] Optionally, based on the current motion state information, the position information, the speed and the acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment are obtained, including: establishing a prediction model, the prediction model is trained by machine learning using multiple sets of data, each set of data in the multiple sets of data includes: historical current motion state information and the corresponding position information, the speed and the acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each predetermined moment, the predetermined moment is later than the moment corresponding to the historical current motion state information; inputting the current motion state information into the prediction model to obtain the position information, the speed and the acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment.

[0011] Optionally, establishing a planning model for the gap includes: using the motion state information of the vehicle to change lanes as the variable, establishing a convex quadratic programming equation, and obtaining the planning model.

[0012] Optionally, the constraint condition includes that during the lane changing process, the vehicle to be changed lanes does not overtake the first target vehicle and the second target vehicle in the driving direction, and overtakes the third target vehicle.

[0013] Optionally, obtaining the constraint conditions corresponding to the planning model includes: obtaining the lane change duration, the lane change duration being the time from receiving the lane change request to the time the vehicle to be changed lanes changes to the second lane; obtaining first position information, the first position information being multiple position information of the vehicle to be changed lanes within the lane change duration; determining second position information, third position information and fourth position information based on the future motion state information and the lane change duration, wherein the second position information is multiple position information of each second target vehicle within the lane change duration, the third position information is multiple position information of each corresponding third target vehicle within the lane change duration, and the fourth position information is multiple position information of the first target vehicle within the lane change duration; determining the constraint condition that the first position information satisfies: within the lane change duration and in the driving direction, the first position information is located in front of the second position information at the corresponding moment, and is located behind the third position information and the fourth position information at the corresponding moment.

[0014] Optionally, the loss function includes at least one of the following: the sum of the squares of the acceleration variables of the vehicle to change lanes at each moment, the speed of the second target vehicle corresponding to the gap, the speed of the third target vehicle corresponding to the gap, and the length of the gap along the direction of the second lane.

[0015] According to another aspect of an embodiment of the present invention, a lane-changing device for a vehicle is also provided, including: an acquisition unit for acquiring future motion state information, the future motion state information including motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, the motion state information including at least one of position information, speed, and acceleration, the first target vehicle being a vehicle located in a first lane, adjacent to a vehicle to be changed lanes, and located in front of the vehicle to be changed lanes in the direction of travel, the second target vehicle and the third target vehicle being two adjacent vehicles located in a second lane, and in the direction of travel, the second target vehicle being located in front of the third target vehicle, and the first lane being the lane where the vehicle to be changed lanes is located , the second lane is the lane that the vehicle to be changed lanes is to merge into; an establishment unit is used to establish a planning model for the gap and obtain the constraints and loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variable of the planning model is the motion state information of the vehicle to be changed lanes; an input unit is used to input the future motion state information into the planning model, and calculate the optimal lane-changing motion state information of the vehicle to be changed lanes according to the constraints and the loss function; a control unit is used to control the vehicle to be changed lanes to change to a target gap during the lane-changing process at least according to the optimal lane-changing motion state information, and the target gap is the gap corresponding to the optimal lane-changing motion state information.

[0016] Optionally, the input unit includes: a calculation module for inputting the future motion state information into the planning model, and calculating the feasible solution corresponding to each of the future moments according to the constraint conditions, the feasible solution including at least one of the speed, acceleration and position information of the vehicle to change lanes; a determination module for determining the optimal solution corresponding to each of the future moments that satisfies the loss function based on the feasible solution corresponding to each of the future moments and the loss function, to obtain the optimal lane-changing motion state information.

[0017] According to yet another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein the program executes any one of the methods described above.

[0018] According to another aspect of an embodiment of the present invention, a processor is provided, wherein the processor is configured to run a program, wherein any one of the methods is executed when the program is run.

[0019] According to another aspect of an embodiment of the present invention, an electronic device is also provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the methods described.

[0020] According to another aspect of an embodiment of the present invention, a vehicle system is provided, including: an autonomous driving vehicle; and a control device for the autonomous driving vehicle, wherein the control device is configured to execute any one of the methods described.

[0021] In an embodiment of the present invention, the lane changing method of the vehicle of the present application first obtains future motion state information representing the motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment, the motion state information including at least one of position, speed and acceleration, the first target vehicle and the vehicle to be changed lanes are both in the first lane and are located in front of the vehicle to be changed lanes, the second target vehicle and the third target vehicle are in the second lane and are adjacent; secondly, using the motion state information of the vehicle to be changed lanes as a variable, a planning model of the gap between the second target vehicle and the third target vehicle is established, and the constraints and loss function corresponding to the planning model are obtained; thirdly, the obtained future motion state information is input into the planning model, and the optimal lane changing motion state information of the vehicle to be changed lanes is calculated according to the constraints and the loss function; finally, at least according to the optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes in the gap corresponding to the optimal lane changing motion state information during the lane changing process. Compared with the existing technology, in which autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes, the present application establishes a planning model for multiple gaps on the lane to be merged, and then calculates the optimal lane changing motion state information of the vehicle to be changed based on the planning model of the gaps, constraints and loss function. That is, the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to the target gap that satisfies the constraints and the loss function is calculated. Finally, based on the optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane changing process to complete the lane change, thereby realizing the prediction and selection of the optimal lane changing environment during the lane changing process, and solving the problem in the existing technology that autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings that constitute part of this application are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation on this application. In the drawings:

[0023] Figure 1 A schematic diagram of a lane changing method for a vehicle according to an embodiment of the present application is shown;

[0024] Figure 2 shows a lane change position diagram of a vehicle according to an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a lane changing device for a vehicle according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0026] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0027] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0028] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0029] It should be understood that when an element (such as a layer, film, region, or substrate) is described as being "on" another element, the element may be directly on the other element or intervening elements may be present. Moreover, in the specification and claims, when it is described that an element is "connected to" another element, the element may be "directly connected to" the other element or "connected to" the other element through a third element.

[0030] As mentioned in the background technology, autonomous driving vehicles in the prior art lack the ability to determine the optimal lane changing environment when changing lanes. In order to solve the above problem, a typical embodiment of the present application provides a vehicle lane changing method, a lane changing device, a computer-readable storage medium, a processor, an electronic device, and a vehicle system.

[0031] According to an embodiment of the present application, a lane changing method for a vehicle is provided.

[0032] Figure 1 Flowchart of the lane changing method of a vehicle according to an embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0033] Step S101, obtaining future motion state information, the future motion state information includes motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment, the motion state information includes at least one of position information, speed and acceleration, such as Figure 2 As shown, the first target vehicle is a vehicle located in the first lane, adjacent to the vehicle to be changed and located in front of the vehicle to be changed in the travel direction; the second target vehicle and the third target vehicle are two adjacent vehicles located in the second lane, and in the travel direction, the second target vehicle is located in front of the third target vehicle; the first lane is the lane where the vehicle to be changed is located, and the second lane is the lane that the vehicle to be changed is to merge into;

[0034] Step S102: Establishing a planning model for the gap and obtaining constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variables of the planning model are the motion state information of the vehicle to be changed lanes;

[0035] Step S103: inputting the future motion state information into the planning model, and calculating the optimal lane-changing motion state information of the vehicle to be changed lanes based on the constraints and the loss function;

[0036] Step S104 , controlling the vehicle to be lane-changed to change lanes to a target gap during the lane-changing process based at least on the optimal lane-changing motion state information, where the target gap is the gap corresponding to the optimal lane-changing motion state information.

[0037] The vehicle lane changing method of the present application first obtains future motion state information representing the motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, the above motion state information including at least one of position, speed, and acceleration, the above first target vehicle and the vehicle to be lane-changed are both in the first lane and are located in front of the vehicle to be lane-changed, and the second target vehicle and the third target vehicle are in the second lane and are adjacent; secondly, using the above motion state information of the vehicle to be lane-changed as a variable, a planning model of the gap between the second target vehicle and the third target vehicle is established, and the constraints and loss function corresponding to the planning model are obtained; thirdly, the obtained future motion state information is input into the above planning model, and the optimal lane-changing motion state information of the vehicle to be lane-changed is calculated according to the constraints and the loss function; finally, according to at least the optimal lane-changing motion state information, the vehicle to be lane-changed is controlled to change lanes into the gap corresponding to the optimal lane-changing motion state information during the lane-changing process. Compared with the existing technology, in which autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes, the present application establishes a planning model for multiple gaps on the lane to be merged, and then calculates the optimal lane changing motion state information of the vehicle to be changed based on the planning model of the gaps, constraints and loss function. That is, the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to the target gap that satisfies the constraints and the loss function is calculated. Finally, based on the above-mentioned optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane changing process to complete the lane change, thereby realizing the prediction and selection of the optimal lane changing environment during the lane changing process, and solving the problem in the existing technology that autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes.

[0038] It should be noted that the above-mentioned optimal lane-changing motion state information is the predicted optimal motion state information of the above-mentioned vehicle to be changed lanes in the lane-changing process that meets the constraint conditions and the loss function.

[0039] According to a specific embodiment of the present application, the future motion state information is input into the planning model, and the optimal lane-changing motion state information of the vehicle to be changed is calculated based on the constraints and the loss function. This includes: inputting the future motion state information into the planning model, and calculating a feasible solution corresponding to each of the future moments based on the constraints, wherein the feasible solution includes at least one of the speed, acceleration, and position information of the vehicle to be changed; and determining the optimal solution corresponding to each of the future moments that satisfies the loss function based on the feasible solutions corresponding to each of the future moments and the loss function, thereby obtaining the optimal lane-changing motion state information. In this embodiment, the feasible solutions for the future moments are first calculated based on the constraints, and then the optimal solution is determined based on the loss function and the multiple feasible solutions obtained. This further avoids the problem of the autonomous vehicle lacking a better lane-changing environment when changing lanes, and further ensures that the better lane-changing environment and the motion state of the vehicle to be changed corresponding to the better lane-changing environment can be selected according to actual needs.

[0040] Specifically, the above loss function can be flexibly set according to the actual lane change requirements, so that the optimal solution can be obtained by screening according to the above loss function.

[0041] In order to further ensure that the above-mentioned vehicle to be changed lanes can change lanes according to the above-mentioned optimal lane-changing motion state information obtained, and then enter the above-mentioned target gap, according to another specific embodiment of the present application, the above-mentioned feasible solution includes the above-mentioned speed and / or the above-mentioned acceleration, and at least according to the above-mentioned optimal lane-changing motion state information, the above-mentioned vehicle to be changed lanes is controlled to change lanes to the target gap during the lane-changing process, including: performing predetermined processing on the above-mentioned speed and / or the above-mentioned acceleration corresponding to each of the above-mentioned future moments to obtain the above-mentioned position information of the above-mentioned vehicle to be changed lanes corresponding to each of the above-mentioned future moments, and the above-mentioned predetermined processing includes integration; generating the motion trajectory of the above-mentioned vehicle to be changed lanes according to each of the above-mentioned position information; controlling the above-mentioned vehicle to be changed lanes to move according to the above-mentioned motion trajectory, so that the above-mentioned vehicle to be changed lanes changes to the above-mentioned target gap. By integrating the speed and / or acceleration at future moments, the output lane-changing trajectory will change with even the slightest deviation in the input speed and / or acceleration, ensuring the accuracy of the trajectory of the vehicle to be changed, thereby enabling the vehicle to change lanes more accurately to the target gap, further resolving the issue of autonomous vehicles lacking a clear path to optimal lane-changing conditions.

[0042] According to another specific embodiment of the present application, obtaining future motion state information includes: obtaining current motion state information in real time, the current motion state information being the position information, speed, and acceleration of the first target vehicle, the plurality of second target vehicles, and the plurality of third target vehicles at each current moment; obtaining the position information, speed, and acceleration of the first target vehicle, the plurality of second target vehicles, and the plurality of third target vehicles at each future moment based on the current motion state information; and determining the gap between each second target vehicle and the corresponding third target vehicle at each future moment based on the position information at each future moment. In this way, the future motion state information can be obtained more accurately.

[0043] Specifically, to control the vehicle to change lanes from the first lane to the second lane, it is necessary to first obtain the positions of all vehicles in the second lane, enumerate the gaps between any two vehicles in the second lane, and predict the motion status of any two vehicles in the second lane. Based on the relationship between distance and time, the speed, acceleration and gap size of any two vehicles in the second lane at each moment can be predicted.

[0044] In order to further ensure that the above-mentioned future motion state information is obtained more accurately and simply, according to another specific embodiment of the present application, based on the above-mentioned current motion state information, the above-mentioned position information, the above-mentioned speed and the above-mentioned acceleration of the above-mentioned first target vehicle, the multiple second target vehicles and the multiple third target vehicles at each of the above-mentioned future moments are obtained, including: establishing a prediction model, the above-mentioned prediction model is trained by machine learning using multiple sets of data, and each set of data in the above-mentioned multiple sets of data includes: historical current motion state information and the corresponding above-mentioned first target vehicle, the multiple second target vehicles and the multiple third target vehicles at each predetermined moment. The above-mentioned predetermined moment is later than the moment corresponding to the above-mentioned historical current motion state information; the above-mentioned current motion state information is input into the above-mentioned prediction model to obtain the above-mentioned position information, the above-mentioned speed and the above-mentioned acceleration of the above-mentioned first target vehicle, the multiple second target vehicles and the multiple third target vehicles at each of the above-mentioned future moments. By training the prediction model and using the current motion state information and the prediction model to obtain the position information, speed and acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment, the accuracy of the obtained data is further guaranteed, thereby facilitating the subsequent establishment of a more accurate planning model based on the obtained data.

[0045] According to another specific embodiment of the present application, establishing a planning model for a gap includes: using the motion state information of the vehicle to change lanes as the variables, establishing a convex quadratic programming equation to obtain the planning model. The planning model established using the convex quadratic programming equation can achieve a global minimum, thereby more easily obtaining optimal lane change motion state information.

[0046] In order to further ensure the safe driving of the above-mentioned vehicle to be changed lanes during the lane change process, according to another specific embodiment of the present application, the above-mentioned constraint conditions include that during the lane change process, the above-mentioned vehicle to be changed lanes does not overtake the above-mentioned first target vehicle and the above-mentioned second target vehicle in the above-mentioned driving direction, and overtakes the above-mentioned third target vehicle. The lane change trajectory of the vehicle to be changed lanes is limited by the constraint conditions, thereby ensuring the accuracy of the optimal lane change trajectory under these conditions. Of course, the constraint conditions of the present application are not limited to the above-mentioned constraint conditions, and those skilled in the art can flexibly set them according to actual conditions.

[0047] According to another specific embodiment of the present application, obtaining the constraint conditions corresponding to the above-mentioned planning model includes: obtaining the lane change duration, the above-mentioned lane change duration is the time required for the above-mentioned vehicle to be changed to change lanes to the above-mentioned second lane from the time the lane change request is received; obtaining the first position information, the above-mentioned first position information is the multiple position information of the above-mentioned vehicle to be changed within the above-mentioned lane change duration; determining the second position information, the third position information and the fourth position information based on the above-mentioned future motion state information and the above-mentioned lane change duration, wherein the above-mentioned second position information is the multiple position information of each of the above-mentioned second target vehicles within the above-mentioned lane change duration, the above-mentioned third position information is the multiple position information of each of the above-mentioned third target vehicles within the above-mentioned lane change duration, and the above-mentioned fourth position information is the multiple position information of the above-mentioned first target vehicle within the above-mentioned lane change duration; determining the above-mentioned constraint condition is that the above-mentioned first position information satisfies: within the above-mentioned lane change duration and in the above-mentioned driving direction, the above-mentioned first position information is located in front of the above-mentioned second position information at the corresponding moment, and is located behind the above-mentioned third position information and the above-mentioned fourth position information at the corresponding moment. In this embodiment, by predicting the position information of the first target vehicle, the second target vehicle and the third target vehicle during driving, the above-mentioned constraint conditions are obtained, which can further ensure that the vehicle to be changed lanes during the lane change process does not exceed the first target vehicle in the first lane and the second target vehicle in the second lane, and exceeds the third target vehicle in the second lane. This further ensures driving safety during the lane change process and further avoids the occurrence of accidents such as rear-end collisions.

[0048] In a specific embodiment, the above constraints are calculated. For example, if the lane change is planned to be completed within 5 seconds, then the optimization variables of the vehicle to be changed lanes at each moment within these 5 seconds are summed or integrated to obtain the position of the vehicle to be changed lanes at each moment within the 5 seconds. The position of the third target vehicle at the corresponding moment is set to be smaller than the position at each moment and smaller than the positions of the first target vehicle and the second target vehicle at the corresponding moments. In this way, the constraints of the optimization problem can be obtained.

[0049] In order to further ensure that user needs can be met during the lane changing process, such as making the vehicle to be changed lanes change to the target gap as smoothly as possible to avoid sudden acceleration and deceleration, or preventing the vehicle from rubbing against or rear-ending the second target vehicle or the third target vehicle during the lane changing process, according to another specific embodiment of the present application, the above-mentioned loss function includes at least one of the following: the sum of the squares of the acceleration variables of the above-mentioned vehicle to be changed lanes at each moment, the speed of the above-mentioned second target vehicle corresponding to the above-mentioned gap, the speed of the above-mentioned third target vehicle corresponding to the above-mentioned gap, and the length of the above-mentioned gap along the direction of the above-mentioned second lane.

[0050] In a specific embodiment, the loss function Fcost = the sum of the squares of the acceleration variables at each moment. In addition, since this is a framework algorithm, different loss variables can be added to enable the lane changing process to achieve certain goals. Therefore, the loss function of this application includes but is not limited to the sum of the squares of the acceleration variables of the vehicle to be changed lanes at each moment. Those skilled in the art can flexibly set it according to actual conditions.

[0051] It should be noted that the present application can optimize the algorithm based on these constraints and loss functions to calculate the optimal optimization variables, that is, the optimal motion state variables of the vehicle to be changed lanes at every moment. Then, based on these state variables at every moment, by summing or integrating, the motion state of the vehicle during the lane change process can be calculated, and the optimal solution is for the current first target vehicle, second target vehicle, and third target vehicle. Substituting the obtained motion state variables at every moment into the optimization target loss function, the loss of the gap between the currently enumerated first target vehicle, second target vehicle, and third target vehicle can be obtained. Based on the optimal gap, the motion trajectory is determined, and the vehicle is controlled to change lanes into the gap. The loss of the gap between the enumerated first target vehicle, second target vehicle, and third target vehicle is compared to obtain the optimal gap, and the optimal motion state at every moment corresponding to the vehicle to be changed lanes with this optimal gap can also be known.

[0052] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0053] The embodiments of the present application also provide a vehicle lane changing device. It should be noted that the vehicle lane changing device of the embodiments of the present application can be used to execute the vehicle lane changing method provided in the embodiments of the present application. The vehicle lane changing device provided in the embodiments of the present application is described below.

[0054] Figure 3 Schematic diagram of a lane changing device for a vehicle according to an embodiment of the present application. Figure 3 As shown, the device includes an acquisition unit 10, a creation unit 20, an input unit 30, and a control unit 40, wherein the acquisition unit 10 is used to acquire future motion state information, the future motion state information including motion state information of a first target vehicle, a plurality of second target vehicles, and a plurality of third target vehicles at each future moment, the motion state information including at least one of position information, speed, and acceleration, such as Figure 2 As shown, the first target vehicle is a vehicle located in the first lane, adjacent to the vehicle to be changed and in front of the vehicle to be changed in the driving direction. The second target vehicle and the third target vehicle are two adjacent vehicles located in the second lane, and in the driving direction, the second target vehicle is in front of the third target vehicle. The first lane is the lane where the vehicle to be changed is located, and the second lane is the lane into which the vehicle to be changed is to merge. The establishment unit 20 is used to establish a planning model for the gap and obtain the constraint conditions and loss function corresponding to the planning model, wherein , the above-mentioned gap is the distance between the above-mentioned second target vehicle and the above-mentioned third target vehicle, and the variable of the above-mentioned planning model is the above-mentioned motion state information of the above-mentioned vehicle to be changed lanes; the above-mentioned input unit 30 is used to input the above-mentioned future motion state information into the above-mentioned planning model, and calculate the optimal lane-changing motion state information of the above-mentioned vehicle to be changed lanes according to the above-mentioned constraints and the above-mentioned loss function; the above-mentioned control unit 40 is used to control the above-mentioned vehicle to be changed lanes to change to a target gap during the lane-changing process based on at least the above-mentioned optimal lane-changing motion state information, and the above-mentioned target gap is the above-mentioned gap corresponding to the above-mentioned optimal lane-changing motion state information.

[0055] The lane changing device of the vehicle of the present application obtains future motion state information representing the motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment through an acquisition unit, the above motion state information includes at least one of position, speed and acceleration, the above first target vehicle and the vehicle to be changed lanes are both in the first lane and are located in front of the vehicle to be changed lanes, and the second target vehicle and the third target vehicle are in the second lane and are adjacent to each other; the above motion state information of the vehicle to be changed lanes is used as a variable by an establishment unit to establish a planning model of the gap between the second target vehicle and the third target vehicle, and the constraints and loss function corresponding to the planning model are obtained; the above future motion state information obtained is input into the above planning model through an input unit, and the optimal lane changing motion state information of the vehicle to be changed lanes is calculated according to the constraints and the loss function; the control unit controls the vehicle to be changed lanes to the gap corresponding to the optimal lane changing motion state information during the lane changing process at least according to the optimal lane changing motion state information. Compared with the prior art, in which autonomous driving vehicles lack the ability to determine the optimal lane-changing environment when changing lanes, the lane-changing device of the vehicle of the present application establishes a planning model for multiple gaps on the lane to be merged, and then calculates the optimal lane-changing motion state information of the vehicle to be changed based on the planning model of the gaps, constraints, and loss function. That is, the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to the target gap that satisfies the constraints and the loss function is calculated. Finally, based on the above-mentioned optimal lane-changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane-changing process to complete the lane change, thereby realizing the prediction and selection of the optimal lane-changing environment during the lane-changing process, and solving the problem in the prior art that autonomous driving vehicles lack the ability to determine the optimal lane-changing environment when changing lanes.

[0056] It should be noted that the above-mentioned optimal lane-changing motion state information is the predicted optimal motion state information of the above-mentioned vehicle to be changed lanes in the lane-changing process that meets the constraint conditions and the loss function.

[0057] According to a specific embodiment of the present application, the input unit includes an input module and a first determination module, wherein the input module is used to input the future motion state information into the planning model and calculate the feasible solution corresponding to each of the above future moments according to the above constraints, wherein the feasible solution includes at least one of the above speed, the above acceleration, and the above position information of the above vehicle to be changed; and the first determination module is used to determine the optimal solution corresponding to each of the above future moments that satisfies the above loss function according to the above feasible solutions corresponding to each of the above future moments and the above loss function, thereby obtaining the above optimal lane change motion state information. In this embodiment, the feasible solution for the future moment is first calculated according to the constraints, and then the optimal solution is determined according to the loss function and the multiple feasible solutions obtained. This further avoids the problem of the autonomous driving vehicle lacking the ability to determine the optimal lane change environment when changing lanes, and further ensures that the optimal lane change environment and the motion state of the vehicle to be changed corresponding to the optimal lane change environment can be selected according to actual needs.

[0058] Specifically, the above loss function can be flexibly set according to the actual lane change requirements, so that the optimal solution can be obtained by screening according to the above loss function.

[0059] To further ensure that the lane-changing vehicle can change lanes according to the obtained optimal lane-changing motion state information and thus enter the target gap, according to another specific embodiment of the present application, the control unit includes a processing module, a generation module, and a control module, wherein the processing module is configured to perform predetermined processing on the speed and / or acceleration corresponding to each future moment to obtain the position information of the lane-changing vehicle corresponding to each future moment, wherein the predetermined processing includes integration; the generation module is configured to generate a motion trajectory of the lane-changing vehicle based on each position information; and the control module is configured to control the lane-changing vehicle to move according to the motion trajectory so that the lane-changing vehicle changes to the target gap. By integrating the speed and / or acceleration at the future moment, any slight deviation in the input speed and / or acceleration will cause the output lane-changing motion trajectory to change, thereby ensuring the accuracy of the lane-changing vehicle's motion trajectory, thereby enabling the lane-changing vehicle to change lanes more accurately to the target gap, further resolving the problem of the autonomous vehicle's lack of determination of the optimal lane-changing environment when changing lanes.

[0060] According to another specific embodiment of the present application, the acquisition unit includes a first acquisition module, a second acquisition module, and a second determination module, wherein the first acquisition module is used to acquire current motion state information in real time, and the current motion state information is the position information, speed, and acceleration of the first target vehicle, multiple second target vehicles, and multiple third target vehicles at each current moment; the second acquisition module is used to obtain the position information, speed, and acceleration of the first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment based on the current motion state information; and the second determination module is used to determine the gap between each second target vehicle and the corresponding third target vehicle at each future moment based on the position information at each future moment. In this way, the future motion state information can be obtained more accurately.

[0061] Specifically, to control the vehicle to change lanes from the first lane to the second lane, it is necessary to first obtain the positions of all vehicles in the second lane, enumerate the gaps between any two vehicles in the second lane, and predict the motion status of any two vehicles in the second lane. Based on the relationship between distance and time, the speed, acceleration and gap size of any two vehicles in the second lane at each moment can be predicted.

[0062] In order to further ensure that the above-mentioned future motion state information is obtained more accurately and simply, according to another specific embodiment of the present application, the above-mentioned second acquisition module includes an establishment submodule and an input submodule, wherein the above-mentioned establishment submodule is used to establish a prediction model, and the above-mentioned prediction model is trained through machine learning using multiple sets of data, and each set of data in the above-mentioned multiple sets of data includes: historical current motion state information and the corresponding above-mentioned first target vehicle, multiple above-mentioned second target vehicles and multiple above-mentioned third target vehicles at each predetermined time. The above-mentioned predetermined time is later than the time corresponding to the above-mentioned historical current motion state information; the above-mentioned input submodule is used to input the above-mentioned current motion state information into the above-mentioned prediction model to obtain the above-mentioned position information, the above-mentioned speed and the above-mentioned acceleration of the above-mentioned first target vehicle, multiple above-mentioned second target vehicles and multiple above-mentioned third target vehicles at each above-mentioned future time. By training the prediction model and using the current motion state information and the prediction model to obtain the position information, speed and acceleration of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment, the accuracy of the obtained data is further guaranteed, thereby facilitating the subsequent establishment of a more accurate planning model based on the obtained data.

[0063] According to another specific embodiment of the present application, the establishment unit includes an establishment module configured to establish a convex quadratic programming equation using the motion state information of the vehicle to change lanes as the variable to obtain the planning model. The planning model established using the convex quadratic programming equation can achieve a global minimum, thereby more easily obtaining optimal lane change motion state information.

[0064] In order to further ensure the safe driving of the above-mentioned vehicle to be changed lanes during the lane change process, according to another specific embodiment of the present application, the above-mentioned constraint conditions include that during the lane change process, the above-mentioned vehicle to be changed lanes does not overtake the above-mentioned first target vehicle and the above-mentioned second target vehicle in the above-mentioned driving direction, and overtakes the above-mentioned third target vehicle. The lane change trajectory of the vehicle to be changed lanes is limited by the constraint conditions, thereby ensuring the accuracy of the optimal lane change trajectory under these conditions. Of course, the constraint conditions of the present application are not limited to the above-mentioned constraint conditions, and those skilled in the art can flexibly set them according to actual conditions.

[0065] According to another specific embodiment of the present application, the establishment unit includes a third acquisition module, a fourth acquisition module, a third determination module and a fourth determination module, wherein the third acquisition module is used to obtain the lane change duration, and the lane change duration is the time from the receipt of the lane change request to the time the vehicle to be changed lanes changes to the second lane; the fourth acquisition module is used to obtain the first position information, and the first position information is a plurality of the position information of the vehicle to be changed lanes within the lane change duration; the third determination module is used to determine the second position information, the third position information and the fourth position information according to the future motion state information and the lane change duration. , wherein the second position information is a plurality of the position information of each of the second target vehicles within the lane change duration, the third position information is a plurality of the position information of each of the third target vehicles within the lane change duration, and the fourth position information is a plurality of the position information of the first target vehicle within the lane change duration; the fourth determination module is used to determine that the constraint condition is that the first position information satisfies: within the lane change duration and in the driving direction, the first position information is located in front of the second position information at the corresponding moment, and is located behind the third position information and the fourth position information at the corresponding moment. In this embodiment, by predicting the position information of the first target vehicle, the second target vehicle, and the third target vehicle during driving, the constraint condition is obtained, which can further ensure that the vehicle to be changed lanes does not exceed the first target vehicle in the first lane and the second target vehicle in the second lane during the lane change process, and exceeds the third target vehicle in the second lane. This further ensures driving safety during the lane change process and further avoids accidents such as rear-end collisions.

[0066] In a specific embodiment, the above constraints are calculated. For example, if the lane change is planned to be completed within 5 seconds, then the optimization variables of the vehicle to be changed lanes at each moment within these 5 seconds are summed or integrated to obtain the position of the vehicle to be changed lanes at each moment within the 5 seconds. The position of the third target vehicle at the corresponding moment is set to be smaller than the position at each moment and smaller than the positions of the first target vehicle and the second target vehicle at the corresponding moments. In this way, the constraints of the optimization problem can be obtained.

[0067] In order to further ensure that user needs can be met during the lane changing process, such as making the vehicle to be changed lanes change to the target gap as smoothly as possible to avoid sudden acceleration and deceleration, or preventing the vehicle from rubbing against or rear-ending the second target vehicle or the third target vehicle during the lane changing process, according to another specific embodiment of the present application, the above-mentioned loss function includes at least one of the following: the sum of the squares of the acceleration variables of the above-mentioned vehicle to be changed lanes at each moment, the speed of the above-mentioned second target vehicle corresponding to the above-mentioned gap, the speed of the above-mentioned third target vehicle corresponding to the above-mentioned gap, and the length of the above-mentioned gap along the direction of the above-mentioned second lane.

[0068] In a specific embodiment, the loss function Fcost = the sum of the squares of the acceleration variables at each moment. In addition, since this is a framework algorithm, different loss variables can be added to enable the lane changing process to achieve certain goals. Therefore, the loss function of this application includes but is not limited to the sum of the squares of the acceleration variables of the vehicle to be changed lanes at each moment. Those skilled in the art can flexibly set it according to actual conditions.

[0069] It should be noted that the present application can optimize the algorithm based on these constraints and loss functions to calculate the optimal optimization variables, that is, the optimal motion state variables of the vehicle to be changed lanes at every moment. Then, based on these state variables at every moment, by summing or integrating, the motion state of the vehicle during the lane change process can be calculated, and the optimal solution is for the current first target vehicle, second target vehicle, and third target vehicle. Substituting the obtained motion state variables at every moment into the optimization target loss function, the loss of the gap between the currently enumerated first target vehicle, second target vehicle, and third target vehicle can be obtained. Based on the optimal gap, the motion trajectory is determined, and the vehicle is controlled to change lanes into the gap. The loss of the gap between the enumerated first target vehicle, second target vehicle, and third target vehicle is compared to obtain the optimal gap, and the optimal motion state at every moment corresponding to the vehicle to be changed lanes with this optimal gap can also be known.

[0070] The lane changing device of the above-mentioned vehicle includes a processor and a memory. The above-mentioned acquisition unit, the above-mentioned establishment unit, the above-mentioned input unit and the above-mentioned control unit are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0071] The processor includes a core, which retrieves the corresponding program unit from memory. One or more cores can be configured, and adjusting the core parameters solves the existing problem of autonomous vehicles lacking the ability to determine optimal lane-changing conditions.

[0072] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0073] An embodiment of the present invention provides a computer-readable storage medium having a program stored thereon, which implements the above-mentioned vehicle lane changing method when executed by a processor.

[0074] An embodiment of the present invention provides a processor, which is used to run a program, wherein the vehicle lane changing method is executed when the program is run.

[0075] An embodiment of the present invention provides a device, comprising a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, at least the following steps are performed:

[0076] Step S101, obtaining future motion state information, the future motion state information including motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, the motion state information including at least one of position information, speed, and acceleration, the first target vehicle being a vehicle located in a first lane, adjacent to a vehicle to be changed lanes, and located in front of the vehicle to be changed lanes in a traveling direction, the second target vehicle and the third target vehicle being two adjacent vehicles located in a second lane, and in the traveling direction, the second target vehicle is located in front of the third target vehicle, the first lane being a lane where the vehicle to be changed lanes is located, and the second lane being a lane into which the vehicle to be changed lanes is to merge;

[0077] Step S102: Establishing a planning model for the gap and obtaining constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variables of the planning model are the motion state information of the vehicle to be changed lanes;

[0078] Step S103: inputting the future motion state information into the planning model, and calculating the optimal lane-changing motion state information of the vehicle to be changed lanes based on the constraints and the loss function;

[0079] Step S104 , controlling the vehicle to be lane-changed to change lanes to a target gap during the lane-changing process based at least on the optimal lane-changing motion state information, where the target gap is the gap corresponding to the optimal lane-changing motion state information.

[0080] The devices in this article can be servers, PCs, PADs, mobile phones, etc.

[0081] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to execute a program for initializing at least the following method steps:

[0082] Step S101, obtaining future motion state information, the future motion state information including motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, the motion state information including at least one of position information, speed, and acceleration, the first target vehicle being a vehicle located in a first lane, adjacent to a vehicle to be changed lanes, and located in front of the vehicle to be changed lanes in a traveling direction, the second target vehicle and the third target vehicle being two adjacent vehicles located in a second lane, and in the traveling direction, the second target vehicle is located in front of the third target vehicle, the first lane being a lane where the vehicle to be changed lanes is located, and the second lane being a lane into which the vehicle to be changed lanes is to merge;

[0083] Step S102: Establishing a planning model for the gap and obtaining constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variables of the planning model are the motion state information of the vehicle to be changed lanes;

[0084] Step S103: inputting the future motion state information into the planning model, and calculating the optimal lane-changing motion state information of the vehicle to be changed lanes based on the constraints and the loss function;

[0085] Step S104 , controlling the vehicle to be lane-changed to change lanes to a target gap during the lane-changing process based at least on the optimal lane-changing motion state information, where the target gap is the gap corresponding to the optimal lane-changing motion state information.

[0086] An embodiment of the present invention also provides a vehicle system, including an autonomous driving vehicle and a control device for the autonomous driving vehicle, wherein the control device is used to execute any one of the above methods.

[0087] The vehicle system of the present application includes the above-mentioned control device, and the above-mentioned control device is used to execute any one of the lane changing methods of the vehicle. First, future motion state information representing the motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment is obtained, and the above-mentioned motion state information includes at least one of position, speed and acceleration. The above-mentioned first target vehicle and the vehicle to be changed lanes are both in the first lane and are located in front of the vehicle to be changed lanes, and the second target vehicle and the third target vehicle are in the second lane and are adjacent; secondly, the above-mentioned motion state information of the vehicle to be changed lanes is used as a variable to establish a planning model of the gap between the second target vehicle and the third target vehicle, and the constraints and loss function corresponding to the planning model are obtained; thirdly, the obtained future motion state information is input into the above-mentioned planning model, and the optimal lane changing motion state information of the vehicle to be changed lanes is calculated according to the constraints and the loss function; finally, at least according to the optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes in the gap corresponding to the optimal lane changing motion state information during the lane changing process. Compared with the existing technology, in which autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes, the vehicle system of the present application establishes a planning model for multiple gaps on the lane to be merged, and then calculates the optimal lane changing motion state information of the vehicle to be changed based on the planning model of the gaps, constraints and loss function. That is, the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to the target gap that satisfies the constraints and the loss function is calculated. Finally, based on the above-mentioned optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane changing process to complete the lane change, thereby realizing the prediction and selection of the optimal lane changing environment during the lane changing process, and solving the problem in the existing technology that autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes.

[0088] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the above-mentioned units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0090] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0091] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0092] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0093] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0094] 1) The vehicle lane changing method of the present application, first, obtains future motion state information representing the motion state information of a first target vehicle, multiple second target vehicles, and multiple third target vehicles at each future moment, the above motion state information including at least one of position, speed, and acceleration, the above first target vehicle and the vehicle to be changed lanes are both in the first lane and are located in front of the vehicle to be changed lanes, and the second target vehicle and the third target vehicle are in the second lane and are adjacent; secondly, using the above motion state information of the vehicle to be changed lanes as a variable, establish a planning model for the gap between the second target vehicle and the third target vehicle, and obtain the constraints and loss function corresponding to the planning model; thirdly, inputs the obtained future motion state information into the above planning model, and calculates the optimal lane-changing motion state information of the vehicle to be changed lanes according to the constraints and the loss function; finally, based on at least the optimal lane-changing motion state information, controls the vehicle to be changed lanes to the gap corresponding to the optimal lane-changing motion state information during the lane-changing process. Compared to the problem in the prior art where autonomous vehicles lack the ability to determine the optimal lane-changing environment when changing lanes, the present application establishes a planning model for multiple gaps in the lane to be merged into, and then calculates the optimal lane-changing motion state information of the vehicle to be changed based on the gap planning model, constraints, and loss function. Specifically, the present application calculates the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to a target gap that satisfies the constraints and the loss function. Finally, based on the optimal lane-changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane-changing process, completing the lane change. This achieves the prediction and selection of the optimal lane-changing environment during the lane-changing process, thus resolving the problem in the prior art where autonomous vehicles lack the ability to determine the optimal lane-changing environment when changing lanes.

[0095] 2) The lane changing device of the vehicle of the present application obtains future motion state information representing the motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment through an acquisition unit, the above-mentioned motion state information includes at least one of position, speed and acceleration, the above-mentioned first target vehicle and the vehicle to be changed lanes are both in the first lane and are located in front of the vehicle to be changed lanes, and the second target vehicle and the third target vehicle are in the second lane and are adjacent to each other; the above-mentioned motion state information of the above-mentioned vehicle to be changed lanes is used as a variable by an establishment unit to establish a planning model of the gap between the second target vehicle and the third target vehicle, and the constraints and loss function corresponding to the planning model are obtained; the above-mentioned future motion state information obtained is input into the above-mentioned planning model through an input unit, and the optimal lane-changing motion state information of the vehicle to be changed lanes is calculated according to the constraints and the loss function; the control unit controls the vehicle to be changed lanes to change into the gap corresponding to the optimal lane-changing motion state information during the lane changing process at least according to the optimal lane-changing motion state information. Compared to the prior art, where autonomous vehicles lack the ability to determine an optimal lane-changing environment when changing lanes, the lane-changing device of the vehicle in the present application establishes a planning model for multiple gaps in the lane to be merged into. The device then calculates the optimal lane-changing motion state information of the vehicle to be changed based on the gap planning model, constraints, and a loss function. Specifically, the device calculates the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to a target gap that satisfies the constraints and the loss function. Finally, based on the optimal lane-changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane-changing process, completing the lane change. This achieves the prediction and selection of an optimal lane-changing environment during the lane-changing process, thereby resolving the prior art problem of autonomous vehicles lacking the ability to determine an optimal lane-changing environment when changing lanes.

[0096] 3) The vehicle system of the present application includes the above-mentioned control device, and the above-mentioned control device is used to execute any one of the lane changing methods of the vehicle. First, future motion state information representing the motion state information of the first target vehicle, multiple second target vehicles and multiple third target vehicles at each future moment is obtained, and the above-mentioned motion state information includes at least one of position, speed and acceleration. The above-mentioned first target vehicle and the vehicle to be changed are both in the first lane and are located in front of the vehicle to be changed, and the second target vehicle and the third target vehicle are in the second lane and are adjacent; secondly, the above-mentioned motion state information of the vehicle to be changed is used as a variable to establish a planning model of the gap between the second target vehicle and the third target vehicle, and the constraints and loss function corresponding to the planning model are obtained; thirdly, the obtained future motion state information is input into the above-mentioned planning model, and the optimal lane changing motion state information of the vehicle to be changed is calculated according to the constraints and the loss function; finally, at least according to the optimal lane changing motion state information, the vehicle to be changed is controlled to change lanes in the gap corresponding to the optimal lane changing motion state information during the lane changing process. Compared with the existing technology, in which autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes, the vehicle system of the present application establishes a planning model for multiple gaps on the lane to be merged, and then calculates the optimal lane changing motion state information of the vehicle to be changed based on the planning model of the gaps, constraints and loss function. That is, the optimal motion state information corresponding to the process of the vehicle to be changed lanes changing to the target gap that satisfies the constraints and the loss function is calculated. Finally, based on the above-mentioned optimal lane changing motion state information, the vehicle to be changed lanes is controlled to change lanes to the target gap during the lane changing process to complete the lane change, thereby realizing the prediction and selection of the optimal lane changing environment during the lane changing process, and solving the problem in the existing technology that autonomous driving vehicles lack the ability to determine the optimal lane changing environment when changing lanes.

[0097] The foregoing description is merely a preferred embodiment of the present application and is not intended to limit the present application. Persons skilled in the art will readily appreciate that various modifications and variations are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present application shall be included within the scope of protection of the present application.

Claims

1. A lane changing method for a vehicle, characterized in that: include: Obtaining future motion state information, the future motion state information including motion state information of a first target vehicle, a plurality of second target vehicles, and a plurality of third target vehicles at each future moment, the motion state information including at least one of position information, velocity, and acceleration, the first target vehicle being a vehicle located in a first lane, adjacent to a vehicle to be lane-changed, and ahead of the vehicle to be lane-changed in a direction of travel, the second target vehicle and the third target vehicle being two adjacent vehicles located in a second lane, and in the direction of travel, the second target vehicle being ahead of the third target vehicle, the first lane being a lane in which the vehicle to be lane-changed is located, and the second lane being a lane into which the vehicle to be lane-changed is to merge; Establishing a planning model for the gap, and obtaining constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variables of the planning model are the motion state information of the vehicle to be changed lanes; Inputting the future motion state information into the planning model, and calculating the optimal lane-changing motion state information of the vehicle to be lane-changed based on the constraint conditions and the loss function; controlling the vehicle to be lane-changed to change lanes to a target gap during a lane-changing process based at least on the optimal lane-changing motion state information, the target gap being the gap corresponding to the optimal lane-changing motion state information; Get future motion status information, including: Acquire current motion state information in real time, the current motion state information being the position information, the speed, and the acceleration of the first target vehicle, the plurality of second target vehicles, and the plurality of third target vehicles at each current moment; Establishing a prediction model, the prediction model is trained by machine learning using multiple sets of data, each set of data including: historical current motion state information and the corresponding position information, speed, and acceleration of the first target vehicle, multiple second target vehicles, and multiple third target vehicles at each predetermined time, the predetermined time being later than the time corresponding to the historical current motion state information; Inputting the current motion state information into the prediction model to obtain the position information, the speed, and the acceleration of the first target vehicle, the plurality of second target vehicles, and the plurality of third target vehicles at each of the future moments; The gap between each second target vehicle and the corresponding third target vehicle at each future time is determined based on the position information at each future time.

2. The method according to claim 1, characterized in that Inputting the future motion state information into the planning model and calculating the optimal lane-changing motion state information of the vehicle to be lane-changed based on the constraint conditions and the loss function includes: Inputting the future motion state information into the planning model, and calculating a feasible solution corresponding to each of the future moments according to the constraint conditions, the feasible solution including at least one of the speed, acceleration, and position information of the vehicle to be lane-changed; Based on the feasible solutions corresponding to the future moments and the loss function, an optimal solution corresponding to the future moments that satisfies the loss function is determined to obtain the optimal lane-changing motion state information.

3. The method according to claim 2, characterized in that The feasible solution includes the speed and / or the acceleration, and controlling the vehicle to be lane-changed to change lanes to a target gap during the lane-changing process based at least on the optimal lane-changing motion state information includes: performing predetermined processing on the speed and / or the acceleration corresponding to each of the future moments to obtain the position information of the vehicle to change lanes corresponding to each of the future moments, the predetermined processing including integration; generating a motion trajectory of the vehicle to be lane-changed according to each of the position information; The vehicle to be lane-changed is controlled to move according to the motion trajectory so that the vehicle to be lane-changed changes lanes to the target gap.

4. The method according to claim 1, wherein Build a planning model for the gap, including: A convex quadratic programming equation is established using the motion state information of the vehicle to change lanes as the variable to obtain the planning model.

5. The method according to claim 1, wherein The constraint condition includes that during the lane changing process, the vehicle to be changed lanes does not overtake the first target vehicle and the second target vehicle in the driving direction, and overtakes the third target vehicle.

6. The method according to claim 5, characterized in that Obtaining the constraints corresponding to the planning model includes: Obtaining a lane change duration, where the lane change duration is the time required from receiving a lane change request to the vehicle to be changed lanes changing to the second lane; Acquire first position information, where the first position information is a plurality of position information of the vehicle to be lane-changed within the lane-changing duration; Determine second position information, third position information, and fourth position information based on the future motion state information and the lane change duration, wherein the second position information is a plurality of position information of each second target vehicle within the lane change duration, the third position information is a plurality of position information of each corresponding third target vehicle within the lane change duration, and the fourth position information is a plurality of position information of the first target vehicle within the lane change duration; Determine that the constraint condition is that the first position information satisfies: within the lane change duration and in the driving direction, the first position information is located in front of the second position information at the corresponding moment, and is located behind the third position information and the fourth position information at the corresponding moment.

7. The method according to claim 1, characterized in that The loss function includes at least one of the following: the sum of the squares of the acceleration variables of the vehicle to change lanes at each moment, the speed of the second target vehicle corresponding to the gap, the speed of the third target vehicle corresponding to the gap, and the length of the gap along the direction of the second lane.

8. A lane changing device for a vehicle, characterized in that: include: an acquisition unit, configured to acquire future motion state information, the future motion state information including motion state information of a first target vehicle, a plurality of second target vehicles, and a plurality of third target vehicles at each future moment, the motion state information including at least one of position information, velocity, and acceleration, the first target vehicle being a vehicle located in a first lane, adjacent to a vehicle to be lane-changed, and in front of the vehicle to be lane-changed in a direction of travel, the second target vehicle and the third target vehicle being two adjacent vehicles located in a second lane, and in the direction of travel, the second target vehicle being in front of the third target vehicle, the first lane being a lane in which the vehicle to be lane-changed is located, and the second lane being a lane into which the vehicle to be lane-changed is to merge; an establishing unit, configured to establish a planning model for a gap, and obtain constraints and a loss function corresponding to the planning model, wherein the gap is the distance between the second target vehicle and the third target vehicle, and the variables of the planning model are the motion state information of the vehicle to be changed lanes; an input unit, configured to input the future motion state information into the planning model, and calculate the optimal lane-changing motion state information of the vehicle to be lane-changed based on the constraint conditions and the loss function; a control unit, configured to control the vehicle to be lane-changed to change lanes to a target gap during a lane-changing process based at least on the optimal lane-changing motion state information, the target gap being the gap corresponding to the optimal lane-changing motion state information; The acquisition unit includes a first acquisition module, a creation submodule, an input submodule and a second determination module, wherein: The first acquisition module is used to acquire current motion state information in real time, wherein the current motion state information is the position information, speed, and acceleration of the first target vehicle, the plurality of second target vehicles, and the plurality of third target vehicles at each current moment; The establishment submodule is used to establish a prediction model, and the prediction model is trained by machine learning using multiple sets of data, each set of data in the multiple sets of data including: historical current motion state information and the corresponding position information, speed, and acceleration of the first target vehicle, multiple second target vehicles, and multiple third target vehicles at each predetermined time, the predetermined time being later than the time corresponding to the historical current motion state information; The input submodule is used to input the current motion state information into the prediction model to obtain the position information, speed and acceleration of the first target vehicle, the plurality of second target vehicles and the plurality of third target vehicles at each of the future moments; The second determining module is configured to determine the gap between each of the second target vehicles and the corresponding third target vehicle at each of the future moments according to the position information at each of the future moments.

9. The device according to claim 8, characterized in that The input unit includes: a calculation module, configured to input the future motion state information into the planning model and, based on the constraints, calculate a feasible solution corresponding to each of the future moments, the feasible solution including at least one of the speed, acceleration, and position information of the vehicle to be lane-changed; A determination module is used to determine the optimal solution corresponding to each of the future moments that satisfies the loss function based on the feasible solutions corresponding to each of the future moments and the loss function, and obtain the optimal lane change motion state information.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 7.

11. A processor, characterized in that: The processor is configured to run a program, wherein the program executes the method according to any one of claims 1 to 7 when running.

12. An electronic device, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include instructions for executing the method according to any one of claims 1 to 7.

13. A vehicle system, characterized in that: include: autonomous vehicles; The control device of the autonomous driving vehicle is used to execute the method described in any one of claims 1 to 7.

Images