Vehicle lane change trajectory planning method, device, storage medium and equipment

Abstract

The present application provides a vehicle lane change trajectory planning method, device, storage medium and equipment. In this method, a vehicle lane change trajectory planning model based on a cubic polynomial is used to obtain a vehicle lane change trajectory set, and a target lane change duration is determined by solving the vehicle energy consumption minimization problem. According to the target lane change duration, the optimal vehicle lane change trajectory is selected from the vehicle lane change trajectory set, and then a model prediction controller based on a Kalman filter is used to accurately track the optimal vehicle lane change trajectory. In this way, without relying on large-scale data, by optimizing the vehicle lane change trajectory, the trajectory quality is effectively improved, and unnecessary energy consumption can be reduced, reducing energy costs, and effectively ensuring the reliability of the vehicle lane change process.

Description

Technical Field

[0001] The present application relates to the field of driving assistance technology, and more specifically, to a vehicle lane change trajectory planning method, device, storage medium and equipment. Background Art

[0002] Autonomous driving technology promotes the development of a new generation of safer, smarter and more environmentally friendly travel by reducing traffic accidents, alleviating the heavy driving burden of human drivers and optimizing traffic efficiency. As one of the basic driving actions, the motion planning of vehicle lane change has always been the research focus in the field of autonomous driving. Existing autonomous vehicles mainly use data-oriented methods to achieve vehicle lane change motion planning. Although this method has the potential to capture the complexity of human driving behavior style, its demand for large-scale data limits its application efficiency. When the amount of data is insufficient, the generated lane change trajectory is not accurate and stable enough, which increases the risk of the vehicle in the lane change process and easily leads to unnecessary energy waste. Summary of the invention

[0003] The purpose of the present application is to provide a vehicle lane change trajectory planning method, device, storage medium and equipment, aiming to solve the problem that the vehicle lane change motion planning method in the related art relies on large-scale data. When the amount of data is insufficient, the generated lane change trajectory is not accurate and stable enough, thereby increasing the risk of the vehicle lane change process and easily leading to unnecessary energy waste.

[0004] In a first aspect, the present application provides a vehicle lane change trajectory planning method, comprising: obtaining a vehicle lane change trajectory set based on a vehicle lane change trajectory planning model; the vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle; by solving the vehicle energy consumption minimization problem, a target lane change duration is determined, and according to the target lane change duration, an optimal vehicle lane change trajectory is selected from the vehicle lane change trajectory set; and a model prediction controller based on a Kalman filter is used to perform trajectory tracking control on the optimal vehicle lane change trajectory so that the vehicle completes the lane change along the optimal vehicle lane change trajectory.

[0005] In the above implementation process, a vehicle lane change trajectory planning model based on cubic polynomials is used to obtain a set of vehicle lane change trajectories. By solving the problem of minimizing vehicle energy consumption, the target lane change duration is determined. According to the target lane change duration, the optimal vehicle lane change trajectory is selected from the set of vehicle lane change trajectories. After that, a model predictive controller based on Kalman filtering is used to accurately track the optimal vehicle lane change trajectory. In this way, without relying on large-scale data, the quality of the trajectory is effectively improved by optimizing the vehicle lane change trajectory, and unnecessary energy consumption and energy costs can be reduced, effectively ensuring the reliability of the vehicle lane change process.

[0006] Furthermore, in some examples, the vehicle energy consumption minimization problem is described based on a polynomial model for representing the vehicle energy consumption rate; the coefficients in the polynomial model for representing the vehicle energy consumption rate are learned through an adaptive neural network.

[0007] In the above implementation process, a method for obtaining the problem of minimizing vehicle energy consumption is provided.

[0008] Furthermore, in some examples, the vehicle energy consumption minimization problem has vehicle dynamics constraints and surrounding vehicle constraints; the vehicle dynamics constraints include boundary conditions of the vehicle sideslip angle and boundary conditions of the yaw angular velocity; the surrounding vehicle constraints include a safe lane change area formed based on a collision point where the vehicle collides with surrounding vehicles.

[0009] In the above implementation process, in the process of solving the vehicle energy consumption minimization problem, the internal constraints of the vehicle dynamics limitations and the external constraints from the driving environment are considered to ensure that the vehicle's motion state conforms to the principles of vehicle dynamics while ensuring the vehicle's own driving safety.

[0010] Further, in some examples, the boundary condition of the vehicle sideslip angle is expressed as the following formula:

[0011]

[0012] The boundary condition of the yaw rate is expressed as the following formula:

[0013]

[0014] in, is the vehicle sideslip angle; is the yaw angular velocity; is the mass of the vehicle; is the acceleration due to gravity; is the road friction coefficient; is the rear tire yaw stiffness; and are the distances from the vehicle’s center of mass to the front and rear axles, respectively; is the longitudinal velocity of the vehicle.

[0015] In the above implementation process, by combining the equations corresponding to the boundary conditions of the vehicle sideslip angle and the boundary conditions of the yaw rate, a stable envelope layer can be obtained to evaluate the stability of the vehicle during movement.

[0016] Furthermore, in some examples, the surrounding vehicle constraints are obtained based on the following method: establishing an edge collision scenario between the host vehicle and the surrounding vehicles during a lane change process; in the edge collision scenario, when the host vehicle starts the lane change operation, the relative distance between the host vehicle and the front vehicle in the same lane is a first relative distance, and the relative distance between the host vehicle and the rear vehicle in the target lane is a second relative distance; based on the first relative distance, obtaining a coordinate equation of a first collision point corresponding to a collision between the host vehicle and the front vehicle, and based on the second relative distance, obtaining a coordinate equation of a second collision point corresponding to a collision between the host vehicle and the rear vehicle; based on the coordinate equations of the first collision point and the second collision point, obtaining a first collision moment and a second collision moment, and then substituting the first collision moment and the second collision moment into the vehicle lane change trajectory planning model to obtain upper and lower bounds of the target lane change duration.

[0017] In the above implementation process, in order to obtain a safe lane change area, an edge collision scenario between the vehicle and the surrounding vehicles during the lane change process is established. According to the edge collision scenario, the collision moment when the vehicle may collide with the preceding vehicle in the same lane and the following vehicle in the target lane is obtained, and it is substituted into the vehicle lane change trajectory planning model to obtain the upper and lower bounds of the target lane change duration, that is, the lane change driving safety constraints of the surrounding vehicles.

[0018] Furthermore, in some examples, the target lane change duration is greater than or equal to the minimum lane change duration; the minimum lane change duration is obtained by querying a calibration table based on the longitudinal speed of the current vehicle and the road friction coefficient; the calibration table is established by simulating the dynamic behavior of the vehicle through simulation software to obtain the correspondence between the longitudinal speed, the road friction coefficient and the minimum lane change duration.

[0019] In the above implementation process, the vehicle dynamics constraints are considered, simulation software is used to simulate the dynamic behavior of the vehicle, and a series of simulation experiments are carried out on the vehicle with different longitudinal speeds and road friction coefficients to record the minimum lane change duration, thereby further ensuring the stability of the vehicle.

[0020] Furthermore, in some examples, the state variables of the model predictive controller include the vehicle's longitudinal speed, lateral speed, yaw angle and yaw angular velocity; the control variables include the front wheel steering angle, the front wheel lateral driving force and the rear wheel lateral driving force; the model predictive controller uses a Kalman filter algorithm to perform state prediction on the state variables, and generates a control output of the vehicle based on the prediction results and the control variables.

[0021] In the above implementation process, a specific working mode of the model predictive controller based on Kalman filtering is provided. The application of this controller can ensure the real-time tracking of the optimal trajectory and ensure the reliability of the vehicle's lane changing process.

[0022] In a second aspect, the present application provides a vehicle lane change trajectory planning device, comprising: an acquisition module, used to acquire a vehicle lane change trajectory set based on a vehicle lane change trajectory planning model; the vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle; a determination module, used to determine a target lane change duration by solving a vehicle energy consumption minimization problem, and select an optimal vehicle lane change trajectory from the vehicle lane change trajectory set according to the target lane change duration; a tracking module, used to perform trajectory tracking control on the optimal vehicle lane change trajectory using a model predictive controller based on Kalman filtering, so that the vehicle completes the lane change along the optimal vehicle lane change trajectory.

[0023] In a third aspect, the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in any one of the first aspects when executing the computer program.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, on which instructions are stored. When the instructions are executed on a computer, the computer executes the method as described in any one of the first aspects.

[0025] In a fifth aspect, the present application provides a computer program product, which, when running on a computer, enables the computer to execute the method as described in any one of the first aspects.

[0026] Other features and advantages disclosed in the present application will be described in the following description, or some features and advantages can be inferred or determined without doubt from the description, or can be learned by implementing the above-mentioned technology disclosed in the present application.

[0027] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0029] Figure 1 A flow chart of a vehicle lane change trajectory planning method provided in an embodiment of the present application;

[0030] Figure 2 A schematic diagram of an edge collision scenario between a host vehicle and surrounding vehicles during a lane change provided in an embodiment of the present application;

[0031] Figure 3 A block diagram of a vehicle lane change trajectory planning device provided in an embodiment of the present application;

[0032] Figure 4 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0034] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0035] As described in the background technology, the vehicle lane change motion planning method in the related art relies on large-scale data. When the amount of data is insufficient, the generated lane change trajectory is not accurate and stable enough, thereby increasing the risk of the vehicle lane change process and easily leading to unnecessary energy waste. Based on this, the embodiment of the present application provides a vehicle lane change trajectory planning solution to solve the above problems.

[0036] Next, the embodiments of the present application are introduced:

[0037] like Figure 1 As shown, Figure 1 1 is a flow chart of a vehicle lane change trajectory planning method provided in an embodiment of the present application. The method can be applied to a vehicle controller, such as an autonomous driving domain controller, etc.

[0038] The method comprises:

[0039] Step 101: obtaining a vehicle lane change trajectory set based on a vehicle lane change trajectory planning model; the vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle;

[0040] The vehicle lane change trajectory planning model mentioned in this step is a mathematical model that can generate the vehicle lane change trajectory. It uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle. That is, its mathematical expression can be expressed as:

[0041]

[0042]

[0043] in, and represent the longitudinal displacement and lateral displacement of the vehicle respectively, and is the coefficient. During the lane change process, the displacement of the vehicle from the starting point to the target end point along the longitudinal direction is , the lateral displacement is , the duration of lane change is , the initial longitudinal velocity of the vehicle is , considering the boundary conditions during the vehicle lane change process, the coefficients of the above cubic polynomial model can be expressed as: , , , , , , , .

[0044] In order to ensure that the vehicle does not exceed the expected longitudinal position after the lane change is completed, the vehicle lane change process must meet At the same time, assuming that the longitudinal speed of the vehicle remains constant during the lane change process, the vehicle lane change trajectory planning model can be mathematically described as follows:

[0045]

[0046]

[0047] Based on the vehicle lane change trajectory planning model, multiple vehicle lane change trajectories that satisfy the above two equations can be generated to form a vehicle lane change trajectory set.

[0048] Step 102: determining a target lane change duration by solving a vehicle energy consumption minimization problem, and selecting an optimal vehicle lane change trajectory from the vehicle lane change trajectory set according to the target lane change duration;

[0049] In this embodiment, the lane change duration is As decision variables, the vehicle energy consumption minimization problem is expressed as , by minimizing energy consumption , the corresponding lane change duration can be determined, that is, the target lane change duration , and then select the energy-efficient optimal vehicle lane change trajectory.

[0050] In some embodiments, the vehicle energy consumption minimization problem mentioned in this step is described based on a polynomial model for representing the vehicle energy consumption rate; the coefficients in the polynomial model for representing the vehicle energy consumption rate are learned through an adaptive neural network. The polynomial model here can be expressed as:

[0051]

[0052] in, Indicates vehicle energy consumption rate (ml / s), Indicates vehicle speed. represents the vehicle acceleration, and are the coefficients in the polynomial model, which can be learned through an adaptive neural network. Then the energy consumption of the vehicle during the lane change is It is expressed as:

[0053]

[0054] Here It can be expressed as fuel consumption in ml.

[0055] In some embodiments, the vehicle energy consumption minimization problem mentioned in this step has vehicle dynamics constraints and surrounding vehicle constraints; the vehicle dynamics constraints include boundary conditions of vehicle sideslip angle and boundary conditions of yaw angular velocity; the surrounding vehicle constraints include a safe lane change area formed based on the collision point where the vehicle collides with surrounding vehicles. In the process of solving the vehicle energy consumption minimization problem, the internal constraints of vehicle dynamics constraints and the external constraints from the driving environment are considered to ensure that the vehicle's motion state conforms to the principles of vehicle dynamics and ensure the vehicle's own driving safety. Among them, the vehicle dynamics constraints include the boundary conditions of the vehicle's sideslip angle, which is a parameter that describes the angle between the vehicle body and the driving direction during the vehicle's driving process. In the process of minimizing energy consumption, the vehicle's sideslip angle needs to be controlled within a reasonable range to ensure the stability and safety of the vehicle; the vehicle dynamics constraints also include the boundary conditions of the yaw angular velocity, which is a physical quantity that describes the speed of the vehicle body rotating around the vertical axis during the vehicle's driving process. Similarly, in the process of minimizing energy consumption, the yaw angular velocity also needs to be controlled within a reasonable range to avoid excessive deviation of the vehicle from the predetermined trajectory or other dangerous situations. As for the constraints on surrounding vehicles, a safe lane change area can be formed based on the collision point between the vehicle and the surrounding vehicles. When the solution to the vehicle energy consumption minimization problem is within this area, the vehicle can safely complete the lane change operation without colliding with the surrounding vehicles.

[0056] Specifically, the vehicle sideslip angle during driving and yaw rate The following relations are satisfied:

[0057]

[0058] in, and are the lateral tire forces on the rear and front axles, respectively; is the vehicle mass; Represents the longitudinal velocity of the vehicle in the geographic coordinate system. When , the vehicle is in a stable state, so that the heading angular velocity reaches the stable boundary. Therefore, in some embodiments, the boundary condition of the yaw angular velocity can be expressed as the following formula:

[0059]

[0060] in, is the acceleration due to gravity; is the road friction coefficient;

[0061] In addition to yaw stability, the saturation of the rear tires must also be considered to ensure vehicle stability, and the lateral force of the rear wheels and tire slip angle The relationship between is represented by the Brush tire model. Under the small angle assumption, the tire side slip angle It can be linearly approximated as:

[0062]

[0063] in, is the rear tire yaw stiffness; and are the distances from the center of mass of the vehicle to the front axle and the rear axle, respectively; therefore, in some embodiments, the boundary condition of the vehicle sideslip angle can be expressed as the following formula:

[0064]

[0065] Combining the equations corresponding to these two boundary conditions, a stable envelope can be obtained to evaluate the stability of the vehicle during motion.

[0066] In some embodiments, the aforementioned surrounding vehicle constraints can be obtained based on the following method: establish an edge collision scenario between the vehicle and surrounding vehicles during the lane change process; in the edge collision scenario, when the vehicle starts the lane change operation, the relative distance between the vehicle and the front vehicle in the same lane is a first relative distance, and the relative distance between the vehicle and the rear vehicle in the target lane is a second relative distance; according to the first relative distance, obtain the coordinate equation of the first collision point corresponding to the collision between the vehicle and the front vehicle, and according to the second relative distance, obtain the coordinate equation of the second collision point corresponding to the collision between the vehicle and the rear vehicle; based on the coordinate equations of the first collision point and the second collision point, obtain the first collision moment and the second collision moment, and then substitute the first collision moment and the second collision moment into the vehicle lane change trajectory planning model to obtain the upper and lower bounds of the target lane change duration. In other words, in order to obtain a safe lane change area, establish an edge collision scenario between the vehicle and surrounding vehicles during the lane change process, in which the relative distance between the vehicle and the front vehicle in the same lane is the first relative distance. , the relative distance between the vehicle and the following vehicle in the target lane is the second relative distance , when the speed of the vehicle is greater than that of the vehicle in front, as the distance decreases, the vehicle may collide with the vehicle in front, and the collision point is , according to the first relative distance The collision point can be obtained Similarly, if the speed of the rear vehicle is greater than that of the vehicle, and the distance between the two vehicles is less than the safe distance before changing lanes, the vehicle may collide with the rear vehicle, and the collision point is , according to the second relative distance The collision point can be obtained The mathematical expression of the coordinates of the collision point and , we can get the safe lane change area, in which the vehicle may perform a safe lane change. By combining the mathematical expressions of the coordinates of the two collision points, we can solve the corresponding collision time. and , the collision point is located at a specific lane change duration On the key lane change trajectory of the feature, and Substituting into the vehicle lane change trajectory planning model, the upper bound of the target lane change duration can be obtained: and the lower bound , that is, considering the lane change driving safety constraints of surrounding vehicles, it is necessary to satisfy .

[0067] In addition, in some embodiments, the target lane change duration mentioned in this step is greater than or equal to the minimum lane change duration; the minimum lane change duration is obtained by querying a calibration table based on the longitudinal speed of the current vehicle and the road friction coefficient; the calibration table is established by simulating the dynamic behavior of the vehicle using simulation software to obtain the correspondence between the longitudinal speed, the road friction coefficient and the minimum lane change duration. In other words, considering the vehicle dynamics constraints, simulation software such as Simpack can also be used in advance to simulate the vehicle's dynamic behavior, and a series of simulation experiments are carried out on the vehicle at different longitudinal speeds and road friction coefficients to record the minimum lane change duration. In this way, when applying it, the corresponding minimum lane change duration can be obtained based on the actual longitudinal speed and road friction coefficient. In the problem of minimizing vehicle energy consumption, it is required to satisfy , thereby further ensuring the stability of the vehicle.

[0068] Step 103: Use a model prediction controller based on Kalman filtering to perform trajectory tracking control on the optimal vehicle lane change trajectory, so that the vehicle completes the lane change along the optimal vehicle lane change trajectory.

[0069] In this embodiment, a model predictive controller based on Kalman filtering is used to accurately track the optimal vehicle lane change trajectory. The controller combines the ideas of Kalman filtering and model predictive control to achieve real-time tracking of the optimal trajectory.

[0070] In some embodiments, the state variables of the model predictive controller mentioned in this step include the longitudinal speed, lateral speed, yaw angle and yaw angular velocity of the vehicle; the control variables include the front wheel steering angle, the front wheel lateral driving force and the rear wheel lateral driving force; the model predictive controller uses the Kalman filter algorithm to predict the state variables, and generates the control output of the vehicle according to the prediction results and the control variables. That is, in the model predictive controller based on Kalman filtering, the state variables can be recorded as , the control variable is recorded as ,in, is the vehicle’s yaw angle, is the front wheel steering angle, and They represent the longitudinal driving force of the front and rear wheels of the vehicle respectively. In the process of trajectory tracking, the model predictive controller first establishes a vehicle dynamics model, and then uses the Kalman filter algorithm to estimate and predict the state of the vehicle. Based on the vehicle dynamics model and the state estimation results of the Kalman filter, the optimization problem of the model predictive controller is constructed. By solving the optimization problem, the optimal control variable sequence is obtained so that the vehicle can reach the desired state or path in the future. According to the control variable sequence, the vehicle control command is generated. In this way, the real-time tracking of the optimal trajectory is ensured, and the reliability of the vehicle lane change process is guaranteed.

[0071] In the embodiment of the present application, a vehicle lane change trajectory planning model based on cubic polynomials is used to obtain a set of vehicle lane change trajectories, and a target lane change duration is determined by solving the vehicle energy consumption minimization problem. According to the target lane change duration, the optimal vehicle lane change trajectory is selected from the set of vehicle lane change trajectories, and then a model prediction controller based on Kalman filtering is used to accurately track the optimal vehicle lane change trajectory. In this way, the quality of the trajectory is effectively improved by optimizing the vehicle lane change trajectory without relying on large-scale data, and unnecessary energy consumption and energy costs can be reduced, effectively ensuring the reliability of the vehicle lane change process.

[0072] In order to explain the solution of this application in more detail, a specific embodiment is introduced below:

[0073] This embodiment provides a lane change trajectory planning solution for an autonomous driving vehicle based on adaptive energy optimization. The overall motion planning system of this embodiment can be divided into a trajectory planning layer and a trajectory tracking control layer; wherein the trajectory planning layer includes:

[0074] S201, establishing a vehicle lane change trajectory planning model based on cubic polynomial;

[0075] Specifically, the mathematical expression of the vehicle lane change trajectory planning model based on cubic polynomial is as follows:

[0076]

[0077]

[0078] Consider the boundary conditions during the vehicle lane change process:

[0079]

[0080]

[0081] in, and is the coefficient, and represent the longitudinal displacement and lateral displacement of the vehicle respectively, It indicates the displacement of the vehicle from the starting point to the target end point in the longitudinal direction during the lane change process. It indicates the displacement of the vehicle from the starting point to the target end point in the lateral direction during the lane change process. is the duration of the lane change, is the initial longitudinal velocity, is the longitudinal velocity of the vehicle after changing lanes. and It can be expressed as: , , , , , , , ;

[0082] The vehicle process needs to be further satisfied ; Assuming that the longitudinal speed of the vehicle remains constant during the lane change process, the vehicle lane change trajectory planning model can be mathematically described as follows:

[0083]

[0084]

[0085] S202, determining an energy-efficient method for acquiring an optimal lane speed change trajectory;

[0086] Specifically, in order to obtain an energy-efficient vehicle lane change trajectory, the following polynomial model representing the vehicle energy consumption rate is adopted:

[0087]

[0088] in, Indicates vehicle energy consumption rate (ml / s), Indicates vehicle speed. represents the vehicle acceleration, and are the coefficients in the polynomial model, which can be learned by an adaptive neural network. As the decision variable, the vehicle energy consumption minimization problem can be expressed as:

[0089]

[0090] in, It represents the total energy consumption of the vehicle during the lane change process, in ml. , the corresponding lane change duration can be determined , thus selecting the energy-efficient optimal vehicle lane-changing trajectory;

[0091] S203, introducing constraints on vehicle dynamics feasibility;

[0092] Specifically, the constraints on vehicle dynamics feasibility include the vehicle sideslip angle Boundary conditions and yaw rate The boundary conditions are as follows: The boundary conditions are expressed as:

[0093]

[0094] Yaw angular velocity The boundary conditions are expressed as:

[0095]

[0096] in, is the vehicle mass; is the acceleration due to gravity; is the road friction coefficient; is the rear tire yaw stiffness; and are the distances from the vehicle’s center of mass to the front and rear axles, respectively; Represents the longitudinal velocity of the vehicle in the geographic coordinate system; and are the lateral tire forces on the rear and front axles, respectively;

[0097] Combining the above two boundary conditions, a stable envelope can be obtained to evaluate the stability of the vehicle during motion;

[0098] Vehicle dynamics feasibility constraints also include , To achieve the minimum lane change duration, the vehicle dynamics simulation software Simpack is used to simulate the dynamic behavior of the vehicle. A series of simulation experiments are conducted on the vehicle at different longitudinal speeds. and road friction coefficient to record the minimum lane change duration ;

[0099] S204, introducing constraints on surrounding traffic vehicles;

[0100] Specifically, to simplify the analysis process and highlight the algorithm itself, this embodiment considers a structured straight road with clear geometric features and assumes that the geometric dimensions of the participating vehicles are the same. Without loss of generality, assume that the host vehicle starts the lane change operation at . The edge collision scenario between the host vehicle and the surrounding vehicles during the lane change process is as follows Figure 2 As shown, the edge collision scene includes the host vehicle 21, the preceding vehicle 22 in the same lane, and the following vehicle 23 in the target lane. The position of the transparent vehicle is the critical position where a collision may occur. The width of the lane is , the width of the vehicle is , the yaw angle of the main vehicle is , the relative distance between the main vehicle and the front vehicle is , the relative distance between the main vehicle and the rear vehicle is , the edge point where the main vehicle and the front vehicle may collide is , the edge point where the main vehicle and the rear vehicle may collide is ;

[0101] The right front end of the main vehicle at the initial lane change moment is taken as the coordinate origin, and the collision moment between the main vehicle and the front vehicle is assumed to be , then the collision point Coordinates It can be expressed as:

[0102]

[0103]

[0104] In the formula, is the speed of the host vehicle at time t, is the speed of the preceding vehicle at time t;

[0105] Similarly, assuming that the collision time between the main vehicle and the rear vehicle is , then the collision point Coordinates It can be expressed as:

[0106]

[0107]

[0108] In the formula, is the speed of the rear vehicle at time t; combining the above four equations, we can solve the critical collision moment and , substituting it into the equation and The set of lane change trajectories in , and considering the kinematic model of the above edge collision scenario:

[0109]

[0110]

[0111] Considering the lane change driving safety constraints of surrounding vehicles, the upper and lower bounds of the lane change duration can be expressed as: .

[0112] In the trajectory tracking control layer, this embodiment scheme designs a model prediction controller based on Kalman filtering to accurately and quickly track and determine the lane change trajectory of the vehicle. In implementation, given the interaction between longitudinal and lateral motions in vehicle trajectory tracking, the coupling relationship between them should be considered when modeling vehicle dynamics. Specifically, the longitudinal, lateral, and yaw motions of the vehicle are considered to construct a three-degree-of-freedom vehicle dynamics model as shown below:

[0113]

[0114]

[0115]

[0116] in, , , are the longitudinal velocity, lateral velocity and yaw angle at the center of mass of the vehicle, and Represent the longitudinal driving force of the front and rear wheels of the vehicle, is the steering angle of the front wheels, is the yaw moment of inertia. The coupling characteristic is reflected in the lateral force of the front wheel generating a longitudinal component , and the longitudinal force of the front wheel produces a lateral component ;

[0117] In the geodetic coordinate system, the longitudinal velocity and the lateral velocity can be converted as follows:

[0118]

[0119]

[0120] The state variables of the model predictive controller are denoted as , the control variable is recorded as , the system output is recorded as , and assuming that the front wheel steering angle and yaw angle Very small, can make , , , ;

[0121] In order to reduce the impact of noise on the trajectory tracking task, Kalman filtering is used to reduce the noise of the state variables of the input controller. First, the state variables are estimated:

[0122] Assume that there is a measurement noise matrix in the system and its variance , process noise matrix and its variance , substituting it into the state space equation, we can get the state space equation with noise as follows:

[0123]

[0124]

[0125] Kalman filtering is used to predict the state of state variables, namely:

[0126]

[0127] Based on the previous three-degree-of-freedom vehicle dynamics model, a nonlinear vehicle dynamics model can be obtained, which can be expressed as:

[0128]

[0129]

[0130]

[0131]

[0132] Model predictive control uses the nonlinear vehicle dynamics model to predict the future state of the vehicle dynamics system, and then considers the physical constraints of the actuator to formulate the trajectory tracking optimal control problem. Finally, by solving the proposed optimal control problem in real time, the driving force and front wheel steering angle can be obtained, thereby realizing trajectory tracking control.

[0133] The scheme of this embodiment has at least the following advantages: First, the dual safety boundary provided by the vehicle lane change trajectory planning model based on the adaptive cubic polynomial is more carefully considered, ensuring that the generated trajectory set not only meets the vehicle dynamics limitations, but also remains safe within the lane change area; Second, the vehicle dynamics limitations and the surrounding vehicle conditions are used as constraints to ensure that the generated vehicle trajectory will not violate the vehicle dynamics limitations during the lane change process, and will also avoid collisions or interference with surrounding vehicles. Such consideration of constraints can improve the safety of vehicle lane change operations and reduce the risk of accidents. At the same time, by optimizing the vehicle change trajectory, unnecessary energy consumption can be reduced, and energy utilization efficiency can be improved, thereby extending the vehicle's cruising range and reducing energy costs; Third, the MPC vehicle lane change trajectory tracking control method based on Kalman filtering is adopted, which not only ensures real-time tracking of the optimal trajectory, but also takes into account the problem of computational efficiency, so that the system can operate efficiently in actual scenarios. The application of this controller ensures the reliability and practicality of the lane change process.

[0134] Corresponding to the embodiments of the aforementioned method, the present application also provides embodiments of a vehicle lane change trajectory planning device and a terminal using the same:

[0135] like Figure 3 As shown, Figure 3 : is a block diagram of a vehicle lane change trajectory planning device provided in an embodiment of the present application, the device comprising:

[0136] An acquisition module 31 is used to acquire a vehicle lane change trajectory set based on a vehicle lane change trajectory planning model; the vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle;

[0137] A determination module 32, configured to determine a target lane change duration by solving a vehicle energy consumption minimization problem, and select an optimal vehicle lane change trajectory from the vehicle lane change trajectory set according to the target lane change duration;

[0138] The tracking module 33 is used to perform trajectory tracking control on the optimal vehicle lane change trajectory using a model prediction controller based on Kalman filtering, so that the vehicle completes the lane change along the optimal vehicle lane change trajectory.

[0139] The implementation process of the functions and effects of each module in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, which will not be repeated here.

[0140] This application also provides an electronic device, see Figure 4 , Figure 4A block diagram of an electronic device provided in an embodiment of the present application. The electronic device may include a processor 410, a communication interface 420, a memory 430, and at least one communication bus 440. The communication bus 440 is used to realize direct connection and communication between these components. The communication interface 420 of the electronic device in the embodiment of the present application is used to communicate signaling or data with other node devices. The processor 410 may be an integrated circuit chip with signal processing capabilities.

[0141] The processor 410 mentioned above can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor 410 can also be any conventional processor, etc.

[0142] The memory 430 may be, but is not limited to, a random access memory (RAM), 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), etc. The memory 430 stores computer-readable instructions. When the computer-readable instructions are executed by the processor 410, the electronic device may execute the above-mentioned Figure 1 The method embodiment involves various steps.

[0143] Optionally, the electronic device may further include a storage controller and an input / output unit.

[0144] The memory 430, storage controller, processor 410, peripheral interface, input and output unit components are directly or indirectly electrically connected to each other to achieve data transmission or interaction. For example, these components can be electrically connected to each other via one or more communication buses 440. The processor 410 is used to execute executable modules stored in the memory 430, such as software function modules or computer programs included in the electronic device.

[0145] The input and output unit is used to provide users with the task creation and to create a start optional time period or preset execution time for the task to realize the interaction between the user and the server. The input and output unit can be, but is not limited to, a mouse and a keyboard.

[0146] Understandably, Figure 4 The structure shown is for illustration only, and the electronic device may also include Figure 4 More or fewer components as shown, or with Figure 4 Different configurations are shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0147] An embodiment of the present application further provides a storage medium having instructions stored thereon. When the instructions are run on a computer, the computer program is executed by a processor to implement the method described in the method embodiment. To avoid repetition, the method will not be described here.

[0148] The present application also provides a computer program product, which, when executed on a computer, enables the computer to execute the method described in the method embodiment.

[0149] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0150] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0151] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0152] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0153] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0154] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants 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, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

Claims

1. A vehicle lane change trajectory planning method, characterized in that: include: Based on the vehicle lane change trajectory planning model, a vehicle lane change trajectory set is obtained; The vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle; By solving the vehicle energy consumption minimization problem, a target lane change duration is determined, and according to the target lane change duration, an optimal vehicle lane change trajectory is selected from the vehicle lane change trajectory set; A model predictive controller based on Kalman filtering is used to perform trajectory tracking control on the optimal vehicle lane change trajectory so that the vehicle completes the lane change along the optimal vehicle lane change trajectory; the state variables of the model predictive controller include the longitudinal speed, lateral speed, yaw angle and yaw angle velocity of the vehicle; the control variables include the front wheel steering angle, the front wheel lateral driving force and the rear wheel lateral driving force; the model predictive controller uses a Kalman filtering algorithm to perform state prediction on the state variables, and generates the control output of the vehicle according to the prediction results and the control variables.

2. The method according to claim 1, characterized in that The vehicle energy consumption minimization problem is described based on a polynomial model for representing the vehicle energy consumption rate; the coefficients in the polynomial model for representing the vehicle energy consumption rate are obtained through adaptive neural network learning.

3. The method according to claim 1, characterized in that: The vehicle energy consumption minimization problem has vehicle dynamics constraints and surrounding vehicle constraints; the vehicle dynamics constraints include boundary conditions of the vehicle sideslip angle and the yaw angular velocity; the surrounding vehicle constraints include a safe lane change area formed based on a collision point where the vehicle collides with surrounding vehicles.

4. The method according to claim 3, characterized in that The boundary condition of the vehicle sideslip angle is expressed as the following formula: The boundary condition of the yaw rate is expressed as the following formula: in, is the vehicle sideslip angle; is the yaw angular velocity; is the mass of the vehicle; is the acceleration due to gravity; is the road friction coefficient; is the rear tire yaw stiffness; and are the distances from the vehicle’s center of mass to the front and rear axles, respectively; is the longitudinal velocity of the vehicle.

5. The method according to claim 3, characterized in that: The surrounding vehicle constraints are obtained based on the following method: Establishing an edge collision scenario between the host vehicle and surrounding vehicles during a lane change process; in the edge collision scenario, when the host vehicle starts the lane change operation, the relative distance between the host vehicle and the preceding vehicle in the same lane is a first relative distance, and the relative distance between the host vehicle and the following vehicle in the target lane is a second relative distance; According to the first relative distance, obtaining a coordinate equation of a first collision point corresponding to a collision between the host vehicle and the preceding vehicle, and according to the second relative distance, obtaining a coordinate equation of a second collision point corresponding to a collision between the host vehicle and the following vehicle; Based on the coordinate equations of the first collision point and the second collision point, a first collision moment and a second collision moment are obtained, and then the first collision moment and the second collision moment are substituted into the vehicle lane change trajectory planning model to obtain the upper and lower bounds of the target lane change duration.

6. The method according to claim 3, characterized in that The target lane change duration is greater than or equal to the minimum lane change duration; the minimum lane change duration is obtained by querying a calibration table based on the longitudinal speed of the current vehicle and the road friction coefficient; the calibration table is established by simulating the dynamic behavior of the vehicle through simulation software to obtain the corresponding relationship between the longitudinal speed, the road friction coefficient and the minimum lane change duration.

7. A vehicle lane change trajectory planning device, characterized in that: include: An acquisition module, used for acquiring a vehicle lane change trajectory set based on a vehicle lane change trajectory planning model; The vehicle lane change trajectory planning model uses a cubic polynomial model to describe the lateral displacement and longitudinal displacement of the vehicle; A determination module, configured to determine a target lane change duration by solving a vehicle energy consumption minimization problem, and select an optimal vehicle lane change trajectory from the vehicle lane change trajectory set according to the target lane change duration; A tracking module is used to use a model prediction controller based on Kalman filtering to perform trajectory tracking control on the optimal vehicle lane change trajectory so that the vehicle completes the lane change along the optimal vehicle lane change trajectory; the state variables of the model prediction controller include the vehicle's longitudinal speed, lateral speed, yaw angle and yaw angle velocity; the control variables include the front wheel steering angle, the front wheel lateral driving force and the rear wheel lateral driving force; the model prediction controller uses a Kalman filter algorithm to perform state prediction on the state variables, and generates the vehicle's control output according to the prediction results and the control variables.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

Images