A vehicle longitudinal control method, device, equipment, medium and product

Abstract

The application discloses a vehicle longitudinal control method, device, equipment, medium and product, comprising: constructing a vehicle longitudinal controller, the vehicle longitudinal controller meets state constraints and control quantity constraints; obtaining a reference state and a vehicle state of a target vehicle; determining a controller parameter initial value of the target vehicle according to the reference state and the vehicle state; updating the controller parameter initial value of the target vehicle to obtain a current controller parameter. The above technical feature effectively reduces the parameter debugging difficulty, adapts to various application scenarios, simultaneously considers vehicle state constraints and driving comfort, and improves the scene adaptability and control smoothness of the controller.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a method, device, equipment, medium, and product for longitudinal vehicle control. Background Technology

[0002] The vehicle longitudinal controller is a core component of autonomous and intelligent driving systems, responsible for controlling the vehicle's longitudinal acceleration, deceleration, and speed maintenance. Its control performance directly determines the vehicle's safety, comfort, and driving efficiency. With the rapid development of the automotive industry and the continuous improvement of its intelligence level, the demand for vehicle longitudinal control systems is increasing to ensure driving safety, comfort, and efficiency.

[0003] Currently, mainstream vehicle longitudinal control methods all employ feedback control strategies. Typical controllers include Proportional Integral Derivative (PID) controllers, such as speed PID controllers, position PID controllers, and speed-position dual PID controllers. These controllers use speed and position errors during vehicle operation as the basis for control, and adjust the output of longitudinal control commands through feedback of these errors to control the vehicle's longitudinal motion. However, the aforementioned vehicle longitudinal control schemes based on PID control suffer from problems such as difficult parameter tuning, stringent requirements for trajectory and speed planning, and an inability to balance vehicle state constraints and driving comfort during control, making them difficult to adapt to the control needs of different driving scenarios. Summary of the Invention

[0004] This invention provides a vehicle longitudinal control method, device, equipment, medium, and product, which effectively reduces the difficulty of parameter debugging, adapts to various application scenarios, and takes into account vehicle state constraints and driving comfort, thereby improving the scenario adaptability and control smoothness of the controller.

[0005] In a first aspect, embodiments of this disclosure provide a vehicle longitudinal control method, including: Construct a vehicle longitudinal controller that satisfies state constraints and control quantity constraints; Obtain the reference status and vehicle status of the target vehicle; The initial values ​​of the controller parameters of the target vehicle are determined based on the reference state and the vehicle state. The initial values ​​of the controller parameters for the target vehicle are updated to obtain the current controller parameters.

[0006] Secondly, embodiments of this disclosure provide a vehicle longitudinal control device, comprising: A controller construction module is used to construct a vehicle longitudinal controller, which satisfies state constraints and control quantity constraints. The status data acquisition module is used to acquire the reference status and vehicle status of the target vehicle; The parameter initial value determination module is used to determine the initial values ​​of the controller parameters of the target vehicle based on the reference state and the vehicle state. The parameter initial value update module is used to update the initial values ​​of the controller parameters of the target vehicle to obtain the current controller parameters.

[0007] Thirdly, embodiments of this disclosure provide an electronic device, including: At least one processor; and A memory that is communicatively connected to at least one processor; wherein, The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform a vehicle longitudinal control method provided in the first aspect embodiment described above.

[0008] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the vehicle longitudinal control method provided in the first aspect of the embodiments described above.

[0009] Fifthly, this disclosure provides a computer program product, which includes a computer program that, when executed by a processor, implements a vehicle longitudinal control method provided in the first aspect of the embodiment.

[0010] The technical solution of this invention involves constructing a vehicle longitudinal controller that satisfies state constraints and control quantity constraints; acquiring a reference state and a vehicle state of the target vehicle; determining initial values ​​of the controller parameters for the target vehicle based on the reference state and the vehicle state; and updating the initial values ​​of the controller parameters to obtain the current controller parameters. These technical features effectively reduce the difficulty of parameter debugging, adapt to various application scenarios, and simultaneously consider vehicle state constraints and driving comfort, thereby improving the controller's scenario adaptability and control smoothness.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a vehicle longitudinal control method provided in an embodiment of the present invention; Figure 2 This is a flowchart of the controller design for a vehicle longitudinal controller provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of vehicle projection in an SL coordinate system provided in an embodiment of the present invention; Figure 4 This is a control block diagram of a vehicle longitudinal control method provided in an embodiment of the present invention; Figure 5 This is a flowchart of another vehicle longitudinal control method provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the structure of a vehicle longitudinal control device provided in an embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] The vehicle longitudinal control scheme based on PID control has several drawbacks. First, the controller contains multiple parameters, and parameter tuning is difficult. Different parameters need to be matched for different driving scenarios to ensure a good driving experience, resulting in poor adaptability. Second, it has stringent requirements for the driving trajectory, requiring the trajectory to complete speed planning. Trajectories without speed planning cannot achieve effective control. Third, the controller design does not incorporate the state considerations of vehicle acceleration and jerk. If it is necessary to meet the upper and lower limits of acceleration and jerk, only simple amplitude limiting can be performed at the controller output, which limits the control accuracy. Finally, the controller design does not set constraints for acceleration and jerk, and the control law output by the controller cannot guarantee continuous change. Discontinuous control input has an adverse effect on the vehicle actuators, reducing actuator life and control smoothness.

[0017] Based on this, embodiments of the present invention provide a vehicle longitudinal control method, which pre-configures the controller performance to solve the above-mentioned technical problems and realize multi-scenario adaptation and smooth control of the controller application.

[0018] In one embodiment, Figure 1 This is a flowchart of a vehicle longitudinal control method provided by an embodiment of the present invention. This embodiment is applicable to situations where controller parameters are determined for a vehicle longitudinal controller. This method can be executed by a vehicle longitudinal control device, which can be implemented in hardware and / or software. The vehicle longitudinal control device can be integrated into the vehicle longitudinal controller.

[0019] like Figure 1 As shown, the method includes: S101. Construct a vehicle longitudinal controller that satisfies state constraints and control quantity constraints.

[0020] In this embodiment, the vehicle bus controller can be understood as a device that implements longitudinal acceleration, deceleration, and constant speed control of the vehicle. It takes state variables and control variables as inputs and outputs control commands to drive the vehicle's actuators. In this embodiment, the vehicle longitudinal controller relies solely on the total control process time T as the core parameter to achieve control. State constraints can be understood as the physical boundaries that the state variables of the vehicle's longitudinal motion must follow; these state variables include the vehicle's position s, velocity v, and acceleration a. Control constraints can be understood as the physical boundaries that the control variables for the vehicle's longitudinal control must follow; these control variables include jerk.

[0021] Figure 2 This is a flowchart illustrating the controller design of a vehicle longitudinal controller according to an embodiment of the present invention. Figure 2As shown, the design of the vehicle longitudinal controller is based on the principle of minima. It constructs a constrained optimal control problem around the longitudinal motion state of the vehicle and obtains a controller that depends only on the total time parameter T of the control process through step-by-step derivation.

[0022] Specifically, the longitudinal motion equation of the vehicle is first proposed. This equation is a mathematical description of the vehicle's longitudinal motion, expressed in the form of differential equations. It describes the mathematical relationship between state variables and input variables. Based on the state equation, the vehicle's state response under different inputs can be predicted. State variables x=(s,v,a) and control variables u=j are selected, where s is the vehicle position, v is the vehicle velocity, a is the vehicle acceleration, and j is the vehicle jerk. The state equation is then constructed based on this. In the formula, A is the system matrix, B is the input matrix, and the constraints of the state equations are also defined. This includes the starting state of the control process. End point state And state constraints (upper and lower bound constraints of state variables). And control constraints (upper and lower limits of control quantities). .

[0023] Then, a performance metric is constructed with the objective of minimizing vehicle jerk. The physical meaning of this performance index is the average jerk J during the vehicle control process, which is an integral form index based on the total control time T. Subsequently, the minimum principle is used to solve for the optimal state that satisfies both state and control constraints. The optimal state is the state value that minimizes the aforementioned jerk performance indicators. The optimal state form obtained by solving is: Where T is the parameter, t is the independent variable of the function, and the corresponding performance index can be expressed as: That is, the performance index is a single-variable function of parameter T, which can determine the functional relationship between the optimal state and T and t, but cannot directly obtain the specific value of T.

[0024] Finally, optimal control is calculated based on the optimal state. The relationship between optimal control and optimal state is given by the state equation. Description: Since the system matrix A and the input matrix B are known quantities, if the optimal state... Once determined, the optimal control quantity can be solved, and the optimal control can be obtained. As can be clearly seen from the optimal control formula, the implementation of this controller depends only on the total time T of the vehicle control process, which lays the foundation for the practical application and real-time parameter adjustment of the controller.

[0025] S102. Obtain the reference state and vehicle state of the target vehicle.

[0026] In this embodiment, the reference state can be understood as the state of reference points that need to be tracked during the longitudinal movement of the target vehicle. It includes at least one of reference time, reference position, reference speed, and reference acceleration. Generally, the reference point originates from the vehicle tracking trajectory, but a specific endpoint can also be directly specified. The trajectory refers to the route used to control the target vehicle's movement. If trajectory speed planning is performed for the trajectory, then reference time exists; otherwise, reference time does not exist. Trajectory speed planning refers to the trajectory's state planning, which includes not only the planned driving route but also the required time, speed, and acceleration to reach each point on the route. The vehicle state can be understood as the longitudinal motion state of the target vehicle itself, including at least one of vehicle time, vehicle position, vehicle speed, and vehicle acceleration. Vehicle time is the timestamp of the current control command (the moment the control command is applied to the target vehicle). Vehicle position, speed, and acceleration can be obtained through projection onto the trajectory's SL coordinate system or directly using the vehicle's own detected state data. The SL coordinate system is a coordinate system with the trajectory as a reference. The trajectory serves as the S-axis of the coordinate system, and at each position on the S-axis, the direction perpendicular to the trajectory is the L-axis.

[0027] Specifically, Figure 3 This is a schematic diagram of a vehicle projection in an SL coordinate system provided by an embodiment of the present invention, such as... Figure 3 As shown, an SL coordinate system is established for the trajectory. First, relevant information about the vehicle tracking trajectory is acquired. If the trajectory has completed speed planning, the trajectory point corresponding to the control command timestamp (e.g., 2 seconds later) is taken as a reference point, and its time, position, speed, and acceleration are the reference state. If the trajectory has not completed speed planning, the farthest forward trajectory point within the pre-aiming distance or a custom-specified endpoint (e.g., 2 meters in front of the target vehicle) is taken as a reference point. The reference position is obtained from this point, and the reference speed and acceleration are freely determined according to the actual driving scenario. Using the SL coordinate system established by the trajectory, the vehicle's center of mass is projected onto the S-axis of the trajectory, and the projected vehicle position, speed, and acceleration are calculated. Combined with the vehicle time corresponding to the current control command timestamp, the complete vehicle state is finally determined. Alternatively, the vehicle's own detected position, speed, and acceleration data can be directly collected and combined with the vehicle time to form the vehicle state.

[0028] S103. Determine the initial values ​​of the controller parameters for the target vehicle based on the reference state and the vehicle state.

[0029] In this embodiment, the initial value of the controller parameter can be understood as the initial value of the core parameter T of the vehicle longitudinal controller. This parameter T is the total time of the vehicle control process and is the only parameter implemented by the controller.

[0030] Specifically, the validity of the established reference state and vehicle state data is first verified to check for missing, abrupt, or abnormal data exceeding preset thresholds. If the data is invalid, the process of determining the vehicle longitudinal controller parameters is terminated directly. If the data is valid, it is determined whether this is the first time the controller parameters are initialized. If it is not the first time, the historical controller parameters from the previous moment are used as the initial values ​​for the current controller parameters. If it is the first time, it is determined whether the trajectory has completed speed planning based on whether the reference state contains a reference time. If it contains a reference time, it means that the trajectory has completed speed planning, and the difference between the reference time and the vehicle time in the vehicle state is used as the initial value for the controller parameters. If it does not contain a reference time, it means that the trajectory has not completed speed planning. The parameter estimate that minimizes the vehicle acceleration performance index is first solved. Then, the estimated value is used as the search starting point and its set multiple is used as the search interval endpoint. The minimum parameter value that satisfies the vehicle state constraints and control quantity constraints is searched within the interval and used as the initial value for the controller parameters.

[0031] S104. Update the initial values ​​of the controller parameters for the target vehicle to obtain the current controller parameters.

[0032] In this embodiment, the current controller parameters can be understood as the final parameters after compensation and optimization of the initial controller parameters during a single iteration of the controller's operation. These parameters serve as the basis for the actual control execution of the vehicle's longitudinal controller. The vehicle's longitudinal controller can operate in real time, acquiring new reference states and vehicle states, and then performing corresponding multi-round iterative calculations to obtain multiple current controller parameters. These current controller parameters can match the vehicle's dynamic position changes and comfort requirements in real time, exhibiting dynamic adaptability.

[0033] Specifically, for real-time position changes of the vehicle itself and the reference target, position change compensation calculations are performed to obtain the position change compensation amounts corresponding to the changes in vehicle position and reference position, correcting parameter deviations caused by dynamic position offsets. For vehicle ride comfort requirements, comfort compensation calculations are performed. By defining a vehicle comfort state range, the deviation amount of the vehicle state exceeding this range is calculated and the comfort compensation amount is obtained, so that the parameters are adapted to ride comfort needs. Finally, the initial values ​​of the controller parameters are accumulated with the above compensation amounts to update the initial values ​​of the controller parameters, obtaining the current controller parameters that fit the current actual state of the vehicle, the state of the reference target, and also take comfort into account.

[0034] The current controller parameters are output, and the controller calculates control commands based on the current controller parameters and drives the target vehicle to complete a parameter optimization closed loop at the current moment, controlling the longitudinal movement of the target vehicle.

[0035] This invention provides a vehicle longitudinal control method, comprising: constructing a vehicle longitudinal controller that satisfies state constraints and control quantity constraints; acquiring a reference state and a vehicle state of the target vehicle; determining initial values ​​of controller parameters for the target vehicle based on the reference state and the vehicle state; and updating the initial values ​​of the controller parameters to obtain the current controller parameters. This technical solution clearly defines the reference state and the actual state of the vehicle, providing accurate and effective data for parameter determination, and is compatible with multiple trajectory planning and state acquisition scenarios, improving versatility. It determines differentiated initial values ​​based on the two states, performs pre-constraint verification, and supports continuous parameter iteration, solving the problem of difficult traditional parameter debugging. Finally, it optimizes parameters through position change and comfort compensation, achieving real-time adaptive parameter adjustment, balancing trajectory tracking accuracy and ride comfort, simplifying control logic, making controller operation more stable, and comprehensively improving vehicle longitudinal control performance.

[0036] Figure 4 This is a control block diagram of a vehicle longitudinal control method provided in an embodiment of the present invention; Figure 5 This is a flowchart of another vehicle longitudinal control method provided in an embodiment of the present invention. As a first optional embodiment of this invention, such as... Figure 4 and Figure 5 As shown, the initial values ​​of the controller parameters for the target vehicle are determined based on the reference state and the vehicle state, including: S1031. Verify the validity of the reference state and vehicle state data. If the data is invalid, terminate the determination of the vehicle longitudinal controller parameters.

[0037] In this embodiment, the reference state and vehicle state of the target vehicle are first obtained. The reference time, reference position, reference speed, and reference acceleration in the reference state, and the vehicle time, vehicle position, vehicle speed, and vehicle acceleration in the vehicle state are validated to determine whether there are any null values, abrupt changes in value, or exceeding a preset threshold. If any abnormality is found, the parameter determination process is terminated directly, and the subsequent initial value calculation is not performed; if all data is valid, S1022 is executed.

[0038] S1032. If the data is valid, determine whether this is the first time the controller parameters are initialized. If not, use the historical controller parameters from the previous moment as the initial values ​​of the controller parameters. If so, determine whether the target vehicle has completed trajectory and speed planning based on the reference state, and determine the initial values ​​of the controller parameters based on the determination result.

[0039] In this embodiment, the historical controller parameters can be understood as the controller parameters calculated at the previous moment.

[0040] Specifically, first determine whether the controller parameter T needs to be initialized (i.e., whether it is the first control). If it is not the first control, no initialization is required, and the historical controller parameter Tprev from the previous cycle can be directly used as the initial value for this control. If it is the first control, initialization is required. Further determine whether there is a reference time in the reference state to distinguish whether the trajectory has completed speed planning, and further calculate the initial value of the controller parameter based on whether speed planning has been completed.

[0041] Furthermore, based on the reference state, it is determined whether the target vehicle has completed trajectory and velocity planning, and the initial values ​​of the controller parameters are determined based on the determination result, including: a1. If the reference state includes a reference time, it is determined that the target vehicle has completed trajectory and speed planning. The difference between the reference time and the vehicle time in the vehicle state is used as the initial value of the controller parameters.

[0042] In this embodiment, the reference time is the timestamp assigned to the reference point after trajectory speed planning, and the vehicle time is the timestamp of the current control cycle. The difference between the two is the initial value of the controller parameter T_init, which represents the expected control time for the vehicle from the current moment to the reference target point.

[0043] Specifically, when the reference state includes the reference time, the trajectory has been determined to have completed speed planning. The reference time and the vehicle time in the vehicle state are directly read. The difference between the two is calculated by T_init = reference time - vehicle time to obtain the initial value of the controller parameter T_init. This value is directly output as the initial value of the controller parameter without the need for additional optimization or constraint search.

[0044] b1. If the reference state does not include the reference time, it is determined that the target vehicle has not completed the trajectory speed planning. Calculate the parameter estimates that meet the acceleration performance index of the target vehicle, and determine the initial values ​​of the controller parameters based on the parameter estimates.

[0045] In this embodiment, the jerk performance index is an indicator of the smoothness of the vehicle's longitudinal motion, which is minimized in integral form. The parameter estimate T_est can be understood as a theoretical parameter obtained only from the perspective of optimal performance, without considering the vehicle's physical constraints.

[0046] Specifically, when there is no reference time for the reference state, the trajectory is determined before the speed planning is completed. First, the minimum value T_est is calculated using the minimum value principle. Then, based on this estimate, the constraint search is entered to obtain the initial values ​​of the controller parameters that meet the vehicle's physical constraints.

[0047] Furthermore, the estimated values ​​of parameters that satisfy the target vehicle's acceleration performance indicators are calculated, and the initial values ​​of the controller parameters are determined based on the estimated values, including: b11. Determine the parameter estimates that minimize the acceleration performance index of the target vehicle.

[0048] In this embodiment, the jerk performance index J is a single-variable function J=g(T) with respect to parameter T. By taking the derivative of J and setting the derivative to 0 (dJ / dT=0), the parameter estimate T_est that optimizes smoothness can be obtained. This value is derived only from the perspective of mathematical optimization and is not included in the constraints of state and control variables.

[0049] Specifically, based on the performance index formula from the controller design phase, this performance index is a function of parameter T. Substituting the state equation and control constraints, setting dJ / dT=0, differentiating J with respect to T, and solving for the extreme points, we obtain the parameter estimate T_est that minimizes the jerk. This value provides the initial starting point for subsequent constraint searches.

[0050] b12. Starting from the parameter estimate, the search interval begins and ends at a set multiple of the parameter estimate. Within the search interval, find the minimum parameter value that satisfies the vehicle state constraints and control quantity constraints, and use the minimum parameter value as the initial value of the controller parameters.

[0051] In this embodiment, the search interval can be understood as the interval starting from the parameter estimate T_est and ending at a set multiple (e.g., 3 times) of T_est. Vehicle state constraints can be understood as the physical limits of vehicle position s, vehicle velocity v, and vehicle acceleration s. The control constraint can be understood as the upper and lower limits of the jerk J. The minimum parameter value can be understood as the parameter T that satisfies all constraints and has the smallest value, which can ensure a more agile control response.

[0052] Specifically, the candidate parameters T are traversed within the interval [T_est, nT_est], and each candidate parameter is verified to ensure that the vehicle state satisfies the position / velocity / acceleration constraints. The control quantity satisfies the jerk constraint. After filtering out all compliant parameters, the smallest parameter T is taken as the initial value of the controller parameter T_init, so that T=T_init, which ensures both smoothness and compliance with the vehicle's physical limitations.

[0053] As a second optional embodiment of this example, Figure 4 and Figure 5 As shown, the initial values ​​of the controller parameters for the target vehicle are updated to obtain the current controller parameters, including: S1041. Perform position change compensation calculation on the initial values ​​of the controller parameters of the target vehicle to obtain the position change compensation amount.

[0054] In this embodiment, the position change compensation calculation is a targeted correction calculation of the initial values ​​of the controller parameters based on the dynamic position changes of the vehicle itself and the reference target. It includes compensation calculations for vehicle position changes and compensation calculations for reference position changes. The position change compensation amount is the total parameter correction value obtained from this calculation, including a first position change compensation amount corresponding to the vehicle position change and a second position change compensation amount corresponding to the reference position change.

[0055] Specifically, the vehicle position at the current moment and the previous moment are extracted from the collected vehicle status data, and the position difference between the two is calculated. Simultaneously, the vehicle speed at the current moment is acquired. The first position change compensation amount is obtained by calculating the position difference and the current vehicle speed. The reference position at the current moment and the previous moment are extracted from the reference status data, and the position difference between the two is calculated. The current reference speed is simultaneously acquired, and the second position change compensation amount is obtained by calculating the position difference and the current reference speed. The two compensation amounts are then summed to obtain the final position change compensation amount.

[0056] S1042. Perform comfort compensation calculations on the initial values ​​of the controller parameters of the target vehicle to obtain the comfort compensation amount.

[0057] In this embodiment, the comfort compensation calculation is a correction calculation of the initial value of the controller parameters based on the requirements of driving comfort. The comfort compensation amount is the comfort-related parameter correction value obtained by the calculation, which is used to constrain the vehicle state within the comfort range and avoid sudden acceleration / deceleration.

[0058] Specifically, first, the permissible state range of the vehicle is determined based on its own mechanical performance and driving safety standards; then, based on this permissible state range, a comfort state range that meets the requirements for driving and riding comfort is defined. The current vehicle state is then checked to see if it exceeds this comfort state range. For vehicle states that exceed the range, the corresponding deviation is calculated. Finally, based on this deviation, a comfort compensation calculation is performed to obtain a comfort compensation amount suitable for the current vehicle state.

[0059] S1043. The initial values ​​of the controller parameters, the position change compensation amount, and the comfort compensation amount are accumulated to obtain the current controller parameters.

[0060] In this embodiment, the initial value of the controller parameter T (T_init), the position change compensation amount (first position change compensation amount ΔT1 + second position change compensation amount ΔT2) and the comfort compensation amount ΔT3 are accumulated to obtain the final parameter T_final as the current controller parameter.

[0061] Furthermore, position change compensation calculations are performed on the initial values ​​of the controller parameters of the target vehicle to obtain the position change compensation amount, including: a2. Determine the difference between the current vehicle position and the previous vehicle position, as well as the current vehicle speed, to obtain the first position change compensation amount corresponding to the vehicle position change.

[0062] In this embodiment, the first position change compensation amount can be understood as a parameter correction term for the change in the vehicle's own position. It is determined by the difference between the vehicle's position at the current moment and the previous moment, and the current vehicle speed. It is used to compensate for the parameter deviation caused by the actual position of the vehicle deviating from the expected trajectory, so that the controller parameters are more in line with the real-time driving position of the vehicle.

[0063] Specifically, the vehicle position at the current moment and the vehicle position at the previous moment are extracted from the vehicle state output by the target vehicle (controlled vehicle), and the difference between the two is calculated; at the same time, the vehicle speed at the current moment is obtained, the position difference is divided by the vehicle speed, and the first position change compensation amount ΔT1 is obtained by (current vehicle position - previous vehicle position) / current vehicle speed.

[0064] b2. Determine the difference between the reference position of the target vehicle at the current moment and the reference position at the previous moment, as well as the reference speed at the current moment, to obtain the second position change compensation amount corresponding to the change in reference position.

[0065] S1032. Determine the difference between the reference position of the target vehicle at the current moment and the reference position at the previous moment, as well as the reference speed at the current moment, to obtain the second position change compensation amount corresponding to the change in reference position.

[0066] In this embodiment, the second position change compensation amount can be understood as a parameter correction term for the change of the reference target position. It is determined by the difference between the reference position at the current time and the previous time and the current reference velocity. It is used to compensate for the parameter deviation caused by the update of the reference target position and ensure that the controller can follow the dynamic adjustment of the target position.

[0067] Specifically, the reference positions at the current time and the previous time are extracted from the reference state input by the system, and the difference between the two is calculated; at the same time, the reference velocity at the current time is obtained, the position difference is divided by the reference velocity, and the second position change compensation amount ΔT2 is obtained by (current reference position - previous reference position) / current reference velocity.

[0068] Furthermore, comfort compensation calculations are performed on the initial values ​​of the target vehicle's controller parameters to obtain the comfort compensation amount, including: a3. Determine the permissible state range of the target vehicle.

[0069] In this embodiment, the permissible state range can be understood as the physical limit range of state quantities such as vehicle position, velocity, acceleration, and jerk, determined by the vehicle's mechanical performance and driving safety boundaries. For example, the limit range for acceleration is [-3m / s²]. 2 3m / s 2 ].

[0070] Specifically, by combining the hardware performance of vehicle longitudinal control with driving safety standards, the performance parameters of the target vehicle's power, braking, chassis and other systems are extracted, and the upper and lower limits of position, speed, acceleration and jerk are determined respectively. The upper and lower limits of each state variable constitute the allowable state range of the corresponding state, forming a full-dimensional vehicle state safety constraint boundary.

[0071] b3. The set ratio of the permissible state range is determined as the comfort state range of the target vehicle.

[0072] In this embodiment, the comfort range can be understood as a milder range after the permissible range has been reduced by a set proportion (e.g., 80%), representing the boundary of a comfortable driving experience. For example, the comfort range for acceleration is [-2.4 m / s²]. 2 2.4m / s 2 The set ratio can be determined according to the comfort requirements of different application scenarios, and this embodiment does not set any limit on it.

[0073] Specifically, for the defined permissible state ranges of each state quantity, the upper and lower limit values ​​of the range are reduced proportionally according to a uniform preset ratio. The central reference of the range is not changed, but only the fluctuation range of the state quantity is reduced. The upper and lower limit values ​​of each state quantity after reduction are determined as the comfort state range of the corresponding state, forming the comfort constraint boundaries of each dimension.

[0074] c3. Determine the comfort compensation amount for the target vehicle based on the deviation of the target vehicle's condition from the comfort range.

[0075] In this embodiment, the historical controller parameters Tprev from the previous moment are substituted into the state trajectory equation. This yields the predicted change curves of vehicle position, speed, acceleration, and jerk within the current control cycle. By iterating through each time point of the state trajectory curve, the actual state values ​​are compared with the comfort zone boundaries, and the deviation of each state quantity is calculated. For example, if the current acceleration is 2.7 m / s², the deviation is calculated. 2 Exceeding the upper limit of comfort by 2.4 m / s 2 The deviation is 0.3 m / s 2Assign preset weights to the excess amounts of different state quantities (e.g., jerk has the highest weight and position has the lowest weight; the allocation ratio of preset weights can also be determined based on actual needs), calculate the product of the weight of each state and the deviation amount, and sum the product results corresponding to each state to obtain the final comfort compensation amount ΔT3.

[0076] As a third optional embodiment of this example, Figure 4 and Figure 5 As shown, it also includes: S104. Update the current controller parameters to the vehicle longitudinal controller; calculate the control command sequence based on the updated current controller parameters; output the first control command in the control command sequence to the vehicle actuator to control the longitudinal movement of the target vehicle.

[0077] In this embodiment, the control command sequence can be understood as, based on the current controller parameter Tfinal and the vehicle state deviation, following optimal control (such as...). ) and optimal state ( The calculated sequence of state and control variables over a future time period. Vehicle actuators can be understood as the vehicle's power system (throttle / electric switch) and braking system, responsible for receiving control commands and executing corresponding acceleration and deceleration actions.

[0078] Specifically, the calculated final parameter Tfinal is input into the controller parameter adjustment module to complete the real-time update of the internal parameters of the vehicle longitudinal controller, ensuring that the controller's calculations are based on the latest optimization results. The controller receives the updated Tfinal and, through optimal control (such as...),... ) and optimal state ( ), and state equations The system calculates a sequence of control commands for multiple future moments. The first control command (the optimal control value for the current cycle) is selected from this sequence and output to the vehicle's throttle / brake actuator. The actuator adjusts its output torque or braking force according to this command, directly controlling the longitudinal movement of the target vehicle, causing the vehicle's actual state to quickly converge to the reference state, thus completing a closed loop of one control cycle.

[0079] In one embodiment, Figure 6 This is a structural schematic diagram of a vehicle longitudinal control device provided in an embodiment of the present invention. Figure 6 As shown, the device includes: Controller construction module 21 is used to construct a vehicle longitudinal controller, which satisfies state constraints and control quantity constraints; The status data acquisition module 22 is used to acquire the reference status and vehicle status of the target vehicle; The parameter initial value determination module 23 is used to determine the initial values ​​of the controller parameters of the target vehicle based on the reference state and the vehicle state. The parameter initial value update module 24 is used to update the initial values ​​of the controller parameters of the target vehicle to obtain the current controller parameters.

[0080] The vehicle longitudinal control device used in this technical solution effectively reduces the difficulty of parameter debugging, adapts to various application scenarios, and takes into account vehicle state constraints and driving comfort, thereby improving the controller's scenario adaptability and control smoothness.

[0081] Optionally, the parameter initial value update module 24 includes: The position compensation calculation unit is used to perform position change compensation calculation on the initial values ​​of the controller parameters of the target vehicle to obtain the position change compensation amount; The comfort compensation calculation unit is used to perform comfort compensation calculation on the initial values ​​of the controller parameters of the target vehicle to obtain the comfort compensation amount. The parameter initial value update unit is used to accumulate the initial value of the controller parameters, the position change compensation amount, and the comfort compensation amount to obtain the current controller parameters.

[0082] Optionally, the vehicle state includes at least one of vehicle time, vehicle position, vehicle speed, and vehicle acceleration, and the reference state includes at least one of reference time, reference position, reference speed, and reference acceleration. The position compensation calculation unit is specifically used for: Determine the difference between the current vehicle position and the previous vehicle position of the target vehicle, as well as the vehicle speed at the current moment, to obtain the first position change compensation amount corresponding to the change in vehicle position. The difference between the reference position of the target vehicle at the current moment and the reference position at the previous moment, as well as the reference speed at the current moment, are determined to obtain the second position change compensation amount corresponding to the change in reference position.

[0083] Optionally, the comfort compensation calculation unit is specifically used for: Determine the permissible state range of the target vehicle; The set ratio of the permissible state range is determined as the comfort state range of the target vehicle; The comfort compensation amount of the target vehicle is determined based on the deviation of the target vehicle's state from the comfort state range.

[0084] Optionally, the parameter initial value determination module 22 includes: The data verification submodule is used to verify the validity of the reference state and vehicle state data. If the data is invalid, the determination of the vehicle longitudinal controller parameters is terminated. The initialization judgment submodule is used to determine whether the controller parameter initialization is the first time if the data is valid. If not, the historical controller parameters from the previous moment are used as the initial values ​​of the controller parameters. The speed planning judgment submodule is used to determine whether the target vehicle has completed trajectory speed planning based on the reference state if the condition is met, and to determine the initial values ​​of the controller parameters based on the judgment result.

[0085] Optionally, the speed planning and judgment submodule includes: The first initial value determination unit is used to determine that the target vehicle has completed trajectory speed planning if the reference state contains a reference time, and to use the difference between the reference time and the vehicle time in the vehicle state as the initial value of the controller parameter. The second initial value determination unit is used to determine that the target vehicle has not completed trajectory speed planning if the reference state does not include reference time, calculate the parameter estimate value that meets the acceleration performance index of the target vehicle, and determine the initial value of the controller parameter based on the parameter estimate value.

[0086] Optionally, the second initial value determination unit is specifically used for: Determine the parameter estimates that minimize the acceleration performance index of the target vehicle; Using the estimated parameter value as the starting point of the search interval and a set multiple of the estimated parameter value as the ending point of the search interval, the minimum parameter value that satisfies the vehicle state constraints and control quantity constraints is found within the search interval, and the minimum parameter value is used as the initial value of the controller parameters.

[0087] Optionally, the device further includes a control module, specifically used for: Update the current controller parameters to the vehicle longitudinal controller; Calculate the control command sequence based on the updated current controller parameters; The first control command in the control command sequence is output to the vehicle actuator to control the longitudinal movement of the target vehicle.

[0088] The vehicle longitudinal control device provided in the embodiments of the present invention can execute the vehicle longitudinal control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0089] In one embodiment, Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. For example... Figure 7The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0090] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0091] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0092] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as vehicle longitudinal control methods.

[0093] In some embodiments, the vehicle longitudinal control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vehicle longitudinal control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the vehicle longitudinal control method by any other suitable means (e.g., by means of firmware).

[0094] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0095] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0096] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0097] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0098] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0099] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0100] This invention also provides a computer program product, including a computer program that, when executed by a processor, can implement the vehicle longitudinal control method provided in any embodiment of this application.

[0101] In the implementation of the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0102] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0103] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle longitudinal control method, characterized in that, include: Construct a vehicle longitudinal controller that satisfies state constraints and control quantity constraints; Obtain the reference status and vehicle status of the target vehicle; The initial values ​​of the controller parameters of the target vehicle are determined based on the reference state and the vehicle state. The initial values ​​of the controller parameters for the target vehicle are updated to obtain the current controller parameters.

2. The method according to claim 1, characterized in that, The step of updating the initial values ​​of the controller parameters of the target vehicle to obtain the current controller parameters includes: The initial values ​​of the controller parameters of the target vehicle are used to calculate the position change compensation, and the position change compensation amount is obtained. The initial values ​​of the controller parameters of the target vehicle are used to calculate the comfort compensation amount. The current controller parameters are obtained by summing the initial values ​​of the controller parameters, the position change compensation amount, and the comfort compensation amount.

3. The method according to claim 2, characterized in that, The vehicle state includes at least one of vehicle time, vehicle position, vehicle speed, and vehicle acceleration; the reference state includes at least one of reference time, reference position, reference speed, and reference acceleration. The step of calculating the position change compensation amount by performing position change compensation on the initial values ​​of the controller parameters of the target vehicle includes: Determine the difference between the current vehicle position and the previous vehicle position of the target vehicle, as well as the vehicle speed at the current moment, to obtain the first position change compensation amount corresponding to the change in vehicle position. The difference between the reference position of the target vehicle at the current moment and the reference position at the previous moment, as well as the reference speed at the current moment, are determined to obtain the second position change compensation amount corresponding to the change in reference position.

4. The method according to claim 2, characterized in that, The process of calculating comfort compensation for the initial values ​​of the controller parameters of the target vehicle to obtain the comfort compensation amount includes: Determine the permissible state range of the target vehicle; The set ratio of the permissible state range is determined as the comfort state range of the target vehicle; The comfort compensation amount of the target vehicle is determined based on the deviation of the target vehicle's state from the comfort state range.

5. The method according to claim 1, characterized in that, The step of determining the initial values ​​of the controller parameters for the target vehicle based on the reference state and the vehicle state includes: Verify the validity of the reference state and vehicle state data. If the data is invalid, terminate the determination of vehicle longitudinal controller parameters. If the data is valid, determine whether this is the first time the controller parameters are initialized. If not, use the historical controller parameters from the previous moment as the initial values ​​of the controller parameters. If so, determine whether the target vehicle has completed trajectory and speed planning based on the reference state, and determine the initial values ​​of the controller parameters based on the determination result.

6. The method according to claim 5, characterized in that, The step of determining whether the target vehicle has completed trajectory and speed planning based on the reference state, and determining the initial values ​​of the controller parameters based on the determination result, includes: If the reference state includes a reference time, it is determined that the target vehicle has completed trajectory and speed planning, and the difference between the reference time and the vehicle time in the vehicle state is used as the initial value of the controller parameter. If the reference state does not include a reference time, it is determined that the target vehicle has not completed trajectory speed planning. The estimated values ​​of the parameters that meet the acceleration performance index of the target vehicle are calculated, and the initial values ​​of the controller parameters are determined based on the estimated values ​​of the parameters.

7. The method according to claim 6, characterized in that, The calculation of parameter estimates that satisfy the target vehicle's acceleration performance index, and the determination of initial controller parameter values ​​based on the parameter estimates, includes: Determine the parameter estimates that minimize the acceleration performance index of the target vehicle; Using the estimated parameter value as the starting point of the search interval and a set multiple of the estimated parameter value as the ending point of the search interval, the minimum parameter value that satisfies the vehicle state constraints and control quantity constraints is found within the search interval, and the minimum parameter value is used as the initial value of the controller parameters.

8. The method according to claim 1, characterized in that, Also includes: Update the current controller parameters to the vehicle longitudinal controller; Calculate the control command sequence based on the updated current controller parameters; The first control command in the control command sequence is output to the vehicle actuator to control the longitudinal movement of the target vehicle.

9. A vehicle longitudinal control device, characterized in that, include: A controller construction module is used to construct a vehicle longitudinal controller, which satisfies state constraints and control quantity constraints. The status data acquisition module is used to acquire the reference status and vehicle status of the target vehicle; The parameter initial value determination module is used to determine the initial values ​​of the controller parameters of the target vehicle based on the reference state and the vehicle state. The parameter initial value update module is used to update the initial values ​​of the controller parameters of the target vehicle to obtain the current controller parameters.

10. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a vehicle longitudinal control method according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement a vehicle longitudinal control method according to any one of claims 1-8.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements a vehicle longitudinal control method according to any one of claims 1-8.

Images