A narrow parking space adaptive parking control method

Abstract

The application provides a narrow parking space adaptive parking control method, comprising: constructing a dynamic equation based on vehicle driving state variables and vehicle driving control variables; constructing a cost function based on reference data of a reference trajectory, vehicle driving state variables at a current time, the dynamic equation, a Q matrix, vehicle driving control variables and an R matrix; determining whether to adjust the Q matrix based on a relationship between a first remaining driving distance of the vehicle at the current time and a first distance threshold; solving the cost function based on boundary constraint conditions between the vehicle driving state variables and the reference data of the reference trajectory and boundary constraint conditions of the vehicle driving control variables to obtain vehicle driving control variables at the current time; obtaining reference control variables based on the reference data of the reference trajectory and a current position of the vehicle at the current time; and obtaining target control variables based on the vehicle driving control variables at the current time and the reference control variables. The method can improve the parking success rate in the extreme narrow parking space scenario.

Description

Technical Field

[0001] This manual relates to the field of intelligent parking, and in particular to an adaptive parking control method for narrow parking spaces. Background Technology

[0002] With the number of motor vehicles in cities increasing year by year, the contradiction between the supply and demand of parking resources in urban core areas is becoming increasingly prominent. In order to improve the utilization rate of parking lot space and increase the number of parking spaces, various types of parking lots generally adopt narrow parking space designs at present. Extremely narrow parking spaces with a width margin of ≤20cm have become the norm in urban parking scenarios. The available adjustment space for parking in such extremely narrow parking spaces is extremely compressed, which puts forward extremely high requirements on the accuracy of vehicle posture control and the flexibility of trajectory adjustment during the parking process.

[0003] Currently, the traditional control schemes used in existing automatic parking systems employ fixed control logic and preset, fixed control parameters, lacking dynamic adaptive adjustment capabilities and unable to adapt to complex parking conditions in extremely narrow spaces. Limited by this fixed control logic, existing automatic parking technology suffers from core flaws such as poor trajectory flexibility and low precision in controlling lateral distance between the vehicle and the parking space, only suitable for regular, spacious parking spaces with ample room. When facing extremely narrow parking spaces, the system cannot accurately control the vehicle's trajectory and posture, easily leading to safety issues such as scraping against the parking space edge or colliding with adjacent parked vehicles. This significantly reduces parking safety and standardization, resulting in an extremely low success rate for automatic parking in extremely narrow spaces, severely impacting the user parking experience and failing to meet the current demand for intelligent parking in commonly used narrow spaces. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this specification provides an adaptive parking control method for narrow parking spaces.

[0005] According to a first aspect of the embodiments of this specification, a narrow parking space adaptive parking control method is provided, the method comprising: Dynamic equations are constructed based on vehicle driving state variables and vehicle driving control variables; A cost function is constructed based on the reference data of the reference trajectory, the vehicle driving state variables at the current moment, the dynamic equation, the Q matrix, the vehicle driving control variables, and the R matrix; where the Q matrix represents the weights of the state variables and the R matrix represents the weights of the control variables. Based on the relationship between the vehicle's first remaining driving distance and the first distance threshold at the current moment, determine whether to adjust the Q matrix; Based on the boundary constraints between the vehicle driving state quantity and the reference data of the reference trajectory, and the boundary constraints of the vehicle driving control quantity, the cost function is solved to obtain the vehicle driving control quantity at the current moment. Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained; The target control quantity is obtained based on the vehicle driving control quantity at the current moment and the reference control quantity.

[0006] In one possible implementation, the cost function constructed based on the reference trajectory, the current vehicle driving state variables, the dynamic equations, the Q matrix, the vehicle driving control variables, and the R matrix includes: Based on the current vehicle driving state quantity and the dynamic equation, the future vehicle driving state quantity is obtained; The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the first aiming distance, a first aiming point is determined on the reference trajectory; Based on the first reference velocity and preset control cycle of the first aiming point, multiple future reference points are determined on the reference trajectory; Based on the current vehicle driving state quantity, the future vehicle driving state quantity, the reference data of the first aiming point, and the reference data of the future reference point, the state quantity difference is obtained; A cost function is constructed based on the state variable difference, Q matrix, vehicle driving control quantity, and R matrix.

[0007] In one possible implementation, the reference control quantity includes a reference steering wheel angle; the reference control quantity is obtained based on reference data of the reference trajectory and the current position of the vehicle at the current moment, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the second aiming distance, a second aiming point is determined on the reference trajectory; Based on the pre-stored curvature of the reference trajectory, the reference curvature of the second aiming point is determined; The front wheel feed angle is determined based on the reference curvature and feed forward gain of the second aiming point; Based on the front wheel feed angle, the reference steering wheel angle is determined.

[0008] In one possible implementation, the method further includes: determining the relationship between the vehicle's first remaining driving distance and a second distance threshold at the current moment, and reducing the feedforward gain when the vehicle's first remaining driving distance at the current moment is less than the second distance threshold.

[0009] In one possible implementation, the reference data for the second aiming point includes a reference heading angle, and the vehicle driving state quantity at the current moment includes the heading angle at the current moment; the state quantity difference includes the heading angle error; The method further includes: when the vehicle's first remaining driving distance is less than a third distance threshold at the current moment, and the heading angle error is contrary to the direction of the reference steering wheel angle, setting the reference steering wheel angle to 0; or When the vehicle's first remaining driving distance is less than the third distance threshold and the heading angle error is less than the angle threshold at the current moment, the reference steering wheel angle is set to 0.

[0010] In one possible implementation, the reference control quantity includes a reference acceleration; based on reference data of the reference trajectory and the current position of the vehicle at the current moment, the reference control quantity is obtained, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the third aiming distance, a third aiming point is determined on the reference trajectory; Based on the pre-stored acceleration of the reference trajectory and the position of the third aiming point, the reference acceleration of the third aiming point is determined.

[0011] In one possible implementation, the target control quantity includes a target acceleration, and the method further includes: when the first remaining driving distance of the vehicle at the current moment is less than a fourth distance threshold, determining a first compensation acceleration based on the vehicle's speed at the current moment and the first remaining driving distance of the vehicle at the current moment; Based on the target acceleration and the first compensated acceleration, the compensated acceleration is obtained.

[0012] In one possible implementation, the target control quantity includes the target acceleration, and the method further includes: when the first remaining driving distance of the vehicle at the current moment is less than the fifth distance threshold, setting a virtual target point in front of the vehicle's position at the current moment; The second compensation acceleration is determined based on the vehicle's current speed and the second remaining travel distance at the virtual target point; Based on the target acceleration and the second compensated acceleration, the compensated acceleration is obtained.

[0013] In one possible implementation, the target control quantity includes a target acceleration, and the method further includes: determining a third compensation acceleration based on the vehicle's pitch angle; Based on the target acceleration and the third compensation acceleration, the compensated acceleration is obtained.

[0014] In one possible implementation, the method further includes: When the distance from the obstacle to the vehicle is greater than the preset safe distance, the TTC time is calculated based on the vehicle's current speed and acceleration. When the TTC time is greater than the time threshold, determine whether the distance from the obstacle to the vehicle is less than the sixth distance threshold; If the distance from the obstacle to the vehicle is less than the sixth distance threshold, the speed of the first aiming point is replaced with a preset speed value.

[0015] The technical solutions provided in the embodiments of this specification may include the following beneficial effects: In this application, by constructing vehicle dynamics equations, the dynamic relationship between vehicle driving state and control during parking is accurately characterized, overcoming the shortcomings of traditional fixed trajectory models that do not consider the dynamic driving characteristics of vehicles, and improving the fit and accuracy of parking trajectory modeling.

[0016] This solution constructs a cost function by combining a reference trajectory, real-time vehicle status, and weighted Q and R matrices. Through differentiated configuration of state weights and control weights, and by dynamically adjusting the state weight Q matrix based on the remaining driving distance, it can adapt the control focus in real-time according to the parking process. It ensures trajectory tracking efficiency in the early stages of parking and improves pose correction accuracy in the later stages, effectively adapting to the characteristics of extremely narrow parking spaces with minimal adjustment margins. This solves the problem of traditional control logic having fixed control parameters and lacking dynamic adaptive adjustment capabilities.

[0017] By combining the boundary constraints between the reference trajectory and the real-time vehicle status, and solving the cost function for the boundary constraints of the vehicle control quantity, real-time and dynamic parking trajectory correction and adaptive adjustment of control parameters can be performed based on the real-time driving status of the vehicle and the deviation from the reference trajectory. This can output the optimal real-time control quantity under the strict space constraints of narrow parking spaces, avoid control overshoot and parking trajectory deviation, significantly improve the control accuracy of the vehicle's lateral distance, and fundamentally eliminate the problem of the vehicle body rubbing against the edge of the parking space and scratching adjacent vehicles.

[0018] Finally, the target control quantity is obtained by fusing the real-time solution of the control quantity and the reference control quantity corresponding to the trajectory. This enables the parking trajectory to be flexibly and adaptively adjusted while following the reference trajectory, breaking through the limitation of traditional automatic parking that is only suitable for regular parking spaces. It significantly improves the parking success rate and parking safety in extremely narrow parking space scenarios.

[0019] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this specification. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this specification and, together with the description, serve to explain the principles of this specification.

[0021] Figure 1 This is a flowchart illustrating an adaptive parking control method for narrow parking spaces according to an exemplary embodiment. Detailed Implementation

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this specification as detailed in the appended claims.

[0023] The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of this specification. The singular forms “a,” “the,” and “the” as used in this specification and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0024] It should be understood that although the terms first, second, third, etc., may be used in this specification to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this specification, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0025] The embodiments described in this specification will now be described in detail.

[0026] like Figure 1 As shown, Figure 1 This is a flowchart illustrating an adaptive parking control method for narrow parking spaces according to an exemplary embodiment, comprising the following steps: S101: Construct dynamic equations based on vehicle driving state variables and vehicle driving control variables.

[0027] In one embodiment, vehicle driving state parameters may include: real-time vehicle position coordinates, vehicle heading angle, vehicle longitudinal velocity, and vehicle yaw rate. These vehicle driving state parameters can be obtained from vehicle-mounted sensors or obtained by processing data output from vehicle-mounted sensors using existing methods.

[0028] In one embodiment, the vehicle driving control quantities include: steering wheel angle and acceleration. These two are the variables to be solved.

[0029] In one embodiment, the dynamic equation is: ,in, =0,1,...,N 1. N represents the prediction time domain length. N can be calibrated based on real-time vehicle speed and trajectory curvature, and is an engineering empirical value. When the vehicle's first remaining travel distance at the current moment is less than the seventh distance threshold, N is automatically reduced to improve the sensitivity of error correction when approaching narrow parking spaces.

[0030] In one embodiment, Indicates the first Vehicle driving status data at any given time. This indicates the vehicle's current driving status. Indicates the first Vehicle driving control quantity at any given time.

[0031] In one embodiment, matrix: Where m is the total mass of the vehicle. For the front axle tire lateral stiffness, For the rear axle tire lateral stiffness, The longitudinal distance from the vehicle's center of gravity to the front axle. The longitudinal distance from the vehicle's center of gravity to the rear axle. Vx represents the vehicle's yaw moment of inertia about the Z-axis. Vx represents the vehicle's longitudinal velocity.

[0032] matrix: matrix: Among them, the reference yaw rate , For reference curvature, For reference heading angle.

[0033] S102: Construct a cost function based on the reference data of the reference trajectory, the vehicle driving state variables at the current moment, the dynamic equation, the Q matrix, the vehicle driving control variables, and the R matrix; where the Q matrix represents the weights of the state variables and the R matrix represents the weights of the control variables.

[0034] In one embodiment, the reference data for the reference trajectory includes: reference point position coordinates, reference heading angle, cumulative mileage along the trajectory at the reference point, reference speed, reference curvature, and reference acceleration. These reference data are calculated by the upper-level planning and control module based on existing methods and bound to each reference point on the reference trajectory. After identifying a narrow parking space, the upper-level planning and control module triggers the execution of the narrow parking space adaptive parking control method described in this application. That is, upon receiving a signal from the upper-level planning and control module, it begins executing the narrow parking space adaptive parking control method of this application, and can directly obtain the reference data of the reference trajectory from the upper-level planning and control module. The signal from the upper-level planning and control module indicates that the parking space is a narrow parking space.

[0035] In one embodiment, the construction of the cost function based on the reference trajectory reference data, the vehicle driving state quantity at the current moment, the dynamic equation, the Q matrix, the vehicle driving control quantity, and the R matrix includes: Based on the current vehicle driving state quantity and the dynamic equation, the future vehicle driving state quantity is obtained; The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the first aiming distance, a first aiming point is determined on the reference trajectory; Based on the first reference velocity and preset control cycle of the first aiming point, multiple future reference points are determined on the reference trajectory; Based on the current vehicle driving state quantity, the future vehicle driving state quantity, the reference data of the first aiming point, and the reference data of the future reference point, the state quantity difference is obtained; A cost function is constructed based on the state variable difference, Q matrix, vehicle driving control quantity, and R matrix.

[0036] In one embodiment, the vehicle's driving state at the current moment ( Given that ), based on the dynamic equations By analogy, the vehicle's driving status at future moments can be obtained. , ...... (k=N-1)), for example, including the vehicle driving state quantity at the first future time, the vehicle driving state quantity at the second future time, ..., the vehicle driving state quantity at the kth future time. The obtained future time vehicle driving state quantities are all expressions that include vehicle driving control quantities.

[0037] In one embodiment, the point with the smallest distance is found by calculating the distance between the vehicle's current position and each point on the reference trajectory at the current moment, which is the matching point.

[0038] In one embodiment, the first aiming distance can be obtained based on the vehicle's current speed and the first base aiming distance. ,in, This is the first aiming distance. This is the first basic aiming distance. It is the first coefficient. and These are values ​​that can be calibrated based on engineering experience.

[0039] In one embodiment, based on the current vehicle's gear information, a first aiming point is determined on the reference trajectory ahead of the driving direction, based on the matching point and the first aiming distance.

[0040] In one embodiment, the first reference velocity of the first pre-aiming point can be obtained by interpolation based on reference data bound to each reference point on the reference trajectory. The preset control period refers to the sampling interval time, i.e., the time between two adjacent moments. Based on the first reference velocity of the first pre-aiming point and the preset control period, a first future reference point can be determined. Similarly, by interpolating the reference velocity of the first future reference point, a second future reference point can be determined based on the reference velocity of the first future reference point and the preset control period, and so on, until the k-th future reference point is determined.

[0041] In one embodiment, the vehicle's driving state at the current moment ( This includes: vehicle real-time position coordinates, vehicle heading angle, vehicle longitudinal velocity, and vehicle yaw rate.

[0042] The vehicle's driving status at future moments includes: the vehicle's driving status at the first future moment, the vehicle's driving status at the second future moment, ..., the vehicle's driving status at the kth future moment. Each of these future moments also includes: the vehicle's real-time position coordinates, the vehicle's heading angle, the vehicle's longitudinal velocity, and the vehicle's yaw rate.

[0043] Reference data for the first aiming point ( The reference points include: reference point position coordinates, reference heading angle, cumulative mileage along the trajectory, reference speed, reference curvature, and reference acceleration.

[0044] The reference data for future reference points includes: reference data for the first future reference point, reference data for the second future reference point, ..., reference data for the kth future reference point. The reference data for each future reference point also includes: reference point position coordinates, reference heading angle, cumulative mileage along the trajectory, reference velocity, reference curvature, and reference acceleration.

[0045] It can be based on the vehicle's current driving status ( ) and reference data for the first aiming point ( The current state quantity difference is obtained; the first state quantity difference is obtained based on the vehicle driving state quantity at the first future time and the reference data of the first future reference point, ... the k-th state quantity difference is obtained based on the vehicle driving state quantity at the k-th future time and the reference data of the k-th future reference point. That is, the state quantity difference includes: the current state quantity difference, the first state quantity difference, ... the k-th state quantity difference.

[0046] In one embodiment, the state quantity difference includes: lateral position error. Horizontal error change rate Heading angle error Rate of change of heading error Longitudinal residual distance error Speed ​​error .

[0047] In one embodiment, lateral position error It can be obtained based on the difference between the vehicle's real-time position coordinates and the corresponding reference point's position coordinates. For example, it can be obtained based on the vehicle's current position coordinates and the reference position coordinates of the first aiming point.

[0048] In one embodiment, the rate of change of lateral error Based on lateral position error Differentiating yields the result.

[0049] In one embodiment, heading angle error It can be obtained based on the difference between the vehicle's heading angle and the corresponding reference heading angle. For example, it can be obtained based on the vehicle's heading angle at the current moment and the reference heading angle of the first aiming point.

[0050] In one embodiment, the rate of change of heading error Based on heading angle error Differentiating yields the result.

[0051] In one embodiment, longitudinal residual distance error : Based on the vehicle's current driving status ( ) and reference data for the first aiming point ( Let's take the difference in the current state variables as an example to illustrate.

[0052] Projecting the vehicle's current position onto the reference trajectory, and using the position of the projected point and the cumulative mileage along the trajectory of the reference points adjacent to the projected point, we can obtain the cumulative mileage along the trajectory of the projected point. Subtracting the cumulative mileage along the trajectory of the projected point from the total mileage of the reference trajectory gives us the vehicle's first remaining distance at the current moment. Subtracting the cumulative mileage along the trajectory of the first preview point from the total mileage of the reference trajectory gives us the remaining distance at the first preview point. The difference between the vehicle's first remaining distance and the remaining distance at the first preview point is the longitudinal remaining distance error. .

[0053] In one embodiment, speed error It can be obtained based on the difference between the vehicle's longitudinal velocity and the corresponding reference velocity. For example, it can be obtained based on the vehicle's longitudinal velocity at the current moment and the reference velocity at the first aiming point.

[0054] In one embodiment, the cost function is: Represents the cost function; This indicates the vehicle's driving status. This indicates the vehicle's current driving status. This represents the vehicle's driving status at the first future moment; Reference data representing the reference trajectory; This represents the reference data for the first aiming point. Reference data representing the first future reference point; Indicates vehicle driving control parameters; This indicates the vehicle's driving control quantity at the current moment.

[0055] Terminal Item ,in For: Terminal status, This is the cost to the end user.

[0056] The Q matrix represents the weights of the state variables. The six diagonal elements of the Q matrix correspond to the differences between the six state variables (lateral position errors). Horizontal error change rate Heading angle error Rate of change of heading error Longitudinal residual distance error Speed ​​error The penalty coefficient.

[0057] The R matrix represents the weights of the control variables. The two diagonal elements of the R matrix correspond to the penalty coefficients of the two control variables (steering wheel angle and acceleration), respectively.

[0058] By determining the first aiming point, this application can obtain reference data of the vehicle's forward trajectory in advance. Based on this forward reference data, the vehicle can turn, accelerate, and decelerate in advance, thereby eliminating control lag and avoiding wheel difference scrapes when turning in narrow parking spaces.

[0059] S103: Based on the relationship between the vehicle's first remaining driving distance and the first distance threshold at the current moment, determine whether to adjust the Q matrix.

[0060] In one embodiment, the upper-level planning and control module simultaneously sets trajectory segmentation markers on the reference trajectory. It can determine whether the vehicle has entered the final trajectory segment by obtaining the trajectory segmentation markers and the vehicle's current position. If the vehicle has entered the final trajectory segment and its remaining distance is less than a first distance threshold, the vehicle is entering the final parking phase and needs to adjust Q. For example, this adjustment might involve correcting the lateral position error in Q. and heading angle error The value corresponding to the coefficient. The first distance threshold can be calibrated based on engineering experience.

[0061] This application strengthens the penalty for tracking accuracy by adjusting Q at the end of parking, ensuring that the vehicle does not deviate from the target pose when approaching the endpoint.

[0062] S104: Based on the boundary constraints between the vehicle driving state quantity and the reference data of the reference trajectory, and the boundary constraints of the vehicle driving control quantity, solve the cost function to obtain the vehicle driving control quantity at the current moment.

[0063] In one embodiment, by setting six state quantity differences (lateral position error) respectively Horizontal error change rate Heading angle error Rate of change of heading error Longitudinal residual distance error Speed ​​error By considering the boundary constraints of the first vehicle and the boundary constraints of the second vehicle and the third vehicle, the vehicle driving control quantity at the current moment can be obtained.

[0064] For example, setting The boundary constraints are Other boundary constraints can be calibrated based on engineering experience.

[0065] By solving the cost function, a series of vehicle driving control quantities, including the vehicle driving control quantity at the current moment, can be obtained. , ...... Take the first one. This serves as the vehicle driving control quantity at the current moment, and is sent to the lower-level controller (e.g., chassis domain / parking integrated controller) to calculate the vehicle driving control quantity at the current moment. It will be used to control the steering wheel angle and acceleration of the vehicle from the current moment to the next moment.

[0066] This application limits vehicle movement to a safe range within the narrow space of a parking space by defining the boundary constraints of the state quantity difference and the control quantity, and generating multi-step future reference points to support multi-constraint optimization. This avoids the risk of the vehicle scraping the edge of the parking space or adjacent vehicles, significantly improves the accuracy of the parking end pose alignment, and effectively reduces the parking pose deviation.

[0067] S105: Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained.

[0068] In one embodiment, the reference control quantities include: reference steering wheel angle and reference acceleration.

[0069] In one embodiment, when the reference control quantity includes a reference steering wheel angle, the reference control quantity is obtained based on reference data of the reference trajectory and the current position of the vehicle at the current moment, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the second aiming distance, a second aiming point is determined on the reference trajectory; Based on the pre-stored curvature of the reference trajectory, the reference curvature of the second aiming point is determined; The front wheel feed angle is determined based on the reference curvature and feed forward gain of the second aiming point; Based on the front wheel feed angle, the reference steering wheel angle is determined.

[0070] In one embodiment, the second aiming distance can be obtained based on the vehicle's current speed and the second base aiming distance. ,in, This is the second aiming distance. This is the second basic aiming distance. This is the second coefficient. and These are values ​​that can be calibrated based on engineering experience.

[0071] In one embodiment, based on the current vehicle's gear information, a second aiming point is determined on the reference trajectory ahead of the driving direction, based on the matching point and the second aiming distance.

[0072] In one embodiment, the reference curvature of the second pre-aiming point can be obtained by the difference between the position of the second pre-aiming point and the pre-stored curvature of the reference points adjacent to the second pre-aiming point.

[0073] In one embodiment, the front wheel feed angle is: ,in, For feedforward gain, This refers to the vehicle's wheelbase. For reference curvature.

[0074] In one embodiment, the reference steering wheel angle is: , Steering ratio (steering wheel angle / front wheel angle, for example: 14~18).

[0075] This application can compensate for the lag defect by determining a second aiming point on the reference trajectory and generating a reference steering wheel angle accordingly. It can adapt to the curvature changes of narrow parking spaces in advance, reduce the frequent steering wheel correction actions, and make the driving trajectory smoother.

[0076] In one embodiment, the method further includes: determining the relationship between the vehicle's first remaining driving distance and a second distance threshold at the current moment, and reducing the feedforward gain when the vehicle's first remaining driving distance is less than the second distance threshold at the current moment.

[0077] In one embodiment, the second distance threshold is a value calibrated based on engineering experience.

[0078] This application reduces the feedforward gain when the vehicle's first remaining driving distance is less than a second distance threshold at the current moment. This weakens the steering intervention force of the reference steering wheel angle in the final stage of parking, avoiding additional heading disturbances. With extremely small margin in the narrow parking space, the risk of vehicle deviation, scraping the edge of the parking space or adjacent vehicles caused by excessive correction of the reference steering wheel angle can be greatly reduced. This allows lateral control to rely more on the precise fine-tuning of the vehicle's position and posture based on the real-time calculated vehicle driving control amount, effectively improving the alignment accuracy in the final stage of parking in narrow spaces.

[0079] In one embodiment, the reference data for the second aiming point includes a reference heading angle, and the vehicle driving status quantity at the current moment includes the heading angle at the current moment; the difference in the status quantity includes the heading angle error. The method further includes: when the vehicle's first remaining driving distance is less than a third distance threshold at the current moment, and the heading angle error contradicts the direction of the reference steering wheel angle, setting the reference steering wheel angle to 0; or When the vehicle's first remaining driving distance is less than the third distance threshold and the heading angle error is less than the angle threshold at the current moment, the reference steering wheel angle is set to 0.

[0080] In one embodiment, the third distance threshold and the angle threshold are calibrated values ​​based on engineering experience.

[0081] In this application, when the remaining distance at the end of the parking space is less than the third distance threshold, if the heading angle error conflicts with the direction of the reference steering wheel angle or the heading angle error itself is extremely small, the reference steering wheel angle is directly set to zero. This can eliminate the steering interference caused by the reference steering wheel angle, and the vehicle attitude can be finely adjusted and corrected solely by the real-time calculated vehicle driving control quantity. This avoids the reference steering wheel angle at the end of the narrow parking space from exacerbating the positional deviation, improves the alignment accuracy of the end point of the extreme narrow parking space, and reduces the risk of collision.

[0082] In one embodiment, when the reference control quantity includes a reference acceleration, the reference control quantity is obtained based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the third aiming distance, a third aiming point is determined on the reference trajectory; Based on the pre-stored acceleration of the reference trajectory and the position of the third aiming point, the reference acceleration of the third aiming point is determined.

[0083] In one embodiment, the third aiming distance can be obtained based on the vehicle's current speed and the third base aiming distance. ,in, This is the third aiming distance. This is the third basic aiming distance. It is the third coefficient. and These are values ​​that can be calibrated based on engineering experience.

[0084] In one embodiment, based on the current vehicle's gear information, a third aiming point is determined on the reference trajectory ahead of the driving direction, based on the matching point and the third aiming distance.

[0085] In one embodiment, the reference acceleration of the third pre-aiming point can be obtained by the difference between the position of the third pre-aiming point and the pre-stored acceleration of the reference points adjacent to the third pre-aiming point.

[0086] In one embodiment, the second aiming distance and the third aiming distance may be the same or different. The second aiming point and the third aiming point may be the same or different.

[0087] In this application, the third pre-aiming point is obtained by combining the matching point with the third pre-aiming distance and the corresponding reference acceleration is extracted to provide a benchmark for longitudinal control. The pre-aiming mechanism plans the acceleration and deceleration requirements in advance, which alleviates the lag problem caused by relying solely on the real-time calculated vehicle driving control quantity, making the acceleration and deceleration actions of parking in narrow spaces smoother and improving the longitudinal parking accuracy in extreme narrow parking spaces.

[0088] S106: Based on the vehicle driving control quantity at the current moment and the reference control quantity, obtain the target control quantity.

[0089] In one embodiment, the vehicle driving control quantities at the current moment include the vehicle steering wheel angle at the current moment and the vehicle acceleration at the current moment.

[0090] The reference control quantities include: reference steering wheel angle and reference acceleration.

[0091] The target control variables include: target steering wheel angle and target acceleration.

[0092] The target steering wheel angle can be obtained by adding the current steering wheel angle and the reference steering wheel angle.

[0093] The target acceleration can be obtained by summing the current acceleration and the reference acceleration.

[0094] In this application, the reference control quantity is a theoretical steering / acceleration output based on advance aiming, which compensates for the motion requirements caused by path curvature and trajectory length, eliminating the control lag that exists if the vehicle driving control quantity is relied upon solely at the current moment. The vehicle driving control quantity at the current moment can eliminate lateral deviation, heading deviation, longitudinal remaining distance deviation, and speed deviation of the vehicle body in real time, and cope with vehicle body disturbances and posture deviations in narrow parking spaces. The two are added together to integrate prediction and real-time correction, taking into account both advanced adjustment and dynamic correction.

[0095] The methods described above in this application can be performed in a model predictive controller, for example, in the MPC (Model Predictive Control) module.

[0096] After obtaining the target acceleration, if the vehicle's initial remaining distance is very short or extremely short, or if there is a slope, the target acceleration can be compensated for according to different situations to obtain the compensated acceleration. The following sections will describe these situations in detail: In one embodiment, when the target control quantity includes the target acceleration, the method further includes: when the first remaining driving distance of the vehicle at the current moment is less than the fourth distance threshold, determining a first compensation acceleration based on the speed of the vehicle at the current moment and the first remaining driving distance of the vehicle at the current moment; Based on the target acceleration and the first compensated acceleration, the compensated acceleration is obtained.

[0097] In one embodiment, the fourth distance threshold can be a value calibrated based on engineering experience.

[0098] In one embodiment, the first compensation acceleration is: , in, This represents the vehicle's first remaining distance at the current moment. is a coefficient.

[0099] In this application, when the remaining driving distance is very short, a first compensation acceleration is introduced to make up for the inadequacy of using only the basic target acceleration control, and to solve the problem of insufficient braking deceleration and inability to stop at close range.

[0100] In one embodiment, when the target control quantity includes the target acceleration, the method further includes: setting a virtual target point in front of the vehicle's current position when the vehicle's first remaining driving distance at the current moment is less than a fifth distance threshold; The second compensation acceleration is determined based on the vehicle's current speed and the second remaining travel distance at the virtual target point; Based on the target acceleration and the second compensated acceleration, the compensated acceleration is obtained.

[0101] In one embodiment, the fifth distance threshold can be a value calibrated based on engineering experience. The fifth distance threshold is less than the fourth distance threshold. For example, the fifth distance threshold is 0.2m.

[0102] In one embodiment, the virtual target point is set at a very small distance (e.g., 0.1 m) in front of the vehicle (in the gear direction). A similar method can be used to determine the second remaining driving distance at the virtual target point by projecting the virtual target point onto a reference trajectory and then interpolating.

[0103] In one embodiment, the second compensation acceleration: , in, This represents the second remaining distance traveled at the virtual target point. is a coefficient.

[0104] In this application, when the vehicle is only a very short distance away from the parking endpoint (e.g., less than 0.2m), the original target acceleration control is prone to problems such as residual speed, braking impact, or overshooting the target point. By setting a virtual target point in front of the vehicle (e.g., 0.1m ahead), a second compensating acceleration is introduced to correct the target acceleration. This avoids the problems of low-speed adjustment lag, repeated acceleration and deceleration, and shaking and overtravel at the end of extremely close-range parking that can occur when relying solely on target acceleration. It can achieve smooth, shock-free, and precise parking, improving the comfort and positioning accuracy of parking at the endpoint.

[0105] In one embodiment, when the target control quantity includes the target acceleration, the method further includes: determining a third compensation acceleration based on the vehicle's pitch angle; Based on the target acceleration and the third compensation acceleration, the compensated acceleration is obtained.

[0106] In one embodiment, the third compensating acceleration: , Where g is the acceleration due to gravity. This refers to the vehicle's pitch angle.

[0107] In this application, by calculating the third compensation acceleration, the problems of vehicle slippage, insufficient power when going uphill, and overshoot when braking caused by the slope can be eliminated, so that the actual output acceleration is not affected by the gravity of the slope, resulting in better consistency of acceleration, deceleration and parking control on flat ground and downhill, and improving parking accuracy and driving smoothness.

[0108] In one embodiment, the calculated compensated accelerations can be combined based on the specific scenario. For example, if the vehicle's first remaining travel distance is less than a fourth distance threshold at the current moment, the target acceleration and the first compensated acceleration are summed to obtain the compensated acceleration. Similarly, if the vehicle's first remaining travel distance is less than a fourth distance threshold at the current moment, and the vehicle is on a slope, the target acceleration, the first compensated acceleration, and the third compensated acceleration are summed to obtain the compensated acceleration. Finally, if the vehicle's first remaining travel distance is less than a fifth distance threshold at the current moment, and the vehicle is on a slope, the target acceleration, the second compensated acceleration, and the third compensated acceleration are summed to obtain the compensated acceleration.

[0109] The following methods provided in this application can be performed in a PEB (Pre-Controlled Emergency Braking) controller.

[0110] In one embodiment, when the distance from the obstacle to the vehicle is greater than a preset safe distance, the TTC time is calculated based on the vehicle's current speed and acceleration. When the TTC time is greater than the time threshold, determine whether the distance from the obstacle to the vehicle is less than the sixth distance threshold; If the distance from the obstacle to the vehicle is less than the sixth distance threshold, the speed of the first aiming point is replaced with a preset speed value.

[0111] In one embodiment, the preset speed value is less than the speed at the first aiming point. The preset speed value can be a value set based on engineering experience, such as 0.8 km / h.

[0112] In one embodiment, the sixth distance threshold may be a value set based on engineering experience, such as 0.7m.

[0113] In one embodiment, ultrasonic sensors are arranged around the vehicle body, each ultrasonic sensor having its own preset safe distance.

[0114] In one embodiment, the distance from the obstacle to the vehicle can be either the distance directly measured by the ultrasonic sensor or an equivalent distance. The equivalent distance can be obtained by dividing the distance directly measured by the ultrasonic sensor by an equivalence factor. Each ultrasonic sensor has its own corresponding equivalence factor. By using the equivalent distance, the raw ultrasonic ranging measurements from different installation positions and detection angles can be corrected to an obstacle-to-vehicle distance under a unified benchmark, eliminating hardware installation and detection angle errors and providing accurate and reliable obstacle distance input.

[0115] In one embodiment, when the distance from the obstacle to the vehicle is less than a preset safe distance, a preset acceleration is sent to the lower-level controller, and the lower-level controller adjusts its acceleration to the preset acceleration. That is, the lower-level controller is forcibly taken over, and the preset acceleration is, for example, -6 m / s².

[0116] In one embodiment, when the distance from the obstacle to the vehicle is greater than a preset safe distance, the TTC time is calculated based on the vehicle's current speed and acceleration. When the TTC time is less than the time threshold, the preset acceleration is sent to the lower-level controller, and the lower-level controller adjusts the acceleration to the preset acceleration.

[0117] In one embodiment, the TTC time calculation formula is as follows: in, Current vehicle speed Acceleration at the current moment The sum of the distance between the vehicle and the obstacle and the preset safe distance.

[0118] In one embodiment, the time threshold may be a value calibrated based on engineering experience, such as 2 seconds.

[0119] In this application, a tiered collision avoidance system is achieved by combining a preset safe distance, a distance threshold, and a TTC collision time: at close range (when the distance from the obstacle to the vehicle is less than the preset safe distance) and when the TTC time is less than the time threshold, the lower-level controller is directly forced to brake suddenly; at medium risk (when the distance from the obstacle to the vehicle is greater than the preset safe distance, the TTC time is greater than the time threshold, and the distance from the obstacle to the vehicle is less than the sixth distance threshold), the speed at the first aiming point is reduced to achieve a gentle deceleration; the tiered control system balances driving smoothness and collision avoidance reliability, and the linkage between the upper and lower level controllers results in rapid braking response, effectively avoiding scrape collisions.

[0120] This application embodiment also provides a narrow parking space adaptive parking control device, the device including an MPC control module, the MPC control module being configured to: Dynamic equations are constructed based on vehicle driving state variables and vehicle driving control variables; A cost function is constructed based on the reference data of the reference trajectory, the vehicle driving state variables at the current moment, the dynamic equation, the Q matrix, the vehicle driving control variables, and the R matrix; where the Q matrix represents the weights of the state variables and the R matrix represents the weights of the control variables. Based on the relationship between the vehicle's first remaining driving distance and the first distance threshold at the current moment, determine whether to adjust the Q matrix; Based on the boundary constraints between the vehicle driving state quantity and the reference data of the reference trajectory, and the boundary constraints of the vehicle driving control quantity, the cost function is solved to obtain the vehicle driving control quantity at the current moment. Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained; The target control quantity is obtained based on the vehicle driving control quantity at the current moment and the reference control quantity.

[0121] It should be noted that the technical features and beneficial effects of the device provided in this application embodiment can be found in the above method embodiment, and will not be repeated here.

[0122] This application also provides an electronic device, including: a memory and a processor; The memory is used to store the relevant program code; The processor is used to call the program code and execute the above method.

[0123] This application also provides a computer-readable storage medium for storing a computer program for performing the above-described method.

[0124] This application also provides a computer program product, which includes a computer program / instructions that, when executed by a processor, implement the above-described method.

[0125] It should be noted that the computer-readable medium described above in this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0126] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java 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 computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0127] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. The units or modules described as separate components may or may not be physically separate. The components shown as units or modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units or modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions, and operations that may be implemented by methods, apparatuses, and devices according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0129] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0130] It should also be noted that, in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0131] The steps of the methods or algorithms described in conjunction with the embodiments disclosed in this application can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0132] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for adaptive parking control in narrow parking spaces, characterized in that, The method includes: Dynamic equations are constructed based on vehicle driving state variables and vehicle driving control variables; A cost function is constructed based on the reference data of the reference trajectory, the vehicle driving state variables at the current moment, the dynamic equation, the Q matrix, the vehicle driving control variables, and the R matrix; where the Q matrix represents the weights of the state variables and the R matrix represents the weights of the control variables. Based on the relationship between the vehicle's first remaining driving distance and the first distance threshold at the current moment, determine whether to adjust the Q matrix; Based on the boundary constraints between the vehicle driving state quantity and the reference data of the reference trajectory, and the boundary constraints of the vehicle driving control quantity, the cost function is solved to obtain the vehicle driving control quantity at the current moment. Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained; The target control quantity is obtained based on the vehicle driving control quantity at the current moment and the reference control quantity.

2. The method according to claim 1, characterized in that, The cost function, constructed from the reference data based on the reference trajectory, the vehicle's current driving state, the dynamic equation, the Q matrix, the vehicle driving control quantity, and the R matrix, includes: Based on the current vehicle driving state quantity and the dynamic equation, the future vehicle driving state quantity is obtained; The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the first aiming distance, a first aiming point is determined on the reference trajectory; Based on the first reference velocity and preset control cycle of the first aiming point, multiple future reference points are determined on the reference trajectory; Based on the current vehicle driving state quantity, the future vehicle driving state quantity, the reference data of the first aiming point, and the reference data of the future reference point, the state quantity difference is obtained; A cost function is constructed based on the state variable difference, Q matrix, vehicle driving control quantity, and R matrix.

3. The method according to claim 1, characterized in that, The reference control quantity includes the reference steering wheel angle; Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the second aiming distance, a second aiming point is determined on the reference trajectory; Based on the pre-stored curvature of the reference trajectory, the reference curvature of the second aiming point is determined; The front wheel feed angle is determined based on the reference curvature and feed forward gain of the second aiming point; Based on the front wheel feed angle, the reference steering wheel angle is determined.

4. The method according to claim 3, characterized in that, The method further includes: determining the relationship between the vehicle's first remaining driving distance and a second distance threshold at the current moment, and reducing the feedforward gain when the vehicle's first remaining driving distance is less than the second distance threshold at the current moment.

5. The method according to claim 3, characterized in that, The reference data for the second aiming point includes the reference heading angle, and the vehicle's current driving status includes the heading angle at the current moment; The state quantity difference includes the heading angle error; The method further includes: when the vehicle's first remaining driving distance is less than the third distance threshold at the current moment, and the heading angle error is contrary to the direction of the reference steering wheel angle, setting the reference steering wheel angle to 0; or When the vehicle's first remaining driving distance is less than the third distance threshold and the heading angle error is less than the angle threshold at the current moment, the reference steering wheel angle is set to 0.

6. The method according to claim 1, characterized in that, The reference control quantity includes the reference acceleration; Based on the reference data of the reference trajectory and the current position of the vehicle at the current moment, a reference control quantity is obtained, including: The matching point is determined on the reference trajectory based on the vehicle's current position at the current moment; Based on the matching point and the third aiming distance, a third aiming point is determined on the reference trajectory; Based on the pre-stored acceleration of the reference trajectory and the position of the third aiming point, the reference acceleration of the third aiming point is determined.

7. The method according to claim 1, characterized in that, The target control quantity includes the target acceleration, and the method further includes: when the first remaining driving distance of the vehicle at the current moment is less than the fourth distance threshold, determining a first compensation acceleration based on the speed of the vehicle at the current moment and the first remaining driving distance of the vehicle at the current moment; Based on the target acceleration and the first compensated acceleration, the compensated acceleration is obtained.

8. The method according to claim 1, characterized in that, The target control quantity includes the target acceleration, and the method further includes: when the first remaining driving distance of the vehicle at the current moment is less than the fifth distance threshold, setting a virtual target point in front of the vehicle's position at the current moment; The second compensation acceleration is determined based on the vehicle's current speed and the second remaining travel distance at the virtual target point; Based on the target acceleration and the second compensated acceleration, the compensated acceleration is obtained.

9. The method according to claim 1, characterized in that, The target control quantity includes the target acceleration, and the method further includes: determining a third compensation acceleration based on the vehicle's pitch angle; Based on the target acceleration and the third compensation acceleration, the compensated acceleration is obtained.

10. The method according to claim 2, characterized in that, The method further includes: When the distance from the obstacle to the vehicle is greater than the preset safe distance, the TTC time is calculated based on the vehicle's current speed and acceleration. When the TTC time is greater than the time threshold, determine whether the distance from the obstacle to the vehicle is less than the sixth distance threshold; If the distance from the obstacle to the vehicle is less than the sixth distance threshold, the speed of the first aiming point is replaced with a preset speed value.

Images