A parking control method, device, apparatus and medium

Abstract

The application relates to the field of automatic parking, in particular to a parking control method and device, equipment and medium, the method comprising the following steps: after receiving a parking instruction, first acquiring a planned warehouse entry path length and a maximum vehicle speed; determining whether to adopt speed control or distance control according to a preset distance-speed curve, in combination with the warehouse entry path length and the maximum vehicle speed; determining a trajectory polynomial according to a data group corresponding to different control modes, in combination with a constraint condition and a time library; and performing parking control according to the trajectory polynomial. The warehouse entry path length and the maximum vehicle speed are combined to select a control mode with high efficiency and comfort, and a corresponding trajectory polynomial is constructed, so as to facilitate parking control, thereby realizing accurate, smooth and efficient parking process, ensuring driving at a reasonable speed, accurately completing warehouse entry along the planned path, improving the safety of parking, and improving the user experience.

Description

Technical Field

[0001] This application relates to the field of automatic parking, and in particular to a parking control method, apparatus, device, and medium. Background Technology

[0002] Automated parking refers to the automatic parking of a car into a parking space. The system controls the vehicle's steering, acceleration, and deceleration to plan multiple driving trajectories and then park the car in the designated space. Each trajectory moves from an initial point to a stopping point, and then from the stopping point to the next trajectory, until the final stopping point is reached and the car is parked.

[0003] In related technologies, for each trajectory segment, the parking control method moves according to the planned trajectory, so that it stops at the last stage. All the accumulated speed and distance deviations are placed in a small distance before the final stop to ensure that the control is smooth and the debugging difficulty is increased. It is often impossible to avoid the feeling of nodding when the vehicle stops heavily and the problem of restarting the vehicle after stopping early, which affects the user's parking experience. Summary of the Invention

[0004] The purpose of this application is to provide a parking control method, device, equipment, and medium that can select an efficient and comfortable control mode by combining the length of the parking path and the maximum vehicle speed, thereby constructing a precise trajectory polynomial for parking control. This achieves a precise, smooth, and efficient parking process, ensuring that the vehicle travels at a reasonable speed and accurately completes parking along the planned path, thus improving parking safety and enhancing the user experience.

[0005] Firstly, a parking control method is provided, comprising: upon receiving a parking instruction, acquiring the planned entry path length and maximum speed; determining a control mode based on the entry path length and maximum speed according to a preset distance-speed curve, wherein the control mode includes: speed control and distance control; determining a trajectory polynomial corresponding to the control mode based on a data set, constraints, and a time database; wherein the data set includes: initial speed and initial acceleration; if the control mode is speed control, the data set also includes the maximum speed; if the control mode is distance control, the data set also includes the remaining distance; and performing parking control based on the trajectory polynomial.

[0006] In a preferred embodiment, this application can be further configured to: determine the trajectory polynomial corresponding to the control method based on the data set, constraints, and time library, including: constructing a trajectory polynomial with undetermined coefficients corresponding to the control method; determining the coefficient set of the trajectory polynomial with undetermined coefficients corresponding to the target time based on the target time and the data set, wherein the target time is any time in the time library; using the constraints, removing times not within the constraints from the time library based on the coefficient sets corresponding to each time in the time library; and determining the trajectory polynomial corresponding to the control method based on the coefficient sets corresponding to the remaining times.

[0007] In a preferred embodiment, this application can be further configured to: determine the trajectory polynomial corresponding to the control mode based on the coefficient group corresponding to the remaining time, including: calculating the cost value of each remaining time; selecting the coefficient group of the remaining time with the smallest cost value based on the cost value of each remaining time; and constructing the trajectory polynomial corresponding to the control mode based on the first coefficient group of the remaining time with the smallest cost value.

[0008] In a preferred embodiment, this application may be further configured to include: determining a predicted distance for stopping at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time; determining a braking acceleration based on the predicted distance and the remaining distance; and stopping the vehicle based on the braking acceleration.

[0009] In a preferred embodiment, this application may be further configured to: before determining the predicted distance corresponding to stopping at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time, the method further includes: determining whether the remaining distance is less than a first preset distance; if so, then performing the determination of the predicted distance corresponding to stopping at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time.

[0010] In a preferred embodiment, this application can be further configured to: determine braking acceleration based on the predicted distance and the remaining distance, including: if the predicted distance is less than the remaining distance and the stitched trajectory is valid, then after passing the shift point, a gentle braking acceleration is invoked for a smooth stop; if the predicted distance is less than the remaining distance and the stitched trajectory is invalid, then at a second preset distance from the shift point, a normal braking acceleration is invoked for a normal stop; if the predicted distance is less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, a normal braking acceleration is invoked for a normal stop; if the predicted distance is not less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, an emergency braking acceleration is invoked for an emergency stop.

[0011] In a preferred embodiment, this application may be further configured to include: acquiring a spliced ​​trajectory, wherein the spliced ​​trajectory is a sub-trajectory in a pre-constructed next trajectory, and the initial point of the sub-trajectory is a shift point; determining whether the spliced ​​trajectory is valid based on the point coordinates of the spliced ​​trajectory and the nearest distance and safe distance from the obstacle; and / or determining whether the safe distance of the shift point meets the requirements based on the nearest distance and safe distance from the obstacle; and / or performing PID control during parking control based on the trajectory polynomial.

[0012] Secondly, a parking control device is provided, comprising: a planning module, used to obtain the planned entry path length and maximum speed when a parking instruction is received; a control mode determination module, used to determine the control mode based on the entry path length and maximum speed according to a preset distance-speed curve, wherein the control mode includes: speed control and distance control; a trajectory determination module, used to determine the trajectory polynomial corresponding to the control mode based on a data set, constraints, and a time library; wherein the data set includes: initial speed and initial acceleration, and if the control mode is speed control, the data set also includes the maximum speed, and if the control mode is distance control, the data set also includes the remaining distance; and a parking control module, used to perform parking control based on the trajectory polynomial.

[0013] Thirdly, an electronic device is provided, the electronic device including a memory and a processor, the memory storing a computer program, the processor executing the parking control method according to any one of the first aspects when running the computer program.

[0014] Fourthly, a computer-readable storage medium is provided, wherein at least one piece of program code is stored therein, the program code being loaded and executed by a processor to implement the parking control method as described in any of the first aspects.

[0015] Fifthly, a computer program product is provided, including a computer program or instructions that, when executed by a processor, implement the parking control method as described in any of the first aspects.

[0016] In summary, the parking control method provided in this application has the following beneficial technical effects:

[0017] Upon receiving a parking instruction, the system first obtains the planned entry path length and maximum speed. Based on a preset distance-speed curve, and considering the entry path length and maximum speed, it determines whether to use speed control or distance control. Based on the data sets corresponding to different control methods, and combining constraints and a time library, it determines the trajectory polynomial. Parking control is then performed based on the trajectory polynomial. By combining the entry path length and maximum speed to select an efficient and comfortable control method, and then constructing the corresponding trajectory polynomial for parking control, the system achieves precise, smooth, and efficient parking. This ensures that the vehicle travels at a reasonable speed and accurately completes entry along the planned path, improving parking safety and enhancing the user experience.

[0018] In addition, this application also provides a parking control device, equipment, and medium, all of which have the aforementioned beneficial technical effects. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of a parking control method provided in an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of a preset distance-velocity curve provided in an embodiment of this application;

[0022] Figure 3 A speed control curve provided for an embodiment of this application;

[0023] Figure 4 A distance control curve provided in an embodiment of this application;

[0024] Figure 5 This is a schematic flowchart of another parking control method provided in an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of trajectory splicing provided in an embodiment of this application;

[0026] Figure 7 This is a schematic diagram of a collision verification method provided in an embodiment of this application;

[0027] Figure 8 This is a flowchart illustrating another parking control method provided in an embodiment of this application;

[0028] Figure 9 This is a schematic diagram of the structure of a parking control device provided in an embodiment of this application;

[0029] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0030] This specific embodiment is merely an explanation of this application and is not intended to limit it. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of this application.

[0031] It should be noted that, in the optional embodiments of this application, the data related to object information, when applied to specific products or technologies, requires the permission or consent of the object. Furthermore, the collection, use, and processing of this data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. In other words, if the embodiments of this application involve data related to an object, it must be obtained with the permission and consent of the object, the permission and consent of relevant departments, and in accordance with the relevant laws, regulations, and standards of the country and region. If the embodiments involve personal information, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject is required. The embodiments also need to be implemented with the permission and consent of the object.

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0034] This application provides a parking control method, such as... Figure 1 As shown, the method provided in this application embodiment can be executed by an electronic device, which is a server. This server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, laptop, desktop computer, or vehicle terminal, etc., but is not limited to these. The terminal device and electronic device can be directly or indirectly connected via wired or wireless communication. This application embodiment does not impose any limitations on this connection. The method includes:

[0035] S101. Upon receiving a parking instruction, obtain the planned entry route length and maximum vehicle speed.

[0036] In this embodiment, when it is determined that automatic parking is required at the current moment, the user can issue a command by clicking "Start Parking." Then, the hybrid A* path planning module plans the parking path curve, obtaining the parking path length S and the maximum vehicle speed Vset for each parking maneuver. The specific planning process is not limited in this embodiment, as long as it achieves the purpose of this embodiment. Of course, other planning modules can also be used. It is understood that by planning the parking path curve using the hybrid A* path planning module, the parking path length S and the maximum vehicle speed Vset can be obtained. The parking path length is from the current vehicle position to the shift point, and the maximum vehicle speed can also be generated based on the parking path curve.

[0037] S102. Based on the length of the entry route and the maximum vehicle speed, determine the control method according to the preset distance-speed curve. The control methods include: speed control and distance control.

[0038] Among them, the preset distance-speed curve is as follows Figure 2 As shown, Pos0, Pos1, and Pos2 are the coordinates of three (S, V) points, corresponding to three calibration values. The three calibration values ​​are pre-set coordinates. The area allocation for speed control and distance control is achieved through these three calibration points.

[0039] Understandably, before each vehicle movement, the planning module provides the entry path length S and maximum speed Vset for the next trajectory (entry path curve). Then, the speed and distance determination module interpolates the ordinate on the determination curve based on the set speed Vset and compares it with the planned target entry path length S. If the entry path length S is greater than or equal to the ordinate on the curve, speed control is initiated; otherwise, distance control is initiated.

[0040] For example, for point A, if the ordinate is higher than the preset distance-speed curve, then the corresponding entry speed control is activated; for point B, if the ordinate is not higher than the preset distance-speed curve, then the corresponding entry distance control is activated.

[0041] S103. Based on the data set, constraints, and time library, determine the trajectory polynomial corresponding to the control method; wherein, the data set includes: initial velocity, initial acceleration, if the control method is speed control, the data set also includes the maximum vehicle speed, if the control method is distance control, the data set also includes the remaining distance;

[0042] The control method is selected by calibrating the speed control and distance control decision modules. That is, the most efficient and comfortable control method is selected when the length of the entry path S, the current actual remaining distance, and the target vehicle speed Vset are known.

[0043] Where the initial speed is the vehicle's speed when the parking instruction is received, the initial acceleration is the vehicle's acceleration when the parking instruction is received, the distance of the vehicle when the parking instruction is received is S0, the length of the parking path is S, and the remaining distance is S. remain =S-S0. The constraints include: speed constraint range, acceleration constraint range, and jerk constraint range. The speed constraint range is from 0 to the maximum vehicle speed; the acceleration constraint range is an empirical value, such as -1 to 1; and the jerk constraint range is an empirical value, such as -4 to 4. The time library is a pre-defined library of 15 time values, and the times in this library are empirical values.

[0044] In one possible embodiment, a trajectory polynomial corresponding to speed control is determined based on the initial speed, initial acceleration, maximum vehicle speed, constraints, and a time library. The trajectory polynomial includes a distance polynomial, a speed polynomial, and an acceleration polynomial. Furthermore, when performing parking control based on the trajectory polynomial, the speed polynomial and acceleration polynomial can be provided to the speed control module for speed control.

[0045] In another possible embodiment, the trajectory polynomial corresponding to distance control is determined based on the initial velocity, initial acceleration, remaining distance, constraints, and time library. The trajectory polynomial includes a distance polynomial, a velocity polynomial, and an acceleration polynomial. Furthermore, when performing parking control based on the trajectory polynomial, the velocity-distance polynomial, velocity polynomial, and acceleration polynomial can be provided to the distance control module for distance control.

[0046] S104. Perform parking control based on the trajectory polynomial.

[0047] Upon receiving a parking instruction, the system first obtains the planned entry path length and maximum speed. Based on a preset distance-speed curve, and considering the entry path length and maximum speed, it determines whether to use speed control or distance control. Based on the data sets corresponding to different control methods, and combining constraints and a time library, it determines the trajectory polynomial. Parking control is then performed based on the trajectory polynomial. By combining the entry path length and maximum speed to select an efficient and comfortable control method, and then constructing the corresponding trajectory polynomial for parking control, the system achieves precise, smooth, and efficient parking. This ensures that the vehicle travels at a reasonable speed and accurately completes entry along the planned path, improving parking safety and enhancing the user experience.

[0048] One possible implementation of this application embodiment is as follows: S103 determines the trajectory polynomial corresponding to the control method based on the data set, constraints, and time library, including:

[0049] S1031. Construct the trajectory polynomial of undetermined coefficients corresponding to the control mode;

[0050] Construct the distance S as a fifth-degree polynomial in time t, where: ; ; ; .

[0051] in These are the coefficients of the 3rd, 4th, and 5th degree terms, respectively. The distance traveled at the initial planning moment relative to the origin of the coordinate system at the parking ignition moment is the distance traveled. Let be the initial velocity of the vehicle at the initial planning time. The initial acceleration is the initial acceleration at the initial planning time. Distance functions The first, second, and third derivatives.

[0052] S1032. Based on the target time and data set, determine the coefficient set of the undetermined coefficient trajectory polynomial corresponding to the target time. The target time is any time in the time library.

[0053] For speed control At this moment, the known distance, velocity, and acceleration at the initial planning time are... , . At time t Between, among For the first There are several available time slots, among which Preset to A total of 15 time libraries are available, targeting speed control. The speed, acceleration, and acceleration Jerk at a given moment are known, meaning the set speed has been reached ( At time ), both acceleration and acceleration Jerk are 0, as follows: , , . ; Assumption It is invertible; by multiplying both sides by its inverse matrix, we can obtain the solution: , , The coefficient set corresponding to each time in the time database is obtained sequentially: .

[0054] For distance control At time 1, i.e., at the first time step of solving for velocity control, the distance, velocity, and acceleration are known: . At time t Between, among Let i be the i-th candidate time, where Preset to There are a total of 15 time libraries, namely At any given moment, the distance, velocity, and acceleration are known, meaning the remaining distance has been covered ( At time ), both the velocity and acceleration are 0, as follows: , . Assuming It is invertible; by multiplying both sides by its inverse matrix, we can obtain the solution: , , , The coefficient set corresponding to each time in the time database is obtained sequentially: .

[0055] S1033. Using the constraints, based on the coefficient groups corresponding to each time in the time database, remove the times that are not within the constraints from the time database.

[0056] The constraints are as follows: , . The constraint range is a pre-set constraint range that takes into account the comfort and smoothness of braking, is related to the driving experience, and is a calibrated empirical value.

[0057] Furthermore, after obtaining In the case of calculation The extrema results of the polynomial are removed from the time database if they do not satisfy the condition. The time constraint range enables the first-level time filtering.

[0058] S1034. Determine the trajectory polynomial corresponding to the control mode based on the coefficient group corresponding to the remaining time.

[0059] One possible implementation of this application is that, based on the coefficient group corresponding to the remaining time, any coefficient group can be selected to determine the trajectory polynomial corresponding to the control mode.

[0060] Another possible implementation of this application is to determine the trajectory polynomial corresponding to the control method based on the coefficient group corresponding to the remaining time: calculate the cost value of each remaining time; select the coefficient group of the remaining time with the smallest cost value based on the cost value of each remaining time; and construct the trajectory polynomial corresponding to the control method based on the first coefficient group of the remaining time with the smallest cost value.

[0061] In this embodiment of the application, the process proceeds to the cost evaluation module. The cost function for time selection is used for the final time filtering calculation. ,in, This is a time cost coefficient, and the value is an empirical value. For the selected i-th time, Between, among To satisfy the time library required by the FindExtrema curve extrema module, the time after the first layer of time filtering in this time library is calculated by the cost evaluation module. The ranking of costs and benefits over time will select the one with the lowest cost. To determine the optimal control time, a final time selection is performed.

[0062] Furthermore, based on the first set of coefficients of the optimal control time (the remaining time with the minimum cost), the trajectory polynomial is obtained. See also Figure 3 , Figure 4 , Figure 3 A speed control curve provided for an embodiment of this application; Figure 4 A distance control curve provided for an embodiment of this application.

[0063] As can be seen, in the embodiments of this application, a global distance, velocity, and acceleration planning scheme is adopted. By constructing a cost function and considering the time cost and acceleration slope cost, the planning time that best matches the executor performance is selected. The cost coefficient can be adjusted for different executor performances, which increases the robustness of the algorithm.

[0064] One possible implementation of this application further includes: determining the predicted distance corresponding to stopping at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time; determining the braking acceleration based on the predicted distance and the remaining distance; and stopping the vehicle based on the braking acceleration.

[0065] In this embodiment, a Brakedown determination module is added. The Brakedown determination module can be triggered when the remaining distance is detected to be less than a first preset distance during the distance control phase; or when the length S determined by the hybrid A* path planning module is less than the first preset distance. Other possible triggers exist, and users can customize the settings.

[0066] Normal braking acceleration is set to a preset value. ,in, This represents the actual speed of the vehicle in real time. , To use the actual vehicle speed according to The time required to decrease downwards to 0 is as follows: Furthermore, the predicted distance will be... Value and remaining distance The braking acceleration is determined through comparison to achieve a complete stop. The remaining distance is determined in real-time during the distance control process.

[0067] As can be seen, in this embodiment, the actual speed reflects the current motion state of the vehicle, the normal braking acceleration reflects the rate of change of acceleration and deceleration during conventional braking, and the braking response time considers the delay from the issuance of the braking command to its actual effect. This allows for the estimation of the predicted distance required for normal braking by using the normal braking acceleration. By comparing this predicted distance with the remaining distance, the braking acceleration is adjusted to select between normal, emergency, or gentle braking. Braking is then performed based on the determined braking acceleration, thus achieving precise control of the braking process. This ensures a smooth stop for the vehicle, avoiding collision risks caused by braking too early (before reaching the shift point) or too late, while also reducing the impact during braking, improving parking safety and comfort, and enhancing the user experience.

[0068] One possible implementation of this application embodiment, before determining the predicted distance for stopping at normal braking acceleration based on actual speed, normal braking acceleration, and braking response time, further includes: determining whether the remaining distance is less than a first preset distance; if so, then executing the determination of the predicted distance for stopping at normal braking acceleration based on actual speed, normal braking acceleration, and braking response time. The first preset distance serves as a key threshold to determine whether to enter a fine-grained braking control phase; the first preset distance can be customized by the user, such as 0.6m.

[0069] As can be seen, in this embodiment of the application, before determining the predicted distance corresponding to stopping at normal braking acceleration, it is first determined whether the remaining distance is less than the first preset distance; when the remaining distance is less than the preset distance, it means that the vehicle is close to the shift point. At this time, the steps of predicting distance calculation and braking acceleration determination are performed, which avoids unnecessary complex calculations when the distance is far, and at the same time ensures the accuracy of braking control in the critical close distance stage.

[0070] Furthermore, it's important to note that the relevant technology fails to correlate the distribution of obstacles at shift points with the braking mode, rigidly ensuring that both the remaining distance and the vehicle speed are zero. This leads to several problems: 1. It places extremely high demands on the acceleration tracking accuracy of the longitudinal actuators, which is difficult to meet, resulting in a long adaptation period with the parking upper level and IPB. 2. Even in open areas, where the safe distance between each shift point and obstacle is large, the cumulative deviation in speed and distance caused by previous control measures results in excessively heavy braking, making seamless braking impossible and failing to fundamentally solve the problem of uncomfortable and inconsistent braking feel. 3. It causes many paths to fail to reach the shift point before braking, leading to subsequent lateral control failing to follow the planned trajectory, resulting in replanning and even the risk of collision.

[0071] Therefore, this application primarily uses a trajectory planning module to determine whether the obstacle distribution at the shift point meets the requirements for adding a stitched trajectory. If it does, it employs a classification braking logic. Specifically, it assesses obstacles at the shift point; if space is sufficient, it initiates seamless braking; if obstacles are too close and the trajectory stitching requirements are not met, it compares the predicted distance S_predict with the remaining distance S_remain to determine whether to initiate emergency or comfortable braking, ensuring safety. Furthermore, adding a trajectory after the shift point avoids issues like multiple replanning attempts or collisions caused by incomplete path completion.

[0072] One possible implementation of this application embodiment determines the braking acceleration based on the predicted distance and the remaining distance, including: if the predicted distance is less than the remaining distance and the stitched trajectory is valid, then after passing the shift point, a gentle braking acceleration is invoked for a smooth stop; if the predicted distance is less than the remaining distance and the stitched trajectory is invalid, then at a second preset distance from the shift point, normal braking acceleration is invoked for a normal stop; if the predicted distance is less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, normal braking acceleration is invoked for a normal stop; if the predicted distance is not less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, emergency braking acceleration is invoked for an emergency stop.

[0073] The shift point refers to the coordinate point where a vehicle is performing a gear shift operation, indicating the key location where the vehicle's motion state changes abruptly.

[0074] Among them, if This means that according to The deceleration slope results in a longer braking distance, and the vehicle speed is relatively faster than the planned speed. If the spliced ​​trajectory is still effective at this point, softbrakedown is invoked after passing the shift point for a smoother braking. If the splicing trajectory status is invalid, the system will enter Normal Brakedown control within a second preset distance (e.g., 0.4m) within the shift point, where the first preset distance is greater than the second preset distance. If the safe distance at the shift point does not meet the requirements, an emergency brakedown should be performed before the shift point is passed to ensure safety. If the safe distance at the shift point does not meet the requirements, then a normal brakedown will be performed before the shift point is passed to ensure braking comfort.

[0075] As can be seen, in this embodiment, the selection of braking acceleration is handled in different cases based on the relationship between the predicted distance and the remaining distance, the validity of the spliced ​​trajectory, and whether the safety distance at the shift point meets the requirements. When the predicted distance is less than the remaining distance and the spliced ​​trajectory is valid, it indicates that the remaining distance is sufficient and the subsequent trajectory connection is smooth. After passing the shift point, a gentle braking acceleration is applied to make the braking process smoother and reduce vehicle impact. When the predicted distance is less than the remaining distance but the spliced ​​trajectory is invalid, it means that there is a problem with the trajectory connection. Normal braking acceleration is applied at the second preset distance from the shift point to ensure both braking effect and stability. When the predicted distance is less than the remaining distance and the safety distance at the shift point does not meet the requirements, normal braking acceleration is applied before the shift point to brake in advance to ensure safety in order to avoid safety hazards at the shift point. When the predicted distance is not less than the remaining distance and the safety distance at the shift point does not meet the requirements, it indicates that the remaining distance is insufficient to support normal braking. Emergency braking acceleration is applied before the shift point to quickly reduce the vehicle speed and avoid danger. It can achieve the optimal selection of braking acceleration according to different driving conditions and distance conditions, which not only ensures that the vehicle can stop safely and smoothly under various conditions, but also significantly improves the reliability of parking braking control.

[0076] For details, see Figure 5 This includes: S11, through the planning module, confirming the remaining distances Sremain and Vset for each planning iteration; verifying the safe distance to obstacles at shift points to confirm whether the trajectory is stitched together; if speed control / distance control is required, then entering the speed control / distance control determination module. If distance verification is required, then entering the Brakedown determination module and executing S15.

[0077] S12 Speed ​​and Distance Control Determination Module; If speed control is required, speed control, constant speed control, and distance control are executed sequentially; if distance control is required, distance control is executed. During distance control, the process can proceed to S13.

[0078] S13 The remaining distance Sremain is less than the threshold calibrated value of 0.6m; if so, then execute S14.

[0079] S14 Triggers Prediction Real-time calculation; execute S16.

[0080] S15 checks if the current distance to the obstacle safety distance threshold is met and whether the trajectory can be spliced. If yes, proceed to S19; otherwise, proceed to S16.

[0081] S16 Judgment If the value is greater than Sremain, proceed to S18; otherwise, proceed to S17.

[0082] S17 performs a normal brakedown to a stop.

[0083] S18 is brought to an emergency brakedown stop.

[0084] After passing the shift point, S19 enters softbrakedown and comes to a stop.

[0085] Furthermore, regarding the splicing trajectory, the splicing trajectory is a sub-trajectory in the pre-constructed trajectory of the next round, and the initial point of the sub-trajectory is the gear shift point.

[0086] Understandably, upon receiving a parking instruction, the system plans the length of the parking path and the maximum speed from the current position to the shift point. Simultaneously, it plans the path starting from the shift point of the next parking maneuver, as well as the length of the parking path and the maximum speed for that next maneuver. At this point, the sub-path of the next maneuver is used as the spliced ​​path.

[0087] A sub-track represents a continuous path segment separated from the complete track, with a specific starting point and target point. Specifically, it refers to a local track starting from a shift point. The initial point refers to the starting position of the sub-track in the spatiotemporal dimension, specifically the shift point of the previous track. The length of the sub-track can be customized by the user, such as 20cm, 50cm, etc., and then determined from the next track based on the preset length. See 6. Figure 6 This is a schematic diagram of trajectory splicing provided in an embodiment of this application. For a spliced ​​trajectory, the point where the vehicle reaches the shift point of the planned trajectory is the currently planned trajectory, and the spliced ​​trajectory is a sub-trajectory in the trajectory of the next round.

[0088] Furthermore, methods for determining whether a stitching trajectory is valid include: acquiring the stitching trajectory; and determining whether the stitching trajectory is valid based on the point coordinates of the stitching trajectory, the nearest distance to the obstacle, and the safe distance.

[0089] After successfully planning the trajectory based on the shift point, a spliced ​​trajectory is inserted at the shift point with a length of 20cm (calibrated value). The intersection of the spliced ​​trajectory's point coordinates (x, y, θ) with the obstacle is calculated to find the shortest distance. If the shortest distance meets the calibrated safety distance limit, the trajectory splicing mode can be performed. After the spliced ​​trajectory is generated, the total distance S for control is the distance from the vehicle's position to the shift point plus the spliced ​​trajectory distance after the shift point. Softbrakedown can then be used after passing the shift point for seamless braking, solving the problem of premature braking and double starts or hard braking that easily occurs when strictly braking to the shift point. This significantly improves the overall control experience.

[0090] See Figure 7The system identifies obstacles, estimates the coordinates of the vehicle's trajectory points after reaching the stitched path, and then calculates the shortest distance between the obstacle and the vehicle's trajectory points. This shortest distance is compared to a preset safety distance. If the shortest distance is greater than the safety distance, the stitched path is considered valid; otherwise, it is invalid. It's understood that if multiple obstacles exist, the determined shortest distance is the shortest distance among the distances corresponding to each obstacle.

[0091] As can be seen, in this embodiment, the splicing trajectory is a sub-trajectory in the pre-constructed next trajectory and takes the shift point as the initial point to ensure the continuity of movement; the validity of the splicing trajectory is determined by the nearest distance and safe distance between the point coordinates of the splicing trajectory and the obstacle: when the nearest distance between each point on the trajectory and the obstacle is greater than the safe distance, it means that the trajectory has no collision risk and is determined to be valid and can be used for subsequent driving; otherwise, it is invalid, thus pre-screening out safe and reliable splicing trajectories.

[0092] Furthermore, determining whether the safe distance to the shift point meets the requirements includes: determining whether the safe distance to the shift point meets the requirements based on the closest distance between the shift point and the obstacle and the safe distance.

[0093] The process involves identifying obstacles, determining the coordinates of the shift point, calculating the nearest distance between the obstacle and the shift point, and comparing this nearest distance with a preset safety distance. If the nearest distance is greater than the safety distance, the safety distance for the shift point meets the requirement; otherwise, it does not. It is understood that if multiple obstacles exist, the determined nearest distance is the shortest distance among the distances corresponding to each obstacle.

[0094] As can be seen, in this embodiment of the application, when the closest distance between the shift point and the obstacle is greater than the safe distance, it indicates that the point is in a safe area and meets the safety requirements; otherwise, it does not meet the requirements. The safety verification is achieved through the above-mentioned determination process.

[0095] Furthermore, it may also include: performing PID control during the parking control process based on the trajectory polynomial.

[0096] For the speed control module, specifically the P control module, a lookup table is constructed for the speed difference and the P term Kp, as shown in Table 1, to adjust the coefficients under different deviation magnitudes.

[0097] Table 1

[0098]

[0099] The I control is implemented using the formula: m_sumErrorVel += m_curErrorVel * time_delta, where m_curErrorVel is the current error, time_delta is the running cycle, and sumErrorVel is the cumulative term of the product of integral deviation and time. A lookup table is constructed to determine the cumulative integral deviation term and the integral coefficient Ki. As shown in Table 2, this allows for the adjustment of the coefficient under different deviation magnitudes.

[0100] Table 2

[0101]

[0102] For the distance control module, see Table 3 for speed P control and Table 4 for distance P control.

[0103] Table 3

[0104]

[0105] Table 4

[0106]

[0107] As can be seen, in this embodiment of the application, the introduction of PID control in the parking control process based on the trajectory polynomial significantly improves the accuracy and stability of parking control, ensuring that the vehicle can accurately travel along the planned trajectory.

[0108] For any of the above embodiments, this application provides a specific control method that brings a more human-like comfort to parking braking. It switches between comfortable and safe braking modes by determining the spatial location at each planned shift point, and the overall polynomial programming can adapt to different longitudinal actuators. By combining polynomial acceleration programming with trajectory planning shift points, different braking modes are selected based on actual judgment. A cost function for time selection is constructed to choose the final time that balances the response performance and efficiency of the longitudinal actuator. By analyzing the speed and remaining distance in the trajectory provided by the planning end, a speed control and distance control determination module selects a highly efficient and comfortable control scheme, increasing control flexibility.

[0109] like Figure 8 As shown, it includes:

[0110] S21. Click "Start Parking" to proceed to S22.

[0111] S22, Hybrid A* Path Planning Module, plans the inbound path curve, the length S of each inbound path and the maximum vehicle speed Vset.

[0112] S23 and TCH are acceleration planning modules that plan acceleration, velocity, and distance curves based on the planning inputs s and vset.

[0113] S24, Speed ​​and Distance Control Decision Module.

[0114] If the problem is determined to be speed control, proceed to step S25;

[0115] S25, speed control, speed control polynomial solver module, cost evaluation module CostFun4Ctrl for time selection and construction, planning speed / acceleration curve outgoing (acceleration feedforward), speed control module.

[0116] In speed control, S26 is executed.

[0117] S26. Determine if the actual vehicle speed is greater than Vset. If so, proceed to S27; otherwise, execute S26 in real time.

[0118] S27, Uniform speed control, uniform speed closed-loop control module.

[0119] S28, Distance Control, Distance Control Polynomial Solver Module, CostFun4Ctrl module for time selection and construction, planning of distance / velocity / acceleration curves (acceleration feedforward), and distance control module.

[0120] S29, SafeDistCheck4GearSwitch shift point safety distance determination module, Brakedown determination module.

[0121] The following describes a device provided by an embodiment of this application. The device described below can be referred to in correspondence with the method described above. The device of this embodiment is installed in an electronic device. Figure 9 , Figure 9 This is a structural block diagram of an apparatus according to one embodiment of this application, comprising:

[0122] The planning module 210 is used to obtain the planned entry path length and maximum vehicle speed when a parking instruction is received;

[0123] The control mode determination module 220 is used to determine the control mode based on the length of the entry path and the maximum vehicle speed according to the preset distance-speed curve. The control modes include: speed control and distance control.

[0124] The trajectory determination module 230 is used to determine the trajectory polynomial corresponding to the control mode based on the data set, constraints, and time library. The data set includes: initial velocity, initial acceleration, and if the control mode is speed control, the data set also includes the maximum vehicle speed; if the control mode is distance control, the data set also includes the remaining distance.

[0125] The parking control module 240 is used to perform parking control based on the trajectory polynomial.

[0126] In one feasible approach, the trajectory determination module 230 is used to: construct a trajectory polynomial with undetermined coefficients corresponding to the control mode; determine the coefficient set of the trajectory polynomial with undetermined coefficients corresponding to the target time based on the target time and the data set, wherein the target time is any time in the time library; using constraints, remove times that are not within the constraints from the time library based on the coefficient sets corresponding to each time in the time library; and determine the trajectory polynomial corresponding to the control mode based on the coefficient sets corresponding to the remaining times.

[0127] In one feasible approach, the trajectory determination module 230 is used to calculate the cost value of each remaining time; select the coefficient group of the remaining time with the smallest cost value based on the cost value of each remaining time; and construct the trajectory polynomial corresponding to the control mode based on the first coefficient group of the remaining time with the smallest cost value.

[0128] In one possible implementation, the system further includes a braking determination module, used to: determine the predicted distance corresponding to braking at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time; determine the braking acceleration based on the predicted distance and the remaining distance; and brake to a stop based on the braking acceleration.

[0129] In one feasible approach, the braking determination module is used to: determine whether the remaining distance is less than a first preset distance; if so, then perform the following: determine the predicted distance for braking to a stop at normal braking acceleration based on the actual speed, normal braking acceleration, and braking response time.

[0130] In one feasible implementation, the braking determination module is configured to: if the predicted distance is less than the remaining distance and the stitched trajectory is valid, then after passing the shift point, invoke gentle braking acceleration for a smooth stop; if the predicted distance is less than the remaining distance and the stitched trajectory is invalid, then at a second preset distance from the shift point, invoke normal braking acceleration for a normal stop; if the predicted distance is less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, invoke normal braking acceleration for a normal stop; if the predicted distance is not less than the remaining distance and the safety distance at the shift point does not meet the requirements, then before the shift point, invoke emergency braking acceleration for an emergency stop.

[0131] In one possible implementation, the system further includes: a trajectory validity determination module, used to: acquire a spliced ​​trajectory, which is a sub-trajectory in a pre-constructed next trajectory, with the initial point of the sub-trajectory being a shift point; determine whether the spliced ​​trajectory is valid based on the point coordinates of the spliced ​​trajectory, the nearest distance to the obstacle, and the safe distance; and / or, a shift point safe distance determination module, used to: determine whether the shift point safe distance meets the requirements based on the nearest distance to the obstacle and the safe distance; and / or, a PID control module, used to: perform PID control during parking control based on the trajectory polynomial.

[0132] This application provides an electronic device, such as... Figure 10 As shown, Figure 10 The illustrated electronic device 300 includes: at least one processor 301 ( Figure 10 The image shows one processor 301 and one memory 303. The processor 301 and memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of this application.

[0133] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0134] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0135] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0136] The memory 303 is used to store application code that executes the solution of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0137] Figure 10 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0138] This application provides a computer-readable storage medium storing at least one piece of program code that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0139] This application provides a computer program product, including a computer program or instructions, which, when executed by a processor, implement the corresponding content in the aforementioned method embodiments.

[0140] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0141] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A parking control method, characterized in that, include: Upon receiving a parking instruction, obtain the planned entry route length and maximum vehicle speed; Based on the length of the entry route and the maximum vehicle speed, a control method is determined according to a preset distance-speed curve. The control method includes: speed control and distance control. Based on the data set, constraints, and time library, determine the trajectory polynomial corresponding to the control method; wherein, the data set includes: initial velocity, initial acceleration, if the control method is speed control, the data set also includes the maximum vehicle speed, if the control method is distance control, the data set also includes the remaining distance; Parking control is performed based on the trajectory polynomial; Based on the data set, constraints, and time library, determine the trajectory polynomial corresponding to the control method, including: Construct the trajectory polynomial of undetermined coefficients corresponding to the control method; Based on the target time and the data set, determine the coefficient set of the undetermined coefficient trajectory polynomial corresponding to the target time, where the target time is any time in the time library; Using constraints, based on the coefficient groups corresponding to each time in the time database, remove times that are not within the constraints from the time database; Based on the coefficient set corresponding to the remaining time, determine the trajectory polynomial corresponding to the control mode. Based on the coefficient set corresponding to the remaining time, determine the trajectory polynomial corresponding to the control mode, including: Calculate the cost of each remaining time period; Based on the cost of each remaining time period, select the coefficient group of the remaining time periods with the lowest cost. Construct the trajectory polynomial corresponding to the control mode based on the first set of coefficients of the remaining time with the minimum cost.

2. The parking control method according to claim 1, characterized in that, Also includes: Based on the actual speed, normal braking acceleration, and braking response time, determine the predicted distance corresponding to stopping at normal braking acceleration; Determine the braking acceleration based on the predicted distance and the remaining distance; Braking is performed based on the braking acceleration.

3. The parking control method according to claim 2, characterized in that, Before determining the predicted distance for stopping at normal braking acceleration based on actual speed, normal braking acceleration, and braking response time, the process also includes: Determine if the remaining distance is less than the first preset distance; If so, the predicted distance for stopping at normal braking acceleration is determined based on the actual speed, normal braking acceleration, and braking response time.

4. The parking control method according to claim 2, characterized in that, Based on the predicted distance and remaining distance, determine the braking acceleration, including: If the predicted distance is less than the remaining distance and the stitched trajectory is valid, then after passing the shift point, gentle braking acceleration will be used to bring the vehicle to a smooth stop. If the predicted distance is less than the remaining distance and the spliced ​​trajectory is invalid, then normal braking acceleration will be invoked to bring the vehicle to a normal stop when it is at the second preset distance from the shift point. If the predicted distance is less than the remaining distance and the safe distance to the shift point does not meet the requirements, then normal braking acceleration will be used to bring the vehicle to a normal stop before the shift point. If the predicted distance is not less than the remaining distance, and the safe distance at the shift point does not meet the requirements, then emergency braking acceleration will be activated before the shift point to bring the vehicle to an emergency stop.

5. The parking control method according to claim 4, characterized in that, Also includes: Obtain the splicing trajectory, which is a sub-trajectory in the pre-constructed trajectory of the next round, and the initial point of the sub-trajectory is the shift point; The validity of the splicing trajectory is determined based on the point coordinates of the splicing trajectory, the nearest distance to the obstacle, and the safe distance.

6. The parking control method according to claim 5, characterized in that, Also includes: Determine whether the safe distance to the shift point meets the requirements based on the closest distance between the shift point and the obstacle, as well as the safe distance.

7. The parking control method according to claim 1, characterized in that, Also includes: PID control is performed during parking control based on the trajectory polynomial.

8. A parking control device, characterized in that, include: The planning module is used to obtain the length of the planned entry route and the maximum vehicle speed when a parking instruction is received. The control mode determination module is used to determine the control mode based on the length of the entry path and the maximum vehicle speed according to a preset distance-speed curve. The control mode includes: speed control and distance control. The trajectory determination module is used to determine the trajectory polynomial corresponding to the control mode based on the data set, constraints, and time library. The data set includes: initial velocity, initial acceleration, and if the control mode is speed control, the data set also includes the maximum vehicle speed; if the control mode is distance control, the data set also includes the remaining distance. The parking control module is used to perform parking control based on the trajectory polynomial. The trajectory determination module is used to construct a trajectory polynomial with undetermined coefficients corresponding to the control mode; determine the coefficient set of the trajectory polynomial with undetermined coefficients corresponding to the target time based on the target time and the data set, wherein the target time is any time in the time library; using constraints, remove times that are not within the constraints from the time library based on the coefficient sets corresponding to each time in the time library; and determine the trajectory polynomial corresponding to the control mode based on the coefficient sets corresponding to the remaining times. The trajectory determination module is used to calculate the cost value of each remaining time; based on the cost value of each remaining time, it selects the coefficient group of the remaining time with the smallest cost value; based on the first coefficient group of the remaining time with the smallest cost value, it constructs the trajectory polynomial corresponding to the control mode.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the parking control method according to any one of claims 1 to 7 when running the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to implement the parking control method as described in any one of claims 1 to 7.

Images