High-efficiency automatic parking system and method based on turning radius optimization

Abstract

The invention discloses a high-efficiency automatic parking system and method based on turning radius optimization, and the system comprises a sensor group which is used for obtaining the state information of a vehicle; the ECU is used for carrying out path planning operation based on a variable radius according to the vehicle state information and carrying out path tracking control operation based on preview distance self-adaption according to a planned path; the actuator is used for responding to the control operation of the ECU; according to the method, multiple parking strategies can be fused, rapid and accurate parking is achieved, and based on the R-S curve algorithm with the variable radius, garage rubbing or parking failure caused by the fixed radius is avoided; search is accelerated based on a simulated annealing algorithm, and a pure tracking algorithm is improved, so that the preview distance is adaptive according to the vehicle speed, the tracking precision and the parking stability are improved, and the automatic parking experience is optimized in all directions.

Description

Technical Field

[0001] The present invention relates to the technical field of joint control of vehicle subsystems, and particularly to a high-efficiency automatic parking system and method based on optimized turning radius. Background Art

[0002] With the rapid development of the automotive industry and continuous progress of technology, the automotive industry is gradually moving towards automation and intelligence; as one of the core functions of the assisted driving system, automatic parking technology has been widely applied in various vehicle models; this technology can greatly improve the convenience and safety of parking, especially in the context of urban congestion and limited parking spaces, which is particularly important.

[0003] During the research and application process of automatic parking technology, parking speed and tracking accuracy have become key performance indicators; increasing the speed of automatic parking can save the user's time cost, while improving tracking accuracy can ensure the stability and safety of the parking process, especially in the narrow parking space condition, the ability to park accurately and quickly has become an important standard for measuring the quality of an automatic parking system; therefore, how to design and develop an automatic parking controller with excellent performance, safety and reliability has become the focus of current research by experts and scholars.

[0004] Currently, there are various existing automatic parking control technology methods, mainly including search algorithms, methods based on optimization theory, and methods based on machine learning, etc., as follows: (1) The search algorithm finds the optimal parking trajectory by continuously trying and optimizing the path, but the computational complexity is large and the real-time performance is poor.

[0005] (2) The method based on optimization theory solves the optimal parking path by establishing a mathematical model, but the model establishment and solution process are complex, and it is easily limited by the accuracy of the model.

[0006] (3) The method based on machine learning learns parking skills by training models such as neural networks, but it requires a large amount of training data and computing resources, and there may be problems with insufficient generalization ability in practical applications.

[0007] (4) The parking control method based on geometric models is widely adopted because of its simple calculation and easy implementation; this method calculates the parking trajectory by establishing a geometric relationship model between the vehicle and the parking space; however, this method has poor adaptability in the specific implementation process and is difficult to handle complex and changeable actual parking conditions, such as blurred parking space lines, obstacle interference, etc., thus limiting its effect in practical applications.

[0008] Therefore, in view of the deficiencies of the existing technology, it is necessary to develop a new type of automatic parking controller that can improve parking accuracy and adaptability while ensuring the calculation speed. Summary of the Invention

[0009] The object of the present invention is to provide a high-efficiency automatic parking system and method based on optimized turning radius, so as to solve all or one of the above problems existing in the prior art.

[0010] To solve the above technical problems, the specific technical solutions of the present invention are as follows: On the one hand, the present invention provides a high-efficiency automatic parking system based on optimized turning radius, including: A sensor group for obtaining vehicle state information; An ECU for performing path planning operations based on variable radius according to the vehicle state information, and performing path tracking control operations based on preview distance adaptation according to the planned path; An actuator for responding to the control operations of the ECU.

[0011] As an improved solution, the sensor group includes: a wheel speed sensor, a camera and a GPS; The vehicle state information includes: real-time vehicle speed, obstacle and parking space information, and position information; The wheel speed sensor is used to detect the real-time vehicle speed of the vehicle; The camera is used to detect the obstacle and parking space information around the vehicle; The GPS is used to obtain the position information of the vehicle.

[0012] As an improved solution, the camera is further used to obtain the obstacle and parking space information by using the YOLO v8 algorithm.

[0013] As an improved solution, the ECU includes: an upper controller; The upper controller is used to perform the path planning operation according to the vehicle state information; The path planning operation performed by the upper controller includes: the upper controller determines constraints, and after determining the constraints, performs R-S curve path planning based on variable radius, performs route optimization based on the simulated annealing algorithm for the R-S curve trajectory, and solves the optimal path curve based on the weight function.

[0014] As an improved solution, the constraints include: maximum wheel steering angle, vehicle speed, vehicle position, and parking position.

[0015] As an improved solution, the upper controller is specifically further used to: determine the optimal turning radius of the vehicle based on the simulated annealing algorithm, and perform path optimization on the R-S curve trajectory within the optimal turning radius according to the vehicle state information; The upper controller is specifically further configured to: use the path length and the number of changes as weights, use whether there is an obstacle in the path as a penalty value, and determine the optimal path curve according to the weights and the weight function corresponding to the penalty value.

[0016] As an improved solution, the search function of the simulated annealing algorithm is: r = r 0 +(q * rand - 1); where r is the turning radius; r 0 is the acting radius of the brake disc; q is the control factor parameter; rand is a random number; The weight function is: ; where l is the path length; cg is the number of direction changes; p is the penalty function.

[0017] As an improved solution, the ECU further includes: a lower controller; The lower controller is configured to: set a preview point model, obtain the path coordinate information corresponding to the optimal path curve in the R - S curve; construct a preview point corresponding to the path coordinate information based on the preview point model; continuously search for the preview point through a pure tracking algorithm to control the vehicle to perform expected path tracking; The lower controller is further configured to: adaptively control the preview distance according to the vehicle speed during the process of controlling the vehicle to perform expected path tracking.

[0018] As an improved solution, the pure tracking algorithm executed by the lower controller includes: the lower controller sets a preview point on the expected path according to the current position of the rear wheels of the vehicle according to the preview distance; when the center of the rear wheels of the vehicle reaches the preview point at a certain radius, the lower controller determines the expected front wheel steering angle according to the preview distance, the turning radius, and the angle between the preview point and the vehicle body; the lower controller outputs the expected front wheel steering angle to the actuator.

[0019] On the other hand, the present invention also provides a high - efficiency automatic parking method based on turning radius optimization, including the following steps: Obtain vehicle state information; Perform a path planning operation based on a variable radius according to the vehicle state information, and perform a path tracking control operation based on preview distance adaptation according to the planned path.

[0020] The beneficial effects of the technical solution of the present invention are: 1. The high-efficiency automatic parking system based on optimized turning radius according to the present invention integrates a variety of parking strategies to achieve fast and accurate parking. Based on the R-S curve algorithm with variable radius, it avoids ramming the garage or parking failure caused by a fixed radius; based on the simulated annealing algorithm to accelerate the search and improve the pure tracking algorithm, the preview distance is adapted to the vehicle speed, improving the tracking accuracy and parking stability, and optimizing the automatic parking experience in all aspects.

[0021] 2. The high-efficiency automatic parking method based on optimized turning radius according to the present invention can orderly call system modules, thereby implementing the system logic of the high-efficiency automatic parking system based on optimized turning radius according to the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a schematic diagram of the logical architecture of the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the control flow of the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 3 It is a schematic diagram of the pure tracking half-vehicle model of the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 4 It is a schematic diagram of the result comparison between the R-S algorithm with variable radius and the traditional R-S algorithm in the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 5 It is a path planning curve diagram of the R-S algorithm with variable radius in the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 6 It is a curve diagram of the path tracking simulation result of the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 7 It is a Prescan simulation comparison diagram during the simulation experiment of the high-efficiency automatic parking system based on optimized turning radius according to Embodiment 1 of the present invention; Figure 8 It is a schematic diagram of the process of the high-efficiency automatic parking method based on optimized turning radius according to Embodiment 2 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following elaborates on the preferred embodiments of the present invention in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby making the protection scope of the present invention more clearly defined.

[0025] In the description of the present invention, it should be noted that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments; based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0026] The terms "first", "second", etc. in the specification, claims and above-mentioned drawings of this article are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, device, product or equipment that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or equipment.

[0027] In the description of the present invention, it should be noted that the shortest path of the traditional R-S curve from the starting point to the end point must be in the following table:

[0028] In the above table, C represents an arc, including two cases of left (L) or right (R); S represents a straight line; the superscript "+" represents forward, and "-" represents backward; "|" represents that the vehicle movement direction changes from forward to backward, or from backward to forward; the field with π / 2 subscript represents that the arc length / angle corresponding to the arc length of this section of the path is π / 2; the field with β subscript represents that the arc lengths / angles corresponding to two adjacent sections of the path are equal; after traversing the above nine combination cases, the optimal path is determined according to influencing factors such as the total path length, and the path length calculation formula is as follows: .

[0029] Embodiment 1, this embodiment provides a high-efficiency automatic parking system based on turning radius optimization, as Figures 1 to 7 shown, including: (1) A sensor group, including: a wheel speed sensor, a camera, and a GPS; the wheel speed sensor, the camera, and the GPS are respectively electrically connected to the vehicle electronic control unit (ECU) through the CAN bus, thereby realizing the transmission of vehicle state information; Among them, the wheel speed sensor is used to detect the real-time vehicle speed, and this vehicle speed is used as the input data of the vehicle electronic control unit (ECU). The corresponding wheel speed sensor signal is uploaded to the vehicle electronic control unit (ECU) as the control input quantity; Among them, the camera is used to detect the obstacles and parking space information around the vehicle, and this information is used as the index parameters for path planning; Among them, the GPS is used to obtain the vehicle's position information, perform vehicle positioning, and assist the vehicle electronic control unit (ECU) in planning the vehicle's parking trajectory; Among them, during the automatic parking control process, the operation process of the sensor group is as follows: (1.1) The wheel speed sensor obtains the vehicle speed; (1.2) The camera obtains the parking space information and obstacle conditions around the vehicle through the YOLO v8 method; (1.3) The GPS obtains the vehicle's position information; (1.4) The sensor group directly transmits the above-obtained data as vehicle state information to the ECU through the CAN bus.

[0030] (2) The vehicle electronic control unit (ECU) is used to perform path planning and path tracking control in sequence according to the data collected by the sensor group, and finally transmits the front wheel steering angle command to the steering motor through the CAN bus for action execution, thereby realizing the automatic parking motion control of the vehicle; Among them, during the automatic parking control process, the operation process of the vehicle electronic control unit (ECU) is as follows: (2.1) After the ECU receives the above vehicle state information, it determines the constraints; after determining the constraints, it performs R-S curve path planning based on a variable radius and performs route optimization on the R-S curve trajectory based on the simulated annealing algorithm, and finally solves the optimal curve through the weight function; Specifically, in this step, the determined constraints include, but are not limited to: the maximum wheel steering angle, vehicle speed, vehicle position, and parking position; Specifically, in this step, the optimal turning radius is determined based on the simulated annealing algorithm, and the R-S curve is searched within the optimal turning radius according to the vehicle position information and obstacle state in the vehicle state information; Specifically, the specific operation logic for searching the R-S curve within the optimal turning radius in this step is as follows: (i) Assuming that the path type is two arcs (radius r) and a straight line, then the starting point and the ending point have the following geometric constraints respectively: the center C of the left arc 1 is , and the center C of the right arc 2 is , the straight line segment needs to connect the endpoints of the two arcs, and its direction is consistent with the tangent of the arc; (ii) Continuing from the previous step, we convert the Cartesian coordinates (x, y) into polar coordinates (r', θ) to obtain (r', θ) = T(x, y), which can be expanded as follows: ; (iii) Continue from the previous step and set the left arc angle to θ 1 , the right arc angle is θ 2 , the length of the straight line segment is d; combined with geometric constraints, the starting point of the straight line is the end point of the left arc, that is: , and at the same time, the end point of the straight line is the starting point of the right arc, that is: , the direction of the straight line should be consistent with the direction of the tangent lines of the two arcs, that is: (direction continuous); (iiii) Finally, the total path length is converted into a function of T, that is: , and then construct the cost function (such as minimizing the length), that is: ; (iiiii) After that, search for the optimal turning radius and substitute the optimal turning radius into the above function to solve the optimal path; where the search function corresponding to the simulated annealing algorithm for the optimal turning radius is: r = r 0 +(q*rand-1); In this formula, r is the turning radius; q is the control factor parameter; rand is a random number, representing a randomly generated number from 0 to 1; r 0 is the effective radius of the brake disc; based on this formula, the optimal turning radius is determined; Specifically, in this step, when determining the optimal curve, the path length and the number of changes are used as weights, and whether there are obstacles in the path is used as a penalty value, and the optimal path is determined based on the corresponding weight function; wherein the weight function is: ; In this formula, l is the path length; cg is the number of direction changes; p is the penalty function, when there is an obstacle in the path, p=10000, when there is no obstacle in the path, p=0.

[0031] (2.2) The ECU imports the path coordinate information corresponding to the optimal path curve into the lower-level controller, which sets a three-degree-of-freedom preview point model (a three-degree-of-freedom half-vehicle steering model), sets a number of preview points corresponding to the path coordinate information based on the three-degree-of-freedom preview point model, and then uses a pure tracking algorithm to control the vehicle to track the path by continuously searching for preview points on the desired path; Specifically, in this step, an improved pure pursuit algorithm is adopted. It realizes vehicle parking control by continuously searching for target points on the expected path and simultaneously controlling the steering motor to change the front wheel angle. During the process, the preview distance is also adaptively controlled according to the vehicle speed, thereby achieving precise tracking of the expected path. Specifically, the pure pursuit algorithm is as follows: As Figure 3 shown, based on the position of the current vehicle's rear wheels, a preview point C is set on the vehicle's expected path at a distance of l d . If the center of the rear wheels reaches this preview point along a certain radius, then according to the geometric relationship between the preview distance l d , the turning radius R, and the orientation angle α in the vehicle coordinate system, the front wheel angle is determined . Finally, the calculation formula for the front wheel angle is: ; in this formula, is the front wheel angle, α is the angle between the preview point and the vehicle body, and l d is the preview distance. Specifically, the derivation process of the calculation formula for the front wheel angle is as follows: (i) Based on Figure 3 analysis, triangle AOC is an isosceles triangle. For triangle AOC, AB⊥OA, then there is: ; (ii) To ensure that the vehicle's rear wheels can smoothly track the arc path and reach point C, triangle AOC needs to satisfy ; (iii) At the same time, the control of the front wheel steering angle needs to satisfy in the Ackermann steering triangle AOC, that is: ; (iiii) Finally, by combining the above three formulas, the expression of the front wheel angle is obtained.

[0032] Specifically, the specific formula for adaptively controlling the preview distance according to the vehicle speed is: , where k is set according to specific circumstances.

[0033] Specifically, the formula for the angle α between the preview point and the vehicle body is: ; in this formula, φ is the heading angle; x r , y r are the coordinates of the preview point respectively, and x h , y h are the coordinates of the center of the rear axle of the half-vehicle model respectively.

[0034] (3) The steering motor (actuator) is used to perform corresponding steering operations according to the steering angle control instructions output by the vehicle electronic control unit (ECU), and complete the automatic parking movement of the vehicle; the steering motor is control-connected to the control unit ECU.

[0035] Among them, during the automatic parking control process, the operation process of the steering motor is as follows: After receiving the front wheel steering angle control amount output by the vehicle electronic control unit (ECU) in real time through the CAN bus, the steering motor performs motion control on the vehicle according to this control amount to achieve automatic parking.

[0036] In a preferred embodiment, the performance of the automatic parking hierarchical controller of the present application is verified through simulation tests, as follows: (i) Set two different parking conditions, namely vertical reverse parking into the garage and oblique reverse parking into the garage, with the vehicle speed being a random speed from 1 m / s to 5 m / s, and verify the automatic parking accuracy and efficiency; (ii) As Figure 5 shown, the planned path of the upper controller is displayed. Based on this figure, it can be intuitively shown that its planned path is smooth and fluent, and the number of times of adjusting the steering wheel is small; (iii) As Figure 6 shown, the lower layer path tracking control result is displayed. Based on this figure, it can be intuitively shown that the deviation between its planned path and the actual path of the vehicle is small, indicating that the adaptive pure tracking algorithm constructed by the lower layer controller has high tracking accuracy and small error; (iiii) As Figure 7 shown, the parking scenario established in Prescan is displayed. After verification, the target vehicle successfully parks in the parking space, and the vertical and oblique reverse parking into the garage are successfully realized; (iiiii) In addition, through comparative experiments, Figure 4 The multiple broken lines are the paths planned by the traditional R-S algorithm, and the smooth curve is the path planned by the R-S algorithm based on variable radius of the present invention. Based on this, it can be intuitively shown that the automatic parking path planned by the present invention has fewer times of adjusting the steering wheel, and the overall parking efficiency and smoothness are higher.

[0037] In summary, the present invention can generate the optimal path that conforms to the vehicle steering characteristics in a short time, the planned trajectory is simple and efficient, and at the same time, precise parking control is realized, meeting the requirements of accurate parking and safe driving out of multiple vehicles in a narrow space.

[0038] It should be noted that the above examples are only for explaining the present invention and should not limit the protection scope of the present invention accordingly.

[0039] Embodiment 2. This embodiment is based on the same inventive concept as the high-efficiency automatic parking system based on turning radius optimization described in Embodiment 1, and provides a high-efficiency automatic parking method based on turning radius optimization, as Figure 8 shown, which includes the following steps: S100. Obtain vehicle status information; S200. Perform path planning operation based on variable radius according to the vehicle status information, and perform path tracking control operation based on preview distance adaption according to the planned path.

[0040] Different from the prior art, by using the high-efficiency automatic parking system and method based on turning radius optimization of the present application, multiple parking strategies can be integrated to achieve fast and accurate parking. Based on the R-S curve algorithm with variable radius, it can avoid ramming the garage or parking failure caused by a fixed radius; based on the simulated annealing algorithm to accelerate the search and improve the pure tracking algorithm, the preview distance can be adapted according to the vehicle speed, improving the tracking accuracy and parking stability, and optimizing the automatic parking experience in all aspects.

[0041] It should be understood that in various embodiments herein, the size of the sequence numbers of the above processes does not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments herein.

[0042] It should also be understood that in the embodiments herein, the term "and / or" is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the preceding and following associated objects.

[0043] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this article.

[0044] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific logical process of the method described above can refer to the corresponding working processes of the system, device, and unit in the foregoing method embodiments, and will not be repeated here.

[0045] In several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces, devices, or units, and can also be in electrical, mechanical, or other forms of connection.

[0046] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments herein.

[0047] In addition, in each embodiment herein, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0048] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution herein, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment herein. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0049] The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention. All equivalent structural or equivalent process transformations made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are equally included in the patent protection scope of the present invention.

Claims

1. A high-efficiency automatic parking system based on turning radius optimization, characterized in that: include: A sensor group for obtaining vehicle status information; An ECU, configured to perform a path planning operation based on a variable radius according to the vehicle state information, and perform a path tracking control operation based on preview distance adaptation according to the planned path; The actuator is used to respond to the control operation of the ECU.

2. The high-efficiency automatic parking system based on turning radius optimization according to claim 1, characterized in that: The sensor group includes: a wheel speed sensor, a camera and a GPS; The vehicle status information includes: real-time vehicle speed, obstacle and parking space information and location information; The wheel speed sensor is used to detect the real-time speed of the vehicle; The camera is used to detect the obstacles and parking space information around the vehicle; The GPS is used to obtain the location information of the vehicle.

3. The high-efficiency automatic parking system based on turning radius optimization according to claim 2, characterized in that: The camera is also used to obtain the obstacle and parking space information using the YOLO algorithm.

4. The high-efficiency automatic parking system based on turning radius optimization according to claim 1, characterized in that: The ECU comprises: an upper controller; The upper controller is used to perform the path planning operation according to the vehicle state information; The path planning operation performed by the upper controller includes: the upper controller determines constraints, and performs RS curve path planning based on a variable radius after determining the constraints, optimizes the RS curve trajectory based on a simulated annealing algorithm, and solves the optimal path curve based on a weight function.

5. The high-efficiency automatic parking system based on turning radius optimization according to claim 4 is characterized in that: The constraints include: maximum wheel turning angle, vehicle speed, vehicle position and parking position.

6. The high-efficiency automatic parking system based on turning radius optimization according to claim 4, characterized in that: The upper controller is further used to: determine the optimal turning radius of the vehicle based on a simulated annealing algorithm, and perform path optimization on the RS curve trajectory within the optimal turning radius according to the vehicle state information; The upper layer controller is further used to: use the path length and the number of changes as weights, use whether there are obstacles in the path as a penalty value, and determine the optimal path curve according to a weight function corresponding to the weight and the penalty value.

7. The high-efficiency automatic parking system based on turning radius optimization according to claim 6, characterized in that: The search function of the simulated annealing algorithm is: r=r0+(q*rand-1); wherein r is the turning radius; r0 is the brake disc effective radius; q is the control factor parameter; rand is a random number; The weight function is: ; Among them, l is the path length; cg is the number of direction changes; p is the penalty function.

8. The high-efficiency automatic parking system based on turning radius optimization according to claim 4, characterized in that: The ECU further includes: a lower layer controller; The lower layer controller is used to: set a preview point model to obtain the path coordinate information corresponding to the optimal path curve in the RS curve; construct a preview point corresponding to the path coordinate information based on the preview point model; continuously search for the preview point through a pure tracking algorithm and control the vehicle to track the desired path; The lower layer controller is further used to adaptively control the preview distance according to the vehicle speed during the process of controlling the vehicle to track the desired path.

9. The high-efficiency automatic parking system based on turning radius optimization according to claim 8, characterized in that: The pure tracking algorithm executed by the lower-level controller includes: the lower-level controller sets a preview point on the expected path according to the preview distance based on the current rear wheel position of the vehicle; when the lower-level controller determines that the center of the rear wheel of the vehicle reaches the preview point according to a certain radius, the expected front wheel turning angle is determined according to the preview distance, the turning radius, and the angle between the preview point and the vehicle body; the lower-level controller outputs the expected front wheel turning angle to the actuator.

10. A high-efficiency automatic parking method based on turning radius optimization, characterized in that: The following steps are involved: Get vehicle status information; A path planning operation based on a variable radius is performed according to the vehicle state information, and a path tracking control operation based on preview distance adaptation is performed according to the planned path.

Images