Reversing control method, device and storage medium for intelligent vehicle

Abstract

The present invention proposes a reversing control method, device and storage medium for an intelligent vehicle, the method comprising: obtaining the current state and reversing reference path of the intelligent vehicle; establishing a rigid six-wheel vehicle model, converting the reversing reference path into a forward reference path based on a virtual vehicle; reversing all reference heading angles of the reversing reference path to obtain a forward reference heading angle; calculating the front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle and the current state of the virtual vehicle; calculating the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; calculating the steering dynamics compensation angle of the intelligent vehicle, and superimposing the steering dynamics compensation angle on the front wheel steering angle control amount of the intelligent vehicle to obtain the final front wheel steering angle control amount. The method improves the accuracy and real-time performance of the reversing control of the intelligent vehicle.

Description

Technical Field

[0001] The present invention relates to the field of vehicle control technology, and in particular to a reversing control method, device and storage medium for an intelligent vehicle that can achieve precise reversing. Background Art

[0002] When parking in and out of parking spaces, smart vehicles often need to adjust their posture. Unlike forward driving, although the speed is lower when reversing, the reversing trajectory usually has a larger curvature, requiring large-angle front wheel turning commands, and the space near the parking space is small, so the lateral control error requirements are also high. When driving in an off-road environment, it is often necessary to reverse to get out of trouble. When encountering very narrow passable areas, the lateral error requirements for reversing will be very high, and the real-time and robustness requirements for the control algorithm will be very high, otherwise it will be dangerous.

[0003] Existing technologies have been extensively studied for lateral control of vehicles in forward driving, and are relatively mature. However, using these control methods for reverse control will result in the following problems:

[0004] Tracking control algorithms based on the center of the vehicle's front axle, such as the Stanley method, cannot be used directly for reversing because the position of the steering wheel changes. The Pure Pursuit method based on the center of the vehicle's rear axle needs to select a shorter preview distance to obtain higher control accuracy when used for reversing, which can easily cause oscillation. The Linear-Quadratic Regulator design (LQR) is suitable for paths with small curvature, which are continuous and cannot change too quickly, so it is very suitable for medium- and high-speed urban driving tracking scenarios. For reversing scenarios with large changes in the curvature of the planned path or rugged terrain, there is a problem of path tracking difficulties. The premise of precise control by the Model Predictive Control (MPC) method is the accurate dynamic modeling of the vehicle. When reversing, the dynamic modeling and constraint conditions need to be re-set, and the MPC algorithm has a large amount of calculation, making it difficult to ensure the real-time performance of reversing control.

[0005] The above method is difficult to ensure the accuracy and real-time performance of reversing control when facing the traversable area in unstructured environment. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a reversing control method, device, and storage medium for an intelligent vehicle that can achieve precise reversing, which can solve the problems of poor reversing control accuracy, oscillation, or poor real-time performance of intelligent vehicles.

[0007] On one hand, the present invention provides a reversing control method for an intelligent vehicle, comprising: obtaining the current state and reversing reference path of the intelligent vehicle, establishing a rigid six-wheel vehicle model of the intelligent vehicle and a virtual vehicle, converting the reversing reference path based on a point on the intelligent vehicle into a forward reference path based on a corresponding point on the virtual vehicle; reversing all reference heading angles of the reversing reference path to obtain a forward reference heading angle; calculating a front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle; calculating a front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; calculating a steering dynamics compensation angle of the intelligent vehicle, and superimposing the steering dynamics compensation angle on the front wheel steering angle control amount of the intelligent vehicle to obtain a final front wheel steering angle control amount; generating a front wheel steering instruction and a driving braking instruction from the final front wheel steering angle control amount and sending them to a steering unit and a driving braking unit, wherein the steering unit executes the front wheel steering instruction, and the driving braking unit executes the driving braking instruction.

[0008] In one embodiment of the present invention, the method for establishing the rigid six-wheel vehicle model includes: fixing the smart vehicle and the virtual vehicle, wherein: the virtual vehicle and the smart vehicle are configured to share a rear axle, and the orientations differ by 180°; the left rear wheel of the smart vehicle is configured to constitute the right rear wheel of the virtual vehicle, and the right rear wheel of the smart vehicle constitutes the left rear wheel of the virtual vehicle; the front axle of the virtual vehicle is configured to be a virtual front axle, and a virtual right front wheel and a virtual left front wheel are installed at both ends of the virtual front axle, and the distance between the virtual right front wheel and the virtual left front wheel is the virtual front wheel track, and the virtual front wheel track is the same as the real front wheel track, and the real front wheel track is the distance between the right front wheel and the left front wheel of the smart vehicle; the vehicle center line of the virtual vehicle is configured to be on the same straight line as the vehicle center line of the smart vehicle.

[0009] In one embodiment of the present invention, a specific method for converting a reversing reference path based on a point on an intelligent vehicle into a forward reference path based on a corresponding point on a virtual vehicle is as follows: a first point on the intelligent vehicle is selected to determine a reversing reference path for the first point; a corresponding point on the virtual vehicle is selected as a second point, and the second point satisfies the following conditions: a vertical distance between the second point and a centerline of the vehicle is equal to a vertical distance between the first point and the centerline of the vehicle; a ratio of a distance from the second point to the rear axle to a distance from the first point to the rear axle is equal to a ratio of a virtual wheelbase to a real wheelbase, wherein the virtual wheelbase is the distance between the front axle and the rear axle of the virtual vehicle, and the real wheelbase is the distance between the front axle and the rear axle of the intelligent vehicle; assuming that the intelligent vehicle reverses according to the reversing reference path, the first point always keeps moving on the reversing reference path, and the heading angle of the vehicle is always consistent with the reference heading angle, and according to the geometric relationship between the second point and the first point in the rigid six-wheel vehicle model, the path passed by the second point is obtained as the forward reference path.

[0010] In one embodiment of the present invention, a lateral control algorithm of a two-degree-of-freedom kinematic model is used to calculate the front wheel steering angle control amount of the virtual vehicle, including: configuring the virtual front wheel center and the rear wheel center to be rigidly connected, with the front wheel responsible for steering, which together constitute a two-degree-of-freedom kinematic model; using the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle as input quantities for lateral control of the two-degree-of-freedom kinematic model, and outputting the front wheel steering angle control amount of the virtual vehicle, wherein the current state of the virtual vehicle is the same as the current state of the intelligent vehicle, including the vehicle's own posture and current vehicle speed.

[0011] In one embodiment of the present invention, the front wheel steering angle control amount of the virtual vehicle is expressed as:

[0012]

[0013] in, represents the front wheel steering angle control amount of the virtual vehicle, Indicates the current speed of the virtual vehicle; represents the lateral error of the virtual vehicle, represents the heading angle error of the virtual vehicle, represents the lateral gain coefficient.

[0014] In one embodiment of the present invention, the front wheel steering angle control amount of the intelligent vehicle is expressed as:

[0015]

[0016] in, represents the front wheel steering angle control value of the intelligent vehicle, Represents the front wheel steering angle control amount of the virtual vehicle; is the actual wheelbase, is the virtual wheelbase, where the virtual wheelbase is the distance between the front axle and the rear axle of the virtual vehicle, and the real wheelbase is the distance between the front axle and the rear axle of the intelligent vehicle.

[0017] In one embodiment of the present invention, the front wheel steering angle control amount of the intelligent vehicle is subtracted from the steering dynamics compensation angle to obtain the final front wheel steering angle control amount:

[0018]

[0019] in, represents the final front wheel steering angle control value, Indicates the front wheel steering angle control value of the intelligent vehicle; represents the steering dynamics compensation angle, and ,in: is the distance from the center of gravity of the smart vehicle to the rear axle, is the curvature of the reversing reference path, For the quality of smart vehicles, Indicates the current speed of the smart vehicle. represents the tire cornering stiffness of the smart vehicle, Represents the real wheelbase, which is the distance between the front axle and the rear axle of the smart vehicle.

[0020] On the other hand, the present invention also provides a reversing control device for an intelligent vehicle, which adopts the above-mentioned reversing control method and includes: a navigation and positioning unit installed on the body or chassis of the intelligent vehicle to collect the current state of the intelligent vehicle; a computing unit installed on the body or chassis of the intelligent vehicle and electrically connected to the navigation and positioning unit to: determine a reversing reference path, and establish a rigid body six-wheeled vehicle model about the intelligent vehicle and the virtual vehicle, convert the reversing reference path based on a point on the intelligent vehicle into a forward reference path based on a corresponding point on the virtual vehicle; reverse all reference heading angles of the reversing reference path to obtain a forward reference heading angle; calculate the front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle; calculate the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; calculate the steering dynamics compensation angle of the intelligent vehicle, and superimpose the steering dynamics compensation angle on the intelligent vehicle. The front wheel steering angle control amount of the vehicle is used to obtain the final front wheel steering angle control amount, and the final front wheel steering angle control amount is used to generate a front wheel steering instruction and a driving braking instruction; a steering unit is installed on the chassis and is electrically connected to the computing unit to execute the front wheel steering instruction, and the steering unit includes: a steering controller and a steering mechanism, wherein: the steering controller is used to receive the front wheel steering instruction, control the steering mechanism to rotate and generate steering state information to send to the computing unit, and the steering mechanism is used to drive the front wheels of the vehicle to achieve steering; a driving braking unit is installed on the chassis and is electrically connected to the computing unit to execute the driving braking instruction, and the driving braking unit includes: a driving braking controller and a driving braking actuator, wherein: the driving braking controller is used to receive the driving braking instruction, control the driving braking actuator to execute, and generate driving braking state information to send to the computing unit, and the driving braking actuator is used to drive the vehicle wheels to move forward or backward.

[0021] In one embodiment of the present invention, the device further includes: a perception unit, which is composed of at least one sensor selected from a camera, a laser radar, and a millimeter-wave radar installed on the outside of the vehicle body, and a sensor data conditioning circuit, for sensing the surrounding environment of the vehicle, determining the passable area behind the vehicle and sending it to the calculation unit to assist in determining the reversing reference path.

[0022] In one embodiment of the present invention, the computing unit 110 is connected and communicated with the steering unit and the driving braking unit via a CAN bus; wherein: the computing unit converts the front wheel steering instruction and the driving braking instruction into a first CAN message and a second CAN message respectively and sends them to the vehicle's wire-controlled chassis CAN bus, wherein the steering controller receives the first CAN message; and the driving braking controller receives the second CAN message.

[0023] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned reversing control method when executed by a processor.

[0024] Another aspect of the present invention provides a computer program product, which implements the steps of the above-mentioned reversing control method when executed by a processor.

[0025] It can be seen from the above scheme that the advantages of the present invention are:

[0026] The reversing control method of the intelligent vehicle disclosed in the present invention establishes a rigid six-wheel vehicle model about the intelligent vehicle and the virtual vehicle, converts the reversing reference path based on a point on the intelligent vehicle into a forward reference path based on the corresponding point on the virtual vehicle and determines the forward reference heading angle; then, according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle, the front wheel steering angle control amount of the virtual vehicle is calculated; according to the front wheel steering angle control amount of the virtual vehicle, the front wheel steering angle control amount of the intelligent vehicle is calculated; and the steering dynamics compensation angle of the intelligent vehicle is calculated, and the steering dynamics compensation angle is superimposed on the front wheel steering angle control amount of the intelligent vehicle to obtain the final front wheel steering angle control amount. This method can solve the problems of poor reversing control accuracy, oscillation or poor real-time performance of intelligent vehicles in related technologies, and realize accurate and real-time reversing control of intelligent vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram showing the structure of a reversing control device for an intelligent vehicle provided by an embodiment of the present invention is shown;

[0028] Figure 2 The schematic diagram of the rigid body six-wheel vehicle model is shown;

[0029] Figure 3 A schematic diagram of the kinematic model of a rigid six-wheeled vehicle turning is shown;

[0030] Figure 4 A schematic diagram of the overall flow of a reversing control method for an intelligent vehicle provided in another embodiment of the present invention is shown.

[0031] Reference numerals:

[0032] 100: Intelligent vehicles;

[0033] 110: computing unit;

[0034] 120: perception unit;

[0035] 130: navigation and positioning unit;

[0036] 140: body;

[0037] 150: steering unit;

[0038] 160: driving brake unit;

[0039] 170: front axle;

[0040] 171: left front wheel;

[0041] 172: right front wheel;

[0042] 180: rear axle;

[0043] 181: left rear wheel;

[0044] 182: right rear wheel;

[0045] 190: chassis;

[0046] 200: virtual vehicle;

[0047] 270: virtual front axle;

[0048] 271: virtual right front wheel;

[0049] 272: virtual left front wheel;

[0050] 310: reversing reference path;

[0051] 320: forward reference path;

[0052] 311: reverse reference heading angle;

[0053] 321: forward reference heading angle;

[0054] 411: front wheel;

[0055] 412: rear wheel;

[0056] 421: Virtual front wheel. DETAILED DESCRIPTION

[0057] In order to make the above features and effects of the present invention more clearly and understandably described, embodiments are given below and described in detail with reference to the accompanying drawings. This specification discloses one or more embodiments that include the features of the present invention. The disclosed embodiments are only for illustration. The scope of protection of the present invention is not limited to the disclosed embodiments, and the present invention is defined by the attached claims.

[0058] It should be noted that, in this application, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0059] Without more constraints, an element defined by the phrase "comprising a..." does not exclude the existence of other identical elements in the process, method, article or apparatus comprising the element.

[0060] Please refer to Figure 1 , which shows a schematic structural diagram of a reversing control device for an intelligent vehicle 100 provided in one embodiment of the present invention.

[0061] Intelligent vehicles integrate multiple functions such as environmental perception, planning and decision-making, and multi-level assisted driving. They use a variety of technologies such as computers, modern sensors, information fusion, communications, artificial intelligence, and automatic control.

[0062] See also Figure 1 As shown in FIG. 1 , the smart vehicle 100 includes a body 140, a chassis 190, a front axle 170 mounted on the chassis 190 (with two ends of the front axle 170 mounted on the front axle 170). Figure 2 The left front wheel 171 and the right front wheel 172 shown in the figure), the rear axle 180 installed on the chassis (the rear axle 180 is installed at both ends Figure 2 The reverse control device comprises: a computing unit 110, a sensing unit 120, a navigation positioning unit 130, a steering unit 150 and a driving brake unit 160. The computing unit 110 and the navigation positioning unit 130 are fixed to the vehicle body 140 or the chassis 190, and the steering unit 150 and the driving brake unit 160 are fixed to the chassis 190.

[0063] Specifically, the navigation and positioning unit 130 is used to collect the current state of the intelligent vehicle and transmit it to the computing unit 110. The current state includes the vehicle's own posture and current vehicle speed. In practice, the navigation and positioning unit 130 is usually composed of an inertial element, a satellite positioning element, and a conditioning circuit.

[0064] The sensing unit 120 is used to sense the surrounding environment of the vehicle, determine the passable area behind the vehicle and send it to the calculation unit 110 to assist in determining the reverse reference path. In practice, the sensing unit 120 is usually composed of at least one sensor selected from a camera, a laser radar, and a millimeter-wave radar installed on the outside of the vehicle body, and a sensor data conditioning circuit.

[0065] The computing unit 110 is electrically connected to the navigation and positioning unit 130, the sensing unit 120, the steering unit 150 and the driving and braking unit 160. In practice, the computing unit is usually composed of a processor, a storage element and a circuit board, and the processor and the storage element communicate through a high-speed bus. The processor is used for calculation, and the storage element is used to store programs and data. There are multiple I\O interfaces on the circuit board for communicating with other devices. In a specific implementation, as an embodiment, the processor may include one or more CPUs. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions). The storage element is used to store the software program that executes the reversing control strategy of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the following method embodiment, which is not specifically introduced here.

[0066] Specifically, in this embodiment, the calculation unit 110 is the core unit of the reversing control device, which is mainly used to determine the various processes of the reversing control strategy, including: determining the reversing reference path; and establishing a rigid six-wheeled vehicle model about the intelligent vehicle and the virtual vehicle, converting the reversing reference path based on a point on the intelligent vehicle into a forward reference path based on the corresponding point on the virtual vehicle; reversing all the reference heading angles of the reversing reference path to obtain a forward reference heading angle; calculating the front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle; calculating the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; calculating the steering dynamics compensation angle of the intelligent vehicle, and superimposing the steering dynamics compensation angle to the front wheel steering angle control amount of the intelligent vehicle to obtain the final front wheel steering angle control amount, and generating the front wheel steering instruction and the driving braking instruction from the final front wheel steering angle control amount. The specific technical scheme of the reversing control strategy of the calculation unit will be described in detail in the subsequent reversing control method, and only a brief introduction is given here.

[0067] The steering unit 150 is used to receive the front wheel steering command transmitted by the computing unit 110 for execution. In practice, the steering unit 150 generally includes: a steering controller and a steering mechanism, wherein: the steering controller is used to receive the front wheel steering command to control the steering mechanism to rotate and generate steering state information to send to the computing unit, and the steering mechanism is used to drive the front wheels of the vehicle to achieve steering.

[0068] The driving brake unit 160 is used to receive the driving brake command transmitted by the computing unit 110 for execution. In practice, the driving brake unit usually includes: a driving brake controller and a driving brake actuator, wherein: the driving brake controller is used to receive the driving brake command, control the driving brake actuator to execute, and generate driving brake state information to send to the computing unit, and the driving brake actuator is used to drive the vehicle wheels to move forward or backward, or to brake the vehicle to achieve precise reversing of the vehicle.

[0069] In addition, it should be noted that in this embodiment, the steering controller and the driving and braking controller are not limited to one controller, but can be a combination of two or more controllers. The steering mechanism and the driving and braking actuator are also a combination of multiple mechanisms.

[0070] In addition, in specific matters, the communication method between the computing unit 110 and the steering unit 150 and the driving brake unit 160 may adopt various communication methods such as CAN communication, Ethernet, direct physical connection, etc.

[0071] For example, in some embodiments, the computing unit 110 communicates with the steering unit 150 and the driving and braking unit 160 via a CAN bus. The computing unit converts the front wheel steering instruction and the driving and braking instruction into a first CAN message and a second CAN message respectively and sends them to the vehicle's wire-controlled chassis CAN bus. Wherein: the steering controller receives the first CAN message, controls the steering mechanism to rotate according to the first CAN message, generates steering state information and sends it to the computing unit, so that the steering mechanism drives the front wheels of the vehicle to achieve steering; the driving and braking controller receives the second CAN message, controls the driving and braking actuator to execute according to the second CAN message, and generates driving and braking state information and sends it to the computing unit, so that the driving and braking actuator drives the vehicle wheels to move forward or backward, or brakes the vehicle, so as to achieve precise reversing of the vehicle.

[0072] In some embodiments, the computing unit 110 communicates with the steering unit 150 and the driving and braking unit 160 via Ethernet. For a vehicle chassis that complies with the Ethernet communication protocol, the computing unit converts the front wheel steering instruction and the driving and braking instruction into a first Ethernet message and a second Ethernet message respectively and sends them to the Ethernet. Wherein: the steering controller receives the first Ethernet message, controls the steering mechanism to rotate according to the first Ethernet message, generates steering state information and sends it to the computing unit, so that the steering mechanism drives the front wheels of the vehicle to achieve steering; the driving and braking controller receives the second Ethernet message, controls the driving and braking actuator to execute according to the second Ethernet message, and generates driving and braking state information and sends it to the computing unit, so that the driving and braking actuator drives the vehicle wheels to move forward or backward, or brakes the vehicle, so as to achieve precise reversing of the vehicle.

[0073] In some embodiments, for a non-wire-controlled chassis, it is necessary to construct a direct physical connection between the computing unit 110 and the steering unit 150 and the drive braking unit 160, so that the computing unit 110 can directly send the front wheel steering instruction and the drive braking instruction to the steering controller and the drive braking controller respectively.

[0074] Using the above-mentioned intelligent vehicle and reversing control device, another embodiment of the present invention also discloses an intelligent vehicle reversing control method, referring to Figure 4 As shown in Figure 4 The overall flow chart of the reversing control method is shown.

[0075] The intelligent vehicle reversing control method specifically comprises the following steps:

[0076] Step S1, obtaining the current state and reversing reference path of the intelligent vehicle.

[0077] Specifically, the computing unit obtains a reversing instruction and reversing starts. The reversing instruction is obtained by at least one of the vehicle's autonomous decision and a human sending a remote control instruction. The computing unit obtains the current state of the intelligent vehicle collected by the navigation and positioning unit, including the vehicle's own posture, current speed and other information, and determines the reversing reference path. The reversing reference path can be obtained by one or more of the following methods, for example: extracting a section of the stored global path as a reversing reference path; when the vehicle is traveling forward, the path passed is stored in real time, and when reversing is required, one section is taken as a reversing reference path; using the perception unit to perceive the passable area behind the vehicle, and using the passable area behind the vehicle to plan a reversing reference path in real time.

[0078] Step S2: Establish a rigid six-wheel vehicle model for the intelligent vehicle and the virtual vehicle, and convert a reverse reference path based on a point on the intelligent vehicle into a forward reference path based on a corresponding point on the virtual vehicle.

[0079] Please refer to Figure 2 , which shows a schematic diagram of the principle of a rigid six-wheel vehicle model. The method of establishing a rigid six-wheel vehicle model is specifically as follows: the intelligent vehicle 100 and the virtual vehicle 200 are fixedly connected, wherein: the virtual vehicle 200 and the intelligent vehicle 100 are configured to share a rear axle 180, and the orientations differ by 180°. The left rear wheel 181 of the intelligent vehicle 100 is configured to constitute the right rear wheel of the virtual vehicle 200, and the right rear wheel 182 of the intelligent vehicle 100 is configured to constitute the left rear wheel of the virtual vehicle 200; the front axle of the virtual vehicle 200 is configured to be a virtual front axle 270, and a virtual right front wheel 271 and a virtual left front wheel 272 are installed at both ends of the virtual front axle 270. The distance between the virtual right front wheel 271 and the virtual left front wheel 272 is the virtual front wheel track, and the virtual front wheel track is the same as the real front wheel track, and the real front wheel track is the distance between the right front wheel and the left front wheel of the intelligent vehicle 100.

[0080] In addition, the actual wheelbase The distance between the front axle 170 and the rear axle 180 of the smart vehicle is constant. Configure the virtual wheelbase is the distance between the virtual front axle 270 and the rear axle 180, which is constant. Can be selected arbitrarily, preferably, The vehicle center line of the virtual vehicle and the vehicle center line of the intelligent vehicle are located on the same straight line, and the vehicle center line is a straight line formed by the center of the front axle and the center of the rear axle of the virtual vehicle or the intelligent vehicle, that is, the center of the front axle 170, the center of the rear axle 180, and the center of the virtual front axle 270 of the intelligent vehicle are located on the same straight line, which is the vehicle center line.

[0081] In addition, the current state of the configured virtual vehicle is the same as the current state of the intelligent vehicle, including the vehicle's own posture and current speed of the virtual vehicle are consistent with those of the intelligent vehicle.

[0082] Through the above constraints, the relative positions of the intelligent vehicle 100 and the virtual vehicle 200 remain unchanged, forming a virtual rigid body with six wheels, that is, a rigid six-wheel vehicle model of the combination of the intelligent vehicle 100 and the virtual vehicle 200.

[0083] Further references Figure 2As shown in the figure, it is shown that the reversing reference path 310 of the intelligent vehicle 100 is converted into the forward reference path 320 of the virtual vehicle 200 through the rigid body six-wheel vehicle model, and the reversing reference heading angle 311 is converted into the forward reference heading angle 321 of the virtual vehicle 200. Specifically, a first point M on the intelligent vehicle 100 is selected, and the first point is an arbitrary point, and the reversing reference path 310 of the first point is determined; the corresponding point on the virtual vehicle 200 is selected as the second point N, and the second point satisfies the following conditions: the vertical distance from the second point N to the center line of the vehicle is equal to the vertical distance from the first point N to the center line of the vehicle; the ratio of the distance from the second point N to the rear axle 180 to the distance from the first point M to the rear axle 180 is equal to the virtual wheelbase The actual wheelbase The ratio of , where the virtual wheelbase is the distance between the front and rear axles of the virtual vehicle, the real wheelbase is the distance between the front axle and the rear axle of the smart vehicle. Assuming that the smart vehicle 100 ideally reverses according to the reverse reference path 310, the first point M always keeps moving on the reverse reference path 310, and the heading angle of the vehicle is always consistent with the reference heading angle 311. According to the geometric relationship between the second point N and the first point M in the rigid six-wheel vehicle model, the path passed by the second point N is the forward reference path 320.

[0084] Step S3: Reverse all reference heading angles of the reversing reference path to obtain a forward reference heading angle.

[0085] The reference heading angle can be obtained by calculating the tangent direction of each point on the reverse reference path. Then, all the reference heading angles of the reverse reference path are reversed (ie, offset by 180°) to obtain the forward reference heading angle 321.

[0086] Step S4, calculating the front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle.

[0087] In this embodiment, a lateral control algorithm of a two-degree-of-freedom kinematic model is used to calculate the front wheel steering angle control amount of the virtual vehicle. Figure 3 As shown in the figure, the center of the virtual front wheel 421 and the center of the rear wheel 412 are rigidly connected, they can move forward and backward, and the virtual front wheel 421 is responsible for steering. Together, they constitute a two-degree-of-freedom kinematic model, also known as a bicycle model. The forward reference path 320, the forward reference heading angle 321, and the current state of the virtual vehicle are used as inputs for lateral control of the two-degree-of-freedom kinematic model, and the front wheel steering angle control value of the virtual vehicle is output. The current state of the virtual vehicle is the same as that of the intelligent vehicle, including the vehicle's own position and current speed.

[0088] The vehicle lateral tracking control method includes the following feedback control calculation formula, and the front wheel steering angle control amount of the virtual vehicle is expressed as:

[0089]

[0090] in, represents the front wheel steering angle control amount of the virtual vehicle 200, represents the current speed of the virtual vehicle 200; represents the lateral error of the virtual vehicle 200, represents the heading angle error of the virtual vehicle 200, represents the lateral gain coefficient.

[0091] Step S5: Calculate the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle.

[0092] Specifically, the relationship between the front wheel steering angle control amount of the virtual vehicle and the front wheel steering angle control amount of the intelligent vehicle is determined by establishing a kinematic model of the rigid six-wheel vehicle turning.

[0093] refer to Figure 3 As shown, Figure 3 The schematic diagram of the kinematic model of the rigid body six-wheel vehicle turning is shown. Among them, A, B, C, D, E, F, and H are the center points of the left front wheel 171, the right front wheel 172, the left rear wheel 181, the right rear wheel 182, the virtual right front wheel 271, the virtual left front wheel 272, and the center point of the rear axle 180 (i.e., the center position of the two rear wheels). Since the steering angles and kinematic results of the left front wheel 171 and the right front wheel 172 follow the Ackerman trapezoid principle, they can be characterized by the steering of a front wheel 411 without width located at the center of the front axle. G is the center of the front wheel 411. The vertical line of the wheel surface of the left front wheel 171 passing through A, the vertical line of the wheel surface of the right front wheel 172 passing through B, the vertical line of the wheel surface of the front wheel 411 passing through G, and the extended line of DC intersect at the rotation center O of the intelligent vehicle. Since the steering angles and kinematic results of the virtual right front wheel 271 and the virtual left front wheel 272 follow the Ackerman trapezoid principle, they can be characterized by the steering of a virtual front wheel 421 without width located at the center of the virtual front axle. I is the center of the virtual front wheel 421, and the turning radius R is the distance between the rotation center O of the intelligent vehicle and the center point H of the rear axle. is the angle between line segment OH and line segment OG, is the angle between line segment OH and line segment OI. The vertical line through the virtual right front wheel 271 of E, the vertical line through the virtual left front wheel 272 of F, the vertical line through the virtual front wheel 421 of I and the extended line DC intersect at the rotation center O' of the virtual vehicle. And because the intelligent vehicle and the virtual vehicle form a rigid six-wheel vehicle, based on kinematic considerations, in order to prevent the wheels from slipping, the rotation center O of the intelligent vehicle coincides with the rotation center O' of the virtual vehicle.

[0094] Therefore, the front wheel steering angle control amount of the intelligent vehicle 100 is The virtual front wheel steering angle control amount of the virtual vehicle 200 Satisfies the following formula:

[0095]

[0096] in, represents the front wheel steering angle control value of the intelligent vehicle, Represents the front wheel steering angle control amount of the virtual vehicle; is the actual wheelbase, is the virtual wheelbase, where is the distance between the front and rear axles of the virtual vehicle, the real wheelbase is the distance between the front axle and the rear axle of the smart vehicle.

[0097] Step S6: Calculate the steering dynamics compensation angle of the intelligent vehicle, and add the steering dynamics compensation angle to the front wheel steering angle control amount of the intelligent vehicle to obtain a final front wheel steering angle control amount.

[0098] Since the kinematic model does not consider the effects of tire force, deformation, slip, etc., the control algorithm based on the kinematic model is usually prone to understeering when the vehicle is turning with a large curvature in forward driving; it is prone to oversteering when reversing with a large curvature, and even causes control system oscillation. Therefore, it is necessary to add a dynamic compensation term to the control quantity. Specifically, according to the distance from the center of gravity of the intelligent vehicle to the rear axle , Actual wheelbase , the curvature of the reversing reference path , Current vehicle speed ,quality The steering dynamics compensation angle of the intelligent vehicle is calculated based on the information. It is expressed as: ,in: is the distance from the center of gravity of the smart vehicle to the rear axle, is the curvature of the reversing reference path, For the quality of smart vehicles, Indicates the current speed of the smart vehicle. represents the tire cornering stiffness of the smart vehicle, Represents the real wheelbase, which is the distance between the front axle and the rear axle of the smart vehicle.

[0099] Then, the front wheel steering angle control value of the intelligent vehicle Subtract the steering dynamics compensation angle , the final front wheel steering angle control value can be obtained as: ,in: represents the final front wheel steering angle control value, Represents the front wheel steering angle control value of the intelligent vehicle.

[0100] Step S7: generating a front wheel steering instruction and a driving braking instruction from the final front wheel steering angle control amount and sending them to the steering unit and the driving braking unit; the steering unit executes the front wheel steering instruction, and the driving braking unit executes the driving braking instruction.

[0101] Specifically, the steering controller of the steering unit 150 receives the front wheel steering command, controls the steering mechanism to rotate, generates steering state information and sends it to the computing unit, and drives the front wheels of the vehicle to steer. The driving brake controller of the driving brake unit 160 receives the driving brake command, controls the driving brake actuator to execute, generates driving brake state information and sends it to the computing unit; the driving brake actuator drives the vehicle wheels to move forward or backward, or brakes the vehicle, so as to achieve precise reversing of the vehicle.

[0102] Finally, the computing unit 110 obtains the position information of the smart vehicle 100 from the navigation positioning unit 130, and detects whether the smart vehicle 100 has reversed to the predetermined position. If it has, the reverse is stopped, the steering mechanism is returned to the normal position, and the reverse is completed; if not, the above steps S1-S7 are re-executed until the vehicle is accurately reversed to the predetermined position. The above process is repeated continuously with the control cycle as a cycle to obtain continuous control instructions.

[0103] In summary, the reversing control method of the intelligent vehicle disclosed in the present invention, by establishing a rigid six-wheeled vehicle model about the intelligent vehicle and the virtual vehicle, converts the reversing reference path based on a point on the intelligent vehicle into a forward reference path based on the corresponding point on the virtual vehicle and determines the forward reference heading angle; then, according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle, the front wheel steering angle control amount of the virtual vehicle is calculated; according to the front wheel steering angle control amount of the virtual vehicle, the front wheel steering angle control amount of the intelligent vehicle is calculated; and the steering dynamics compensation angle of the intelligent vehicle is calculated, and the steering dynamics compensation angle is superimposed on the front wheel steering angle control amount of the intelligent vehicle to obtain the final front wheel steering angle control amount. This method can solve the problems of poor reversing control accuracy, oscillation or poor real-time performance of intelligent vehicles in related technologies, and realize accurate and real-time reversing control of intelligent vehicles.

[0104] In addition, the present invention also provides a computer program product in one embodiment, which includes a computer program. The computer program can be stored in a readable storage medium. When the computer program is executed by a processor, the computer can execute the reversing control methods provided by the above methods.

[0105] The present invention also proposes a storage medium in another embodiment for storing a computer program for executing the reversing control method. It should be understood that the storage medium in the embodiment of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0106] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. A reversing control method for an intelligent vehicle, characterized in that: Include: Obtain the current state and reversing reference path of the intelligent vehicle; A rigid six-wheeled vehicle model of an intelligent vehicle and a virtual vehicle is established, and a reverse reference path based on a point on the intelligent vehicle is converted into a forward reference path based on a corresponding point on the virtual vehicle; Reverse all the reference heading angles of the reversing reference path to obtain a forward reference heading angle; Calculating a front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle; Calculate the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; Calculating a steering dynamics compensation angle of the intelligent vehicle, and adding the steering dynamics compensation angle to a front wheel steering angle control amount of the intelligent vehicle to obtain a final front wheel steering angle control amount; The final front wheel steering angle control amount generates a front wheel steering instruction and a driving braking instruction which are sent to a steering unit and a driving braking unit. The steering unit executes the front wheel steering instruction, and the driving braking unit executes the driving braking instruction.

2. The method according to claim 1, characterized in that The method for establishing the rigid body six-wheel vehicle model comprises: The smart vehicle and the virtual vehicle are connected, wherein: The virtual vehicle and the smart vehicle share the same rear axle, with their orientations differing by 180°; The left rear wheel of the intelligent vehicle is configured to constitute the right rear wheel of the virtual vehicle, and the right rear wheel of the intelligent vehicle is configured to constitute the left rear wheel of the virtual vehicle; The front axle of the virtual vehicle is configured as a virtual front axle, a virtual right front wheel and a virtual left front wheel are installed at both ends of the virtual front axle, the distance between the virtual right front wheel and the virtual left front wheel is the virtual front wheel track, the virtual front wheel track is the same as the real front wheel track, and the real front wheel track is the distance between the right front wheel and the left front wheel of the smart vehicle; The vehicle center line of the virtual vehicle and the vehicle center line of the intelligent vehicle are configured to be located on the same straight line.

3. The method according to claim 2, characterized in that The specific method of converting the reverse reference path based on a point on the intelligent vehicle into the forward reference path based on the corresponding point on the virtual vehicle is: Selecting a first point on the intelligent vehicle and determining a reversing reference path for the first point; The corresponding point on the virtual vehicle is selected as the second point, and the second point satisfies the following conditions: The vertical distance between the second point and the centerline of the vehicle is equal to the vertical distance between the first point and the centerline of the vehicle; The ratio of the distance from the second point to the rear axle to the distance from the first point to the rear axle is equal to the ratio of the virtual wheelbase to the real wheelbase, wherein the virtual wheelbase is the distance between the front axle and the rear axle of the virtual vehicle, and the real wheelbase is the distance between the front axle and the rear axle of the intelligent vehicle; Assuming that the intelligent vehicle reverses according to the reversing reference path, the first point always keeps moving on the reversing reference path, and the heading angle of the vehicle is always consistent with the reference heading angle. According to the geometric relationship between the second point and the first point in the rigid six-wheel vehicle model, the path passed by the second point is the forward reference path.

4. The method according to claim 1, characterized in that: The lateral control algorithm of the two-degree-of-freedom kinematic model is used to calculate the front wheel steering angle control amount of the virtual vehicle, including: The virtual front wheel center and the rear wheel center are configured to be rigidly connected, and the front wheel is responsible for steering, which together constitute a two-degree-of-freedom kinematic model; The forward reference path, the forward reference heading angle, and the current state of the virtual vehicle are used as inputs of the two-degree-of-freedom kinematic model for lateral control, and a front wheel steering angle control value of the virtual vehicle is output, wherein the current state of the virtual vehicle is the same as the current state of the intelligent vehicle, including the vehicle's own posture and current vehicle speed; The front wheel steering angle control value of the virtual vehicle is expressed as: in, represents the front wheel steering angle control amount of the virtual vehicle, Indicates the current speed of the virtual vehicle; represents the lateral error of the virtual vehicle, represents the heading angle error of the virtual vehicle, represents the lateral gain coefficient.

5. The method according to claim 4, characterized in that The front wheel steering angle control quantity of the intelligent vehicle is expressed as: in, represents the front wheel steering angle control value of the intelligent vehicle, Represents the front wheel steering angle control amount of the virtual vehicle; is the actual wheelbase, is the virtual wheelbase, where the virtual wheelbase is the distance between the front axle and the rear axle of the virtual vehicle, and the real wheelbase is the distance between the front axle and the rear axle of the intelligent vehicle.

6. The method according to claim 5, characterized in that The front wheel steering angle control amount of the intelligent vehicle is subtracted from the steering dynamics compensation angle to obtain the final front wheel steering angle control amount: in, represents the final front wheel steering angle control value, Indicates the front wheel steering angle control value of the intelligent vehicle; represents the steering dynamics compensation angle, and ,in: is the distance from the center of gravity of the smart vehicle to the rear axle, is the curvature of the reversing reference path, For the quality of smart vehicles, Indicates the current speed of the smart vehicle. represents the tire cornering stiffness of the smart vehicle, Represents the real wheelbase, which is the distance between the front axle and the rear axle of the smart vehicle.

7. A reversing control device for an intelligent vehicle, characterized in that: Include: A navigation and positioning unit is installed on the body or chassis of the smart vehicle to collect the current status of the smart vehicle; The computing unit is installed on the body or chassis of the intelligent vehicle and is electrically connected to the navigation and positioning unit to: Determine the reversing reference path, and A rigid six-wheeled vehicle model of an intelligent vehicle and a virtual vehicle is established, and a reverse reference path based on a point on the intelligent vehicle is converted into a forward reference path based on a corresponding point on the virtual vehicle; Reverse all the reference heading angles of the reversing reference path to obtain a forward reference heading angle; Calculating a front wheel steering angle control amount of the virtual vehicle according to the forward reference path, the forward reference heading angle, and the current state of the virtual vehicle; Calculate the front wheel steering angle control amount of the intelligent vehicle according to the front wheel steering angle control amount of the virtual vehicle; Calculating the steering dynamics compensation angle of the intelligent vehicle, and superimposing the steering dynamics compensation angle on the front wheel steering angle control amount of the intelligent vehicle to obtain a final front wheel steering angle control amount, and generating a front wheel steering instruction and a driving braking instruction from the final front wheel steering angle control amount; A steering unit is mounted on the chassis and electrically connected to the computing unit to execute the front wheel steering command, and the steering unit comprises: a steering controller and a steering mechanism, wherein: the steering controller is used to receive the front wheel steering command to control the steering mechanism to rotate and generate steering state information to send to the computing unit, and the steering mechanism is used to drive the front wheels of the vehicle to achieve steering; A driving brake unit is installed on the chassis and electrically connected to the computing unit to execute the driving brake command, and the driving brake unit includes: a driving brake controller and a driving brake actuator, wherein: the driving brake controller is used to receive the driving brake command, control the driving brake actuator to execute, and generate driving brake status information to send to the computing unit, and the driving brake actuator is used to drive the vehicle wheels to move forward or backward.

8. The reversing control device for an intelligent vehicle according to claim 7, characterized in that: Also includes: The perception unit is composed of at least one sensor selected from the group consisting of a camera, a laser radar, and a millimeter-wave radar installed on the outside of the vehicle body, and a sensor data conditioning circuit, and is used to perceive the vehicle's surrounding environment, determine the passable area behind the vehicle, and send it to the calculation unit to assist in determining the reversing reference path.

9. The reversing control device for an intelligent vehicle according to claim 7, characterized in that: The calculation unit is connected and communicated with the steering unit and the driving and braking unit via a CAN bus; wherein: the calculation unit converts the front wheel steering instruction and the driving and braking instruction into a first CAN message and a second CAN message respectively and sends them to the vehicle's wire-controlled chassis CAN bus, wherein the steering controller receives the first CAN message; and the driving and braking controller receives the second CAN message.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images