A positioning method and device based on parking space recognition

Abstract

The application relates to the technical field of parking space positioning, in particular to a positioning method and device based on parking space recognition, which are used for solving the problem that the prior art depends on GPS signals or maps. The method comprises the following steps: S1, starting; S2, wheel speed direct positioning; S3, judging whether a target parking space is received; if the target parking space is not received, directly outputting a wheel speed direct positioning result and returning to S2 to perform wheel speed direct positioning again; if the target parking space is received, fusing target parking space data to perform fusion positioning, outputting a fusion positioning result and returning to S2 to perform wheel speed direct positioning again. The application provides a low-cost high-precision positioning scheme which has low requirements on a perception algorithm and does not depend on a high-precision map. The automatic parking can be performed in an underground parking lot without GPS signals, and the robustness and precision of positioning are improved through the fusion positioning mode.

Description

Technical Field

[0001] This invention relates to the field of parking space positioning technology, and in particular to a positioning method and device based on parking space identification. Background Technology

[0002] In underground parking lots, GPS signals are weak, making normal base station positioning impossible. Therefore, local positioning accuracy is particularly important, especially for automatic parking scenarios. In local positioning, due to accumulated sensor errors and external disturbances, errors in DR (radio frequency response) calculations based on sensors such as wheel speedometers and IMUs can accumulate and fail to converge.

[0003] Therefore, external input is needed for error correction. Existing technology CN202210627066.8 discloses a positioning map construction method for HPA and a vehicle parking method based on HPA. This scheme is a map-based positioning method, requiring map construction before self-positioning correction of the vehicle, which demands high computing power and high map accuracy. Overall, the performance requirements for both the sensor and domain control are high.

[0004] The prior art CN202110609565.X discloses an autonomous driving method for automatic parking and charging / swapping of electric vehicles. It uses a pre-built high-precision map of the parking lot. After the vehicle enters the selected parking lot, the high-precision map of the parking lot is loaded according to the vehicle's GPS signal. This scheme is a typical high-precision map scheme, which requires the preparation of a high-precision map in advance. Moreover, in places such as underground parking lots, the GPS signal cannot work properly, and it cannot work properly through high-precision positioning.

[0005] Existing technology CN202011177574.8 discloses an automatic parking method and apparatus. This scheme is a purely vision-based approach, parking by continuously recalculating the relative position of the vehicle to the parking space. This scheme heavily relies on the accuracy of the visual perception algorithm, and any severe interference during the parking process will directly affect the positioning result. It has extremely poor anti-interference capability, requires good ambient lighting, and places extremely high demands on the computing power of the camera sensor and the computational unit domain control of the perception algorithm. Summary of the Invention

[0006] In view of this, the purpose of this invention is to propose a positioning method and device based on parking space recognition, so as to solve the problem of existing technologies relying on GPS signals or maps.

[0007] To achieve the above objectives, the present invention provides a positioning method based on parking space recognition, characterized in that it includes...

[0008] S1, Start;

[0009] S2, direct wheel speed positioning;

[0010] S3, determine whether the target parking space has been received;

[0011] If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again;

[0012] If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again.

[0013] As a further improvement to this application, wheel speed direct positioning includes

[0014] Establish a wheel positioning coordinate system with the rear axle center of the vehicle as the origin, the direction pointing towards the front of the vehicle as the positive x-axis, the direction perpendicular to the x-axis pointing towards the left rear wheel as the positive y-axis, the direction perpendicular to the x-axis and y-axis pointing upwards as the positive z-axis, and the angle between the direction of the front of the vehicle and the x-axis as the attitude angle θ.

[0015] A vehicle kinematic model was constructed using a two-wheeled bicycle model;

[0016] Obtain the steering wheel angle and wheel speeds of both wheels, and input them into the vehicle kinematics model;

[0017] Obtain the coefficients K used, and the vehicle's center of gravity slip angle β at time t. t The vehicle's steering angular velocity at time t Vehicle center of mass trajectory velocity at time t Position data of the vehicle's center of mass at time t (X′) t ,Y′ t ,θ′ t ) and the positioning data (X) of the rear axle center of the vehicle at time t. t ,Y t ,θ t ).

[0018] The coefficient K is:

[0019]

[0020] The vehicle's center of gravity slip angle β at time t t :

[0021]

[0022] The vehicle steering angular velocity at time t

[0023]

[0024] k f k r These are the lateral stiffness coefficients of the front and rear tires, respectively, and α is the steering angle. f and αr These are the front and rear wheel deflection angles, v is the velocity at the vehicle's center of gravity, and m is the vehicle's mass. x and v y These are the decompositions of v in the x and y directions of the vehicle coordinate system, respectively; l f and l r These are the distances from the vehicle's center of gravity to the front and rear axles, respectively; β is the slip angle, and ω is the distance from the vehicle's center of gravity to the front and rear axles, respectively. r Rotational speed in the yaw direction. Let be the vehicle's steering angular velocity at time t. Let α be the vehicle speed output at time t. t It is the front wheel steering angle, β t Let t be the vehicle's center of gravity slip angle at time t, and K be the coefficient used in the calculation.

[0025] Obtain the trajectory velocity of the vehicle's center of mass at time t. and steering angular velocity

[0026]

[0027] Obtain the vehicle's centroid positioning data (X′) at time t. t ,Y′ t ,θ′ t The calculation is as follows:

[0028]

[0029] Obtain the positioning data (X) at the center of the rear axle of the vehicle at time t. t ,Y t ,θ t ):

[0030]

[0031] k f k r These are the front and rear tire lateral stiffness coefficients, I z Let α be the vehicle's moment of inertia about the z-axis, and α be the steering angle. f and α r These are the front and rear wheel deflection angles, respectively; v is the velocity at the vehicle's center of gravity. x and v y These are the decompositions of v in the x and y directions of the vehicle coordinate system, respectively; l f and l r These are the distances from the vehicle's center of gravity to the front and rear axles, respectively; β is the slip angle, and ω is the distance from the vehicle's center of gravity to the front and rear axles, respectively. r Rotational speed in the yaw direction. Let be the vehicle's steering angular velocity at time t. Let α be the vehicle speed output at time t. tIt is the front wheel steering angle, Δt is the time interval between time t-1 and time t; at time t=0, (X′ t ,Y′ t ,θ′ t )=(l r ,0,0).

[0032] As a further improvement to this application, the wheel speed direct positioning is obtained through a wheel speed positioning device.

[0033] As a further improvement to this application, the fusion positioning includes

[0034] The coordinates of points 1 and 2 of the target parking space in the vehicle coordinate system are obtained as (x1, y1) and (x2, y2), respectively. Points 1 and 2 are the two interior corners of the target parking space that are closest to the vehicle. The coordinate changes of points 1 and 2 are used to perform fusion positioning.

[0035] As a further improvement to this application, the fusion positioning includes

[0036] t = t p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt .

[0037] As a further improvement to this application, the fusion positioning includes

[0038] t = t p At time 1, the coordinates of the midpoint between points 1 and 2 are:

[0039] t>t p At time 1, the coordinates of the midpoint between points 1 and 2 are: but

[0040]

[0041] t = t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis.p

[0042]

[0043] t>t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis. pt

[0044]

[0045]

[0046] t>t p The position and attitude of the vehicle in the positioning coordinate system at any given time are:

[0047]

[0048] θ t =θ p -Δφ pt ;

[0049] forecast value Projected onto the pixel plane to obtain The projection residuals of the parking space corner points are obtained as follows:

[0050]

[0051] The pixel coordinates of the back projection of point 1 are related to the positioning data.

[0052] These are the pixel coordinates of the two-point back projection, which are related to the positioning data.

[0053] To receive the pixel coordinates of the target parking space 1,

[0054] The received pixel coordinates of point 2 in the target parking space;

[0055] Minimizing the reprojection error is achieved by minimizing the loss function:

[0056]

[0057] Where X is the sum of the reprojection residual and the position residual, r c For the appeal back projection residual, r v The residual is derived from the wheel speed recursion, as follows:

[0058] The wheel speed recursive residual r of four-wheel steering v :

[0059]

[0060] Where (X) t ,Y t ,θ t () represents the recursive result of the pure wheel velocity at time t. The wheel speed at time t is used to recursively calculate the optimization result of the target parking space.

[0061] A parking space recognition device, including

[0062] Start the module;

[0063] Direct positioning module for direct wheel speed positioning;

[0064] The fusion module is used to determine whether the target parking space has been received.

[0065] If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again;

[0066] If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again.

[0067] As a further improvement to this application, the judgment fusion module includes a calculation unit, used for determining the fusion at t = t p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt .

[0068] The beneficial effects of this invention are as follows: This application provides a low-cost, high-precision positioning solution that does not require sophisticated perception algorithms and does not rely on high-precision maps. It achieves this by fusing visual perception results with data from sensors such as wheel speedometers and IMUs. It enables automatic parking even in underground parking lots without GPS signals, and the fusion positioning method improves the robustness and accuracy of the positioning. Attached Figure Description

[0069] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0070] Figure 1 This is a flowchart illustrating a positioning method based on parking space recognition according to an embodiment of the present invention.

[0071] Figure 2 This is a schematic diagram of a two-wheeled bicycle model illustrating a positioning method based on parking space recognition according to an embodiment of the present invention.

[0072] Figure 3 This is a schematic diagram illustrating the relative position change of a parking space according to a positioning method based on parking space recognition in an embodiment of the present invention.

[0073] Figure 4 This is a schematic diagram of the fusion positioning process of a positioning method based on parking space recognition according to an embodiment of the present invention. Detailed Implementation

[0074] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0075] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0076] like Figure 1-3 As shown, a positioning method based on parking space recognition includes...

[0077] S1, Start;

[0078] S2, direct wheel speed positioning, wherein the direct wheel speed positioning is obtained through a wheel speed positioning device, including...

[0079] Establish a wheel positioning coordinate system with the rear axle center of the vehicle as the origin, the direction pointing towards the front of the vehicle as the positive x-axis, the direction perpendicular to the x-axis pointing towards the left rear wheel as the positive y-axis, the direction perpendicular to the x-axis and y-axis pointing upwards as the positive z-axis, and the angle between the direction of the front of the vehicle and the x-axis as the attitude angle θ.

[0080] A vehicle kinematic model was constructed using a two-wheeled bicycle model;

[0081] Obtain the steering wheel angle and wheel speeds of both wheels, and input them into the vehicle kinematics model;

[0082] Obtain the coefficients K used, and the vehicle's center of gravity slip angle β at time t. t The vehicle's steering angular velocity at time t Vehicle center of mass trajectory velocity at time t Position data of the vehicle's center of mass at time t (X′) t ,Y′ t ,θ′ t ) and the positioning data (X) of the rear axle center of the vehicle at time t. t ,Y t ,θ t ).

[0083] The coefficient K is:

[0084]

[0085] The vehicle's center of gravity slip angle β at time t t :

[0086]

[0087] The vehicle steering angular velocity at time t

[0088]

[0089] k f k r These are the lateral stiffness coefficients of the front and rear tires, respectively, and α is the steering angle. f and α r These are the front and rear wheel deflection angles, v is the velocity at the vehicle's center of gravity, and m is the vehicle's mass. x and v y These are the decompositions of v in the x and y directions of the vehicle coordinate system, respectively; l f and l r These are the distances from the vehicle's center of gravity to the front and rear axles, respectively; β is the slip angle, and ω is the slip angle. r Rotational speed in the yaw direction. Let be the vehicle's steering angular velocity at time t. Let α be the vehicle speed output at time t. t It is the front wheel steering angle, βt Let t be the vehicle's center of gravity slip angle at time t, and K be the coefficient used in the calculation.

[0090] Obtain the trajectory velocity of the vehicle's center of mass at time t. and steering angular velocity

[0091]

[0092] Obtain the vehicle's centroid positioning data (X′) at time t. t ,Y′ t ,θ′ t The calculation is as follows:

[0093]

[0094] Obtain the positioning data (X) at the center of the rear axle of the vehicle at time t. t ,Y t ,θ t ):

[0095]

[0096] k f k r These are the front and rear tire lateral stiffness coefficients, I z Let α be the vehicle's moment of inertia about the z-axis, and α be the steering angle. f and α r These are the front and rear wheel deflection angles, respectively; v is the velocity at the vehicle's center of gravity. x and v y These are the decompositions of v in the x and y directions of the vehicle coordinate system, respectively; l f and l r These are the distances from the vehicle's center of gravity to the front and rear axles, respectively; β is the slip angle, and ω is the distance from the vehicle's center of gravity to the front and rear axles, respectively. r Rotational speed in the yaw direction. Let be the vehicle's steering angular velocity at time t. Let α be the vehicle speed output at time t. t It is the front wheel steering angle, Δt is the time interval between time t-1 and time t; at time t=0, (X′ t ,Y′ t ,θ′ t )=(l r ,0,0).

[0097] S3, determine whether the target parking space has been received;

[0098] If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again;

[0099] If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again.

[0100] The fusion positioning includes

[0101] The coordinates of points 1 and 2 of the target parking space in the vehicle coordinate system are obtained as (x1, y1) and (x2, y2), respectively. Points 1 and 2 are the two interior corners of the target parking space that are closest to the vehicle. The coordinate changes of points 1 and 2 are used to perform fusion positioning.

[0102] The fusion positioning includes

[0103] t = t p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt .

[0104] The fusion positioning includes

[0105] t = t p At time 1, the coordinates of the midpoint between points 1 and 2 are:

[0106] t>t p At time 1, the coordinates of the midpoint between points 1 and 2 are: but

[0107]

[0108] t = t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis. p

[0109]

[0110] t>t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis. pt

[0111]

[0112]

[0113] t>t p The position and attitude of the vehicle in the positioning coordinate system at any given time are:

[0114]

[0115] θ t =θ p -Δφ pt ;

[0116] forecast value Projected onto the pixel plane to obtain The projection residuals of the parking space corner points are obtained as follows:

[0117]

[0118] The pixel coordinates of the back projection of point 1 are related to the positioning data.

[0119] These are the pixel coordinates of the two-point back projection, which are related to the positioning data.

[0120] To receive the pixel coordinates of the target parking space 1,

[0121] The received pixel coordinates of point 2 in the target parking space;

[0122] Minimizing the reprojection error is achieved by minimizing the loss function:

[0123]

[0124] Where X is the sum of the reprojection residual and the position residual, r c For the appeal back projection residual, r v The residual is derived from the wheel speed recursion, as follows:

[0125] The wheel speed recursive residual r of four-wheel steering v :

[0126]

[0127] Where (X) t ,Y t ,θ t () represents the recursive result of the pure wheel velocity at time t. The wheel speed at time t is used to recursively calculate the optimization result of the target parking space.

[0128] like Figure 4 As shown, points 1 and 2 are acquired and identified by camera capture. The perceived parking position is used to obtain the visually calculated position. The wheel is directly located by recursively obtaining the position through wheel speed measurement and IMU. Then, the method of minimizing the residual between the two is used to jointly optimize and obtain the optimized result.

[0129] A parking space recognition device, including

[0130] Start the module;

[0131] Direct positioning module for direct wheel speed positioning;

[0132] The fusion module is used to determine whether the target parking space has been received.

[0133] If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again;

[0134] If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again.

[0135] The judgment and fusion module includes a calculation unit, used for calculating the result at t=t. p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt .

[0136] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of the invention (including the claims) is limited to these examples; within the framework of the invention, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in the details for the sake of brevity.

[0137] This invention is intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A positioning method based on parking space recognition, characterized in that, include: S1. Begin; S2. Direct wheel speed positioning; S3. Determine if the target parking space has been received; If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again; If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again; The fusion positioning includes: The coordinates of points 1 and 2 of the target parking space in the vehicle coordinate system are obtained as (x1, y1) and (x2, y2), respectively. Points 1 and 2 are the two interior corner points of the target parking space that are closest to the vehicle. The coordinate changes of points 1 and 2 are used to perform fusion positioning. The fusion positioning also includes: t = t p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt ; The fusion positioning also includes: t = t p At time 1, the coordinates of the midpoint between points 1 and 2 are: ; t>t p At time 1, the coordinates of the midpoint between points 1 and 2 are: ,but ； t = t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis. p , ； t>t p At time 2, the vector from point 2 to point 1 makes an angle φ with the x-axis. pt , ； ； t>t p The position and attitude of the vehicle in the positioning coordinate system at any given time are: ； i t =θ p -Df pt ; forecast value Projected onto the pixel plane to obtain The projection residuals of the parking space corner points are obtained as follows: ； The pixel coordinates of the back projection of point 1 are related to the positioning data. These are the pixel coordinates of the two-point back projection, which are related to the positioning data. To receive the pixel coordinates of the target parking space 1, The received pixel coordinates of point 2 in the target parking space; Minimizing the reprojection error is achieved by minimizing the loss function: ， Where X is the sum of the reprojection residual and the position residual, r c For the appeal back projection residual, r v The residual is derived from the wheel speed recursion, as follows: The wheel speed recursive residual r of four-wheel steering v : ， Among them, (X) t ,Y t ,θ t () represents the recursive result of the pure wheel velocity at time t. The wheel speed at time t is used to recursively calculate the optimization result of the target parking space.

2. The positioning method based on parking space recognition according to claim 1, characterized in that, Direct wheel speed positioning includes: Establish a wheel positioning coordinate system with the rear axle center of the vehicle as the origin, the direction pointing towards the front of the vehicle as the positive x-axis, the direction perpendicular to the x-axis pointing towards the left rear wheel as the positive y-axis, the direction perpendicular to the x-axis and y-axis pointing upwards as the positive z-axis, and the angle between the direction of the front of the vehicle and the x-axis as the attitude angle θ. A vehicle kinematic model was constructed using a two-wheeled bicycle model. Obtain the steering wheel angle and wheel speeds of both wheels, and input them into the vehicle kinematics model; Obtain the coefficients K used, and the vehicle's center of gravity slip angle β at time t. t The vehicle's steering angular velocity at time t The velocity of the vehicle's center of mass trajectory at time t The vehicle's center of mass positioning data at time t (X′) t ,Y′ t ,θ′ t ) and the positioning data (X) of the rear axle center of the vehicle at time t. t ,Y t ,θ t ).

3. The positioning method based on parking space recognition according to claim 2, characterized in that, The coefficient K is: ； The vehicle's center of gravity slip angle β at time t t : ； The vehicle steering angular velocity at time t for, ； k f k r These are the lateral stiffness coefficients of the front and rear tires, respectively, and α is the steering angle. f and α r These are the front and rear wheel deflection angles, v is the velocity at the vehicle's center of gravity, and m is the vehicle's mass. x and v y These are the decompositions of v in the x and y directions of the vehicle coordinate system, respectively; l f and l r These are the distances from the vehicle's center of gravity to the front and rear axles, respectively; β is the slip angle, and ω is the distance from the vehicle's center of gravity to the front and rear axles, respectively. r Rotational speed in the yaw direction. Let be the vehicle's steering angular velocity at time t. Let α be the vehicle speed output at time t. t It is the front wheel steering angle, β t Let t be the vehicle's center of gravity slip angle at time t, and K be the coefficient used in the calculation.

4. The positioning method based on parking space recognition according to claim 2, characterized in that, The vehicle's center of mass trajectory velocity at time t : ； The turning angular velocity at time t : 。 5. The positioning method based on parking space recognition according to claim 2, characterized in that, The vehicle centroid positioning data (X′) at time t t ,Y′ t ,θ′ t The calculation is as follows: ； The positioning data (X) at the center of the rear axle of the vehicle at time t t ,Y t ,θ t ): ； I z Let X' be the moment of inertia of the vehicle about the z-axis, and Δt be the time interval between time t-1 and time t; at time t=0, (X′) t ,Y′ t ,θ′ t )=(l r ,0,0).

6. A positioning device based on parking space recognition, characterized in that... The method for implementing the parking space recognition-based positioning method according to any one of claims 1-5 includes: Start the module; Direct positioning module for direct wheel speed positioning; The fusion module is used to determine whether the target parking space has been received. If the target parking space is not received, the wheel speed direct positioning result is output directly and S2 is returned to perform wheel speed direct positioning again; If the target parking space is received, the target parking space data is merged for fusion positioning, the fusion positioning result is output and returned to S2 for direct wheel speed positioning again.

7. The positioning device based on parking space recognition according to claim 6, characterized in that, include: The judgment and fusion module includes a calculation unit for t = t p At time 1, the target parking space data is received for the first time. The coordinates of points 1 and 2 in the vehicle coordinate system are (x1, y1) and (x2, y2) respectively. The vehicle positioning data is (X... p ,Y p ,θ p ); t > t p At time 1, the coordinates of points 1 and 2 are (x... 1t ,y 1t ) and (x 2t ,y 2t Between these two moments, the vehicle moves while the parking space remains stationary. The relative positional relationship between the parking space and the vehicle changes, which is equivalent to the vehicle remaining stationary while the parking space moves in the vehicle's coordinate system. The transformation of the parking space coordinates is equivalent to performing a translation and a rotation transformation sequentially. Let the translation vector be T. pt Let the rotation angle be Δφ pt .

Images