A high-precision positioning-based integrated control method and system for berthing and sailing

Abstract

This invention proposes a parking and driving integrated control method and system based on high-precision positioning, relating to the field of automotive assisted driving technology. The method involves acquiring the vehicle's starting position and parking space information; calculating the first rear axle center coordinates of the starting position in the geodetic coordinate system using latitude and longitude; acquiring parking data corresponding to the parking space based on the parking space information; calculating the second rear axle center coordinates of the vehicle after parking based on the parking data; calculating dual-track control points corresponding to the tangent direction vectors of the first and second rear axle center coordinates; discretizing a Bezier curve with multiple control points using a preset step size to generate an initial parking trajectory point sequence; and smoothly interpolating the initial parking trajectory point sequence using a geometric model tracking algorithm to obtain the target parking trajectory sequence. This application helps to shorten parking operation time and improve the robustness of the parking and driving integrated control.

Description

Technical Field

[0001] This invention relates to the field of automotive driver assistance technology, and in particular to a driving and parking integrated control method and system based on high-precision positioning. Background Technology

[0002] The integrated driving and parking function of automobiles represents the mainstream direction of current autonomous driving technology development, providing users with a significantly enhanced intelligent experience. In certain closed operational scenarios, such as ports, industrial parks, and farms, the integrated driving and parking function is the optimal autonomous driving technology for achieving full automation of transportation, fixed-point operations, and charging processes, and it is currently the most promising autonomous driving technology for commercialization.

[0003] Chinese Patent CN111152782A discloses an automatic parking control system and method. The system includes a remote control system, a vehicle positioning system, and a vehicle control system. The remote control system includes an on-board terminal (T-Box) to acquire parking task information and the location information of the target parking space. The vehicle positioning system acquires the vehicle's location information. The vehicle control system includes an automatic driving controller and a vehicle controller. The automatic driving controller is connected to the on-board terminal (T-Box), the vehicle positioning system, and the vehicle controller, respectively. Based on the acquired vehicle information and the target parking space information, it calculates the vehicle's operating state parameters and parking trajectory, and transmits the calculation results to the vehicle controller. The vehicle controller transmits execution information to the vehicle's actuators to control the vehicle to move to the target parking space. However, this solution relies on the remote T-Box and the backend server for command issuance and scheduling, making it susceptible to network jitter, latency, or connection drops. Furthermore, it lacks planning constraint processing, often resulting in abrupt and uneven parking trajectories. Therefore, it is essential to provide a parking control method and system based on high-precision positioning to shorten parking operation time and improve the robustness of parking control. Summary of the Invention

[0004] In view of this, the present invention proposes a parking and driving integrated control method and system based on high-precision positioning. By obtaining the latitude and longitude of the vehicle's starting point and converting it to the rear axle center in the geodetic coordinate system, a geometric model tracking algorithm is used for smooth interpolation to eliminate trajectory inflection points and discontinuous slope changes, effectively shortening parking operation time and improving the robustness of the parking and driving integrated system.

[0005] This invention provides a high-precision positioning-based integrated navigation and parking control method, the method comprising:

[0006] Obtain the vehicle's starting point location and parking space information;

[0007] The coordinates of the center of the rear axle of the first vehicle in the geodetic coordinate system are calculated using latitude and longitude.

[0008] Based on the parking space information, obtain the parking data corresponding to the parking space, and calculate the center coordinates of the second rear axle of the vehicle after it is parked based on the parking data.

[0009] Based on the tangent direction vectors corresponding to the rear axle center coordinates of the first vehicle and the rear axle center coordinates of the second vehicle, calculate the dual trajectory control points corresponding to the tangent direction vectors.

[0010] Discretize the Bézier curve with multiple control points using a preset step size to generate an initial parking trajectory point sequence;

[0011] The initial parking trajectory point sequence is smoothly interpolated using a geometric model tracking algorithm to obtain the target parking trajectory sequence.

[0012] Based on the above technical solutions, preferably, the step of calculating the center coordinates of the second rear axle of the vehicle after parking based on the parking data specifically includes:

[0013] Based on the coordinates of the four vertices of the parking space in the parking space information, calculate the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the depth of the parking space, and the width of the parking space.

[0014] The coordinates of the rear axle center of the second vehicle are calculated based on the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the length of the vehicle's rear suspension, and a preset safety distance.

[0015] Based on the above technical solutions, preferably, the geometric model-based tracking algorithm performs smooth interpolation on the initial parking trajectory point sequence to obtain the target parking trajectory sequence, specifically including:

[0016] Based on the starting point position, a set of continuous trajectory points within the pre-aiming distance range is extracted from the initial parking trajectory point sequence;

[0017] Calculate the Euclidean distance from each trajectory point in the continuous trajectory point set to the starting point, and select the trajectory point with the smallest Euclidean distance to obtain the pre-aiming distance;

[0018] Spline interpolation is performed on the continuous trajectory point set to generate multiple subdivided trajectory points. One subdivided trajectory point is selected as the preview point, and the deflection angle between the preview point and the vehicle's heading is calculated.

[0019] Based on the deflection angle, vehicle wheelbase, and pre-aiming distance, the steering angle required for tracking is calculated to obtain the target parking trajectory sequence.

[0020] More preferably, the control points corresponding to the Bezier curve include the coordinates of the rear axle center of the first vehicle, the dual-track control points, and the coordinates of the rear axle center of the second vehicle.

[0021] More preferably, if the vehicle is in the automatic parking phase, the method further includes:

[0022] The mobile terminal sends a first operation instruction to the application server, and the application server forwards the first operation instruction to the vehicle through the 4G communication module;

[0023] Based on the vehicle's location coordinates and vehicle number, obtain the first four vertex coordinate group of the corresponding parking space, and plan the parking exit trajectory curve corresponding to the target parking trajectory sequence.

[0024] The vehicle's driving trajectory is adjusted according to the parking trajectory curve, and the parked vehicle is driven to the permission handover point on the autonomous driving path to complete the first operation command.

[0025] More preferably, if the vehicle is in the parking phase, the method further includes:

[0026] The mobile terminal sends a second operation command to the application server, and the application server forwards the second operation command to the vehicle through the 4G communication module;

[0027] Based on the vehicle's location coordinates and the parking space information to be parked, a parking trajectory curve corresponding to the target parking trajectory sequence is planned, wherein the parking space information to be parked includes the second and fourth vertex coordinate group of the parking space corresponding to the vehicle.

[0028] When the vehicle travels to a position that is a preset adjustable length away from the parking space to be parked, the vehicle's pose adjustment path is planned based on the second four-vertex coordinate group and the vehicle's current heading angle to complete the second operation command.

[0029] Furthermore, the autonomous driving path is planned based on the map trajectory coordinates in the vehicle coordinate system, lane boundaries, traffic light status, speed limit information, and the real-time location of the current vehicle.

[0030] A second aspect of this application provides a high-precision positioning-based integrated navigation and parking control system, which includes a data acquisition module, a trajectory modulation module, and a trajectory generation module, wherein...

[0031] The data acquisition module is used to obtain the vehicle's starting point location and parking space information;

[0032] The trajectory generation module is used to calculate the coordinates of the first vehicle rear axle center in the geodetic coordinate system based on the latitude and longitude of the starting point, obtain parking data corresponding to the parking space based on the parking space information, calculate the coordinates of the second vehicle rear axle center after the vehicle is parked based on the parking data, calculate the dual trajectory control points corresponding to the tangent direction vectors corresponding to the first and second vehicle rear axle center coordinates, and discretize the Bezier curve with multiple control points with a preset step size to generate an initial parking trajectory point sequence.

[0033] The trajectory modulation module is used to smoothly interpolate the initial parking trajectory point sequence based on a geometric model tracking algorithm to obtain the target parking trajectory sequence.

[0034] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory.

[0035] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the steps of a high-precision positioning-based integrated navigation and parking control method.

[0036] The integrated navigation and berthing control method and system based on high-precision positioning provided by this invention has the following advantages over existing technologies:

[0037] (1) By obtaining the latitude and longitude of the vehicle's starting point and converting it to the rear axle center of the geodetic coordinate system, the vehicle's pose can be obtained with centimeter-level or even higher precision. Combined with parking space information and standard parking data, the target rear axle center coordinates can be quickly calculated to ensure the accuracy of the final parking position. At the same time, based on the starting point, the end point rear axle center and its tangent direction, the dual trajectory control points are automatically calculated to construct a Bézier curve that satisfies the vehicle's steering constraints. The Bézier curve is discretized with a preset step size to obtain the initial trajectory point sequence. Then, the geometric model tracking algorithm is used for smooth interpolation to eliminate trajectory inflection points and discontinuous slope changes, generating a smooth and continuous target trajectory. High-speed or low-speed driving and precise parking can be completed within the same planning framework, effectively shortening the parking operation time and improving the robustness of the driving and parking integration. It also has a strong tolerance for parameters such as starting position, parking space size, and road environment, and can be applied to various parking scenarios such as parallel, perpendicular, and oblique parking.

[0038] (2) Based on the real-time parking space starting point, a subset of trajectory points within a pre-aiming window is extracted. Only the most critical intervals of the current driving path are calculated. The pre-aiming distance can be dynamically adjusted according to the current position and speed of the vehicle. By selecting the trajectory point that best matches the pre-aiming distance in real time, the pre-aiming point is always on the most reasonable path, thus achieving effective prediction and correction of the vehicle's lateral deviation. At the same time, spline interpolation is performed on the discrete trajectory points within the pre-aiming window to generate a high-density, curvature-continuous subdivided point sequence, avoiding the curvature abrupt change of the original discrete points at corners or sharp bends. The smoothed trajectory can maintain continuous and stable curvature changes when performing steering, greatly reducing the phenomenon of sudden steering wheel turns or shaking. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 A flowchart illustrating an integrated navigation and berthing control method based on high-precision positioning provided by the present invention;

[0041] Figure 2 A schematic diagram of a parking space provided by the present invention;

[0042] Figure 3 A schematic diagram of the trajectory during the automatic parking phase provided by this invention;

[0043] Figure 4 A schematic diagram of the trajectory during the parking and entry phase provided by this invention;

[0044] Figure 5 A schematic diagram of the integrated navigation and berthing control system provided by the present invention;

[0045] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention.

[0046] Explanation of reference numerals in the attached diagram: 1. Integrated navigation and parking control system; 11. Data acquisition module; 12. Track generation module; 13. Track modulation module; 2. Electronic equipment; 21. Processor; 22. Communication bus; 23. User interface; 24. Network interface; 25. Memory. Detailed Implementation

[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0048] This invention discloses an integrated navigation and parking control method based on high-precision positioning, with reference to... Figure 1 The steps of this method include S1 to S6.

[0049] Step S1: Obtain the starting point location and parking space information of the vehicle.

[0050] Step S2: Calculate the coordinates of the center of the rear axle of the first vehicle in the geodetic coordinate system using latitude and longitude.

[0051] In this step, the starting point P0 is obtained in real time using BeiDou positioning, and the position P0 of the vehicle's rear axle center in the geodetic coordinate system is calculated from latitude and longitude. ).

[0052] Step S3: Based on the parking space information, obtain the parking data corresponding to the parking space, and calculate the center coordinates of the second rear axle of the vehicle after parking based on the parking data.

[0053] This step also includes steps S31 to S32.

[0054] Step S31: Based on the coordinates of the four vertices of the parking space in the parking space information, calculate the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the depth of the parking space, and the width of the parking space.

[0055] In this step, the coordinates A(x) of the four vertices of the parking space in the geodetic coordinate system are known. A ,y A ), B(x) B ,y B ), C(x) C ,y C ), D(x D ,y D ) and the distance K between the vehicle's longitudinal direction and the parking space boundary, calculate the key points of the parking space: the midpoint M of the front boundary of the parking space = ), the midpoint N of the rear boundary of the parking space = ), calculate parking space depth Dep= Parking space width Wid= .

[0056] Step S32: Calculate the center coordinates of the rear axle of the second vehicle based on the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the length of the rear overhang of the vehicle, and the preset safety distance.

[0057] In this step, a safety distance of 20cm is reserved. After parking, the target position point P3 of the rear axle center of the vehicle is P3( ),in This refers to the rear overhang length of the vehicle.

[0058] In this embodiment, the midpoints of the front and rear boundaries of the parking space, as well as its depth and width, are calculated using a four-vertex coordinate system to fully obtain the geometric dimensions and centroid position of the parking space. This accurately quantifies the parking space size, eliminating errors caused by manual calibration or empirical estimation, and achieving centimeter-level parking space description. Four-vertex modeling is compatible with parallel, perpendicular, diagonal, and irregular parking spaces. The calculation method is highly versatile, requiring no pre-set fixed parking space size library, and can analyze any parking space size and orientation in real time. Based on the midpoints of the front and rear boundaries, the target coordinates of the second rear axle center are automatically calculated by considering the vehicle's rear overhang length and a preset safety distance. Simultaneously, the optimal distance between the rear of the vehicle and the front and rear boundaries is satisfied, avoiding collisions with boundaries, curbs, and adjacent vehicles. Parking space geometry and safety constraints are incorporated into the path planning endpoint calculation, enabling rapid replanning in dynamic environments or various parking space scenarios.

[0059] Step S4: Calculate the dual-track control points corresponding to the tangent direction vectors based on the coordinates of the rear axle center of the first vehicle and the coordinates of the rear axle center of the second vehicle, respectively.

[0060] In this step, the tangent directions V0 and V3 of the starting and ending points are calculated, and the vector expressions for the two control points P1 and P2 are obtained using a vector algorithm: P1 = P2= , where P 0x This represents the x-coordinate of the starting point P0 in the geodetic coordinate system. 0y This represents the y-coordinate of the starting point P0 in the geodetic coordinate system. 3x This represents the x-coordinate of the starting point P3 in the geodetic coordinate system. 3y V represents the y-coordinate of the starting point P3 in the geodetic coordinate system. 0x V represents the x-coordinate of the tangent vector V0 at the starting point P0. 0y V represents the ordinate of the tangent vector V0 at the starting point P0. 3x V represents the x-coordinate of the tangent vector V3 from the starting point P3. 3y V3 represents the ordinate of the tangent vector V3 at the starting point P3, and K represents the distance between the vehicle's longitudinal direction and the boundary of the parking space.

[0061] Step S5: Discretize the Bézier curve with multiple control points using a preset step size to generate an initial parking trajectory point sequence.

[0062] In this step, the control points corresponding to the Bézier curve include the coordinates of the rear axle center of the first vehicle, the dual-track control points, and the coordinates of the rear axle center of the second vehicle. That is, a cubic Bézier curve is generated, and the curve parametric equation is: Discretize t with a step size of 0.01 to calculate the initial parking trajectory point sequence.

[0063] Step S6 involves smoothing the initial parking trajectory point sequence using a geometric model tracking algorithm to obtain the target parking trajectory sequence. This employs an improved PurePursuit geometric model tracking algorithm, ensuring continuous steering wheel changes during parking and improving the smoothness and comfort of the parking process.

[0064] This step also includes steps S61 to S64.

[0065] Step S61: Using the starting point position as a reference, extract a set of continuous trajectory points within the pre-aiming distance range from the initial parking trajectory point sequence.

[0066] In this step, the coordinates P(rear axle center position) of the vehicle in the current geodetic coordinate system are obtained. The system retrieves the planned trajectory points from the planning module and adds index information, then matches the location data to truncate the data.

[0067] Step S62: Calculate the Euclidean distance from each trajectory point in the continuous trajectory point set to the starting point, and select the trajectory point with the smallest Euclidean distance to obtain the pre-aiming distance.

[0068] In this step, trajectory points are typically generated using a 10ms discrete sequence. The vehicle speed during parking is usually around 1m / s. To anticipate the distance of 0.75m before and after the target, a sequence of 150 trajectory points {P1, P2, P3...P...} near the current coordinates is selected. 150} Calculate the distance from each of the 150 trajectory points to point P, and find the point P that is closest to the target P. J .

[0069] Step S63: Perform spline interpolation on the continuous trajectory point set, then smooth to generate multiple subdivided trajectory points, and select one subdivided trajectory point from all the subdivided trajectory points as the aiming point, and calculate the deflection angle between the aiming point and the vehicle heading.

[0070] In this step, to make the tracked trajectory smoother and more continuous, and to avoid abrupt changes in the trajectory after the above sequence truncation of the curve segment, splev function is used for spline interpolation to further smooth the trajectory. Calculate P to P J Vector expression, discretization to obtain P to P J Given 20 trajectory sequences, take the 10th trajectory point as the aiming point and calculate its coordinates P. r ( Based on the two-wheeled vehicle model, calculate the angle between the aiming point and the vehicle body. .

[0071] Step S64: Based on the yaw angle, vehicle wheelbase, and pre-aiming distance, calculate the steering angle required for tracking to obtain the target parking trajectory sequence.

[0072] In this step, the aiming distance is determined. According to the Ackermann turning discrete equation The steering angle required for tracking the trajectory is calculated in real time, where L is the vehicle wheelbase.

[0073] In this embodiment, a subset of trajectory points within a preview window is extracted based on the real-time parking space starting point. Calculations are performed only on the most critical sections of the current driving path. The preview distance is dynamically adjusted based on the vehicle's current position and speed by selecting the trajectory point that best matches the preview distance in real-time, ensuring that the preview point always falls on the most reasonable path and effectively predicting and correcting lateral deviations of the vehicle. Spline interpolation is performed on the discrete trajectory points within the preview window to generate a high-density, curvature-continuous subdivided point sequence, avoiding abrupt curvature changes at corners or sharp bends in the original discrete points. The smoothed trajectory maintains continuous and stable curvature changes during steering, greatly reducing sudden steering wheel turns or vibrations. Using the geometric deflection angle between the preview point and the vehicle's heading line, combined with the vehicle's wheelbase and the preview distance, the required steering angle is accurately calculated using a classic pure pursuit model or other geometric models. Interpolation and angle calculations are performed only within the preview window, avoiding repeated traversal of the global trajectory point sequence and significantly reducing the computational load of online path tracking.

[0074] In one example, if the vehicle is in the automatic parking phase, the method also includes:

[0075] The mobile terminal sends a first operation command to the application server, and the application server forwards the first operation command to the vehicle through the 4G communication module.

[0076] Based on the vehicle's location coordinates and vehicle number, obtain the first four vertex coordinate set of the corresponding parking space, and plan the parking exit trajectory curve corresponding to the target parking trajectory sequence.

[0077] The vehicle's trajectory is adjusted according to the parking trajectory curve, and the parked vehicle is driven to the permission handover point on the autonomous driving path to complete the first operation command.

[0078] Furthermore, based on the map trajectory coordinates in the vehicle coordinate system, lane boundaries, traffic light status, speed limit information, and the real-time location of the current vehicle, an autonomous driving path is planned.

[0079] Understandably, users can issue work instructions through service or management software, and the vehicle has the ability to automatically park itself from the parking space onto the work route. Based on the work instructions, the vehicle automatically drives from the parking space or charging station to the designated work point. The process definition for outbound operations is as follows: Figure 3 As shown, Part 1 is the automatic parking process; Part 2 is the automatic driving process to the work point.

[0080] like Figure 3 As shown, the user requests a job service using a WeChat mini-program on their mobile phone. The job operation command is defined as follows: Message header: #BDSPILOT, ID: 63070WH10C001 (reference), Command: 01 (start), Checksum: CRC32, End character: .

[0081] The command, transmitted as a string from the mobile terminal network to the application server, simultaneously sends vehicle control commands to the vehicle via the 4G communication module, initiating autonomous driving mode. The application server obtains the current vehicle status and location information via the 4G communication module, matches it with the depot data for the vehicle's current departure point, and the dispatch system queries the coordinates (x, y) of the vehicle's current parking space based on the operation record corresponding to the vehicle's number. A ,y A ), (x B ,y B ), (x C ,y C ), (x D ,y D The system acquires vehicle BeiDou positioning data and vehicle status data to plan a parking trajectory curve. The application server sends map data to the vehicle via a 4G communication module. After receiving the data, the vehicle verifies it with the application server. If the data is correct, the automatic parking module controls the vehicle to follow the parking trajectory and complete the automatic parking. After parking, the vehicle travels to the vicinity of the permission handover point on the planned autonomous driving path (10m from the longitudinal centerline of the perpendicular parking space, and 10m from the lateral centerline of the horizontal parking space) (within an allowable error of 40cm). The automatic parking module then stops the vehicle and releases control, allowing the autonomous driving system to take over. If the vehicle has not reached the permission handover point, it automatically reports to the backend for manual confirmation. The autonomous driving module plans an autonomous driving path based on the map data sent by the application server (including map trajectory coordinates in the vehicle coordinate system, lane boundaries, traffic light status, speed limit information, etc.) and the current real-time positioning of the vehicle. It then obtains vehicle control and controls the vehicle to complete Part 2 of the process definition to reach the designated work point.

[0082] During the above process, the obstacle detection module uses perception data in real time to determine if there is a collision risk and actively controls the brakes to stop suddenly when a collision risk exists. The fault detection module acquires vehicle body and sensor status data in real time to determine if any components have failed or wiring harnesses have broken. Vehicle positioning data and vehicle status data are uploaded to the mobile application server in real time and dynamically displayed on the user's mini-program. After completing the parking process and reaching the designated work point, the autonomous driving module sends a "complete" status to the application server via the 4G communication module. The application server stores the process data of this operation and prompts the user on the mobile terminal's mini-program that the vehicle is ready and has entered the work state.

[0083] In one example, if the vehicle is in the parking phase, the method also includes:

[0084] The mobile terminal sends a second operation command to the application server, and the application server forwards the second operation command to the vehicle through the 4G communication module.

[0085] Based on the vehicle's location coordinates and the parking space information, a parking trajectory curve corresponding to the target parking trajectory sequence is planned. The parking space information includes the coordinates of the second and fourth vertices of the parking space corresponding to the vehicle.

[0086] When the vehicle travels to a position that is a preset adjustable length away from the parking space, the vehicle's pose adjustment path is planned based on the second four-vertex coordinate set and the vehicle's current heading angle to complete the second operation command.

[0087] Understandably, users can issue work instructions through service or management software. Based on the work instructions or vehicle status such as battery level or malfunction, the vehicle will automatically return to the parking area or charging area and automatically park in the parking space. The process definition for outbound operations is as follows: Figure 4 As shown, Part 1 is the vehicle's autonomous driving process; Part 2 is the vehicle's automatic posture adjustment process before parking; and Part 3 is the vehicle's automatic parking process.

[0088] like Figure 4 As shown, the user requests a job service using the WeChat mini-program on their mobile phone. The "job" operation command is defined as follows: Message header: #BDSPILOT, ID: 63070WH10C001 (reference), Command: 02 (stop), Checksum: CRC32, End character: .

[0089] The command, transmitted in string format from the mobile terminal network to the mobile application server, simultaneously sends an "autonomous driving" control command to the vehicle via the 4G communication module, initiating the vehicle into autonomous driving mode. The application server obtains the current vehicle status and location information via the 4G communication module, matches it with the data of the depot the vehicle is about to enter, and the dispatch system determines the parking space the vehicle will soon park in. The application server sends map data to the vehicle via the 4G communication module. After receiving the data, the vehicle verifies it with the application server. If the data is correct, the autonomous driving module completes trajectory planning for the following route and controls the vehicle to follow the trajectory, completing Part 1 of the process definition.

[0090] When the vehicle is 2-3 times its own length away from the parking space, the autonomous driving module controls the vehicle to stop and transmits the coordinates of the four corners of the parking space (x, y, y). A ,y A ), (x B ,y B ), (x C ,y C ), (x D ,y D The data is sent to the automatic parking module. The automatic driving module releases vehicle control authority. The automatic parking module plans the vehicle's pose adjustment path based on the parking space coordinates and the current vehicle's heading angle, obtains vehicle control authority, and controls the vehicle to complete the pose adjustment process defined in the process definition. After the pose adjustment is completed, the automatic parking module plans the parking trajectory based on the parking space coordinates and the current BeiDou positioning data, and controls the vehicle to complete the parking process defined in the process definition by following the closed-loop tracking path.

[0091] During the above process, the obstacle detection module uses perception data in real time to determine if there is a collision risk and actively controls the brakes to stop suddenly when a collision risk exists. The fault detection module acquires vehicle body and sensor status data in real time to determine if any components have failed or wiring harnesses have broken. Vehicle positioning data and vehicle status data are received by the application server in real time and dynamically displayed on the user's mini-program. After the parking process is completed, the parking module sends a "complete" status to the application server via the 4G communication module. The server stores the process data of this operation and simultaneously notifies the user on the mobile terminal's mini-program that parking is complete.

[0092] In this embodiment, by acquiring the latitude and longitude of the vehicle's starting point and converting it to the rear axle center in the geodetic coordinate system, vehicle pose acquisition with centimeter-level or even higher precision is achieved. Combined with parking space information and standard parking data, the target rear axle center coordinates are quickly calculated to ensure the accuracy of the final parking position. Simultaneously, based on the starting and ending rear axle centers and their tangent directions, dual-track control points are automatically calculated to construct a Bézier curve that satisfies the vehicle's steering constraints. The Bézier curve is discretized with a preset step size to obtain an initial trajectory point sequence. Then, a geometric model tracking algorithm is used for smooth interpolation to eliminate trajectory inflection points and discontinuous slope changes, generating a smooth and continuous target trajectory. High-speed or low-speed driving and precise parking are completed within the same planning framework, effectively shortening parking operation time and improving the robustness of the integrated driving and parking system. Furthermore, it has strong tolerance for parameters such as starting position, parking space size, and road environment, and is applicable to various parking scenarios such as parallel, perpendicular, and angled parking.

[0093] This solution eliminates the need for sensors such as cameras and LiDAR, thus avoiding increased site equipment costs. It utilizes only a high-precision positioning module and a 4G communication module, along with a backend server-side scheduling and management system that matches the autonomous driving map to assign parking space coordinates for vehicle operation and return. It achieves fully automated parking using a fusion positioning method combining high-precision satellite positioning (BeiDou Navigation Satellite System) and IMU (Inertial Measurement Unit). The solution generates motion trajectories using cubic Bézier curve equations and smooth interpolation algorithms, ensuring continuous curvature without abrupt changes. Combined with motion and environmental constraints, this improves the reliability and success rate of the parking process. It also improves upon Pure... Pursuit's geometric model tracking algorithm uses spline sampling to smooth and re-interpolate the trajectory sequence, thereby more accurately determining the aiming point, reducing the control algorithm's dependence on chassis steering performance, and making the steering wheel changes continuous during parking, improving the smoothness and comfort of the parking process. It can be applied to all unmanned vehicles with high-precision navigation functions, including but not limited to unmanned sweeping vehicles, unmanned sightseeing vehicles, unmanned logistics vehicles, unmanned buses, unmanned agricultural machinery, and mobile operation robots parked in open outdoor areas. Extending its application to different vehicle models only requires calibrating the control parameters of the parking control function according to the vehicle chassis parameters (length, width, turning radius, etc.), making it easy to port.

[0094] Based on the above method, this application discloses an integrated navigation and parking control system based on high-precision positioning, with reference to... Figure 5 The integrated navigation and parking control system 1 includes a data acquisition module 11, a trajectory generation module 12, and a trajectory modulation module 13, wherein...

[0095] The data acquisition module 11 is used to acquire the starting point position of the vehicle and parking space information;

[0096] The trajectory generation module 12 is used to calculate the coordinates of the center of the rear axle of the first vehicle in the geodetic coordinate system based on the latitude and longitude, obtain parking data corresponding to the parking space based on the parking space information, calculate the coordinates of the center of the rear axle of the second vehicle after the vehicle is parked based on the parking data, calculate the dual trajectory control points corresponding to the tangent direction vectors corresponding to the center of the rear axle of the first vehicle and the center of the rear axle of the second vehicle respectively, and discretize the Bézier curve with multiple control points with a preset step size to generate an initial parking trajectory point sequence.

[0097] The trajectory modulation module 13 is used to smoothly interpolate the initial parking trajectory point sequence based on the geometric model tracking algorithm to obtain the target parking trajectory sequence.

[0098] In one example, the trajectory generation module 12 is used to calculate the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the depth of the parking space, and the width of the parking space based on the coordinates of the four vertices of the parking space in the parking space information; and to calculate the coordinates of the center of the rear axle of the second vehicle based on the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the length of the rear overhang of the vehicle, and the preset safety distance.

[0099] In one example, the trajectory modulation module 13 is used to extract a continuous set of trajectory points within a pre-aiming distance range from the initial parking trajectory point sequence, based on the starting point position; calculate the Euclidean distance from each trajectory point in the continuous trajectory point set to the starting point position, and select the trajectory point with the smallest Euclidean distance to obtain the pre-aiming distance; perform spline interpolation on the continuous trajectory point set, and then smooth to generate multiple subdivided trajectory points, and select one subdivided trajectory point as the pre-aiming point from all the subdivided trajectory points, and calculate the deflection angle between the pre-aiming point and the vehicle heading; based on the deflection angle, the vehicle wheelbase, and the pre-aiming distance, calculate the steering angle required for tracking to obtain the target parking trajectory sequence.

[0100] In one example, the control points corresponding to the Bézier curve include the coordinates of the rear axle center of the first vehicle, the dual-track control points, and the coordinates of the rear axle center of the second vehicle.

[0101] In one example, if the vehicle is in the automatic parking phase, the method also includes:

[0102] The mobile terminal sends a first operation command to the application server, and the application server forwards the first operation command to the vehicle through the 4G communication module.

[0103] Based on the vehicle's location coordinates and vehicle number, obtain the first four vertex coordinate set of the corresponding parking space, and plan the parking exit trajectory curve corresponding to the target parking trajectory sequence.

[0104] The vehicle's trajectory is adjusted according to the parking trajectory curve, and the parked vehicle is driven to the permission handover point on the autonomous driving path to complete the first operation command.

[0105] In one example, if the vehicle is in the parking phase, the method also includes:

[0106] The mobile terminal sends a second operation command to the application server, and the application server forwards the second operation command to the vehicle through the 4G communication module.

[0107] Based on the vehicle's location coordinates and the parking space information, a parking trajectory curve corresponding to the target parking trajectory sequence is planned. The parking space information includes the coordinates of the second and fourth vertices of the parking space corresponding to the vehicle.

[0108] When the vehicle travels to a position that is a preset adjustable length away from the parking space, the vehicle's pose adjustment path is planned based on the second four-vertex coordinate set and the vehicle's current heading angle to complete the second operation command.

[0109] In one example, an autonomous driving path is planned based on the map trajectory coordinates in the vehicle coordinate system, lane boundaries, traffic light status, speed limit information, and the real-time location of the current vehicle.

[0110] Please see Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6 As shown, the electronic device 2 may include: at least one processor 21, at least one network interface 24, user interface 23, memory 25, and at least one communication bus 22.

[0111] The communication bus 22 is used to enable communication between these components.

[0112] The user interface 23 may include a display screen and a camera. Optionally, the user interface 23 may also include a standard wired interface and a wireless interface.

[0113] The network interface 24 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0114] The processor 21 may include one or more processing cores. The processor 21 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 25, and by calling data stored in the memory 25. Optionally, the processor 21 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 21 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 21 and may be implemented as a separate chip.

[0115] The memory 25 may include random access memory (RAM) or read-only memory. Optionally, the memory 25 may include non-transitory computer-readable storage medium. The memory 25 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 25 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 25 may also be at least one storage device located remotely from the aforementioned processor 21. Figure 6 As shown, the memory 25, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a high-precision positioning-based integrated navigation and parking control method.

[0116] exist Figure 6In the electronic device 2 shown, the user interface 23 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 21 can be used to call an application program stored in the memory 25 that is a high-precision positioning-based integrated navigation and parking control method. When executed by one or more processors, the electronic device executes one or more methods as described in the above embodiments.

[0117] A computer-readable storage medium storing instructions that, when executed by one or more processors, cause a computer to perform one or more methods as described in the embodiments above.

[0118] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0119] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0123] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0124] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of other embodiments of this disclosure upon considering the specification and the disclosure of practical truths. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure.

[0125] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for integrated navigation and berthing control based on high-precision positioning, characterized in that, The method includes: Obtain the vehicle's starting point location and parking space information; The coordinates of the center of the rear axle of the first vehicle in the geodetic coordinate system are calculated using latitude and longitude. Based on the parking space information, obtain the parking data corresponding to the parking space, and calculate the center coordinates of the second rear axle of the vehicle after it is parked based on the parking data. Based on the tangent direction vectors corresponding to the rear axle center coordinates of the first vehicle and the rear axle center coordinates of the second vehicle, calculate the dual trajectory control points corresponding to the tangent direction vectors. Discretize the Bézier curve with multiple control points using a preset step size to generate an initial parking trajectory point sequence; The initial parking trajectory point sequence is smoothly interpolated based on a geometric model tracking algorithm to obtain the target parking trajectory sequence; The geometric model-based tracking algorithm performs smooth interpolation on the initial parking trajectory point sequence to obtain the target parking trajectory sequence, specifically including: Based on the starting point position, a set of continuous trajectory points within the pre-aiming distance range is extracted from the initial parking trajectory point sequence; Calculate the Euclidean distance from each trajectory point in the continuous trajectory point set to the starting point, and select the trajectory point with the smallest Euclidean distance to obtain the pre-aiming distance; Spline interpolation is performed on the continuous trajectory point set, and multiple subdivided trajectory points are generated by smoothing. One subdivided trajectory point is selected as the aiming point from all the subdivided trajectory points, and the deflection angle between the aiming point and the vehicle heading is calculated. Based on the deflection angle, vehicle wheelbase, and pre-aiming distance, the steering angle required for tracking is calculated to obtain the target parking trajectory sequence.

2. The integrated navigation and parking control method based on high-precision positioning as described in claim 1, characterized in that, The step of calculating the coordinates of the second rear axle center of the vehicle after parking based on the parking data specifically includes: Based on the coordinates of the four vertices of the parking space in the parking space information, calculate the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the depth of the parking space, and the width of the parking space. The coordinates of the rear axle center of the second vehicle are calculated based on the midpoint of the front boundary of the parking space, the midpoint of the rear boundary of the parking space, the length of the vehicle's rear suspension, and a preset safety distance.

3. The integrated navigation and parking control method based on high-precision positioning as described in claim 1, characterized in that, The control points corresponding to the Bezier curve include the coordinates of the rear axle center of the first vehicle, the dual-track control points, and the coordinates of the rear axle center of the second vehicle.

4. The integrated navigation and parking control method based on high-precision positioning as described in claim 1, characterized in that, If the vehicle is in the automatic parking phase, the method further includes: The mobile terminal sends a first operation instruction to the application server, and the application server forwards the first operation instruction to the vehicle through the 4G communication module; Based on the vehicle's location coordinates and vehicle number, obtain the first four vertex coordinate group of the corresponding parking space, and plan the parking exit trajectory curve corresponding to the target parking trajectory sequence. The vehicle's driving trajectory is adjusted according to the parking trajectory curve, and the parked vehicle is driven to the permission handover point on the autonomous driving path to complete the first operation command.

5. The integrated navigation and parking control method based on high-precision positioning as described in claim 1, characterized in that, If the vehicle is in the parking phase, the method further includes: The mobile terminal sends a second operation command to the application server, and the application server forwards the second operation command to the vehicle through the 4G communication module; Based on the vehicle's location coordinates and the parking space information to be parked, a parking trajectory curve corresponding to the target parking trajectory sequence is planned, wherein the parking space information to be parked includes the second and fourth vertex coordinate group of the parking space corresponding to the vehicle. When the vehicle travels to a position that is a preset adjustable length away from the parking space to be parked, the vehicle's pose adjustment path is planned based on the second four-vertex coordinate group and the vehicle's current heading angle to complete the second operation command.

6. The integrated navigation and parking control method based on high-precision positioning as described in claim 1, characterized in that, Based on the map trajectory coordinates in the vehicle coordinate system, lane boundaries, traffic light status, speed limit information, and the real-time location of the current vehicle, an autonomous driving path is planned.

7. A high-precision positioning-based integrated navigation and parking control system, characterized in that, The integrated navigation and parking control system (1) includes a data acquisition module (11), a trajectory generation module (12), and a trajectory modulation module (13), wherein, The data acquisition module (11) is used to acquire the starting point position and parking space information of the vehicle; The trajectory generation module (12) is used to calculate the coordinates of the center of the rear axle of the first vehicle in the geodetic coordinate system based on the latitude and longitude, obtain parking data corresponding to the parking space based on the parking space information, calculate the coordinates of the center of the rear axle of the second vehicle after the vehicle is parked based on the parking data, calculate the dual trajectory control points corresponding to the tangent direction vectors corresponding to the center of the rear axle of the first vehicle and the center of the rear axle of the second vehicle respectively, and discretize the Bezier curve with multiple control points with a preset step size to generate an initial parking trajectory point sequence. The trajectory modulation module (13) is used to perform smooth interpolation on the initial parking trajectory point sequence based on the geometric model tracking algorithm to obtain the target parking trajectory sequence; The geometric model-based tracking algorithm performs smooth interpolation on the initial parking trajectory point sequence to obtain the target parking trajectory sequence, specifically including: Based on the starting point position, a set of continuous trajectory points within the pre-aiming distance range is extracted from the initial parking trajectory point sequence; Calculate the Euclidean distance from each trajectory point in the continuous trajectory point set to the starting point, and select the trajectory point with the smallest Euclidean distance to obtain the pre-aiming distance; Spline interpolation is performed on the continuous trajectory point set, and multiple subdivided trajectory points are generated by smoothing. One subdivided trajectory point is selected as the aiming point from all the subdivided trajectory points, and the deflection angle between the aiming point and the vehicle heading is calculated. Based on the deflection angle, vehicle wheelbase, and pre-aiming distance, the steering angle required for tracking is calculated to obtain the target parking trajectory sequence.

8. An electronic device, characterized in that, The device includes a processor (21), a memory (25), a user interface (23), and a network interface (24). The memory (25) is used to store instructions. The user interface (23) and the network interface (24) are used to communicate with other devices. The processor (21) is used to execute the instructions stored in the memory (25) to cause the electronic device (2) to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-6.

Images