An automatic parking method, electronic device and storage medium

Abstract

This invention discloses an automatic parking method, system, electronic device, and storage medium, comprising: acquiring environmental element information around the vehicle through an environmental perception module, the element type including parking spaces; when an empty parking space is detected, determining a target parking space from the empty parking spaces; establishing a parking space coordinate system for the target parking space and determining the parking endpoint and the first parking pose of the parking endpoint in the current vehicle coordinate system, the parking endpoint being the position of a reference point on the vehicle in the target parking space when parking is completed; planning an initial parking path based on the environmental element information to move the reference point on the vehicle to the position of the first parking pose, the vehicle coordinate system having the reference point on the vehicle as the origin; and controlling the vehicle to park according to the initial parking path. By establishing the vehicle coordinate system and the parking space coordinate system separately, and determining the position of the reference point on the vehicle in the parking space when parking is completed, parking path planning can be performed after pose transformation, without relying on GPS.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving planning technology, and in particular to an automatic parking method, electronic device, and storage medium. Background Technology

[0002] In current automated parking applications, positioning technology plays a crucial role. On one hand, it effectively represents the real-time location of the vehicle during parking; on the other hand, it effectively represents the positions of parking spaces, pedestrians, and other obstacles within the parking environment. These two aspects provide the basis for the vehicle to plan its driving path.

[0003] Currently, positioning technology generally uses one or more sensors such as GPS, IMU, and wheel speedometer to form a combination of inertial navigation system and RTK (Real Time Kinematic) system to locate the vehicle and the current environmental parameters. However, in underground parking lots or when large obstacles block the view, the accuracy of GPS and IMU positioning devices will drop significantly, resulting in large positioning errors and making it difficult to accurately achieve automatic parking. Therefore, how to eliminate or reduce the dependence on GPS and IMU positioning devices during automatic parking is a problem that needs to be solved. Summary of the Invention

[0004] This invention provides an automatic parking method to solve the problem of dependence on GPS and IMU positioning devices during automatic parking.

[0005] In a first aspect, the present invention provides an automatic parking method applied to an automatic parking system including an environmental perception module, the method comprising:

[0006] The environmental perception module acquires information about environmental elements around the vehicle, including element type and element pose, and the element type includes parking space.

[0007] When an available parking space is detected, the target parking space is determined from among the available parking spaces;

[0008] Establish the parking space coordinate system of the target parking space and determine the parking endpoint G1 and the first parking pose of the parking endpoint G1 in the current vehicle coordinate system. The parking endpoint G1 is the position of the reference point on the vehicle in the target parking space when parking is completed.

[0009] In the current vehicle coordinate system, an initial parking path is planned based on the environmental element information to move the reference point on the vehicle to the location of the first parking pose. The vehicle coordinate system takes the reference point on the vehicle as the origin.

[0010] Control the vehicle parking according to the initial parking path.

[0011] In a second aspect, the present invention provides an automatic parking system, comprising:

[0012] An environmental perception module is used to acquire environmental element information around the vehicle, the environmental element information including element type and element pose, the element type including parking space;

[0013] The parking space selection module is used to determine the target parking space from the available parking spaces when an available parking space is detected.

[0014] The first parking position determination module is used to establish the parking space coordinate system of the target parking space and determine the parking endpoint G1 and the first parking position of the parking endpoint G1 in the current vehicle coordinate system. The parking endpoint G1 is the position of the reference point on the vehicle in the target parking space when parking is completed.

[0015] The decision module is used to plan an initial parking path for moving the reference point on the vehicle to the location of the first parking pose based on the environmental element information in the current vehicle coordinate system. The vehicle coordinate system takes the reference point on the vehicle as the origin.

[0016] The control module is used to control the vehicle parking according to the initial parking path.

[0017] Thirdly, the present invention provides an electronic device, the electronic device comprising:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the automatic parking method described in the first aspect of the invention.

[0021] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement the automatic parking method described in the first aspect of the present invention.

[0022] This invention provides an automatic parking method applied to an automatic parking system including an environmental perception module. The environmental perception module acquires environmental element information around the vehicle, including element type and element pose. The element type includes parking spaces. When an available parking space is detected, a target parking space is determined from among the available spaces. A parking space coordinate system for the target parking space is established, and the parking endpoint G1 and its first parking pose in the current vehicle coordinate system are determined. The parking endpoint G1 is the position of a reference point on the vehicle within the target parking space when parking is completed. In the current vehicle coordinate system, an initial parking path is planned based on the environmental element information to move the reference point on the vehicle to the position of the first parking pose. The vehicle coordinate system has the reference point on the vehicle as its origin. The vehicle is then controlled to park according to the initial parking path. After determining the target parking space, a vehicle coordinate system and a parking space coordinate system are established respectively. The position of the reference point on the vehicle when parking is completed is determined in the parking space, that is, the parking endpoint is determined. The pose of the parking endpoint is transformed from the parking space coordinate system to the vehicle coordinate system. The parking path from the reference point to the parking endpoint can be planned in the vehicle coordinate system without relying on GPS or other positioning systems for positioning guidance. This can improve the adaptability of the parking system in underground and other scenarios with no or weak positioning. Automatic parking can be achieved based on the data collected by external visual sensors (i.e., environmental perception modules).

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying 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.

[0025] Figure 1 This is a flowchart of an automatic parking method provided in an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram illustrating the construction of a vehicle coordinate system and a parking space coordinate system of a target parking space, provided by an embodiment of the present invention.

[0027] Figure 3 This is a flowchart of another automatic parking method provided in an embodiment of the present invention;

[0028] Figure 4This is a schematic diagram of a parking space origin G0 located at the edge of the detection range of the environmental perception module, provided by an embodiment of the present invention.

[0029] Figure 5 This is a schematic diagram of a parking space origin G0 located outside the detection range of the environmental perception module, provided by an embodiment of the present invention.

[0030] Figure 6 This is a schematic diagram of the structure of an automatic parking system provided in an embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0032] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0033] Figure 1 This is a flowchart illustrating an automatic parking method provided in an embodiment of the present invention. This embodiment is applicable to automatic parking in scenarios where GPS or IMU is difficult to function effectively. The method can be executed by an automatic parking system including an environmental perception module. This automatic parking system can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the automatic parking method includes:

[0034] S101. Obtain information about environmental elements around the vehicle through the environmental perception module.

[0035] The environmental perception module is an environmental perception device containing a camera and an analysis unit. It can acquire environmental images around the vehicle via the camera and send them to the analysis unit. The analysis unit processes and analyzes the environmental images to obtain environmental element information, typically involving techniques such as edge detection and contour extraction. Environmental element information includes element type and element pose. Element types include parking spaces, and may also include obstacles, restricted areas, etc. When the element is an irregularly shaped or large object, the element pose can specifically be a set of poses of the element's contour points. The pose describes the position and orientation of an object in three-dimensional space, including (spatial) coordinates and rotation angles.

[0036] This invention also establishes a vehicle coordinate system with a reference point on the vehicle as the origin. When the positions of the camera and the reference point coincide, the pose of the element acquired by the camera is the pose in the vehicle coordinate system. However, there may be cases where the positions of the camera and the reference point do not coincide. For example, in order to facilitate the acquisition of environmental images around the vehicle, the camera is usually located on the top of the vehicle body, while the reference point is located at the center of the rear axle of the vehicle. Since the positions of the reference point and the camera on the vehicle are fixed, coordinate (pose) transformation can be performed based on the orientation relationship between the two. Then, the pose acquired by the camera can be directly converted into the pose in the vehicle coordinate system, so that the element poses of the acquired environmental elements are all poses in the vehicle coordinate system. By uniformly setting the poses in the vehicle coordinate system, it is convenient to perform pose data processing in subsequent steps.

[0037] S102. When an available parking space is detected, the target parking space is determined from the available parking spaces.

[0038] The environmental perception module starts from the entrance of the parking space and detects the internal empty distance of the parking space. When the detected internal empty distance is greater than a preset distance, the parking space is designated as vacant, for example, 50cm. The detection range of the environmental perception module is usually greater than the overall length of the vehicle. For example, the radius of the detection range is usually not less than 15m. Therefore, the environmental perception module can detect a wide range and may be able to detect multiple vacant parking spaces.

[0039] Optionally, in one use case, all parking spaces in a parking lot are the same size and all can be used to park the vehicle. In this scenario, at least a portion of the parking area with a preset length is within the environmental perception module. Therefore, the nearest parking space can be selected as the target parking space. Furthermore, since vehicles typically have a human-machine interface, all available parking spaces can be sent to the interface as a distributed map, allowing the user to select the target parking space.

[0040] Optionally, in another use case, parking spaces in a parking lot have different sizes to accommodate the parking needs of vehicles of different sizes. When an empty parking space is detected, the target parking space is determined from the empty parking spaces. Specifically, this includes: when an empty parking space is detected, obtaining the vehicle size parameters and the size parameters of the empty parking space; and determining the target parking space from the empty parking spaces based on the size parameters of the vehicle and the empty parking space.

[0041] Environmental elements include parking spaces. When an empty parking space is detected, its pose, including its contour pose, can be obtained. In this scenario, when detecting the size of an empty parking space, the entire area of ​​the empty parking space must be within the detection range of the environmental perception module. Then, the size parameters of the parking space, i.e., its length and width, can be calculated based on the contour pose. Vehicle size parameters are usually directly obtainable, for example, from the manufacturer's specifications, including the vehicle's length and width. It's easy to understand that for a parking space to be used for a vehicle, its length and width must be greater than the vehicle's length and width. Therefore, based on this principle, qualified parking spaces can be identified from the available spaces. When the number of qualified parking spaces is greater than one, the qualified parking space closest to the vehicle can be used as the target parking space, or the user can select it.

[0042] S103. Establish the parking space coordinate system of the target parking space and determine the parking endpoint G1 and the first parking pose of the parking endpoint G1 in the current vehicle coordinate system. The parking endpoint G1 is the position of the reference point on the vehicle in the target parking space when parking is completed.

[0043] Spatial coordinate systems are usually three-dimensional, but in this invention, both the vehicle and the parking space are located on the ground, so parking planning can be regarded as a two-dimensional planar problem. Therefore, it is only necessary to construct a coordinate system in the XY plane.

[0044] After determining the target parking space, a parking space coordinate system is established with one point within the target parking space as the origin. In an optional embodiment, establishing the parking space coordinate system includes: the parking space coordinate system of the target parking space, with a point at the entrance of the target parking space as the origin G0, the orientation of the target parking space as the positive Y-axis, and the direction to the right perpendicular to the Y-axis as the positive X-axis. The point at the entrance of the target parking space can be the midpoint or any endpoint of the parking space entrance, and the orientation of the target parking space is a direction perpendicular to the parking space entrance and pointing outwards from the target parking space.

[0045] Figure 2 This is a schematic diagram illustrating the construction of a vehicle coordinate system and a parking space coordinate system for the target parking space; such as... Figure 2 As shown, the origin G0 of the parking space coordinate system is located at the midpoint of the entrance of the target parking space 2. The orientation of the target parking space 2 is taken as the positive direction of the Y-axis, and the right direction perpendicular to the Y-axis is taken as the positive direction of the X-axis. The origin of the vehicle coordinate system is the reference point A0 on the vehicle. The vertical forward direction of the vehicle is taken as the positive direction of the X-axis, and the direction perpendicular to the X-axis and close to the target parking space is taken as the positive direction of the Y-axis.

[0046] The above construction of the vehicle coordinate system and parking space coordinate system is only an example. There are many methods for determining the origin, X-axis, and Y-axis of the coordinate system. In addition, the reference point on the vehicle can also be located at the position of the camera (the center of the detection range). The vehicle coordinate system can take the vehicle's vertical forward direction as the positive X-axis and the direction perpendicular to the X-axis and away from the target parking space as the positive Y-axis. Alternatively, it can take the vehicle's right lateral direction as the X-axis and the vehicle's vertical forward direction as the Y-axis, etc. The construction method of the parking space coordinate system is similar and will not be shown one by one.

[0047] In an optional embodiment, such as Figure 2 As shown, A0 is the reference point on vehicle 1, located at the center of the rear axle of vehicle 1. The parking endpoint G1 is the position of the reference point A0 on the vehicle in the target parking space when parking is completed. Under ideal parking conditions, vehicle 1 is usually parked at the center of the width direction of the target parking space 2. The Y-axis of the current parking space coordinate system passes through the midpoint of the parking space entrance. Therefore, the parking endpoint G1 is in the negative Y-axis direction of the parking space coordinate system. Then, the length L1 of the vehicle body from A0 to the front of the vehicle is obtained. The point with a distance of L1 from G0 in the negative Y-axis direction is taken as the parking endpoint G1. Furthermore, the point with a distance of (L1+L2) from G0 in the negative Y-axis direction can also be taken as the parking endpoint G1. L2 is the parking redundancy distance, for example, L2 is 30cm.

[0048] The parking space origin G0 of the parking space coordinate system is within the detection range of the environmental perception module, which can detect the pose of the parking space origin G0 in the vehicle coordinate system. This means the pose of the parking space origin in both the vehicle and parking space coordinate systems can be determined simultaneously. Therefore, the pose transformation relationship between the parking space coordinate system and the current vehicle coordinate system is also definite. After determining the parking endpoint G1 and the parking pose system, the pose of the parking endpoint G1 in the parking space coordinate system can be determined. Then, the pose of the parking endpoint G1 in the parking space coordinate system is transformed to the vehicle coordinate system to obtain the first parking pose of the parking endpoint G1 in the current vehicle coordinate system. The advantage of this setup is that the pose of the parking endpoint G1 in the vehicle coordinate system can be obtained regardless of whether the parking endpoint G1 is within the detection range of the environmental perception module.

[0049] In another optional embodiment, determining the parking endpoint G1 and its first parking pose in the current vehicle coordinate system includes: obtaining a preset distance parameter of the vehicle relative to the boundary of the target parking space under ideal parking conditions; determining the parking endpoint G1 in the target parking space based on the preset distance parameter and the position of a reference point on the vehicle within the vehicle; determining the pose of the parking endpoint G1 in the parking space coordinate system based on the pose relationship between the parking endpoint G1 and the origin G0 of the parking space; and transforming the pose of the parking endpoint G1 in the parking space coordinate system to the current vehicle coordinate system to obtain the first parking pose.

[0050] The preset distance parameter for the vehicle relative to the boundary of the target parking space under ideal parking conditions can be the distance from the front, rear, left, or right side of the vehicle relative to the boundary of the target parking space. Determining the preset distance parameter is equivalent to determining the vehicle's position in the target parking space when parking is complete. Therefore, based on the pose relationship between the reference point and the vehicle, and between the vehicle and the parking space, the position of the parking endpoint G1 overlapping with the reference point under ideal parking conditions can be determined. Then, the pose of the parking endpoint G1 in the parking space coordinate system can be obtained. Finally, the pose of the parking endpoint G1 in the parking space coordinate system can be transformed to the vehicle coordinate system to obtain the pose of the parking endpoint G1 in the vehicle coordinate system.

[0051] S104. In the current vehicle coordinate system, plan the initial parking path for the reference point on the vehicle to move to the location of the first parking pose based on the environmental element information. The vehicle coordinate system takes the reference point on the vehicle as the origin.

[0052] Environmental element information can include element type and element pose. Element type includes parking space, obstacle, no-entry zone, etc. Therefore, in the current vehicle coordinate system, the initial parking path is obtained by taking the reference point on the vehicle (i.e. the current coordinate origin) as the starting point and the first parking pose as the ending point, and combining the environmental element information.

[0053] S105. Control the vehicle to park according to the initial parking path.

[0054] The vehicle is equipped with a control module. After generating the initial parking path, the control module generates corresponding control commands based on the initial parking path, including speed adjustment and steering angle. Then, it controls the vehicle to drive according to the control commands, so that the vehicle can drive along the initial parking path.

[0055] In an optional embodiment, controlling vehicle parking based on an initial parking path includes: dividing the initial parking path into multiple continuous arc segments, where each arc segment's configuration information includes its length and turning angle; and controlling vehicle movement based on the arc segment configuration information to achieve parking. Segmenting the initial parking path allows for control of the vehicle's movement along that path, improving the accuracy and controllability of the vehicle's movement path.

[0056] This invention provides an automatic parking method applied to an automatic parking system including an environmental perception module. The environmental perception module acquires environmental element information around the vehicle, including element type and element pose. The element type includes parking spaces. When an available parking space is detected, a target parking space is determined from among the available spaces. A parking space coordinate system for the target parking space is established, and the parking endpoint G1 and its first parking pose in the current vehicle coordinate system are determined. The parking endpoint G1 is the position of a reference point on the vehicle within the target parking space when parking is completed. In the current vehicle coordinate system, an initial parking path is planned based on the environmental element information to move the reference point on the vehicle to the position of the first parking pose. The vehicle coordinate system has the reference point on the vehicle as its origin. The vehicle is then controlled to park according to the initial parking path. After determining the target parking space, a vehicle coordinate system and a parking space coordinate system are established respectively. The position of the reference point on the vehicle when parking is completed is determined in the parking space, that is, the parking endpoint is determined. The pose of the parking endpoint is transformed from the parking space coordinate system to the vehicle coordinate system. The parking path from the reference point to the parking endpoint can be planned in the vehicle coordinate system without relying on GPS or other positioning systems for positioning guidance. This can improve the adaptability of the parking system in underground and other scenarios with no or weak positioning. Automatic parking can be achieved based on the data collected by external visual sensors (i.e., environmental perception modules).

[0057] In one embodiment of the present invention, after controlling the vehicle to park according to the initial parking path, in order to ensure that the vehicle can be parked successfully, the vehicle's driving data and environmental element information are further monitored and analyzed during the parking process. Figure 3 A flowchart of another automatic parking method provided in an embodiment of the present invention is shown below. Figure 3 As shown, the automatic parking method also includes:

[0058] S301. During the vehicle parking process, when the parking space origin G0 is within the detection range of the environmental perception module, detect and save the last N frames of the parking space origin G0 in the vehicle coordinate system as a backup pose.

[0059] N is a preset positive integer greater than or equal to 1, meaning there is at least one spare pose; the parking space origin G0 is the location of the origin of the parking space coordinate system.

[0060] During parking, the vehicle is in motion, and the position of the reference point on the vehicle and the vehicle coordinate system with the reference point as the origin are changing. Simultaneously, the relative position (alternate pose) between the parking space origin G0 and the vehicle is also changing. The last N frames of alternate poses are saved in a rolling format [x1, y1, YAW1], [x2, y2, YAW2]… where YAW is the rotation angle. Because the vehicle is moving and the detection range of the environmental perception module is limited, detecting and saving the last N frames of alternate poses of the parking space origin G0 in the vehicle coordinate system is to ensure that when the parking space origin G0 is outside the detection range and a new path needs to be replanned, the alternate poses can be used to determine the pose of the parking space origin G0 in the vehicle coordinate system during path replanning.

[0061] S302. When the path replanning condition is triggered, determine whether the parking space origin G0 is within the detection range of the environmental perception module.

[0062] The main reasons for path replanning are path deviation or obstacle encounter. The reasons for path deviation mainly include: the control algorithm cannot control the vehicle to accurately follow the planned trajectory, or the vehicle tilts slightly due to road inclination, tire pressure, etc.

[0063] The reasons for encountering obstacles can be broadly categorized into the following types:

[0064] A. Due to perception bias, the visual perception of obstacles becomes less accurate the further away they are, which leads to errors in the planned initial parking path. When driving according to the initial parking path, collisions may occur, requiring real-time collision detection to trigger replanning.

[0065] B. The passage of dynamic obstacles or the addition of static obstacles, such as an ice cream cone being added to the initial parking path after parking begins, will also trigger the real-time collision detection algorithm.

[0066] When the path replanning condition is triggered, it is necessary to determine the current position of the vehicle itself (reference point) and the pose of the parking endpoint in the current vehicle coordinate system. This requires obtaining the correspondence between the parking space coordinate system and the current vehicle coordinate system. Whether the parking space origin G0 is within the detection range is equivalent to whether the vehicle can directly obtain the correspondence between the parking space coordinate system and the current vehicle coordinate system. Therefore, it is necessary to determine whether the parking space origin G0 is within the detection range. If not, then execute S303.

[0067] When the path replanning condition is triggered and the parking space origin G0 is within the detection range of the environmental perception module, the second parking pose of the parking endpoint G1 in the current vehicle coordinate system is determined; in the current vehicle coordinate system, a first updated parking path is planned based on the current environmental element information to move the reference point on the vehicle to the location of the second parking pose; the vehicle is controlled to park according to the first updated parking path.

[0068] When the path replanning condition is triggered and the parking space origin G0 is within the detection range of the environmental perception module, the environmental perception module on the current vehicle can detect the parking space origin G0. This allows it to determine the correspondence between the current vehicle coordinate system and the parking space coordinate system. Specifically, it can transform the pose of the parking endpoint G1 in the parking space coordinate system to the current vehicle coordinate system, obtaining the second parking pose. Then, based on the second parking pose, the current vehicle's reference point, and environmental element information, path planning is performed to obtain the first updated parking path and control the vehicle's movement. The specific process is similar to S104-S105; please refer to the relevant descriptions for details.

[0069] S303. Determine the first relative pose from the N frames of spare poses, and use the location of the reference point on the vehicle when the first relative pose is detected as the relay point.

[0070] When the path replanning condition is triggered and the parking space origin G0 is not within the detection range of the environmental perception module, the pose of the parking space (parking space origin G0) in the current vehicle coordinate system cannot be directly determined, and path replanning cannot be directly performed. Therefore, it is necessary to determine the relay point to assist in determining the pose of the parking space origin G0 in the current vehicle coordinate system.

[0071] In an optional example, N is 1 or 2. When N is 1, the number of backup poses is 1 frame, and this backup pose is directly used as the first relative pose. When N is 2, any frame of backup poses can be used as the first relative pose.

[0072] In an optional example, determining the first relative pose from N frames of alternative poses includes: fitting a pose curve based on the alternative poses, determining whether there are abnormal poses based on the smoothness of the pose curves, removing abnormal poses if so, and determining the first relative pose based on the remaining alternative poses.

[0073] The smoothness of the pose curve can quickly identify abnormal poses, preventing them from affecting path planning. In this example, setting N≥3 helps to identify abnormal poses, improves the fault tolerance of pose recording, avoids data loss or noise interference, and allows for the selection of poses from other frames if an abnormal pose occurs in a certain frame.

[0074] In another optional example, determining the first relative pose from N frames of spare poses includes: calculating the pose difference between two adjacent spare poses; determining whether there are abnormal poses in the N frames of spare poses based on the magnitude of the change in the pose difference; if so, removing the abnormal poses and determining the first relative pose based on the remaining spare poses. Preferably, in this example, N ≥ 5.

[0075] Since the vehicle parking process is a low-speed operation, the change in pose is small in a short period of time. Therefore, the difference between the remaining spare poses is also small. The first relative pose is determined based on the remaining spare poses. Specifically, the last remaining spare pose can be used as the first relative pose, or any remaining spare pose can be used as the first relative pose, or the average of the remaining spare poses can be used as the first relative pose. This embodiment does not limit this.

[0076] Figure 4 This is a schematic diagram illustrating a parking space origin G0 located at the edge of the detection range of the environmental perception module, as shown below. Figure 4 As shown, L1 is the initial parking path, and the parking space origin G0 is located at the edge of the detection range of the environmental perception module. Therefore, when the last N frames of the spare pose are detected, the vehicle's position is... Figure 4 If the positions are the same or similar, and assuming that the location of the reference point A0 on the vehicle is M when the first relative pose is detected, then M is the relay point.

[0077] S304. Obtain vehicle driving data from the time the first relative pose is detected to the time when the path replanning condition is triggered.

[0078] Figure 5 This is a schematic diagram illustrating a parking space origin G0 located outside the detection range of the environmental perception module, as shown below. Figure 5 As shown, L1 is the initial parking path, the parking space origin G0 is outside the detection range of the environmental perception module, the position where the first relative pose is detected is the relay point M, and the position where the path replanning condition is triggered is the current reference point A0 of the vehicle. That is, the vehicle driving data from the reference point of the vehicle to the current position is obtained.

[0079] S305. Calculate the second relative pose of the reference point on the current vehicle relative to the relay point based on the vehicle driving data.

[0080] In an optional example, the vehicle driving data includes multiple arc segments divided based on the initial parking path and configuration information of the arc segments. The configuration information of each arc segment includes the length and turning angle of the arc segment. The second relative pose of the reference point on the current vehicle relative to the relay point is calculated based on the vehicle driving data, including: obtaining the arc segments executed when the vehicle's reference point moves from the relay point to the current position and the configuration information of the arc segments; accumulating the length of each arc segment to obtain the total driving distance; accumulating the turning angle of each arc segment to obtain the vehicle turning angle; and determining the second relative pose of the reference point on the vehicle relative to the relay point based on the total driving distance and the vehicle turning angle.

[0081] Based on the existing initial parking path, the configuration information of the arc segment is obtained, and the total driving distance and vehicle turning angle are calculated based on the configuration information between the relay point and the current reference point. This allows for the rapid acquisition of the second relative pose. Specifically, the distance from the starting point to the ending point can be obtained through the radian calculation formula. By changing the angle, the orientation and angular relationship between the ending point and the starting point in the X and Y axes can be obtained, i.e., the relative pose between the ending point and the starting point.

[0082] In another optional example, the vehicle driving data includes wheel speed sensor data. The calculation of a second relative pose of the reference point on the current vehicle relative to the relay point, based on the vehicle driving data, further includes: calculating the total distance traveled by the reference point from the relay point to the current position and the difference in travel distance between the left and right wheels of the vehicle based on the wheel speed sensor data; calculating the vehicle turning angle from the relay point to the current position based on the total travel distance and the difference in travel distance between the left and right wheels; and determining the second relative pose of the reference point on the vehicle relative to the relay point based on the total travel distance and the vehicle turning angle.

[0083] In low-speed parking situations, wheel speed is difficult to control precisely. This can lead to path deviations when controlling vehicle movement based on control commands, resulting in inaccurate vehicle angles or travel distances. Therefore, wheel speed meters can be used to calculate wheel travel distances. A wheel speed meter is a device that calculates vehicle posture (position and orientation) by measuring wheel rotation speed. Its working principle is based on photoelectric encoders mounted on the drive wheel motors. By detecting the distance the wheels travel over a certain period, it calculates the vehicle's relative posture changes.

[0084] Wheel speed meter data includes wheel counts, wheel length (circumference), etc., and the following incremental data between two adjacent frames can be calculated based on the wheel speed meter data.

[0085] Vehicle forward distance: forward_dis = π(cl*wl+cr*wr) / (resolution / 2);

[0086] Difference in travel distance between left and right wheels: delta_dis = π(-cl*wl+cr*wr) / resolution;

[0087] Vehicle turning angle: delta_theta = delta_dis / Base_length.

[0088] The left wheel count increment is cl, the right wheel count increment is cr, the left wheel circumference is wl, the right wheel circumference is wr, the vehicle width is Base_length, and the count increment for one wheel rotation is resolution.

[0089] After the calculation is complete, the incremental data during the time it takes for the vehicle's reference point to move from the relay point to the current position is accumulated to obtain the total travel distance and the vehicle's turning angle. Based on this total travel distance and the vehicle's turning angle, the relative pose of the relay point with respect to the current vehicle's reference point is determined, i.e., the second relative pose. The second relative pose is the pose in the current vehicle coordinate system. Using wheel speed sensor data to calculate the second relative pose can improve its accuracy, especially in situations where path deviation may occur.

[0090] S306. Determine the third relative pose of the parking space origin G0 relative to the reference point on the current vehicle based on the first relative pose and the second relative pose.

[0091] Let the coordinate system of the parking space be Tp;

[0092] The first relative pose is the pose of the parking space origin G0 detected at the location of the relay point M in the vehicle coordinate system at that moment, that is, the pose of the parking space origin G0 relative to the relay point. Let the vehicle coordinate system at that moment be Tv1, then the first relative pose is the pose in the vehicle coordinate system Tv1.

[0093] The second relative pose is the pose of the current vehicle's reference point relative to the relay point, that is, the pose of the current vehicle's reference point in the relay point coordinate system.

[0094] Given the poses of the parking space origin G0 and the reference point on the current vehicle relative to the relay point, the pose of the parking space origin G0 relative to the reference point on the current vehicle, i.e., the third relative pose, can be calculated.

[0095] Let the current vehicle coordinate system be Tv2; the third relative pose is the pose of the parking space origin G0 in the current vehicle coordinate system Tv2.

[0096] S307, Controlling vehicle parking based on third relative pose and current environmental element information.

[0097] In an optional example, vehicle parking is controlled based on a third relative pose and current environmental element information, including: determining a fourth relative pose of the parking endpoint G1 relative to a reference point on the current vehicle based on the third relative pose and the relative pose of the parking endpoint G1 and the parking space origin G0; planning a second updated parking path based on the current environmental element information and the fourth relative pose to move the reference point on the current vehicle to the parking endpoint G1; and controlling vehicle parking based on the second updated parking path.

[0098] Once the third relative pose is determined, that is, the pose of the parking space origin G0 in the current vehicle coordinate system Tv2, the relative poses of the parking end point G1 and the parking space origin G0, as well as the third relative pose, can be used to determine the pose of the parking end point G1 relative to the reference point on the current vehicle, thus obtaining the fourth relative pose, that is, the pose of the parking end point G1 in the current vehicle coordinate system Tv2.

[0099] In an optional example, the parking space origin is located at the midpoint of the parking space entrance. Vehicle parking is controlled based on the third relative pose and current environmental element information. The method further includes: planning a temporary parking path based on the current environmental element information and the third relative pose, moving the reference point on the vehicle to the parking space origin G0; controlling vehicle movement based on the temporary parking path; during the movement, when the environmental perception module detects the parking space origin G0, re-determining the parking endpoint G1 and its third parking pose in the current vehicle coordinate system; planning a third updated parking path based on the current environmental element information, moving the reference point on the vehicle to the location of the third parking pose; and controlling vehicle parking based on the third updated parking path.

[0100] Since the parking space origin G0 is located at the midpoint of the parking space entrance, the reference point on the vehicle may pass through or be near the parking space origin G0 when parking. Therefore, the parking space origin G0 can serve as a relay target point for the vehicle to enter the parking space, and a temporary parking path can be planned using the parking space origin G0. When the parking space origin G0 is detected again, the parking endpoint G1 is re-determined and a new parking path is planned. When the parking space origin G0 is within the detection range, the pose data of the parking space origin G0 and the parking endpoint G1 in the current vehicle coordinate system can be obtained more accurately, improving the positioning accuracy of key positions in the parking space. Replanning the parking path based on this pose data is beneficial for achieving precise parking.

[0101] Corresponding to the automatic parking method of the present invention, in one embodiment of the present invention, an automatic parking system is also provided. Figure 6 This is a schematic diagram of an automatic parking system provided in an embodiment of the present invention.

[0102] like Figure 6 As shown, the automatic parking system includes:

[0103] An environmental perception module 601 is used to acquire environmental element information around the vehicle through the environmental perception module. The environmental element information includes element type and element pose. The element type includes parking space.

[0104] The parking space selection module 602 is used to determine the target parking space from the available parking spaces when an available parking space is detected.

[0105] The first parking position determination module 603 is used to establish the parking space coordinate system of the target parking space and determine the parking endpoint G1 and the first parking position of the parking endpoint G1 in the current vehicle coordinate system. The parking endpoint G1 is the position of the reference point on the vehicle in the target parking space when parking is completed.

[0106] The decision module 604 is used to plan an initial parking path for moving the reference point on the vehicle to the location of the first parking pose based on the environmental element information in the current vehicle coordinate system, with the reference point on the vehicle as the origin.

[0107] The control module 605 is used to control the parking of the vehicle according to the initial parking path.

[0108] Optionally, the first parking position determination module 603 includes:

[0109] The parking space coordinate system establishment submodule is used to establish the parking space coordinate system of the target parking space, with a point at the entrance of the target parking space as the parking space origin G0, the orientation of the target parking space as the positive Y-axis, and the right direction perpendicular to the Y-axis as the positive X-axis.

[0110] The preset distance parameter acquisition submodule is used to acquire the preset distance parameter of the vehicle relative to the boundary of the target parking space when parking is completed;

[0111] The parking endpoint determination submodule is used to determine the parking endpoint G1 in the target parking space based on the preset distance parameters and the position of the reference point on the vehicle in the vehicle.

[0112] The parking space coordinate system pose determination submodule is used to determine the pose of the parking end point G1 in the parking space coordinate system based on the pose relationship between the parking end point G1 and the parking space origin G0.

[0113] The vehicle coordinate system pose determination submodule is used to transform the pose of the parking endpoint G1 in the parking space coordinate system to the current vehicle coordinate system to obtain the first parking pose.

[0114] Optionally, the control module 605 includes:

[0115] The arc segment division submodule is used to divide the initial parking path into multiple continuous arc segments, and the configuration information of each arc segment includes the length and turning angle of the arc segment;

[0116] The control submodule is used to control the vehicle's movement based on the configuration information of the arc segment to achieve parking.

[0117] Optionally, the automatic parking system also includes:

[0118] The backup pose recording module is used to detect and save the backup pose of the parking space origin G0 in the vehicle coordinate system in the last N frames when the parking space origin G0 is within the detection range of the environmental perception module during the vehicle parking process. N is a preset positive integer greater than or equal to 1, and the parking space origin G0 is the location of the origin of the parking space coordinate system.

[0119] The parking space origin detection module is used to determine whether the parking space origin G0 is within the detection range of the environment perception module when the path replanning condition is triggered; if not, the contents of the first relative pose determination module are executed.

[0120] The first relative pose determination module is used to determine the first relative pose from the N frames of backup poses, and to use the location of the reference point on the vehicle when the first relative pose is detected as the relay point.

[0121] The vehicle driving data acquisition module is used to acquire vehicle driving data from the detection of the first relative pose to the triggering of the path replanning condition;

[0122] The second relative pose calculation module is used to calculate the second relative pose of the reference point on the current vehicle relative to the relay point based on the vehicle driving data.

[0123] The third relative pose module is used to determine the third relative pose of the parking space origin G0 relative to the reference point on the current vehicle based on the first relative pose and the second relative pose.

[0124] The first re-parking control module is used to control vehicle parking based on the third relative pose and current environmental element information.

[0125] Optionally, the first relative pose determination module includes:

[0126] The pose difference calculation submodule is used to calculate the pose difference between the backup poses in two adjacent frames.

[0127] An abnormal pose determination submodule is used to determine whether there is an abnormal pose in the N frames of the backup poses based on the change range of the pose difference; if so, the contents of the pose filtering submodule are executed.

[0128] The pose filtering submodule is used to remove the abnormal poses and determine the first relative pose based on the remaining backup poses.

[0129] Optionally, the vehicle driving data includes wheel speed sensor data, and the second relative pose calculation module includes:

[0130] The driving distance difference calculation submodule is used to calculate the total driving distance of the vehicle from the relay point to the current position and the driving distance difference between the left and right wheels of the vehicle based on the wheel speed meter data.

[0131] The vehicle turning angle calculation submodule is used to calculate the vehicle turning angle from the relay point to the current position based on the total driving distance and the difference in driving distance between the left and right wheels;

[0132] The second relative pose calculation submodule is used to determine the second relative pose of the reference point on the vehicle relative to the relay point based on the total driving distance and the vehicle turning angle.

[0133] Optionally, the automatic parking system also includes:

[0134] The second parking pose determination module is used to determine the second parking pose of the parking endpoint G1 in the current vehicle coordinate system when the path replanning condition is triggered and the parking space origin G0 is within the detection range of the environmental perception module.

[0135] The updated parking path planning module is used to plan an updated parking path in the current vehicle coordinate system, based on the current environmental element information, to move the reference point on the vehicle to the location of the second parking pose.

[0136] The second reparking module is used to control vehicle parking based on the first updated parking path.

[0137] Optionally, the second reparking module includes:

[0138] The fourth relative pose determination submodule is used to determine the fourth relative pose of the parking endpoint G1 relative to the reference point on the current vehicle based on the third relative pose and the relative pose of the parking endpoint G1 and the parking space origin G0.

[0139] The second updated parking path planning submodule is used to plan the second updated parking path based on the current environmental element information and the fourth relative pose, moving the reference point on the current vehicle to the parking endpoint G1.

[0140] The vehicle parking control submodule is used to control vehicle parking based on the second updated parking path.

[0141] The automatic parking system provided in this embodiment of the invention can execute the automatic parking method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0142] Figure 7A schematic diagram of an electronic device 40 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0143] like Figure 7 As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0144] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0145] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as automatic parking methods.

[0146] In some embodiments, the automatic parking method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the automatic parking method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the automatic parking method by any other suitable means (e.g., by means of firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, system, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0152] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0153] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0154] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. An automatic parking method, characterized in that, The method, applied to an automated parking system including an environmental perception module, comprises: The environmental perception module acquires information about environmental elements around the vehicle, including element type and element pose, and the element type includes parking space. When an available parking space is detected, the target parking space is determined from among the available parking spaces; Establish the parking space coordinate system of the target parking space and determine the parking endpoint G1 and the first parking pose of the parking endpoint G1 in the current vehicle coordinate system. The parking endpoint G1 is the position of the reference point on the vehicle in the target parking space when parking is completed. In the current vehicle coordinate system, an initial parking path is planned based on the environmental element information to move the reference point on the vehicle to the location of the first parking pose. The vehicle coordinate system takes the reference point on the vehicle as the origin. Control vehicle parking according to the initial parking path; During the vehicle parking process, when the parking space origin G0 is within the detection range of the environmental perception module, the last N frames of the parking space origin G0 in the vehicle coordinate system are detected and saved as backup poses. N is a preset positive integer greater than or equal to 1, and the parking space origin G0 is the location of the origin of the parking space coordinate system. When the path replanning condition is triggered, it is determined whether the parking space origin G0 is within the detection range of the environmental perception module; If not, determine the first relative pose from the backup poses in N frames, and use the location of the reference point on the vehicle when the first relative pose is detected as the relay point; Acquire vehicle driving data from the time the first relative pose is detected to the time when the path replanning condition is triggered; Calculate the second relative pose of the reference point on the current vehicle relative to the relay point based on the vehicle driving data; The third relative pose of the parking space origin G0 relative to the reference point on the current vehicle is determined based on the first relative pose and the second relative pose.

2. The method as described in claim 1, characterized in that, The establishment of the parking space coordinate system for the target parking space includes: The parking space coordinate system of the target parking space takes a point at the entrance of the target parking space as the origin G0, the orientation of the target parking space as the positive Y-axis, and the right direction perpendicular to the Y-axis as the positive X-axis. Determining the parking endpoint G1 and the first parking pose of the parking endpoint G1 in the current vehicle coordinate system includes: Obtain the preset distance parameter of the vehicle relative to the boundary of the target parking space when parking is completed; The parking endpoint G1 in the target parking space is determined based on the preset distance parameters and the position of the reference point on the vehicle within the vehicle. The pose of the parking endpoint G1 in the parking space coordinate system is determined based on the pose relationship between the parking endpoint G1 and the parking space origin G0. Transform the parking endpoint G1 in the parking space coordinate system to the current vehicle coordinate system to obtain the first parking pose.

3. The method as described in claim 1, characterized in that, The step of controlling vehicle parking based on the initial parking path includes: The initial parking path is divided into multiple continuous arc segments, and the configuration information of each arc segment includes the length and turning angle of the arc segment; The vehicle is controlled to drive based on the configuration information of the arc segment in order to achieve parking.

4. The method as described in claim 1, characterized in that, Determining the first relative pose from the N frames of backup poses includes: Calculate the pose difference between the backup poses in two adjacent frames; The abnormal pose is determined in the N frames of the backup pose based on the change range of the pose difference; N is a positive integer greater than or equal to 5. If so, the abnormal pose is removed, and the first relative pose is determined based on the remaining backup poses.

5. The method as described in claim 1, characterized in that, The vehicle driving data includes wheel speed measurement data, and the calculation of the second relative pose of the reference point on the current vehicle relative to the relay point based on the vehicle driving data includes: Calculate the total distance traveled by the vehicle from the relay point to its current position and the difference in travel distance between the left and right wheels of the vehicle based on the wheel speed meter data; The vehicle's turning angle from the relay point to its current position is calculated based on the total driving distance and the difference in driving distance between the left and right wheels. The second relative pose of the reference point on the vehicle relative to the relay point is determined based on the total travel distance and the vehicle turning angle.

6. The method as described in claim 1, characterized in that, When the path replanning condition is triggered and the parking space origin G0 is within the detection range of the environmental perception module, the following is also included: Determine the second parking pose of the parking endpoint G1 in the current vehicle coordinate system; In the current vehicle coordinate system, based on the current environmental element information, a first updated parking path is planned to move the reference point on the vehicle to the location of the second parking pose. Control vehicle parking based on the first updated parking path.

7. The method as described in claim 1, characterized in that, Controlling vehicle parking based on the third relative pose and current environmental element information includes: Based on the third relative pose and the relative pose of the parking endpoint G1 and the parking space origin G0, determine the fourth relative pose of the parking endpoint G1 relative to the reference point on the current vehicle. Based on the current environmental element information and the fourth relative pose, a second updated parking path is planned to move the reference point on the current vehicle to the parking endpoint G1. Vehicle parking is controlled based on the second updated parking path.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor to enable the at least one processor to perform the automatic parking method according to any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the automatic parking method according to any one of claims 1-7.

Images