Vehicle parking-out method and device, vehicle and computer program product

Abstract

The invention relates to the technical field of automatic driving, in particular to a vehicle parking-out method and device, a vehicle and a computer program product, and the method comprises the steps: receiving a parking-out instruction; planning a path to a middle target position according to the map data and the real-time sensing data based on the parking-out instruction; and after the parking space arrives at the middle target position, a final planning path is generated according to the real-time sensing data and the final target position, and the final planning path is executed to complete parking of the parking space from the middle target position to the final target position. Therefore, the problems that the parking efficiency is low and the parking is unsafe when the vehicle looks around invisible dynamic obstacles or looks around inaccurately are solved, the parking efficiency of the vehicle is improved, and the risks of low parking efficiency and scratching caused by inaccurate perception when the vehicle is parked out are reduced.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and more particularly to a vehicle parking method, device, vehicle, and computer program product. Background Art

[0002] With the popularity of autonomous driving related vehicles, the automatic parking function has become an important reference function for consumers to purchase cars. Automatic parking in and out are important components of automatic parking. How to improve the parking function has become an important issue for every manufacturer to consider, such as how to improve the success rate and efficiency of parking in. As an important component of automatic parking, how to improve the efficiency and safety of parking out has also become a practical problem faced by every self-driving engineer. This patent can improve the success rate and safety of parking.

[0003] The parking control method in the prior art is: when parking is activated, the parking space type is identified through the memory map and the memory path, and the parking path of the vehicle is calculated in real time in combination with the image and point cloud information obtained in real time during the parking process. According to the parking path, the vehicle is controlled to complete the parking. Alternatively, when a parking instruction is received, the surrounding obstacle information and surrounding vehicle information are obtained, and the vehicle is controlled to park according to the selected parking direction. However, these control methods are strongly dependent on perception. For the situation where there are no obstacles on both sides, the parking efficiency is relatively high. However, when the camera is blocked, such as the camera is blocked by pillars and walls, the invisible part during parking relies on the memory map, but the memory map only memorizes fixed obstacles, and will not memorize dynamic obstacles such as cars. There are many cases of rubbing the parking space during parking, and the efficiency is low. Secondly, when the surround view is blocked or the perception is inaccurate, such as the perception jumps, when the above control methods are used, it is easy to be stuck or scratched, which needs to be solved urgently. Summary of the invention

[0004] The present application provides a vehicle parking method, device, vehicle and computer program product to solve the problem that the parking efficiency is low and the parking is unsafe when the vehicle encounters dynamic obstacles that are not visible in the surround view or the surround view perception is inaccurate.

[0005] A first aspect of the present application provides a method for parking a vehicle, comprising the following steps: receiving a parking instruction; planning a path to an intermediate target location based on map data and real-time perception data based on the parking instruction, wherein the intermediate target location is a location that satisfies preset spatial constraints; after reaching the intermediate target location, generating a final planned path based on the real-time perception data and the final target location, and executing the final planned path to complete parking from the intermediate target location to the final target location.

[0006] Optionally, planning a path to reach the intermediate target position based on the map data and real-time perception data includes: extracting the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle at the initial position; determining a path to reach the intermediate target position based on the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle at the initial position.

[0007] Optionally, generating a final planned path based on the real-time perception data and the final target position includes: extracting the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position; determining the final planned path based on the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position.

[0008] Optionally, before planning a path to reach the intermediate target position based on the map data and real-time perception data, it further includes: obtaining initial perception data collected by multiple sensors; preprocessing the initial perception data and fusing the preprocessed initial perception data to obtain the real-time perception data, where the preprocessing includes denoising operations, filtering operations, and data correction operations.

[0009] Optionally, when executing the final planned path to complete parking out of the parking space from the intermediate target position to the final target position, it includes: detecting the working status of each execution system; if the working status of one or more of the execution systems is abnormal, stopping the parking out process.

[0010] Optionally, after executing the final planned path to complete parking out of the parking space from the intermediate target position to the final target position, it includes: feeding back a parking out success message to an external device so that the external device outputs a reminder message corresponding to the parking out success message.

[0011] An embodiment of the second aspect of the present application provides a parking out device for a vehicle, including: a receiving module for receiving a parking out instruction; a planning module for planning a path to reach an intermediate target position based on the parking out instruction, according to map data and real-time perception data, where the intermediate target position is a position that meets preset spatial constraint conditions; a parking module for generating a final planned path based on real-time perception data and a final target position after reaching the intermediate target position, and executing the final planned path to complete parking out of the parking space from the intermediate target position to the final target position.

[0012] Optionally, the planning module is further configured to: extract the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle at the initial position; determine a path to reach the intermediate target position based on the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle at the initial position.

[0013] Optionally, the parking module is further configured to: extract the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position; determine the final planned path based on the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position.

[0014] Optionally, before planning the path to the intermediate target position according to the map data and the real-time perception data, the planning module is further configured to: obtain the initial perception data collected by multiple sensors; preprocess the initial perception data and fuse the preprocessed initial perception data to obtain the real-time perception data, where the preprocessing includes denoising operations, filtering operations, and data correction operations.

[0015] Optionally, when executing the final planned path to complete the parking out from the intermediate target position to the final target position, the parking module is further configured to: detect the working state of each execution system; if the working state of one or more of the execution systems is abnormal, stop the parking out process.

[0016] Optionally, after executing the final planned path to complete the parking out from the intermediate target position to the final target position, the parking module is further configured to: feedback the parking out success information to an external device, so that the external device outputs a reminder message corresponding to the parking out success information.

[0017] An embodiment of the third aspect of the present application provides a vehicle, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the vehicle parking out method as described in the above embodiment.

[0018] An embodiment of the fourth aspect of the present application provides a computer program product, on which a computer program is stored, and the program is executed by a processor to be used to implement the vehicle parking out method as described in the above embodiment.

[0019] In the above implementation manner, based on the parking out instruction, the path to the intermediate target position is planned according to the map data and the real-time perception data, and the intermediate target position is a position that meets the preset space constraint conditions. After reaching the intermediate target position, the final planned path is generated according to the real-time perception data and the final target position, and the final planned path is executed to complete the parking out from the intermediate target position to the final target position. Thereby, it solves the problems that when the vehicle encounters dynamic obstacles that are not visible in the surround view or the surround view perception is inaccurate, the parking out efficiency is low and there are safety problems during parking out, improves the parking out efficiency of the vehicle, and reduces the risks of low parking out efficiency and scratching caused by inaccurate perception during parking out.

[0020] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present application. Description of the Drawings

[0021] The above-mentioned and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the drawings, where:

[0022] Figure 1 It is a flowchart of a vehicle parking-out method provided according to an embodiment of the present application;

[0023] Figure 2 It is a schematic structural diagram related to a vehicle parking-out method according to an embodiment of the present application;

[0024] Figure 3 It is a flowchart of a vehicle parking-out method according to an embodiment of the present application;

[0025] Figure 4 It is a schematic diagram of the intermediate target position range according to an embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of the left front parking-out process according to an embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of the final target position according to an embodiment of the present application;

[0028] Figure 7 It is an example diagram of a vehicle parking-out device according to an embodiment of the present application;

[0029] Figure 8 It is a schematic diagram of a vehicle structure according to an embodiment of the present application. Detailed Description of the Embodiments

[0030] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0031] The following describes a vehicle parking-out method, device, vehicle, and computer program product according to an embodiment of the present application with reference to the accompanying drawings. In view of the problems of low parking efficiency and unsafe parking-out when the vehicle cannot see dynamic obstacles in the panoramic view or the panoramic perception is inaccurate as mentioned in the above background art, the present application provides a vehicle parking-out method. In this method, based on a parking-out instruction, a path to an intermediate target position is planned according to map data and real-time perception data, where the intermediate target position is a position that meets preset spatial constraint conditions. After reaching the intermediate target position, a final planned path is generated according to real-time perception data and the final target position, and the final planned path is executed to complete the parking-out of the vehicle from the intermediate target position to the final target position. Thereby, the problems of low parking efficiency and unsafe parking-out when the vehicle cannot see dynamic obstacles in the panoramic view or the panoramic perception is inaccurate are solved, the parking-out efficiency of the vehicle is improved, and the risks of low parking efficiency and scratching caused by inaccurate perception during parking-out are reduced.

[0032] Specifically, Figure 1 is a schematic flowchart of a vehicle parking-out method provided by an embodiment of the present application.

[0033] In the present application, an instruction receiving module, a real-time perception module, a map memory module, a positioning module, and a planning and control module are involved, as Figure 2 shown. Among them,

[0034] The instruction receiving module is used to receive a vehicle parking-out instruction issued by a user; the real-time perception module is used to obtain surrounding environment information, such as obstacles, point clouds, and drivable areas of a camera, echo and point clouds of an ultrasonic wave, point clouds of a lidar, etc.; the map memory module is used to remember the surrounding environment information when entering the parking space. For example, after parking in the parking space for the first time, the limit block is under the vehicle. If not remembered, when parking out, neither the camera nor the ultrasonic wave can detect it, and when parking out, the planning module cannot receive relevant information, which may lead to parking-out failure; the positioning module is used to locate the position of the vehicle; the planning and control module is used to plan the vehicle parking-out according to the surrounding environment information.

[0035] As Figure 1 shown, the vehicle parking-out method includes the following steps:

[0036] In step S101, a parking-out instruction is received.

[0037] The driver can issue a parking-out instruction through a control button, a touch screen, or a voice control system in the vehicle. For example, select the "Vehicle Parking-Out" function on the touch screen, or say "Start Vehicle Parking-Out" through a voice command.

[0038] The driver can use an external device (such as a smartphone, a smartwatch, etc.) paired with the vehicle to issue a parking-out instruction. Through the vehicle APP or the application of the smartwatch, the driver can remotely control the parking-out operation of the vehicle.

[0039] In step S102, based on the parking-out instruction, a path to an intermediate target position is planned according to the map data and the real-time perception data, where the intermediate target position is a position that satisfies the preset spatial constraint conditions.

[0040] Specifically, as Figure 3 shown, based on the parking-out instruction, a path to an intermediate target position is planned according to the map data and the real-time perception data. The intermediate target position is a position that satisfies the preset spatial constraint conditions, and it can also be understood that the intermediate target position is a position where there is no effective occlusion within a certain distance of the vehicle. Taking the example of parking out to the left front in a perpendicular parking space, as Figure 4 shown, the intermediate target position maintains a certain distance C (C≥0, a calibrated value) from the left front obstacle, a distance B (B≥20 cm) from the left obstacle, and a distance A (A≥30 cm) from the right obstacle.

[0041] As an embodiment, it can be:

[0042] The vehicle first receives a parking-out instruction from the host computer. The system obtains the map data of the parking lot from the database, including the parking space layout, aisle width, obstacle positions, etc. The vehicle uses sensors (such as cameras, lidar, ultrasonic radars, etc.) to perceive the surrounding environment in real time, including dynamic obstacles (such as pedestrians, other vehicles) and static obstacles (such as walls, columns, etc.).

[0043] Based on the map data and the real-time perception data, the system uses a path planning algorithm (such as the A* algorithm, Dijkstra algorithm, etc.) to generate a preliminary path from the current parking space to the intermediate target position.

[0044] It should be noted that if the path to the intermediate target position cannot be planned according to the map data and the real-time perception data, the current automatic parking-out process is ended, and the user is reminded to take over the vehicle manually.

[0045] Optionally, in some embodiments, before planning the path to the intermediate target position according to the map data and the real-time perception data, it further includes: obtaining the initial perception data collected by multiple sensors; preprocessing the initial perception data, and fusing the preprocessed initial perception data to obtain the real-time perception data, where the preprocessing includes denoising operations, filtering operations, and data correction operations.

[0046] Since the data collected by sensors often contains noise, missing values, and outliers, directly using it for path planning may lead to inaccurate results. Therefore, it is necessary to preprocess the initial perception data to improve the quality and reliability of the data.

[0047] Specifically, for the denoising operation: By using mathematical methods or filtering algorithms, the noise components in the data are removed, and the useful signals are retained. For example, methods such as Kalman filtering, mean filtering, or wavelet transform can be used for denoising.

[0048] Filtering operation: Different filtering algorithms are applicable to different data types and application scenarios. For example, the clipping filtering method is suitable for eliminating accidental pulse interference, the median filtering method is suitable for removing occasional spike noises, and the arithmetic mean filtering method is suitable for smoothing signals with slow changes.

[0049] Data correction operation: The data correction operation corrects the sensor output by comparing it with known standard data or reference data to improve the accuracy of the data. For example, methods such as zero-offset calibration and scale calibration can be used to correct sensors such as accelerometers and gyroscopes.

[0050] Since different types of sensors have different sensing capabilities and limitations, the data of a single sensor may not comprehensively and accurately reflect the environment around the vehicle. Therefore, it is necessary to fuse the preprocessed initial perception data to obtain more comprehensive and accurate real-time perception data.

[0051] Among them, there are various methods for data fusion, including data-level fusion, feature-level fusion, and decision-level fusion, etc. In the parking system, common fusion methods may include the weighted average method, Kalman filtering method, Bayesian estimation method, Dempster-Shafer evidence reasoning method, etc.

[0052] In step S103, after reaching the intermediate target position, a final planned path is generated based on the real-time perception data and the final target position, and the final planned path is executed to complete the parking out of the vehicle from the intermediate target position to the final target position.

[0053] Optionally, in some embodiments, planning the path to reach the intermediate target position based on the map data and the real-time perception data includes: extracting the center point of the rear axle of the vehicle within the intermediate target position and the center point of the rear axle of the vehicle at the initial position; determining the path to reach the intermediate target position based on the center point of the rear axle of the vehicle within the intermediate target position and the center point of the rear axle of the vehicle at the initial position.

[0054] Optionally, in some embodiments, generating the final planned path based on the real-time perception data and the final target position includes: extracting the center point of the rear axle of the vehicle within the intermediate target position and the center point of the rear axle of the vehicle within the final target position; determining the final planned path based on the center point of the rear axle of the vehicle within the intermediate target position and the center point of the rear axle of the vehicle within the final target position.

[0055] It can be understood that, as Figure 3As shown, when the vehicle successfully reaches the intermediate target position, the system will pause the current driving and re-evaluate the surrounding environment. Using sensors (such as cameras, lidar, etc.) to sense data in real time, update the perception data of the surrounding environment, and extract the center point of the rear axle of the vehicle within the intermediate target position and the preset center point of the rear axle of the vehicle within the final target position. These two points serve as key reference points for path planning. Based on these two key points, the system adopts a path planning algorithm to generate a final planned path from the intermediate target position to the final target position.

[0056] Suppose in an intelligent parking lot, the vehicle needs to park out from the current parking space (initial position), pass through an intermediate target position (such as a spacious turning area), and finally reach the exit parking space (final target position). The system first extracts the center point of the rear axle of the vehicle within the current parking space and the preset center point of the rear axle of the vehicle within the intermediate target position. Based on these two points, the system plans a path to avoid obstacles so that the vehicle can successfully reach the intermediate target position. After the vehicle reaches the intermediate target position, the system pauses the driving and updates the perception of the surrounding environment. Assuming that no new obstacles appear at this time, the system extracts the center point of the rear axle of the vehicle within the intermediate target position and the preset center point of the rear axle of the vehicle within the exit parking space. Based on these two points, the system generates a final planned path from the intermediate target position to the exit parking space, and the vehicle starts driving according to the final plan and finally successfully reaches the exit parking space.

[0057] This application takes the example of parking out to the left front from a vertical parking space. As Figures 4 - 6 shown, based on the initial position (the initial position is Figure 4 the position of the black solid and dashed frame 1) and the real-time perception data at this position, plan a path to reach the intermediate target position (the intermediate target position is Figure 4 the position of the black dashed and solid frame 2). The range of the intermediate target position can refer to Figure 4 the position, the distance C between the front side point of the B-pillar ( Figure 4 the B-pillar of ) and the left front side of the obstacle (for example, C≥0, here is a calibrated value), the distance B from the left side of the obstacle (for example, C≥20cm, here is a calibrated value), and the distance A from the right obstacle (for example, C≥30cm, here is a calibrated value).

[0058] Further, extract the center point of the rear axle of the vehicle in the intermediate target position ( Figure 5 point E in ) and the center point of the rear axle of the vehicle at the initial position ( Figure 5 point D in ). Pass through point D and point E, and be tangent to the vehicle center line at point E. A planned path S1 from point D to point E to reach the intermediate target position is formed. As Figure 5 shown, the method of forming the planned path can be a geometric algorithm, A* algorithm or machine learning, etc. The steering wheel angle is used to evaluate the quality of S1. The smaller the angle, the better S1. Through the formula ( (where $\theta$ is the steering wheel angle, $L$ is the wheelbase, and $R$ is the turning radius), the tire angle can be calculated, and the steering wheel angle can be obtained using the speed ratio $i$ between the steering wheel and the tire angle. If the steering wheel angle is smaller, it is determined that S1 is better.

[0059] After reaching the intermediate target position, combining the real-time perception data and the final target position, the final target position is Figure 6 the red dotted box 3 as shown. The range of the final target position is as Figure 6 shown. There is a lateral distance $G$ (e.g., $\geq0.1m$, which is a calibrated value here) between it and the initial position ( Figure 6 the black solid box in it), a longitudinal distance $H$ (e.g., 4m, which is a calibrated value here) between it and the initial position, an angle $\theta$ (e.g., $90^{\circ}\pm10^{\circ}$, which is a calibrated value here) between the center lines $O1$ and $O2$. A planned path $S2$ is formed through points $E$ and $F$ as Figure 5 shown. The method for forming the planned path can be a geometric algorithm, the A* algorithm, machine learning, etc., and the steering wheel angle is used to evaluate the quality of the final planned path $S2$. The smaller the angle, the better the final planned path $S2$.

[0060] For example, a geometric algorithm forms a planned circular arc path $S2$ from point $E$ to point $F$, a circular arc that is tangent to the intermediate target position at point $F$. The fixed radius $R$ of the circular arc is known. Through the formula ( where $\theta$ is the steering wheel angle, $L$ is the wheelbase, and $R$ is the turning radius), the tire angle can be calculated, and the steering wheel angle can be obtained using the speed ratio $i$ between the steering wheel and the tire angle. If the steering wheel angle is smaller, it is determined that the final planned path $S2$ is better.

[0061] It should be noted that if a path to reach the final target position cannot be planned based on the real-time perception data and the final target position, the current automatic parking out process is ended, and the user is reminded to take over the vehicle manually.

[0062] Optionally, in some embodiments, when executing the final planned path to complete the parking out of the vehicle from the intermediate target position to the final target position, it includes: detecting the working state of each execution system; if the working state of one or more execution systems is abnormal, the parking out process is stopped.

[0063] Specifically, the vehicle starts from the intermediate target position and drives towards the final target position according to the final planned path. During the execution of the final planned path, the parking system will monitor the working states of various execution systems on the vehicle in real time. These execution systems can include the steering system, the braking system, the power system (such as the engine or the motor), etc.

[0064] The system obtains the working state data of each execution system through sensors or controllers, such as steering angle, braking pressure, engine speed, etc. Suppose that during the execution of the parking out process, the system detects an abnormality in the steering system. For example, the steering system cannot perform the operation corresponding to the control instruction, or although it can perform the operation, the steering angle is inaccurate (i.e., abnormal operation). This abnormality may be due to a malfunction of the steering system itself (such as motor failure, sensor failure, etc.), or due to other external factors (such as tire skidding caused by uneven road surface). Once the system detects an abnormality in the working state of the steering system, it will immediately determine that there is a risk of an accident if the vehicle continues to park out (for example, the vehicle may not be able to drive along the planned path, thus colliding with other vehicles or obstacles).

[0065] Therefore, the system will immediately stop the parking out process to avoid potential accident risks.

[0066] Specific example: Suppose a vehicle is about to park out in an underground parking lot with a complex environment and closely parked surrounding vehicles. The vehicle starts from the middle target position and drives towards the final target position according to the planned path.

[0067] During the execution of the parking out process, the system detects an abnormality in the steering system. For example, when a steering instruction is issued through the touch screen, the steering angle of the vehicle significantly deviates from the expected value.

[0068] The parking system immediately identifies that there is an abnormality in the working state of the steering system and determines that there is a risk of collision with surrounding vehicles or obstacles if the vehicle continues to park out. Therefore, the system immediately controls the vehicle to stop and displays an error message on the in-vehicle display screen to inform the driver that there is a malfunction in the steering system.

[0069] After seeing the error message, the driver realizes that the vehicle cannot continue to park out automatically, so he takes over the vehicle control and safely drives the vehicle out of the parking space through manual operation.

[0070] Optionally, in some embodiments, after completing the parking out of the parking space from the middle target position to the final target position by executing the final planned path, it includes: feeding back the parking out success information to an external device so that the external device outputs a reminder message corresponding to the parking out success information.

[0071] It can be understood that the vehicle parks out to the final target position according to the final planned path, and the parking system detects that the vehicle has stopped stably and determines that the parking out operation is successfully completed.

[0072] The parking system encodes the parking out success information into a message or signal through the vehicle-mounted communication module, and this message or signal is sent to the mobile phone through a wireless connection method (such as Bluetooth, Wi-Fi, etc.), and the mobile phone receives the parking out success information from the vehicle.

[0073] The relevant application program on the mobile phone (which may be the official APP provided by the car manufacturer or a third-party intelligent parking assistance APP) parses this information and identifies the status of successful parking out.

[0074] Based on the information of successful parking out, the application program generates a reminder message, such as "Parking successful, the vehicle has stopped stably in parking space XX". This reminder message is displayed on the screen of the mobile phone or broadcast in voice form through the speaker of the mobile phone.

[0075] According to the vehicle parking-out method proposed in the embodiment of the present application, based on the parking-out instruction, a path to reach the intermediate target position is planned according to the map data and real-time perception data, and the intermediate target position is a position that meets the preset space constraint conditions. After reaching the intermediate target position, a final planned path is generated according to the real-time perception data and the final target position, and the final planned path is executed to complete the parking out of the vehicle from the intermediate target position to the final target position. Thereby, the problems that when the vehicle encounters dynamic obstacles that are not visible by the surround view or the surround view perception is inaccurate, the parking efficiency is low and there are safety problems during parking out are solved, the parking-out efficiency of the vehicle is improved, and the risks of low parking efficiency and scratching caused by inaccurate perception during parking out are reduced.

[0076] Next, the vehicle parking-out device proposed in the embodiment of the present application will be described with reference to the accompanying drawings.

[0077] Figure 7 It is a block diagram of the vehicle parking-out device according to the embodiment of the present application.

[0078] As Figure 7 shown, the vehicle parking-out device 10 includes: a receiving module 100, a planning module 200, and a parking module 300.

[0079] Among them, the receiving module 100 is used to receive the parking-out instruction; the planning module 200 is used to plan a path to reach the intermediate target position based on the parking-out instruction according to the map data and real-time perception data, and the intermediate target position is a position that meets the preset space constraint conditions; the parking module 300 is used to generate a final planned path according to the real-time perception data and the final target position after reaching the intermediate target position, and execute the final planned path to complete the parking out of the vehicle from the intermediate target position to the final target position.

[0080] Optionally, in some embodiments, the planning module 200 is further used to: extract the center point of the vehicle's rear axle in the intermediate target position and the center point of the vehicle's rear axle at the initial position; determine the path to reach the intermediate target position according to the center point of the vehicle's rear axle in the intermediate target position and the center point of the vehicle's rear axle at the initial position.

[0081] Optionally, in some embodiments, the parking module 300 is further configured to: extract the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position; determine the final planned path based on the center point of the vehicle's rear axle within the intermediate target position and the center point of the vehicle's rear axle within the final target position.

[0082] Optionally, in some embodiments, before planning the path to the intermediate target position according to the map data and the real-time perception data, the planning module 200 is further configured to: obtain the initial perception data collected by multiple sensors; perform preprocessing on the initial perception data and fuse the preprocessed initial perception data to obtain the real-time perception data, where the preprocessing includes denoising operations, filtering operations, and data correction operations.

[0083] Optionally, in some embodiments, when executing the final planned path to complete the parking out from the intermediate target position to the final target position, the parking module 300 is further configured to: detect the working state of each execution system; if the working state of one or more execution systems is abnormal, stop the parking out process.

[0084] Optionally, in some embodiments, after executing the final planned path to complete the parking out from the intermediate target position to the final target position, the parking module 300 is further configured to: feedback the parking out success information to an external device so that the external device outputs a reminder message corresponding to the parking out success information.

[0085] It should be noted that the foregoing explanation of the embodiments of the vehicle parking out method also applies to the vehicle parking out device of this embodiment, and will not be elaborated here.

[0086] According to the vehicle parking out device provided by the embodiments of the present application, based on the parking out instruction, plan the path to the intermediate target position according to the map data and the real-time perception data, where the intermediate target position is a position that meets the preset space constraint conditions. After reaching the intermediate target position, generate the final planned path according to the real-time perception data and the final target position, and execute the final planned path to complete the parking out from the intermediate target position to the final target position. Thereby, it solves the problems that when the vehicle has invisible dynamic obstacles in the surround view or the surround view perception is inaccurate, the parking out efficiency is low and there are safety problems during parking out, improves the parking out efficiency of the vehicle, and reduces the risks of low parking out efficiency and scratching caused by inaccurate perception during parking out.

[0087] Figure 8 The structural schematic diagram of the vehicle provided by the embodiments of the present application. The vehicle may include:

[0088] A memory 801, a processor 802, and a computer program stored on the memory 801 and executable on the processor 802.

[0089] When the processor 802 executes the program, it implements the vehicle parking-out method provided in the above embodiments.

[0090] Furthermore, the vehicle further includes:

[0091] A communication interface 803, which is used for communication between the memory 801 and the processor 802.

[0092] A memory 801, which is used to store a computer program that can run on the processor 802.

[0093] The memory 801 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory.

[0094] If the memory 801, the processor 802, and the communication interface 803 are implemented independently, the communication interface 803, the memory 801, and the processor 802 can be interconnected through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of simplicity of representation, Figure 8 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0095] Optionally, in a specific implementation, if the memory 801, the processor 802, and the communication interface 803 are integrated on a chip, the memory 801, the processor 802, and the communication interface 803 can communicate with each other through an internal interface.

[0096] The processor 802 may be a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0097] The embodiments of the present application further provide a computer program product, on which a computer program is stored, and when the program is executed by a processor, it implements the above vehicle parking-out method.

[0098] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0099] In addition, the terms "first" and "second" are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of such features. In the description of this application, the meaning of "N" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0100] Any process or method description shown in a flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more N executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of this application includes additional implementations, where the functions can be executed in a substantially simultaneous manner or in the reverse order according to the involved functions, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of this application pertain.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer program product for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer program product" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in combination with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer program products include the following: an electrical connection part (electronic device) having one or N wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer program product can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then storing it in a computer memory.

[0102] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0103] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the said program can be stored in a computer program product. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0104] In addition, each functional unit in various embodiments of the present application may be integrated into a processing module, may exist physically alone for each unit, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer program product.

[0105] The above-mentioned computer program product may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for parking a vehicle, characterized in that: The following steps are involved: receiving a docking instruction; Based on the parking instruction, a path to an intermediate target position is planned according to map data and real-time perception data, wherein the intermediate target position is a position that satisfies a preset spatial constraint condition; After reaching the intermediate target location, a final planned path is generated according to the real-time perception data and the final target location, and the final planned path is executed to complete parking from the intermediate target location to the final target location.

2. The method according to claim 1, characterized in that The planning of a path to the intermediate target location according to the map data and the real-time perception data includes: Extracting the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle at the initial position; A path to the intermediate target position is determined based on the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle at the initial position.

3. The method according to claim 1, characterized in that Generating a final planning path according to the real-time perception data and the final target position includes: Extracting the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle in the final target position; The final planned path is determined based on the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle in the final target position.

4. The method according to claim 1, characterized in that: Before planning the path to the intermediate destination based on map data and real-time perception data, it also includes: Obtain initial perception data collected by multiple sensors; The initial perception data is preprocessed, and the preprocessed initial perception data is fused to obtain the real-time perception data, wherein the preprocessing includes a denoising operation, a filtering operation, and a data correction operation.

5. The method according to claim 1, characterized in that When executing the final planned path to complete parking from the intermediate target location to the final target location, the method includes: Detect the working status of each execution system; If there is an abnormality in the working status of one or more of the execution systems, the parking process is stopped.

6. The method according to claim 1, characterized in that After executing the final planned path to complete parking from the intermediate target location to the final target location, the method includes: Feedback the parking success information to the external device, so that the external device outputs the reminder information corresponding to the parking success information.

7. A vehicle parking device, characterized in that: include: A receiving module, used for receiving a docking instruction; A planning module, configured to plan a path to an intermediate target location based on the parking instruction, map data and real-time perception data, wherein the intermediate target location is a location that satisfies a preset spatial constraint condition; The parking module is used to generate a final planning path according to the real-time perception data and the final target position after reaching the intermediate target position, and execute the final planning path to complete parking from the intermediate target position to the final target position.

8. The device according to claim 7, characterized in that The planning module is also used for: Extracting the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle at the initial position; A path to the intermediate target position is determined based on the center point of the rear axle of the vehicle in the intermediate target position and the center point of the rear axle of the vehicle at the initial position.

9. A vehicle, characterized in that: The system comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle parking method as claimed in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the vehicle parking method according to any one of claims 1 to 6 is implemented.

Images