Automatic parking method and device

Abstract

An automatic parking method is provided. The method includes the steps of: determining parking space information for a plurality of candidate parking spaces based on a first image and a second image of an own vehicle, where the parking space information indicates the location of the parking space in a multi-story parking garage, the first image being an environmental image in a first orientation of the own vehicle, and the second image being a panoramic surround view image of the own vehicle; determining a target parking space from the plurality of candidate parking spaces based on the parking space information for the plurality of candidate parking spaces; and controlling the own vehicle so that the own vehicle is parked in the target parking space. This automatic parking method enables more accurate recognition of parking spaces, improving the accuracy of parking space detection results. An automatic parking device is also provided.

Description

[Technical Field]

[0001] The present application relates to the field of automated driving technology, and in particular to an automated parking method and apparatus. [Background technology]

[0002] With the development of intelligent driving technology, automatic parking functions are being applied more and more widely to meet people's demands for a convenient and safe parking experience. The automatic parking function can be applied to the cruising phase and the parking phase. In the cruising phase, the automatic parking function is mainly used to detect parking spaces, and in the parking phase, the automatic parking function is mainly used to park the vehicle in the detected parking space.

[0003] However, when a current automatic parking function detects a parking space, obstacle information may be recognized as parking space information. In other words, an obstacle that is not a parking space may be recognized as a parking space. If the vehicle is then parked in the incorrectly detected parking space, there is a risk of collision with various obstacles, such as other vehicles.

[0004] Therefore, how to improve the accuracy of parking space detection results is important for implementing automatic parking functions in order to safely park a vehicle in a parking space. Summary of the Invention [Problem to be solved by the invention]

[0005] The present application provides an automatic parking method and apparatus for improving the accuracy of parking space detection results. [Means for solving the problem]

[0006] To achieve the aforementioned objectives, the present application uses the following technical solutions:

[0007] According to a first aspect, the present application provides an automatic parking method, including: determining parking space information for a plurality of candidate parking spaces based on a first image and a second image of an egocentric vehicle, the parking space information indicating a location of the parking space in a multi-story parking garage, the first image being an environmental image in a first orientation of the egocentric vehicle, and the second image being a panoramic surround view image of the egocentric vehicle; determining a target parking space from the plurality of candidate parking spaces based on the parking space information for the plurality of candidate parking spaces; and controlling the egocentric vehicle to park in the target parking space.

[0008] Based on the above technical solution, in a parking scenario in a multi-story parking garage and during a vehicle cruise phase, i.e., during the process of searching for a parking space, parking space information for the multiple candidate parking spaces is determined based on an environmental image in a specific orientation of the host vehicle and a panoramic surround-view image of the host vehicle. The parking space information may indicate the location of the parking space. That is, the parking space is detected based on the environmental image and the panoramic image in a specific orientation. If a parking space is detected in both the environmental image and the panoramic image in a first orientation, it indicates a high probability of the existence of the parking space. In this way, the accuracy of the parking space detection result can be improved. In addition, the panoramic image has a wider field of view, which can improve the probability of detecting a parking space.

[0009] In one possible design, the step of determining parking space information for a plurality of candidate parking spaces based on a first image and a second image of the host vehicle includes: determining parking space information for at least one first candidate parking space based on a first image of the host vehicle, wherein the first image includes an image of the at least one first candidate parking space; and determining parking space information for at least one second candidate parking space based on a second image of the host vehicle, wherein the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space.

[0010] Based on this configuration, a parking space is detected based on an environmental image and a panoramic image in a specific direction. If a parking space is detected in both the environmental image and the panoramic image in a specific direction, it indicates a high probability that a parking space exists. In this way, the accuracy of the parking space detection result can be improved. In addition, the panoramic image has a wider field of view, which can improve the probability of detecting a parking space.

[0011] In one possible design, the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space corner, and a positional relationship between the parking space corners.

[0012] In one possible design, the parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and a vertex coordinate of the parking space.

[0013] In one possible design, the step of determining a target parking space from the plurality of candidate parking spaces based on parking space information of the plurality of candidate parking spaces includes: determining at least one third candidate parking space based on parking space information of the at least one first candidate parking space and parking space information of the at least one second candidate parking space, wherein the third candidate parking space is a parking space having a confidence level equal to or greater than a predetermined confidence level threshold for the at least one second candidate parking space and belongs to the at least one first candidate parking space, wherein the confidence level indicates the accuracy of the parking space detection result; and determining a target parking space based on the at least one third candidate parking space.

[0014] Based on this design, the target parking space is determined based on the confidence level of the candidate parking space, and the confidence level can reflect the accuracy of the parking space detection result. In this way, the candidate parking space whose confidence level meets the preset confidence level threshold, for example, the candidate parking space with a high confidence level, is used as the target parking space, that is, the candidate parking space that is accurately detected is used as the target parking space. This can further improve the accuracy of the parking space detection result.

[0015] In one possible design, the method further includes capturing a third image of the ego-vehicle in the process of controlling the ego-vehicle to park in the target parking space, the third image being an environment image in a third orientation of the ego-vehicle, the third image including an image of the target parking space; and updating parking space information of the target parking space based on the third image. Based on this design, in a parking scenario in a multi-story parking garage and in the parking phase, i.e., in the process of parking the ego-vehicle in the target parking space, the parking space information of the target parking space is calibrated by using the third image including the target parking space. This can improve parking accuracy.

[0016] In one possible design, the step of determining parking space information of at least one first candidate parking space based on a first image of the host vehicle includes: inputting the first image into a first preset model; and outputting parking space information of the at least one first candidate parking space through the first preset model. Based on this design, the first image is input into the model to recognize candidate parking spaces, and compared with conventional feature extraction algorithms, the model is less affected by the environment, light, and the like. This can improve the accuracy of the parking space detection result. Also, compared with conventional feature extraction algorithms, the model can avoid excessive manual parameter adjustment and improve the robustness of the entire algorithm.

[0017] In one possible design, the step of determining parking space information of at least one second candidate parking space based on a second image of the host vehicle includes: inputting the second image into a second preset model; and outputting parking space information of the at least one second candidate parking space through the second preset model. Based on this design, the panoramic image is input into the model to recognize candidate parking spaces, and compared with conventional feature extraction algorithms, the model is less affected by the environment, light, and the like. This can improve the accuracy of the parking space detection results. Furthermore, compared with conventional feature extraction algorithms, the model can avoid excessive manual parameter adjustment and improve the robustness of the entire algorithm.

[0018] According to a second aspect, the present application provides an automatic parking device. The automatic parking device includes a corresponding module or unit for implementing the aforementioned method. The module or unit may be implemented by hardware, software, or hardware by executing corresponding software. In one possible design, the automatic parking device includes a processing unit (also referred to as a processing module). The processing unit is configured to determine parking space information for a plurality of candidate parking spaces based on a first image and a second image of an ego-vehicle, where the parking space information indicates a location of the parking space in a multi-story parking garage, the first image is an environmental image at a first orientation of the ego-vehicle, and the second image is a panoramic surround-view image of the ego-vehicle; the processing unit is further configured to determine a target parking space from the plurality of candidate parking spaces based on the parking space information for the plurality of candidate parking spaces; and the processing unit is further configured to control the ego-vehicle to be parked in the target parking space.

[0019] In one possible design, the processing unit is specifically configured to determine parking space information for at least one first candidate parking space based on a first image of the host vehicle, where the first image includes an image of the at least one first candidate parking space; and the processing unit is specifically configured to determine parking space information for at least one second candidate parking space based on a second image of the host vehicle, where the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space.

[0020] In one possible design, the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space angle, and a positional relationship between the parking space angles.

[0021] In one possible design, the parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and a vertex coordinate of the parking space.

[0022] In one possible design, the processing unit is specifically configured to determine at least one third candidate parking space based on parking space information of the at least one first candidate parking space and parking space information of the at least one second candidate parking space, where the third candidate parking space is a parking space in the at least one second candidate parking space that has a confidence level equal to or greater than a preset confidence level threshold and belongs to the at least one first candidate parking space, where the confidence level indicates the accuracy of the parking space detection result; and the processing unit is specifically configured to determine a target parking space based on the at least one third candidate parking space.

[0023] In one possible design, the processing unit is further configured to capture a third image of the host vehicle in the process of controlling the host vehicle to park in the target parking space, the third image being an environmental image at a third orientation of the host vehicle, and the third image including an image of the target parking space; and the processing unit is further configured to update parking space information of the target parking space based on the third image.

[0024] In one possible design, the processing unit is specifically configured to input a first image into a first preset model and output parking space information of the at least one first candidate parking space through the first preset model.

[0025] In one possible design, the processing unit is specifically configured to input the second image into a second preset model and output parking space information of the at least one second candidate parking space through the second preset model.

[0026] According to a third aspect, the present application provides an automated parking system including a processor, the processor coupled to a memory, and the processor configured to execute a computer program stored in the memory to cause the automated parking system to perform a method according to the first aspect and any design of the first aspect. Optionally, the memory may be coupled to the processor or may be separate from the processor.

[0027] In one possible design, the automated parking device further includes a communication interface that may be used by the automated parking device to communicate with another device. For example, the communication interface may be a transceiver, an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, associated circuitry, etc.

[0028] The automatic parking device in the third aspect may be a computing platform in an intelligent driving system, and the computing platform may be an in-vehicle computing platform or a cloud computing platform.

[0029] According to a fourth aspect, the present application provides a computer-readable storage medium containing a computer program or instructions that, when executed on an automated driving device, enables the automated driving device to perform a method according to the first aspect and any design of the first aspect.

[0030] According to a fifth aspect, the present application provides a computer program product, the computer program product including computer programs or instructions that, when executed on a computer, enable the computer to perform a method according to the first aspect and any design of the first aspect.

[0031] According to a sixth aspect, the present application provides a chip system including at least one processor and at least one interface circuit, the at least one interface circuit configured to perform a transmit / receive function and send instructions to the at least one processor, and when the at least one processor executes the instructions, the at least one processor performs a method according to the first aspect and any design of the first aspect.

[0032] It should be noted that the technical effects provided by any design of the second to sixth aspects refer to the technical effects provided by the corresponding design of the first aspect, and the details will not be described again in this specification. [Brief explanation of the drawings]

[0033] [Figure 1] FIG. 1 is a diagram of a system architecture according to an embodiment of the present application.

[0034] [Figure 2] FIG. 2 is a diagram of the structure of a control device according to an embodiment of the present application.

[0035] [Figure 3] FIG. 1 is a functional block diagram of a vehicle according to an embodiment of the present application.

[0036] [Figure 4] FIG. 1 is a diagram of a camera deployed in a vehicle according to an embodiment of the present application.

[0037] [Figure 5] 1 is a schematic flowchart of an automatic parking method according to an embodiment of the present application.

[0038] [Figure 6-1] FIG. 1 is a diagram of a goal-directed scenario according to an embodiment of the present application. [Figure 6-2] FIG. 1 is a diagram of a goal-directed scenario according to an embodiment of the present application.

[0039] [Figure 7] FIG. 1 is a view of a parking space entrance direction according to an embodiment of the present application.

[0040] [Figure 8] FIG. 1 is a diagram of a parking scenario according to an embodiment of the present application.

[0041] [Figure 9] 1 is a diagram of the structure of an automatic parking device according to an embodiment of the present application;

[0042] [Figure 10] 1 is a diagram of the structure of a chip system according to an embodiment of the present application. DETAILED DESCRIPTION OF THE INVENTION

[0043] The following describes the technical solutions of the embodiments in this application with reference to the accompanying drawings.

[0044] In the description of this application, unless otherwise specified, the symbol " / " indicates that the associated objects are in an "or" relationship. For example, A / B may represent A or B. The term "and / or" in this application simply describes the associated relationship between the associated objects and indicates that three relationships may exist. For example, A and / or B may represent three cases: only A is present, both A and B are present, or only B is present. A and B may be singular or plural.

[0045] Also, in this description, "plurality" means two or more unless otherwise specified. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or multiple items. For example, at least one of a, b, or c can refer to a, b, c, a and b, a and c, b and c, and a, b and c, where a, b, and c can be singular or plural.

[0046] In addition, in order to clearly describe the technical solutions in the embodiments of the present application, terms such as "first" and "second" are used to distinguish between the same or similar items that provide essentially the same function or purpose in the embodiments of the present application. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity or execution sequence, and terms such as "first" and "second" do not indicate clear distinctions.

[0047] Additionally, in the embodiments of the present application, the words "example" or "for example" indicate providing an example, illustration, or explanation. Any embodiment or design solution described in the embodiments of the present application as an "example" or "for example" should not be described as being preferred or having more advantages than another embodiment or design solution. Rather, the use of terms such as "example" or "for example" is intended to present related concepts in a concrete manner for ease of understanding.

[0048] The features, structures, or characteristics herein may be combined in any suitable manner in one or more embodiments. The sequence numbers of the processes do not imply the execution sequence in the embodiments of the present application. The execution sequence of the processes should be determined according to the functions and internal logic of the processes, and should not be construed as any limitation on the implementation process of the embodiments of the present application.

[0049] In some scenarios, some optional features in the embodiments of the present application may be implemented independently without relying on other features to solve corresponding technical problems and achieve corresponding effects, or in some scenarios, optional features may be combined with other features based on requirements.

[0050] In this application, unless otherwise specified, the same or similar parts in the embodiments will be referred to each other. In the embodiments of this application, unless otherwise specified or there is no logical contradiction, the terms and / or descriptions between different embodiments are consistent and may be referred to each other, and the technical features in different embodiments may be combined based on their internal logical relationships to form a new embodiment. The implementation of this application is not intended to limit the protection scope of this application.

[0051] In addition, the network architectures and service scenarios described in the embodiments of the present application are intended to more clearly explain the technical solutions in the embodiments of the present application, and do not constitute limitations on the technical solutions provided in the embodiments of the present application. Those skilled in the art can know that: with the evolution of network architectures and the emergence of new service scenarios, the technical solutions provided in the embodiments of the present application can also be applied to similar technical problems.

[0052] The technical solutions in the embodiments of the present application may be applied to various automatic parking systems, for example, automatic parking systems based on any communication standard, such as vehicle-to-everything (V2X) communication, device-to-device (D2D) communication, Internet of Vehicles, or driverless driving systems.

[0053] For example, Figure 1 is a diagram of a system architecture according to an embodiment of the present application. As shown in Figure 1, a system 10 includes a control device 11 and a vehicle 12.

[0054] The control device 11 can provide an automatic parking service for the vehicle 12 and may be a device with wireless and / or wired receiving and transmitting capabilities, or may be a module, chip system, subsystem, or other component disposed within the device, or may be a device set including multiple devices. In the embodiments of the present application, a device, device set, module, chip, subsystem, or other component capable of providing an automatic parking service is collectively referred to as a control device. The control device 11 includes, but is not limited to, an automatic parking server, a control module, a terminal device, etc.

[0055] Vehicle 12 may support an automatic parking function. Vehicle 12 may wirelessly receive automatic parking instructions from a control device and complete the automatic parking operation according to the instructions; or may receive navigation information from a navigation service provider and perform automatic driving based on the navigation information. Vehicle 12 typically includes one or more built-in on-board modules, assemblies, components, chips, or units. The vehicle may implement the automatic parking method provided herein by using the built-in on-board modules, assemblies, components, chips, or units. Optionally, the vehicle may further include various devices configured to implement the automatic parking operation, such as an on-board radar, an on-board infrared imaging device, an on-board positioning device, an on-board lighting device, and a vehicle control system.

[0056] Optionally, the control device 11 and the vehicle 12 may be integrated together or may be located separately.

[0057] It can be understood that Figure 1 is only a simplified example diagram for ease of understanding. In actual application, the above system may further include other devices not shown in the figure.

[0058] For example, the control device 11 in this embodiment of the present application may be implemented by using various devices. For example, the control device 11 in this embodiment of the present application may be implemented by using a communication device shown in Figure 2. Figure 2 is a diagram of the hardware structure of the control device 11 according to an embodiment of the present application. The control device 11 includes at least one processor 201, a communication line 202, a memory 203, and at least one communication interface 204.

[0059] The processor 201 may be a general purpose CPU, a microprocessor, an ASIC, or one or more integrated circuits configured to control program execution of the present solution.

[0060] Communication lines 202 may include the paths by which information is transferred between the above components.

[0061] The communication interface 204 is configured to communicate with other devices. In this embodiment of the present application, the communication interface 204 may be a module, a circuit, a bus, an interface, a transceiver, or another apparatus capable of implementing a communication function. Optionally, if the communication interface is a transceiver, the transceiver may be an independently located transmitter, and the transmitter may be configured to transmit information to another device. Alternatively, the transceiver may be an independently located receiver, and configured to receive information from another device. Alternatively, the transceiver may be a component that integrates information transmission and information reception functions. The specific implementation of the transceiver is not limited in this embodiment of the present application.

[0062] Memory 203 may be read-only memory (ROM) or another type of static storage device capable of storing static information and instructions, or random access memory (RAM) or another type of dynamic storage device capable of storing information and instructions, or may be electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other compact disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disc storage media or other magnetic storage devices, or any other medium that can be used to carry or store expected program code in the form of instructions or data structures and that can be accessed by a computer. Memory 203 may exist independently and be connected to processor 201 through communication line 202. Memory 203 may alternatively be integrated with processor 201.

[0063] The memory 203 is configured to store computer-executable instructions for implementing the solutions of the present application. The processor 201 is configured to execute the computer-executable instructions stored in the memory 203 to perform the methods provided in the following embodiments of the present application.

[0064] Optionally, the computer-executable instructions in this embodiment of the present application may be referred to as application code, instructions, computer programs, or other names, without limitation in this embodiment of the present application.

[0065] In a particular implementation, in one embodiment, processor 201 may include one or more CPUs, for example, CPU 0 and CPU 1 of FIG.

[0066] In a specific implementation, in one embodiment, control device 11 may include multiple processors, such as processor 201 and processor 205 of FIG. 2. Each of the processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. A processor herein may be one or more devices, circuits, and / or processing cores configured to process data (e.g., computer program instructions).

[0067] The control device 11 may be a general-purpose device or a dedicated device, and the type of the control device 11 is not limited in this embodiment of the present application.

[0068] It may be understood that the schematic structure in this embodiment of the present application does not constitute a specific limitation on the control device 11. In some other embodiments of the present application, the control device 11 may include more or fewer components than those shown in the figure, may combine some components, may separate some components, or may have a different component arrangement. The components shown in the figure may be implemented by hardware, software, or a combination of software and hardware.

[0069] An example will be used in which the vehicle 12 is an autonomous vehicle. FIG. 3 is a functional block diagram of the vehicle 12.

[0070] Vehicle 12 may include various subsystems, such as a driving system 110, a sensor system 120, a control system 130, one or more peripheral devices 140, a power source 150, a computer system 160, and a user interface 170. Optionally, vehicle 12 may include more or fewer subsystems, and each subsystem may include multiple elements. Furthermore, the subsystems and elements of vehicle 12 may all be interconnected, either wired or wirelessly.

[0071] The traction system 110 includes components that provide the vehicle 12 with power for movement. In one embodiment, the traction system 110 includes an engine 111, a transmission 112, an energy source 113, and wheels 114. The engine 111 may be an internal combustion engine, an electric motor, an air-compression engine, or a combination of other types of engines, such as a hybrid engine formed by a gasoline engine and an electric motor, or a hybrid engine formed by an internal combustion engine and an air-compression engine. The engine 111 converts the energy source 113 into mechanical energy.

[0072] Examples of energy source 113 include gasoline, diesel, other oil-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other power sources. Energy source 113 may also provide energy for other systems of vehicle 12.

[0073] The transmission 112 can transmit mechanical power from the engine 111 to the wheels 114. The transmission 112 can include a gearbox, a differential, and a drive shaft. In some embodiments, the transmission 112 can further include other components, such as a clutch. The drive shaft can include one or more shafts that can be coupled to one or more wheels 114.

[0074] Sensor system 120 may include several sensors that sense information about the environment surrounding vehicle 12. For example, sensor system 120 may include a positioning system 121 (which may be a global positioning system (GPS), a BeiDou system, or another positioning system), an inertial measurement unit (IMU) 122, radar 123, lidar 124, and a camera 125. Sensor data from one or more of these sensors may be used to detect objects and their corresponding characteristics (e.g., position, shape, orientation, speed, etc.). Such detection and recognition are key functions for the safe and autonomous operation of vehicle 12.

[0075] Positioning system 121 may be configured to estimate the geographic position of vehicle 12. IMU 122 is configured to sense changes in position and orientation of vehicle 12 based on inertial acceleration. In one embodiment, IMU 122 may be a combination of an accelerometer and a gyroscope.

[0076] Radar 123 may sense objects in the environment surrounding vehicle 12 by using radio signals. In some embodiments, in addition to sensing objects, radar 123 may be further configured to sense the speed and / or direction of travel of the objects.

[0077] LIDAR 124 may use lasers to sense objects in the environment in which vehicle 12 is located. In some embodiments, LIDAR 124 may include one or more laser sources, a laser scanner, one or more detectors, and other system components.

[0078] Camera 125 may be configured to capture images of the environment surrounding vehicle 12 and images within the vehicle driver's cabin. In some embodiments of the present application, the images of the environment surrounding vehicle 12 include one or more images of, but are not limited to, unoccupied parking spaces, occupied parking spaces, vehicles, people, obstacles, etc.

[0079] The camera 125 may be a still camera or a video camera. For example, the camera 125 may include, but is not limited to, one or more of a long-range camera, a mid-range camera, a close-range camera, a fish-eye camera, etc. The type of camera 125 is not limited herein.

[0080] In some embodiments of the present application, there may be multiple cameras 125, and the cameras 125 are separately configured to capture images at different orientations of the vehicle 12. For example, the vehicle orientation may include various orientations such as, but not limited to, east, west, south, north, northeast, southeast, southwest, and northwest. Alternatively, the vehicle orientation may include various orientations such as, but not limited to, up, down, left, right, up-left, down-left, up-right, and down-right. In some embodiments, the cameras 125 may be deployed at different locations on the vehicle 12, for example, at the front of the vehicle, at the rear of the vehicle, on two sides of the body, and on top of the vehicle, to help capture images at different orientations of the vehicle 12.

[0081] For example, Figure 4 is a diagram of cameras deployed on a vehicle, according to some embodiments of the present application. As shown in Figure 4, camera 401 may be deployed at the front of the vehicle and configured to capture an image of the environment ahead of the vehicle. Camera 402 may be deployed on the right side of the vehicle body and configured to capture an image of the environment on the right side of the vehicle. Camera 403 may be deployed on the left side of the vehicle body and configured to capture an image of the environment on the left side of the vehicle. Camera 404 may be deployed at the rear of the vehicle and configured to capture an image of the environment behind the vehicle.

[0082] The control system 130 may control the operation of the vehicle 12 and its components. The control system 130 may include various elements, such as a steering system 131, an accelerator 132, a braking unit 133, a computer vision system 134, a route control system 135, and an obstacle avoidance system 136.

[0083] The steering system 131 may be operated to adjust the direction of travel of the vehicle 12. For example, in one embodiment, the steering system 131 may be a steering wheel system.

[0084] The axel 132 is configured to control the operating speed of the engine 111 , which in turn controls the speed of the vehicle 12 .

[0085] The braking unit 133 controls the vehicle 12 to decelerate.

[0086] The computer vision system 134 may be operated to process and analyze images captured by the camera 125 to recognize objects and / or features in the vehicle 12's environment, as well as the physical and facial features of the driver within the vehicle's driver cabin. The objects and / or features may include traffic signals, road conditions, and obstacles, and the driver's physical and facial features include the driver's behavior, gaze, and facial expression, etc.

[0087] Route control system 135 is configured to determine a driving route for vehicle 12. In some embodiments, route control system 135 can determine a driving route for vehicle 12 based on data from sensors, positioning system 121, and one or more predetermined maps.

[0088] The obstacle avoidance system 136 is configured to recognize, evaluate, and avoid or otherwise go around potential obstacles in the environment of the vehicle 12 .

[0089] Of course, in one example, control system 130 may additionally or alternatively include components other than those shown and described, or alternatively, some of the aforementioned components may be eliminated.

[0090] Vehicle 12 interacts with external sensors, other vehicles, other computer systems, or a user through peripheral devices 140. Peripheral devices 140 may include a wireless communication system 141, an onboard computer 142, a microphone 143, and / or a speaker 144. In some embodiments, peripheral devices 140 provide a means for a user of vehicle 12 to interact with a user interface 170.

[0091] The wireless communication system 141 may communicate wirelessly with one or more devices directly or through a communication network.

[0092] The power source 150 may provide power to various components of the vehicle 12 .

[0093] Some or all of the functions of vehicle 12 are controlled by computer system 160. Computer system 160 may include at least one processor 161. Processor 161 executes instructions 1621 stored, for example, in data storage device 162. Computer system 160 may also be multiple computing devices that control individual components or subsystems of vehicle 12 in a distributed manner.

[0094] Processor 161 may be any conventional processor, such as a CPU, an ASIC, or another dedicated hardware-based processor. While FIG. 4 functionally depicts the processor, data storage, and other elements within the same physical enclosure, those skilled in the art will understand that a processor, computer system, or data storage device may actually include multiple processors, computer systems, or data storage devices housed within the same physical enclosure, or multiple processors, computer systems, or data storage devices housed within different physical enclosures. For example, a data storage device may be a hard disk drive or another storage medium located in a different physical enclosure. Thus, reference to a processor or computer system is understood to include reference to a set of processors, computer systems, or data storage devices that may operate in parallel, or a set of processors, computer systems, or data storage devices that may not operate in parallel. Unlike using a single processor to perform the steps described herein, some components, such as the steering component and the deceleration component, may include their own processors. The processors perform only calculations related to the component's specific function.

[0095] In various aspects described herein, the processor may be located remotely from the vehicle and in wireless communication with the vehicle. In another aspect, some processes described herein are executed on a processor located within the vehicle, and other processes are executed by a remote processor, which may include performing the steps necessary for a single operation.

[0096] In some embodiments, data storage 162 may include instructions 1621 (e.g., program logic) that may be executed by processor 161 to perform various functions of vehicle 12, including those described above. Data storage 162 may also include additional instructions, including instructions for transmitting data to, receiving data from, interacting with, and / or controlling one or more of driving system 110, sensor system 120, control system 130, and peripheral devices 140.

[0097] In addition to instructions 1621, data storage device 162 may further store data such as road maps, route information, vehicle position, direction, speed, and other vehicle data, and other information. Such information may be used by vehicle 12 and computer system 160 when vehicle 12 operates in autonomous, semi-autonomous, and / or manual modes.

[0098] User interface 170 is configured to provide information to or receive information from a user of vehicle 12. Optionally, user interface 170 may interact with one or more input / output devices in set of peripheral devices 140, such as one or more of wireless communication system 141, onboard computer 142, microphone 143, and speaker 144.

[0099] The computer system 160 may control the vehicle 12 based on information obtained from various subsystems (e.g., the driving system 110, the sensor system 120, and the control system 130) and information received from the user interface 170.

[0100] Optionally, one or more of the aforementioned components may be located separately from or associated with vehicle 12. For example, data storage device 162 may exist partially or completely separate from vehicle 12. The aforementioned components may be coupled together to communicate in a wired and / or wireless manner.

[0101] Optionally, the above components are merely examples. In practical applications, components in the above modules can be added or deleted based on practical requirements. Figure 3 should not be understood as a limitation on this embodiment of the present application.

[0102] Vehicle 12 may be an automobile, truck, motorcycle, bus, boat, airplane, helicopter, lawn mower, recreational vehicle, amusement park vehicle, construction device, trolley, golf cart, train, push cart, etc., which is not particularly limiting in this embodiment of the present application.

[0103] In some other embodiments of the present application, the autonomous vehicle may further include a hardware structure and / or a software module, and may implement functions in the form of a hardware structure, a software module, or both a hardware structure and a software module. Whether a function in the aforementioned functions is performed by using a hardware structure, a software module, or a combination of a hardware structure and a software module depends on the specific application and design constraints of the technical solution.

[0104] For example, Figure 5 shows an automated parking method according to an embodiment of the present application. The method may be performed by the control device shown in Figure 1 or by a processor within the control device, for example, the processor shown in Figure 2. The method includes the following steps:

[0105] S501: Determine parking space information for a plurality of candidate parking spaces based on at least two images of the host vehicle.

[0106] It may be appreciated that the image may be an image of the environment at a particular orientation of the vehicle.

[0107] For example, the image may alternatively be an image captured by a visual sensor such as a fish-eye camera.

[0108] In some embodiments, the images may include images of candidate parking spaces, which may be understood as unoccupied parking spaces, i.e., vacant parking spaces. Optionally, the images may include images other than images of candidate parking spaces, such as images of people, vehicles, occupied parking spaces, or obstacles.

[0109] It may be understood that parking spaces in embodiments of the present application may include various types of parking spaces, such as, but not limited to, parking spaces in a parking structure, marked parking spaces, etc.

[0110] The parking space information may indicate the location of the parking space, for example, the location of the parking space within a parking structure. In some embodiments, the parking space information may further indicate the entrance direction of the parking space, etc.

[0111] In some embodiments, the at least two images may include environmental images in any at least two orientations of the host vehicle, for example, environmental images on the left, right, and front sides of the vehicle, or in another example, environmental images on the left and left front sides of the vehicle. In other words, the at least two images include environmental images in different orientations.

[0112] Optionally, the at least two directions may be adjacent directions, such as left and left-front, left and left-downward, left-front and forward, or right and right-downward. In this case, the at least two directions are adjacent directions, and the environmental images in the adjacent directions may have partially overlapping areas, and the candidate parking space may be present in the overlapping area. If a candidate parking space is detected based on each of the two images, it indicates a high probability of the existence of the candidate parking space. In this way, the accuracy of parking space detection can be improved.

[0113] S502: Determine a target parking space from the plurality of candidate parking spaces based on the parking space information of the plurality of candidate parking spaces.

[0114] In one possible implementation, any of a plurality of candidate parking spaces may be determined as the target parking space.

[0115] In another possible implementation, a parking space among multiple candidate parking spaces that satisfies a preset condition can be determined as a target parking space. For example, the preset condition may be that the parking space is closest to the vehicle. In this way, the candidate parking space closest to the vehicle is used as the target parking space. This can improve parking efficiency.

[0116] In another possible implementation, the plurality of candidate parking spaces may be further output, and the user may select one of the candidate parking spaces as the target parking space.

[0117] S503: The host vehicle is controlled so as to park in the target parking space.

[0118] Based on the above technical solution, during the vehicle cruising phase, i.e., during the process of searching for a parking space, parking space detection is performed based on multiple environmental images at multiple orientations of the vehicle. If a parking space is detected in all of the multiple images, it indicates a high probability that the parking space exists. In this way, the accuracy of the parking space detection result can be improved.

[0119] In some other embodiments, the at least two images described in step S501 may include a first image and a second image.

[0120] The first image is an environment image in a first orientation of the host vehicle. Optionally, the first orientation may be any orientation of the host vehicle, for example, left or right. Alternatively, the first orientation may be a target orientation of the host vehicle, and the target orientation may be the same as the orientation of the parking space. It may be understood that the parking space may include an occupied parking space or an unoccupied parking space, i.e., a candidate parking space. In this way, when parking space detection is performed based on an environment image in a target orientation of the host vehicle, i.e., an image in the orientation of the parking space, it becomes easier to detect the candidate parking space.

[0121] For example, Figures 6(1) and 6(2) show some example scenarios of target orientations according to certain embodiments of the present application. As shown in Figure 6(1), if the parking spaces are located on the left and right sides of the host vehicle, the target orientation may be to the left, right, both left and right sides of the host vehicle, etc. As shown in Figure 6(2), if the parking spaces are located in front of the host vehicle, the target orientation may be in front of the host vehicle, etc.

[0122] Optionally, there may be one or more first images. If there are multiple first images, the first images may be images of the environment at different orientations. For example, the first images may be images captured by a fisheye camera.

[0123] The second image is a panoramic surround view image (also called a panoramic image, a surround view image, etc.) of the host vehicle. It can be understood that the second image may include the first image, i.e., the first image is a part of the second image.

[0124] According to the above technical solution, a parking space is detected based on an environmental image at a specific orientation of the ego-vehicle and a panoramic surround view image. If a parking space is detected in one image and also in another image, it indicates a high probability of the existence of the parking space. In this way, the accuracy of the parking space detection result can be improved. In addition, the panoramic surround view image has a wider field of view, which can improve the probability of detecting the parking space.

[0125] In some embodiments, the second image may be generated based on an image of the environment at a different orientation of the ego-vehicle. For example, the second image may be a fisheye surround view image formed by stitching together images captured by multiple (e.g., four) fisheye lenses (which may alternatively be referred to as inverse perspective mapping (IPM)).

[0126] In one possible implementation, the multiple candidate parking spaces include a first candidate parking space and / or a second candidate parking space, and step S501 may be specifically implemented as step S501a and step S501b (not shown).

[0127] S501a: Determine parking space information of at least one first candidate parking space based on a first image of the host vehicle.

[0128] The first image includes an image of the at least one first candidate parking space. Optionally, the first image may further include an image other than an image of the first candidate parking space, for example, an image of a person, a vehicle, or an obstacle.

[0129] Optionally, the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space angle, and a positional relationship between the parking space angles. For example, the parking space line may be parking space line 1, parking space line 2, or parking space line 3 shown in FIG. 6(1), and the parking space angle (corner) may be vertex 1, vertex 2, vertex 3, or vertex 4 shown in FIG. 6(1). The positional relationship between the parking space angles may be the positional relationship between the vertices shown in FIG. 6(1).

[0130] In some possible implementations, the first image may be input to a first preset model, and parking space information of the at least one first candidate parking space may be output through the first preset model. Optionally, the first preset model may be a model obtained through training by using the first image as input and the parking space information of the candidate parking space as output. The model may be a machine learning model or a neural network model. This is not limited in the present application. Based on this design, the first image is input to the model to recognize the candidate parking space. Compared with conventional feature extraction algorithms, the model is less affected by the environment, light, etc. This can improve the accuracy of the parking space detection result. Also, compared with conventional feature extraction algorithms, the model can avoid excessive manual parameter adjustment and improve the robustness of the overall algorithm.

[0131] S501b: Determine parking space information of at least one second candidate parking space based on a second image of the host vehicle.

[0132] The second image includes an image of the at least one second candidate parking space. Optionally, the panoramic image may further include images other than images of the second candidate parking spaces, for example, images of people, vehicles, or obstacles.

[0133] The at least one second candidate parking space includes one or more of the at least one first candidate parking spaces. In other words, the at least one second candidate parking space and the at least one first candidate parking space include the same candidate parking spaces.

[0134] Optionally, the parking space information of the at least one second candidate parking space may include at least one of the entrance direction of the parking space and the vertex coordinates of the parking space. For example, a multi-story parking space is used as an example. Figure 7 is a diagram of the entrance direction of the parking space according to an embodiment of the present application. As shown in Figure 7, the direction of the white arrow is the entrance direction (also called the opening direction) of the parking space.

[0135] In some possible implementations, the second image may be input to a second preset model, and parking space information of the at least one second candidate parking space may be output through the second preset model. Optionally, the second preset model may be a model obtained through training by using the second image as input and the parking space information of the candidate parking space as output. The model may be a machine learning model or a neural network model. This is not limited to this application. In this way, a panoramic image is input to the model to recognize the candidate parking space. Compared to conventional feature extraction algorithms, the model is less affected by the environment, light, etc., which can improve the accuracy of the parking space detection result. Also, compared to conventional feature extraction algorithms, the model can avoid excessive manual parameter adjustment and improve the robustness of the overall algorithm.

[0136] In one possible implementation, step S502 may be specifically implemented as the following steps S502a and S502b (not shown).

[0137] S502a: Determine at least one third candidate parking space based on the parking space information of the at least one first candidate parking space and the parking space information of the at least one second candidate parking space.

[0138] In some embodiments, each of the at least one second candidate parking space corresponds to a confidence level, and a third candidate parking space may be a parking space having a confidence level equal to or greater than a preset confidence level threshold in the at least one second candidate parking space and belonging to the at least one first candidate parking space.

[0139] In an embodiment of the present application, it may be understood that the confidence level indicates the accuracy of the parking space detection result. A higher confidence level indicates a more accurate parking space detection result, and a more accurate parking space detection result may indicate a higher probability of the existence of a parking space and / or a more accurate location of the parking space. For example, if the confidence level corresponding to candidate parking space 1 is 5 and the confidence level corresponding to candidate parking space 2 is 7, and the confidence level 7 is greater than the confidence level 5, it indicates that the probability of the existence of candidate parking space 2 is greater than the probability of the existence of candidate parking space 1, or it indicates that the location of candidate parking space 2 is more accurate than the location of candidate parking space 1.

[0140] Optionally, a confidence level corresponding to the second candidate parking space may be output by the second preset model. For example, for each second candidate parking space, the second preset model outputs a corresponding confidence level to reflect the accuracy of the detection result corresponding to the candidate parking space.

[0141] In some other embodiments, each of the at least one first candidate parking space corresponds to one confidence level, and the third candidate parking space may be a parking space having a confidence level equal to or greater than a preset confidence level threshold in the at least one first candidate parking space and belonging to the at least one second candidate parking space.

[0142] Optionally, a confidence level corresponding to the first candidate parking space may be output by the first preset model. For example, for each first candidate parking space, the first preset model outputs a corresponding confidence level to reflect the accuracy of the detection result corresponding to the candidate parking space.

[0143] In some other embodiments, each of the at least one second candidate parking space may correspond to a confidence level, and each of the at least one first candidate parking space may also correspond to a confidence level. A third candidate parking space may be a parking space whose confidence level is equal to or greater than a first preset confidence level threshold for the at least one second candidate parking space and whose confidence level is equal to or greater than a second preset confidence level threshold for the at least one first candidate parking space. In other words, the confidence level of the third candidate parking space is equal to or greater than both the first preset confidence level threshold and the second preset confidence level threshold.

[0144] It can be understood that in the embodiment of the present application, each trust level threshold may be set by a developer based on actual requirements, which is not limited in the present application.

[0145] S502b: Determine a target parking space based on the at least one third candidate parking space.

[0146] In one possible implementation, any one of a plurality of third candidate parking spaces may be determined as the target parking space.

[0147] In another possible implementation, among the plurality of third candidate parking spaces, a parking space that satisfies a preset condition can be evaluated as a target parking space. For example, the preset condition may be that the parking space is closest to the vehicle. In this way, the candidate parking space closest to the vehicle is used as the target parking space. This can improve parking efficiency.

[0148] In another possible implementation, a candidate parking space among the plurality of third candidate parking spaces having a highest corresponding confidence level may be determined as the target parking space. Optionally, the confidence level may be output by the first preset model or the second preset model.

[0149] In another possible implementation, multiple third candidate parking spaces may be further output, and the user selects one of the third candidate parking spaces as the target parking space.

[0150] Based on the above technical solution, the target parking space is determined based on the confidence level of the candidate parking space, and the confidence level can reflect the accuracy of the parking space detection result. In this way, the candidate parking space with a high confidence level is used as the target parking space. That is, the candidate parking space that is accurately detected is used as the target parking space. This can further improve the accuracy of the parking space detection result.

[0151] The above mainly describes the cruise phase, i.e., the process of finding a parking space. The following describes the parking phase, i.e., the process of parking the vehicle in the parking space after it has been found.

[0152] In some embodiments, the method shown in FIG. 5 further comprises the following steps (not shown):

[0153] S504: In the process of controlling the ego vehicle to park in the target parking space, a third image of the ego vehicle is captured.

[0154] The third image is an environmental image in a third orientation of the host vehicle, and the third image includes an image of the target parking space. Optionally, the third image may further include an image other than the image of the target parking space, such as an image of a person, a vehicle, or an obstacle.

[0155] In some embodiments, the third image may be an environmental image oriented toward the side of the parking space. As shown in FIG. 8, the third image may be, for example, a left environmental image and / or a rear environmental image of the host vehicle.

[0156] Optionally, there may be one or more third images. If there are multiple third images, the third images may be images of the environment at different orientations.

[0157] Optionally, the orientations corresponding to the first image and the third image may be the same or different.

[0158] S505: Update the parking space information of the target parking space based on the third image.

[0159] Optionally, first parking space information of the target parking space may be determined based on the third image, and the parking space information of the target parking space may be updated based on the determined first parking space information. For example, the positions of the parking space line and the parking space angle of the target parking space may be calibrated. Optionally, the third image may be input to a first preset model, and the first parking space information of the target parking space is output through the first preset model. For example, the third image may alternatively be an image captured by a fisheye camera.

[0160] Based on this design, in the parking phase, i.e., in the process of parking the vehicle in the target parking space, the position information of the target parking space is calibrated by using the third image containing the target parking space, which can improve the parking accuracy.

[0161] The above mainly describes the solutions provided in the embodiments of the present application from the perspective of methods. To implement the above functions, it can be understood that the recognition model training device includes corresponding hardware structures and / or corresponding software modules for performing each function. With reference to the units and algorithm steps described in the embodiments disclosed herein, the embodiments of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether the functions are performed by hardware or by hardware driven by a computer depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementations should not be considered to exceed the scope of the technical solutions in the embodiments of the present application.

[0162] In the embodiment of the present application, based on the above-described method example, the recognition model training device may be divided into functional modules. For example, each functional module may be obtained through division based on its corresponding function, or two or more functions may be integrated into one processing unit. The integrated unit may be implemented in the form of hardware or a software functional module. Note that in the embodiment of the present application, the division into units is merely an example and represents a logical division of functions. In actual implementation, other division methods may be used.

[0163] 9 is a diagram of the structure of an automatic parking device according to an embodiment of the present application. The automatic parking device 900 may be configured to implement the method described in the above method embodiment. Optionally, the automatic parking device may be the control device 11 shown in FIG. 1 or a module (e.g., a chip) used in a server. The server may be located in the cloud. For example, the automatic parking device 900 may specifically include a processing unit 901.

[0164] The processing unit 901 is configured to support the automatic parking device 900 in performing steps S501 to S503 of FIG. 5, and / or the processing unit 901 is further configured to support the automatic parking device 900 in performing other steps performed by the automatic parking device in an embodiment of the present application.

[0165] Optionally, the automatic parking apparatus 900 shown in Fig. 9 may further include a communication unit 902. The communication unit 902 is configured to support the automatic parking apparatus 900 in performing steps of communication between the automatic parking apparatus and another device in the embodiment of the present application.

[0166] Optionally, the automatic parking device 900 shown in FIG. 9 may further include a storage unit (not shown in FIG. 9), which stores programs or instructions. When the processing unit 901 executes the programs or instructions, the automatic parking device 900 shown in FIG. 9 can perform the methods in the above-described method embodiments.

[0167] For technical effects of the automatic parking apparatus 900 shown in Fig. 9, please refer to the technical effects described in the above method embodiments. Details will not be described again in this specification. The processing unit 901 in the automatic parking apparatus 900 shown in Fig. 9 may be implemented by a processor or a processor-related circuit component, and may be a processor or a processing module. The communication unit 902 may be implemented by a transceiver or a transceiver-related circuit component, and may be a transceiver or a transceiver module.

[0168] An embodiment of the present application further provides a chip system. As shown in FIG. 10 , the chip system includes at least one processor 1001 and at least one interface circuit 1002. The processor 1001 and the interface circuit 1002 may be interconnected through a line. For example, the interface circuit 1002 may be configured to receive a signal from another device. In another example, the interface circuit 1002 may be configured to transmit a signal to another device (e.g., the processor 1001). For example, the interface circuit 1002 may read instructions stored in a memory and send the instructions to the processor 1001. When the instructions are executed by the processor 1001, the automatic parking device may perform the steps performed by the automatic parking device in the above-described embodiment. Of course, the chip system may further include other discrete components. This is not particularly limited in the embodiment of the present application.

[0169] Optionally, there may be one or more processors in the chip system. The processor may be implemented using hardware or software. When the processor is implemented using hardware, the processor may be a logic circuit, an integrated circuit, etc. When the processor is implemented using software, the processor may be a general-purpose processor and is implemented by reading software code stored in a memory.

[0170] Optionally, there may be one or more memories in the chip system. The memory may be integrated with the processor or located separately from the processor. This is not limited in this application. For example, the memory may be a non-transitory processor, such as a read-only memory (ROM). The memory and the processor may be integrated on the same chip or located separately on different chips. The type of memory and the manner in which the memory and the processor are located are not particularly limited in this application.

[0171] For example, the chip system may be a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system on a chip (SoC), a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a microcontroller unit (MCU), a programmable logic device (PLD), or another integrated chip.

[0172] It should be understood that the steps in the foregoing method embodiments may be completed by using integrated logic circuitry in hardware within a processor or instructions in the form of software, and the steps of the methods disclosed with reference to the embodiments of the present application may be performed directly by a hardware processor, or may be performed through a combination of hardware and software modules within a processor.

[0173] An embodiment of the present application further provides a computer storage medium, which stores computer instructions that, when executed on the automated parking device, enable the automated parking device to perform the method in the method embodiment described above.

[0174] An embodiment of the present application provides a computer program product, which includes computer programs or instructions that, when executed on a computer, enable the computer to perform the method in the method embodiments described above.

[0175] In addition, an embodiment of the present application further provides an apparatus. The apparatus may specifically be a chip, a component, or a module. The apparatus may include a processor and a memory connected to each other. The memory is configured to store computer-executable instructions. When the apparatus operates, the processor may execute the computer-executable instructions stored in the memory to enable the apparatus to perform the method in the above-mentioned method embodiment.

[0176] The automatic parking device, computer storage medium, computer program product, or chip provided in the embodiments are all configured to execute the corresponding methods provided above. Therefore, for the beneficial effects that can be achieved by the automatic parking device, computer storage medium, computer program product, or chip, please refer to the beneficial effects of the corresponding methods provided above. Details will not be described again in this specification.

[0177] Based on the above description of the implementation aspects, those skilled in the art can understand that the above division into functional modules is used as an example for illustration purposes for the purpose of simple description. In actual application, the above functions may be allocated to different functional modules and implemented based on requirements. In other words, the internal structure of the device is divided into different functional modules to implement all or part of the above functions.

[0178] In some embodiments provided herein, it should be understood that the disclosed devices and methods may be implemented in other ways. Embodiments may be combined with or referenced to each other without inconsistency. The described device embodiments are merely examples. For example, the division into modules or units is merely a logical division of function, and other divisions may be used in actual implementation. For example, multiple units or components may be combined or integrated into another device, or some features may be omitted or not implemented. In addition, the shown or discussed mutual couplings or direct couplings or communication connections may be implemented using some interfaces. Indirect couplings or communication connections between devices or units may be implemented electronically, mechanically, or in other ways.

[0179] The units described as separate parts may or may not be physically separate, and the parts shown as units may be one or more physical units, located in one place or distributed in different places. Some or all of the units may be selected based on actual requirements to achieve the objectives of the solutions of the embodiments.

[0180] In addition, the functional units in the embodiments of the present application may be integrated into one processing unit, each of the units may exist physically alone, or two or more units may be integrated into one unit. The integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0181] When an integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, the integrated unit may be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application may essentially be implemented in the form of a software product, or the portion that contributes to the prior art, or all or part of the technical solutions. The software product may be stored in a storage medium and include instructions for instructing a device (which may be a single-chip microcomputer, a chip, etc.) or a processor to perform all or part of the steps of the method described in the embodiments of the present application. The storage medium may include any medium capable of storing program code, such as a USB flash drive, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0182] The above description is merely a specific implementation of the present application and is not intended to limit the scope of protection of the present application. Any modifications or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in the present application shall fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the scope of protection of the claims.

Claims

1. 1. A method for automated parking, the method comprising: determining parking space information for a plurality of candidate parking spaces based on a first image and a second image of the host vehicle, the parking space information indicating locations of the parking spaces in a multi-story parking garage, the first image being an environmental image in a first orientation of the host vehicle, and the second image being a panoramic surround view image of the host vehicle; determining a target parking space from the plurality of candidate parking spaces based on parking space information of the plurality of candidate parking spaces; controlling the vehicle so that the vehicle is parked in the target parking space; A method comprising:

2. The step of determining parking space information for a plurality of candidate parking spaces based on the first image and the second image of the ego vehicle includes: determining parking space information for at least one first candidate parking space based on the first image of the host vehicle, the first image including an image of the at least one first candidate parking space; determining parking space information of at least one second candidate parking space based on the second image of the host vehicle, wherein the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space; The method of claim 1 , comprising:

3. The method of claim 2 , wherein the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space angle, and a positional relationship between the parking space angles.

4. The method according to claim 2 or 3, wherein the parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and a vertex coordinate of the parking space.

5. The step of determining a target parking space from the plurality of candidate parking spaces based on parking space information of the plurality of candidate parking spaces includes: determining at least one third candidate parking space based on parking space information of the at least one first candidate parking space and parking space information of the at least one second candidate parking space, wherein the third candidate parking space is a parking space having a confidence level equal to or greater than a preset confidence level threshold of the at least one second candidate parking space and belongs to the at least one first candidate parking space, and the confidence level indicates the accuracy of the parking space detection result; determining a target parking space based on the at least one third candidate parking space; 5. The method of claim 2, comprising:

6. The method comprises: capturing a third image of the host vehicle in the process of controlling the host vehicle to be parked in the target parking space, the third image being an image of the environment at a third orientation of the host vehicle, the third image including an image of the target parking space; updating parking space information of the target parking space based on the third image; 6. The method of claim 1, further comprising:

7. Determining parking space information of at least one first candidate parking space based on the first image of the ego vehicle includes: inputting the first image into a first preset model; and outputting parking space information of the at least one first candidate parking space through the first preset model.

7. The method according to any one of claims 2 to 6.

8. The step of determining parking space information of at least one second candidate parking space based on the second image of the ego vehicle includes: inputting the second image into a second preset model; and outputting parking space information of the at least one second candidate parking space through the second preset model.

8. The method according to any one of claims 2 to 7.

9. An automated parking device having a processing unit, The processing unit is configured to determine parking space information for a plurality of candidate parking spaces based on a first image and a second image of the ego vehicle, where the parking space information indicates a location of the parking space in a multi-story parking garage, the first image is an environmental image in a first orientation of the ego vehicle, and the second image is a panoramic surround view image of the ego vehicle; The processing unit is further configured to determine a target parking space from the plurality of candidate parking spaces based on parking space information of the plurality of candidate parking spaces; The processing unit is further configured to control the host vehicle so that the host vehicle is parked in the target parking space. Device.

10. The processing unit is specifically configured to determine parking space information of at least one first candidate parking space based on the first image of the host vehicle, where the first image includes an image of the at least one first candidate parking space; The processing unit is specifically configured to determine parking space information of at least one second candidate parking space based on the second image of the host vehicle, where the second image includes an image of the at least one second candidate parking space, and the at least one second candidate parking space includes one or more of the at least one first candidate parking space; 10. The apparatus of claim 9.

11. The device of claim 10 , wherein the parking space information of the at least one first candidate parking space includes at least one of a parking space line, a parking space angle, and a positional relationship between the parking space angles.

12. The parking space information of the at least one second candidate parking space includes at least one of an entrance direction of the parking space and a vertex coordinate of the parking space; 12. Apparatus according to claim 10 or 11.

13. The processing unit is specifically configured to determine at least one third candidate parking space based on the parking space information of the at least one first candidate parking space and the parking space information of the at least one second candidate parking space, wherein the third candidate parking space is a parking space having a confidence level equal to or greater than a preset confidence level threshold in the at least one second candidate parking space and belonging to the at least one first candidate parking space, and the confidence level indicates the accuracy of the parking space detection result; the processing unit is particularly configured to determine the target parking space based on the at least one third candidate parking space; 13. Apparatus according to any one of claims 10 to 12.

14. The processing unit is further configured to capture a third image of the host vehicle in the process of controlling the host vehicle to be parked in the target parking space, the third image being an environment image at a third orientation of the host vehicle, the third image including an image of the target parking space; the processing unit is further configured to update parking space information of the target parking space based on the third image.

14. Apparatus according to any one of claims 9 to 13.

15. The processing unit is specifically configured to input the first image into a first preset model, and output parking space information of the at least one first candidate parking space through the first preset model; 15. Apparatus according to any one of claims 10 to 14.

16. The processing unit is specifically configured to input the second image into a second preset model, and output parking space information of the at least one second candidate parking space through the second preset model.

16. Apparatus according to any one of claims 10 to 15.

17. An automated parking device having a processor, the processor coupled to a memory, the processor configured to execute a computer program stored in the memory so that the automated parking device performs a method according to any one of claims 1 to 8.

18. 9. A computer-readable storage medium, the computer-readable storage medium including a computer program or instructions, the computer program or instructions, when executed on an automated driving device, enabling the automated driving device to perform the method of any one of claims 1 to 8.

19. 9. A computer program product comprising computer programs or instructions which, when executed on a computer, enable the computer to carry out a method according to any one of claims 1 to 8.

Images