Intelligent parking method and device

Abstract

An intelligent parking method and device. The method comprises: if a first vehicle has encountered a navigation obstruction in a parking route towards a target parking space and has failed to achieve autonomous extrication, the first vehicle sends a first request to a terminal device; the first vehicle receives first parking information from the terminal device, parks on the basis of the first parking information and sends a second request to the terminal vehicle; and the first vehicle then receives a first instruction from the terminal device, and on the basis of the first instruction, continues driving from a parking position corresponding to the first parking information to the target parking space in the parking route, wherein the first request is used for requesting to assist the first vehicle in extrication, the first parking information is used for indicating a first parking pose required for the first vehicle to achieve extrication, the second request is used for requesting to confirm whether the first vehicle has achieved extrication, and the first instruction is used for indicating the first vehicle to recover parking operation. The method can improve the reliability and the success rate of unmanned valet parking by means of autonomous vehicle extrication combined with remote assistance of users.

Description

INTELLIGENT PARKING METHOD AND DEVICE

[01] This application claims priority to Chinese Patent Application No. 202410365364.3, filed with the China National Intellectual Property Administration on March 27, 2024 and entitled "INTELLIGENT PARKING METHOD AND DEVICE", which is incorporated herein by reference in its entirety.TECHNICAL FIELD

[02] This application relates to the field of intelligent driving technologies, and in particular, to an intelligent parking method and apparatus.BACKGROUND

[03] Nowadays, a parking difficulty is a common challenge faced by urban transportation. Especially in busy commercial districts and residential areas, drivers usually need to spend a lot of time in searching for suitable parking spaces. A traditional manual parking method cannot meet requirements of modern life of people. With development of intelligent assisted driving technologies, an automated valet parking technology enables a vehicle to autonomously perform search and selection and complete a parking process in a parking lot, without requiring a driver to perform an operation in person on the vehicle, thereby bringing consumers more convenient and efficient parking experience.

[04] However, during practical application, the automated valet parking technology still faces some challenges and limitations. For example, a parking lot environment is very complex, often with a narrow passage and a lack of a traffic rule constraint compared to a road driving environment. Consequently, a behavior of a social vehicle is more unpredictable, potentially causing difficulties for an autonomous decision-making system of an automated vehicle, and a passing difficulty such as ego vehicle immobilization or traffic blockage may occur, bringing unsatisfactory experience to a vehicle user.SUMMARY

[05] This application provides an intelligent parking method and apparatus, to improve reliability and a success rate of automated valet parking, thereby improving user experience.

[06] According to a first aspect, this application provides an intelligent parking method. The method may be performed by an intelligent parking apparatus. For example, the intelligent parking apparatus may be executed by a first vehicle or a module (such as a processor, a processing unit, a chip, a chip system, or a circuit) of a first vehicle. It should be understood that the method may alternatively be implemented by a logical node, a logical module, or software that can implement all or a part of functions of the first vehicle. For example, the following uses an example in which the first vehicle performs the intelligent parking method. The method may include the following steps: If the first vehicle encounters a passing difficulty in a parking route to a target parking space, the first vehicle may send a first request to a terminal device when autonomous extrication of the first vehicle fails, where the first request may be for requesting to assist the first vehicle with extrication; then, the first vehicle may receive first parking information from the terminal device, may park based on the first parking information, and may send a second request to the terminal device, where the first parking information may indicate a first parking pose required for extrication of the first vehicle, and the second request may be for requesting to confirm whether extrication of the first vehicle succeeds; and after that, the first vehicle may receive a first instruction from the terminal device, and may travel, according to the first instruction, from a parking position corresponding to the first parking information to the parking route to continue proceeding to the target parking space, where the first instruction may instruct the first vehicle to resume a parking operation.

[07] In this method, when the first vehicle encounters a passing difficulty in the parking route to the target parking space, because the vehicle has a specific autonomous extrication capability, the first vehicle may attempt autonomous extrication. In this way, remote intervention frequency of a user can be minimized, thereby helping ensure user experience. If the autonomous extrication attempt of the first vehicle fails, the first vehicle may send a remote assistance request (for example, the first request) to the terminal device, so that the user can remotely assist the first vehicle with extrication. After extrication of the first vehicle succeeds with remote assistance of the user, the first vehicle may continue proceeding to the target parking space based on the parking route and a corresponding instruction from the terminal device. In this way, the method can improve reliability and a success rate of automated valet parking by combining autonomous extrication of the vehicle and remote assistance of the user, and can maximally avoid affecting user experience and use willingness due to onsite intervention of the user, thereby helping address the passing difficulty encountered by the automated valet parking vehicle. In addition, the method does not need to depend on a cloud cockpit and security personnel, and therefore can reduce device and maintenance costs.

[08] In a possible implementation, after the first vehicle sends the second request to the terminal device, the method further includes: The first vehicle may receive second parking information from the terminal device, where the second parking information may indicate a second parking pose required for continued extrication of the first vehicle; then, the first vehicle may park based on the second parking information, and may send a third request to the terminal device, where the third request may be for requesting to confirm whether extrication of the first vehicle succeeds; and after that, the first vehicle may receive a second instruction from the terminal device, and may travel, according to the second instruction, from a parking position corresponding to the second parking information to the parking route to continue proceeding to the target parking space, where the second instruction may instruct the first vehicle to resume the parking operation.

[09] In the foregoing implementation, the first vehicle may park based on the second parking pose from the terminal device, to implement continued extrication of the first vehicle (or may be referred to as performing extrication again). If extrication of the first vehicle succeeds, the first vehicle may travel, according to the second instruction from the terminal device, from the parking position corresponding to the second parking information to the parking route to continue proceeding to the target parking space, thereby completing autonomous parking of the first vehicle. In addition, in this implementation, the parking pose required for extrication of the first vehicle may be dynamically adjusted by the user by using the terminal device based on an actual situation of the first vehicle (that is, if the user finds that extrication of the first vehicle is not successful, the user may continue to specify a new parking pose on the terminal device, for example, the user may continuously adjust the parking pose multiple times on the terminal device). This can make an extrication manner of the first vehicle more flexible, and better adapt to different scenarios and requirements.

[010] In a possible implementation, the method further includes: The first vehicle may receive a third instruction from the terminal device, where the third instruction may instruct the first vehicle to wait for onsite takeover by the user.

[011] In the foregoing implementation, if the first vehicle receives the third instruction from the terminal device, the first vehicle may be in a standby state in place, and wait for onsite takeover by the user. This can facilitate the user to go to the site in a timely and effective manner to find the first vehicle and take over the first vehicle (for example, take over the parking operation of the first vehicle).

[012] In a possible implementation, the first vehicle determines, based on at least one of the following, that the first vehicle encounters a passing difficulty in a process of proceeding to the target parking space: The first vehicle blocks passing of a first target or a second target blocks passing of the first vehicle, where the first target may be a target that is in a traveling area in which the first vehicle is located and that has a bidirectional interaction relationship with the first vehicle, and the second target may be a target that is in the traveling area in which the first vehicle is located and that has a unidirectional interaction relationship with the first vehicle.

[013] In the foregoing implementation, if the first vehicle encounters one or more of the two targets in the process of proceeding to the target parking space, the first vehicle may determine that a passing difficulty occurs. In this case, the first vehicle may start to attempt autonomous extrication (for example, the first vehicle may plan, based on ambient environment information, a route required for autonomous extrication).

[014] In a possible implementation, the method further includes: The first vehicle may obtain sensing information corresponding to the first vehicle; then, the first vehicle may determine a plurality of targets based on the sensing information, and may determine decision-making results of the plurality of targets, where a decision-making result of each of the plurality of targets may indicate an avoidance measure taken by the first vehicle on the target; and after that, when the plurality of targets include the first target, the first vehicle may perform extrication planning (or may be referred to as autonomous extrication planning) for the first target based on the decision-making result of the first target; or when the plurality of targets include the second target, the first vehicle may perform extrication planning for the second target based on the decision-making result of the second target.

[015] In the foregoing implementation, for the first target, the first vehicle may perform autonomous extrication planning based on the decision-making result of the first vehicle on the first target, or for the second target, the first vehicle may perform autonomous extrication planning based on the decision-making result of the first vehicle on the second target. In this way, the first vehicle can make a targeted autonomous extrication attempt, thereby making autonomous extrication of the first vehicle more accurate and effective.

[016] In a possible implementation, when the first vehicle blocks passing of the first target, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, that the first vehicle performs extrication planning for the first target includes: When there is an idle area around the first vehicle, the first vehicle may attempt to park in the idle area, to leave passing space for the first target.

[017] In the foregoing implementation, when determining that there is the idle area around the first vehicle, the first vehicle may attempt to park in the idle area to leave the passing space for the first target, to implement autonomous extrication of the first vehicle.

[018] In a possible implementation, when the second target blocks passing of the first vehicle, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, that the first vehicle performs extrication planning for the second target includes: The first vehicle may attempt to pass through a narrow passage between the second target and a boundary of a passable area of the first vehicle; or the first vehicle may attempt to bypass the second target.

[019] In the foregoing implementation, the first vehicle may attempt to pass through the narrow passage or attempt to bypass the second target, to implement autonomous extrication of the first vehicle.

[020] According to a second aspect, this application provides an intelligent parking method. The method may be performed by an intelligent parking apparatus. For example, the intelligent parking apparatus may be executed by a terminal device or a module (such as a processor, a processing unit, a chip, a chip system, or a circuit) of a terminal device. It should be understood that the method may alternatively be implemented by a logical node, a logical module, or software that can implement all or a part of functions of the terminal device. For example, the following uses an example in which the terminal device performs the intelligent parking method. The method may include the following steps: The terminal device may receive a first request from a first vehicle, where the first request may be for requesting to assist the first vehicle with extrication; then, in response to a first operation of a user on a parking interface, the terminal device may obtain first parking information of the first vehicle, and may send the first parking information to the first vehicle, where the first operation may be an operation of dragging a virtual parking space on the parking interface by the user, and the first parking information may indicate a first parking pose required for extrication of the first vehicle; then, the first vehicle may receive a second request from the first vehicle, where the second request may be for requesting to confirm whether extrication of the first vehicle succeeds; and after that, in response to a second operation of the user on the parking interface, the terminal device may obtain a first instruction, and may send the first instruction to the first vehicle, where the second operation may be an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance, and the first instruction may instruct the first vehicle to resume a parking operation.

[021] For technical effects that can be achieved in the second aspect, refer to the technical effects that can be achieved in the first aspect. Details are not described herein again. In addition, it should be understood that, in the method, the user may also complete delivery of a corresponding instruction by performing a simple drag and tap-to-select operation (for example, the operation of dragging the virtual parking space) on the parking interface of the terminal device, so that the first vehicle can perform a corresponding operation in a timely and accurate manner based on the corresponding instruction. In this way, a user threshold is low, and user-friendliness is high.

[022] In a possible implementation, after the terminal device receives the second request from the first vehicle, the method further includes:

[023] In response to a third operation of the user on the parking interface, the terminal device may obtain second parking information of the first vehicle, and may send the second parking information to the first vehicle, where the third operation may be an operation of continuing to drag the virtual parking space on the parking interface by the user, and the second parking information may indicate a second parking pose required for continued extrication of the first vehicle; then, the terminal device may receive a third request from the first vehicle, where the third request may be for requesting to confirm whether extrication of the first vehicle succeeds; and after that, in response to a fourth operation of the user on the parking interface, the terminal device may obtain a second instruction, and may send the second instruction to the first vehicle, where the fourth operation may be an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance, and the second instruction may instruct the first vehicle to resume the parking operation.

[024] In the foregoing implementation, if the user determines that extrication of the first vehicle has not been successful and continued extrication is needed, the user may trigger the third operation on the parking interface, so that the first vehicle can continue to perform autonomous extrication based on the second parking pose. In this way, in this implementation, the user can continue to specify a new target pose (for example, the second parking pose) by dragging the virtual parking space on the parking interface, and further, the user can dynamically adjust, based on an actual situation of the first vehicle (for example, an actual situation of extrication or whether a parking position at which the first vehicle performs extrication affects another vehicle or pedestrian), the parking pose required for extrication of the first vehicle. This can make an extrication manner of the first vehicle more flexible, thereby making extrication of the first vehicle as successful as possible and helping improve a success rate of vehicle extrication.

[025] In a possible implementation, the method further includes: In response to a fifth operation of the user on the parking interface, the terminal device may obtain a third instruction, and may send the third instruction to the first vehicle, where the fifth operation may be an operation triggered on the parking interface by the user due to failed extrication of the first vehicle with remote assistance, and the third instruction may instruct the first vehicle to wait for onsite takeover by the user.

[026] In the foregoing implementation, if the user determines that remote assistance cannot facilitate extrication of the first vehicle, the user may edit, on the parking interface, the third instruction enabling the first vehicle to wait in place for onsite takeover by the user, and perform the fifth operation for submission. This can allow the first vehicle to be in a standby state in place, waiting for onsite takeover by the user, and facilitate the user to go to the site in a timely and effective manner to find the first vehicle and take over the first vehicle (for example, take over the parking operation of the first vehicle).

[027] According to a third aspect, this application provides an intelligent parking apparatus. The intelligent parking apparatus has a function of implementing the first aspect and the second aspect. For example, the intelligent parking apparatus includes a corresponding module, a unit, or a means for performing an operation in the first aspect and the second aspect. The function, unit, or means may be implemented by software, or may be implemented by hardware, or may be implemented by hardware executing corresponding software.

[028] In a possible implementation, the intelligent parking apparatus includes a transceiver module (or may be referred to as a communication module, a transceiver unit, or a communication unit, configured to send and receive data) and a processing module (or may be referred to as a processing unit). The transceiver module may be configured to receive and send a signal, to implement communication between the intelligent parking apparatus and another apparatus. For example, the transceiver module is configured to send corresponding data to a terminal device (or the transceiver module is configured to send corresponding data to a first vehicle). The processing module may be configured to perform some internal operations of the intelligent parking apparatus. Functions performed by the transceiver module and the processing module may correspond to operations in the first aspect and the second aspect.

[029] In a possible implementation, the intelligent parking apparatus includes a processor, and the processor may be configured to be coupled to a memory. The memory may store a computer program or instructions necessary for implementing the functions in the first aspect and the second aspect. The processor may execute the computer program or the instructions stored in the memory. When the computer program or the instructions are executed, the intelligent parking apparatus is enabled to implement the method according to any one of the possible implementations of the first aspect and the second aspect.

[030] In a possible implementation, the intelligent parking apparatus includes a processor and a memory. The memory may store a computer program or instructions necessary for implementing the functions in the first aspect and the second aspect. The processor may execute the computer program or the instructions stored in the memory. When the computer program or the instructions are executed, the intelligent parking apparatus is enabled to implement the method according to any one of the possible implementations of the first aspect and the second aspect.

[031] In a possible implementation, the intelligent parking apparatus includes a processor and an interface circuit. The processor is configured to: communicate with another apparatus through the interface circuit, and perform the method according to any one of the possible implementations of the first aspect and the second aspect.

[032] It may be understood that in the third aspect, the processor may be implemented by hardware or software. When the processor is implemented by the hardware, the processor may be a logic circuit, an integrated circuit, or the like. When the processor is implemented by the software, the processor may be a general-purpose processor, and is implemented by reading software code stored in the memory. In addition, there may be one or more processors, and one or more memories. The memory may be integrated with the processor, or the memory and the processor are disposed separately. In a specific implementation process, the memory and the processor may be integrated on a same chip, or may be separately disposed on different chips. A type of the memory and a manner in which the memory and the processor are disposed are not limited in embodiments of this application.

[033] According to a fourth aspect, this application provides a vehicle. The vehicle includes an image capture system, a chassis sensing device, and an intelligent parking apparatus configured to perform the method according to any one of the possible implementations of the first aspect. The image capture system is configured to obtain (or may be referred to as collecting) ambient environment information of the vehicle, and the chassis sensing device is configured to obtain traveling state information of the vehicle.

[034] According to a fifth aspect, this application provides a terminal device. The cloud includes an intelligent parking apparatus configured to perform the method according to any one of the possible implementations of the second aspect.

[035] According to a sixth aspect, this application provides a computer program product. The computer program product includes a computer program or instructions, and when the computer program or the instructions are run on a computer, the computer is enabled to perform the method according to any one of the possible implementations of the first aspect or the method according to any one of the possible implementations of the second aspect.

[036] According to a seventh aspect, this application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program or instructions, and when the computer program or the instructions are executed by a computer, the computer is enabled to perform the method according to any one of the possible implementations of the first aspect or the method according to any one of the possible implementations of the second aspect.

[037] According to an eighth aspect, this application provides a chip. The chip may include a processor, and may further include a memory (or the chip is coupled to the memory), and the chip executes program instructions in the memory, to perform the method according to any one of the possible implementations of the first aspect or the method according to any one of the possible implementations of the second aspect. "Coupling" means that two components are directly or indirectly combined with each other. For example, coupling may mean an electrical connection between the two components.

[038] According to a ninth aspect, this application further provides a chip system. The chip system includes a processor, configured to support a computer apparatus in implementing the method according to any one of the possible implementations of the first aspect or the method according to any one of the possible implementations of the second aspect. In a possible implementation, the chip system further includes a memory. The memory is configured to store a program and data that are necessary for the computer apparatus. The chip system may include a chip, or may include a chip and another discrete component.

[039] In this application, the implementations provided in the foregoing aspects may be further combined to provide more implementations.BRIEF DESCRIPTION OF DRAWINGS

[040] FIG. 1 is an example of a diagram of a possible application scenario according to an embodiment of this application.

[041] FIG. 2 is an example of a diagram of a system architecture for implementing an intelligent parking method according to an embodiment of this application.

[042] FIG. 3 is an example of a schematic flowchart of an intelligent parking method according to an embodiment of this application.

[043] FIG. 4 is an example of a diagram of selecting a target parking space on a parking interface by a user according to an embodiment of this application.

[044] FIG. 5 is an example of a diagram of determining, by a vehicle passing state detection and autonomous extrication unit, whether a first vehicle encounters a passing difficulty according to an embodiment of this application.

[045] FIG. 6a is an example of a diagram of a scenario in which a vehicle passing state detection and autonomous extrication unit determines whether a vehicle A blocks passing of a vehicle B according to an embodiment of this application.

[046] FIG. 6b is an example of a diagram of a scenario in which a vehicle passing state detection and autonomous extrication unit determines whether a vehicle C blocks passing of a vehicle A according to an embodiment of this application.

[047] FIG. 7 is an example of an ambient environment view of a first vehicle presented on a parking interface according to an embodiment of this application.

[048] FIG. 8 is an example of a diagram of remotely assisting a vehicle with extrication by a user according to an embodiment of this application.

[049] FIG. 9 is an example of a diagram of a structure of a possible intelligent parking apparatus according to an embodiment of this application.

[050] FIG. 10 is an example of a diagram of a structure of another possible intelligent parking apparatus according to an embodiment of this application.DESCRIPTION OF EMBODIMENTS

[051] The following describes in detail embodiments of this application with reference to accompanying drawings.

[052] The following describes an application scenario to which an intelligent parking method provided in this application is applicable. It should be noted that the descriptions are for ease of understanding by a person skilled in the art, and are not intended to limit the protection scope claimed by this application.

[053] FIG. 1 is an example of a diagram of a possible application scenario to which an embodiment of this application is applicable. As shown in FIG. 1, in this application scenario, an example in which an intelligent parking method is applied to a vehicle is used, and the vehicle has an automated parking function. As shown in FIG. 1, it is assumed that a to-be-parked vehicle is a vehicle 100, and the vehicle 100 has an automated valet parking function. In an automated valet parking scenario, after a user of the vehicle 100 taps the automated valet parking function in a target application installed on a terminal device, the target application may present a parking interface to the user, and wait for the user to select a target parking space. A parking area (or may be referred to as a parking region, for example, a parking lot) is presented on the parking interface. The parking area includes a plurality of candidate parking spaces. The user may select one of the plurality of candidate parking spaces as the target parking space. For example, when the user selects (or picks) a candidate parking space from the plurality of candidate parking spaces presented on the parking interface as the target parking space, in response to a selection operation (or a pick operation) of the user, the terminal device may obtain related information (for example, position coordinates or orientation information of the target parking space) of the target parking space selected by the user, and may send the related information of the target parking space to the vehicle 100. For another example, after selecting a candidate parking space from the plurality of candidate parking spaces presented on the parking interface as the target parking space, the user may tap a submit button (or a confirm button). In response to the tap operation of the user, the terminal device may obtain related information (for example, position coordinates or orientation information of the target parking space) of the target parking space selected by the user, and may send the related information of the target parking space to the vehicle 100. Then, after receiving the related information of the target parking space, the vehicle 100 may plan (or generate or determine) a parking route (or may be referred to as a traveling route or a parking route or a parking path or a traveling path or a path of parking) based on a current position of the vehicle 100 and the related information of the target parking space, and may automatically travel to (or may be referred to as automatically proceed to) the target parking space based on the parking route.

[054] It may be understood that the target application may be used to assist the user in implementing automated valet parking. For example, the target application may be a client (for example, a head unit client, a personal computer (personal computer, PC) client, or a mobile phone client), a web application, or a mini program embedded in another application. Optionally, the terminal device may also include a display, configured to present the parking interface, to implement human-computer interaction. The parking interface displays information edited by the user (for example, an instruction (for example, a cruise resumption instruction or a confirmation instruction) delivery operation or a virtual parking space dragging operation) or information provided for the user (for example, parking space information of a parking lot).

[055] For example, the terminal device is a device that provides voice or data connectivity for a user, or may be an internet of things device, or may be referred to as a terminal, user equipment (user equipment, UE), an access terminal device, a vehicle-mounted terminal, an industrial control terminal, a mobile terminal (mobile terminal, MT), a remote terminal device, a mobile device, or the like. For example, the terminal device may be: a mobile phone (mobile phone), a tablet computer (Pad), a notebook computer, a palmtop computer, a customer premises equipment (customer-premises equipment, CPE), a personal digital assistant (personal digital assistant, PDA) computer, a handheld device (handset), a laptop computer (laptop computer), a computer with a wireless transceiver function, a virtual reality (virtual reality, VR) terminal device, an augmented reality (augmented reality, AR) terminal device, a head mounted display (head mounted display, HMD), a wireless terminal in industrial control (industrial control), a mobile internet device (mobile internet device, MID), a vehicle-mounted terminal (or referred to as a vehicle-mounted functional module or a vehicle-mounted apparatus, for example, a telematics box (Telematics Box, T-Box) in a vehicle), a wireless terminal in self driving (self driving), a wireless terminal in remote medical (remote medical), a wireless terminal in a smart city (smart city), or a wireless terminal in a smart home (smart home).

[056] For example, the vehicle 100 may be a pure electric vehicle (pure electric vehicle / battery electric vehicle, pure EV / battery EV), a hybrid electric vehicle (hybrid electric vehicle, HEV), a range extended electric vehicle (range extended electric vehicle, REEV), a plug-in hybrid electric vehicle (plug-in hybrid electric vehicle, PHEV), an intelligent vehicle (such as an automated guided vehicle (automated guided vehicle, AGV)), a digital vehicle, an automated vehicle, an intelligent manufacturing vehicle, or a vehicle in another form, and these vehicles may be applied to fields such as self driving, assisted driving, intelligent driving, autonomous driving, or connected vehicles.

[057] It should be understood that the foregoing application scenario is merely an example. The intelligent parking method provided in this application may alternatively be applied to another possible scenario, and is not limited to the scenario in the foregoing example. For example, the intelligent parking method may be further applied to the field of smart home, for example, a ground sweeping robot, a ground mopping robot, an autonomous food delivery robot, or a mobile smart household appliance. These devices may interact with a user terminal, to assist the user in remotely instructing a safe parking position. For another example, the intelligent parking method may be further applied to a smart life scenario, for example, may be applied to an auto-follow suitcase, or may be applied to a smart dining chair, or may be applied to a smart personal mobility device. Possible application scenarios are not enumerated herein.

[058] It should be noted that FIG. 1 provides only an example of a possible application scenario. The example application scenario is used to describe technical solutions in embodiments of this application more clearly, and does not constitute a limitation on an application scenario of the intelligent parking method provided in this application. In addition, a person of ordinary skill in the art may learn that, as a new application scenario emerges, the technical solutions provided in embodiments of this application are also applicable to a similar technical problem.

[059] Based on the application scenario shown in FIG. 1, for ease of understanding this application, a system architecture for implementing an intelligent parking method is first provided. The system architecture is configured in the vehicle 100. As shown in FIG. 2, the system architecture may include three types in terms of functions: a sensor system, a computing platform, and an actuator. It should be noted that a connection relationship between the functional modules shown in FIG. 2 is merely an example, and does not constitute a limitation on this application. The following separately describes functions of the functional modules.

[060] The sensor system is responsible for collecting environment information (for example, ambient environment information of the vehicle) or state information of the vehicle (for example, a vehicle position, a speed, a deceleration, an acceleration, or an attitude angle (for example, a pitch angle, a roll angle, or a yaw angle)). For example, the sensor system may include an image capture system, a global positioning system (Global Positioning System, GPS), and a chassis sensing device. The image capture system may include an image capture apparatus. Optionally, the image capture system may further include a radar device.

[061] The image capture apparatus may include but is not limited to a visible light camera, a depth camera (that is, a three-dimensional camera), a fisheye camera, a monocular camera, a binocular camera, a near-infrared camera, a video camera, a cockpit camera, a dashboard camera (that is, a video recording terminal), a reversing camera, a depth camera, or the like. For example, the image capture apparatus is a fisheye camera. Fisheye cameras may be separately disposed in four directions of the vehicle 100: front, rear, left, and right, to collect environment information in the front, rear, left, and right directions of the vehicle 100. A field of view of each of the four fisheye cameras may be greater than 180 degrees, so that ambient environment information of the vehicle 100 can be comprehensively captured. It should be understood that a larger field of view of the image capture apparatus indicates a larger range that can be sensed by the image capture apparatus.

[062] When the image capture system further includes a radar device, the radar device may transmit an electromagnetic wave signal to the outside through an antenna, receive an echo signal obtained by reflecting the electromagnetic wave signal by the target, and perform processing such as amplification and down-conversion on the echo signal, to obtain information such as a relative distance, a relative speed, and an angle between the vehicle 100 and the target. For example, the radar device may be at least one of a lidar sensor, a millimeter-wave radar sensor, or the like. The millimeter-wave radar sensor may sense a target in an ambient environment of the vehicle 100 by using a radio signal, for example, may collect information about a distance between an obstacle around the vehicle and the ego vehicle. In some embodiments, in addition to sensing the target, the millimeter-wave radar sensor may be further configured to sense a speed and / or a moving direction of the target. The lidar may sense, by using a laser, the target in the environment in which the vehicle 100 is located.

[063] The GPS may be any sensor configured to estimate a geographical position of the vehicle 100. For example, the GPS may include a transceiver that estimates a position of the vehicle 100 relative to the earth based on satellite positioning data.

[064] The chassis sensing device may be configured to collect traveling state information (or may be referred to as traveling data or traveling state data, for example, a vehicle position, a speed, a deceleration, an acceleration, or an attitude angle) of the vehicle. For example, the chassis sensing device may include an inertial measurement unit (Inertial Measurement Unit, IMU) and a brake for changing a position and / or an orientation of the sensor. The IMU may be configured to sense position and orientation changes of the vehicle 100 based on an inertial acceleration and any combination thereof. In some embodiments, a combination of sensors in the IMU may include an accelerometer sensor and a gyroscope sensor.

[065] The computing platform is configured to control some functions of the vehicle 100, or may be responsible for processing corresponding information or data. For example, the computing platform may include a perception module (or may be referred to as a perception system), a decision-making and planning module (or may be referred to as a decision-making and planning system), and a control module (or may be referred to as a control system).

[066] The perception module may obtain sensing information (for example, ambient environment information of the vehicle 100) corresponding to the vehicle 100 from an image capture apparatus or a radar device in the sensor system, and may process the sensing information to obtain a dynamic-static object (or may be referred to as a dynamic-static target, such as an obstacle, a vehicle, a pedestrian, or a lane line) existing in the ambient environment and an attribute of the dynamic-static object (for example, a future movement intention of each object, a type (for example, a specific object, for example, a vehicle, an obstacle, a pedestrian, or another object), position information, a movement direction, or shape information), to establish a world model including a road, an obstacle, or the like for a downstream module (for example, a decision-making and planning module).

[067] The decision-making and planning module may obtain the dynamic-static object and the attribute of the dynamic-static object from the perception module, and may obtain the traveling state information of the vehicle 100 from the chassis sensing device in the sensor system. Then, the decision-making and planning module may make a behavior decision (for example, determine whether a traveling trajectory of the ego vehicle conflicts with an obstacle, and how to avoid the obstacle when there is a conflict, or determine whether a traveling trajectory of the ego vehicle conflicts with a traveling trajectory of another vehicle, and how to avoid another vehicle when there is a conflict) based on the dynamic-static object, the attribute of the dynamic-static object, and the traveling state information of the vehicle 100, and generate a decision-making solution (for example, a solution for avoiding an obstacle or a solution for avoiding another vehicle), to obtain an expected traveling trajectory (or may be referred to as an expected traveling path) of the vehicle 100.

[068] The control module may obtain the decision-making solution from the decision-making and planning module, and may obtain the traveling state information of the vehicle 100 from the chassis sensing device in the sensor system. Then, the control module may determine, based on the decision-making solution and the traveling state information of the vehicle 100, a control variable (or may be referred to as control information or a control signal) used to control the vehicle 100 to travel (or avoid another vehicle or avoid an obstacle), and may send the corresponding control variable to the actuator. For example, the control variable may be a torque instruction used to drive the vehicle 100 to travel or a braking instruction used to drive a brake control system.

[069] For example, the control module may be a throttle, a brake control system (or may be referred to as a brake unit), a steering control system (or may be referred to as a steering unit), a gear control system, or the like in a vehicle. The throttle is configured to control an operating speed of an engine and further control a speed of the vehicle 100. The brake pedal control system is configured to control the vehicle 100 to decelerate or stop. The brake pedal control system may use friction, a current, or the like to slow down rotation of a wheel. The steering control system is configured to control (or adjust) a forward or backward direction of the vehicle 100. The gear control system may be configured to control (or adjust) a gear (for example, a drive gear, a reverse gear, or a parking gear) of the vehicle 100.

[070] The actuator is configured to perform a corresponding operation based on the control variable from the control module. For example, the actuator may include a motor drive unit and a motor (or a solenoid valve). The motor drive unit may drive, based on the received control variable, the motor (or the solenoid valve) to run, to perform corresponding processing. For example, the motor drive unit drives the solenoid valve to adjust an intake air volume of a valve. It should be understood that the actuator may be any component that can implement a corresponding function based on a control signal output by the control system. This is not limited in this application. Optionally, the control module may communicate with the actuator through a controller area network (controller area network, CAN) bus or an input / output (input / output, I / O) hardwire.

[071] As described in the background, there are passing difficulty problems such as ego vehicle immobilization or traffic blockage in an existing automated valet parking technology. As a result, a success rate of automated parking is low, and user experience is poor. For example, in automated parking solutions currently provided in the industry, one automated parking solution is to process a difficulty encountering scenario of an autonomous vehicle by remotely controlling a vehicle actuator. However, remotely controlling the vehicle actuator to operate the autonomous vehicle in real time has high communication latency requirements, and a vehicle actuator control operation on a handheld device is complex and difficult. In another automated parking solution, in response to receiving a request message from an autonomous vehicle, the autonomous vehicle and a cloud-side cockpit are calibrated, so that an initial state of a first operating apparatus in the cockpit is consistent with an initial state of a corresponding second operating apparatus in the autonomous vehicle, and the calibration is performed to prepare for subsequent control of the autonomous vehicle. The first operating apparatus in the cockpit performs an operation, generates a control signal, and sends the control signal to the autonomous vehicle, to control the second operating apparatus in the autonomous vehicle to perform an action based on the operation of the first operating apparatus in the cloud cockpit. However, a solution of using the cloud-side cockpit requires support of a cloud device and personnel, and costs are high. Therefore, the solution is not applicable to a large-scale commercial scenario of automated valet parking. In addition, a link of the solution is long, and reliability of remote control of the autonomous driving system is affected.

[072] In view of this, this application provides an intelligent parking method, to improve reliability and a success rate of automated valet parking by combining autonomous extrication of the vehicle and remote assistance with extrication by the user, thereby improving user experience.

[073] The following describes in detail a specific implementation of the intelligent parking method in embodiments of this application based on the application scenario shown in FIG. 1.

[074] FIG. 3 is an example of a schematic flowchart of an intelligent parking method according to an embodiment of this application. The method is applicable to the application scenario shown in FIG. 1. For example, the intelligent parking method shown in FIG. 3 is described by using an example in which the first vehicle and the terminal device are used as execution bodies of interaction illustration. However, the execution bodies of the interaction illustration are not limited in this application. It may be understood that the method performed by the first vehicle in this application may be performed by a module (such as a processor, a processing unit, a chip system, a circuit, or a chip) applied to the first vehicle, or may be implemented by a logical node, a logical module, or software that can implement all or some functions of a network device. The method performed by the terminal device in this application may be performed by a module (such as a processor, a processing unit, a chip system, a circuit, or a chip) applied to the terminal device, or may be implemented by a logical node, a logical module, or software that can implement all or some functions of the terminal device.

[075] As shown in FIG. 3, the method includes the following steps.

[076] Step 301: If the first vehicle encounters a passing difficulty in a parking route to a target parking space, the first vehicle sends a first request to the terminal device when autonomous extrication of the first vehicle fails. Correspondingly, the terminal device receives the first request from the first vehicle.

[077] The first request may be for requesting to assist the first vehicle with extrication, or the first request may indicate that autonomous extrication of the first vehicle (that is, autonomously getting out of the difficulty) fails and remote assistance of a user is required for extrication.

[078] For example, when the user of the first vehicle needs to start an automated valet parking task, the user may select and submit a target parking space on a vehicle-mounted application or a vehicle application installed on the terminal device (for example, a smartphone). The vehicle-mounted application or the vehicle application may be a target application, and may present a parking interface to implement human-computer interaction. In response to the submission operation of the user, the vehicle-mounted application or the vehicle application may obtain related information (for example, position coordinates of the target parking space) of the target parking space, and may deliver the related information of the target parking space to the first vehicle. For example, as shown in FIG. 4, after a user of the first vehicle taps an automated valet parking function in a target application (for example, the vehicle-mounted application installed on the first vehicle or the vehicle application (Application, APP) installed on the smartphone) installed on the terminal device, the target application may present the parking interface to the user, and wait for the user to select the target parking space. A parking area (for example, a parking lot) is presented on the parking interface. The parking area includes a plurality of candidate parking spaces. The user may select one candidate parking space (for example, B8-F5-1375) from the plurality of candidate parking spaces as the target parking space, or the user selects one candidate parking space from the plurality of candidate parking spaces as the target parking space and taps a submit button (or a confirm button). In response to the selection operation or the tap operation of the user, the terminal device may obtain related information (for example, position coordinates or orientation information of the target parking space) of the target parking space selected by the user, and may send the related information of the target parking space to the first vehicle.

[079] Optionally, still refer to FIG. 4. When the first vehicle has been parked in the target parking space, if the user of the first vehicle needs to summon the first vehicle (which may be understood as that the user of the first vehicle does not want to go to the position of the target parking space, but wants the first vehicle to automatically travel from the target parking space to a position of the user of the first vehicle), the user of the first vehicle may edit, on the parking interface of the target application (for example, a vehicle APP) installed on the terminal device, an instruction (or indication information) for enabling the first vehicle to automatically proceed to the position of the user of the first vehicle, and submit the instruction. The instruction (or the indication information) instructs the first vehicle to automatically proceed to the position of the user. For example, the instruction (or the indication information) may include a position of the user (or may be referred to as a current position of the user or coordinates of the position of the user). In response to a corresponding operation triggered by the user on the parking interface, the terminal device may obtain the instruction (or the indication information), and may send the instruction (or indication information) to the first vehicle. After the instruction (or the indication information), the first vehicle may plan, based on the instruction (or the indication information), a traveling route (or may be referred to as a traveling path) from the target parking space to the position of the user. For example, the first vehicle may plan a corresponding traveling route based on the position of the target parking space and the position of the user. Then, the first vehicle may automatically proceed to the position of the user based on the traveling route.

[080] After obtaining the related information of the target parking space, the first vehicle may determine the parking route based on the related information of the target parking space and the position information of the first vehicle. Then, the first vehicle may automatically cruise to the target parking space based on the parking route. When the first vehicle encounters a passing difficulty (for example, ego vehicle immobilization or blockage of traveling of another vehicle) in a process of automatically cruising to the target parking space based on the parking route, the first vehicle may attempt autonomous extrication. When the first vehicle does not encounter a passing difficulty in the process of automatically cruising to the target parking space based on the parking route, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. It may be understood that, the first vehicle may continuously detect whether the first vehicle encounters a passing difficulty in the process of proceeding to the target parking space. For example, in the process of proceeding to the target parking space based on the parking route, the first vehicle may determine, based on traveling state information of the first vehicle and ambient environment information (for example, interaction information between the first vehicle and a surrounding social vehicle), whether a passing difficulty occurs.

[081] In an example, if the autonomous extrication attempt of the first vehicle fails, the first vehicle may send the first request to the terminal device. Optionally, after the autonomous extrication attempt fails, the first vehicle may alternatively send a vehicle state of the first vehicle to the terminal device (for example, a current state of the first vehicle, for example, ego vehicle immobilization or encountering a passing difficulty due to blockage of traveling of another vehicle).

[082] In another example, if the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. Then, if the first vehicle does not encounter a passing difficulty in a subsequent automated cruise process, the first vehicle starts to park when arriving near the target parking space based on the parking route, until the first vehicle parks into the target parking space. In this case, the automated valet parking task ends. Optionally, if the first vehicle encounters a passing difficulty again in the subsequent automated cruise process, the first vehicle may attempt autonomous extrication again. When the autonomous extrication attempt of the first vehicle fails, the first vehicle may send the first request to the terminal device. When the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. The rest may be deduced by analogy until the first vehicle parks into the target parking space or wait for onsite takeover by the user.

[083] The following describes, in the following several possible implementations, a case in which the first vehicle encounters a passing difficulty in the process of proceeding to the target parking space.

[084] Implementation 1: In the process in which the first vehicle proceeds to the target parking space, when the first vehicle blocks passing of a first target, the first vehicle determines that a passing difficulty occurs.

[085] The first target is a target that is in a traveling area in which the first vehicle is located and that has a bidirectional interaction relationship with the first vehicle. For example, the first target may be a vehicle meeting target, for example, an approaching vehicle, or the first target may be another game target, for example, a crossing vehicle or a vehicle merging into the same lane. It may be understood that the bidirectional interaction relationship refers to a relationship in which behaviors of both parties affect each other. For example, an ego vehicle and another vehicle (or may be referred to as an oncoming vehicle) that travels relative to the ego vehicle are used as an example. If there is a traveling trajectory conflict or a traveling intention conflict between the ego vehicle and another vehicle that travels relative to the ego vehicle, there is a bidirectional interaction relationship between the ego vehicle and the another vehicle that travels relative to the ego vehicle. In this case, the ego vehicle determines that a passing difficulty occurs. In other words, if there is an intersection (or may be referred to as a conflict) between a future traveling trajectory (or may be referred to as a future traveling intention or a future movement trajectory or a future movement intention) of the ego vehicle and a future traveling trajectory of another vehicle that travels relative to the ego vehicle, there is a bidirectional interaction relationship between the ego vehicle and the another vehicle that travels relative to the ego vehicle. In this case, the ego vehicle determines that a passing difficulty occurs.

[086] In this embodiment of this application, the first vehicle may obtain, by using a sensor (for example, an image capture apparatus, a radar device, or a chassis sensing device) of the ego vehicle (or may be referred to as the first vehicle), sensing information corresponding to the ego vehicle, and may determine a plurality of targets based on the sensing information. Then, the first vehicle may obtain state information (for example, position information, speed information, movement directions, shape information, or turn light information) of the plurality of targets based on the sensing information, and may predict future movement trajectories (or may be referred to as future movement intentions) of the plurality of targets based on the state information of the plurality of targets. Then, the first vehicle may determine interaction relationships between the first vehicle and the plurality of targets based on a future movement trajectory of the first vehicle and the future movement trajectories of the plurality of targets. The future traveling trajectory of the first vehicle is determined based on a current position of the first vehicle and a parking route of the first vehicle. For each of the plurality of targets, if there is no conflict (or may be referred to as no intersection) between the future movement trajectory of the first vehicle and the future movement trajectory of the target, the first vehicle has no interaction relationship with the target. It should be understood that no interaction relationship may mean that the movement of the ego vehicle does not affect the target. For example, when the target is a stationary vehicle parked in a parking space, a vehicle traveling away from the ego vehicle, a traffic sign, a pedestrian on a roadside sidewalk, or the like, there is no interaction between the target and the first vehicle. If there is a conflict between the future movement trajectory of the first vehicle and the future movement trajectory of the target, the first vehicle has an interaction relationship with the target. For example, there may be two types of interaction relationships: one is a bidirectional interaction relationship, and the other is a unidirectional interaction relationship. When there is a bidirectional interaction relationship between the first vehicle and the target, the target may be the first target. In this case, the first vehicle may block passing of the target, and the first vehicle determines that a passing difficulty occurs.

[087] For example, the sensing information may include information about the first vehicle and ambient environment information of the first vehicle, for example, may include but is not limited to a position of the ego vehicle, a current wheel steering of the ego vehicle, a position of another vehicle within a threshold range of the ego vehicle, a distance between the another vehicle and the ego vehicle, a position of a road boundary within the threshold range of the ego vehicle (or a sensing area or a region of interest (region of interest, ROI)), a distance between the road boundary and the ego vehicle, an image corresponding to an ambient environment, or the like.

[088] It may be understood that the threshold range may be a maximum sensing range of the capture apparatus (for example, a sensor) of the ego vehicle. For example, it is assumed that the sensing range of the capture apparatus of the ego vehicle is a circular area formed by using the ego vehicle in which the capture apparatus is located as a dot and a radius of 200 meters, the threshold range in this embodiment of this application may be a circular area formed by using the ego vehicle as a dot and a radius of 200 meters. For example, the sensing area or the region of interest may be an area extending 15 m in front of the ego vehicle and 3 m to the left and right.

[089] For example, the plurality of targets may include a static target and a dynamic target. For example, the static target may include but is not limited to a road boundary, a column in a parking garage, a wall in a parking garage, a traffic post in a parking garage, a fire-proof rolling gate in a parking garage, a traffic post in a parking lot, a road sign in a parking lot, a tree in a parking lot, or another roadblock. The dynamic target may include but is not limited to a traveling vehicle, a pedestrian, an animal, another moving object, and the like.

[090] In addition, in this embodiment of this application, the first vehicle may alternatively determine decision-making results of the plurality of targets. A decision-making result of each of the plurality of targets indicates an avoidance measure taken by the first vehicle on the target. In other words, the decision-making result may be an action that the first vehicle needs to take on a surrounding target, to subsequently determine a movement trajectory (or may be referred to as a traveling trajectory) required for autonomous extrication of the first vehicle.

[091] It may be understood that, for a static target, whether to bypass is determined, and if so, to bypass from the left or the right is determined; and for an oncoming vehicle, whether to perform a lateral avoidance and a longitudinal deceleration is determined. Similarly, in the case of the lateral avoidance, whether to avoid to the left or to the right is determined. For example, in a process in which the first vehicle proceeds to the target parking space based on the parking route, if the first vehicle travels in the middle of a wide lane, and a distant oncoming vehicle also travels in the middle of the lane, the decision-making result in this case may be a lateral avoidance to the right, and no longitudinal deceleration is needed to complete a meeting with the oncoming vehicle. If a lane width is narrow, the decision-making result may be a lateral avoidance to the right and a longitudinal deceleration, to avoid a collision risk.

[092] For example, the first vehicle may determine, based on road environment information and a traffic rule, a right-of-way relationship between the first vehicle and the plurality of targets, and comprehensively consider indicators such as safety, passability, and comfort, to determine an action (that is, a decision-making result) to be performed on the plurality of targets.

[093] The following briefly describes the preceding indicators.

[094] (1) Right of way: The right-of-way refers to the right of an object to travel in specific space and time. For example, the following are examples of right-of-way levels in different scenarios:Intersection scenario rules: zebra crossing>go straight>turn left>turn right>U turn;Non-intersection scenario rules: zebra crossing>straight through the lane>lane change>reverse straight>crossing>opening.

[095] For example, in an intersection scenario, if an obstacle is on a zebra crossing, and the first vehicle goes straight, the right of way of the obstacle is higher. If the first vehicle goes straight, and an obstacle turns left, the right of way of the first vehicle is higher.

[096] (2) Safety: Safety refers to safety of an interaction process between the first vehicle and the target (for example, an obstacle). For example, in the interaction process between the first vehicle and the obstacle, a distance greater than a specific threshold is always maintained. In this case, safety is high. For another example, a collision occurs in the interaction process between the first vehicle and the obstacle. In this case, safety is the lowest. Higher safety of the obstacle indicates a stronger tendency to maintain the current state. The following are examples of safety levels in different scenarios:Intersection scenario rules: zebra crossing>go straight>turn left>turn right>U turn;Non-intersection scenario rules: crossing>straight through the lane>lane change>reverse straight>opening.

[097] (3) Passability: The first vehicle needs to keep a specific speed through specific space. For example, passing through an intersection is used as an example. Generally, faster passing through the intersection indicates higher passability. However, if a brake is performed midway, passing through the intersection is very slow, and the passability is lower. The following are examples of passability levels in different scenarios:Intersection scenario rules: go straight>turn left>turn right>U turn (U turn)>zebra crossing;Non-intersection scenario rules: straight through the lane>lane change>reverse straight>crossing>opening.

[098] For example, in an intersection scenario, if an obstacle is on a zebra crossing, and the first vehicle goes straight, passability of the first vehicle is higher.

[099] (4) Comfort: Comfort can be represented by a jerk value. A larger jerk value indicates poorer comfort. Higher comfort indicates a stronger tendency to maintain the current state. In different scenarios, comfort can be further classified into horizontal and vertical comfort. The following are examples of comfort levels in different scenarios:

[0100] Intersection scenario rules:Horizontal: U-turn>turn left≈turn right>zebra crossing>go straight;Vertical: zebra crossing>go straight>turn left≈turn right>U-turn.

[0101] Non-intersection scenario rules:Horizontal: lane change>opening>reverse straight>straight through the lane≈crossing;Vertical: straight through the lane>lane change>reverse straight>crossing>opening.

[0102] Implementation 2: In the process in which the first vehicle proceeds to the target parking space, when a second target blocks passing of the first vehicle, the first vehicle determines that a passing difficulty occurs.

[0103] The second target is a target (for example, a non-game target) that is in the traveling area in which the first vehicle is located and that has a unidirectional interaction relationship with the first vehicle. For example, the second target may be a stationary vehicle parked on a roadside, or may be a roadside obstacle (for example, a traffic post). It may be understood that the unidirectional interaction relationship is a relationship in which traveling of an ego vehicle is affected by a target, but the target is not affected by the ego vehicle. For example, an ego vehicle and a stationary vehicle parked on a roadside are used as an example. If the stationary vehicle parked on the roadside affects traveling of the ego vehicle, there is a unidirectional interaction relationship between the ego vehicle and the stationary vehicle parked on the roadside. In this case, the ego vehicle determines that a passing difficulty occurs.

[0104] In this embodiment of this application, for each of the plurality of targets, when there is a unidirectional interaction relationship between the first vehicle and the target, the target may be the second target. In this case, the target may block passing of the first vehicle, and the first vehicle determines that a passing difficulty occurs.

[0105] It should be understood that Implementation 1 and Implementation 2 may be separately implemented, or may be implemented in combination. This is not limited in this embodiment of this application.

[0106] Optionally, a process of determining whether the first vehicle encounters a passing difficulty in the process of proceeding to the target parking space based on the parking route may be performed by a vehicle passing state detection and autonomous extrication unit in the first vehicle. The vehicle passing state detection and autonomous extrication unit is in the decision-making and planning module. To further describe a specific determining process, the following describes, with reference to FIG. 5, an implementation process in which the vehicle passing state detection and autonomous extrication unit determines whether the first vehicle encounters a passing difficulty in the process of proceeding to the target parking space based on the parking route. It should be understood that the vehicle passing state detection and autonomous extrication unit may continuously detect whether the first vehicle encounters a passing difficulty in the process of proceeding to the target parking space.

[0107] As shown in FIG. 5, the perception module in the first vehicle performs sensing prediction on the sensing information, to obtain a plurality of targets and attributes of the plurality of targets (for example, a future movement intention, a type, position information, a movement direction, or shape information of each target). Then, the decision-making and planning module (or a decision-making submodule included in the decision-making and planning module) in the first vehicle may perform interaction decisions on the plurality of targets based on the plurality of targets, the attributes of the plurality of targets, and traveling state information of the first vehicle, to determine a static target, a vehicle meeting target, and a non-game target, and determine interaction states (for example, bidirectional interaction, unidirectional interaction, or no interaction) between the first vehicle and the static target, the vehicle meeting target, and the non-game target respectively. Then, when the first vehicle is in a low-speed state (for example, a vehicle speed is 3.5 km / h), the vehicle passing state detection and autonomous extrication unit in the decision-making and planning module may determine (or extract) left and right boundaries of a drivable area of the first vehicle (or may be referred to as left and right boundaries of a passable area of the first vehicle, or a boundary range of the drivable area of the first vehicle, or a boundary range of the passable area of the first vehicle) based on an attribute of the static target and composition boundary information (for example, road or lane boundary composition).

[0108] For example, the vehicle meeting target may be a target (for example, a bidirectional interaction target), in the plurality of targets, with a vehicle head direction opposite to a parking route of an ego vehicle. For example, the decision-making and planning module (or a decision-making submodule included in the decision-making and planning module) may select, from a plurality of targets, at least one target that has or has had a reverse speed (for example, a speed less than –1 km / h) and whose included angle between a vehicle head direction and a parking route of an ego vehicle is within –180 deg to –150 deg or 150 deg to 180 deg. For each of the at least one target, if the ego vehicle passes by the target or the target passes by the ego vehicle, the decision-making and planning module (or a decision-making submodule included in the decision-making and planning module) may determine the target as the vehicle meeting target.

[0109] For each vehicle meeting target in the region of interest (or the sensing area or the threshold range of the ego vehicle), the vehicle passing state detection and autonomous extrication unit may determine, based on the left and right boundaries of the drivable area of the first vehicle and an interaction state between the first vehicle and the vehicle meeting target, whether the first vehicle blocks traveling of the vehicle meeting target (which may be understood as that the vehicle passing state detection and autonomous extrication unit determines, based on interaction decision–based vehicle meeting passability determination, whether the first vehicle blocks traveling of the vehicle meeting target). If the first vehicle blocks traveling (or passing) of the vehicle meeting target, the vehicle passing state detection and autonomous extrication unit determines that the first vehicle encounters a passing difficulty. In this case, the vehicle meeting target is the first target (which may be understood as an extrication candidate target).

[0110] For example, in some possible embodiments, when the interaction state between the first vehicle and the vehicle meeting target is bidirectional interaction, if the vehicle meeting target travels relative to the first vehicle at a position on the left side of the first vehicle, the vehicle passing state detection and autonomous extrication unit may select (or determine) a plurality of points in a left-side passable area of the first vehicle at a specified distance interval (for example, every 0.1 m interval), and for each of the plurality of points, calculate whether a passable width corresponding to the point is greater than or equal to a first width threshold. If the vehicle meeting target travels relative to the first vehicle at a position on the right side of the first vehicle, the vehicle passing state detection and autonomous extrication unit may select (or determine) a plurality of points in a left-side passable area of the first vehicle at a specified distance interval (for example, every 0.1 m interval), and for each of the plurality of points, calculate whether a passable width corresponding to the point is greater than or equal to the first width threshold. It may be understood that, if a passable width corresponding to any point is less than the first width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the first vehicle blocks traveling (or passing) of the vehicle meeting target. If passable widths respectively corresponding to the plurality of points are all greater than or equal to the first width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the first vehicle does not block traveling (or passing) of the vehicle meeting target. For example, the first width threshold may be a sum of a width of the vehicle meeting target and an additional quantity. For example, the additional quantity may be 0.3 m×2.

[0111] For example, the first vehicle is a vehicle A, the vehicle meeting target is a vehicle B, the vehicle B may pass through a left-side passable area of the vehicle A, and N points (for example, a point 1, a point 2, a point 3, ..., and a point N) are determined in the left-side passable area of the vehicle A based on a specified distance interval (for example, 0.1 m). As shown in FIG. 6a, a vehicle passing state detection and autonomous extrication unit in the vehicle A may calculate, in a sequence of the point 1, the point 2, the point 3, ..., and the point N, whether a distance width between each point and a left boundary of the drivable area of the vehicle A is greater than or equal to the first width threshold. If a distance width between at least one of the N points and the left boundary of the drivable area of the vehicle A is less than the first width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the vehicle A blocks passing of the vehicle B. If distance widths between the N points and the left boundary of the drivable area of the vehicle A are all greater than or equal to the first width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the vehicle A does not block passing of the vehicle B.

[0112] In some other possible embodiments, the passable width needs to be considered, and a kinematic characteristic of the vehicle meeting target and an obstacle around the vehicle meeting target also need to be comprehensively considered. For example, when a meeting of an ego vehicle and a vehicle meeting target occurs at a corner, a passable width beside the ego vehicle may be greater than or equal to the first width threshold. However, if the vehicle meeting target does not reverse, a pose cannot be adjusted to pass by the ego vehicle. If there is an obstacle behind the vehicle meeting target, and the vehicle meeting target cannot reverse, the ego vehicle in this case still blocks passing of the vehicle meeting target if the ego vehicle does not yield space.

[0113] For each non-game target in the region of interest (or the sensing area or the threshold range of the ego vehicle), the vehicle passing state detection and autonomous extrication unit may determine, based on the left and right boundaries of the drivable area of the first vehicle and an interaction state between the first vehicle and the non-game target, whether the non-game target blocks traveling of the first vehicle. If the non-game target blocks traveling of the first vehicle, the vehicle passing state detection and autonomous extrication unit determines that the first vehicle encounters a passing difficulty, and may deduce extrication feasibility for the non-game target. In this case, the non-game target is the second target (which may be understood as an extrication candidate target).

[0114] For example, in some possible embodiments, when the interaction state between the first vehicle and the non-game target is unidirectional interaction, if the non-game target is in a static state at a left front position of the first vehicle, the vehicle passing state detection and autonomous extrication unit may determine a plurality of points in the drivable area of the first vehicle at a specified distance interval (for example, every 0.1 m interval), and for each of the plurality of points, calculate whether a passable width corresponding to the point is greater than or equal to a second width threshold. If the non-game target is in a static state at a right front position of the first vehicle, the vehicle passing state detection and autonomous extrication unit may determine a plurality of points in the drivable area of the first vehicle based on a specified distance interval (for example, every 0.1 m interval), and for each of the plurality of points, calculate whether a passable width corresponding to the point is greater than or equal to the second width threshold. It may be understood that, if a passable width corresponding to any point is less than the second width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the non-game target blocks traveling (or passing) of the first vehicle. If passable widths respectively corresponding to the plurality of points are all greater than or equal to the second width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the non-game target does not block traveling (or passing) of the first vehicle. For example, the second width threshold may be a sum of a width of the first vehicle and an additional quantity. For example, the additional quantity may be 0.15 m×2.

[0115] For example, the first vehicle is a vehicle A, the non-game target is a vehicle C, the vehicle C is parked at a left front position of the vehicle A, and N points (for example, a point 1, a point 2, ..., and a point N) are determined in a right-side passable area of the vehicle C based on a specified distance interval (for example, 0.1 m). As shown in FIG. 6b, a vehicle passing state detection and autonomous extrication unit in the vehicle A may calculate, in a sequence of the point 1, the point 2, ..., and the point N, whether a distance width between each point and a right boundary of the drivable area of the vehicle A is greater than or equal to the second width threshold. If a distance width between at least one of the N points and the right boundary of the drivable area of the vehicle A is less than the second width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the vehicle C blocks passing of the vehicle A. If distance widths between the N points and the right boundary of the drivable area of the vehicle A are all greater than or equal to the second width threshold, the vehicle passing state detection and autonomous extrication unit may determine that the vehicle C does not block passing of the vehicle A.

[0116] Based on the foregoing content, the following describes, in the following several possible implementations, an implementation process in which the first vehicle performs extrication planning (or may be referred to as autonomous extrication planning or movement planning) for the first target or the second target.

[0117] Manner 1: When the first vehicle determines at least one first target (for example, at least one vehicle meeting target used as the extrication candidate target), the first vehicle may arbitrate (or select or determine) one of the at least one first target as an extrication target (or may be understood as using a first target as the extrication target), and may perform extrication planning for the first target based on a decision-making result of the first target, to attempt to initiate autonomous extrication.

[0118] In this embodiment of this application, the first vehicle may obtain an extrication priority of the at least one first target, and may determine, from the at least one first target based on the extrication priority of the at least one first target, a first target with the highest extrication priority as the extrication target. The extrication priority of each of the at least one first target is determined based on a traffic condition of a road area in which the first target is located, a type of the first target, a right-of-way relationship between the first vehicle and the first target, and in combination with indicators such as safety, passability, comfort, and attention.

[0119] Optionally, the first vehicle may alternatively perform extrication planning for the first target based on the decision-making result of the first target and a boundary of the passable area of the first vehicle (or may be referred to as a boundary of the drivable area, including a left boundary and a right boundary of the drivable area). In this way, a boundary restriction status of the road area (or a surrounding area of the first vehicle) in which the first vehicle is located can be fully considered by introducing the boundary of the passable area of the first vehicle, so that the first vehicle can more accurately determine whether a parking position (or may be referred to as a parking area) for autonomous extrication of the first vehicle exists in the road area in which the first vehicle is located, thereby making extrication planning for the first target by the first vehicle more accurate and targeted.

[0120] In an example, when an autonomous extrication attempt of the first vehicle fails (for example, passing of the first target fails and / or passing of the first vehicle fails), the first vehicle may send a first request to the terminal device in time. In another example, when an autonomous extrication attempt of the first vehicle succeeds (that is, passing of both the first target and the first vehicle succeeds), the first vehicle may continue to automatically cruise to the target parking space based on the parking route. If the first vehicle does not encounter a passing difficulty in a subsequent automated cruise process, the first vehicle starts to park when arriving near the target parking space based on the parking route, until the first vehicle parks into the target parking space. Optionally, if the first vehicle encounters a passing difficulty again in the subsequent automated cruise process, the first vehicle may attempt autonomous extrication again. When the autonomous extrication attempt of the first vehicle fails, the first vehicle may send the first request to the terminal device. When the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. The rest may be deduced by analogy until the first vehicle parks into the target parking space or wait for onsite takeover by the user.

[0121] In this embodiment of this application, when the first vehicle blocks passing of the first target, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, after using a first target as the extrication target, the first vehicle may adopt (or use) the following extrication planning: If it is determined that there is an idle area (or may be referred to as an open area) around the first vehicle, the first vehicle may attempt to park in the idle area, to leave passing space (or may be referred to as a passing area) for the first target, thereby implementing autonomous extrication of the first vehicle. It may be understood that when the first vehicle determines that there is an idle area around the first vehicle, the first vehicle may plan, based on ambient environment information, a traveling route to the idle area, and may proceed to the idle area based on the planned traveling route.

[0122] For example, the first vehicle may determine, based on a decision-making result of the first target (for example, avoiding the first target to the right side and needing a longitudinal deceleration) (or based on the decision-making result of the first target and a boundary of the drivable area of the first vehicle), whether an idle area for the first vehicle to park exists on the right side of the first vehicle. If an idle area for the first vehicle to park exists on the right side of the first vehicle, the first vehicle may attempt to park in the idle area on the right side, to leave passing space for the first target on the left side of the first vehicle. After the first target passes through the passing space, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. In other words, the autonomous extrication attempt of the first vehicle succeeds. If an idle area for the first vehicle to park does not exist on the right side of the first vehicle, it is determined that the autonomous extrication attempt of the first vehicle fails. In this case, the first vehicle may send the first request to the terminal device.

[0123] Optionally, the first vehicle may alternatively determine, based on a decision-making result of the first target (for example, avoiding the first target to the right side and needing a longitudinal deceleration) (or based on the decision-making result of the first target and a boundary of the passable area of the first vehicle), whether the first vehicle can attempt to park on a road edge on the right side, to leave sufficient passing space for the first target. If the first vehicle successfully attempts to park on the road edge on the right side to leave sufficient passing space for the first target, after the first target passes through the passing space, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. In other words, the autonomous extrication attempt of the first vehicle succeeds. If the first vehicle fails to attempt to park on the road edge on the right side to leave sufficient passing space for the first target, it is determined that the autonomous extrication attempt of the first vehicle fails. In this case, the first vehicle may send the first request to the terminal device.

[0124] For example, still refer to FIG. 5. After using a first target as the extrication target, the vehicle passing state detection and autonomous extrication unit in the first vehicle may send related information (for example, a name or an identifier of the first target) of the first target to the decision-making submodule in the decision-making and planning module. After receiving the related information of the first target (or may be referred to as the related information of the extrication target), the decision-making submodule may determine, based on road environment information and a traffic rule, a right-of-way relationship between the first vehicle and the first target, and comprehensively consider indicators such as safety, passability, and comfort, to determine an action (that is, a decision-making result) to be performed on the first target, and may send the decision-making result of the first target to a planning submodule included in the decision-making and planning module. After receiving the decision-making result of the first target, the planning submodule may perform extrication planning for the first target based on the decision-making result of the first target (or based on the decision-making result of the first target and the boundary of the passable area of the first vehicle), to obtain an extrication planning solution (or may be referred to as an extrication decision-making solution, for example, a solution of how to park in the idle area on the right side or a solution of how to park on the road edge on the right side), and may send the extrication planning solution to a control module. The boundary of the passable area of the first vehicle is obtained from the vehicle passing state detection and autonomous extrication unit. After receiving the extrication planning solution, the control module may determine, based on the extrication planning solution and traveling state information of the first vehicle, a control variable used to control the first vehicle to implement the extrication planning solution (for example, park in the idle area on the right side or park on the road edge on the right side), and may send the control variable to the actuator.

[0125] Manner 2: When the first vehicle determines at least one second target (for example, at least one non-game target used as the extrication candidate target), the first vehicle may arbitrate one of the at least one second target as an extrication target (or may be understood as using a second target as the extrication target), and may perform extrication planning for the second target based on a decision-making result of the second target, to attempt to initiate autonomous extrication.

[0126] In this embodiment of this application, the first vehicle may obtain an extrication priority of the at least one second target, and may determine, from the at least one second target based on the extrication priority of the at least one second target, a second target with the highest extrication priority as the extrication target. The extrication priority of each of the at least one second target is determined based on a traffic condition of a road area in which the second target is located, a type of the second target, a right-of-way relationship between the first vehicle and the second target, and in combination with indicators such as safety, passability, comfort, and attention.

[0127] Optionally, the first vehicle may alternatively perform extrication planning for the second target based on the decision-making result of the second target and a boundary of the passable area of the first vehicle. In this way, a boundary restriction status of the road area (or a surrounding area of the first vehicle) in which the first vehicle is located can be fully considered by introducing the boundary of the passable area of the first vehicle, so that the first vehicle can more accurately determine whether a parking position for autonomous extrication of the first vehicle exists in the road area in which the first vehicle is located, thereby making extrication planning for the second target by the first vehicle more accurate and targeted.

[0128] In an example, when an autonomous extrication attempt of the first vehicle fails (for example, passing of the first vehicle fails), the first vehicle may send a first request to the terminal device in time. In another example, when an autonomous extrication attempt of the first vehicle succeeds (that is, passing of the first vehicle succeeds), the first vehicle may continue to automatically cruise to the target parking space based on the parking route. If the first vehicle does not encounter a passing difficulty in a subsequent automated cruise process, the first vehicle starts to park when arriving near the target parking space based on the parking route, until the first vehicle parks into the target parking space. Optionally, if the first vehicle encounters a passing difficulty again in the subsequent automated cruise process, the first vehicle may attempt autonomous extrication again. When the autonomous extrication attempt of the first vehicle fails, the first vehicle may send the first request to the terminal device. When the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. The rest may be deduced by analogy until the first vehicle parks into the target parking space or wait for onsite takeover by the user.

[0129] In this embodiment of this application, when the second target blocks passing of the first vehicle, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, after using a second target as the extrication target, the first vehicle may adopt (or use) the following extrication planning: The first vehicle may attempt to pass through a narrow passage between the second target and the boundary of the passable area of the first vehicle, or the first vehicle may attempt to bypass the second target. If the first vehicle successfully passes through the narrow passage or successfully bypasses the second target, the first vehicle may continue to automatically cruise to the target parking space based on the parking route. In other words, the autonomous extrication attempt of the first vehicle succeeds. If the first vehicle fails to attempt to pass through the narrow passage (or may be referred to as a failure) or fails to attempt to bypass the second target, it is determined that the autonomous extrication attempt of the first vehicle fails. In this case, the first vehicle may send the first request to the terminal device. It may be understood that if the first vehicle attempts to bypass the second target, the first vehicle may plan, based on ambient environment information, a traveling route required for bypassing the second target, and may bypass the second target based on the planned traveling route.

[0130] For example, the first vehicle is a vehicle A, the non-game target is a vehicle C, and the vehicle C is parked at a left front position of the vehicle A. When the vehicle C blocks passing of the vehicle A, causing the vehicle A to encounter a passing difficulty, the vehicle A may attempt to slowly and carefully pass through a narrow passage between the vehicle C and a right boundary of a passable area of the vehicle A, or the vehicle A may attempt to bypass the vehicle C. For another example, the first vehicle is a vehicle A, the non-game target is a vehicle C, and the vehicle C is parked at a right front position of the vehicle A. When the vehicle C blocks passing of the vehicle A, causing the vehicle A to encounter a passing difficulty, the vehicle A may attempt to slowly and carefully pass through a narrow passage between the vehicle C and a left boundary of a passable area of the vehicle A, or the vehicle A may attempt to bypass the vehicle C.

[0131] For example, still refer to FIG. 5. After using a second target as the extrication target, the vehicle passing state detection and autonomous extrication unit in the first vehicle may send related information (for example, a name or an identifier of the second target) of the second target to the decision-making submodule in the decision-making and planning module. After receiving the related information of the second target (or may be referred to as the related information of the extrication target), the decision-making submodule may determine, based on road environment information and a traffic rule, a right-of-way relationship between the first vehicle and the second target, and comprehensively consider indicators such as safety, passability, and comfort, to determine an action (that is, a decision-making result) to be performed on the second target, and may send the decision-making result of the second target to a planning submodule included in the decision-making and planning module. After receiving the decision-making result of the second target, the planning submodule may perform extrication planning for the second target based on the decision-making result of the second target (or based on the decision-making result of the second target and the boundary of the passable area of the first vehicle), to obtain an extrication planning solution (for example, a solution of how to pass through the narrow passage or a solution of how to bypass the second target), and may send the extrication planning solution to a control module. After receiving the extrication planning solution, the control module may determine, based on the extrication planning solution and traveling state information of the first vehicle, a control variable used to control the first vehicle to implement the extrication planning solution (for example, passing through the narrow passage or bypassing the second target), and may send the control variable to the actuator.

[0132] Manner 3: When the first vehicle determines at least one first target (for example, at least one vehicle meeting target used as the extrication candidate target) and at least one second target (for example, at least one non-game target used as the extrication candidate target), the first vehicle may arbitrate one target (for example, a first target or a second target) from the at least one first target and the at least one second target as the extrication target, and may perform extrication planning for the target based on a decision-making result of the target, to attempt to initiate autonomous extrication.

[0133] In this embodiment of this application, the first vehicle may obtain an extrication priority of the at least one first target and an extrication priority of the at least one second target, and may determine, from the at least one first target and the at least one second target based on the extrication priority of the at least one first target and the extrication priority of the at least one second target, a target with the highest extrication priority as the extrication target.

[0134] For example, the first vehicle is a vehicle A, the first target is an oncoming vehicle (for example, a vehicle B), and the second target is a traffic post in a parking garage. The vehicle A determines, by comprehensively considering a traffic condition of a road area in which the vehicle A is located, a type of the vehicle B, a type of the traffic post, a right-of-way relationship between the first vehicle and the vehicle B and a right-of-way relationship between the first vehicle and the traffic post, and indicators such as safety, passability, comfort, and attention, that an extrication priority of the vehicle B is higher than an extrication priority of the traffic post. Then, the vehicle A may arbitrate the vehicle B as the extrication target (which may be understood as using the vehicle B as the extrication target). Optionally, for the vehicle B as the extrication target, the vehicle A may adopt the following extrication planning: The vehicle A selects reverse to enable the vehicle B to pass normally, thereby implementing autonomous extrication of the vehicle A.

[0135] Optionally, the first vehicle may alternatively perform extrication planning for the first target based on the decision-making result of the target and a boundary of the passable area of the first vehicle. In this way, a boundary restriction status of the road area (or a surrounding area of the first vehicle) in which the first vehicle is located can be fully considered by introducing the boundary of the passable area of the first vehicle, so that the first vehicle can more accurately determine whether a parking position (or may be referred to as a parking area) required for autonomous extrication of the first vehicle exists in the road area in which the first vehicle is located, thereby making extrication planning for the target by the first vehicle more accurate and targeted.

[0136] For example, the target is a first target. For related descriptions of performing extrication planning for the first target in Manner 3, refer to the related descriptions of Manner 1. Details are not described herein again. For another example, the target is a second target. For related descriptions of performing extrication planning for the second target in Manner 3, refer to the related descriptions of Manner 2. Details are not described herein again.

[0137] Step 302: In response to a first operation of the user on the parking interface, the terminal device obtains first parking information of the first vehicle, and sends the first parking information to the first vehicle. Correspondingly, the first vehicle receives the first parking information from the terminal device.

[0138] The first operation may be an operation of dragging a virtual parking space (or may be referred to as a virtual parking space border) on the parking interface by the user of the first vehicle. The first parking information may indicate a first parking pose required for extrication of the first vehicle.

[0139] In an example, after receiving the first request from the first vehicle, the terminal device may display prompt information on a parking interface presented by a target application (for example, a vehicle-mounted application installed on the first vehicle or a vehicle APP installed on a smartphone). The prompt information is used to prompt the user to confirm whether to remotely assist the first vehicle with extrication. In response to the confirmation operation of the user, the terminal device may generate an ambient environment view (for example, a 360° aerial view) of the first vehicle based on the traveling state information of the first vehicle and the ambient environment information of the first vehicle that are collected by a vehicle-mounted device (for example, the sensor system) of the first vehicle, and may present the ambient environment view of the first vehicle on the parking interface. The ambient environment view of the first vehicle may include a virtual parking space. For example, the ambient environment view of the first vehicle may enable the user to view the ambient environment information of the first vehicle in real time to effectively determine a traffic condition.

[0140] In another example, after receiving the first request from the first vehicle, the terminal device may generate an ambient environment view (for example, a 360° aerial view) of the first vehicle based on the traveling state information of the first vehicle and the ambient environment information of the first vehicle that are collected by a vehicle-mounted device (for example, the sensor system) of the first vehicle, and may present the ambient environment view of the first vehicle on the parking interface, so that the user can effectively determine a traffic condition by viewing the ambient environment information of the first vehicle in real time. The ambient environment view of the first vehicle may include a virtual parking space.

[0141] As shown in FIG. 7, the user may specify a target pose (for example, a first parking pose) of the first vehicle by dragging a customized virtual parking space in the ambient environment view (for example, a 360° aerial view) of the first vehicle, to specify a parking position of the first vehicle, thereby helping control the first vehicle to park to the specified position in a timely and effective manner, and facilitating extrication of the first vehicle. In this way, compared with the conventional technology, the method can achieve cost reduction, network dependence reduction, ease of operation, and strong flexibility. For example, the user may specify the target pose (for example, the first parking pose) of the first vehicle by dragging the virtual parking space in the 360° aerial view. For example, the target pose (for example, the first parking pose) of the first vehicle may include a parking position (or may be understood as parking position coordinates) and a parking posture (or may be referred to as a parking pose, for example, an attitude angle (for example, a pitch angle or a roll angle) during parking) of the first vehicle. In response to the operation of dragging the virtual parking space in the 360° aerial view by the user, the terminal device may obtain the first parking pose of the first vehicle, and may send the first parking pose of the first vehicle to the first vehicle. In this way, the user only needs to perform a simple drag and tap-to-select operation by using the target application on the terminal device, and does not need to directly and accurately operate the throttle, brake control system, steering control system, or gear control system on the bottom layer of the vehicle. Therefore, a use threshold is low and user-friendliness is high. In addition, in the method, the user does not need to perform a real-time operation on the target application. Because a great part of the extrication operation of the first vehicle is autonomously completed by the first vehicle, dependency on a high-bandwidth and low-latency network can be reduced, and availability and robustness of the system can be improved. In addition, in the method, the target pose of the first vehicle is specified by dragging the customized virtual parking space by the user, so that the user can dynamically formulate a corresponding extrication solution based on an actual situation (that is, the user continues to drag the virtual parking space to specify a new target pose to form a new extrication manner (or may be referred to as a new extrication solution) of the first vehicle, and for example, the user may continuously drag the virtual parking space on the parking interface multiple times to respectively correspond to new target poses). In this way, the system is highly flexible, and can better adapt to different scenarios and requirements.

[0142] FIG. 8 is a diagram of remotely assisting a vehicle with extrication by a user according to an embodiment of this application. As shown in FIG. 8, an automated driving system (Automated Driving System, ADS) corresponding to the first vehicle may send a request for remote assistance with extrication to a client (for example, a vehicle-mounted application installed on the first vehicle or a vehicle APP installed on a smartphone) on the terminal device. The request for remote assistance with extrication is for requesting the user to remotely assist the first vehicle with extrication. After receiving the request for remote assistance with extrication, the client may present an ambient environment view of the first vehicle on a parking interface. Optionally, for a manner of generating the ambient environment view of the first vehicle, refer to the foregoing related descriptions. Details are not described herein again. The user may specify a target pose of the first vehicle by dragging a customized virtual parking space in the ambient environment view of the first vehicle (which may be understood as that the user drags the virtual parking space on the parking interface to specify the target pose of the first vehicle). In response to the operation of dragging the virtual parking space by the user, the terminal device may obtain the target pose (for example, the first parking pose) of the first vehicle, and may send the target pose of the first vehicle to the ADS.

[0143] Step 303: The first vehicle parks based on the first parking information, and sends a second request to the terminal device. Correspondingly, the terminal device receives the second request from the first vehicle.

[0144] The second request may be for requesting to confirm whether extrication of the first vehicle succeeds.

[0145] In this embodiment of this application, after receiving the first parking information of the first vehicle, the first vehicle may park based on the first parking information, and switch to a standby (standby) state (which may be understood as waiting for an instruction, for example, waiting for a next instruction of the user) after parking is completed. Then, the first vehicle may send the second request to the terminal device.

[0146] Still refer to FIG. 8. After receiving the target pose of the first vehicle, the ADS invokes a parking capability (for example, a capability of driving the first vehicle to park by the throttle, brake control system, steering control system, or gear control system in the first vehicle) of the first vehicle based on the target pose of the first vehicle, to implement parking of the first vehicle. After the first vehicle completes parking, the ADS switches to the standby state, and sends the second request to the client.

[0147] Step 304: In response to a second operation of the user on the parking interface, the terminal device obtains a first instruction, and sends the first instruction to the first vehicle. Correspondingly, the first vehicle receives the first instruction from the terminal device.

[0148] The second operation may be an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance. The first instruction may instruct the first vehicle to resume a parking operation (or may be understood as resuming a cruise operation).

[0149] In a possible implementation, after receiving the second request, the terminal device may display the second request to the user on the parking interface in a manner of a pop-up window, prompt information (or a prompt message), or a notification message, to prompt the user to perform a corresponding operation. If the user determines that extrication of the first vehicle succeeds, the user may edit, on the parking interface, the first instruction for resuming parking (or resuming cruise) of the first vehicle, and submit the first instruction. In response to the second operation (for example, an operation of editing and submitting the first instruction) of the user on the parking interface, the terminal device may obtain the first instruction, and may send the first instruction to the first vehicle.

[0150] For example, still refer to FIG. 8. After receiving the second request, the client may display the second request to the user on the parking interface in a manner of a pop-up window, prompt information (or a prompt message), or a notification message, to prompt the user to perform a corresponding operation. If the user determines that extrication of the first vehicle succeeds, the user may deliver a parking resumption instruction or a cruise resumption instruction (for example, the first instruction) to the first vehicle on the parking interface, so that the first vehicle may continue proceeding to the target parking space based on the parking route and the parking resumption instruction or the cruise resumption instruction. If the user determines that extrication of the first vehicle has not been successful and continued extrication is needed, the user may continue to drag the virtual parking space on the parking interface to specify a new target pose (for example, a second parking pose) of the first vehicle, and may deliver the second parking pose of the first vehicle to the first vehicle, so that the first vehicle can invoke a parking capability based on the second parking pose to implement parking of the first vehicle.

[0151] Optionally, if the user determines that extrication of the first vehicle has not been successful and continued extrication is needed, the user may trigger a third operation on the parking interface. The third operation may be an operation of continuing to drag the virtual parking space on the parking interface by the user. In response to the third operation of the user on the parking interface, the terminal device may obtain second parking information of the first vehicle, and may send the second parking information of the first vehicle to the first vehicle. The second parking information may indicate a second parking pose required for continued extrication of the first vehicle. For example, the second parking pose of the first vehicle may include a parking position and a parking posture (for example, an attitude angle (for example, a pitch angle or a roll angle) during parking) of the first vehicle. After receiving the second parking information, the first vehicle may park based on the second parking information, and may send a third request to the terminal device. The third request is for requesting to confirm whether extrication of the first vehicle succeeds (which may be understood as requesting to continue to confirm whether extrication of the first vehicle succeeds). After receiving the third request, the terminal device may display the third request to the user on the parking interface in a manner of a pop-up window, prompt information (or a prompt message), or a notification message, to prompt the user to perform a corresponding operation. If the user determines that extrication of the first vehicle succeeds, the user may edit, on the parking interface, a second instruction for resuming parking (or resuming cruise) of the first vehicle, and submit the second instruction. In response to the fourth operation (for example, an operation of editing and submitting the second instruction) of the user on the parking interface, the terminal device may obtain the second instruction, and may send the second instruction to the first vehicle. The fourth operation may be an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance. The second instruction may instruct the first vehicle to resume a parking operation (or may be understood as resuming a cruise operation). After receiving the second instruction, the first vehicle may travel, according to the second instruction, from a parking position corresponding to the second parking information to the parking route to continue proceeding to the target parking space. In this way, in the method, the user can continue to specify a new target pose by dragging the virtual parking space on the parking interface, and further, the user can dynamically adjust, based on an actual situation of the first vehicle (for example, an actual situation of extrication or whether a parking position at which the first vehicle performs extrication affects another vehicle or pedestrian), the parking pose required for extrication of the first vehicle. This can make an extrication manner of the first vehicle more flexible, thereby making extrication of the first vehicle as successful as possible and helping improve a success rate of vehicle extrication.

[0152] For example, if the user determines that extrication of the first vehicle has not been successful and continued extrication is needed, the user may continue to specify a new target pose (for example, a second parking pose) of the first vehicle by dragging a customized virtual parking space in the ambient environment view (for example, a 360° aerial view) of the first vehicle shown in FIG. 7, to specify a new parking position of the first vehicle, thereby helping control the first vehicle to park to the new specified position in a timely and effective manner, and helping continued extrication of the first vehicle. For example, the user may specify a new target pose (for example, the second parking pose) of the first vehicle by dragging the virtual parking space in the 360° aerial view. In response to the operation of dragging the virtual parking space in the 360° aerial view by the user, the terminal device may obtain the second parking pose of the first vehicle, and may send the second parking pose of the first vehicle to the first vehicle. After receiving the second parking pose, the first vehicle may park based on the second parking pose, and may send a third request to the terminal device. It may be understood that for related descriptions after the terminal device receives the third request, refer to the foregoing related descriptions after the terminal device receives the third request. Details are not described herein again.

[0153] In a possible implementation, after receiving the second request, the terminal device may display the second request to the user on the parking interface in a manner of a pop-up window, prompt information (or a prompt message), or a notification message, and wait for confirmation of the user. If the user determines that extrication of the first vehicle succeeds, the user may tap, on the parking interface, a button (for example, a button "Yes") indicating that extrication of the first vehicle succeeds. In response to the tap operation of the user, the terminal device may generate the first instruction, and may send the first instruction to the first vehicle. Optionally, if the user determines that extrication of the first vehicle succeeds, the user may alternatively edit, on the parking interface, the first instruction for resuming a parking operation (or resuming a cruise operation) of the first vehicle, and submit the first instruction. In response to the submission operation of the user, the terminal device may obtain the first instruction, and may send the first instruction to the first vehicle. Optionally, if the user determines that extrication of the first vehicle succeeds, the user may alternatively tap, on the parking interface, a button indicating that extrication of the first vehicle succeeds, and after tapping, edit, on the parking interface, the first instruction for resuming a parking operation (or resuming a cruise operation) of the first vehicle, and submit the first instruction. In response to the tap operation and the submission operation of the user, the terminal device may obtain the first instruction, and may send the first instruction to the first vehicle.

[0154] Optionally, if the user determines that extrication of the first vehicle has not been successful and continued extrication is needed, the user may tap, on the parking interface, a button (for example, a button "No") indicating that extrication of the first vehicle fails, and then continue to trigger the third operation on the parking interface. In response to the third operation of the user on the parking interface, the terminal device may obtain second parking information of the first vehicle, and may send the second parking information of the first vehicle to the first vehicle. After receiving the second parking information, the first vehicle may park based on the second parking information, and may send a third request to the terminal device. After receiving the third request, the terminal device may display the third request to the user on the parking interface in a manner of a pop-up window, prompt information (or a prompt message), or a notification message, to prompt the user to perform a corresponding operation. If the user determines that extrication of the first vehicle succeeds, the user may edit, on the parking interface, a second instruction for resuming parking (or resuming cruise) of the first vehicle, and submit the second instruction. In response to the fourth operation of the user on the parking interface, the terminal device may obtain the second instruction, and may send the second instruction to the first vehicle. After receiving the second instruction, the first vehicle may travel, according to the second instruction, from a parking position corresponding to the second parking information to the parking route to continue proceeding to the target parking space. In this way, in the method, the user can continue to specify a new target pose by dragging the virtual parking space on the parking interface, and further, the user can dynamically adjust, based on an actual situation of the first vehicle (for example, an actual situation of extrication or whether a parking position at which the first vehicle performs extrication affects another vehicle or pedestrian), the parking pose required for extrication of the first vehicle. This can make an extrication manner of the first vehicle more flexible, thereby making extrication of the first vehicle as successful as possible and helping improve a success rate of vehicle extrication.

[0155] In addition, it may be understood that, if the user determines that remote assistance cannot facilitate extrication of the first vehicle, the user may trigger a fifth operation on the parking interface. The fifth operation may be an operation triggered on the parking interface by the user due to failed extrication of the first vehicle with remote assistance (for example, the user edits, on the parking interface, the third instruction enabling the first vehicle to wait in place for onsite takeover by the user, and perform the operation for submission), and the third instruction may instruct the first vehicle to wait for onsite takeover by the user. In response to the fifth operation of the user on the parking interface, the terminal device may obtain the third instruction, and may send the third instruction to the first vehicle. After receiving the third instruction, the first vehicle may wait in place for onsite takeover by the user.

[0156] Step 305: The first vehicle travel, according to the first instruction, from a parking position corresponding to the first parking information to the parking route to continue proceeding to the target parking space.

[0157] In this embodiment of this application, after receiving the first instruction, the first vehicle may plan, based on the parking position included in the first parking pose indicated by the first parking information, a first traveling route connected to the parking route. Then, the first vehicle may travel to the parking route based on the first traveling route, and continue on the parking route to proceed to the target parking space. If the first vehicle does not subsequently encounter a passing difficulty on the parking route, the first vehicle starts to park when arriving near the target parking space based on the parking route, until the first vehicle parks into the target parking space. In this case, the automated valet parking task ends. If the first vehicle subsequently encounters a passing difficulty again on the parking route, the first vehicle may continue to attempt autonomous extrication. When the autonomous extrication attempt of the first vehicle fails, the first vehicle may continue to send the request for remote assistance with extrication to the terminal device. When the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue proceeding to the target parking space based on the parking route.

[0158] Optionally, after the first vehicle receives the second instruction, the first vehicle may alternatively plan, based on the parking position included in the second parking pose indicated by the second parking information, a second traveling route connected to the parking route. Then, the first vehicle may travel to the parking route based on the second traveling route, and continue on the parking route to proceed to the target parking space. If the first vehicle does not subsequently encounter a passing difficulty on the parking route, the first vehicle starts to park when arriving near the target parking space based on the parking route, until the first vehicle parks into the target parking space. In this case, the automated valet parking task ends. If the first vehicle subsequently encounters a passing difficulty again on the parking route, the first vehicle may continue to attempt autonomous extrication. When the autonomous extrication attempt of the first vehicle fails, the first vehicle may continue to send the request for remote assistance with extrication to the terminal device. When the autonomous extrication attempt of the first vehicle succeeds, the first vehicle may continue proceeding to the target parking space based on the parking route.

[0159] It can be learned from the foregoing step 301 to step 305 that, when the first vehicle encounters a passing difficulty in the parking route to the target parking space, because the vehicle has a specific autonomous extrication capability, the first vehicle may attempt autonomous extrication. In this way, remote intervention frequency of the user can be minimized, thereby helping ensure user experience. If the autonomous extrication attempt of the first vehicle fails, the first vehicle may send a remote assistance request (for example, the first request) to the terminal device, so that the user can remotely assist the first vehicle with extrication. After extrication of the first vehicle succeeds with remote assistance of the user, the first vehicle may continue proceeding to the target parking space based on the parking route and a corresponding instruction from the terminal device. In this way, the method can improve reliability and a success rate of automated valet parking by combining autonomous extrication of the vehicle and remote assistance of the user, and can maximally avoid affecting user experience and use willingness due to onsite intervention of the user, thereby helping address the passing difficulty encountered by the automated valet parking vehicle. In addition, the method does not need to depend on a cloud cockpit and security personnel, and therefore can reduce device and maintenance costs.

[0160] It should be noted that in descriptions of this application, "at least one" means one or more, and "a plurality of" means two or more. The term "and / or" describes an association relationship between associated objects, and represents that three relationships may exist. For example, A and / or B may represent the following cases: Only A exists, both A and B exist, and only B exists, where A and B may be singular or plural. The character " / " generally indicates an "or" relationship between the associated objects. At least one of the following items (pieces) or a similar expression thereof indicates any combination of these items, including a single item (piece) or any combination of a plurality of items (pieces). For example, "at least one of A, B, and C" includes A, B, C, AB, AC, BC, or ABC. In addition, unless otherwise specified, ordinal numbers such as "first", "second", and "third" in embodiments of this application are used to distinguish between a plurality of objects, and are not used to limit a sequence, a time sequence, priorities, or importance of the plurality of objects. In addition, the terms "include", "contain", "have", and variations thereof that appear in this application all mean "including but not limited to", unless otherwise specifically emphasized in another manner.

[0161] In addition, it should be noted that each step in the foregoing embodiments may be performed by a corresponding device, or may be performed by a component like a chip, a processor, or a chip system in the device. This is not limited in embodiments of this application. The foregoing embodiments are described only by using an example in which each step is performed by the corresponding device.

[0162] It should be noted that in the foregoing embodiments, a part of steps may be selected for implementation, or a sequence of steps in the figure may be adjusted for implementation. This is not limited in this application. It should be understood that performing a part of steps in the figure, adjusting a sequence of steps, or combining the two manners for specific implementation shall fall within the protection scope of this application.

[0163] It may be understood that, to implement functions in the foregoing embodiments, devices in the foregoing embodiments include corresponding hardware structures and / or software modules for performing the functions. A person skilled in the art should be easily aware that, in combination with the units and the method steps in the examples described in embodiments disclosed in this application, this application can be implemented by using hardware or a combination of hardware and computer software. Whether a function is performed by hardware or hardware driven by computer software depends on particular application scenarios and design constraints of the technical solutions.

[0164] It should be noted that the "step" in embodiments of this application is merely an example, is a representation method used to better understand embodiments, and does not constitute a substantive limitation on execution of the solutions in this application. For example, the "step" may also be understood as a "feature". In addition, the step does not constitute any limitation on an execution sequence of the solutions in this application, and a new technical solution formed through an operation, for example, step sequence change, step combination, or step splitting, performed on this basis without affecting implementation of the overall solutions also falls within the scope disclosed in this application.

[0165] The following is a diagram of a structure of a possible intelligent parking apparatus according to an embodiment of this application. These intelligent parking apparatuses may be configured to implement functions of the first vehicle or the terminal device in the foregoing method embodiments, and therefore can also achieve beneficial effects of the foregoing method embodiments For example, the intelligent parking apparatus may be the vehicle 100 shown in FIG. 1, or may be a functional element (for example, a processor or a chip) disposed in the vehicle 100. The functional element has a function of implementing the intelligent parking method performed by the first vehicle in the foregoing method embodiments. The intelligent parking apparatus may be a terminal device, or may be a functional element (for example, a processor or a chip) in the terminal device. The functional element has a function of implementing the intelligent parking method performed by the terminal device in the foregoing method embodiments.

[0166] As shown in FIG. 9, the intelligent parking apparatus 900 includes a transceiver module 901 (or may be referred to as a communication module, a transceiver unit, or a communication unit, configured to send and receive data) and a processing module 902 (or may be referred to as a processing unit). The intelligent parking apparatus 900 is configured to implement a function of the first vehicle or the terminal device in the method embodiment shown in FIG. 3.

[0167] Optionally, the transceiver module 901 may include a receiving module and / or a sending module. The receiving module may be configured to receive a signal (or information, or data, or the like) by the intelligent parking apparatus 900, and the sending module may be configured to send a signal (or information, or data, or the like) by the intelligent parking apparatus 900. The sending module may send a signal (or information, or data, or the like) under control of the processing module 902, and the receiving module may receive a signal (or information, or data, or the like) under control of the processing module 902.

[0168] When the intelligent parking apparatus 900 is configured to implement a function of the first vehicle in the method embodiment shown in FIG. 3, the transceiver module 901 is configured to: if the first vehicle encounters a passing difficulty in a parking route to a target parking space, send a first request to the terminal device when autonomous extrication of the first vehicle fails. The first request may be for requesting to assist the first vehicle with extrication. The transceiver module 901 is further configured to receive first parking information from the terminal device. The first parking information may indicate a first parking pose required for extrication of the first vehicle. The processing module 902 is configured to park based on the first parking information. The transceiver module 901 is further configured to send a second request to the terminal device. The second request may be for requesting to confirm whether extrication of the first vehicle succeeds. The transceiver module 901 is further configured to receive a first instruction from the terminal device. The first instruction may instruct the first vehicle to resume a parking operation. The processing module 902 is further configured to travel, according to the first instruction, from a parking position corresponding to the first parking information to the parking route to continue proceeding to the target parking space.

[0169] When the intelligent parking apparatus 900 is configured to implement a function of the terminal device in the method embodiment shown in FIG. 3, the transceiver module 901 is configured to receive the first request from the first vehicle. The first request may be for requesting to assist the first vehicle with extrication. The transceiver module 901 is further configured to: in response to a first operation of a user on the parking interface, obtain first parking information of the first vehicle, and send the first parking information to the first vehicle. The first operation may be an operation of dragging a virtual parking space on the parking interface by the user, and the first parking information may indicate a first parking pose required for extrication of the first vehicle. The transceiver module 901 is further configured to receive the second request from the first vehicle. The second request may be for requesting to confirm whether extrication of the first vehicle succeeds. The transceiver module 901 is further configured to: in response to a second operation of the user on the parking interface, obtain a first instruction, and sends the first instruction to the first vehicle. The second operation may be an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance. The first instruction may instruct the first vehicle to resume a parking operation. The processing module 902 is configured to perform a corresponding processing operation, for example, configured to process ambient environment information collected by a vehicle-mounted device (for example, a sensor system) of the first vehicle.

[0170] For more detailed descriptions of the transceiver module 901 and the processing module 902, refer to related descriptions in the method embodiment shown in FIG. 3. Details are not described herein again.

[0171] It should be understood that the transceiver module 901 in this embodiment of this application may be implemented by using a communication interface or a communication interface–related circuit component, and the processing module 902 may be implemented by using a processor or a processor-related circuit component.

[0172] It should be noted that division into the modules in embodiments of this application is an example, and is merely logical function division. In actual implementation, there may be another division manner. In addition, functional units in embodiments of this application may be integrated into one processing unit, or may exist alone physically, or two or more units may be integrated into one unit. The integrated unit may be implemented in a form of hardware, or may be implemented in a form of a software functional unit.

[0173] When the 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 computer-readable storage medium. Based on such an understanding, the technical solutions of this application essentially, or the part contributing to the conventional technology, or all or some of the technical solutions may be implemented in a form of a software product. The computer software product is stored in a storage medium and includes several instructions for instructing a computer device (which may be a personal computer or a server) or a processor (processor) to perform all or some of the steps of the methods described in embodiments of this application. The foregoing storage medium includes any medium that can store program code, such as a USB flash drive, a removable hard disk, a read-only memory (read-only memory, ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disc.

[0174] Based on a same concept, an embodiment of this application further provides a possible intelligent parking apparatus. The intelligent parking apparatus is configured to implement the technical solution of the first vehicle or the terminal device in the method embodiment shown in FIG. 3. Therefore, beneficial effects of the first vehicle or the terminal device in the method embodiment shown in FIG. 3 can also be implemented. Refer to FIG. 10. An intelligent parking apparatus 1000 includes a communication interface 1001 and a processor 1002. Optionally, the intelligent parking apparatus 1000 further includes a memory 1003. The communication interface 1001, the processor 1002, and the memory 1003 are connected to each other. When the intelligent parking apparatus 1000 is configured to implement the technical solution related to the first vehicle or the terminal device provided in the foregoing embodiments, the communication interface 1001 may be configured to implement a function of the transceiver module 901, and the processor 1002 is configured to implement a function of the processing module 902.

[0175] Optionally, the communication interface 1001, the processor 1002, and the memory 1003 are connected to each other through a bus 1004. The bus 1004 may be a peripheral component interconnect (peripheral component interconnect, PCI) bus, an extended industry standard architecture (extended industry standard architecture, EISA) bus, or the like. Buses may be classified into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is for representing the bus in FIG. 10, but this does not mean that there is only one bus or only one type of bus.

[0176] The communication interface 1001 is configured to receive and send data. For example, when the intelligent parking apparatus 1000 is the vehicle 100 shown in FIG. 1, the communication interface 1001 may communicate with another device (for example, a terminal device, another vehicle, or a vehicle server) outside the application scenario shown in FIG. 1. In an example, the communication interface may be a transceiver apparatus integrated with a data receiving and sending function. In another example, the communication interface may alternatively include a transmitter and a receiver. The transmitter is configured to send data, and the receiver is configured to receive data.

[0177] Optionally, the communication interface 1001 may include a transmitter and / or a receiver. The transmitter is configured to send a signal, a message, information, data, or the like. The receiver is configured to receive a signal, a message, information, data, or the like. For example, the transmitter sends a signal, a message, information, data, or the like under control of the processor 1002. The receiver receives a signal, a message, information, data, or the like under control of the processor 1002.

[0178] For a function of the processor 1002, refer to descriptions of corresponding functions of the first vehicle or the terminal device in the foregoing embodiments. Details are not described herein again. The processor 1002 may be a central processing unit (central processing unit, CPU), a network processor (network processor, NP), a combination of a CPU and an NP, or the like. The processor 1002 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD), or a combination thereof. The PLD may be a complex programmable logic device (complex programmable logic device, CPLD), a field programmable logic gate array (field programmable gate array, FPGA), a generic array logic (generic array logic, GAL), or any combination thereof. The processor 1002 may implement the foregoing functions by using hardware or certainly by using hardware executing corresponding software.

[0179] The memory 1003 is configured to store program instructions and the like. Specifically, the program instructions may include program code. The program code includes computer operation instructions. The memory 1003 may include a random access memory (random access memory, RAM), or may be a non-volatile memory (non-volatile memory), for example, at least one magnetic disk memory. The processor 1002 executes the program instructions stored in the memory 1003, to implement the foregoing functions, thereby implementing the method steps that need to be performed by the first vehicle or the terminal device in the foregoing embodiments.

[0180] Based on a same concept, an embodiment of this application further provides a vehicle. The vehicle includes an image capture system, a chassis sensing device, and an intelligent parking apparatus. The image capture system is configured to obtain ambient environment information of the vehicle, the chassis sensing device is configured to obtain traveling state information of the vehicle, and the intelligent parking apparatus is configured to implement the technical solutions related to the first vehicle in the foregoing method embodiments.

[0181] Based on a same concept, an embodiment of this application further provides a terminal device. The terminal device includes an intelligent parking apparatus. The intelligent parking apparatus is configured to implement the technical solutions related to the terminal device in the foregoing method embodiments.

[0182] Based on a same concept, an embodiment of this application further provides a computer program product. The computer program product includes a computer program or instructions. When the computer program or the instructions are run on a computer, the computer is enabled to perform the intelligent parking method provided in the foregoing embodiments.

[0183] Based on a same concept, an embodiment of this application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program or instructions. When the computer program or the instructions are executed by a computer, the computer is enabled to perform the intelligent parking method provided in the foregoing embodiments.

[0184] The storage medium may be any usable medium that can be accessed by the computer. The following provides an example but does not impose a limitation: The computer-readable medium may include a RAM, a ROM, an EEPROM, a CD-ROM, or another optical disc storage or disk storage medium, or another magnetic storage device, or any other medium that can carry or store expected program code in a form of an instruction or a data structure and can be accessed by a computer.

[0185] Based on a same concept, an embodiment of this application further provides a chip. The chip may include a processor, and may further include a memory (or the chip is coupled to a memory). The chip executes a program instruction in the memory, to perform the intelligent parking method provided in the foregoing embodiments. "Coupling" means that two components are directly or indirectly combined with each other. For example, coupling may mean an electrical connection between the two components.

[0186] Based on a same concept, an embodiment of this application further provides a chip system. The chip system includes a processor, configured to support a computer apparatus in implementing a function related to the first vehicle or the terminal device in the foregoing embodiments. In a possible implementation, the chip system further includes a memory. The memory is configured to store a program and data that are necessary for the computer apparatus. The chip system may include a chip, or may include a chip and another discrete component.

[0187] All or some of the methods in embodiments of this application may be implemented by using software, hardware, firmware, or any combination thereof. When software is used to implement the embodiments, all or some of the embodiments may be implemented in a form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on the computer, the procedure or functions according to embodiments of this application are all or partially generated. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable apparatuses. The computer instructions may be stored in a computer-readable storage medium or may be transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website, computer, server, or data center to another website, computer, server, or data center in a wired (for example, a coaxial cable, an optical fiber, or a digital subscriber line (digital subscriber line, DSL)) or wireless (for example, infrared, radio, or microwave) manner. The computer-readable storage medium may be any usable medium accessible by the computer, or a data storage device, for example, a server or a data center, integrating one or more usable media. The usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, a high-density digital video disc (digital video disc, DVD)), a semiconductor medium (for example, a solid-state drive (solid-state drive, SSD)), or the like.

[0188] The steps of the method described in embodiments of this application may be directly embedded into hardware, a software unit executed by a processor, or a combination thereof. The software unit may be stored in a RAM, a ROM, an EEPROM, a register, a hard disk drive, a removable magnetic disk, a CD-ROM, or a storage medium of any other form in the art. For example, the storage medium may connect to a processor, so that the processor may read information from the storage medium and write information to the storage medium. Optionally, the storage medium may alternatively be integrated into the processor. The processor and the storage medium may be disposed in an ASIC.

[0189] This application is described with reference to the flowcharts and / or block diagrams of the method, the device (system), and the computer program product according to this application. It should be understood that computer program instructions may be used to implement each process and / or each block in the flowcharts and / or the block diagrams and a combination of a process and / or a block in the flowcharts and / or the block diagrams. These computer program instructions may be provided for a general-purpose computer, a dedicated computer, an embedded processor, or a processor of any other programmable data processing device to generate a machine, so that the instructions executed by a computer or a processor of any other programmable data processing device generate an apparatus for implementing a specific function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.

[0190] These computer program instructions may also be loaded onto a computer or another programmable data processing device, so that a series of operations and steps are performed on the computer or the another programmable device, thereby generating computer-implemented processing. Therefore, the instructions executed on the computer or the another programmable device provide steps for implementing a specific function in one or more processes in the flowcharts and / or in one or more blocks in the block diagrams.

[0191] It is clearly that a person skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. In this case, this application is intended to cover these modifications and variations of this application provided that they fall within the scope of protection defined by the following claims and their equivalent technologies.

Claims

1. An intelligent parking method, applied to a first vehicle, wherein the method comprises:if the first vehicle encounters a passing difficulty in a parking route to a target parking space, sending a first request to a terminal device when autonomous extrication of the first vehicle fails, wherein the first request is for requesting to assist the first vehicle with extrication;receiving first parking information from the terminal device, wherein the first parking information indicates a first parking pose required for extrication of the first vehicle;parking based on the first parking information, and sending a second request to the terminal device, wherein the second request is for requesting to confirm whether extrication of the first vehicle succeeds;receiving a first instruction from the terminal device, wherein the first instruction instructs the first vehicle to resume a parking operation; andtraveling, according to the first instruction, from a parking position corresponding to the first parking information to the parking route to continue proceeding to the target parking space.

2. The method according to claim 1, wherein after sending the second request to the terminal device, the method further comprises:receiving second parking information from the terminal device, wherein the second parking information indicates a second parking pose required for continued extrication of the first vehicle;parking based on the second parking information, and sending a third request to the terminal device, wherein the third request is for requesting to confirm whether extrication of the first vehicle succeeds;receiving a second instruction from the terminal device, wherein the second instruction instructs the first vehicle to resume the parking operation; andtraveling, according to the second instruction, from a parking position corresponding to the second parking information to the parking route to continue proceeding to the target parking space.

3. The method according to claim 1 or 2, wherein the method further comprises:receiving a third instruction from the terminal device, wherein the third instruction instructs the first vehicle to wait for onsite takeover by a user.

4. The method according to claim 1 or 2, wherein it is determined, based on at least one of the following, that the first vehicle encounters a passing difficulty in a process of proceeding to the target parking space: the first vehicle blocks passing of a first target or a second target blocks passing of the first vehicle, wherein the first target is a target that is in a traveling area in which the first vehicle is located and that has a bidirectional interaction relationship with the first vehicle, and the second target is a target that is in the traveling area in which the first vehicle is located and that has a unidirectional interaction relationship with the first vehicle.

5. The method according to claim 4, wherein the method further comprises:obtaining sensing information corresponding to the first vehicle;determining a plurality of targets based on the sensing information, and determining decision-making results of the plurality of targets, wherein a decision-making result of each of the plurality of targets indicates an avoidance measure taken by the first vehicle on the target; andwhen the plurality of targets comprise the first target, performing extrication planning for the first target based on the decision-making result of the first target; or when the plurality of targets comprise the second target, performing extrication planning for the second target based on the decision-making result of the second target.

6. The method according to claim 5, wherein when the first vehicle blocks passing of the first target, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, performing extrication planning for the first target comprises:when there is an idle area around the first vehicle, attempting to park in the idle area, to leave passing space for the first target.

7. The method according to claim 5 or 6, wherein when the second target blocks passing of the first vehicle, causing the first vehicle to encounter a passing difficulty in the process of proceeding to the target parking space, performing extrication planning for the second target comprises:attempting to pass through a narrow passage between the second target and a boundary of a passable area of the first vehicle; orattempting to bypass the second target.

8. The method according to claim 1 or 2, wherein the first parking pose is determined based on traveling state information and ambient environment information collected by the first vehicle.

9. An intelligent parking method, applied to a terminal device, wherein the method comprises:receiving a first request from a first vehicle, wherein the first request is for requesting to assist the first vehicle with extrication;in response to a first operation of a user on a parking interface, obtaining first parking information of the first vehicle, and sending the first parking information to the first vehicle, wherein the first operation is an operation of dragging a virtual parking space on the parking interface by the user, and the first parking information indicates a first parking pose required for extrication of the first vehicle;receiving a second request from the first vehicle, wherein the second request is for requesting to confirm whether extrication of the first vehicle succeeds; andin response to a second operation of the user on the parking interface, obtaining a first instruction, and sending the first instruction to the first vehicle, wherein the second operation is an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance, and the first instruction instructs the first vehicle to resume a parking operation.

10. The method according to claim 9, wherein after receiving the second request from the first vehicle, the method further comprises:in response to a third operation of the user on the parking interface, obtaining second parking information of the first vehicle, and sending the second parking information to the first vehicle, wherein the third operation is an operation of continuing to drag the virtual parking space on the parking interface by the user, and the second parking information indicates a second parking pose required for continued extrication of the first vehicle;receiving a third request from the first vehicle, wherein the third request is for requesting to confirm whether extrication of the first vehicle succeeds; andin response to a fourth operation of the user on the parking interface, obtaining a second instruction, and sending the second instruction to the first vehicle, wherein the fourth operation is an operation triggered on the parking interface by the user due to successful extrication of the first vehicle with remote assistance, and the second instruction instructs the first vehicle to resume the parking operation.

11. The method according to claim 9 or 10, wherein the method further comprises:in response to a fifth operation of the user on the parking interface, obtaining a third instruction, and sending the third instruction to the first vehicle, wherein the fifth operation is an operation triggered on the parking interface by the user due to failed extrication of the first vehicle with remote assistance, and the third instruction instructs the first vehicle to wait for onsite takeover by the user.

12. The method according to claim 9 or 10, wherein the first parking pose is determined based on traveling state information and ambient environment information collected by the first vehicle.

13. An intelligent parking apparatus, comprising a communication interface, a processor, and a memory, whereinthe communication interface is configured to receive and send data;the memory is configured to store computer program instructions and data; andthe processor is configured to execute the computer program instructions and the data that are stored in the memory, to enable the intelligent parking apparatus to perform the method according to any one of claims 1 to 8 or the method according to any one of claims 9 to 12.

14. A vehicle, comprising an image capture system, a chassis sensing device, and an intelligent parking apparatus configured to perform the method according to any one of claims 1 to 8, whereinthe image capture system is configured to obtain ambient environment information of the vehicle, and the chassis sensing device is configured to obtain traveling state information of the vehicle.

15. A terminal device, comprising an intelligent parking apparatus configured to perform the method according to any one of claims 9 to 12.

16. A computer-readable storage medium, wherein the computer-readable storage medium stores a computer program or instructions, and when the computer program or the instructions are executed by a computer, the computer is enabled to perform the method according to any one of claims 1 to 8 or the method according to any one of claims 9 to 12.

17. A chip, wherein the chip comprises a processor, the processor is coupled to a memory, and the processor is configured to execute a computer program or instructions stored in the memory, to enable the chip to perform the method according to any one of claims 1 to 8 or the method according to any one of claims 9 to 12.

Images