Parking method and apparatus, and vehicle

Abstract

A parking method (400) is disclosed, including: obtaining a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space; planning a first path for the vehicle to travel from a current pose to the first temporary parking pose; and controlling, based on the first path, the vehicle to travel to the first temporary parking pose. A parking apparatus (900), a vehicle (100), a computer-readable storage medium, a computer program product, and a chip are also included. The parking method may be applied to an intelligent vehicle or an electric vehicle, to help improve an intelligence degree of the vehicle in an automatic parking process, and also help improve parking experience of a user.

Description

PARKING METHOD AND APPARATUS, AND VEHICLE

[0001] This application claims priority to Chinese Patent Application No. 202410268788.8, filed with the China National Intellectual Property Administration on March 8, 2024 and entitled "PARKING METHOD AND APPARATUS, AND VEHICLE", which is incorporated herein by reference in its entirety.TECHNICAL FIELD

[0002] This application relates to the field of intelligent driving, and more specifically, to a parking method and apparatus, and a vehicle.BACKGROUND

[0003] Automatic parking (auto parking, AP) means that a vehicle automatically parks into a parking space. To be specific, an automatic driving system can semi-automatically or fully automatically help a user park the vehicle in the parking space. The automatic parking may include automatic parking assist (auto parking assist, APA), remote parking assist (remote parking assist, RPA), automated valet parking (auto valet parking, AVP), and the like.

[0004] In a process in which the vehicle automatically parks into a target parking space, the vehicle may be in interaction deadlock with another vehicle, causing traffic congestion. In this case, a driver needs to take over the vehicle, and use an automatic parking function to park into the target parking space after the traffic congestion is relieved. Consequently, the vehicle has a low intelligence degree in the automatic parking process, and parking experience of a user is poor.SUMMARY

[0005] This application provides a parking method and apparatus, and a vehicle, to improve an intelligence degree of the vehicle in an automatic parking process, and improve parking experience of a user.

[0006] According to a first aspect, a parking method is provided. The method includes: obtaining a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space; planning a first path for the vehicle to travel from a current pose to the first temporary parking pose; and controlling, based on the first path, the vehicle to travel to the first temporary parking pose.

[0007] Based on the foregoing technical solution, when the vehicle is in the interaction deadlock state with the first obstacle, the vehicle may obtain a temporary parking pose, and plan a path from the current pose to the temporary parking pose. In this way, the vehicle is controlled to travel along the path to the temporary parking pose, so that traffic congestion can be relieved, and the interaction deadlock state can be released. In addition, a driver does not need to intervene in this process. This helps improve an intelligence degree of the vehicle in an automatic parking process, and helps improve parking experience of a user.

[0008] In some possible implementations, when the vehicle is in the first temporary parking pose, the interaction deadlock state between the vehicle and the first obstacle may be released.

[0009] In some possible implementations, the first obstacle is another vehicle. The method further includes: when a vehicle head of the another vehicle faces a vehicle head of the vehicle and the vehicle cannot start within preset duration, determining that the vehicle is in an interaction deadlock state with the another vehicle; or when a difference between a sum of a width of the vehicle and a width of the another vehicle and a width of a passage is less than or equal to a preset difference, determining that the vehicle is in an interaction deadlock state with the another vehicle. For example, the passage may be a passage through which the vehicle and the another vehicle pass.

[0010] In some possible implementations, obtaining the first temporary parking pose when the vehicle is in the interaction deadlock state with the first obstacle in the process of automatically parking into the target parking space includes: obtaining the first temporary parking pose when the vehicle and a moving obstacle cannot travel based on respective predetermined intents in the process in which the vehicle automatically parks into the target parking space.

[0011] In some possible implementations, when the vehicle is in the interaction deadlock state with the first obstacle in the process of parking into the target parking space through AVP, and the first temporary parking pose is a pose in the temporary parking space, the method further includes: sending a first instruction to a mobile terminal, where the first instruction is used to prompt the user whether to park the vehicle into the temporary parking space. In this way, when receiving the first instruction, the mobile terminal may prompt the user whether to park the vehicle into the temporary parking space.

[0012] In some possible implementations, the method further includes: receiving a second instruction of the mobile terminal, where the second instruction instructs to park the vehicle into the temporary parking space; and in response to receiving the second instruction, locking and powering off the vehicle after the vehicle parks into the temporary parking pose. In this way, traffic congestion can be quickly relieved, and the vehicle can quickly park into the parking space.

[0013] In some possible implementations, the method further includes: sending information about the temporary parking space to the mobile terminal.

[0014] In some possible implementations, the method further includes: if no second instruction sent by the mobile terminal is received within preset duration from sending the first instruction to the mobile terminal, or when a third instruction sent by the mobile terminal is received, and when the interaction deadlock state is released, continuing to control the vehicle to park into the target parking space, where the third instruction instructs to park the vehicle into the target parking space.

[0015] With reference to the first aspect, in some implementations of the first aspect, the method further includes: obtaining at least one of road structure information, the current pose of the vehicle, and information about a vacant parking space around the vehicle. Obtaining the first temporary parking pose includes: determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0016] Based on the foregoing technical solution, the first temporary parking pose may be determined based on at least one of the road structure information, the current pose, and the information about the vacant parking space around the vehicle. In this way, the temporary parking pose can be more proper, effectively relieving traffic congestion.

[0017] In some possible implementations, the road structure information may include at least one of information about a center line of a road structure and a width of a road.

[0018] In some possible implementations, the vacant parking space around the vehicle may also be referred to as an idle parking space. The vacant parking space may be an idle parking space that is identified by the vehicle and that is located around the vehicle when the vehicle is in the interaction deadlock state with the first obstacle.

[0019] In some possible implementations, the first temporary parking pose may include a pose not in a parking space (for example, a temporary parking pose for parking on a roadside or a temporary parking pose on a roadside) or a pose in a parking space (for example, a pose in the vacant parking space).

[0020] With reference to the first aspect, in some implementations of the first aspect, determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space includes: obtaining a first temporary parking pose set; when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjusting and screening at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, where a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; and determining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0021] Based on the foregoing technical solution, at least a part of temporary parking poses in the first temporary parking pose set may be first adjusted and screened based on the preset adjustment distance, and then the first temporary parking pose is determined, based on at least one of the road structure information, the current pose, and the information about the vacant parking space, from the second temporary parking pose set obtained through screening. In this way, the temporary parking pose is adjusted and screened based on the preset adjustment distance, so that the vehicle can select the first temporary parking pose from a small quantity of temporary parking poses that are far away from the obstacle. This helps improve efficiency of determining the temporary parking pose, and improve parking efficiency.

[0022] With reference to the first aspect, in some implementations of the first aspect, the first temporary parking pose is a pose not in a parking space. Determining the first temporary parking pose from the second temporary parking pose set includes: determining the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

[0023] In some possible implementations, an included angle between an orientation of the first temporary parking pose and the current pose of the vehicle is less than or equal to a preset included angle, and / or an included angle between an orientation of the first temporary parking pose and a tangent direction of a center line of a road structure closest to the first temporary parking pose is less than or equal to a second preset included angle.

[0024] With reference to the first aspect, in some implementations of the first aspect, the first temporary parking pose is a pose in the vacant parking space. Determining the first temporary parking pose from the second temporary parking pose set includes: determining the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

[0025] Based on the foregoing technical solution, when the first temporary parking pose is a pose in the vacant parking space (or the temporary parking space), a projection of the first temporary parking pose on the ground may be allowed to exceed a parking space line of the vacant parking space by a specific length. In this way, a selection range of the temporary parking pose may be further expanded, and parking efficiency of the vehicle when the vehicle parks into the vacant parking space may also be improved, thereby helping relieve traffic congestion as soon as possible, and helping improve parking experience of the user.

[0026] With reference to the first aspect, in some implementations of the first aspect, determining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space includes: screening the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, where the third temporary parking pose set includes a plurality of temporary parking poses; and determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders the another vehicle from passing through, and a first included angle, where the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

[0027] Based on the foregoing technical solution, the first temporary parking pose may be determined from the plurality of temporary parking poses by considering the cost of each temporary parking pose, the probability that each temporary parking pose hinders the another vehicle from passing through, and the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose. In this way, the cost for the vehicle to reach the first temporary parking pose may be relatively small, the probability that the first temporary parking pose hinders the another vehicle from passing through is relatively low, and the first temporary parking pose better meets an intent of the ego vehicle. This helps further improve parking efficiency, and helps improve parking experience of the user.

[0028] In some possible implementations, the cost of each temporary parking pose includes one or more of a distance cost between the temporary parking pose and the vehicle, an included angle cost between the orientation of the temporary parking pose and the orientation of the current pose of the vehicle, or a gear shifting cost for the vehicle to move from the current pose to the temporary parking pose.

[0029] In some possible implementations, the probability that the temporary parking pose hinders the another vehicle from passing through includes at least one of whether an intended path of the another vehicle intersects (or partially overlaps) the temporary parking pose and a remaining passage width after the vehicle reaches the temporary parking pose.

[0030] With reference to the first aspect, in some implementations of the first aspect, the process of automatically parking the vehicle into the target parking space includes a parking phase. Determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, and the first included angle includes: when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

[0031] Based on the foregoing technical solution, in the parking phase, a distance cost between the temporary parking pose and the target parking space may be further considered. This can avoid a case in which the temporary parking pose is excessively far away from the target parking space, to help improve parking efficiency in the parking phase, so as to help improve parking experience of the user.

[0032] With reference to the first aspect, in some implementations of the first aspect, before controlling, based on the first path, the vehicle to travel to the first temporary parking pose, the method further includes: determining that a quantity of gear shifts when the vehicle travels along the first path meets a preset condition and / or a probability that the vehicle occupies an intended path of the another vehicle when traveling along the first path meets a preset condition.

[0033] Based on the foregoing technical solution, the quantity of gear shifts and the probability of occupying the intended path of the another vehicle are considered, so that it can be ensured that the vehicle travels to the first temporary parking pose more quickly while traffic congestion is relieved.

[0034] With reference to the first aspect, in some implementations of the first aspect, determining the first temporary parking pose from the plurality of temporary parking poses includes: determining the first temporary parking pose from the plurality of temporary parking poses through a first thread, and determining the first path from one or more paths through the first thread. Planning the first path for the vehicle to travel from the current pose to the first temporary parking pose includes: planning the one or more paths through a second thread.

[0035] Based on the foregoing technical solution, the first thread may be used to perform screening of the temporary parking pose and screening the path, and the second thread may be used to perform a path planning process. In this way, the first thread and the second thread cooperate with each other, so that screening of the temporary parking pose and the path and path planning can be performed in parallel. This helps improve efficiency of obtaining a path by the vehicle through planning, and helps improve efficiency of relieving traffic congestion.

[0036] With reference to the first aspect, in some implementations of the first aspect, the method further includes: when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, stopping traveling along the first path and obtaining a second temporary parking pose; planning a second path for the vehicle to travel from the current pose to the second temporary parking pose; and controlling, based on the second path, the vehicle to travel to the second temporary parking pose.

[0037] Based on the foregoing technical solution, when the vehicle is in the interaction deadlock state with the second obstacle in the process of traveling to the first temporary parking pose, the vehicle may stop traveling along the first path, re-obtain the second temporary parking pose, and re-plan the second path for traveling to the second temporary parking pose. In this way, controlling the vehicle to travel to the second temporary parking pose along the second path helps release the interaction deadlock state with the first obstacle and the interaction deadlock state with the second obstacle. In addition, in this process, a driver does not need to intervene. This helps improve an intelligence degree of the vehicle in an automatic parking process, and helps improve parking experience of the user.

[0038] With reference to the first aspect, in some implementations of the first aspect, the method further includes: before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, controlling the vehicle to stop traveling along the first path and continue to automatically park into the target parking space.

[0039] Based on the foregoing technical solution, before the vehicle travels along the first path to the first temporary parking pose, if it is detected that the interaction state is released, the vehicle may stop traveling along the first path and switch to continue to automatically park into the target parking space. In this way, parking efficiency is improved, thereby improving parking experience of the user.

[0040] According to a second aspect, a parking apparatus is provided. The apparatus includes: an obtaining unit, configured to obtain a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space; a path planning unit, configured to plan a first path for the vehicle to travel from a current pose to the first temporary parking pose; and a control unit, configured to control, based on the first path, the vehicle to travel to the first temporary parking pose.

[0041] With reference to the second aspect, in some implementations of the second aspect, the obtaining unit is specifically configured to: obtain at least one of road structure information, the current pose of the vehicle, and information about a vacant parking space around the vehicle; and determine the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0042] With reference to the second aspect, in some implementations of the second aspect, the obtaining unit is specifically configured to: obtain a first temporary parking pose set; when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjust and screen at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, where a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; and determine the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0043] With reference to the second aspect, in some implementations of the second aspect, the first temporary parking pose is a pose not in the parking space, and the obtaining unit is specifically configured to determine the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

[0044] With reference to the second aspect, in some implementations of the second aspect, the first temporary parking pose is a pose in the vacant parking space, and the obtaining unit is specifically configured to determine the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

[0045] With reference to the second aspect, in some implementations of the second aspect, the obtaining unit is specifically configured to: screen the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, where the third temporary parking pose set includes a plurality of temporary parking poses; and determine the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders the another vehicle from passing through, and a first included angle, where the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

[0046] With reference to the second aspect, in some implementations of the second aspect, the process in which the vehicle automatically parks into the target parking space includes a parking phase. The obtaining unit is specifically configured to: when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determine the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

[0047] With reference to the second aspect, in some implementations of the second aspect, the apparatus further includes a determining unit, and the determining unit is configured to: before the control unit controls the vehicle to travel to the first temporary parking pose, determine that a quantity of gear shifts when the vehicle travels along the first path meets a preset condition and / or a probability that the vehicle occupies an intended path of the another vehicle when traveling along the first path meets a preset condition.

[0048] With reference to the second aspect, in some implementations of the second aspect, the obtaining unit is specifically configured to determine the first temporary parking pose from the plurality of temporary parking poses through a first thread. The determining unit is specifically configured to determine the first path from the one or more paths through the first thread. The path planning unit is specifically configured to plan the one or more paths through a second thread.

[0049] With reference to the second aspect, in some implementations of the second aspect, the control unit is further configured to: when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, control the vehicle to stop traveling along the first path. The obtaining unit is further configured to obtain a second temporary parking pose. The path planning unit is further configured to plan a second path for the vehicle to travel from the current pose to the second temporary parking pose. The control unit is further configured to control, based on the second path, the vehicle to travel to the second temporary parking pose.

[0050] With reference to the second aspect, in some implementations of the second aspect, the control unit is further configured to: before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, control the vehicle to stop traveling along the first path and continue to automatically park into the target parking space.

[0051] According to a third aspect, this application provides a parking apparatus. This apparatus includes a processor and a memory. The memory is configured to store instructions, and the processor executes the instructions stored in the memory, so that the apparatus performs any possible method according to the first aspect.

[0052] According to a fourth aspect, this application provides a vehicle. The vehicle includes any possible apparatus according to the second aspect or the third aspect.

[0053] According to a fifth aspect, this application provides a computer program product. The computer program product includes computer program code. When the computer program code is run on a computer, the computer is enabled to perform any possible method according to the first aspect.

[0054] It should be noted that all or a part of the computer program code may be stored in a first storage medium. The first storage medium may be packaged together with a processor, or may be packaged separately from a processor. This is not specifically limited in this embodiment of this application.

[0055] According to a sixth aspect, this application provides a computer-readable storage medium. The computer-readable storage medium stores program code. When the computer program code is run on a computer, the computer is enabled to perform any possible method according to the first aspect.

[0056] According to a seventh aspect, this application provides a chip system. The chip system includes a processor configured to invoke a computer program or computer instructions stored in a memory, so that the processor performs any possible method according to the first aspect.

[0057] With reference to the seventh aspect, in a possible implementation, the processor is coupled to the memory through an interface.

[0058] With reference to the seventh aspect, in a possible implementation, the chip system further includes the memory. The memory stores the computer program or the computer instructions.

[0059] According to an eighth aspect, this application provides a chip. The chip system includes a circuit. The circuit is configured to perform any possible method according to the first aspect.BRIEF DESCRIPTION OF DRAWINGS

[0060] FIG. 1 is a functional block diagram of a vehicle according to an embodiment of this application;

[0061] FIG. 2 is a diagram of a system architecture according to an embodiment of this application;

[0062] FIG. 3 is a diagram of a parking scenario according to an embodiment of this application;

[0063] FIG. 4 is a schematic flowchart of a parking method according to an embodiment of this application;

[0064] FIG. 5 is a schematic flowchart of a temporary parking pose generation method according to an embodiment of this application;

[0065] FIG. 6 to FIG. 14 are diagrams of temporary parking poses in several parking scenarios according to an embodiment of this application;

[0066] FIG. 15A and FIG. 15B are a schematic flowchart of a temporary parking and real-time scoring method that is based on an asynchronous architecture according to an embodiment of this application;

[0067] FIG. 16 to FIG. 19 are other diagrams of a parking scenario according to an embodiment of this application; and

[0068] FIG. 20 is a schematic flowchart of a parking apparatus according to an embodiment of this application.DESCRIPTION OF EMBODIMENTS

[0069] The following describes the technical solutions in embodiments of this application with reference to the accompanying drawings in embodiments of this application. In description in embodiments of this application, " / " means "or" unless otherwise specified. For example, A / B may represent A or B. In this specification, "and / or" describes only an association relationship for describing associated objects and represents that three relationships may exist. For example, A and / or B may represent the following three cases: Only A exists, both A and B exist, and only B exists. "At least one item" means one or more items. For example, "at least one of A and B ", similar to "A and / or B", describes an association relationship between associated objects and indicates that three relationships may exist. For example, at least one of A and B may indicate the following three cases: Only A exists, both A and B exist, and only B exists.

[0070] Prefix words "first", "second", and the like in embodiments of this application are merely intended to distinguish between different objects, and impose no limitation on positions, sequences, priorities, quantities, content, or the like of the described objects. Use of prefixes such as ordinal numbers used to distinguish the described objects in embodiments of this application does not constitute a limitation on the described objects. For descriptions of the described objects, refer to the context description in claims or embodiments, and the use of such prefix words should not constitute a redundant limitation. In addition, in the descriptions of embodiments, unless otherwise specified, "a plurality of" means two or more.

[0071] FIG. 1 is a functional block diagram of a vehicle 100 according to an embodiment of this application. The vehicle 100 may include a sensing system 110, a compute platform 120, and a display apparatus 130. The sensing system 110 may include one or more sensors for sensing information about an environment around the vehicle 100. For example, the sensing system 110 may include a positioning system. The positioning system may be a global positioning system (global positioning system, GPS), a BeiDou system, or another positioning system. For another example, the sensing system 110 may include one or more of an inertial measurement unit (inertial measurement unit, IMU), an acceleration sensor, a lidar, a millimeter-wave radar, an ultrasonic radar, and an image shooting apparatus. For example, the acceleration sensor may include a sensor for detecting an acceleration signal of an air suspension system, or may include a sensor for an acceleration signal of ESC.

[0072] A part of or all functions of the vehicle 100 may be controlled by the compute platform 120. The compute platform 120 may include one or more processors, for example, processors 121 to 12n (where n is a positive integer). The processor is a circuit having a signal processing capability. In an implementation, the processor may be a circuit having an instruction reading and running capability, for example, a central processing unit (central processing unit, CPU), a microprocessor, a graphics processing unit (graphics processing unit, GPU) (which may be understood as a microprocessor), or a digital signal processor (digital signal processor, DSP). In another implementation, the processor may implement a specific function based on a logical relationship of a hardware circuit. The logical relationship of the hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an application-specific integrated circuit (application-specific integrated circuit, ASIC) or a programmable logic device (programmable logic device, PLD), for example, a field programmable gate array (field programmable gate array, FPGA). In the reconfigurable hardware circuit, a process in which the processor loads a configuration document to implement hardware circuit configuration may be understood as a process in which the processor loads an instruction to implement functions of some or all of the foregoing units. In addition, the processor may alternatively be a hardware circuit designed for artificial intelligence, and may be understood as an ASIC, for example, a neural network processing unit (neural network processing unit, NPU), a tensor processing unit (tensor processing unit, TPU), or a deep learning processing unit (deep learning processing unit, DPU). Moreover, the compute platform 120 may further include a memory. The memory is configured to store instructions, and a part or all of the processors 121 to 12n may invoke the instructions in the memory, to implement a corresponding function.

[0073] The display apparatus 130 in a cabin is mainly classified into two types: a first type is a vehicle-mounted display, and a second type is a projection display, for example, a head-up display (head-up display, HUD) apparatus. The in-vehicle display is a physical display, and is an important part of an in-vehicle infotainment system. A plurality of displays may be disposed in the cabin, for example, a digital dashboard display, a central display screen, a display in front of a passenger in a front passenger seat (also referred to as a front-row passenger), a display in front of a rear-seat passenger on the left, and a display in front of a rear-seat passenger on the right. Even a window may be used as a display for display. Head-up display, also referred to as a head-up display system. The head-up display is mainly configured to display driving information such as a speed and navigation on a display device (for example, a windshield) in front of a driver, to reduce line-of-sight transfer time of the driver, avoid a pupil change caused by a line-of-sight transfer of the driver, and improve driving safety and comfort. For example, the HUD includes a combiner head-up display (combiner-HUD, C-HUD) system, a windshield head-up display (windshield-HUD, W-HUD) system, and an augmented reality head-up display (augmented reality HUD, AR-HUD) system. It should be understood that the HUD may also have another type of system with technology evolution. This is not limited in this application.

[0074] The foregoing display apparatus 130 is described by using the vehicle-mounted display and the projection display as examples. This embodiment of this application is not limited thereto. For example, the display apparatus 130 may alternatively be a light display or a projection screen.

[0075] The vehicle 100 may include an advanced driving assistant system (advanced driving assistant system, ADAS). The ADAS obtains information around the vehicle using a plurality of types of sensors (including but not limited to the lidar, the millimeter-wave radar, the image shooting apparatus, the ultrasonic sensor, the global positioning system, and the inertial measurement unit) in the vehicle, and analyzes and processes the obtained information, to implement functions such as obstacle sensing, target recognition, vehicle positioning, path planning, and driver monitoring / reminder. This improves traveling safety, automation, and comfort of the vehicle. At different autonomous driving levels (L0 to L5), the ADAS may implement different levels of autonomous driving assistance based on information obtained by utilizing an artificial intelligence algorithm and a plurality of sensors. The foregoing autonomous driving levels (L0 to L5) are based on a grading standard of the society of automotive engineers (society of automotive engineers, SAE). The level L0 indicates no automation, a level L1 indicates driving assistance, a level L2 indicates partial automation, a level L3 indicates conditional automation, a level L4 indicates high automation, and the level L5 indicates full automation. Tasks of monitoring and responding to road conditions at the L1 to L3 levels are jointly completed by a driver and a system, and the driver needs to take over a dynamic driving task. The L4 and L5 levels may enable the driver to be completely transformed into a passenger. For example, automatic parking may include APA, RPA, AVP, and the like. For the APA, the driver does not need to control a steering wheel, but still needs to control a throttle and a brake in a vehicle. For the RPA, the driver may remotely park the vehicle outside the vehicle by utilizing a terminal (for example, a mobile phone). For the AVP, the vehicle may complete parking without the driver. In terms of the corresponding autonomous driving levels, the APA is approximately at the level L1, the RPA is approximately between the levels L2 and L3, and the AVP is approximately at the level L4.

[0076] For example, FIG. 2 is a diagram of a system architecture according to an embodiment of this application. The system architecture includes an ADAS and hardware of a vehicle. In terms of logical functions, the ADAS may include three main functional modules: a sensing system 110, a planning system 220, and a control system 230. The sensing system 110 senses an ambient environment of a vehicle body through a sensor, and inputs corresponding real-time data to the planning system 220. The planning system 220 plans a parking trajectory based on information obtained by the sensing module 210, and sends the planned parking trajectory to the control system 230. The control system 230 receives information about the parking trajectory from the planning system 220, and controls the vehicle based on the parking trajectory. For example, the control system 230 may control the hardware of the vehicle, so that the vehicle changes a lane, turns, brakes, and the like.

[0077] In this embodiment of this application, the sensing system 110 may extract information about an obstacle and a parking space in the ambient environment, and send the information to the planning system 220 for further processing. The planning system 220 receives the sensing information sent by the sensing system 110, plans a parking trajectory for completing an end-to-end task, and delivers the parking trajectory to the control system 230. After receiving the information from the planning system 220, the control system 230 sends a control instruction to the hardware of the vehicle to perform actual closed-loop vehicle control. In this embodiment of this application, related improvements are made in the planning system 220, and traffic congestion or traffic jam is avoided by using an active temporary parking method during vehicle meeting, thereby helping improve traffic efficiency.

[0078] The planning system 220 and the control system 230 may be located in the compute platform 120.

[0079] In an embodiment, the vehicle 100 may further interact with an electronic device (for example, a mobile phone) through a network. For example, in an unmanned parking scenario, the vehicle 100 may send information about a parking trajectory obtained through planning to the mobile phone, so that a user can view a parking process of the vehicle 100 through the mobile phone.

[0080] As described above, in a process in which the vehicle automatically parks into a target parking space, interaction deadlock with another vehicle may occur, causing traffic congestion. In this case, a driver needs to take over the vehicle to relieve the traffic congestion. In this way, an intelligence degree of automatic parking is low, and parking experience of the user is poor. An AVP function is used as an example. When passing through an intersection in a cruise phase, the vehicle may be in interaction deadlock with another vehicle, causing traffic congestion. The vehicle cannot perform automatic adjustment based on a complex dynamic interaction environment change, but needs to prompt, through a prompt apparatus (for example, a display apparatus), the driver to intervene to relieve traffic congestion.

[0081] Embodiments of this application provide a parking method and apparatus, and a vehicle. When the vehicle is in the interaction deadlock state with an obstacle, the vehicle may obtain a temporary parking pose, and plan a path from a current pose to the temporary parking pose. In this way, the vehicle is controlled to travel along the path to the temporary parking pose, so that traffic congestion can be relieved, and the interaction deadlock state can be released. In addition, a driver does not need to intervene in this process. This helps improve an intelligence degree of the vehicle in an automatic parking process, and helps improve parking experience of a user.

[0082] For example, FIG. 3 is a diagram of a parking scenario according to an embodiment of this application.

[0083] As shown in (a) in FIG. 3, a vehicle 100 passes through a crossroad in a process of parking into a target parking space based on a parking trajectory, and intersects with a vehicle 200 that travels oppositely at the crossroad. Because a size of the crossroad cannot meet a requirement that the vehicle 100 and the vehicle 200 pass through the crossroad side by side, interaction deadlock may occur, causing traffic congestion.

[0084] As shown in (b) in FIG. 3, the vehicle 100 passes through a narrow intersection in a process of parking into a target parking space based on a parking trajectory, and intersects with a vehicle 200 that travels oppositely at the narrow intersection. Because a size D of the narrow intersection cannot meet a requirement that the vehicle 100 and the vehicle 200 pass through the narrow intersection side by side, interaction deadlock may occur, causing traffic congestion.

[0085] In the parking scenarios shown in (a) and (b) in FIG. 3, when the vehicle 100 is in interaction deadlock with the vehicle 200, the vehicle 100 may determine a temporary parking pose and plan a path from a current position to the temporary parking pose. The vehicle 100 may travel to the temporary parking pose based on the path. When the interaction deadlock state is released, the vehicle 100 may continue to automatically park into the target parking space. In this embodiment of this application, for the crossroad, the narrow intersection, and a turn of a narrow road, when an ego vehicle (for example, the vehicle 100) and another vehicle (for example, the vehicle 200) are in an interaction deadlock state, the ego vehicle may actively park temporarily to give a way, to relieve current traffic congestion.

[0086] For example, a process in which the vehicle parks into the target parking space by using an AVP function includes a cruise phase and a parking phase. If interaction deadlock with another vehicle occurs in the cruise phase, the ego vehicle plans a path for roadside temporary parking or a path for temporary parking into a temporary parking space. The ego vehicle does not need to wait for long time, and can stop and quickly return to continue a cruise task after the another vehicle passes through.

[0087] For example, when interaction deadlock occurs between another vehicle and the ego vehicle in the parking phase, the ego vehicle may temporarily park on a roadside and yield a current road. After the another vehicle passes through, the ego vehicle can resume parking into the target parking space, and can dynamically park temporarily a plurality of times and repeatedly resolve interaction deadlock in the process of parking into the target parking space.

[0088] FIG. 4 is a schematic flowchart of a parking method 400 according to an embodiment of this application. The method 400 may be performed by the vehicle 100, or the method 400 may be performed by the compute platform 120, or the method 400 may be performed by a system including the compute platform 120 and the sensing system 110, or the method 400 may be performed by a system-on-a-chip (system-on-a-chip, SoC) on the compute platform 120, or the method 400 may be performed by a processor, a chip, or a circuit on the compute platform 120, or the method 400 may be performed by the planning system 220. The method 400 includes the following steps.

[0089] S410: Obtain a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space.

[0090] Optionally, the method 400 further includes: obtaining at least one of road structure information, a current pose of the vehicle, and information about a vacant parking space around the vehicle. Obtaining the first temporary parking pose includes: determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0091] For example, the road structure information may include at least one of information about a center line of a road structure and a width of a road.

[0092] For example, the first obstacle may be a moving obstacle, for example, another vehicle, a motorcycle, or a non-motor vehicle.

[0093] Optionally, determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space includes: obtaining a first temporary parking pose set; when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjusting and screening at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, where a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; and determining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[0094] The obstacle may include a stationary obstacle (for example, a column, a wall, or another vehicle parking in a parking space) and a moving obstacle.

[0095] The following describes a method for generating a temporary parking pose by the vehicle 100 when interaction deadlock occurs, scoring the temporary parking pose, planning a trajectory for temporary parking based on an asynchronous architecture, and scoring the trajectory in real time.

[0096] For example, FIG. 5 is a schematic flowchart of a temporary parking pose generation method 500 according to an embodiment of this application. The method 500 may be a possible implementation of implementing step S410. The method 500 includes the following steps.

[0097] S501: Extract road structure information based on data collected by the sensing system 110.

[0098] For example, the road structure information includes information such as a road boundary, a center line of a road, and a width of the road.

[0099] S502: Generate a temporary parking pose set 1 based on the road boundary, where the temporary parking pose set 1 includes a plurality of temporary parking poses.

[00100] The plurality of temporary parking poses include a pose of parking a vehicle 100 on a roadside and a pose of parking the vehicle 100 into a vacant parking space.

[00101] The plurality of temporary parking poses are poses that are generated by the vehicle 100 to avoid a first obstacle (for example, the vehicle 200) and that are used for temporary parking.

[00102] For example, a plurality of temporary parking poses are generated in a moving direction of the vehicle 100 and around the vehicle 100 at a specific interval, and an included angle between an orientation of each temporary parking pose and an orientation of a current pose of the vehicle 100 may be any included angle.

[00103] For example, if there is a vacant parking space around the vehicle 100, a temporary parking pose of the vehicle 100 parking into the vacant parking space may be extracted. The temporary parking pose may include a pose after the head of the vehicle 100 is parked into the vacant parking space and a pose after the tail of the vehicle 100 is parked into the vacant parking space.

[00104] Because the vehicle 100 temporarily parks in the vacant parking space to relieve traffic congestion, when an environment around the vacant parking space meets a condition (for example, no vehicle parks in a parking space around the vacant parking space), the vehicle 100 may be allowed to over a parking space line after parking into the vacant parking space based on the temporary parking pose, or allowed to exceed a parking space line by a preset threshold d. A pose in the vacant parking space is not restricted by the following angle limitation.

[00105] S503: Adjust and screen the temporary parking poses in the temporary parking pose set 1 based on the road structure information, to obtain a temporary parking pose set 2.

[00106] For example, a part of temporary parking poses in the temporary parking pose set 1 generated in S502 may be in contact with an obstacle or too close to an obstacle. Based on the temporary parking pose set 1 generated in S502, in S503, the part of temporary parking poses may be adjusted in different directions within a specific adjustment limit (for example, a preset threshold a), until a distance between the temporary parking pose and the obstacle can avoid a collision between the vehicle 100 and the obstacle. If the temporary parking pose still contacts the obstacle or is too close to the obstacle when the adjustment limit is exceeded, the temporary parking pose is deleted. Finally, after the temporary parking pose in the temporary parking pose set 1 is adjusted and screened, the temporary parking pose set 2 may be obtained.

[00107] For example, the temporary parking pose set 1 includes a temporary parking pose 1, and the temporary parking pose 1 is in contact with a column. The planning system 220 may adjust the temporary parking pose 1 based on the adjustment limit. For example, if the temporary parking pose 1 is adjusted to a temporary parking pose 2 within the adjustment limit, the temporary parking pose 2 may not be in contact with the column. In this way, the planning system 220 may replace the temporary parking pose 1 with the temporary parking pose 2.

[00108] For another example, the temporary parking pose set 1 includes a temporary parking pose 3, and the temporary parking pose 3 is in contact with the column. The planning system 220 may adjust the temporary parking pose 3 based on the adjustment limit. For example, if the temporary parking pose 3 is adjusted to any other pose within the adjustment limit and is still in contact with the column, the planning system 220 may delete the temporary parking pose 3.

[00109] Adjustment of the temporary parking pose in S503 may be adjustment in any direction. An objective of adjusting the temporary parking pose is to prevent the adjusted temporary parking pose from contacting the obstacle.

[00110] S504: Screen a temporary parking pose in the temporary parking pose set 2 based on an included angle between an orientation of the temporary parking pose and the orientation of the current pose of the vehicle 100, to obtain a temporary parking pose set 3.

[00111] An object to be screened in S504 may be a temporary parking pose that is in the temporary parking pose set 2 and that is for parking on a roadside.

[00112] For example, the temporary parking pose set 2 includes a temporary parking pose 4. If an included angle between an orientation of the temporary parking pose 4 and the orientation of the current pose of the vehicle 100 is greater than the preset threshold b, the temporary parking pose 4 is deleted.

[00113] For example, the temporary parking pose set 2 includes a temporary parking pose 5. If an included angle between an orientation of the temporary parking pose 5 and the orientation of the current pose of the vehicle 100 is less than or equal to the preset threshold b, the temporary parking pose 5 is retained.

[00114] S505: Screen the temporary parking pose set 3 based on an included angle between an orientation of a temporary parking pose and a tangent direction of a center line of a road structure, to obtain a temporary parking pose set 4.

[00115] An object to be screened in S505 may be a temporary parking pose that is in the temporary parking pose set 3 and that is for parking on a roadside.

[00116] For example, the temporary parking pose set 3 includes a temporary parking pose 6. When an included angle between an orientation of the temporary parking pose 6 and a tangent direction of a center line of a road structure that is recently detected by the vehicle 100 is greater than a preset threshold c, the temporary parking pose 6 is deleted.

[00117] For example, the temporary parking pose set 3 includes a temporary parking pose 7. When an included angle between an orientation of the temporary parking pose 7 and a tangent direction of a center line of a road structure that is recently detected by the vehicle 100 is less than or equal to the preset threshold c, the temporary parking pose 7 is retained.

[00118] S506: Delete a temporary parking pose, from the temporary parking pose set 4, at which another vehicle cannot pass through, to obtain a temporary parking pose set 5.

[00119] For example, the temporary parking pose set 4 includes a temporary parking pose 8. If the planning system 220 determines that the another vehicle still cannot pass through or an interaction deadlock (or traffic congestion) state cannot be released after the vehicle 100 switches from the current pose to the temporary parking pose 8, the temporary parking pose 8 may be deleted.

[00120] There is no actual sequence between S503, S504, S505, and S506.

[00121] S503 to S506 in the method 500 are optional steps. The planning system 220 may perform all or some of the steps. This is not specifically limited in embodiments of this application. For example, the planning system 220 may not perform S503 but perform S504 to S506.

[00122] Optionally, the first temporary parking pose is a pose not in a parking space. Determining the first temporary parking pose from the second temporary parking pose set includes: determining the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

[00123] For example, the second temporary parking pose set may be the temporary parking pose set 2 or the temporary parking pose set 5.

[00124] Optionally, the first temporary parking pose is a pose in the vacant parking space. Determining the first temporary parking pose from the second temporary parking pose set includes: determining the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

[00125] For example, the second temporary parking pose set may be the temporary parking pose set 5. The temporary parking pose set 5 may include a temporary parking pose for roadside parking and a pose for parking in a temporary parking space. The planning system 220 may determine the first temporary parking pose from the pose for parking in the temporary parking space in the temporary parking pose set 5, to control the vehicle to park into the temporary parking space. When it is detected that the interaction deadlock state is released, the planning system 220 may continue to control the vehicle 100 to park into the target parking space.

[00126] Optionally, determining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space includes: screening the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, where the third temporary parking pose set includes a plurality of temporary parking poses; and determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders the another vehicle from passing through, and a first included angle, where the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

[00127] For example, the foregoing describes, based on the method 500, a process of obtaining a temporary parking pose set through screening. The following describes a process of scoring a temporary parking pose in the temporary parking pose set with reference to a cost of each temporary parking pose, a probability that each temporary parking pose hinders another vehicle from passing through, and the first included angle.

[00128] For example, if the temporary parking pose set 5 includes N poses, and N is a positive integer greater than 1, a score of an ith (1≤i≤N and i is an integer) temporary parking pose in the temporary parking pose set may be shown in Formula (1):(1)

[00129] Herein, is a score of a cost for the vehicle 100 to reach the ith temporary parking pose, is a score of a probability that the ith temporary parking pose hinders another vehicle from passing through, is a score of matching between the ith temporary parking pose and an intent of the ego vehicle, and are corresponding weights.

[00130] Optionally, for different scenarios, values of may be different. For example, values of may be determined based on a congestion degree of a current road.

[00131] For example, in a particularly congested scenario (for example, a scenario in which there are other vehicles in front of and behind the ego vehicle), and may be 0.2, and may be 0.6.

[00132] For another example, in a relatively congested scenario (for example, a scenario in which there is another vehicle in front of the ego vehicle or there is another vehicle behind the ego vehicle), and may be 0.25, and may be 0.5.

[00133] Optionally, the score of the cost for the vehicle 100 to reach the ith temporary parking pose may be determined by the cost required by the vehicle 100 to reach the ith temporary parking pose. A higher cost required by the vehicle 100 to reach the ith temporary parking pose indicates a smaller , and a lower cost indicates a larger .

[00134] For example, the cost required by the vehicle 100 to reach the ith temporary parking pose includes but is not limited to the following costs.

[00135] (1) Distance cost cost1 between the ith temporary parking pose and the vehicle 100

[00136] A smaller distance between the ith temporary parking pose and the vehicle 100 indicates a smaller distance cost cost1. A smaller distance between the ith temporary parking pose and the vehicle 100 may be understood as a smaller cost planned by the planning system 220 for reaching the ith temporary parking pose.

[00137] (2) Included angle cost cost2 between an orientation of the ith temporary parking pose and the orientation of the current pose of the vehicle 100

[00138] A smaller included angle between the orientation of the ith temporary parking pose and the orientation of the current pose of the vehicle 100 indicates a smaller included angle cost cost2. A larger included angle between the orientation of the ith temporary parking pose and the orientation of the current pose of the vehicle 100 indicates that the planning system 220 is more inclined to plan a turn trajectory, and a cost is larger.

[00139] (3) Gear shifting cost cost3

[00140] For example, a search-based planning algorithm may be used to calculate and predict a quantity of gear shifts on a path for reaching the ith temporary parking pose. A smaller quantity of gear shifts indicates a smaller gear shifting cost cost3.

[00141] For example, the score of the probability that the ith temporary parking pose hinders the another vehicle from passing through may be determined from the following two aspects.

[00142] (1) Whether an intended path of the another vehicle intersects with the ith temporary parking pose

[00143] If the ith temporary parking pose is farther away from the intended path of another vehicle, it is less likely to hinder the another vehicle, and the score of the probability that the ith temporary parking pose hinders the another vehicle from passing through is higher.

[00144] (2) Remaining passage width after the ego vehicle reaches the ith temporary parking pose.

[00145] In addition to the intended path of the another vehicle, the road structure and whether the generated temporary parking pose is sufficient for the another vehicle to pass through further need to be considered. When the another vehicle passes through the temporary parking pose, a larger remaining passage width indicates a higher score of the probability that the ith temporary parking pose hinders the another vehicle from passing through.

[00146] For example, the score of matching between the ith temporary parking pose and the intent of the ego vehicle may be determined by an included angle between a vehicle head direction of the vehicle 100 at the ith temporary parking pose and a tangent line of a center line of a road structure closest to the ith temporary parking pose. A smaller included angle indicates better matching with the intent of the ego vehicle, and is more helpful for improving parking efficiency. In this case, the score of matching between the ith temporary parking pose and the intent of the ego vehicle is higher.

[00147] Optionally, the process in which the vehicle automatically parks into the target parking space includes a parking phase. Determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, and the first included angle includes: when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

[00148] For example, if the vehicle performs automatic parking by using an AVP function, a phase of automatic parking of the vehicle may be divided into a cruise phase and the parking phase. The cruise phase is a phase in which the vehicle travels from a start position to a position near the target parking space, and the parking phase is a phase in which the vehicle parks into the target parking space after reaching the position near the target parking space. In the parking phase, in addition to the cost of each temporary parking pose, the probability that each temporary parking pose hinders the another vehicle from passing through, and the first included angle, the distance cost between the temporary parking pose and the target parking space may be further considered. This can avoid a case in which the temporary parking pose is excessively far away from the target parking space, to help improve parking efficiency in the parking phase, so as to help improve parking experience of the user.

[00149] For example, FIG. 6 to FIG. 19 are diagrams of temporary parking poses in several parking scenarios according to an embodiment of this application.

[00150] As shown in FIG. 6, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning left at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and travels straight. In this case, the vehicle 100 may determine a temporary parking pose 9 based on the foregoing method, so that the vehicle 100 may be controlled to move from a current pose to the temporary parking pose 9. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00151] For example, the vehicle 100 may first determine a temporary parking pose set 5 based on the temporary parking pose generation method 500, and select one or more temporary parking poses from the temporary parking pose set 5, to obtain the temporary parking pose 9.

[00152] The temporary parking pose 9 may be understood as a temporary parking pose for parking on a roadside.

[00153] As shown in FIG. 7, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning left at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns right. In this case, the vehicle 100 may determine a temporary parking pose 10 (which may also be referred to as a temporary parking pose for parking on a roadside) or a temporary parking pose 11 (which may also be referred to as a temporary parking pose in a temporary parking space) based on the foregoing method, so that the vehicle 100 may be controlled to move from a current pose to the temporary parking pose 10 or the temporary parking pose 11. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00154] In an embodiment, when a width D of a road on which the vehicle 100 is located can ensure that the vehicle 100 and the vehicle 200 pass through side by side, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 10. Otherwise, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 11.

[00155] As shown in FIG. 8, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning left at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns left. In this case, the vehicle 100 may determine a temporary parking pose 12 based on the foregoing method, so that the vehicle 100 may be controlled to move from a current pose to the temporary parking pose 12. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00156] As shown in FIG. 9, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when traveling straight at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and travels straight. In this case, the vehicle 100 may determine a temporary parking pose 13 based on the foregoing method, so that the vehicle 100 may be controlled to move from a current pose to the temporary parking pose 13. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00157] As shown in FIG. 10, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when traveling straight at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns right. In this case, the vehicle 100 may determine a temporary parking pose 14 based on the foregoing method, so that the vehicle 100 may be controlled to move from a current pose to the temporary parking pose 14. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00158] As shown in FIG. 11, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when traveling straight at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns left. In this case, the vehicle 100 may determine a temporary parking pose 15 or a temporary parking pose 16 based on the foregoing method, so that the vehicle 100 can be controlled to move from a current pose to the temporary parking pose 15 or the temporary parking pose 16. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00159] In an embodiment, when a width D of a road on which the vehicle 100 is located can ensure that the vehicle 100 and the vehicle 200 pass through side by side, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 16. Otherwise, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 15.

[00160] As shown in FIG. 12, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning right at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and travels straight. In this case, the vehicle 100 may determine a temporary parking pose 17 or a temporary parking pose 18 based on the foregoing method, so that the vehicle 100 can be controlled to move from a current pose to the temporary parking pose 17 or the temporary parking pose 18. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00161] As shown in FIG. 13, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning right at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns right. In this case, the vehicle 100 may determine a temporary parking pose 19 or a temporary parking pose 20 based on the foregoing method, so that the vehicle 100 can be controlled to move from a current pose to the temporary parking pose 19 or the temporary parking pose 20. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00162] In an embodiment, when a width D of a road on which the vehicle 100 is located can ensure that the vehicle 100 and the vehicle 200 pass through side by side, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 19. Otherwise, the vehicle 100 may determine a temporary parking pose as the temporary parking pose 20.

[00163] As shown in FIG. 14, in a process in which a vehicle 100 parks into a target parking space by using an AVP function, when turning right at an intersection of a parking lot, the vehicle 100 is in an interaction deadlock state with a vehicle 200 that also passes through the intersection and turns left. In this case, the vehicle 100 may determine a temporary parking pose 21 or a temporary parking pose 22 based on the foregoing method, so that the vehicle 100 can be controlled to move from a current pose to the temporary parking pose 21 or the temporary parking pose 22. In this way, after the vehicle 200 passes through the intersection (or the interaction deadlock state is released), the vehicle 100 may continue to park into the target parking space.

[00164] S420: Plan a first path for the vehicle to travel from the current pose to the first temporary parking pose.

[00165] In the foregoing step S420, the path from the current pose to the first temporary parking pose may be planned by using a geometric method, an A* algorithm, a hybrid A* algorithm, or the like.

[00166] Optionally, determining the first temporary parking pose from the plurality of temporary parking poses includes: determining the first temporary parking pose from the plurality of temporary parking poses through a first thread. Determining the first path from the one or more parking paths includes: determining the first path from the one or more parking paths through the first thread.

[00167] Optionally, planning the first path for the vehicle to travel from the current pose to the first temporary parking pose includes: planning the one or more parking paths through a second thread, where the one or more parking paths include the first path.

[00168] For example, FIG. 15A and FIG. 15B are a schematic flowchart of a temporary parking and real-time scoring method 700 that is based on an asynchronous architecture according to an embodiment of this application.

[00169] The asynchronous architecture may be understood as that a planning system 220 includes a main thread and a secondary thread. The main thread may be configured to screen and score a temporary parking pose, and send a temporary parking pose with a high score to the secondary thread after scoring. The secondary thread may plan a path for a vehicle 100 from a current pose to the temporary parking pose. When completing path planning for the temporary parking pose, the secondary thread may send the planned path to the main thread, so that the main thread scores the path. When the secondary thread performs path planning, the main thread may screen and score the temporary parking pose and score the path in real time. The main thread may be the first thread, and the secondary thread may be the second thread. The method 700 includes the following steps.

[00170] S701: Set a generation threshold of the temporary parking pose.

[00171] The generation threshold of the temporary parking pose may include one or more of a threshold a, a threshold b, a threshold c, and a threshold d.

[00172] Optionally, when an interaction deadlock state occurs, the vehicle 100 may first set the threshold a, the threshold b, the threshold c, and the threshold d to tightened thresholds.

[00173] S702: Obtain a temporary parking pose set.

[00174] For example, the vehicle 100 may obtain the temporary parking pose set 5 based on the method 500.

[00175] S703: Score and sort temporary parking poses.

[00176] For example, N poses in the temporary parking pose set 5 may be scored and sorted based on Formula (1).

[00177] For example, S701 to S703 may be performed by the main thread.

[00178] S704: Transfer the sorted temporary parking poses to a planning thread for path planning.

[00179] For example, the planning thread may be the secondary thread.

[00180] S705: Score the obtained path in real time.

[00181] Optionally, the vehicle 100 may determine the first path based on at least one of a quantity of gear shifts and / or a probability of occupying the intended path of the another vehicle when the vehicle travels along the path.

[00182] For example, in the path scoring method, weighted scoring may be performed by using the quantity of gear shifts and / or the probability of occupying the intended path of the another vehicle. For example, a smaller quantity of gear shifts indicates a higher score of the path. For another example, a smaller probability of occupying the intended path of the another vehicle indicates a higher score of the path.

[00183] S706: Determine whether the vehicle is in a tightened threshold mode.

[00184] For example, if the threshold used in S701 is a tightened threshold, the vehicle is currently in the tightened threshold mode, and performs S707. If the threshold used in S701 is a relaxed threshold, the vehicle is currently in a non-tightened threshold mode (or a relaxed threshold mode), and performs S711.

[00185] S707: When it is determined that the vehicle is currently in the tightened threshold mode, determine whether timeout time of the tightened threshold is reached.

[00186] For example, if the timeout time of the tightened threshold is reached, S708 is performed; otherwise, real-time scoring continues to be performed on the path.

[00187] S708: Determine whether there is a path whose score reaches a scoring threshold.

[00188] If there is a path whose score reaches the scoring threshold before the timeout time of the tightened threshold is reached, S709 may be performed; otherwise, S710 is performed.

[00189] S709: Control the vehicle to travel along a path with a highest score.

[00190] For example, when determining, in S708, that there are a plurality of paths whose scores reach the score threshold, the vehicle 100 may control the vehicle to travel along the path with the highest score.

[00191] S710: Stop all requests in planning, and set the generation threshold of temporary parking pose to a relaxed threshold.

[00192] For example, Table 1 shows the tightened threshold and the relaxed threshold.Table 1 Threshold aThreshold bThreshold cThreshold dTightened threshold20 cm10°10°10 cmRelaxed threshold50 cm20°20°30 cm 

[00193] The foregoing table is merely an example. Specific values of the tightened threshold and the relaxed threshold are not specifically limited in embodiments of this application.

[00194] In this embodiment of this application, a generation threshold of the temporary parking pose set is first tightened, the temporary parking pose set 5 is generated based on the temporary parking pose generation method 500 described above, and the N poses in the temporary parking pose set 5 are scored and sorted. The sorted temporary parking poses are transferred to an asynchronous planning thread for path planning. Before the timeout time of the tightened threshold is reached, the obtained path is continuously scored in real time. If a path whose score reaches the scoring threshold appears, the vehicle is controlled to travel along the path with the highest score.

[00195] If no path whose score exceeds the score threshold appears before a time upper limit planned in the tightened threshold mode is reached, a planning request for path planning in the planning thread is interrupted, a generation threshold of the target pose is relaxed, and the foregoing process S701 to S706 is repeated.

[00196] S711: When it is determined that the vehicle is currently in the non-tightened threshold mode, determine whether timeout time of the relaxed threshold is reached.

[00197] For example, if the timeout time of the relaxed threshold is reached, S712 is performed; otherwise, real-time scoring continues to be performed on the path.

[00198] S712: Determine whether there is a stored path.

[00199] For example, if there is a stored path, S713 is performed; otherwise, S714 is performed.

[00200] S713: Control the vehicle to travel along the path with the highest score.

[00201] For example, when timeout time of the relaxed threshold is reached, and a plurality of paths are obtained through planning, the vehicle 100 may control the vehicle 100 to travel along the path with the highest score.

[00202] S714: Determine that temporary parking fails.

[00203] If no path whose score exceeds the score threshold appears after a planning time upper limit of a relaxed threshold mode is reached, the path with the highest score is tracked in the existing paths. Otherwise, if there is no stored path, it is considered that temporary parking fails.

[00204] In an embodiment, when it is determined that temporary parking fails, the vehicle 100 may prompt, through a prompt apparatus, the user to take over the vehicle; or the vehicle 100 may send an instruction to a mobile terminal (for example, a mobile phone), where the instruction instructs the user to take over the vehicle.

[00205] In this embodiment of this application, a form of a tightened threshold and a relaxed threshold may be used, to improve planning robustness, and avoid a case in which a proper path cannot be found because too many temporary parking poses are screened out due to an excessively tight threshold.

[00206] S430: Control, based on the first path, the vehicle to travel to the first temporary parking pose.

[00207] Optionally, the method 400 further includes: when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, stopping traveling along the first path and obtaining a second temporary parking pose; planning a second path for the vehicle to travel from the current pose to the second temporary parking pose; and controlling, based on the second path, the vehicle to travel to the second temporary parking pose.

[00208] Although the target pose selection and path planning method in the foregoing attempts to alleviate interaction deadlock and an interaction conflict, because a scenario faced by the vehicle is a dynamic interaction process, there is still a case in which interaction deadlock is caused by blocking by the another vehicle on a path in a process of traveling from a current pose of the vehicle to a temporary parking pose. In this case, another temporary parking pose should be found for dynamic temporary parking.

[00209] FIG. 16 to FIG. 19 are other diagrams of a parking scenario according to an embodiment of this application.

[00210] For example, as shown in FIG. 16, when a vehicle 100 is in a cruise phase, the vehicle 100 and a vehicle 200 meet at a narrow intersection. Because a width D of the narrow intersection cannot meet a requirement for the vehicle 100 and the vehicle 200 to pass side by side, the vehicle 100 may obtain a temporary parking pose 23 based on the method 500 and plan a path 1 from a current pose to the temporary parking pose 23.

[00211] As shown in FIG. 17, before the vehicle 100 travels to the temporary parking pose 23 along the path 1, it is determined that a vehicle 300 behind the vehicle 100 travels toward the vehicle 100. In this case, the vehicle 100 is in an interaction deadlock state with a vehicle 300 in the process in which the vehicle 100 travels to the temporary parking pose 23. The vehicle 100 may stop traveling to the temporary parking pose 23 along the path 1, and obtain a temporary parking pose 24 again based on the foregoing method 500. The vehicle 100 may plan a path 2 from the current pose to the temporary parking pose 24. In this way, when the vehicle 100 travels to the temporary parking pose 24 along the path 2, the interaction deadlock state between the vehicle 100 and the vehicle 200 may be released, or the interaction deadlock state between the vehicle 100 and the vehicle 300 may be released. In this way, after the vehicle 200 passes through the narrow intersection, the vehicle 100 and the vehicle 300 may successively pass through the narrow intersection, so that traffic congestion can be relieved.

[00212] For example, as shown in FIG. 18, when the vehicle 100 reaches near the target parking space, the vehicle 100 may switch from the cruise phase to the parking phase. When the vehicle 100 is in the parking phase, the vehicle 100 is in interaction deadlock with the vehicle 200 behind the vehicle 100. The vehicle 100 may obtain a temporary parking pose 25 based on the foregoing method 500, and plan a path 3 from the current pose to the temporary parking pose 25.

[00213] As shown in FIG. 19, in a process in which the vehicle 100 travels along the path 3 to the temporary parking pose 25, it is detected that the vehicle 300 travels toward the vehicle 100. In this case, the vehicle 100 is in the interaction deadlock state with the vehicle 300 in the process in which the vehicle 100 travels to the temporary parking pose 25. The vehicle 100 may stop traveling to the temporary parking pose 25 along the path 3, and obtain a temporary parking pose 26 again based on the foregoing method 500. The vehicle 100 may plan a path 4 from the current pose to the temporary parking pose 26. In this way, the vehicle 100 travels along the path 4 to the temporary parking pose 26. After both the vehicle 200 and the vehicle 300 pass through the road, the vehicle 100 may continue to park into the target parking space.

[00214] Optionally, when selecting the temporary parking pose in the tracking process in the parking phase, the vehicle 100 may further consider a score of a distance between the temporary parking pose and the target parking space when scoring the temporary parking pose.

[00215] For example, the score of the distance between the temporary parking pose and the target parking space may be determined by a distance cost between the temporary parking pose and the target parking space. A longer distance between the temporary parking pose and the target parking space indicates a larger distance cost between the temporary parking pose and the target parking space and a lower score of the distance between the temporary parking pose and the target parking space.

[00216] After the road traffic congestion is relieved, the vehicle 100 may immediately brake along the planned path, continue to perform the parking task, and repeatedly park into the target parking space, or directly switch to the cruise phase. The interaction process of temporary parking and temporary parking recovery may be dynamically repeated a plurality of times.

[00217] Optionally, the method 400 further includes: before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, controlling the vehicle to stop traveling along the first path and continue to automatically park into the target parking space. In this way, before the vehicle 100 travels to the temporary parking pose, if the vehicle 100 determines that the interaction deadlock state is released, the vehicle 100 may stop traveling along the first path, and continue to automatically park into the target parking space.

[00218] FIG. 20 is a schematic flowchart of a parking apparatus 900 according to an embodiment of this application. As shown in FIG. 20, the apparatus 900 includes: an obtaining unit 910, configured to obtain a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space; a path planning unit 920, configured to plan a first path for the vehicle to travel from a current pose to the first temporary parking pose; and a control unit 930, configured to control, based on the first path, the vehicle to travel to the first temporary parking pose.

[00219] Optionally, the obtaining unit 910 is specifically configured to: obtain at least one of road structure information, the current pose of the vehicle, and information about a vacant parking space around the vehicle; and determine the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[00220] Optionally, the obtaining unit 910 is specifically configured to: obtain a first temporary parking pose set; when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjust and screen at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, where a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; and determine the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

[00221] Optionally, the first temporary parking pose is a pose not in a parking space, and the obtaining unit 910 is specifically configured to: determine the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

[00222] Optionally, the first temporary parking pose is a pose in the vacant parking space, and the obtaining unit 910 is specifically configured to: determine the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

[00223] Optionally, the obtaining unit 910 is specifically configured to: screen the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, where the third temporary parking pose set includes a plurality of temporary parking poses; and determine the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders the another vehicle from passing through, and a first included angle, where the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

[00224] Optionally, the process in which the vehicle automatically parks into the target parking space includes a parking phase. The obtaining unit 910 is specifically configured to: when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determine the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

[00225] Optionally, the apparatus 900 further includes a determining unit. The determining unit is configured to: before the control unit controls the vehicle to travel to the first temporary parking pose, determine the first path from one or more parking paths based on a quantity of gear shifts when the vehicle travels along the first path, and / or a probability that the vehicle occupies an intended path of the another vehicle when the vehicle travels along the first path.

[00226] Optionally, the obtaining unit 910 is specifically configured to determine the first temporary parking pose from the plurality of temporary parking poses through a first thread. The determining unit is specifically configured to determine the first path from the one or more parking paths through the first thread. The path planning unit 920 is specifically configured to plan the one or more parking paths through a second thread.

[00227] Optionally, the control unit 930 is further configured to: when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, control the vehicle to stop traveling along the first path. The obtaining unit 910 is further configured to obtain a second temporary parking pose. The path planning unit 920 is further configured to plan a second path for the vehicle to travel from the current pose to the second temporary parking pose. The control unit 930 is further configured to control, based on the second path, the vehicle to travel to the second temporary parking pose.

[00228] Optionally, the control unit 930 is further configured to: before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, control the vehicle to stop traveling along the first path and continue to automatically park into the target parking space.

[00229] For example, the obtaining unit 910 may be the compute platform in FIG. 1, or a processing circuit, a processor, or a controller on the compute platform. For example, the obtaining unit 910 is a processor 121 on the compute platform, and the processor 121 may determine the first temporary parking pose based on information about an ambient environment.

[00230] For another example, the path planning unit 920 may be the compute platform in FIG. 1, or a processing circuit, a processor, or a controller on the compute platform in FIG. 1. For example, the path planning unit 920 is the processor 122 on the compute platform. The processor 122 may plan, based on the first temporary parking pose determined by the processor 121, a path from the current position to the first temporary parking pose.

[00231] For another example, the control unit 930 may be the compute platform in FIG. 1, or a processing circuit, a processor, or a controller on the compute platform in FIG. 1. For example, the control unit 930 is the processor 123 on the compute platform. The processor 123 may determine a path based on the processor 122, and control the vehicle to travel from the current pose to the first temporary parking pose.

[00232] The function implemented by the obtaining unit 910, the function implemented by the path planning unit 920, and the function implemented by the control unit 930 may be implemented by different processors, or may be implemented by a same processor, or some functions may be implemented by a same processor. This is not limited in embodiments of this application.

[00233] It should be understood that division into the units in the foregoing apparatus is merely division into logical functions. In practice, all or some of the units may be integrated into one physical entity, or may be physically separated. In addition, the units of the apparatus may be implemented in a form of software invoked by a processor. For example, the apparatus includes a processor, the processor is connected to a memory, the memory stores instructions, and the processor invokes the instructions stored in the memory, to implement any one of the foregoing methods or implement functions of the units of the apparatus. The processor is, for example, a general-purpose processor, for example, a CPU or a microprocessor, and the memory is a memory inside the apparatus or a memory outside the apparatus. Alternatively, the units of the apparatus may be implemented in a form of a hardware circuit, and functions of some or all of the units may be implemented by designing the hardware circuit. The hardware circuit may be understood as one or more processors. For example, in an implementation, the hardware circuit is an ASIC, and functions of some or all of the foregoing units are implemented by designing a logical relationship between elements in the circuit. For another example, in another implementation, the hardware circuit may be implemented by using a PLD. An FPGA is used as an example. The hardware circuit may include a large quantity of logic gate circuits, and a connection relationship between the logic gate circuits is configured by using a configuration file, to implement functions of some or all of the foregoing units. All units of the foregoing apparatuses may be implemented in a form of software invoked by the processor, or all units may be implemented in a form of the hardware circuit, or some units may be implemented in a form of software invoked by the processor, and a remaining part may be implemented in a form of the hardware circuit.

[00234] In embodiments of this application, the processor is a circuit having a signal processing capability. In an implementation, the processor may be a circuit having a capability of instruction reading and running, for example, a CPU, a microprocessor, a GPU, or a DSP. In another implementation, the processor may implement a specific function based on a logical relationship of a hardware circuit. The logical relationship of the hardware circuit is fixed or reconfigurable. For example, the processor is a hardware circuit implemented by an ASIC or a PLD, for example, an FPGA. In the reconfigurable hardware circuit, a process in which the processor loads a configuration document to implement hardware circuit configuration may be understood as a process in which the processor loads an instruction to implement functions of some or all of the foregoing units. In addition, the processor may alternatively be a hardware circuit designed for artificial intelligence, and may be understood as an ASIC, for example, an NPU, a TPU, or a DPU.

[00235] It can be learned that each unit of the foregoing apparatus may be one or more processors (or processing circuits) configured to implement the foregoing method, for example, a CPU, a GPU, an NPU, a TPU, a DPU, a microprocessor, a DSP, an ASIC, or an FPGA, or a combination of at least two of these processor forms.

[00236] In addition, all or some of the units of the foregoing apparatus may be integrated, or may be implemented independently. In an implementation, these units are integrated and implemented in a form of SoC. The SoC may include at least one processor, configured to implement any one of the foregoing methods or achieve the functions of the units in the apparatus. Types of the at least one processor may be different. For example, the at least one processor includes a CPU and an FPGA, a CPU and an artificial intelligence processor, or a CPU and a GPU.

[00237] An embodiment of this application further provides an apparatus. The apparatus includes a processing unit and a storage unit. The storage unit is configured to store instructions, and the processing unit executes the instructions stored in the storage unit, so that the apparatus performs the method or the steps performed in the foregoing embodiments.

[00238] Optionally, if the apparatus is located in a vehicle, the processing unit may be the processors 121 to 12n shown in FIG. 1.

[00239] An embodiment of this application further provides a parking system. The control system may include a compute platform and a sensing system. The compute platform may include the parking apparatus 900.

[00240] An embodiment of this application further provides a vehicle. The vehicle may include the parking apparatus 900 or the parking system.

[00241] An embodiment of this application further provides a computer program product. The computer program product includes computer program code. When the computer program code is run on a computer, the computer is enabled to perform the method in the foregoing embodiments.

[00242] An embodiment of this application further provides a computer-readable medium. The computer-readable medium stores program code. When the computer program code is run on a computer, the computer is enabled to perform the method in the foregoing embodiments.

[00243] An embodiment of this application further provides a chip. The chip includes a circuit, and the circuit is configured to perform the method in the foregoing embodiments.

[00244] In an implementation process, steps in the foregoing methods can be implemented by using a hardware integrated logic circuit in the processor, or by using instructions in a form of software. The method of the communication disclosed with reference to embodiments of this application may be directly performed by a hardware processor, or may be performed by using a combination of hardware in the processor and a software module. The software module may be located in a mature storage medium in the art, like a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, or a register. The storage medium is located in the memory, and a processor reads information in the memory and completes the steps in the foregoing methods in combination with hardware of the processor. To avoid repetition, details are not described herein again.

[00245] It should be understood that in this embodiment of this application, the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.

[00246] It should be further understood that sequence numbers of the foregoing processes do not mean execution sequences in embodiments of this application. The execution sequences of the processes should be determined based on functions and internal logic of the processes, and should not be construed as any limitation on the implementation processes of embodiments of this application.

[00247] A person of ordinary skill in the art may be aware that, units and algorithm steps in the examples described with reference to embodiments disclosed in this specification can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed by hardware or software depends on particular applications and design constraint conditions of the technical solutions. A person skilled in the art may use different methods to implement the described functions for each particular application, but it should not be considered that the implementation goes beyond the scope of this application.

[00248] It may be clearly understood by a person skilled in the art that, for the purpose of convenient and brief descriptions, for a detailed working process of the foregoing system, apparatus, and unit, refer to a corresponding process in the foregoing method embodiments. Details are not described herein again.

[00249] In the several embodiments provided in this application, it should be understood that the disclosed system, apparatus, and method may be implemented in other manners. For example, the described apparatus embodiments are merely examples. For example, division into the units is merely logical function division. There may be another division manner during actual implementation. For example, a plurality of units or components may be combined or integrated into another system, or some features may be ignored or not performed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections may be implemented through some interfaces. The indirect couplings or communication connections between the apparatuses or units may be implemented in electronic, mechanical, or other forms.

[00250] The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual requirements to achieve the objectives of the solutions in embodiments.

[00251] In addition, functional units in the embodiments of this application may be integrated into one processing unit, each of the units may exist alone physically, or two or more units are integrated into one unit.

[00252] When the functions are implemented in the form of a software functional unit and sold or used as an independent product, the functions 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 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, a server, or a network device) 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.

[00253] The foregoing descriptions are merely specific implementations of this application, but are not intended to limit the protection scope of this application. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in this application shall fall within the protection scope of this application. Therefore, the protection scope of this application shall be subject to the protection scope of the claims. 

Claims

1. A parking method, comprising:obtaining a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space;planning a first path for the vehicle to travel from a current pose to the first temporary parking pose; andcontrolling, based on the first path, the vehicle to travel to the first temporary parking pose.

2. The method according to claim 1, wherein the method further comprises:obtaining at least one of road structure information, the current pose of the vehicle, and information about a vacant parking space around the vehicle; andobtaining the first temporary parking pose comprises:determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

3. The method according to claim 2, wherein determining the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space comprises:obtaining a first temporary parking pose set;when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjusting and screening at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, wherein a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; anddetermining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

4. The method according to claim 3, wherein the first temporary parking pose is a pose not in a parking space, and determining the first temporary parking pose from the second temporary parking pose set comprises:determining the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

5. The method according to claim 3, wherein the first temporary parking pose is a pose in the vacant parking space, and determining the first temporary parking pose from the second temporary parking pose set comprises:determining the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

6. The method according to any one of claims 3 to 5, wherein determining the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space comprises:screening the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, wherein the third temporary parking pose set comprises a plurality of temporary parking poses; anddetermining the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders another vehicle from passing through, and a first included angle, wherein the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

7. The method according to claim 6, wherein the process in which the vehicle automatically parks into the target parking space comprises a parking phase, and determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, and the first included angle comprises:when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determining the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

8. The method according to claim 6 or 7, wherein before controlling, based on the first path, the vehicle to travel to the first temporary parking pose, the method further comprises:determining that a quantity of gear shifts of the vehicle when the vehicle travels along the first path meets a preset condition and / or a probability that the vehicle occupies an intended path of the another vehicle when the vehicle travels along the first path meets a preset condition.

9. The method according to claim 8, wherein determining the first temporary parking pose from the plurality of temporary parking poses comprises:determining the first temporary parking pose from the plurality of temporary parking poses through a first thread, and determining the first path from one or more paths through the first thread; andplanning the first path for the vehicle to travel from the current pose to the first temporary parking pose comprises:planning the one or more paths through a second thread.

10. The method according to any one of claims 1 to 9, wherein the method further comprises:when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, stop traveling along the first path and obtain a second temporary parking pose;planning a second path for the vehicle to travel from the current pose to the second temporary parking pose; andcontrolling, based on the second path, the vehicle to travel to the second temporary parking pose.

11. The method according to any one of claims 1 to 10, wherein the method further comprises:before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, controlling the vehicle to stop traveling along the first path and continue to automatically park into the target parking space.

12. A parking apparatus, comprising:an obtaining unit, configured to obtain a first temporary parking pose when a vehicle is in an interaction deadlock state with a first obstacle in a process of automatically parking into a target parking space;a path planning unit, configured to plan a first path for the vehicle to travel from a current pose to the first temporary parking pose; anda control unit, configured to control, based on the first path, the vehicle to travel to the first temporary parking pose.

13. The apparatus according to claim 12, wherein the obtaining unit is specifically configured to:obtain at least one of road structure information, the current pose of the vehicle, and information about a vacant parking space around the vehicle; anddetermine the first temporary parking pose based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

14. The apparatus according to claim 13, wherein the obtaining unit is specifically configured to:obtain a first temporary parking pose set;when a distance between at least a part of temporary parking poses in the first temporary parking pose set and an obstacle is less than or equal to a first preset distance, adjust and screen at least the part of temporary parking poses based on a preset adjustment distance, to obtain a second temporary parking pose set, wherein a distance between each temporary parking pose in the second temporary parking pose set and the obstacle is greater than the first preset distance; anddetermine the first temporary parking pose from the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space.

15. The apparatus according to claim 14, wherein the first temporary parking pose is a pose not in a parking space, and the obtaining unit is specifically configured to:determine the first temporary parking pose from the second temporary parking pose set based on at least one of an included angle between an orientation of each temporary parking pose in the second temporary parking pose set and an orientation of the current pose and an included angle between the orientation of each temporary parking pose and a tangent direction of a center line of a road structure closest to each temporary parking pose.

16. The apparatus according to claim 14, wherein the first temporary parking pose is a pose in the vacant parking space, and the obtaining unit is specifically configured to:determine the first temporary parking pose from the second temporary parking pose set based on a length by which each temporary parking pose in the second temporary parking pose set exceeds a parking space line of the vacant parking space.

17. The apparatus according to any one of claims 14 to 16, wherein the obtaining unit is specifically configured to:screen the second temporary parking pose set based on at least one of the road structure information, the current pose, and the information about the vacant parking space, to obtain a third temporary parking pose set, wherein the third temporary parking pose set comprises a plurality of temporary parking poses; anddetermine the first temporary parking pose from the plurality of temporary parking poses based on at least one of a cost for the vehicle to reach each of the plurality of temporary parking poses, a probability that each temporary parking pose hinders another vehicle from passing through, and a first included angle, wherein the first included angle is the included angle between the orientation of each temporary parking pose and the tangent direction of the center line of the road structure closest to each temporary parking pose.

18. The apparatus according to claim 17, wherein the process in which the vehicle automatically parks into the target parking space comprises a parking phase, and the obtaining unit is specifically configured to:when the vehicle is in the interaction deadlock state with the first obstacle in the parking phase, determine the first temporary parking pose from the plurality of temporary parking poses based on at least one of the cost for the vehicle to reach each of the plurality of temporary parking poses, the probability that each temporary parking pose hinders the another vehicle from passing through, the first included angle, and a distance cost between each temporary parking pose and the target parking space.

19. The apparatus according to claim 17 or 18, wherein the apparatus further comprises a determining unit; andthe determining unit is configured to: before the control unit controls the vehicle to travel to the first temporary parking pose, determine that a quantity of gear shifts of the vehicle when the vehicle travels along the first path meets a preset condition and / or a probability that the vehicle occupies an intended path of the another vehicle when the vehicle travels along the first path meets a preset condition.

20. The apparatus according to claim 19, whereinthe obtaining unit is specifically configured to determine the first temporary parking pose from the plurality of temporary parking poses through a first thread;the determining unit is specifically configured to determine the first path from one or more paths through the first thread; andthe path planning unit is specifically configured to plan the one or more paths through a second thread.

21. The apparatus according to any one of claims 12 to 20, whereinthe control unit is further configured to: when the vehicle is in an interaction deadlock state with a second obstacle in a process of traveling along the first path to the first temporary parking pose, control the vehicle to stop traveling along the first path;the obtaining unit is further configured to obtain a second temporary parking pose;the path planning unit is further configured to plan a second path for the vehicle to travel from the current pose to the second temporary parking pose; andthe control unit is further configured to control, based on the second path, the vehicle to travel to the second temporary parking pose.

22. The apparatus according to any one of claims 12 to 21, whereinthe control unit is further configured to: before the vehicle travels along the first path to the first temporary parking pose, when the interaction deadlock state is released, control the vehicle to stop traveling along the first path and continue to automatically park into the target parking space.

23. A parking apparatus, comprising:a memory, configured to store a computer program; anda processor, configured to execute the computer program stored in the memory, so that the apparatus performs the method according to any one of claims 1 to 11.

24. A vehicle, comprising the apparatus according to any one of claims 12 to 23.

25. A computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed by a processor, the processor is enabled to implement the method according to any one of claims 1 to 11.

26. A computer program product, wherein the computer program product comprises computer program code, and when the computer program code is run on a computer, the computer is enabled to perform the method according to any one of claims 1 to 11.

27. A chip, wherein the chip comprises a circuit, and the circuit is configured to perform the method according to any one of claims 1 to 11.

Images