Automatic valet parking method, vehicle and storage medium

Abstract

The invention provides an automatic valet parking method, a vehicle and a storage medium, and relates to the technical field of vehicles, in the method, a first vehicle responds to a parking request sent by a user in a get-off area before the user queues to enter a parking lot, a vehicle wireless communication V2X formation function is triggered, and the V2X formation function enables the first vehicle and a second vehicle to form a vehicle team. And the first vehicle automatically follows the second vehicle in the motorcade so as to queue up to enter the parking lot. And after the motorcade enters the parking lot, the first vehicle drives to the target parking space to complete parking work according to the position information of the target parking space transmitted by the cloud. According to the scheme, the vehicles autonomously queue to enter the parking lot, drive to the distributed parking spaces and park, and the users leave the vehicles immediately, so that the waiting time of the users is greatly shortened, and the parking experience of the users is improved.

Description

Technical Field

[0001] This disclosure relates to the field of vehicle technology, and more specifically, to an automated valet parking method, a vehicle, and a storage medium. Background Technology

[0002] Automated valet parking technology allows the driver to completely leave the vehicle and trigger the vehicle to complete the parking process autonomously by locking the car.

[0003] Traditional automated valet parking technology requires users to drive their vehicles into the parking lot and then remain stationary while the vehicles find parking spaces on their own. This process still requires considerable effort from the user and is generally time-consuming.

[0004] There is an urgent need for solutions to address the current issues of low automation levels in valet parking technology, which negatively impact parking efficiency and user experience. Summary of the Invention

[0005] The purpose of this disclosure is to provide an automated valet parking method, vehicle, and storage medium to at least solve the aforementioned problems of low automation in valet parking technology, which affect parking efficiency and user experience.

[0006] To achieve the above objectives, the first aspect of this disclosure provides an automated valet parking method applied to a first vehicle, comprising:

[0007] In response to a user's parking request issued in the drop-off area before queuing to enter the parking lot, the vehicle-to-everything (V2X) platooning function is triggered; the V2X platooning function is used to platoon the first vehicle and the second vehicle using the V2X platooning function. Based on the V2X platooning function, the vehicle forms a convoy with the second vehicle and travels along the path to enter the parking lot. Send vehicle information to the cloud and receive the location information of the target parking space designated by the cloud for the first vehicle based on the vehicle information; After entering the parking lot, based on the location information of the target parking space, drive to the target parking space to complete the parking work.

[0008] Optionally, while driving on the path to enter the parking lot in a queue, the vehicle receives a cooperative obstacle avoidance command transmitted by the second vehicle to avoid obstacles. The cooperative obstacle avoidance command is generated by the second vehicle after identifying obstacles through environmental data collected by its sensors.

[0009] Optionally, the cooperative obstacle avoidance command includes obstacle type, relative position, movement trend, and suggested avoidance direction; The method further includes: In response to the cooperative obstacle avoidance command, the longitudinal speed and lateral offset of the first vehicle are adjusted in real time; when the obstacle disappears or the formation leaves the obstacle area, the preset formation spacing and / or the baseline driving trajectory are automatically restored.

[0010] Optionally, the method further includes: If an obstacle is detected by the camera, the radar is triggered to measure the distance. If the distance measurement result is less than the safety threshold, the first vehicle is controlled to switch to a preset circular detour path to avoid obstacles, so that it automatically returns to the baseline driving trajectory after avoiding obstacles.

[0011] Optionally, the method further includes: When driving on the path to enter the parking lot in a queue, in response to receiving queuing congestion information sent by the second vehicle, the distance to the vehicle in front is adjusted to a preset distance, which is used to prevent other vehicles from cutting in. The queuing congestion information is generated by the second vehicle based on perception data acquired by its radar and / or camera.

[0012] Optionally, the step of sending vehicle information to the cloud and receiving the location information of the target parking space designated by the cloud for the first vehicle based on the vehicle information includes: Send vehicle information to the cloud, the vehicle information including vehicle identification and destination information, which is used by the cloud to allocate and lock a target parking space for the first vehicle from the currently vacant parking spaces based on the virtual parking space database, based on the first vehicle's predetermined priority and / or the parking distance between the parking space and the first vehicle; Receive the location information of the target parking space sent from the cloud.

[0013] Optionally, the method further includes: After parking is completed, parking space status update information is sent to the cloud. The cloud uses the parking space image captured by the parking lot camera to verify whether the first vehicle has been parked in the target parking space. If the verification is successful, the cloud updates the status of the target parking space.

[0014] Optionally, the method further includes: Parking information is displayed to the user through an application on the terminal device. The parking information includes: vehicle queuing progress, target parking space locking status, and estimated parking completion time. After parking is completed, a parking completion notification is pushed to the terminal device, and the one-click pick-up function entry is displayed; In response to a user initiating a one-click pick-up request through the one-click pick-up function entry, the cloud sends pick-up route information to the first vehicle, and the vehicle drives to the passenger pick-up area according to the pick-up route information to complete the handover.

[0015] A second aspect of this disclosure provides a vehicle for performing the automated valet parking method provided by the first aspect and another possible implementation thereof.

[0016] A third aspect of this disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the automated valet parking method provided in the first aspect and another possible implementation thereof.

[0017] A fourth aspect of this disclosure provides an automated valet parking device, comprising: The platooning module is configured to trigger the V2X platooning function in response to a parking request issued by a user in the drop-off area before queuing to enter the parking lot; the V2X platooning function is used to platoon the first vehicle and the second vehicle using the V2X platooning function.

[0018] The following module is configured to form a convoy with the second vehicle based on the V2X platooning function and drive on the path to enter the parking lot while queuing.

[0019] The parking space retrieval module is configured to send vehicle information to the cloud and receive the location information of the target parking space assigned to the first vehicle by the cloud based on the vehicle information.

[0020] The parking module is configured to, after entering the parking lot, drive to the target parking space based on the location information of the target parking space to complete the parking task.

[0021] Through the above technical solution, the first vehicle responds to a user's parking request issued in the drop-off area before queuing to enter the parking lot, triggering the V2X platooning function. This V2X platooning function enables the first vehicle to form a platoon with the second vehicle. The first vehicle automatically follows the second vehicle in the platoon, thus queuing to enter the parking lot. After the platoon enters the parking lot, the first vehicle drives to the target parking space based on the location information of the target parking space transmitted from the cloud to complete the parking task. This solution enables vehicles to autonomously queue to enter the parking lot, drive to the assigned parking space, and park, allowing users to leave immediately after exiting the vehicle. Therefore, it greatly reduces user waiting time and improves the user parking experience.

[0022] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings: Figure 1 This is a flowchart illustrating an automated valet parking method according to an exemplary embodiment.

[0024] Figure 2 This is a schematic diagram of convoy cooperative obstacle avoidance according to an exemplary embodiment.

[0025] Figure 3 This is a flowchart illustrating independent obstacle avoidance by a vehicle according to an exemplary embodiment.

[0026] Figure 4 This is a flowchart illustrating a parking interaction scheme for a terminal device according to an exemplary embodiment.

[0027] Figure 5 This is a schematic diagram of a terminal device parking interaction scheme according to an exemplary embodiment.

[0028] Figure 6 The valet parking system architecture of an embodiment of this disclosure is shown.

[0029] Figure 7 This is a block diagram illustrating an automated valet parking device according to an exemplary embodiment.

[0030] Figure 8 This is a block diagram of a vehicle according to an exemplary embodiment. Detailed Implementation

[0031] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0032] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0033] It should be understood that the steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, the method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect.

[0034] The term "comprising" and its variations as used herein are open-ended inclusions, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Definitions of other terms will be given in the description below.

[0035] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0036] With the acceleration of urbanization, congestion at parking lots in shopping malls, residential areas, airports, and high-speed rail stations is becoming increasingly serious. As mentioned in the background, traditional valet parking solutions require users to drive their vehicles into the parking lot and wait for the vehicles to find parking spaces automatically. The drop-off point is actually near a parking space inside the parking lot. On the one hand, vehicles spend a lot of time searching for parking spaces; on the other hand, users spend a lot of time entering the parking lot when the entrance is congested. Therefore, current valet parking technology has a low degree of automation, still requiring users to spend too much time waiting for the vehicle to park automatically, resulting in low parking efficiency and a poor user experience.

[0037] Traditional valet parking technology requires vehicles to be inside a parking lot before it can park autonomously, failing to address the pain points of long queues, congested roads, and the time-consuming process of vehicles searching for parking spaces. This disclosure provides an automated valet parking method, vehicle, and storage medium. Before entering the parking lot, the user exits the vehicle, which then forms a convoy with other vehicles using V2X platooning. Dynamic platoon management technology allows the vehicle to automatically follow other vehicles, enabling it to autonomously manage the queuing process. Before parking, the vehicle receives a target parking space from the cloud and drives directly to that space to complete the parking maneuver. This high degree of automation allows users to leave the parking lot immediately after exiting their vehicle, saving them parking waiting time and providing a better user experience.

[0038] The methods provided in the embodiments of this disclosure will be described below.

[0039] Figure 1 This is a flowchart illustrating an automated valet parking method according to an exemplary embodiment. Figure 1 As shown, the automated valet parking method includes steps S11 to S14.

[0040] In step S11, in response to a user issuing a parking request in the drop-off area before queuing to enter the parking lot, the vehicle-to-everything (V2X) platooning function is triggered; the V2X platooning function is used to platoon the first and second vehicles using the V2X platooning function.

[0041] In this embodiment, the drop-off area is located before queuing to enter the parking lot. Taking an underground parking lot as an example, the drop-off area is located in front of the turnstile entrance. After a user gets off the vehicle in the drop-off area, they can send a parking request to the first vehicle through the terminal device's application. In response to the parking request, the first vehicle executes the subsequent valet parking process.

[0042] In some embodiments, a vehicle equipped with the valet parking function of this disclosure can push the location of the drop-off area to the user via a mobile terminal or vehicle-mounted system before entering a parking lot that supports the valet parking function of this disclosure, so that the user can drive the vehicle to the drop-off area.

[0043] In some embodiments, users input their destination via a mobile app, such as Area A on the second floor of a shopping mall, and select the dynamic queue mode on the app. When the user alights at the drop-off area, the V2X queuing function is triggered. No manual operation is required from the user; the first vehicle proactively requests a parking space and joins the dynamic queue.

[0044] In this step, after the user gets out of the car, the in-vehicle terminal can turn off the voice prompts and remain in silent mode.

[0045] In this step, the Vehicle to Everything (V2X) platooning function refers to the formation of a platoon of vehicles, and the exchange of information between vehicles, between vehicles and infrastructure, and between vehicles and the cloud through V2X communication.

[0046] In some embodiments, vehicles on the road between the drop-off area and the parking gate can form platoons. A first vehicle joins other vehicles on the road in the drop-off area, and then leaves the platoon after passing the parking gate. In this embodiment, the number of vehicles in a platoon can be limited. When the number of vehicles in a platoon reaches a preset value, the remaining vehicles are assigned to another platoon; that is, multiple platoons can run simultaneously on this road segment. Vehicles within each platoon can communicate with each other to ensure the platoon as a whole travels according to a preset platoon spacing and / or a baseline driving trajectory.

[0047] In other embodiments, the first vehicle does not leave the platoon after passing through the parking lot gate, so that the first vehicle can communicate with other vehicles in the platoon via V2X when driving to the target parking space and during the parking process.

[0048] In step S12, the vehicle forms a convoy with the second vehicle based on the V2X platooning function and drives on the path to enter the parking lot.

[0049] The second vehicle is the vehicle preceding the first vehicle, meaning the second vehicle is traveling in front of the first vehicle. However, the second and first vehicles can be non-adjacent vehicles; for example, there can be one or more vehicles not using V2X platooning between the first and second vehicles. A third vehicle can also be present between the first and second vehicles. If the third vehicle has joined the second vehicle's platoon, then the platoon formed after the first vehicle joins the platoon includes the first, second, and third vehicles. That is, this embodiment does not limit the first vehicle to forming a platoon with vehicles that are not in platooning.

[0050] Understandably, V2X platooning enables vehicles within a platoon to communicate with each other and automatically follow each other based on the information exchanged. In congested queuing areas at parking lot entrances, vehicles can drive autonomously without requiring users to wait in their cars.

[0051] In addition to eliminating the need for users to wait while queuing to enter the parking lot, the first vehicle can also automatically park in the target parking space without requiring users to wait for the vehicle to park near the space, as shown in steps S13 and S14 below.

[0052] In step S13, the vehicle information is sent to the cloud, and the location information of the target parking space designated by the cloud for the first vehicle based on the vehicle information is received.

[0053] Unlike the initial step where the first vehicle enters the parking lot and searches for an available space, this step involves the cloud assigning a target parking space to the first vehicle and transmitting its location information. Information transmission between the vehicle and the cloud can utilize V2X, which offers low latency and high reliability, ensuring the real-time and accurate delivery of the target parking space's location information. In this step, the cloud can dynamically plan the optimal target parking space based on multi-dimensional data such as real-time parking lot maps, parking space occupancy status, and vehicle dimensions. This involves interaction between the parking lot management unit and the cloud; the parking lot management unit can pre-synchronize the real-time occupancy status, dimensions, and access routes of all parking spaces in the parking lot to the cloud, allowing the cloud to match a suitable parking space for the first vehicle.

[0054] The target parking space can be the most suitable parking space found by the cloud based on a preset algorithm for the first vehicle, such as the vacant standard parking space closest to the entrance, or a widened parking space that fits the size of the vehicle, or a parking space with a charging station that also takes into account charging needs.

[0055] In step S14, after entering the parking lot, the vehicle drives to the target parking space and completes the parking operation based on the location information of the target parking space.

[0056] The location information transmitted to the cloud can include the path, parking space coordinates, and parking space number. The vehicle's infotainment system or navigation system uses this information to analyze and plan a parking path to the target parking space. The vehicle then drives to the target parking space according to the parking path.

[0057] In some embodiments, the parking path can be displayed on the user's mobile device so that the user can perceive the current parking progress and the expected parking location. The user can remotely view the real-time parking scene via the mobile device, and after confirming that the vehicle has arrived safely, the user can instruct the vehicle to be locked on the mobile device.

[0058] During parking, the vehicle's onboard sensors continuously scan for surrounding obstacles. Combined with high-precision maps and dynamically updated parking space status from the cloud, the system corrects path deviations and avoids obstacles in real time. In some embodiments, if the target parking space is detected to be temporarily occupied, the cloud can immediately reallocate a nearby vacant parking space and synchronize the new parking space path to the first vehicle.

[0059] Through the above technical solution, the first vehicle responds to a user's parking request issued in the drop-off area before queuing to enter the parking lot, triggering the V2X platooning function. This V2X platooning function enables the first vehicle to form a convoy with the second vehicle. The first vehicle automatically follows the second vehicle in the convoy, thus queuing to enter the parking lot. After the convoy enters the parking lot, the first vehicle drives to the target parking space based on the location information of the target parking space transmitted from the cloud to complete the parking task. This solution enables vehicles to autonomously queue to enter the parking lot, drive to the assigned parking space, and park, allowing users to leave immediately after exiting the vehicle. Therefore, it greatly reduces user waiting time and improves the user parking experience.

[0060] In some embodiments, the method further includes: while driving on a path to enter a parking lot, receiving a cooperative obstacle avoidance command transmitted by a second vehicle to achieve vehicle obstacle avoidance, the cooperative obstacle avoidance command being generated by the second vehicle after identifying obstacles through environmental data collected by its sensors.

[0061] like Figure 2 As shown, a convoy of vehicles 201 and 202 is formed. Vehicle 202 is the lead vehicle of vehicle 201, so it can detect obstacles 203 in advance. The second vehicle synchronizes the information about the presence of obstacles 203 with the other vehicles in the convoy. In this embodiment, vehicle 202 generates a cooperative obstacle avoidance command 204 based on the information about the presence of obstacles 203 and sends the command to vehicle 201, enabling vehicle 201 to anticipate and adjust its speed and / or path in advance to avoid sudden braking and collisions.

[0062] In an embodiment of convoy cooperative obstacle avoidance, the cooperative obstacle avoidance command may include obstacle type, relative position, movement trend, and suggested avoidance direction. After receiving the cooperative obstacle avoidance command, the first vehicle can perform multi-source fusion judgment by combining its own sensor data with a high-precision map to obtain the adjustment amount. As an example, in response to the cooperative obstacle avoidance command, the first vehicle adjusts its longitudinal speed and lateral offset in real time to avoid obstacles. When the obstacle disappears or the convoy leaves the obstacle area, the preset convoy spacing and / or baseline driving trajectory are automatically restored, allowing the convoy to return to a cooperative driving state. This technical solution can improve the safety and traffic efficiency of the first vehicle during automatic parking and has good adaptability to scenarios such as temporary congestion and pedestrian crossings. Especially in weak signal scenarios such as complex underground parking lots, it can still maintain convoy stability by relying on the low latency characteristics of V2X communication.

[0063] In some of these embodiments, such as Figure 3 As shown, the above method also includes steps S31 to S32.

[0064] Step S31: If an obstacle is detected by the camera, the radar is triggered to measure the distance.

[0065] Step S32: If the distance measurement result is less than the safety threshold, control the first vehicle to switch to the preset circular detour path to avoid obstacles, so that it automatically returns to the baseline driving trajectory after avoiding obstacles.

[0066] This embodiment corresponds to an emergency handling scenario where the first vehicle independently detects an obstacle. The first vehicle identifies the obstacle using multimodal sensors and, after confirming the risk through radar ranging, immediately initiates a circular detour strategy. The circular detour path can be dynamically generated by the onboard navigation system based on a high-precision map and real-time positioning. The first vehicle then returns to formation after bypassing the obstacle. This technical solution improves the first vehicle's ability to independently respond to environmental changes, especially demonstrating high obstacle recognition accuracy in complex weather conditions.

[0067] In some embodiments, the V2X platooning function also includes the ability for platoons to share congestion information. The method further includes: while driving on a path queuing to enter a parking lot, in response to receiving queuing congestion information from a second vehicle, adjusting the distance to the vehicle in front to a preset distance. This preset distance is used to prevent other vehicles from cutting in. The queuing congestion information is generated by the second vehicle based on perception data acquired by its radar and / or camera. Through this technical solution, platoons can proactively optimize their following strategies, maintaining a compact formation and continuous traffic flow in low-speed congestion scenarios, reducing energy consumption and driving discomfort caused by frequent starts and stops.

[0068] In some embodiments, step S13 above, sending vehicle information to the cloud and receiving the location information of the target parking space designated by the cloud for the first vehicle based on the vehicle information, includes: Send vehicle information to the cloud, including vehicle identification and destination information, which is used by the cloud to allocate and lock a target parking space for the first vehicle from the currently vacant parking spaces based on the first vehicle's predetermined priority and / or the parking distance between the first vehicle and the parking space; receive the location information of the target parking space sent by the cloud.

[0069] In this embodiment, the cloud generates a virtual parking space database based on parking map data provided by the parking management unit. The parking space status reported by vehicles and / or the parking management unit is used to update the virtual parking space database in real time. When the cloud receives the vehicle information of the first vehicle, it determines the currently vacant parking spaces based on the current virtual parking space database, and then, combined with the first vehicle's predetermined priority (such as reserved parking time) and / or parking distance, allocates and locks a suitable parking space for the first vehicle. Once locked, the parking space cannot be occupied by other vehicles, ensuring that the target parking space is still available when the first vehicle arrives. In addition, the cloud can also simultaneously push the target vehicle's location information, such as parking space coordinates, guidance route, and estimated parking time, to the vehicle's infotainment system or the user's terminal device. This technical solution significantly improves parking efficiency and user experience, avoiding unnecessary detours and waiting in the traditional parking search process.

[0070] In this embodiment, the cloud can also dynamically optimize the parking space allocation strategy based on historical parking data and real-time traffic flow prediction models, giving priority to ensuring the parking success rate of reserved vehicles during peak hours; at the same time, when the first vehicle approaches the target parking space, the vehicle-side perception system automatically verifies the actual status of the parking space. If an anomaly is detected, the cloud-based rescheduling mechanism is triggered to switch to an alternative parking space or indicate to the user that there are currently no available parking spaces.

[0071] In some embodiments, the method further includes: after parking is completed, sending parking space status update information to the cloud, which is used by the cloud to verify whether the first vehicle has been parked in the target parking space by combining the parking space image captured by the parking lot camera; if the verification is successful, the cloud updates the status of the target parking space.

[0072] In this embodiment, the cloud platform combines the parking space status update information reported by the first vehicle with the parking space image reported by the parking lot management unit to perform dual verification to ensure the accuracy of the status update. For example, when the first vehicle reports that it has parked in the target parking space, the cloud platform retrieves the latest image frame of the corresponding target parking space, uses an image recognition algorithm to determine whether the target parking space is occupied, and identifies whether the license plate number matches the reported vehicle identifier. If no vehicle is detected in the image or the license plate does not match, a manual review process can be triggered to prevent false reports from causing incorrect updates to the parking space status.

[0073] In some embodiments, the method can also support multi-vehicle collaborative parking scheduling. When adjacent vehicles in a fleet apply for parking spaces at the same time, the cloud generates an interference-free collaborative parking sequence based on factors such as vehicle size, parking direction, and path conflict probability. That is, vehicles in the same fleet will not conflict when parking, thereby improving valet parking efficiency.

[0074] In some of these embodiments, such as Figure 4 As shown, the method further includes steps S41 to S43.

[0075] In step S41, parking information is displayed to the user through the application of the terminal device. The parking information includes: vehicle queuing progress, target parking space locking status and estimated parking completion time.

[0076] In step S42, after parking is completed, a parking completion notification is pushed to the terminal device, and the one-click pick-up function entry is displayed.

[0077] For example, the mobile app supports voice announcement of the current location, such as parking space 08-12 on the second basement floor of Zone A in the shopping mall.

[0078] In step S43, in response to the user initiating a one-click pick-up request through the one-click pick-up function entry, the cloud is triggered to send pick-up route information to the first vehicle, and the vehicle is driven to the passenger pick-up area according to the pick-up route information to complete the handover.

[0079] For example, such as Figure 5 As shown, the terminal device is a mobile phone. The parking interface 501 of the phone displays a progress bar 502 showing the queuing progress of vehicles. The progress bar is refreshed in real time and includes dynamic icons. The target parking space is locked as a lock icon 503, indicating "locked". Next to the icon 503, the parking space number 504 and the distance to the parking space 505 can be displayed. The estimated parking completion time 506 is displayed as a countdown on the parking interface 501. The parking interface 501 also displays a one-click pick-up button 507, which the user can click to trigger a pick-up command.

[0080] In this way, users can monitor the entire parking process through their terminal devices, improving their experience using the valet parking function.

[0081] The following describes an automated valet parking method provided by an embodiment of this disclosure, in conjunction with the system architecture. Figure 6 The valet parking system architecture of an embodiment of this disclosure is shown. For example... Figure 6 As shown, the system includes a user APP, a cloud-based dispatch system (i.e., the cloud mentioned above), a vehicle-road-cloud collaborative platform, an in-vehicle terminal, a parking space sharing network, a dynamic queue management system, and a parking space retrieval system.

[0082] The user app supports parking space reservations, allowing users to book parking spaces directly through the app. The cloud platform determines reservation priority based on the user's reservation time. If there are insufficient parking spaces, the reservation fails, and the user app can push alternative options, such as showing other parking lot locations or suggesting parking during off-peak hours. Once the vehicle arrives at the drop-off point and the user alights, the user app displays parking information, as detailed below. Figure 4 And related explanations.

[0083] The cloud-based dispatch system establishes a virtual parking space database, integrates parking space sharing protocols, and provides vehicles with real-time available parking space resources.

[0084] The vehicle-road-cloud collaborative platform refers to the linkage between the roadside layer, cloud layer, and terminal layer. The roadside layer can deploy RSU nodes to collect traffic data and push it to vehicles (e.g., the first vehicle). The cloud layer integrates parking management data and provides parking space recommendation strategies. The terminal layer performs localized control, such as adjusting parking routes in response to sudden environmental changes. The linkage of the vehicle-road-cloud collaborative platform can use V2X communication. The cloud uses the MQTT protocol to transmit parking space status updates. Security mechanisms in this architecture include: vehicle identity authentication: based on BeiDou high-precision positioning and blockchain technology to prevent unauthorized vehicle takeover; data encryption: using the national cryptographic algorithm SM4 to encrypt communication content. Through the interconnection and interoperability of parking lot, vehicle, and cloud data, parking scheduling efficiency and parking space utilization are improved.

[0085] The vehicle-mounted terminal refers to the in-vehicle infotainment system mentioned above, which integrates sensors such as millimeter-wave radar and cameras, as well as V2X modules. The vehicle-mounted terminal also supports Roadside Unit (RSU) communication, enabling it to acquire data such as traffic light status, traffic congestion information, and pedestrian flow. The vehicle-mounted terminal incorporates multiple parking decision algorithms, such as a reinforcement learning-based dynamic following model that calculates safe following distance and optimal speed in real time; and an obstacle avoidance algorithm that, upon camera detection of a sudden obstacle, triggers millimeter-wave radar ranging and automatically switches to a circular detour path.

[0086] Parking space sharing networks are used by cloud-based scheduling systems to integrate available parking space data and lock in target parking spaces for vehicles.

[0087] The dynamic queue management system is used to keep vehicles in a queue with other vehicles in the queue before they enter the parking lot, based on V2X queuing functionality.

[0088] The parking space retrieval system dynamically allocates parking space resources through cloud scheduling. Vehicles do not need to make reservations in advance; they can lock in an available parking space and park immediately upon arrival.

[0089] The valet parking system provided in this disclosure is applicable to high-density parking scenarios such as shopping malls, office buildings, and scenic spots, including functions such as queuing in congested areas, controlling parking lot entrances and exits, and detouring through temporarily restricted areas. This system can be deeply integrated with car-sharing and smart city construction, breaking through the functional limitations of traditional valet parking systems in congested scenarios and achieving an upgrade from passive parking to proactive service.

[0090] Based on the same concept, embodiments of this disclosure also provide an automated valet parking device, such as... Figure 7 As shown, it includes: The platooning module 701 is configured to trigger the vehicle-to-everything (V2X) platooning function in response to a parking request issued by a user in the drop-off area before queuing to enter the parking lot; the V2X platooning function is used to platoon the first and second vehicles using the V2X platooning function.

[0091] The following module 702 is configured to form a convoy with a second vehicle based on V2X platooning functionality and drive along the path of queuing to enter the parking lot.

[0092] The parking space retrieval module 703 is configured to send vehicle information to the cloud and receive the location information of the target parking space assigned to the first vehicle by the cloud based on the vehicle information.

[0093] The parking module 704 is configured to drive to the target parking space and complete the parking task after entering the parking lot, based on the location information of the target parking space.

[0094] In some embodiments, the following module 702 is further configured to receive a cooperative obstacle avoidance command transmitted by a second vehicle while driving on a path queuing to enter a parking lot, so as to enable the vehicle to avoid obstacles. The cooperative obstacle avoidance command is generated by the second vehicle after identifying obstacles through environmental data collected by its sensors.

[0095] In some embodiments, the following module 702 is also configured to adjust the longitudinal speed and lateral offset of the first vehicle in real time in response to a cooperative obstacle avoidance command; and to automatically restore the preset formation spacing and / or baseline driving trajectory when the obstacle disappears or the formation leaves the obstacle area.

[0096] In some embodiments, the system also includes a vehicle obstacle avoidance module, configured to trigger radar to measure distance if an obstacle is detected by the camera; if the distance measurement result is less than a safety threshold, the system controls the first vehicle to switch to a preset circular detour path to avoid the obstacle, so that the vehicle automatically returns to the baseline driving trajectory after obstacle avoidance.

[0097] In some embodiments, the following module 702 is further configured to, when driving on a path queuing to enter a parking lot, adjust the distance to the vehicle in front to a preset distance in response to receiving queuing congestion information sent by a second vehicle. The preset distance is used to prevent other vehicles from cutting in. The queuing congestion information is generated by the second vehicle based on perception data acquired by its radar and / or camera.

[0098] In some embodiments, the parking space retrieval module 703 is further configured to send vehicle information to the cloud, the vehicle information including: vehicle identification and destination information, for the cloud to allocate and lock a target parking space for the first vehicle from currently vacant parking spaces based on the virtual parking space database, based on the first vehicle's predetermined priority and / or the parking distance between the parking space and the first vehicle; and to receive the location information of the target parking space sent by the cloud.

[0099] In some embodiments, the parking module 704 is further configured to send parking space status update information to the cloud after completing the parking work, so that the cloud can verify whether the first vehicle has been parked in the target parking space by combining the parking space image captured by the parking lot camera; if the verification is successful, the cloud updates the status of the target parking space.

[0100] In some embodiments, a display module is also included, configured to display parking information to the user via an application on a terminal device. The parking information includes: vehicle queuing progress, target parking space locking status, and estimated parking completion time. After parking is completed, a parking completion notification is pushed to the terminal device, and a one-click pick-up function entry is displayed. In response to the user initiating a one-click pick-up request through the one-click pick-up function entry, the cloud is triggered to send pick-up route information to the first vehicle, and the vehicle is driven to the pick-up area according to the pick-up route information to complete the handover.

[0101] Figure 8 This is a block diagram illustrating a vehicle according to an exemplary embodiment. (e.g.) Figure 8 As shown, the vehicle 80 includes a drive system 801, a body 802, a sensor module 803, a communication module 804, a processor 805, a memory 806, and a chassis 807.

[0102] The drive system 801 is used to control the vehicle's movement.

[0103] The sensor module 803 includes sensors, radar, etc., and is used to acquire data such as the vehicle's current speed, environmental images, and radar ranging results.

[0104] The communication module 804 is responsible for data transmission between the vehicle and external networks (such as the cloud or fleet).

[0105] The processor 805 and the memory 806 are communicatively connected. The memory 806 stores computer programs that can be executed by the processor 805, such as obstacle avoidance algorithms. In this embodiment, the memory 806 may be a solid-state memory (e.g., flash memory) or random access memory (RAM) for storing programs and intermediate calculation results.

[0106] The processor 805 is the core component of the vehicle controller, responsible for processing and executing various instructions, as well as calculating and controlling data. When the processor 805 executes a computer program, it implements the vehicle control method provided in this disclosure embodiment. The processor 805 can be a general-purpose processor, a dedicated digital signal processor (DSP), or other suitable processor. As an example, the vehicle 80 includes a SoC (System on Chip) chip, which integrates the processor 805, memory 806, peripheral interfaces, dedicated function modules, and software firmware, forming a microelectronic system with complete system functions.

[0107] The body 802 and chassis 807 are essential hardware structures for the vehicle, and will not be elaborated upon here.

[0108] Based on the same technical concept, embodiments of this disclosure also provide a computer-readable storage medium having a computer program stored thereon, which, when executed, implements the method shown in any embodiment of this disclosure.

[0109] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0110] It should also be noted that the various specific technical features described in the above embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0111] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. An automatic valet parking method characterized by, Applied to a first vehicle, comprising: In response to a user issuing a parking request at a drop-off area before queuing into a parking lot, triggering a vehicle-to-everything (V2X) platooning function; the V2X platooning function is used to platoon the first vehicle and a second vehicle using the V2X platooning function; Based on the V2X platooning function and the second vehicle forming a vehicle fleet, driving on a path of queuing into a parking lot; Sending self-vehicle information to the cloud, receiving position information of a target parking space designated by the cloud for the first vehicle based on the self-vehicle information; After entering the parking lot, based on the position information of the target parking space, driving to the target parking space to complete the parking work.

2. The automatic valet parking method according to claim 1, characterized in that, The method further comprises: When driving on the path of queuing into the parking lot, receiving a cooperative obstacle avoidance instruction transmitted by the second vehicle to realize vehicle obstacle avoidance, the cooperative obstacle avoidance instruction being generated by the second vehicle after identifying an obstacle through environmental data collected by its sensor.

3. The automatic valet parking method according to claim 2, characterized in that, The cooperative obstacle avoidance instruction includes obstacle type, relative position, motion trend, and recommended avoidance direction; The method further comprises: In response to the cooperative obstacle avoidance instruction, adjusting the longitudinal speed and lateral offset of the first vehicle in real time; when the obstacle disappears or the platoon is away from the obstacle area, automatically restoring the preset platoon spacing and / or the reference driving trajectory.

4. The automatic valet parking method according to any one of claims 1 to 3, characterized in that, The method further comprises: If an obstacle is identified through a camera, triggering a radar to measure the distance; If the measurement result is less than a safety threshold, controlling the first vehicle to switch to a preset circular bypass path to avoid the obstacle, so that the first vehicle automatically returns to the reference driving trajectory after avoiding the obstacle.

5. The automatic valet parking method according to claim 1, characterized by, The method further comprises: When driving on the path of queuing into the parking lot, in response to receiving queuing congestion information sent by the second vehicle, adjusting the distance to the front vehicle to a preset distance, the preset distance being used to prevent other vehicles from cutting in, the queuing congestion information being generated by the second vehicle based on perception data obtained by its radar and / or camera.

6. The automatic valet parking method according to claim 1, characterized by, The method further comprises: Sending self-vehicle information to the cloud, the self-vehicle information including: vehicle identification and destination information, for the cloud to allocate and lock a target parking space for the first vehicle from currently vacant parking spaces in the parking lot based on a virtual parking space database, based on the predetermined priority of the first vehicle and / or the parking distance between the first vehicle and the parking space; Receiving position information of the target parking space sent by the cloud.

7. The automatic valet parking method according to claim 1, characterized by, The method further comprises: After completing the parking work, sending parking space status update information to the cloud, for the cloud to verify whether the first vehicle has parked in the target parking space in combination with parking space images captured by a parking lot camera; if the verification is passed, the cloud updates the status of the target parking space.

8. The automatic valet parking method according to claim 1, characterized by, The method further comprises: Displaying parking information to the user through an application program of a terminal device, the parking information including: vehicle queuing progress, target parking space locking status, and estimated parking completion time; After completing the parking work, pushing a parking completion notification to the terminal device and displaying a one-key pick-up function entry; In response to a user initiating a one-key pick-up request through the one-key pick-up function portal, triggering the cloud to send pick-up path information to the first vehicle, and driving to the pick-up area according to the pick-up path information to complete the handover work.

9. A vehicle characterized by comprising: A method for performing the automatic valet parking method of any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, A computer program stored thereon, which, when executed, implements the automatic valet parking method of any one of claims 1 to 8.

Images