Vehicle loading control method and device, vehicle and storage medium

Abstract

The invention provides a vehicle loading control method and device, a vehicle and a storage medium, and relates to the field of vehicle control. And identifying a target user with the riding intention and the historical riding credit value passing the riding credit verification according to the gesture action in the driving environment. And determining the parking position of the vehicle according to the current position of the target user. And obtaining service authorization verification information after the vehicle is driven to the parking position. And according to the service authorization verification information, determining whether the target user can pay the loading task or not. If yes, after the target user gets on the vehicle, a multi-mode signal output by the target user is obtained, and the final position is determined; and executing the loading task based on the final position. The temporary and random street riding requirements of the user can be met, and the service scene is expanded. And in combination with gesture actions and riding credit verification, the user really having the riding intention is identified from a complex driving environment. Under the condition that no pre-associated order exists, operation safety and financial closed loop are ensured through service authorization verification information.

Description

Technical Field

[0001] This application relates to the field of vehicle control, and in particular to a method, apparatus, vehicle, and storage medium for vehicle loading control. Background Technology

[0002] With the rapid development of autonomous driving technology, robotaxi, with its advantages of low operating costs and high safety, will become an important form of smart mobility in the future. Currently, the main operating model of robotaxi is ride-hailing, where users place orders through mobile applications, and after receiving the order, the robotaxi drives to the starting point specified in the order to pick up the user and take them to the destination specified in the order.

[0003] However, this "car-to-point" operating model is rigid and cannot meet users' temporary and random street ride needs, thus limiting the service scenarios for autonomous taxis. Summary of the Invention

[0004] In view of this, this application provides a vehicle pick-up control method, the method comprising: Identify target users in the driving environment; the target users are those whose intention to take a ride is determined based on their gestures and whose historical ride credit scores have passed the ride credit verification. Determine the vehicle's parking location based on the target user's current location; After the vehicle arrives at the parking location, service authorization verification information is obtained; Based on the service authorization verification information, determine whether the target user is eligible to pay for this pickup task; If so, after the target user boards the vehicle, the multimodal signal output by the target user is acquired; based on the multimodal signal, the destination location of the current pick-up and drop-off task is determined; and based on the destination location, the current pick-up and drop-off task is executed.

[0005] Optionally, identifying the target user in the driving environment includes: Acquire user image sequences captured by the visual sensor; Based on the user image sequence, identify the hand movement trajectories of all users in the user image sequence; Determine whether all users include candidate users whose hand movement trajectories meet the characteristics of soliciting passengers; the characteristics of soliciting passengers include at least one of the following: the number of hand movements within a first preset time period is greater than a preset number, and the amplitude of hand movements is greater than a preset amplitude; If included, then collect the biometric data of the candidate users; based on the biometric data, determine the target users from the candidate users whose historical travel credit values ​​have passed the travel credit verification.

[0006] Optionally, when there is only one candidate user, based on the biometric data, the target user whose historical ride credit score has passed the ride credit verification is determined from the candidate user, including: Determine whether the biometric data is valid; If the data is not valid, the process of collecting the biometric data of the candidate user will be repeated during the vehicle's operation, and subsequent steps will be executed until the preset conditions are met. If the data is valid, proceed with the following steps: Obtain a pre-constructed mapping relationship; the mapping relationship is the correspondence between a user's unique identifier and their historical ride credit value; the historical ride credit value is the ratio of the number of historical rides to the number of historical ride solicitations; Based on the biometric data and the mapping relationship, the target ride credit score corresponding to the candidate user is determined; If the target ride credit score is greater than the preset credit score, then the candidate user will be selected as the target user.

[0007] Optionally, when there are multiple candidate users, based on the biometric data, target users whose historical ride credit scores have passed the ride credit verification are determined from the candidate users, including: During the process of the vehicle traveling to the designated location, it is determined whether there is a candidate user among the candidate users whose target ride credit score is greater than the preset credit score; the designated location is the location of the candidate user farthest from the vehicle; If it exists, perform the following steps: When there is only one candidate user, the candidate user shall be used as the target user. When there are multiple candidate users, each candidate user is scored to determine the target user from among them.

[0008] Optionally, scoring each of the candidate users to determine the target user from among the candidate users includes: Based on the target number of hand movements and the target amplitude of the selected users within a second preset time period, a ride intention score is determined; the ride intention score is positively correlated with both the target number of hand movements and the target amplitude of the hand movements. A distance score is determined based on the distance between the candidate user and the vehicle; the distance score is negatively correlated with the distance. The user rating corresponding to the candidate user is determined based on the ride intention score, the distance score, and the target ride credit score; The candidate user with the highest user rating will be selected as the target user.

[0009] Optionally, determining the vehicle's parking location based on the target user's current location includes: The current location is mapped onto a map to obtain the designated area where the target user is located; the designated area is the area formed by the locations on the vehicle's current driving road and at a preset distance from the current location; Determine whether the designated area includes a parking area; If included, the location closest to the current location within the specified area will be taken as the docking location; If not included, the nearest available parking area to the current location is taken as the parking location; guidance information is generated based on the parking location and the current location, and the guidance information is output through the guidance device on the vehicle.

[0010] Optionally, the service authorization verification information includes the biometric data of the target user; determining whether the target user is eligible to pay for the pickup task based on the service authorization verification information includes: A biometric template is generated based on the biometric data; the biometric template includes at least one feature set extracted from the biometric data. The system determines whether a template with a similarity greater than a preset similarity exists in the user information database, thereby determining whether the target user has a payment account; the user information database is used to store user registration information, which includes biometric templates and corresponding payment accounts; If such a user exists, then it is determined that the target user is capable of paying for this pickup task.

[0011] Optionally, the service authorization verification information may also include the payment token presented by the target user; if it does not exist, the method may further include: Generate a prompt message to prompt the target user to present a payment token; output the prompt message through the prompting device on the vehicle; Determine whether the payment token has been collected within a third preset time period from the time the prompt message is output; If the payment token is collected, it is determined that the target user can pay for the current pickup task.

[0012] This application also provides a vehicle pick-up control device, the device comprising: The target user identification module is used to identify target users in the driving environment; the target user is a user whose intention to take a ride is determined based on gestures and whose historical ride credit value has passed the ride credit verification. The docking location determination module is used to determine the docking location based on the current location of the target user; The verification information acquisition module is used to acquire service authorization verification information after the vehicle has driven to the parking location; The service authorization verification module is used to determine whether the target user can pay for this pickup task based on the service authorization verification information; if so, the pickup module is triggered. The pick-up module is used to acquire the multimodal signal output by the target user after the target user boards the vehicle; determine the destination location of the current pick-up task based on the multimodal signal; and execute the current pick-up task based on the destination location.

[0013] This application also provides a vehicle, including: Memory, used to store computer programs; A processor, used to execute the computer program to implement the steps of any of the above-described vehicle pick-up control methods.

[0014] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described vehicle pick-up control methods.

[0015] In summary, this application provides a vehicle pick-up control method, apparatus, vehicle, and storage medium. It identifies a target user in the driving environment by recognizing their intention to ride and whose historical ride credit score has passed ride credit verification based on gestures. The vehicle's stopping location is determined based on the target user's current location. Service authorization verification information is acquired after the vehicle arrives at the stopping location. Based on the service authorization verification information, it is determined whether the target user can pay for the pick-up task. If so, after the target user boards the vehicle, the multimodal signal output by the target user is acquired to determine the destination location; the pick-up task is then executed based on the destination location.

[0016] As can be seen, this application can meet users' temporary and random street ride needs, expanding the service scenarios of autonomous taxis. Furthermore, by combining gesture control and ride credit verification, it accurately identifies users with genuine ride intentions in complex driving environments. Even without pre-assigned orders, it determines whether the target user can pay for the ride before allowing them to board and executing the ride, ensuring operational safety and financial closure. Attached Figure Description

[0017] Figure 1A flowchart illustrating a vehicle pick-up control method provided in this application; Figure 2 A schematic diagram of the first principle of a vehicle pick-up control method provided in this application; Figure 3 A schematic diagram of a driving environment provided for this application; Figure 4 A second schematic diagram of a vehicle pick-up control method provided in this application; Figure 5 A first structural schematic diagram of a vehicle pick-up control device provided in this application; Figure 6 This is a second structural schematic diagram of a vehicle pick-up control device provided in this application. Detailed Implementation

[0018] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0019] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0020] Please refer to Figure 1 , Figure 1 A flowchart illustrating a vehicle pick-up control method provided in this application, the method comprising: S1: Identify target users in the driving environment; target users are those whose intention to take a ride is determined based on gestures and whose historical ride credit scores have passed the ride credit verification.

[0021] To meet users' temporary and random street ride needs, it is first necessary to identify users with genuine ride intentions from the complex driving environment. Considering that users with ride intentions typically use gesturing gestures (such as raising and waving their arms) to attract vehicles, this application determines whether a user has ride intentions based on their gestures, thereby initially filtering out irrelevant users in the driving environment who do not have ride intentions.

[0022] In addition to this, to verify the credibility of a user's travel intentions, this application also verifies the user's historical travel credit score. The historical travel credit score is used to characterize a user's past travel credit history. When the historical travel credit score passes the verification, the user's travel intentions are considered credible, and the user can be picked up. When the historical travel credit score fails the verification, the user is considered to pose a risk of not being picked up (e.g., repeatedly soliciting rides but not taking them), and the user will not be considered a target user, i.e., the user will not be picked up.

[0023] This application combines gestures and historical ride credit scores to identify target users with genuine and credible ride intentions in complex driving environments, laying the foundation for the smooth completion of subsequent pick-up tasks and ensuring the safety and reliability of operations.

[0024] The specific implementation methods for determining the intention to take a ride based on gestures and verifying the ride credit score based on historical ride credit scores will be described in detail in subsequent embodiments, and will not be repeated here.

[0025] S2: Determine the vehicle's parking location based on the target user's current location.

[0026] After identifying the target user, the vehicle needs to be driven to the designated parking location to pick them up. Considering the complex parking environment along the route, if the target user's current location does not allow parking, the parking location needs to be replanned to ensure the compliance and safety of the vehicle's journey while picking up the user.

[0027] Based on this, this application determines the vehicle's parking location according to the target user's current location. For example, it first determines whether parking is permitted at the target user's current location; if parking is permitted, the current location is directly used as the parking location, and the vehicle travels to the target user's current location to pick up the user; if parking is not permitted at the current location, other nearby permitted parking locations are determined, and the vehicle and the target user travel together to the parking location to successfully pick up the target user.

[0028] The specific implementation method for determining the parking location will be described in detail in subsequent embodiments, and will not be repeated here.

[0029] S3: After the vehicle arrives at the parking location, obtain service authorization verification information.

[0030] S4: Based on the service authorization verification information, determine whether the target user can pay for this pickup task; if so, proceed to step S5.

[0031] For users' temporary and random street ride needs, there is no pre-established order association between the user and the ride request. To achieve a closed-loop financial system and ensure operational safety, this application obtains service authorization verification information after the vehicle arrives at the designated stop. Only when the service authorization verification information confirms that the target user can pay for the ride will the subsequent steps of picking up the target user and executing the ride request proceed.

[0032] This application does not specifically limit the type of service authorization verification information or the specific implementation of determining whether the target user can pay for the ride-hailing service. For example, biometric data that can characterize the user's identity can be used as service authorization verification information. Based on the biometric data, it can be determined whether a payment account linked to the target user exists, thereby determining whether the user can pay for the ride-hailing service electronically; or, it can be determined whether the user has cash on hand, thereby determining whether the user can pay for the ride-hailing service in cash using a self-service payment device installed in the vehicle. Subsequent embodiments will describe the above process in detail, and will not be repeated here.

[0033] S5: After the target user boards the vehicle, acquire the multimodal signal output by the target user; determine the destination location of this pick-up and drop-off task based on the multimodal signal; and execute the pick-up and drop-off task based on the destination location.

[0034] After confirming that the target user can pay for the ride, the vehicle picks up the user. For example, after confirming that the target user can pay for the ride, a door opening control signal is generated; this signal is then sent to the door lock controller to activate the door lock controller and open the door. In short, confirming that the target user can pay for the ride serves as the sole proof of payment, ensuring successful payment for the ride, achieving a closed-loop financial system, and ensuring operational safety.

[0035] After the target user boards the vehicle, the system acquires the multimodal signal output by the target user and determines the destination location based on the multimodal signal. For example, it acquires the target user's voice (e.g., "I want to go to Terminal 3 of Beijing Capital International Airport") and identifies the destination location (the destination location is Terminal 3 of Beijing Capital International Airport); or it acquires the destination location entered by the target user on the vehicle's touchscreen.

[0036] Once the destination of the pickup / transfer mission is determined, the mission can be executed based on that destination. This application does not specify the exact process for executing the mission. For example, a route is planned based on the vehicle's current location and the destination; the vehicle travels along the planned route and begins recording the travel time and mileage until the destination is reached; the amount due for payment is determined based on the travel time and mileage; the amount is deducted from the target user's payment account or settled in cash using the vehicle's self-service payment device. At this point, the vehicle has transported the user to the destination, completed the settlement, and the pickup / transfer mission is complete.

[0037] In addition, please refer to Figure 2 , Figure 2 This is a schematic diagram illustrating the first principle of a vehicle pick-up control method provided in this application. Figure 2 As shown, a task status switching mechanism can also be set for the vehicle, allowing it to better adapt to dynamic changes in the journey. Specifically, during the vehicle's operation, the current task status is acquired at preset time intervals; the task status includes route navigation status and empty cruising status. If the current task status is route navigation status, the vehicle continues to perform the current pick-up task; if the current task status is empty cruising status, it proceeds to the step of identifying the target user in the driving environment and executes subsequent steps. Furthermore, after the target user boards the vehicle, the vehicle's task status is updated to route navigation status; after the current pick-up task is completed, the task status is switched from route navigation status to empty cruising status.

[0038] In summary, this application identifies target users in the driving environment by determining their intention to ride based on gestures and verifying their historical ride credit scores, laying the foundation for the successful completion of pick-up and drop-off tasks. Furthermore, even without a pre-order, after confirming that the target user can pay for the pick-up and drop-off task based on the obtained service authorization verification information, the application picks up the target user and executes the task, thus binding the identified target user to a complete pick-up and drop-off service, ensuring operational safety and financial closure. Therefore, this application can meet users' temporary and random street ride needs, expanding the service scenarios for autonomous vehicles.

[0039] Based on the above embodiments: The process of identifying target users in a driving environment will be explained below.

[0040] As an optional embodiment, identifying the target user in the driving environment includes: Acquire user image sequences captured by the visual sensor; Based on user image sequences, identify the hand movement trajectories of all users in the user image sequences; Determine whether there are candidate users whose hand movement trajectories meet the characteristics of soliciting passengers among all users; the characteristics of soliciting passengers include at least one of the following: the number of hand swings within a first preset time period is greater than a preset number, and the swing amplitude of the hand movement trajectory is greater than a preset amplitude; If included, biometric data of candidate users are collected; based on the biometric data, target users whose historical ride credit scores have passed the ride credit verification are identified from the candidate users.

[0041] like Figure 2 As shown, in this embodiment, the user image sequence is first acquired by the visual sensor. This embodiment does not specifically limit the type of visual sensor. For example, the visual sensor is a wide-angle camera located on the outside of the vehicle; correspondingly, the user image sequence is a video stream acquired by the wide-angle camera.

[0042] Considering that users intending to board a vehicle typically make soliciting gestures (such as raising and waving their arms) to attract passengers, this embodiment pre-sets soliciting features based on these characteristics. Specifically, these features include at least one of the following: the number of hand movements within a first preset duration is greater than a preset number of movements, and the amplitude of the hand movements is greater than a preset amplitude. The first preset duration, the preset number of movements, and the preset amplitude can all be set according to actual needs, and this embodiment does not impose any particular limitations on them. By using at least one of the number of hand movements and the amplitude of the hand movements, irrelevant users making malicious or non-directional disruptive gestures are filtered out, ensuring the safety and reliability of vehicle operation.

[0043] Based on the above, after acquiring the user image sequence, the hand movement trajectories of all users in the user image sequence are identified; users whose hand movement trajectories meet the above-mentioned characteristics of soliciting passengers are selected as candidate users. This embodiment does not specifically limit the specific implementation method for identifying candidate users. For example, a computer vision-based recognition model can be pre-built; the video stream captured by a wide-angle camera can be input into the recognition model so that the model can identify hand movement trajectories that meet the characteristics of soliciting passengers from the video stream, and select the users corresponding to these hand movement trajectories as candidate users.

[0044] Thus, this embodiment identifies candidate users with the intention to ride in the vehicle from the vehicle's driving environment.

[0045] Furthermore, this embodiment confirms the credibility of the candidate user's travel intention, that is, it verifies the candidate user's historical travel credit score; the candidate user who passes the travel credit verification is selected as the target user. Specifically, this embodiment collects the candidate user's biometric data to determine the candidate user's historical travel credit score based on the biometric data and to perform travel credit verification. The aforementioned biometric data includes, but is not limited to, facial, iris, voice, and fingerprint data, which are uniquely associated with the user to improve the reliability of travel credit verification.

[0046] In addition, the quality of the collected biometric data can be improved by using a telephoto camera installed on the vehicle to collect the user's biometric data.

[0047] Considering that in practical applications, there may be only one candidate user with the intention to take a ride in the driving environment, or there may be multiple candidate users with the intention to take a ride simultaneously, the process of identifying the target user from the candidate users will be explained below for both scenarios.

[0048] As an optional embodiment, when there is only one candidate user, the target user whose historical ride credit score has passed the ride credit verification is determined from the candidate users based on biometric data, including: Determine whether the biometric data is valid; If the data is not valid, the system will return to the step of collecting the candidate user's biometric data while the vehicle is in motion, and execute subsequent steps until the preset conditions are met. If the data is valid, proceed with the following steps: Obtain the pre-built mapping relationship; the mapping relationship is the correspondence between the user's unique identifier and the historical ride credit value; the historical ride credit value is the ratio of the number of historical rides to the number of historical ride solicitations; Based on biometric data and mapping relationships, the target ride credit score corresponding to the candidate user is determined; If the target user's credit score is greater than the preset credit score, the candidate user will be selected as the target user.

[0049] In this embodiment, a mapping relationship is pre-established, which is the correspondence between a user's unique identifier and their historical ride credit score. The mapping relationship can be stored in the cloud or on the vehicle; this embodiment does not impose any particular limitation on this and can be set according to actual needs.

[0050] The aforementioned unique user identifier is determined based on the user's biometric data. This embodiment does not specifically limit the method for determining the unique user identifier. For example, the collected user's facial image can be used as biometric data; the hash value generated based on the facial image can be used as the unique user identifier.

[0051] The aforementioned historical ride credit score is determined based on the number of historical rides and the number of historical solicitations. For example, the historical ride credit score is obtained by dividing the number of historical rides by the number of historical solicitations. A higher historical ride credit score indicates a more reliable user's intention to ride; conversely, a lower score indicates a less reliable user's intention. For example, users who solicit rides multiple times but do not take them will have a lower historical ride credit score. In short, using the ratio of historical rides to historical solicitations as the historical ride credit score allows for more accurate screening of reliable target users from among the many pedestrians in the driving environment.

[0052] Based on this, this embodiment first determines whether the collected biometric data is valid. This embodiment does not specifically limit the method for determining valid data. For example, when using facial images as biometric data, the validity of the facial image is determined based on whether its resolution meets resolution requirements, its clarity meets clarity requirements, and whether the area of ​​facial occlusion is within a preset range.

[0053] If the collected biometric data is valid, the target ride credit value for the candidate user is determined based on the biometric data and the pre-built mapping relationship. For example, firstly, a candidate user identifier is generated based on the collected biometric data; then, the historical ride credit value corresponding to the candidate user identifier in the mapping relationship is used as the target ride credit value for that candidate user.

[0054] As mentioned earlier, the historical ride credit score is the ratio of the number of historical rides to the number of historical solicitations; the higher the historical ride credit score, the more credible the user's ride intention. Therefore, if the target ride credit score is greater than the preset credit score, the candidate user is selected as the target user. The preset credit score can be set according to actual needs, and this embodiment does not impose any particular limitation on it.

[0055] It should also be noted that if the target ride credit value for a candidate user does not exist in the mapping relationship, it indicates that the candidate user may be a new user. In this case, the candidate user can also be used as the target user, and the user's unique identifier and historical ride credit value should be added to the mapping relationship.

[0056] If the collected biometric data is invalid, the system continues to collect biometric data of candidate users while the vehicle is in motion, and performs subsequent steps to determine whether the biometric data is valid, until a preset condition is met. As an optional embodiment, the preset condition is that the actual collection time reaches a preset duration, or the distance between the vehicle and the candidate user is less than a preset distance. The actual collection time is the time from the first collection of the candidate user's biometric data to the current moment. The preset duration can be the ratio between the distance between the vehicle and the candidate user and the vehicle's speed. The preset distance can be set according to actual needs; this embodiment does not impose any particular limitation.

[0057] This concludes the process of determining whether a candidate user is the target user when there is only one candidate user. By using the candidate user's biometric data and pre-established relationships, a reliable and efficient verification method is used to verify the candidate user's travel credit.

[0058] The following explains the process of determining the target user from among multiple candidate users.

[0059] As an optional embodiment, when there are multiple candidate users, target users whose historical ride credit scores have passed the ride credit verification are determined from the candidate users based on biometric data, including: During the process of the vehicle traveling to the designated location, it is determined whether there are any candidate users among the candidate users whose target ride credit score is greater than the preset credit score; the designated location is the location of the candidate user farthest from the vehicle; If it exists, perform the following steps: When there is only one candidate user, the candidate user will be used as the target user. When there are multiple candidate users, each candidate user is scored in order to determine the target user from among them.

[0060] In this embodiment, the location of the candidate user furthest from the vehicle is designated as the specified location. As the vehicle travels towards the specified location, a ride credit verification is performed on each candidate user, specifically to determine if there are any candidate users whose target ride credit score is greater than a preset credit score. The process for determining the target ride credit score for each candidate user can be referred to the above embodiment and will not be repeated here.

[0061] like Figure 3 As shown, Figure 3This application provides a schematic diagram of a driving environment. In the current driving environment, three users (user A, user B, and user C) exist within the field of view of the vehicle's visual sensors, with user C being the furthest from the vehicle. The location of user C can then be designated as the specified location. As the vehicle travels to user C's location, biometric data of the three users is simultaneously collected. Following the description in the preceding embodiments, the biometric data is used to determine whether there is a candidate user among the candidate users whose target ride credit score is greater than a preset credit score.

[0062] If only one candidate user exists, that user is directly selected as the target user. If multiple candidate users exist, the target user needs to be further selected from among them. This embodiment determines the target user by scoring each candidate user. For example, a comprehensive score is given based on the strength of the user's intention to take the ride, the credibility of that intention, and the convenience of vehicle access. The scoring process is explained below.

[0063] As an optional embodiment, scoring each candidate user to determine the target user from among the candidate users includes: The ride intention score is determined based on the target number of swings and the target swing amplitude within a second preset time period according to the hand movement trajectory of the candidate user; the ride intention score is positively correlated with both the target number of swings and the target swing amplitude. A distance score is determined based on the distance between the candidate user and the vehicle; the distance score is negatively correlated with the distance. Based on the ride intention score, distance score, and target ride credit score, the user score corresponding to the candidate user is determined; The candidate user with the highest user rating is selected as the target user.

[0064] Considering that the stronger a user's intention to travel, the higher the frequency and amplitude of their hand movements, this embodiment first determines the travel intention score based on the target number of hand movements and the target amplitude within a second preset time period according to the candidate user's hand movement trajectory. The travel intention score is positively correlated with both the target number of hand movements and the target amplitude. This embodiment does not specifically limit the specific implementation method for determining the travel intention score. For example, after normalizing the target number of hand movements and the target amplitude, a weighted sum can be performed using their respective preset weights to obtain the aforementioned travel intention score.

[0065] The closer the vehicle is to the user, the easier it is for the vehicle to pick up the user. Therefore, in this embodiment, a distance score is determined based on the distance between the candidate user and the vehicle, and the distance score is negatively correlated with the distance.

[0066] Subsequently, the user score corresponding to the candidate user is determined by comprehensively considering the ride intention score, the target ride credit score, and the distance score. This embodiment does not specifically limit the specific implementation method for determining the user score. In one optional embodiment, a preset score weight can be set for each of the ride intention score, the target ride credit score, and the distance score based on their respective contributions (or importance) in determining whether a user is a target user; the higher the contribution, the larger the corresponding preset score weight. Using these preset score weights, the ride intention score, the target ride credit score, and the distance score are weighted and summed to determine the user score. In summary, the user score comprehensively reflects the strength of the user's ride intention, the credibility of that intention, and the convenience of vehicle pick-up, ensuring the reliability and accuracy of the selected target users.

[0067] Thus, in all situations, accurate identification of target users in the driving environment is achieved, laying the foundation for the smooth execution of subsequent pick-up tasks.

[0068] The process of determining the parking location of a vehicle will be explained below.

[0069] As an optional embodiment, determining the vehicle's parking location based on the target user's current location includes: Map the current location onto the map to obtain the specified area where the target user is located; the specified area is the area formed by the locations on the vehicle's current driving road and at a preset distance from the current location; Determine whether the designated area includes a parking area; If included, the location closest to the current location within the specified area will be used as the docking location; If not included, the nearest available parking area will be used as the parking location; guidance information will be generated based on the parking location and the current location, and the guidance information will be output through the guidance device on the vehicle.

[0070] Given the complex parking environment on the road, if the current location of the target user does not allow the vehicle to park, the parking location needs to be replanned to ensure the compliance and safety of the vehicle's operation while picking up the user.

[0071] In this embodiment, the vehicle can load either an offline or online map, and parking areas are pre-marked on both maps. First, the target user's current location is mapped onto the map to determine the designated area where the target user is located. This embodiment does not specifically limit the specific implementation method for mapping the target user's current location onto the map. For example, the relative distance between the target user's current location and the vehicle's location can be determined, and the current location can be mapped onto the map based on the vehicle's coordinates on the map. The designated area is the area formed by locations at a preset distance from the current location on the vehicle's current driving road. The preset distance can be set according to actual needs, and this embodiment does not specifically limit it.

[0072] If the designated area includes parking zones, the location within that area closest to the user's current location will be chosen as the parking spot. In other words, the target user can remain stationary while the vehicle travels to their current location to pick them up.

[0073] If the designated area does not include a parking area, the parking location needs to be replanned to ensure the compliance and safety of vehicle operation. Specifically, the nearest available parking area to the user's current location will be designated as the parking location. Furthermore, guidance information (including but not limited to guidance routes, parking locations, and surrounding landmarks) will be generated based on the parking location and the current location, and displayed through the vehicle's guidance devices (including but not limited to displays and speakers). In other words, the user will proceed to the parking location according to the guidance information, and the vehicle will also move to the designated parking location to pick up the user.

[0074] In summary, this embodiment determines the parking location differently based on whether the user's current location is a parking area, which can both pick up the target user and ensure the compliance and safety of vehicle operation.

[0075] The following explains the process of using service authorization verification information to determine whether the target user is eligible to pay for this pickup task.

[0076] As an optional embodiment, the service authorization verification information includes the target user's biometric data; based on the service authorization verification information, determining whether the target user is eligible to pay for this pick-up service includes: Based on biometric data, a biometric template is generated; the biometric template includes at least one feature set extracted from the biometric data. The system determines whether a template with a similarity greater than a preset similarity exists in the user information database to determine whether the target user has a payment account. The user information database stores user registration information, which includes biometric templates and corresponding payment accounts. If such a user exists, then it is determined that the target user is eligible to pay for this pickup task.

[0077] In this embodiment, a user information database is pre-built in the cloud or on the vehicle. This database stores user registration information, including biometric templates and corresponding payment accounts. Users whose biometric templates and payment accounts are stored in the database are considered registered users. Users can register through a specified application; this embodiment does not impose any particular limitations on this.

[0078] For example, during the user registration process through a designated application, the user's biometric data is obtained after obtaining the user's permission. Biometric data includes, but is not limited to, the user's facial image, fingerprint, and iris. Subsequently, this biometric data is processed and abstracted into a structured, easily comparable, and storable biometric template. The biometric template includes at least one feature set extracted from the biometric data, such as at least one of the following: a set of facial feature points, a set of minutiae coordinates of the fingerprint, or a set of texture vectors from the iris.

[0079] If the target user's payment account can be found in the user information database, it can be assumed that the target user can pay for this pickup task through that payment account. Please refer to... Figure 4 , Figure 4 This is a schematic diagram illustrating the second principle of a vehicle pick-up control method provided in this application. Specifically, firstly, a biometric template is generated based on the biometric data of the target user. Then, it is determined whether a template with a similarity greater than a preset similarity to the target user's biometric template exists in the user information database. If such a template exists, the target user is considered a registered user; the payment account corresponding to the template with a similarity greater than the preset similarity in the user information database can be used as the target user's payment account.

[0080] After determining the target user's payment account in the manner described above, the target user is deemed eligible to pay for this pickup task. Of course, further judgments can be made regarding whether the target user's payment account is frozen, whether the available balance can cover the amount to be paid for this pickup task, etc., but this embodiment does not impose any particular limitations on these aspects.

[0081] Considering that the target users may also be unregistered users, the process for determining whether an unregistered target user can pay for this pickup task is explained below.

[0082] As an optional embodiment, the service authorization verification information also includes a payment token presented by the target user; if it does not exist, the method further includes: Generate a prompt message to prompt the target user to present a payment token; output the prompt message through the prompting device on the vehicle; Determine whether a payment token has been collected within the third preset time period starting from the time the prompt message is output; If a payment token is collected, it is determined that the target user can pay for this pickup task.

[0083] In this embodiment, the service authorization verification information also includes the payment token presented by the target user. If it is determined that there is no template in the user information database with a similarity greater than a preset similarity to the biometric template, the target user is considered an unregistered user. In this case, although it is impossible to directly pay for the pickup task using the target user's payment account, if the user can present a payment token, it can still be considered that the user can pay for this pickup task.

[0084] like Figure 4 As shown, a prompt message is first generated to prompt the target user to present a payment token, and then the prompt message is output through a prompting device on the vehicle. For example, "Please present payment code" may be displayed on the vehicle's screen, or "Please present payment code" may be announced through the vehicle's speaker, etc. This embodiment does not limit this to any particular method.

[0085] Within a third preset time period from the moment the prompt message is output, it is determined whether a payment token has been collected by the token collection device on the vehicle (including but not limited to a QR code scanner and an NFC card reader). If a payment token is collected, it is determined that the target user can pay for this pick-up service. The aforementioned third preset time period can be set according to actual needs, and this embodiment does not limit it.

[0086] Furthermore, the validity of the collected payment tokens can be verified. This embodiment does not specifically limit the method for verifying the validity of the payment tokens. Moreover, for the aforementioned unregistered users, a prompting device on the vehicle can guide them to complete registration through a designated application, facilitating their subsequent use of the pick-up service.

[0087] By utilizing the target user's biometric data and the presented payment token, it was determined whether the target user could pay for the pick-up service. The reliable result ensured a closed-loop financial system and guaranteed the operational safety of the vehicle pick-up service.

[0088] Please refer to Figure 5 , Figure 5 A first structural schematic diagram of a vehicle pick-up control device provided in this application, the device comprising: The target user identification module 501 is used to identify target users in the driving environment; the target user is a user whose intention to take a ride is determined based on gesture actions and whose historical ride credit value has passed the ride credit verification. The docking location determination module 502 is used to determine the docking location based on the current location of the target user; The verification information acquisition module 503 is used to acquire service authorization verification information after the vehicle arrives at the parking location; The service authorization verification module 504 is used to determine whether the target user can pay for this pickup task based on the service authorization verification information; if so, the pickup module 505 is triggered. The pick-up module 505 is used to acquire the multimodal signal output by the target user after the target user gets on the vehicle; determine the destination position of this pick-up task based on the multimodal signal; and execute the pick-up task based on the destination position.

[0089] For a detailed description of the vehicle pick-up control device provided in this application, please refer to the embodiments of the vehicle pick-up control method described above; this application will not repeat the details here.

[0090] In addition, please refer to Figure 6 , Figure 6 This application provides a second structural schematic diagram of a vehicle pick-up control device. The vehicle is equipped with an onboard perception system, which includes at least a vision sensor to acquire user image sequences, facilitating the target user identification module 501 to identify the target user based on the user image sequences. The vehicle is also equipped with a human-machine interaction system, such as a multimodal human-machine interface, to acquire multimodal signals input by the user and determine the destination location.

[0091] The core processing system also includes a task management module to set task states for vehicles; task states include route navigation state and empty cruising state. For example, when a vehicle stops at a pick-up location, the task state is set to route navigation state; when the vehicle reaches its destination, the task state is set to empty cruising state.

[0092] The vehicle is also equipped with a vehicle execution system, including a door lock controller, a trip billing module, and a route planning module. After confirming that the user can pay for the ride, the door lock controller unlocks the door, the trip billing module starts billing, and the route planning module plans the vehicle's driving route based on the obtained destination location to execute the ride.

[0093] Based on the above embodiments: As an optional embodiment, the target user identification module 501 includes: Image sequence acquisition module, used to acquire user image sequences collected by the vision sensor; The motion trajectory recognition module is used to identify the hand motion trajectories of all users in a user image sequence based on the user image sequence. The candidate user determination module is used to determine whether there are candidate users among all users whose hand movement trajectories meet the characteristics of soliciting passengers; the characteristics of soliciting passengers include at least one of the following: the number of hand swings within a first preset time period is greater than a preset number, and the swing amplitude of the hand movement trajectory is greater than a preset amplitude; if so, the data collection module is triggered. The data acquisition module is used to collect biometric data of candidate users; The user identification submodule is used to identify target users who have passed the ride credit verification based on their historical ride credit scores from candidate users, using biometric data.

[0094] As an optional embodiment, when there is only one candidate user, the user identification submodule includes: The validity assessment module is used to determine whether biometric data is valid. If the data is not valid, the system will return to the trigger acquisition module and trigger subsequent modules during vehicle operation until the preset conditions are met. If the data is valid, the following module will be triggered: The mapping relationship acquisition module is used to acquire pre-built mapping relationships; the mapping relationship is the correspondence between a user's unique identifier and historical ride credit value; the historical ride credit value is the ratio of the number of historical rides to the number of historical ride solicitations; The credit score determination module is used to determine the target ride credit score corresponding to the candidate user based on biometric data and mapping relationship; if the target ride credit score is greater than the preset credit score, the candidate user is used as the target user.

[0095] As an optional embodiment, when there are multiple candidate users, the user identification submodule includes: The candidate user determination module is used to determine, during the process of the vehicle traveling to the designated location, whether there are candidate users among the candidate users whose target ride credit score is greater than the preset credit score; the designated location is the location of the candidate user farthest from the vehicle; If it exists, the following module will be triggered: The first processing module is used to select a single candidate user as the target user when there is only one candidate user. The second processing module is used to score each candidate user when there are multiple candidate users, so as to determine the target user from among the candidate users.

[0096] As an optional embodiment, the second processing module includes: The intent scoring module is used to determine the ride intention score based on the target number of swings and the target swing amplitude within a second preset time period according to the hand movement trajectory of the candidate user; the ride intention score is positively correlated with both the target number of swings and the target swing amplitude; The distance score determination module is used to determine the distance score based on the distance between the candidate user and the vehicle; the distance score is negatively correlated with the distance. The user rating determination module is used to determine the user rating corresponding to the candidate users based on the ride intention rating, distance rating, and target ride credit score. The second processing submodule is used to select the candidate user with the highest user rating as the target user.

[0097] As an optional embodiment, the docking location determination module 502 includes: The designated area determination module is used to map the current location onto a map to obtain the designated area where the target user is located; the designated area is the area formed by the location on the vehicle's current driving road and at a preset distance from the current location; The parking determination module is used to determine whether a specified area includes a parking area; if it does, the first location determination module is triggered; if it does not, the second location determination module is triggered. The first location determination module is used to select the location closest to the current location within a specified area as the docking location; The second location determination module is used to select the nearest available parking area as the parking location; generate guidance information based on the parking location and the current location, and output the guidance information through the guidance device on the vehicle.

[0098] As an optional embodiment, the service authorization verification information includes the biometric data of the target user; the service authorization verification module 504 includes: A template generation module is used to generate a biometric template based on biometric data; the biometric template includes at least one feature set extracted from the biometric data; The account determination module is used to determine whether there is a template in the user information database that has a similarity greater than a preset similarity with the biometric template, so as to determine whether the target user has a payment account; the user information database is used to store user registration information, including biometric templates and corresponding payment accounts; if they exist, it is determined that the target user can pay for this pickup task.

[0099] As an optional embodiment, the service authorization verification information also includes a payment token presented by the target user; if it does not exist, the device further includes: The prompting module is used to generate prompt messages to prompt the target user to present the payment token; and outputs the prompt messages through the prompting device on the vehicle. The token acquisition module is used to determine whether a payment token has been acquired within the third preset time period from the time the prompt message is output; if a payment token is acquired, it is determined that the target user can pay for this pickup task.

[0100] This application also provides a vehicle comprising: Memory, used to store computer programs; A processor, used to execute the computer program to implement the steps of any of the above-described vehicle pick-up control methods.

[0101] It should be noted that the vehicles provided in the embodiments of this application may include, but are not limited to, sedans, sport utility vehicles (SUVs), multi-purpose vehicles (MPVs), off-road vehicles, pickup trucks, or other power-driven, non-rail-borne vehicles.

[0102] For a detailed description of the vehicle provided in this application, please refer to the embodiments of the vehicle pick-up control method described above; this application will not repeat the details here.

[0103] This application also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the above-described vehicle pick-up control methods.

[0104] The aforementioned storage media include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or integrated into dedicated logic circuitry.

[0105] For a detailed description of the storage medium provided in this application, please refer to the embodiments of the vehicle pick-up control method; this application will not repeat the details here.

[0106] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0107] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0108] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for controlling vehicle takeover, characterized in that, The method includes: Identify target users in the driving environment; the target users are those whose intention to take a ride is determined based on their gestures and whose historical ride credit scores have passed the ride credit verification. Determine the vehicle's parking location based on the target user's current location; After the vehicle arrives at the parking location, service authorization verification information is obtained; Based on the service authorization verification information, determine whether the target user is eligible to pay for this pickup task; If so, after the target user boards the vehicle, the multimodal signal output by the target user is acquired; based on the multimodal signal, the destination location of the current pick-up and drop-off task is determined; and based on the destination location, the current pick-up and drop-off task is executed.

2. The vehicle pick-up control method as described in claim 1, characterized in that, The identification of target users in the driving environment includes: Acquire user image sequences captured by the visual sensor; Based on the user image sequence, identify the hand movement trajectories of all users in the user image sequence; Determine whether all users include candidate users whose hand movement trajectories meet the characteristics of soliciting passengers; the characteristics of soliciting passengers include at least one of the following: the number of hand movements within a first preset time period is greater than a preset number, and the amplitude of hand movements is greater than a preset amplitude; If included, then collect the biometric data of the candidate users; based on the biometric data, determine the target users from the candidate users whose historical travel credit values ​​have passed the travel credit verification.

3. The vehicle pick-up control method as described in claim 2, characterized in that, When there is only one candidate user, the target user whose historical ride credit score has passed the ride credit verification is determined from the candidate users based on the biometric data, including: Determine whether the biometric data is valid; If the data is not valid, the process of collecting the biometric data of the candidate user will be repeated during the vehicle's operation, and subsequent steps will be executed until the preset conditions are met. If the data is valid, proceed with the following steps: Obtain a pre-constructed mapping relationship; the mapping relationship is the correspondence between a user's unique identifier and their historical ride credit value; the historical ride credit value is the ratio of the number of historical rides to the number of historical ride solicitations; Based on the biometric data and the mapping relationship, the target ride credit score corresponding to the candidate user is determined; If the target ride credit score is greater than the preset credit score, then the candidate user will be selected as the target user.

4. The vehicle pick-up control method as described in claim 3, characterized in that, When there are multiple candidate users, the target users whose historical ride credit scores have passed the ride credit verification are determined from the candidate users based on the biometric data, including: During the process of the vehicle traveling to the designated location, it is determined whether there is a candidate user among the candidate users whose target ride credit score is greater than the preset credit score; the designated location is the location of the candidate user farthest from the vehicle; If it exists, perform the following steps: When there is only one candidate user, the candidate user shall be used as the target user. When there are multiple candidate users, each candidate user is scored to determine the target user from among them.

5. The vehicle pick-up control method as described in claim 4, characterized in that, Scoring each of the candidate users to determine the target user from among the candidate users includes: Based on the target number of hand movements and the target amplitude of the selected users within a second preset time period, a ride intention score is determined; the ride intention score is positively correlated with both the target number of hand movements and the target amplitude of the hand movements. A distance score is determined based on the distance between the candidate user and the vehicle; the distance score is negatively correlated with the distance. The user rating corresponding to the candidate user is determined based on the ride intention score, the distance score, and the target ride credit score; The candidate user with the highest user rating will be selected as the target user.

6. The vehicle pick-up control method as described in claim 1, characterized in that, Based on the target user's current location, determine the vehicle's parking location, including: The current location is mapped onto a map to obtain the designated area where the target user is located; the designated area is the area formed by the locations on the vehicle's current driving road and at a preset distance from the current location; Determine whether the designated area includes a parking area; If included, the location closest to the current location within the specified area will be taken as the docking location; If not included, the nearest available parking area to the current location is taken as the parking location; guidance information is generated based on the parking location and the current location, and the guidance information is output through the guidance device on the vehicle.

7. The vehicle pick-up control method as described in claim 1, characterized in that, The service authorization verification information includes the biometric data of the target user; determining whether the target user is eligible to pay for this pick-up service based on the service authorization verification information includes: A biometric template is generated based on the biometric data; the biometric template includes at least one feature set extracted from the biometric data. The system determines whether a template with a similarity greater than a preset similarity exists in the user information database, thereby determining whether the target user has a payment account; the user information database is used to store user registration information, which includes biometric templates and corresponding payment accounts; If such a user exists, then it is determined that the target user is capable of paying for this pickup task.

8. The vehicle pick-up control method as described in claim 7, characterized in that, The service authorization verification information also includes the payment token presented by the target user; If it does not exist, the method further includes: Generate a prompt message to prompt the target user to present a payment token; output the prompt message through the prompting device on the vehicle; Determine whether the payment token has been collected within a third preset time period from the time the prompt message is output; If the payment token is collected, it is determined that the target user can pay for the current pickup task.

9. A vehicle pick-up control device, characterized in that, The device includes: The target user identification module is used to identify target users in the driving environment; the target user is a user whose intention to take a ride is determined based on gestures and whose historical ride credit value has passed the ride credit verification. The docking location determination module is used to determine the docking location based on the current location of the target user; The verification information acquisition module is used to acquire service authorization verification information after the vehicle has driven to the parking location; The service authorization verification module is used to determine whether the target user can pay for this pickup task based on the service authorization verification information; if so, the pickup module is triggered. The pick-up module is used to acquire the multimodal signal output by the target user after the target user boards the vehicle; determine the destination location of the current pick-up task based on the multimodal signal; and execute the current pick-up task based on the destination location.

10. A vehicle, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the vehicle pick-up control method as described in any one of claims 1 to 8.

11. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the vehicle pick-up control method as described in any one of claims 1 to 8.

Images