Method, apparatus, and storage medium for controlling an autonomous vehicle

Abstract

The present disclosure provides a method, an apparatus, and a storage medium for controlling an autonomous vehicle. The method includes: obtaining expected values of a plurality of users for parameters used to adjust a driving behavior of the vehicle, where the expected value of each user is generated based on an input of the user on a corresponding terminal device; and calculating a set value of the parameter according to the expected values of the plurality of users.

Description

Technical Field

[0001] The present disclosure generally relates to autonomous driving technology, and particularly to the control of driving behaviors of autonomous vehicles. Background Art

[0002] Autonomous driving technology, also known as driverless technology, is an increasingly popular technical field that has attracted widespread attention. It is generally believed that the impact of driverless on the automotive industry is unprecedented and will bring profound changes to the automotive industry. Research shows that driverless will bring disruptive improvements in areas such as enhancing road safety, reducing air pollution, and alleviating traffic congestion.

[0003] The research and development of autonomous driving technology mostly focuses on safety. However, as an upcoming mode of travel, how to improve the riding experience of users of autonomous vehicles also needs to be considered. Summary of the Invention

[0004] According to one aspect of the present disclosure, a method for controlling an autonomous vehicle is provided. The method includes: obtaining expected values of multiple users for parameters used to adjust the driving behavior of the vehicle, where the expected value of each user is generated based on the input of the user on the corresponding terminal device; and calculating a set value of the parameter according to the expected values of the multiple users.

[0005] According to another aspect of the present disclosure, an apparatus for controlling an autonomous vehicle is provided. The apparatus includes: an obtaining unit configured to obtain expected values of multiple users for parameters used to adjust the driving behavior of the vehicle, where the expected value of each user is generated based on the input of the user on the corresponding terminal device. The apparatus further includes a calculating unit configured to calculate a set value of the parameter according to the expected values of the multiple users.

[0006] According to another aspect of the present disclosure, an apparatus for controlling an autonomous vehicle is provided. The apparatus includes: a processor and a memory storing a program. The program includes instructions that, when executed by the processor, cause the processor to execute the method described in the present disclosure. According to another aspect of the present disclosure, a vehicle is provided. The vehicle includes the apparatus for controlling an autonomous vehicle described in the present disclosure.

[0007] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing a program is provided. The program includes instructions that, when executed by one or more processors, cause the one or more processors to execute the method described in the present disclosure. Brief Description of the Drawings

[0008] The accompanying drawings exemplarily illustrate embodiments and form part of the specification, and are used together with the textual description of the specification to explain the exemplary implementation manners of the embodiments. The illustrated embodiments are for illustrative purposes only and do not limit the scope of the claims. In all the drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0009] Figure 1 is a flowchart showing a method for controlling an autonomous vehicle according to an exemplary embodiment;

[0010] Figure 2 is a schematic diagram showing a graphical user interface for selecting autonomous driving parameters displayed on a user terminal device according to an exemplary embodiment;

[0011] Figure 3 is a schematic diagram showing a graphical user interface for selecting an expected value of an autonomous driving parameter according to an exemplary embodiment;

[0012] Figure 4 is a flowchart showing a method for controlling an autonomous vehicle according to another exemplary embodiment;

[0013] Figure 5 is a schematic diagram showing an application scenario for allocating vehicles to multiple users according to an exemplary embodiment;

[0014] Figure 6 is a block diagram showing a device for controlling an autonomous vehicle according to an exemplary embodiment; and

[0015] Figure 7 is a schematic diagram showing an application scenario of a motor vehicle according to an exemplary embodiment. Detailed Embodiments

[0016] In the present disclosure, unless otherwise specified, the terms "first", "second", etc. are used to describe various elements and are not intended to limit the positional relationship, timing relationship or importance relationship of these elements. Such terms are only used to distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, and in certain cases, based on the context description, they may also refer to different instances.

[0017] In the description of various examples in the present disclosure, the terms used are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically defined, the element may be one or more. In addition, the term "and / or" used in the present disclosure covers any one of the listed items and all possible combinations.

[0018] In the present disclosure, an autonomous vehicle can be understood as a motor vehicle with autonomous driving functions. For example, it can include driverless vehicles and various other motor vehicles that have and have switched to autonomous driving functions. Among them, a driverless vehicle can be a vehicle used to provide Autonomous Vehicle Mobility as a Service.

[0019] The driving behavior of an autonomous vehicle can be described in several aspects. These aspects include but are not limited to: the frequency of lane changes of the vehicle, the following distance between the vehicle and the vehicle in front during driving, and the acceleration of the vehicle.

[0020] Specifically, the frequency of lane changes of the vehicle can correspond to the tolerance threshold of the vehicle for the vehicle in front. The greater the set frequency of lane changes, the lower the corresponding tolerance threshold. Here, the setting of the tolerance threshold can be related to the driving speed of the vehicle being followed and / or the following time of the vehicle itself. In the case of a lower tolerance threshold, the autonomous vehicle is more likely to trigger automatic control of the powertrain and steering system to complete a lane change operation and thus overtake. Therefore, the frequency of lane changes is also higher. On the other hand, in the case of a higher tolerance threshold, the autonomous vehicle is more likely to follow the vehicle in front and continue driving without performing a lane change operation to overtake. Therefore, the frequency of lane changes is also lower.

[0021] The following distance refers to the distance between the vehicle itself and the vehicle in front during driving. When the actual distance is lower than the threshold of the following distance, automatic control of the powertrain and braking system can be triggered to control the distance between the vehicle itself and the vehicle in front to be not lower than the distance threshold.

[0022] In addition, acceleration can be used to set the acceleration curve of the autonomous vehicle. When the road conditions ahead are good, automatic control of the powertrain can be triggered to accelerate according to this acceleration curve. The speed at which the autonomous vehicle speeds up is related to the steepness of the acceleration curve.

[0023] It should be noted that the three aspects listed above are only exemplary, and other aspects that can affect driving behavior can also be conceived.

[0024] It is understandable that users of autonomous vehicles may have different expectations for the driving behavior of the vehicle. For example, for users who are in a hurry, they are likely to expect the vehicle to change lanes as frequently as necessary during driving to avoid wasting too much time following a slow vehicle ahead; in addition, they may also expect the vehicle to closely follow the vehicle ahead as much as possible on the premise of ensuring safety; furthermore, they may also hope that the vehicle can increase its speed with a higher acceleration when the road conditions are good. On the other hand, for users who attach more importance to ride comfort or safety, they may have exactly the opposite expectations for the driving behavior of the autonomous vehicle. For example, they are likely to expect the vehicle not to change lanes frequently, maintain a large safety distance from the vehicle ahead, and accelerate evenly and gently. Therefore, for autonomous vehicles that can accommodate multiple passengers especially, their driving behavior needs to seek a balance between time efficiency and ride comfort in order to meet the riding needs of different users as much as possible and thus improve the riding experience.

[0025] Figure 1 The flowchart of a method for controlling an autonomous vehicle according to an exemplary embodiment is shown.

[0026] In step S101, for the parameters used to adjust the driving behavior of the vehicle, the expected values of multiple users are obtained. Among them, the expected value of each user is generated based on the input of the user on the corresponding terminal device.

[0027] Here, the parameters used to adjust the driving behavior of the vehicle can be one or more of several autonomous driving parameters including lane change frequency, following distance, and acceleration. As Figure 2 shown, the autonomous driving parameters selected for adjusting the driving behavior of the vehicle can be displayed on the user's terminal device as a first graphical user interface, which can be achieved through a dedicated terminal device application (APP). The terminal device can be an intelligent mobile device with a touch display screen such as the user's mobile phone, tablet computer, smart watch (ring), etc. In addition, Figure 2 the first graphical user interface shown is only exemplary, and user interfaces including other autonomous driving parameters or having other layout styles can be envisioned.

[0028] In response to the user clicking Figure 2 the button corresponding to a certain parameter on the shown interface, the user's terminal device can display a second graphical user interface as shown in Figure 3 . In response to the user's input on the sliding input bar, the terminal device can determine the user's expected value for the lane change frequency. It should be noted that Figure 3The displayed sliding input bar is merely exemplary. For example, other forms of graphical user interfaces provided with "+" and "-" buttons are also conceivable. In addition, it can be envisioned that the second graphical user interface for inputting expected values is different corresponding to different types of autonomous driving parameters. For example, for "following distance", the second graphical user interface can provide the user with the possibility of inputting specific values.

[0029] According to some embodiments, when multiple users are already inside the vehicle, the user's terminal devices can respectively establish communication connections with the vehicle. The communication device of the vehicle can have one or more of Bluetooth, Wi-Fi, or mobile communication functions, thereby forming a communication link with the user's terminal devices. The expected values input by each user on the terminal device are transmitted to the vehicle via the corresponding communication link for subsequent processing. This is particularly applicable to the situation where multiple users are riding in a privately-owned vehicle. Since the vehicle can directly obtain the expected values of relevant parameters from each user's terminal device, the process of the vehicle obtaining the expected values can be made more convenient.

[0030] In step S103, according to the expected values of multiple users, the set value of the parameter is calculated.

[0031] According to the present disclosure, the set values of the parameters for adjusting the driving behavior of the vehicle are calculated based on the expected values of multiple users. Thus, the needs of each user can be comprehensively considered, so that the driving behavior adjusted based on the set values can conform to the riding expectations of all users as much as possible.

[0032] According to some embodiments, the average value of the expected values of multiple users is calculated as the set value of the corresponding parameter.

[0033] On the one hand, calculating the set value of the corresponding parameter by taking the average value can simplify the calculation process of the set value; on the other hand, since the finally determined average value must fall within the range of the expected values of each user, it can further ensure that the finally determined set value is as close as possible to the expected value of each user.

[0034] The operation of calculating the average value can be performed, for example, by the vehicle's own controller. As an alternative, after the vehicle receives the expected values from each user, it is also feasible to transmit them to an online server for calculation or to a cloud server for cloud computing. The calculation result will then be transmitted to the vehicle for adjusting the driving behavior of the vehicle.

[0035] After the vehicle receives the corresponding set value, it will control the powertrain, steering system, braking system, etc. according to the set value to control the driving behavior of the autonomous vehicle, which will not be elaborated here.

[0036] According to some embodiments, the average value is a weighted average value, and the expected value of each user is assigned a corresponding weight.

[0037] Configuring weights for each user can consider factors that require extra care, such as the age of the user. Suppose the following scenario. When there are only two users (i.e., passengers) inside the vehicle, even if both users tend to the same type of driving behavior (e.g., comfort first), their specific expected values for the corresponding parameters may still deviate. For example, one passenger's expected value for the lane change frequency may be "low", while the other passenger's expected value for the lane change frequency may be "extremely low". In other words, the latter user may very much not want to change lanes for overtaking. At this time, in order to enable both parties to obtain a satisfactory riding experience, simply taking the arithmetic mean of the two users' expected values for the lane change frequency is likely not the optimal solution. The reason is that compared with young passengers, older passengers may have a lower tolerance for the deviation between the actual driving behavior and the expected driving behavior of the vehicle. In this case, by configuring a higher weight (e.g., 80%) for the older passenger and a lower weight (e.g., 20%) for the younger passenger, the finally determined set value can be between the median of the two expected values and the set value corresponding to "extremely low" for the lane change frequency.

[0038] It should be noted that the above-mentioned age factor of the user and the specific weight configuration are only exemplary. Based on the teachings of the present disclosure, one or more other factors that can be considered when configuring weights (e.g., health status) and other weight configuration strategies are also conceivable.

[0039] The factors affecting the weight configuration can be transmitted to the vehicle together with the expected values input by the user. For example, the data transmitted from the user's terminal device to the vehicle can include fields regarding user information (such as user ID, basic information, etc.).

[0040] The operation of calculating the weighted average can be performed by the vehicle's own controller. After receiving the relevant information, the vehicle's controller can assign corresponding weights to the expected values of each user according to a predetermined rule and calculate the set value of the corresponding parameter. As an alternative, after receiving the expected values from each user, it is also feasible for the vehicle to transmit them to an online server for calculation or to a cloud server for cloud computing. The calculation result will be transmitted back to the vehicle for adjusting the driving behavior of the vehicle.

[0041] According to some embodiments, when multiple users are outside the vehicle, the above method for controlling an autonomous vehicle further includes: clustering the multiple users according to their expected values to form one or more groups; assigning the vehicle to the users belonging to the same group; and calculating the set value of the parameter for the vehicle according to the expected values of the users to whom the vehicle is assigned in the same group.

[0042] Figure 4 The flowchart of a method for controlling an autonomous vehicle according to another exemplary embodiment is shown.

[0043] In step S401, for parameters used to adjust the vehicle driving behavior, the expected values of multiple users are obtained.

[0044] Users who need autonomous mobility services can send their expected values to an online server through an application on their own terminal devices (e.g., a ride-hailing software). In addition, as mentioned above, the data sent by users to the online server can also include the user's ID and other user information.

[0045] In step S403, according to the expected values of multiple users, multiple users are clustered to form one or more groups.

[0046] By preprocessing the expected values of multiple users, users with the same expectations for driving behavior can be divided into one group. For example, users who tend to reach the destination as soon as possible can be divided into one group, while users who tend to focus on riding comfort can be divided into another group.

[0047] Cluster analysis can be used for preprocessing the expected values of users.

[0048] According to one implementation, the K-Means algorithm is used for cluster analysis. Among them, the value of k in the K-Means algorithm is related to the number of groups expected to be divided.

[0049] For example, different users are divided into a group that expects to save time and a group that expects to ride comfortably. Therefore, the K-Means algorithm pre-assumes the existence of 2 groups, and by continuously iterating to find the nearest center of each sample, it converges to a stable mean position, and this mean position is the group (cluster) that these samples finally belong to.

[0050]

[0051] In the above formula 1, X represents a data set containing n vectors. The K-Means algorithm needs to divide n vectors into k clusters c i to minimize the within-group sum of squares, u i is the median of all points in the cluster c i Here, the number of vectors n is determined by the number of users, and the dimension in each vector is related to the number of parameters for which users need to provide expected values.

[0052] According to another implementation, the Mean-Shift algorithm is adopted for cluster analysis. The Mean-Shift algorithm is a hill-climbing algorithm based on kernel density estimation, and the basic form of the Mean-Shift algorithm can be expressed as:

[0053]

[0054] Among them, Kernel represents the kernel function, such as the RBF kernel function (Radial Basis Function Kernel). N(x i ) represents a neighborhood that contains several x j and has x i as the center (mean). Different from the K-Means algorithm, since it is unknown how many user groups can be divided in an unknown user set, Mean-Shift clustering does not require specifying the number of k. Therefore, the advantages of using Mean-Shift clustering are as follows: 1) It is not necessary to pre-specify the number of groups to be finally divided; 2) Only the radius of the kernel function Kernel needs to be specified, and here the radius determines the maximum value of the difference in the expected values of users. In addition, the DBSCAN algorithm can also be considered.

[0055] In step S405, vehicles are assigned to users belonging to the same group.

[0056] After dividing multiple users who call for an autonomous mobility service into several groups, the scheduling system of the online server can assign vehicles (e.g., driverless taxis Robo Taxi) to users in one of the groups. During the vehicle assignment process, the specific passenger capacity limit of the vehicle, as well as the current location and destination of the users, can also be considered. Planning a path based on the current location and destination location is an existing technology in the field of autonomous driving and will not be elaborated here.

[0057] Figure 5 An application scenario of assigning vehicles to multiple users according to an exemplary embodiment is shown. Among them, through clustering analysis of the expected values of users, multiple users who request a mobility service are divided into two groups 501 and 503. Subsequently, the scheduling system of the online server assigns vehicles to users in different groups according to the results of the clustering analysis.

[0058] Through preprocessing of clustering multiple users, users who will take the same vehicle have relatively similar expectations for the driving behavior of the vehicle. On this basis, further calculating the set value of the corresponding parameter according to the expected values of the users assigned to the same vehicle can make the finally determined driving behavior closer to the expectations of each user, and further improve the riding experience of the users.

[0059] In step S407, according to the expected values of the users assigned vehicles in the same group, calculate the set value of the parameter for the vehicle.

[0060] According to some embodiments, the average value of the expected values of the users assigned to the same vehicle in a group is calculated as the set value of the corresponding parameter for the vehicle.

[0061] On the one hand, calculating the set value of the corresponding parameter by taking the average value can simplify the calculation process of the set value; on the other hand, since the finally calculated average value must fall within the range of the expected values of each user, it can further ensure that the finally determined set value is as close as possible to the expected value of each user.

[0062] The operation of calculating the average value can be performed, for example, by the controller of the vehicle itself. Specifically, the online server sends the expected values of multiple users assigned to the same vehicle to the vehicle. Alternatively, after the online server determines multiple users assigned to the same vehicle, the set value of the corresponding parameter can be calculated based on the expected values of these multiple users, and the finally calculated set value can be sent to the assigned vehicle for adjusting the driving behavior of the vehicle.

[0063] According to some embodiments, the average value is a weighted average value, and the expected value of each user among the users assigned to the vehicle is given a corresponding weight.

[0064] Configuring weights for each user can consider factors that require extra attention, such as the age of the user. It can be understood that even if the users assigned to the same vehicle tend to the same type of driving behavior, there may still be deviations in the specific expected values of these users for the corresponding parameters. Moreover, for the differences between the actual driving behavior and the expected driving behavior caused by such deviations, different users may show different tolerances. In order to enable all users to obtain a satisfactory riding experience, simply taking the arithmetic mean of the expected values is likely not the optimal solution.

[0065] It should be noted that the above-mentioned age factor of the user and the specific weight configuration are only exemplary. Based on the teachings of the present disclosure, other one or more factors that can be considered when configuring weights (such as, health status) and other weight configuration strategies are also conceivable.

[0066] The factors affecting the weight configuration can be transmitted to the vehicle by the online server together with the expected values input by the users. For example, the data transmitted from the user's terminal device to the online server can include fields regarding user information (such as user ID, basic information, etc.).

[0067] The operation of calculating the weighted average value can be performed by the controller of the vehicle itself. After receiving the relevant information, the controller of the vehicle can assign corresponding weights to the expected values of each user according to the predetermined rules and calculate the set value of the corresponding parameter. Alternatively, after the online server determines multiple users assigned to the same vehicle, the set value of the corresponding parameter can be calculated based on the expected values of the multiple users and the relevant information, and the calculated final set value can be sent to the assigned vehicle for adjusting the driving behavior of the vehicle.

[0068] Figure 6 is a block diagram showing a device for controlling an autonomous vehicle according to an exemplary embodiment.

[0069] The device 600 for controlling an autonomous vehicle according to the exemplary embodiment may include: an acquisition unit 601 and a calculation unit 603. Among them, the acquisition unit 601 may be configured to acquire the expected values of multiple users for the parameters used to adjust the driving behavior of the vehicle. Among them, the expected value of each user is generated based on the input of the user on the corresponding terminal device. The calculation unit 603 may be configured to calculate the set value of the parameter according to the expected values of the multiple users.

[0070] According to some embodiments, the calculation unit 603 may be further configured to: calculate the average value of the expected values of multiple users as the set value of the corresponding parameter. Among them, the average value may be a weighted average value, and corresponding weights are assigned to the expected values of each user. It can be understood that the foregoing description of the method steps in combination with Figures 1 to 5 is applicable to Figure 6 the unit that executes the corresponding method steps, and will not be repeated here.

[0071] According to another aspect of the present disclosure, there is provided a device for controlling an autonomous vehicle. The device includes: a processor and a memory storing a program. The program includes instructions that, when executed by the processor, cause the processor to execute the method for controlling an autonomous vehicle described in the present disclosure.

[0072] According to another aspect of the present disclosure, there is provided a vehicle. The vehicle includes the device for controlling an autonomous vehicle described in the present disclosure.

[0073] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing a program. The program includes instructions that, when executed by one or more processors, cause the one or more processors to execute the method for controlling an autonomous vehicle described in the present disclosure.

[0074] Figure 7Shows a schematic diagram of an application scenario including a motor vehicle 2010 and a communication and control system for the motor vehicle 2010. It should be noted that Figure 7 The structure and functions of the illustrated vehicle 2010 are only an example. According to specific implementation forms, the vehicle of the present disclosure may include Figure 7 One or more of the structures and functions of the illustrated vehicle 2010.

[0075] The motor vehicle 2010 may include sensors 2110 for sensing the surrounding environment. The sensors 2110 may include one or more of the following sensors: ultrasonic sensors, millimeter-wave radars, lidars (LiDAR), vision cameras, and infrared cameras. Different sensors may provide different detection accuracies and ranges. Ultrasonic sensors may be installed around the vehicle to measure the distance between an object outside the vehicle and the vehicle by taking advantage of the strong directivity of ultrasonic waves. Millimeter-wave radars may be installed in the front, rear, or other positions of the vehicle to measure the distance between an object outside the vehicle and the vehicle by using the characteristics of electromagnetic waves. Lidars may be installed in the front, rear, or other positions of the vehicle to detect object edge and shape information for object recognition and tracking. Due to the Doppler effect, the radar device can also measure the speed change between the vehicle and a moving object. Cameras may be installed in the front, rear, or other positions of the vehicle. Vision cameras can capture the situation inside and outside the vehicle in real time and present it to the driver and / or passengers. In addition, by analyzing the images captured by the vision camera, information such as traffic signal indications, intersection situations, and the operating states of other vehicles can be obtained. Infrared cameras can capture objects in night vision conditions.

[0076] The motor vehicle 2010 may further include output devices 2120. The output devices 2120 include, for example, a display and a speaker, etc., to present various outputs or instructions. In addition, the display may be implemented as a touch screen, so that inputs can also be detected in different ways. A user graphical interface may be presented on the touch screen to enable the user to access and control the corresponding controls.

[0077] The motor vehicle 2010 may also include one or more controllers 2130. The controller 2130 may include a processor communicating with various types of computer-readable storage devices or media, such as a central processing unit (CPU) or a graphics processing unit (GPU), or other dedicated processors, etc. The computer-readable storage device or media may include any non-transitory storage device, and a non-transitory storage device may be any storage device that is non-transitory and can implement data storage, and may include but not be limited to disk drives, optical storage devices, solid-state memories, floppy disks, flexible disks, hard disks, magnetic tapes or any other magnetic media, optical discs or any other optical media, read-only memory (ROM), random access memory (RAM), cache memory, and / or any other memory chip or cartridge, and / or any other media from which a computer can read data, instructions, and / or code. Some of the data represented in the computer-readable storage device or media are executable instructions used by the controller 2130 to control the vehicle. The controller 2130 may include an autonomous driving system for automatically controlling various actuators in the vehicle. The autonomous driving system is configured to control the powertrain, steering system, and braking system, etc. of the motor vehicle 2010 via a plurality of actuators in response to inputs from a plurality of sensors 2110 or other input devices to control acceleration, steering, and braking respectively, without human intervention or with limited human intervention. Part of the processing functions of the controller 2130 may be implemented by cloud computing. For example, some processing may be performed using an on-vehicle processor, while other processing may be performed using computing resources in the cloud. According to some embodiments, the controller 2130 may be configured to execute the method described in conjunction with Figures 1 to 6 The controller 2130 and its associated computer-readable storage device are an example of the device 600 above Figure 6 . The computer-readable storage device associated with the controller 2130 may be an example of the non-transitory computer-readable storage medium described above.

[0078] The motor vehicle 2010 further includes a communication device 2140. The communication device 2140 includes a satellite positioning module capable of receiving satellite positioning signals from the satellite 2012 and generating coordinates based on these signals. The communication device 2140 further includes a module for communicating with the mobile communication network 2013, and the mobile communication network may implement any suitable communication technology, such as current or evolving wireless communication technologies such as GSM / GPRS, CDMA, LTE, etc. (such as 5G technology). The communication device 2140 may also have a vehicle networking or Vehicle-to-Everything (V2X) module configured to enable vehicle-to-vehicle (V2V) communication with other vehicles 2011 and vehicle-to-infrastructure (V2I) communication with the infrastructure. In addition, the communication device 2140 may also have a module configured to communicate with the user terminal 2014 (including but not limited to smartphones, tablets, or wearable devices such as watches) via, for example, a wireless local area network using the IEEE802.11 standard or Bluetooth. With the communication device 2140, the motor vehicle 2010 can access the online server 2015 or the cloud server 2016 via the wireless communication system, and the online server or the cloud server is configured to provide services such as corresponding data processing, data storage, and data transmission for the motor vehicle.

[0079] In addition, the motor vehicle 2010 further includes Figure 7 a powertrain, a steering system, a braking system, etc. for realizing the motor vehicle driving function not shown in the figure.

[0080] Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above methods, systems, and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is only defined by the authorized claims and their equivalent scope. Various elements in the embodiments or examples may be omitted or replaced by their equivalent elements. In addition, the steps may be executed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. Importantly, with the evolution of technology, many of the elements described herein may be replaced by equivalent elements that emerge after the present disclosure.

Claims

1. A method for controlling an autonomous vehicle, the method comprising: Obtaining expected values of a plurality of users for parameters used to adjust the driving behavior of the vehicle, wherein the expected value of each user is generated based on the input of the user on the corresponding terminal device; and Calculating a set value of the parameter according to the expected values of the plurality of users, wherein the plurality of users are located outside the vehicle, and the method further comprises: Clustering the plurality of users according to the expected values of the plurality of users to form one or more groups; Allocating the vehicle to the users belonging to the same group; Calculating a set value of the parameter for the vehicle according to the expected values of the users to whom the vehicle is allocated in the same group.

2. The method according to claim 1, wherein When the plurality of users are inside the vehicle, there is a communication connection between the terminal devices of the plurality of users and the vehicle.

3. The method according to claim 1, wherein Calculating the average value of the expected values of the users to whom the vehicle is allocated in the same group as the set value of the corresponding parameter for the vehicle.

4. The method according to claim 3, wherein, The average value is a weighted average value, and the expected value of each user among the users to whom the vehicle is allocated is given a corresponding weight.

5. The method according to any one of claims 1, 3 and 4, wherein The vehicle is used for autonomous driving mobility services.

6. A device for controlling an autonomous vehicle, comprising: An obtaining unit configured to obtain expected values of a plurality of users for parameters used to adjust the driving behavior of the vehicle, wherein the expected value of each user is generated based on the input of the user on the corresponding terminal device; and A calculating unit configured to calculate a set value of the parameter according to the expected values of the plurality of users, wherein the plurality of users are located outside the vehicle, and the calculating unit is further configured to: Cluster the plurality of users according to the expected values of the plurality of users to form one or more groups; Allocate the vehicle to the users belonging to the same group; Calculate a set value of the parameter for the vehicle according to the expected values of the users to whom the vehicle is allocated in the same group.

7. A device for controlling an autonomous vehicle, comprising: A processor, and A memory storing a program, the program including instructions that, when executed by the processor, cause the processor to execute the method according to any one of claims 1 to 5.

8. A vehicle, comprising: The device for controlling an autonomous vehicle according to claim 6 or 7.

9. A non-transitory computer-readable storage medium storing a program, the program including instructions that, when executed by one or more processors, cause the one or more processors to execute the method according to any one of claims 1 to 5.

Images