Method for controlling autonomous driving vehicle, autonomous driving system, vehicle and computer program product

Abstract

The present application relates to a method for controlling an autonomous vehicle, comprising: monitoring a driving speed of the vehicle when the vehicle (1) activates an autonomous driving function; under the condition that the running speed of the vehicle is lower than a preset speed threshold value, voice information from the interior and / or the exterior of a compartment of the vehicle is acquired; analyzing and processing the acquired voice information to determine the content of the voice information and the identity information of the voice publisher; and controlling the vehicle at least on the basis of the voice information if the voice information contains a predetermined control command assigned to the identity type of the voice publisher. According to the method and the device, when the automatic driving vehicle runs at a low speed, the automatic driving vehicle is controlled based on the voice information, and different control instruction permissions are configured for the voice publishers with different identity types, so that the vehicle can be quickly controlled through the voice instruction in an emergency, and vehicle accidents are avoided as much as possible.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and in particular to a method for controlling an autonomous driving vehicle, an autonomous driving system, a vehicle including an autonomous driving system according to the present application, and a computer program product for at least assisting in implementing the steps of the method according to the present application. Background Art

[0002] With the development of vehicle technology, vehicles with autonomous driving functions are becoming more and more popular. They can not only drive in specific areas, such as parking lots, but also drive on public roads under the corresponding operation design domain. However, once the driving environment changes and an emergency occurs, the owner or operator needs to input control instructions in the application to control the vehicle. The application can be installed in the owner's or operator's mobile terminal or in a dedicated remote control device. This process is relatively cumbersome and complicated. It is difficult to control the vehicle to stop in time in an emergency, which leads to traffic accidents.

[0003] Therefore, there is still room for improvement in the current autonomous driving system. Summary of the invention

[0004] The purpose of the present application is to provide a method for controlling an autonomous driving vehicle, an autonomous driving system, a vehicle including an autonomous driving system according to the present application, and a computer program product, so as to at least partially solve the problems in the prior art.

[0005] According to a first aspect of the present application, a method for controlling an autonomous driving vehicle is provided, the method comprising:

[0006] -Monitor the vehicle's speed when the vehicle's autonomous driving function is turned on;

[0007] - when the driving speed of the vehicle is lower than a predetermined speed threshold, acquiring voice information from inside and / or outside the vehicle cabin;

[0008] - Analyze and process the acquired voice information to determine the content of the voice information and the identity information of the voice publisher; and

[0009] If the voice message contains a predefined control command which is assigned to an identity type of the speaker of the voice, the vehicle is controlled at least on the basis of the voice message.

[0010] The core concept of this application is that when an autonomous driving vehicle is traveling at a low speed, voice information from inside and / or outside the vehicle can be obtained, and the autonomous driving vehicle can be controlled based on the voice information. Since different control command permissions are configured for voice publishers of different identity types, the vehicle can be quickly controlled through voice commands in an emergency, eliminating the tedious process of entering control commands through an application and avoiding vehicle accidents as much as possible.

[0011] According to an optional embodiment of the present application, the location information of the voice publisher can be determined with the help of a vehicle-mounted microphone arranged inside and / or outside the vehicle compartment, and the identity information of the voice publisher can be determined based on the location information of the voice publisher and the location information of the vehicle key, wherein, when the location information of the voice publisher is consistent with the location information of the vehicle key, the identity information of the voice publisher is determined to be the vehicle owner or operator, and when the location information of the voice publisher is inconsistent with the location information of the vehicle key, the identity information of the voice publisher is determined to be a road user.

[0012] According to another optional embodiment of the present application, when the number of vehicle-mounted microphones arranged outside the vehicle cabin is lower than a predetermined number threshold, the vehicle windows can be opened so that the vehicle-mounted microphones arranged inside the vehicle cabin can obtain voice information from outside the vehicle cabin.

[0013] According to another optional embodiment of the present application, the identity information of the voice publisher may be determined based on the voice characteristic information of the vehicle owner or operator, wherein the voice characteristic information may include accent, timbre and / or pitch, etc.

[0014] According to another optional embodiment of the present application, the identity information of the voice publisher may be determined based on the facial feature information of the vehicle owner or operator and the facial feature information of the voice publisher.

[0015] According to another optional embodiment of the present application, the language type of the acquired voice information may be determined, and semantic analysis may be performed on the voice information based on the determined language type, thereby determining the content of the voice information.

[0016] According to another optional embodiment of the present application, the pre-set control instruction assigned to the road user may only include a parking instruction, while the pre-set control instruction assigned to the vehicle owner or operator may include a parking instruction, a driving instruction and / or a deceleration instruction, etc.

[0017] According to another optional embodiment of the present application, when the voice information includes a parking instruction from a road user, the vehicle can be controlled to park, and the vehicle can be controlled to continue driving after obtaining a driving instruction from the vehicle owner or operator.

[0018] According to another optional embodiment of the present application, when the voice information includes a parking instruction from the vehicle owner or operator, the vehicle can be controlled to park.

[0019] According to another optional embodiment of the present application, when the voice information includes a deceleration instruction from the vehicle owner or operator, the vehicle is controlled to decelerate and the driving environment of the vehicle is re-detected.

[0020] According to a second aspect of the present application, an automatic driving system is provided, wherein the automatic driving system is used to execute the method according to the present application, wherein the automatic driving system may include the following components:

[0021] - a vehicle speed monitoring unit, which is configured to monitor the driving speed of the vehicle;

[0022] - a vehicle-mounted microphone configured to acquire voice information from inside and / or outside a vehicle cabin; and

[0023] - A control unit configured to perform the method according to the application.

[0024] According to another optional embodiment of the present application, the autonomous driving system may further include a vehicle-mounted camera, which is configured to obtain facial feature information of the voice publisher and is installed inside and / or outside the vehicle compartment.

[0025] According to a third aspect of the present application, a vehicle is provided, comprising an automatic driving system according to the present application.

[0026] According to a fourth aspect of the present application, a computer program product, such as a computer-readable program carrier, is provided, which contains or stores computer program instructions, and when the computer program instructions are executed by a processor, they at least assist in implementing the steps of the method according to the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The principles, features and advantages of the present application may be better understood by describing the present application in more detail below with reference to the accompanying drawings. The accompanying drawings show:

[0028] Figure 1 A flowchart showing a method for controlling an autonomous driving vehicle according to an exemplary embodiment of the present application is shown;

[0029] Figure 2 A schematic diagram showing a driving scenario according to an exemplary embodiment of the present application; and

[0030] Figure 3 A schematic block diagram of an autonomous driving system according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION

[0031] In order to make the technical problems, technical solutions and beneficial technical effects to be solved by the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and multiple exemplary embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the scope of protection of the present application.

[0032] Figure 1 A flowchart of a method for controlling an autonomous driving vehicle according to an exemplary embodiment of the present application is shown. The following exemplary embodiments describe the method according to the present application in more detail.

[0033] like Figure 1 As shown, the method may include steps S1 to S4. In step S1, when the vehicle 1 turns on the automatic driving function, the driving speed of the vehicle 1 can be monitored. In the meaning of this application, "automatic driving function" refers to automatic driving functions of level L3 and above, and the vehicle 1 equipped with the automatic driving function can automatically complete driving tasks in specific environments such as parking lots, urban roads, and highways. The method according to this application is applied in scenarios where the vehicle is driving at a low speed, for example Figure 2 In the exemplary driving scene diagram shown, a vehicle 1 with the automatic driving function turned on is driving at a low speed in a parking lot and performing a remote parking function. During the driving process, the driving speed of the vehicle 1 can be monitored by a vehicle speed monitoring unit 11 of the vehicle 1, and the vehicle speed monitoring unit can be a vehicle speed sensor for detecting wheel speed or a positioning device for detecting the vehicle position in real time.

[0034] In step S2, when the driving speed of the vehicle 1 is lower than a predetermined speed threshold value, that is, the vehicle 1 is in a low-speed running state, voice information from inside and / or outside the vehicle cabin of the vehicle 1 can be obtained. Here, not only can the voice information from inside the vehicle cabin of the vehicle 1 be obtained by means of a vehicle microphone arranged inside the vehicle cabin, and the voice information is issued by the vehicle owner or operator, but also the voice information from outside the vehicle cabin of the vehicle 1 can be obtained by means of a vehicle microphone arranged outside the vehicle cabin, and the voice information can be issued by a road user 2 within a predetermined distance range outside the vehicle cabin of the vehicle 1, or by a vehicle owner or operator within a predetermined distance range outside the vehicle cabin of the vehicle 1. In the sense of the present application, the road user 2 may include pedestrians, cyclists, battery-powered vehicle riders, and / or motorcycle riders, etc.

[0035] It is understandable that the position of the voice publisher can be determined by detecting voice information simultaneously by at least three vehicle-mounted microphones. When the number of vehicle-mounted microphones arranged outside the vehicle compartment is less than a predetermined number threshold (e.g., three), or even when no vehicle-mounted microphone is installed outside the vehicle compartment, the window of the vehicle 1 can be slightly opened so that the vehicle-mounted microphone arranged inside the vehicle compartment can obtain voice information from outside the vehicle compartment.

[0036] In step S3, the acquired voice information may be analyzed and processed to determine the content of the voice information and the identity information of the voice publisher. Here, the language type of the acquired voice information may be determined, such as Mandarin, dialect, English, German, etc., and the voice information may be semantically analyzed based on the determined language type to determine the content of the voice information.

[0037] When the number of vehicle microphones inside and / or outside the vehicle is sufficient, the location information of the voice publisher can be determined by means of the arrangement of the vehicle microphones. At the same time, the location information of the vehicle key can be obtained, and the identity information of the voice publisher can be determined based on the location information of the voice publisher and the location information of the vehicle key. Here, the vehicle key can be a physical key inserted in the keyhole of the vehicle, or an electronic key, which is installed in a mobile terminal of the owner or operator, or installed in a dedicated electronic device with wireless transmission function (such as a Bluetooth key or a key card) carried by the owner or operator. When the location information of the voice publisher is consistent with the location information of the vehicle key, the identity information of the voice publisher can be determined as the owner or operator, who can be inside the vehicle, for example, in the scenario of remote parking, or within a predetermined distance range outside the vehicle; when the location information of the voice publisher is inconsistent with the location information of the vehicle key, the identity information of the voice publisher can be determined as road user 2, who is within a predetermined distance range outside the vehicle.

[0038] Optionally, the identity information of the voice publisher can also be determined based on the voice feature information of the vehicle owner or operator, and the voice feature information includes, for example, accent, timbre and / or pitch, etc. Here, the machine learning model can be trained using the pre-stored voice feature information of the vehicle owner or operator, and the trained machine learning model can distinguish whether the voice publisher is the vehicle owner or operator.

[0039] Optionally, the identity information of the voice publisher can also be determined based on the facial feature information of the vehicle owner or operator and the facial feature information of the voice publisher. Here, the position of the voice publisher can be detected by the vehicle camera 14, thereby obtaining the facial feature information of the voice publisher, and using the pre-stored facial feature information of the vehicle owner or operator to distinguish whether the voice publisher is the vehicle owner / operator or the road user 2. The vehicle camera 14 can be installed inside and / or outside the vehicle compartment of the vehicle 1.

[0040] In step S4, when the voice information includes a predetermined control instruction assigned to the identity type of the voice publisher, the vehicle 1 can be controlled at least based on the voice information. Here, different effective instructions can be set for different identity types, for example, the predetermined control instruction assigned to the owner or operator includes a parking instruction, a driving instruction and / or a deceleration instruction, etc., while the predetermined control instruction assigned to the road user only includes a parking instruction, so that the automatic driving system 10 of the vehicle 1 reacts differently to the voice information of the owner / operator and the road user 2.

[0041] like Figure 2 As shown, the vehicle 1 is traveling toward the road user 2. As the distance between the vehicle 1 and the road user 2 is getting closer and closer, a collision accident may occur. The owner or operator may issue a parking command of "stop", and the vehicle 1 may be controlled to stop when the voice information contains the parking command of the owner or operator. Optionally, the owner or operator may also issue a parking command of "stop" or a deceleration command of "be careful" or "pay attention to safety", and the vehicle 1 may be controlled to decelerate when the voice information contains the deceleration command of the owner or operator, and the current driving environment may be re-detected with higher detection accuracy. In an emergency, the road user 2 may also issue a voice message such as "stop", so as to control the vehicle 1 to perform an emergency stop based on the parking command of the road user 2. The owner or operator may issue a driving command of "continue driving" after determining that the driving environment is safe, and the automatic driving system 10 may control the vehicle 1 to continue driving after obtaining the driving command of the owner or operator.

[0042] According to the present application, when an autonomous driving vehicle is traveling at a low speed, voice information from inside and / or outside the vehicle can be obtained, and the autonomous driving vehicle can be controlled based on the voice information. Since different control command permissions are configured for voice publishers of different identity types, the vehicle can be quickly controlled through voice commands in an emergency situation, eliminating the tedious process of entering control commands through an application and avoiding vehicle accidents as much as possible.

[0043] In addition, it should be noted that the step numbers described herein do not necessarily represent a chronological order, but are merely a figure mark. The order can be changed according to specific circumstances as long as the technical purpose of the present application can be achieved.

[0044] Figure 3 A schematic block diagram of an autonomous driving system according to an exemplary embodiment of the present application is shown.

[0045] like Figure 3 As shown, the automatic driving system 10 may include the following components:

[0046] - a vehicle speed monitoring unit 11, which is configured to monitor the driving speed of the vehicle 1, wherein the vehicle speed monitoring unit may include a vehicle speed sensor for detecting wheel speed and / or a positioning device for real-time detection of the vehicle position, etc.;

[0047] - a vehicle-mounted microphone 12, which is configured to obtain voice information from inside and / or outside the vehicle compartment of the vehicle 1, wherein the number of the vehicle-mounted microphones 12 is greater than or equal to 3;

[0048] - A control unit 13 configured to carry out the method according to the present application.

[0049] Optionally, the autonomous driving system 10 may further include a vehicle-mounted camera 14 , which is configured to obtain facial feature information of the voice publisher and may be installed inside and / or outside a cabin of the vehicle 1 .

[0050] If an embodiment includes an “and / or” relationship between a first feature and a second feature, it should be interpreted as follows: according to one embodiment, the embodiment has both the first feature and the second feature, and according to another embodiment, the embodiment has either only the first feature or only the second feature.

[0051] Although specific embodiments have been described above, these embodiments are not intended to limit the scope of the present disclosure, even when only a single embodiment is described with respect to specific features. The feature examples provided in the present disclosure are intended to be illustrative, not restrictive, unless otherwise stated. In specific implementations, multiple features may be combined with each other, where technically feasible, according to actual needs. Various substitutions, changes, and modifications may also be conceived without departing from the spirit and scope of the present application.

Claims

1. A method for controlling an autonomous vehicle, the method comprising: When the vehicle (1) turns on the automatic driving function, monitoring the driving speed of the vehicle (1); When the driving speed of the vehicle (1) is lower than a predetermined speed threshold, acquiring voice information from inside and / or outside the vehicle cabin of the vehicle (1); Analyze and process the acquired voice information to determine the content of the voice information and the identity information of the voice publisher; as well as If the voice message contains a predefined control command which is assigned to an identity type of the speaker of the voice, the vehicle (1) is controlled at least based on the voice message.

2. The method according to claim 1, wherein: The location information of the voice publisher is determined with the help of a vehicle microphone arranged inside and / or outside the vehicle compartment, and the identity information of the voice publisher is determined based on the location information of the voice publisher and the location information of the vehicle key. When the location information of the voice publisher is consistent with the location information of the vehicle key, the identity information of the voice publisher is determined to be the vehicle owner or operator; when the location information of the voice publisher is inconsistent with the location information of the vehicle key, the identity information of the voice publisher is determined to be a road user.

3. A method according to any one of the preceding claims, wherein: When the number of vehicle microphones arranged outside the vehicle cabin is less than a predetermined number threshold, the window of the vehicle (1) is opened so that the vehicle microphones arranged inside the vehicle cabin can acquire voice information from outside the vehicle cabin.

4. A method according to any one of the preceding claims, wherein: Determining the identity information of the voice publisher based on the voice characteristic information of the vehicle owner or operator, wherein the voice characteristic information includes accent, timbre and / or pitch; and / or Determine the identity information of the voice publisher based on the facial feature information of the vehicle owner or operator and the facial feature information of the voice publisher; and / or The language type of the acquired voice information is determined, and semantic analysis is performed on the voice information based on the determined language type, thereby determining the content of the voice information.

5. A method according to any one of the preceding claims, wherein: The predetermined control command assigned to the road user includes a parking command; and / or The predetermined control command assigned to the vehicle owner or operator includes a parking command, a driving command and / or a deceleration command.

6. A method according to any one of the preceding claims, wherein: When the voice information contains a parking instruction from a road user, the vehicle (1) is controlled to park, and after obtaining a driving instruction from a vehicle owner or operator, the vehicle (1) is controlled to continue driving; and / or When the voice information contains a parking instruction from the vehicle owner or operator, controlling the vehicle (1) to park; and / or When the voice information contains a deceleration instruction from the vehicle owner or operator, the vehicle (1) is controlled to decelerate and the driving environment of the vehicle (1) is re-detected.

7. An automatic driving system (10) for executing the method according to any one of the preceding claims, wherein: The automatic driving system (10) comprises the following components: A vehicle speed monitoring unit (11) configured to monitor the driving speed of the vehicle (1); A vehicle-mounted microphone (12) configured to acquire voice information from inside and / or outside a vehicle compartment of the vehicle (1); and A control unit (13) configured to carry out the method according to any one of the preceding claims.

8. The automatic driving system (10) according to claim 7, wherein: The automatic driving system (10) further comprises a vehicle-mounted camera (14), which is configured to obtain facial feature information of the voice publisher and is installed inside and / or outside the vehicle compartment of the vehicle (1).

9. A vehicle (1), comprising an automatic driving system (10) according to claim 7 or 8. 10 . A computer program product, such as a computer-readable program carrier, comprising or storing computer program instructions, which, when executed by a processor, at least assist in implementing the steps of the method according to claim 1 .

Images