Method, device, electronic equipment and system for controlling an autonomous vehicle

Abstract

The present disclosure provides a method, device, electronic device, system, storage medium and program product for controlling an autonomous vehicle, relates to the technical field of artificial intelligence, and in particular to the technical field of intelligent transportation, autonomous driving, high-definition map, cloud service, and Internet of Vehicles. The specific implementation scheme is: in response to receiving cloud information from the cloud and road information from the road, performing fusion processing on vehicle information from the vehicle, the cloud information and the road information to obtain vehicle fusion information, the cloud information, the road information and the vehicle information each comprising information related to the vehicle; based on the vehicle fusion information, generating driving decision information for controlling the vehicle; based on the driving decision information, generating a control instruction for controlling the vehicle; and controlling the vehicle according to the control instruction.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of intelligent transportation, autonomous driving, high-precision map, cloud service, and Internet of Vehicles, and more particularly to a method and device for controlling an autonomous vehicle, an electronic device, a system for controlling an autonomous vehicle, a storage medium, and a program product. BACKGROUND

[0002] Autonomous driving technology mainly includes two technical routes, namely, a single-vehicle intelligent technical route and an intelligent network technical route. By using the single-vehicle intelligent technical route, the operation of an autonomous vehicle is more sensitive, and the driving speed can be improved. By using the intelligent network technical route, the perception and analysis capabilities of an autonomous vehicle are more accurate, and the driving safety can be improved. How to combine the advantages of the two technical routes to support intelligent autonomous driving has become a research direction. SUMMARY

[0003] The present disclosure provides a method and device for controlling an autonomous vehicle, an electronic device, a system for controlling an autonomous vehicle, a storage medium, and a program product.

[0004] According to an aspect of the present disclosure, a method for controlling an autonomous vehicle is provided, including: in response to receiving cloud information from a cloud and road information from a road, performing fusion processing on vehicle-end information from the vehicle, the cloud information, and the road information to obtain vehicle-end fusion information, wherein the cloud information, the road information, and the vehicle-end information each include information related to the vehicle; based on the vehicle-end fusion information, generating driving decision information for controlling the vehicle; based on the driving decision information, generating a control instruction for controlling the vehicle; and controlling the vehicle according to the control instruction.

[0005] According to another aspect of the present disclosure, a method for controlling an autonomous vehicle is provided, including: in response to receiving vehicle-end information from a vehicle end and road information from a road end, performing fusion processing on cloud information, the vehicle-end information, and the road information to obtain cloud-end fusion information, wherein the road information, the vehicle-end information, and the cloud information each include information related to the vehicle; based on the cloud-end fusion information, generating cloud-end auxiliary driving decision information for controlling the vehicle; and in response to receiving a request from the vehicle end for requesting auxiliary decision information, sending the cloud-end auxiliary driving decision information to the vehicle end, so that the vehicle end generates a control instruction for controlling the vehicle based on the cloud-end auxiliary driving decision information.

[0006] According to another aspect of the present disclosure, a method for controlling an autonomous vehicle is provided, including: in response to receiving vehicle-end information from a vehicle end and cloud-end information from a cloud end, performing fusion processing on road-end information, the vehicle-end information and the cloud-end information to obtain road-end fusion information, wherein the cloud-end information, the vehicle-end information and the road-end information each comprises information related to the vehicle; based on the road-end fusion information, generating road-end auxiliary driving decision information for controlling the vehicle; and receiving a request from the vehicle end for requesting auxiliary decision information, and sending the road-end auxiliary driving decision information to the vehicle end so that the vehicle end generates a control instruction for controlling the vehicle according to the road-end auxiliary driving decision information.

[0007] According to another aspect of the present disclosure, a system for controlling an autonomous vehicle is provided, including: a vehicle end for, in response to receiving cloud-end information from a cloud end and road-end information from a road end, performing fusion processing on vehicle-end information from the vehicle, the cloud-end information and the road-end information to obtain vehicle-end fusion information, wherein the cloud-end information, the road-end information and the vehicle-end information each comprises information related to the vehicle; based on the vehicle-end fusion information, generating driving decision information for controlling the vehicle; based on the driving decision information, generating a control instruction for controlling the vehicle; and controlling the vehicle according to the control instruction; a cloud end for sending the cloud-end information to the vehicle end; and a road end for sending the road-end information to the vehicle end.

[0008] According to another aspect of the present disclosure, an apparatus for controlling an autonomous vehicle is provided, including: a vehicle-end fusion module for, in response to receiving cloud-end information from a cloud end and road-end information from a road end, performing fusion processing on vehicle-end information from the vehicle, the cloud-end information and the road-end information to obtain vehicle-end fusion information, wherein the cloud-end information, the road-end information and the vehicle-end information each comprises information related to the vehicle; a vehicle-end decision module for, based on the vehicle-end fusion information, generating driving decision information for controlling the vehicle; a vehicle-end control module for, based on the driving decision information, generating a control instruction for controlling the vehicle; and a vehicle-end execution module for controlling the vehicle according to the control instruction.

[0009] According to another aspect of the present disclosure, there is provided an apparatus for controlling an autonomous vehicle, comprising: a cloud fusion module configured to, in response to receiving vehicle-end information from a vehicle-end and road-end information from a road-end, perform a fusion process on cloud-end information, the vehicle-end information and the road-end information to obtain cloud-end fusion information, wherein the road-end information, the vehicle-end information, and the cloud-end information each comprise information related to the vehicle; a cloud decision module configured to generate cloud-end assisted driving decision information for controlling the vehicle based on the cloud-end fusion information; and a cloud decision sending module configured to, in response to receiving a request from the vehicle-end for requesting assisted decision information, send the cloud-end assisted driving decision information to the vehicle-end so that the vehicle-end generates control instructions for controlling the vehicle based on the cloud-end assisted driving decision information.

[0010] According to another aspect of the present disclosure, there is provided an apparatus for controlling an autonomous vehicle, comprising: a road-end fusion module configured to, in response to receiving vehicle-end information from a vehicle-end and cloud-end information from a cloud-end, perform a fusion process on road-end information, the vehicle-end information and the cloud-end information to obtain road-end fusion information, wherein the cloud-end information, the vehicle-end information, and the road-end information each comprise information related to the vehicle; a road-end decision module configured to generate road-end assisted driving decision information for controlling the vehicle based on the road-end fusion information; and a road-end decision sending module configured to receive a request from the vehicle-end for requesting assisted decision information, and send the road-end assisted driving decision information to the vehicle-end so that the vehicle-end generates control instructions for controlling the vehicle according to the road-end assisted driving decision information.

[0011] According to another aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method according to the present disclosure.

[0012] According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are configured to cause a computer to perform a method according to the present disclosure.

[0013] According to another aspect of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method according to the present disclosure.

[0014] It should be understood that the contents described in this part are not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0016] Figure 1 An exemplary system architecture to which the method and device for controlling an autonomous vehicle according to embodiments of the present disclosure can be applied is schematically shown;

[0017] Figure 2 A system block diagram for controlling an autonomous vehicle according to embodiments of the present disclosure is schematically shown;

[0018] Figure 3 A flowchart of a method for controlling an autonomous vehicle according to embodiments of the present disclosure is schematically shown, applied to a vehicle end;

[0019] Figure 4 A schematic diagram of generating driving decision information according to embodiments of the present disclosure is schematically shown;

[0020] Figure 5 A schematic diagram of generating auxiliary driving decision information according to another embodiment of the present disclosure is schematically shown;

[0021] Figure 6 A schematic diagram of generating auxiliary control instructions according to another embodiment of the present disclosure is schematically shown;

[0022] Figure 7 A flowchart of a method for controlling an autonomous vehicle according to another embodiment of the present disclosure is schematically shown, applied to a cloud end;

[0023] Figure 8 A flowchart of a method for controlling an autonomous vehicle according to another embodiment of the present disclosure is schematically shown, applied to a road end;

[0024] Figure 9 A schematic diagram of generating road end auxiliary control instructions according to another embodiment of the present disclosure is schematically shown;

[0025] Figure 10 A block diagram of a device for controlling an autonomous vehicle according to embodiments of the present disclosure is schematically shown, applied to a vehicle end;

[0026] Figure 11 A block diagram of a device for controlling an autonomous vehicle according to embodiments of the present disclosure is schematically shown, applied to a cloud end;

[0027] Figure 12 a block diagram of an apparatus for controlling an autonomous vehicle according to an embodiment of the present disclosure is shown schematically, which is applied to a road end; and

[0028] Figure 13 a block diagram of an electronic device adapted to implement a method for controlling an autonomous vehicle according to an embodiment of the present disclosure is shown schematically. DETAILED DESCRIPTION

[0029] Exemplary embodiments of the present disclosure are described herein with reference to the accompanying drawings, which are included to provide a thorough understanding of the embodiments of the present disclosure, and are taken to illustrate the preferred embodiments of the present disclosure, but not to limit the present disclosure. Accordingly, those of ordinary skill in the art will recognize that there are numerous variations and modifications that can be made to the embodiments described and / or illustrated herein without departing from the scope and spirit of the present disclosure. As well, in the interest of clarity, not all of the familiar features of a technology can be described or shown in this description.

[0030] The present disclosure provides a method, an apparatus, an electronic device, a system for controlling an autonomous vehicle, a storage medium, and a program product.

[0031] According to an embodiment of the present disclosure, a method for controlling an autonomous vehicle is provided, comprising: in response to receiving cloud information from a cloud and road information from a road, performing fusion processing on vehicle end information from a vehicle, the cloud information and the road information to obtain vehicle end fusion information, wherein the cloud information, the road information and the vehicle end information each comprise information related to the vehicle; generating driving decision information for controlling the vehicle based on the vehicle end fusion information; generating a control instruction for controlling the vehicle based on the driving decision information; and controlling the vehicle according to the control instruction.

[0032] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information comply with relevant laws and regulations, necessary security measures are taken, and the public order and good customs are not violated.

[0033] In the technical solutions of the present disclosure, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0034] Figure 1 An exemplary system architecture to which the method and apparatus for controlling an autonomous vehicle according to an embodiment of the present disclosure can be applied is shown schematically.

[0035] It should be noted that, Figure 1 The shown is only an example of a system architecture to which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but it does not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0036] As shown in Figure 1 The system architecture 100 according to the embodiment can include a system for controlling an autonomous vehicle. For example, the system architecture 100 can include a vehicle end 101, a cloud end 102, and a road end 103.

[0037] As shown in Figure 1 The vehicle end 101 can include a vehicle configured to operate in an autonomous driving mode, for example, L4. For example, the vehicle end 101 can include an autonomous vehicle, but is not limited thereto. The vehicle end 101 can also include a vehicle configured to operate in a manual mode, for example, L0, or a partially autonomous driving mode, for example, L1, L2, or L3.

[0038] As shown in Figure 1 The cloud end 102 can include a cloud server. The cloud server is a host product in a cloud computing service system, which solves the defects of large management difficulty and weak business scalability in traditional physical host and VPS (Virtual Private Server, VPS) services. In addition, the cloud server can be one of the following: a cloud control platform, a third-party platform, a vehicle-road cooperation management system, a center subsystem, an edge computing platform, and a cloud computing platform. The cloud control platform can include at least one of the following: an edge cloud control platform, a regional cloud control platform, and a central cloud control platform. The third-party platform can include at least one of the following: a traffic management platform, a map platform, a travel service platform, a vehicle management platform, and an OEM (Original Entrusted Manufacture) platform.

[0039] As shown in Figure 1 The road end 103 can be a device installed on a traffic road for collecting traffic information, for example, a roadside device. The roadside device can also include a connecting piece and a sensing piece. The connecting piece is used to fix the roadside device to an external device. The sensing piece can refer to a device with information collection function.

[0040] As shown in Figure 1 The vehicle end, the cloud end, and the road end can be communicatively connected to each other through various communication connection types. For example, the communication connection types can include at least one of the following: wired communication and wireless communication. For example, the wireless communication can include V2X (Vehicle to X). For example, the V2X can include at least one of the following: DSRC (Dedicated Short Range Communication) based V2X and cellular mobile communication based V2X. The cellular mobile communication based V2X can include at least one of the following: 4G (The 4th Generation) based V2X, 5G (The 5th Generation) based V2X, and C-V2X (Cellular Vehicle to Everything). thGeneration Mobile Communication Technology, 4G) and the vehicle wireless communication based on the fifth generation mobile communication (The 5 th Generation Mobile Communication Technology, 5G) for vehicles.

[0041] According to the embodiments of the present disclosure, the vehicle end, the cloud end and the road end are communicatively connected with each other, and the integrated perception, the integrated decision planning and the integrated control of the vehicle end, the cloud end and the road end can be realized, and the automatic driving vehicle can be cooperatively controlled by the vehicle end, the cloud end and the road end, and the safety and the intelligence of the automatic driving vehicle in the automatic driving operation mode can be improved.

[0042] According to the embodiments of the present disclosure, the automatic driving vehicle can include vehicle-mounted sensors and vehicle execution components. The vehicle-mounted sensors can include a camera, a global positioning system, an inertial measurement unit, a radar unit, a light detection and ranging unit, and the like. The vehicle execution components can include commonly used components for realizing vehicle driving, such as an engine, a wheel, a steering wheel, a transmission, and the like. The automatic driving vehicle can further include a vehicle end positioning unit, and the vehicle end positioning unit can include at least one of a global positioning system (GPS), a BeiDou satellite navigation system (BDS), a global navigation satellite system (GNSS), a GLONASS (GLObal NAvigation Sarwllite System), an inertial measurement unit (IMU), a visual sensor, a vehicle end laser radar and a vehicle end radar. In addition, the automatic driving vehicle can further include a software application. The software application can include at least one of a navigation type application, an entertainment type application and an instant messaging type application.

[0043] According to embodiments of the present disclosure, the road side device can include road side sensors. The road side sensors can include, but are not limited to, radars, cameras, traffic lights and signs, intelligent bollards, and environmental sensors, etc. The road side device can also include a road side perception unit and a road side computing unit (RSCU). The road side computing unit can be a small server modified to meet the extreme conditions of low voltage, high temperature and high humidity of the road side lamp post. In addition, the road side computing unit can be replaced by a mobile edge computing unit (MEC). The deployment of the road side device can be determined according to actual business needs. For example, the road side sensors can include at least one of a road side vision sensor, a road side radar, and a road side lidar. The road side perception unit can include a processor and a memory. In another system architecture, the road side perception unit itself can include computing functions.

[0044] Figure 2 A system block diagram for controlling an autonomous vehicle according to embodiments of the present disclosure is schematically shown.

[0045] As shown in Figure 2 , the vehicle end V100 can include a vehicle end perception unit V110, a vehicle end decision unit V120, a vehicle end control unit V130, and an execution component V140. The road end I100 can include a road end perception unit I110, a road end decision unit I120, and a road end control unit I130. The cloud end N100 can include a cloud end perception unit N110, a cloud end decision unit N120, and a cloud end control unit N130.

[0046] As shown in Figure 2 , the vehicle end perception unit V110 of the vehicle end V100 can receive cloud end information from the cloud end perception unit N110, and road end information from the road end perception unit I110. The vehicle end perception unit V110 can perform fusion processing on the vehicle end information, the cloud end information, and the road end information to obtain vehicle end fusion information.

[0047] As shown in Figure 2 , the road end perception unit I110 can receive cloud end information from the cloud end perception unit N110, and vehicle end information from the vehicle end perception unit V110. The road end perception unit I110 can perform fusion processing on the vehicle end information, the cloud end information, and the road end information to obtain road end fusion information.

[0048] As shown in Figure 2 , the cloud end perception unit N110 can receive road end information from the road end perception unit I110, information from a third party platform, and vehicle end information from the vehicle end perception unit V110, and perform fusion processing on the vehicle end information, the cloud end information, and the road end information to obtain cloud end fusion information.

[0049] As shown in FIG. 1, the vehicle-end decision unit V120 can generate driving decision information by using the vehicle-end fusion information, and the vehicle-end control unit V130 can generate control instructions by using the driving decision information. The driving decision information can include routing information, behavior decision information, and motion planning information. The control instructions can be commands for controlling the execution components V140 of the vehicle, such as acceleration instructions, deceleration instructions, steering instructions, or braking instructions. Figure 2 As shown in FIG. 1, in the case of a failure of the vehicle-end decision unit V120, the cloud-end decision unit N120 can generate cloud-end driving decision information by using the cloud-end fusion information. Alternatively, the road-end decision unit I120 generates road-end driving decision information by using the road-end fusion information, as the driving decision information of the vehicle end.

[0050] Figure 2 As shown in FIG. 1, in the case of a failure of the vehicle-end control unit V130, the cloud-end control unit N130 can generate cloud-end control instructions, or the road-end control unit I130 can generate road-end control instructions, as the control instructions of the vehicle end to control the vehicle to run in the autonomous driving mode.

[0051] As shown in FIG. 1, in the case of a failure of the vehicle-end decision unit V120, the cloud-end decision unit N120 can generate cloud-end driving decision information by using the cloud-end fusion information. Alternatively, the road-end decision unit I120 generates road-end driving decision information by using the road-end fusion information, as the driving decision information of the vehicle end. Figure 2 The system for controlling an autonomous vehicle provided by the embodiments of the present disclosure can make the vehicle end, the cloud end, and the road end work together to realize the vehicle running in the VICAD mode, thereby improving the safety, intelligence, and control effectiveness of the autonomous driving.

[0052] It should be noted that the serial numbers of the operations in the following method are only used to represent the operations and are not intended to represent the execution order of the operations. The method does not need to be executed in the order shown unless otherwise specified.

[0053]

[0054] A flowchart of a method for controlling an autonomous vehicle according to an embodiment of the present disclosure is schematically shown. Figure 3 As shown in FIG. 1, the method is applied to the vehicle end and includes operations S310-S340.

[0055] Figure 3 In operation S310, in response to receiving cloud-end information from the cloud end and road-end information from the road end, the vehicle-end information from the vehicle, the cloud-end information, and the road-end information are fused to obtain vehicle-end fusion information. The cloud-end information, the road-end information, and the vehicle-end information each include information related to the vehicle.

[0056] In operation S310, in response to receiving cloud-end information from the cloud end and road-end information from the road end, the vehicle-end information from the vehicle, the cloud-end information, and the road-end information are fused to obtain vehicle-end fusion information. The cloud-end information, the road-end information, and the vehicle-end information each include information related to the vehicle. ​​

[0057] In operation S320, driving decision information for controlling the vehicle is generated based on the vehicle-end fusion information.

[0058] In operation S330, control instructions for controlling the vehicle are generated based on the driving decision information.

[0059] In operation S340, the vehicle is controlled according to the control instructions.

[0060] According to an embodiment of the present disclosure, the cloud-end information can be information related to a perceived object. The cloud-end information can include at least one of the following: other vehicle-end information from other autonomous vehicles, high-precision map information from a third-party platform, and the like.

[0061] According to an embodiment of the present disclosure, the road-end information can be information related to a perceived object collected by a road-end sensor. The road-end information can include at least one of the following: road-end information of a road-side sensor itself and other road-end information of other road-side sensors.

[0062] According to an embodiment of the present disclosure, the vehicle-end information can be information related to a perceived object collected by a vehicle-end sensor. The vehicle-end information can include at least one of the following: vehicle-end information of an autonomous vehicle itself and other vehicle-end information of other autonomous vehicles.

[0063] According to an embodiment of the present disclosure, the perceived object can include at least one of the following: an autonomous vehicle, an interactive object, an object related to a driving path, and an object related to a driving environment. The interactive object can refer to an object having an interactive relationship with the autonomous vehicle. The interactive relationship can include at least one of the following: an interactive conflict and a road blockage. The interactive object can be referred to as an obstacle. The interactive object can include at least one of the following: a static interactive object and a dynamic interactive object. The static interactive object can refer to an interactive object in a stationary state. The dynamic interactive object can refer to an interactive object in a motion state. The object related to the driving path can include at least one of the following: a passable road, a signboard, a traffic signal, and a lane line. The object related to the driving environment can include at least one of the following: road information and weather information.

[0064] According to an embodiment of the present disclosure, the fusion processing of the vehicle-end information, the cloud-end information, and the road-end information can include fusion processing of at least two of the vehicle-end information, the cloud-end information, and the road-end information.

[0065] According to an embodiment of the present disclosure, the fusion processing can include: converting the format, for example, the coordinate system, of the vehicle-end information, the cloud-end information and the road-end information respectively, and performing intersection processing on the same information and union processing on the different information. For example, for the road-end information, information beyond the visual range of the vehicle can be included, and the vehicle-end information and the road-end information can be union processed, that is, combined, so that the vehicle-end fusion information includes the vehicle-end information obtained by the vehicle perception unit and the information about the beyond visual range that cannot be perceived by the vehicle perception unit.

[0066] According to an embodiment of the present disclosure, the driving decision information can be generated based on the vehicle-end fusion information. The driving decision information can include one or more of route planning information, behavior decision information and motion planning information.

[0067] According to an embodiment of the present disclosure, the control instruction can be generated based on the driving decision information. The control instruction can be a control command for controlling the control components of the vehicle, for example, the control instruction can include an acceleration instruction, a deceleration instruction, a steering instruction or a braking instruction, etc.

[0068] According to other embodiments of the present disclosure, the vehicle-end can also receive the cloud-end information from the cloud-end, fuse the vehicle-end information and the cloud-end information, and take the fused information as the vehicle-end fusion information. Alternatively, the vehicle-end receives the road-end information from the road-end, fuses the vehicle-end information and the road-end information, and takes the fused information as the vehicle-end fusion information.

[0069] According to an embodiment of the present disclosure, compared with the vehicle-end fusion information obtained by fusing the vehicle-end information with the cloud-end information or fusing the vehicle-end information with the road-end information, the vehicle-end fusion information obtained by fusing the vehicle-end information, the cloud-end information and the road-end information is more accurate.

[0070] By using the method for controlling the automatic driving vehicle provided by the embodiments of the present disclosure, the vehicle-end can fuse the vehicle-end information, the cloud-end information and the road-end information to obtain the vehicle-end fusion information, realize the integrated cooperation of the cloud-end, the road-end and the cloud-end, so that the automatic driving vehicle is more accurate and sensitive in perceiving the surrounding traffic environment during driving, and the intelligence and sensitivity of the driving decision information and the control instruction of the automatic driving generated based on the vehicle-end fusion information are improved.

[0071] Figure 4 A schematic diagram for generating driving decision information according to an embodiment of the present disclosure is schematically shown.

[0072] As Figure 4As shown, the vehicle end V100 can receive the cloud end decision information from the cloud end N100 and the road end decision information from the road end I100 by using the vehicle end perception unit V110. The vehicle end information, the cloud end information and the road end information are fused to obtain vehicle end fusion information. The vehicle end decision unit V120 is used to generate vehicle end decision information based on the vehicle end fusion information. The cloud end decision information, the road end decision information and the vehicle end decision information are fused by using the vehicle end decision unit V120 to obtain driving decision information.

[0073] According to an embodiment of the present disclosure, the fusion of the cloud end decision information, the road end decision information and the vehicle end decision information can include fusion processing of at least two of the cloud end decision information, the road end decision information and the vehicle end decision information.

[0074] According to an embodiment of the present disclosure, the fusion can be performed according to a predetermined fusion rule that the vehicle end decision information is primary and the cloud end decision information and the road end decision information are secondary, or the fusion can be performed by inputting the cloud end decision information, the road end decision information and the vehicle end decision information into a decision fusion model. The decision fusion model can be a model for outputting driving decision information, and the decision fusion model can be a trained deep learning model. The fusion can also be performed by taking the road end decision information or the cloud end decision information as the driving decision information when the vehicle end decision information cannot be generated.

[0075] According to an embodiment of the present disclosure, the vehicle end, the road end and the cloud end can each perform operations for generating decision information at the same time. For example, the vehicle end can generate vehicle end decision information based on vehicle end fusion information. For example, the road end can fuse the road end information, the vehicle end information and the cloud end information to generate road end fusion information. The road end decision information is generated based on the road end fusion information. For example, the cloud end can fuse the road end information, the vehicle end information and the cloud end information to generate cloud end fusion information. The cloud end decision information is generated based on the cloud end fusion information. The vehicle end can receive the cloud end decision information from the cloud end and the road end decision information from the road end, and perform fusion operations of decision planning, for example, fuse the cloud end decision information, the road end decision information and the vehicle end decision information to obtain driving decision information. The vehicle end can generate control instructions according to the driving decision information, and then control the vehicle according to the control instructions.

[0076] By using the method for controlling an automatic driving vehicle provided by the embodiments of the present disclosure, the perception information from the vehicle end, the road end and the cloud end can be fused at the vehicle end, and the decision information from the vehicle end, the road end and the cloud end can also be fused at the vehicle end, so that the generated vehicle end fusion information is comprehensive and accurate, and the generated driving decision information is also comprehensive and accurate, thereby improving the flexibility and safety of automatic driving.

[0077] Figure 5A schematic diagram illustrating generation of auxiliary driving decision information according to another embodiment of the present disclosure is shown.

[0078] As shown in Figure 5 In a case where it is determined that the decision operation result satisfies the predetermined decision operation condition, for example, in a case where it is determined that the vehicle end decision unit V120 is unable to send the driving decision information to the vehicle end control unit V130, the vehicle end V100 can send a request for requesting the auxiliary driving decision information to the auxiliary decision end. The vehicle end control unit V130 can receive the auxiliary driving decision information from the auxiliary decision end. The control instruction for controlling the vehicle is generated according to the auxiliary driving decision information.

[0079] According to an embodiment of the present disclosure, the decision operation result is used to represent a result of a case where the decision operation is performed. The decision operation is used to represent that the driving decision information for controlling the vehicle is generated based on the fusion information. The predetermined decision operation condition can be used to represent that the case where the decision operation is performed is a failure. For example, the predetermined decision operation condition can mean that the vehicle end decision unit for generating the driving decision information fails and is unable to perform the operation for generating the driving decision information. Alternatively, the predetermined decision operation condition can mean that the vehicle end decision unit for generating the driving decision information is unable to send the driving decision information to the vehicle end control unit.

[0080] As shown in Figure 5 The auxiliary decision end includes the road end I100, for example, the road end decision unit I120, or the cloud end N100, for example, the cloud end decision unit N120. The vehicle end V100 can send the request for requesting the auxiliary driving decision information to the road end I100 or the cloud end N100, or preferentially send the request for requesting the auxiliary driving decision information to the cloud end N100, as long as the vehicle end control unit V130 is able to generate the control instruction for controlling the vehicle according to the auxiliary driving decision information in response to receiving the auxiliary driving decision information. The vehicle end control unit V130 can send the control instruction to the execution component V140, and the execution component V140 controls the vehicle to operate according to the control instruction.

[0081] By using the method for controlling the automatic driving vehicle provided by the embodiment of the present disclosure, the vehicle end can determine the case where the decision operation result satisfies the predetermined decision operation condition, and use the auxiliary decision end to send the auxiliary driving decision information to provide the decision planning service for the vehicle, so as to reduce the probability of the vehicle having the decision planning failure and improve the intelligence of the vehicle in the automatic driving mode.

[0082] Figure 6 A flowchart illustrating generation of auxiliary control instruction according to an embodiment of the present disclosure is shown.

[0083] As shown in Figure 6As shown, when the vehicle-side V100 determines that the control operation result meets the predetermined control operation conditions, for example, when it determines that the vehicle-side control unit V130 cannot send a control command to the execution component V140, the vehicle-side V100 can send a request to the auxiliary control terminal for an auxiliary control command. The execution component V140 can receive the auxiliary control command from the auxiliary control terminal and control the vehicle according to the auxiliary control command.

[0084] According to embodiments of this disclosure, the control operation result can be used to characterize the outcome of executing the control operation. The control operation characterizes the generation of control commands for controlling the vehicle based on driving decision information. A predetermined control operation condition can be used to characterize the failure of executing the control operation. For example, a predetermined control operation condition could mean that the vehicle-side control unit used to generate the control commands malfunctions and cannot perform the operation to generate the control commands. Alternatively, a predetermined control operation condition could mean that the vehicle-side control unit used to generate the control commands cannot send the control commands to the execution component.

[0085] like Figure 6 As shown, the auxiliary control terminal includes a roadside I100, such as a roadside control unit I130, or a cloud-based N100, such as a cloud-based control unit N130. The vehicle-side V100 can simultaneously send requests for auxiliary control commands to either the roadside I100 or the cloud-based N100, or it can prioritize sending requests for auxiliary control commands to the N100, as long as the auxiliary control command can be generated. Upon receiving the auxiliary control command, the execution component V140 controls the vehicle according to the auxiliary control command.

[0086] The method for controlling autonomous vehicles provided in this disclosure, when applied to the vehicle, can provide control services to the vehicle by sending auxiliary control commands through an auxiliary control terminal when the control operation result meets the predetermined control operation conditions. This reduces the probability of control failures in the vehicle and improves the intelligence of the vehicle in autonomous driving mode.

[0087] Figure 7 A flowchart illustrating a method for controlling an autonomous vehicle according to another embodiment of the present disclosure is shown schematically.

[0088] like Figure 7 As shown, this method is applied to the cloud and includes operations on S710 to S730.

[0089] When operating the S710, in response to receiving vehicle-side information from the vehicle and roadside information from the roadside, the cloud-based information, vehicle-side information, and roadside information are fused to obtain cloud-fused information. The roadside information, vehicle-side information, and cloud-based information each include vehicle-related information.

[0090] At operation S720, cloud-side auxiliary driving decision information for controlling the vehicle is generated based on the cloud-side fusion information.

[0091] At operation S730, in response to receiving a request from the vehicle-side for the auxiliary decision information, the cloud-side auxiliary driving decision information is sent to the vehicle-side so that the vehicle-side generates control instructions for controlling the vehicle based on the cloud-side auxiliary driving decision information.

[0092] According to an embodiment of the present disclosure, the cloud-side fusion information can be generated in a similar manner to the vehicle-side fusion information, and the difference between the cloud-side fusion information and the vehicle-side fusion information is that the cloud-side fusion information is generated by fusing the cloud-side information, the vehicle-side information, and the road-side information, with the cloud side as the execution subject.

[0093] According to an embodiment of the present disclosure, the cloud-side auxiliary driving decision information for controlling the vehicle can be generated based on the cloud-side fusion information. However, it is not limited thereto. Generating the cloud-side auxiliary driving decision information for controlling the vehicle based on the cloud-side fusion information can further include generating cloud-side driving decision information for controlling the vehicle based on the cloud-side fusion information, receiving road-side driving decision information from the road-side, and fusing the cloud-side driving decision information and the road-side driving decision information to generate the cloud-side auxiliary driving decision information.

[0094] According to an embodiment of the present disclosure, the cloud-side information can include vehicle information received by the cloud side from other vehicles, high-precision map information, and the like sent by a third-party platform.

[0095] The method for controlling an autonomous vehicle provided by the embodiment of the present disclosure is applied to the cloud side, and the cloud side can collect vehicle-side information, road-side information, and cloud-side information to obtain cloud-side fusion information. The cloud-side auxiliary driving decision information is generated based on the cloud-side fusion information. In the case where the vehicle-side decision unit for generating driving decision information fails to perform the operation for generating driving decision information, or in the case where the vehicle-side decision unit for generating driving decision information fails to send the driving decision information to the vehicle-side control unit, the cloud-side auxiliary driving decision information can be sent to the vehicle side so that the vehicle side can use the cloud-side auxiliary driving decision information to realize cloud-side remote assistance for autonomous driving. In this way, the cloud side, the road side, and the vehicle side work together to improve the intelligence of decision planning and control of autonomous driving during the driving process of the autonomous vehicle.

[0096] According to an embodiment of the present disclosure, after operation S720, the cloud-side auxiliary driving decision information for controlling the vehicle is generated based on the cloud-side fusion information, the method can further perform the following operation.

[0097] For example, based on the cloud-assisted driving decision information, cloud-assisted control instructions for controlling the vehicle are generated. In response to receiving a request from the vehicle end for requesting the assistance control instructions, the cloud-assisted control instructions are sent to the vehicle end so that the vehicle end controls the vehicle according to the cloud-assisted control instructions.

[0098] According to embodiments of the present disclosure, the capability of generating cloud-assisted control instructions for controlling the vehicle based on cloud-assisted driving decision information is set at the cloud end. In the case that the vehicle end control unit for generating the control instructions fails and cannot perform the operation for generating the control instructions, or in the case that the vehicle end control unit for generating the control instructions cannot send the control instructions to the execution component, the cloud end is utilized to take over the vehicle. Cloud end integrated perception, generation of cloud-assisted driving decision information and cloud-assisted control instructions are implemented to realize remote control of the vehicle operation by the cloud end.

[0099] According to other embodiments of the present disclosure, on the basis of cloud end integrated perception, generation of cloud-assisted driving decision information and cloud-assisted control instructions, a cloud end safety officer mechanism can also be introduced to further modify the assistance control instructions output to the vehicle to overcome the problem of vehicle accidents in extreme scenarios.

[0100] Figure 8 A flowchart of a method for controlling an autonomous vehicle according to another embodiment of the present disclosure is schematically shown.

[0101] As shown in Figure 8 , the method is applied to the road end and includes operations S810-S830.

[0102] In operation S810, in response to receiving vehicle end information from the vehicle end and cloud end information from the cloud end, the road end information, the vehicle end information and the cloud end information are fused to obtain road end fusion information. The cloud end information, the vehicle end information and the road end information each include information related to the vehicle.

[0103] In operation S820, based on the road end fusion information, road end assistance driving decision information for controlling the vehicle is generated.

[0104] In operation S830, a request from the vehicle end for requesting the assistance decision information is received, and the road end assistance driving decision information is sent to the vehicle end so that the vehicle end generates control instructions for controlling the vehicle according to the road end assistance driving decision information.

[0105] According to embodiments of the present disclosure, the road end information is not limited to the road end information perceived by the road end using sensors, but can also include road end information from other road ends. The road end can utilize a road end perception unit, such as a MEC perception unit, to fuse the road end information, the vehicle end information and the cloud end information to generate the road end fusion information.

[0106] According to an embodiment of the present disclosure, the road-side decision unit can generate road-side assisted driving decision information based on the road-side fusion information generated by the road-side perception unit. In the case that the vehicle-side decision unit for generating driving decision information fails to perform the operation for generating driving decision information, or in the case that the vehicle-side decision unit for generating driving decision information fails to send the driving decision information to the vehicle-side control unit, the road-side assisted driving decision information can be sent to the vehicle-side so as to generate control instructions by the vehicle-side using the road-side assisted driving decision information.

[0107] According to an embodiment of the present disclosure, after the road-side assisted driving decision information for controlling the vehicle is generated based on the road-side fusion information in operation S820, the method can further perform the following operation.

[0108] For example, the road-side assisted control instructions for controlling the vehicle are generated based on the road-side assisted driving decision information. The road-side assisted control instructions are sent to the vehicle-side in response to receiving a request from the vehicle-side for requesting the assisted control instructions so as to control the vehicle according to the road-side assisted control instructions by the vehicle-side.

[0109] According to an embodiment of the present disclosure, the road-side is provided with the capability of generating road-side assisted control instructions for controlling the vehicle based on the road-side assisted driving decision information. In the case that the vehicle-side control unit for generating control instructions fails to perform the operation for generating control instructions, or in the case that the vehicle-side control unit for generating control instructions fails to send the control instructions to the execution components, the vehicle can be taken over by the road-side. The road-side integrated perception, the generation of road-side assisted driving decision information and road-side assisted control instructions are implemented to achieve the remote control of the vehicle operation by the road-side.

[0110] According to other embodiments of the present disclosure, the road-side can introduce the intervention and control of the road-side to the traffic infrastructure, such as the signal lights or the variable traffic signs, based on the road-side integrated perception, the generation of road-side assisted driving decision information and road-side assisted control instructions, and further achieve the assisted control of the vehicle through the indirect control of the traffic infrastructure or the traffic environment by the road-side.

[0111] Figure 9 A flowchart of generating road-side assisted control instructions according to an embodiment of the present disclosure is schematically shown.

[0112] As Figure 9As shown, the road end I100 can generate weak control instructions for controlling the traffic infrastructure while the road end control unit I130 generates the road end auxiliary control instructions, or the vehicle end V100 can generate the control instructions while the vehicle end control unit V130 generates the weak control instructions. The traffic infrastructure feeds back the operation state information of the traffic infrastructure or other collected information to the vehicle end control unit V130 or the road end control unit I130, so that the control instructions generated by the vehicle end control unit V130 or the auxiliary control instructions generated by the road end control unit I130 are combined with the operation state information of the traffic infrastructure. The safety and intelligence of the vehicle running in the automatic driving mode are improved.

[0113] According to an embodiment of the present disclosure, the weak control instructions can include instructions for monitoring the occupancy of a parking space, or instructions for controlling the lifting of a lifting rod arranged at a gate, for example. Through the weak control instructions, the vehicle can be assisted to conveniently and quickly travel in the automatic driving mode.

[0114] Figure 10 A block diagram of an apparatus for controlling an automatic driving vehicle according to an embodiment of the present disclosure is schematically shown.

[0115] As Figure 10 shown, the apparatus 1000 for controlling an automatic driving vehicle applied to a vehicle end includes a vehicle end fusion module 1010, a vehicle end decision module 1020, a vehicle end control module 1030, and a vehicle end execution module 1040.

[0116] The vehicle end fusion module 1010 is configured to perform fusion processing on vehicle end information from the vehicle, cloud information from the cloud, and road end information from the road end in response to receiving the cloud information and the road end information, to obtain vehicle end fusion information, wherein the cloud information, the road end information, and the vehicle end information each include information related to the vehicle.

[0117] The vehicle end decision module 1020 is configured to generate driving decision information for controlling the vehicle based on the vehicle end fusion information.

[0118] The vehicle end control module 1030 is configured to generate control instructions for controlling the vehicle based on the driving decision information.

[0119] The vehicle end execution module 1040 is configured to control the vehicle according to the control instructions.

[0120] According to an embodiment of the present disclosure, the apparatus for controlling an automatic driving vehicle further includes a decision request module, a decision receiving module, and a first auxiliary control module.

[0121] The decision request module is used to send a request for assisted driving decision information to the auxiliary decision terminal when the decision operation result meets the predetermined decision operation conditions. The decision operation result is used to characterize the result of the execution of the decision operation, and the decision operation is used to characterize the driving decision information generated for controlling the vehicle based on the vehicle-side fused information. The auxiliary decision terminal includes the roadside or the cloud.

[0122] The decision receiving module is used to receive assisted driving decision information from the auxiliary decision-making terminal.

[0123] The first auxiliary control module is used to generate control commands for controlling the vehicle based on the assisted driving decision information.

[0124] According to embodiments of this disclosure, the apparatus for controlling an autonomous vehicle further includes a control request module, a control receiving module, and an auxiliary execution module.

[0125] The control request module is used to send a request for auxiliary control instructions to the auxiliary control terminal when it is determined that the control operation result meets the predetermined control operation conditions. The control operation result is used to characterize the result of the execution of the control operation, and the control operation is used to characterize the control instructions generated for controlling the vehicle based on driving decision information. The auxiliary control terminal includes the roadside or the cloud.

[0126] The control receiving module is used to receive auxiliary control commands from the auxiliary control terminal.

[0127] The auxiliary execution module is used to control the vehicle according to auxiliary control commands.

[0128] According to embodiments of this disclosure, the vehicle-side decision-making module includes a decision receiving unit, a decision generating unit, and a decision fusion unit.

[0129] The decision receiving unit is used to receive cloud-based decision information from the cloud and road-side decision information from the road end.

[0130] The decision generation unit is used to generate vehicle-side decision information based on vehicle-side fusion information.

[0131] The decision fusion unit is used to fuse cloud-based decision information, roadside decision information, and vehicle-side decision information to obtain driving decision information.

[0132] Figure 11 A block diagram of an apparatus for controlling an autonomous vehicle according to an embodiment of the present disclosure is shown schematically.

[0133] like Figure 11 As shown, the device 1100 for controlling autonomous vehicles is applied to the cloud and includes: a cloud fusion module 1110, a cloud decision module 1120, and a cloud decision transmission module 1130.

[0134] The cloud fusion module 1110 is used to respond to receiving vehicle-side information from the vehicle and road-side information from the road, and to perform fusion processing on the cloud information, vehicle-side information and road-side information to obtain cloud fused information, wherein the road-side information, vehicle-side information and cloud information each include vehicle-related information.

[0135] The cloud decision module 1120 is used to generate cloud-based assisted driving decision information for controlling the vehicle based on cloud-based fused information.

[0136] The cloud-based decision transmission module 1130 is used to respond to a request from the vehicle for requesting auxiliary decision information by sending cloud-based assisted driving decision information to the vehicle so that the vehicle can generate control commands for controlling the vehicle based on the cloud-based assisted driving decision information.

[0137] According to embodiments of this disclosure, the device for controlling an autonomous vehicle further includes a cloud control module and a cloud control transmission module.

[0138] The cloud control module is used to generate cloud-based assisted driving decision information to control the vehicle.

[0139] The cloud control sending module is used to respond to a request from the vehicle for auxiliary control commands and send the cloud auxiliary control commands to the vehicle so that the vehicle can control the vehicle according to the cloud auxiliary control commands.

[0140] Figure 12 A block diagram of an apparatus for controlling an autonomous vehicle according to an embodiment of the present disclosure is shown schematically.

[0141] like Figure 12 As shown, the device 1200 for controlling autonomous vehicles is applied at the roadside and includes: a roadside fusion module 1210, a roadside decision module 1220, and a roadside decision transmission module 1230.

[0142] The roadside fusion module 1210 is used to respond to receiving vehicle-side information from the vehicle and cloud-side information from the cloud, and to perform fusion processing on the roadside information, vehicle-side information and cloud-side information to obtain roadside fusion information, wherein the cloud-side information, vehicle-side information and roadside information each include vehicle-related information.

[0143] The roadside decision module 1220 is used to generate roadside assisted driving decision information for controlling vehicles based on roadside fusion information.

[0144] The road-side decision sending module 1230 is configured to receive a request for requesting the auxiliary decision information from the vehicle-side, and send the road-side auxiliary driving decision information to the vehicle-side, so that the vehicle-side generates the control instruction for controlling the vehicle according to the road-side auxiliary driving decision information.

[0145] According to an embodiment of the present disclosure, the apparatus for controlling the autonomous vehicle further includes a road-side control module and a road-side control sending module.

[0146] The road-side control module is configured to generate the road-side auxiliary control instruction for controlling the vehicle based on the road-side auxiliary driving decision information.

[0147] The road-side control sending module is configured to send the road-side auxiliary control instruction to the vehicle-side in response to receiving a request for requesting the auxiliary control instruction from the vehicle-side, so that the vehicle-side controls the vehicle according to the road-side auxiliary control instruction.

[0148] According to an embodiment of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0149] According to an embodiment of the present disclosure, an electronic device includes at least one processor and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to an embodiment of the present disclosure.

[0150] According to an embodiment of the present disclosure, a non-transitory computer readable storage medium stores computer instructions, wherein the computer instructions are used to enable a computer to perform the method according to an embodiment of the present disclosure.

[0151] According to an embodiment of the present disclosure, a computer program product includes a computer program, and the computer program, when executed by a processor, implements the method according to an embodiment of the present disclosure.

[0152] Figure 13 A schematic block diagram of an example electronic device 1300 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0153] As Figure 13As shown, the device 1300 includes a computing unit 1301 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 1302 or a computer program loaded from the storage unit 1308 into a random access memory (RAM) 1303. Various programs and data required for the operation of the device 1300 can also be stored in the RAM 1303. The computing unit 1301, the ROM 1302, and the RAM 1303 are connected to each other through a bus 1304. An input / output (I / O) interface 1305 is also connected to the bus 1304.

[0154] A plurality of components in the device 1300 are connected to the I / O interface 1305, including: an input unit 1306, such as a keyboard, a mouse, etc.; an output unit 1307, such as various types of displays, speakers, etc.; a storage unit 1308, such as a magnetic disk, an optical disk, etc.; and a communication unit 1309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 1309 allows the device 1300 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0155] The computing unit 1301 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1301 performs various methods and processes described above, such as the method for controlling an autonomous vehicle. For example, in some embodiments, the method for controlling an autonomous vehicle can be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 1308. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 1300 via the ROM 1302 and / or the communication unit 1309. When the computer program is loaded into the RAM 1303 and executed by the computing unit 1301, one or more steps of the method for controlling an autonomous vehicle described above can be performed. Alternatively, in other embodiments, the computing unit 1301 can be configured to perform the method for controlling an autonomous vehicle by any other appropriate means, such as by means of firmware.

[0156] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a complex programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0157] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces the functions / operations specified in the flowcharts and / or the block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0158] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0159] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0160] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0161] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0162] It should be understood that various forms of flow shown above can be used, with steps reordered, added, or removed. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, without limitation herein, so long as the desired results of the technology of the present disclosure are achieved.

[0163] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above.

Claims

1. A method for controlling an autonomous vehicle, comprising: in response to receiving cloud information from a cloud and road information from a road, performing fusion processing on vehicle information from the vehicle, the cloud information and the road information to obtain vehicle fusion information, wherein the cloud information, the road information and the vehicle information each comprises information related to the vehicle; generating driving decision information for controlling the vehicle based on the vehicle fusion information; generating control instructions for controlling the vehicle based on the driving decision information; controlling the vehicle according to the control instructions; in a case where it is determined that a control operation result meets a predetermined control operation condition, sending a request for requesting auxiliary control instructions to the road, wherein the control operation result is used to represent a result of a case where a control operation is performed, and the control operation is used to represent that the control instructions for controlling the vehicle are generated based on the driving decision information; receiving road auxiliary control instructions from the road; and controlling the vehicle according to the road auxiliary control instructions; wherein, while the road generates the road auxiliary control instructions, the road generates weak control instructions so as to control a traffic infrastructure through the weak control instructions to assist the vehicle to travel in an autonomous driving mode. 2.The method of claim 1, further comprising: in a case where it is determined that a decision operation result meets a predetermined decision operation condition, sending a request for requesting auxiliary driving decision information to an auxiliary decision end, wherein the decision operation result is used to represent a result of a case where a decision operation is performed, the decision operation is used to represent that the driving decision information for controlling the vehicle is generated based on the vehicle fusion information, and the auxiliary decision end comprises the road or the cloud; receiving auxiliary driving decision information from the auxiliary decision end; and generating control instructions for controlling the vehicle according to the auxiliary driving decision information.

3. The method of claim 1 or 2, wherein, The generating of the driving decision information for controlling the vehicle based on the vehicle fusion information comprises: receiving cloud decision information from the cloud and road decision information from the road; generating vehicle decision information based on the vehicle fusion information; and performing fusion on the cloud decision information, the road decision information and the vehicle decision information to obtain the driving decision information. 4.A method for controlling an autonomous vehicle, comprising: in response to receiving vehicle information from a vehicle end and cloud information from a cloud, performing fusion processing on road information, the vehicle information and the cloud information to obtain road fusion information, wherein the cloud information, the vehicle information and the road information each comprises information related to the vehicle; generating road auxiliary driving decision information for controlling the vehicle based on the road fusion information; receiving a request for requesting auxiliary decision information from the vehicle end, and sending the road auxiliary driving decision information to the vehicle end so that the vehicle end generates control instructions for controlling the vehicle according to the road auxiliary driving decision information; generating, based on the road-side assistant driving decision information, a road-side assistant control instruction for controlling the vehicle; and sending, in response to receiving a request for assistant control instruction from the vehicle-side, the road-side assistant control instruction to the vehicle-side so that the vehicle-side controls the vehicle according to the road-side assistant control instruction; wherein the request for assistant control instruction is sent by the vehicle-side in a case where a control operation result meets a predetermined control operation condition, wherein the control operation result is used to represent a result of a case where a control operation is performed, and the control operation is used to represent that a control instruction for controlling the vehicle is generated based on driving decision information; wherein the road-side generates a weak control instruction at the same time when the road-side generates the assistant control instruction, so that the vehicle is assisted to travel in an autonomous driving mode by controlling the traffic infrastructure through the weak control instruction.

5. A system for controlling an autonomous driving vehicle, comprising: a vehicle-side for performing fusion processing on vehicle-side information from the vehicle, cloud-side information from a cloud-side, and road-side information from a road-side to obtain vehicle-side fusion information, in response to receiving the cloud-side information and the road-side information, wherein the cloud-side information, the road-side information, and the vehicle-side information each comprises information related to the vehicle; generating driving decision information for controlling the vehicle based on the vehicle-side fusion information; generating a control instruction for controlling the vehicle based on the driving decision information; controlling the vehicle according to the control instruction; sending a request for assistant control instruction to the road-side in a case where a control operation result meets a predetermined control operation condition, wherein the control operation result is used to represent a result of a case where a control operation is performed, and the control operation is used to represent that a control instruction for controlling the vehicle is generated based on the driving decision information; receiving road-side assistant control instruction from the road-side; and controlling the vehicle according to the road-side assistant control instruction; a cloud-side for sending the cloud-side information to the vehicle-side; and a road-side for sending the road-side information to the vehicle-side and performing fusion processing on the road-side information, the vehicle-side information, and the cloud-side information to obtain road-side fusion information, in response to receiving the vehicle-side information from the vehicle-side and the cloud-side information from the cloud-side, wherein the cloud-side information, the vehicle-side information, and the road-side information each comprises information related to the vehicle; generating road-side assistant driving decision information for controlling the vehicle based on the road-side fusion information; generating a road-side assistant control instruction for controlling the vehicle based on the road-side assistant driving decision information; wherein the road-side also generates a weak control instruction at the same time when the road-side generates the road-side assistant control instruction, so that the vehicle is assisted to travel in an autonomous driving mode by controlling the traffic infrastructure through the weak control instruction.

6. An apparatus for controlling an autonomous driving vehicle, comprising: a vehicle-end fusion module configured to fuse vehicle-end information from the vehicle, cloud-end information from the cloud, and road-end information from the road to obtain vehicle-end fusion information, in response to receiving the cloud-end information and the road-end information, wherein the cloud-end information, the road-end information, and the vehicle-end information each comprises information related to the vehicle; a vehicle-end decision module configured to generate driving decision information for controlling the vehicle based on the vehicle-end fusion information; a vehicle-end control module configured to generate control instructions for controlling the vehicle based on the driving decision information; a vehicle-end execution module configured to control the vehicle according to the control instructions; a control request module configured to send a request for auxiliary control instructions to the road, in a case where a control operation result meets a predetermined control operation condition, wherein the control operation result is used to represent a result of a case where a control operation is performed, and the control operation is used to represent generating control instructions for controlling the vehicle based on the driving decision information; a control receiving module configured to receive road-end auxiliary control instructions from the road; and an auxiliary execution module configured to control the vehicle according to the road-end auxiliary control instructions; wherein, while the road generates the auxiliary control instructions, the road generates weak control instructions to control the traffic infrastructure by the weak control instructions to assist the vehicle to travel in an autonomous driving mode.

7. The apparatus of claim 6, further comprising: a decision request module configured to send a request for auxiliary driving decision information to an auxiliary decision end, in a case where a decision operation result meets a predetermined decision operation condition, wherein the decision operation result is used to represent a result of a case where a decision operation is performed, and the decision operation is used to represent generating driving decision information for controlling the vehicle based on the vehicle-end fusion information, and the auxiliary decision end comprises the road or the cloud; a decision receiving module configured to receive auxiliary driving decision information from the auxiliary decision end; and a first auxiliary control module configured to generate control instructions for controlling the vehicle according to the auxiliary driving decision information.

8. The apparatus of claim 6 or 7, wherein, The vehicle-end decision module comprises: a decision receiving unit configured to receive cloud-end decision information from the cloud and road-end decision information from the road; a decision generating unit configured to generate vehicle-end decision information based on the vehicle-end fusion information; and a decision fusion unit configured to fuse the cloud-end decision information, the road-end decision information, and the vehicle-end decision information to obtain the driving decision information.

9. An apparatus for controlling an autonomous vehicle, comprising: a road-end fusion module configured to fuse road-end information, vehicle-end information from the vehicle, and cloud-end information from the cloud to obtain road-end fusion information, in response to receiving the vehicle-end information and the cloud-end information, wherein the cloud-end information, the vehicle-end information, and the road-end information each comprises information related to the vehicle; a road-end decision module configured to generate road-end auxiliary driving decision information for controlling the vehicle based on the road-end fusion information; a road-side decision sending module, configured to receive a request for requesting assistance decision information from the vehicle-side, and send the road-side assistance driving decision information to the vehicle-side, so that the vehicle-side generates control instructions for controlling the vehicle according to the road-side assistance driving decision information; a road-side control module, configured to generate road-side assistance control instructions for controlling the vehicle based on the road-side assistance driving decision information; and a road-side control sending module, configured to send the road-side assistance control instructions to the vehicle-side in response to receiving a request for requesting assistance control instructions from the vehicle-side, so that the vehicle-side controls the vehicle according to the road-side assistance control instructions; wherein the request for requesting assistance control instructions is sent by the vehicle-side in a case where a control operation result meets a predetermined control operation condition, wherein the control operation result is used to represent a result of a case where a control operation is performed, and the control operation is used to represent that control instructions for controlling the vehicle are generated based on driving decision information; wherein the road-side generates weak control instructions for controlling the traffic infrastructure to assist the vehicle to travel in the automatic driving mode through the weak control instructions, while the road-side generates the assistance control instructions.

10. An electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 4.

11. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1 to 4.

12. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 4.

Images