1. A control method for autonomous driving, comprising:

acquiring the information of the sensed road conditions around the vehicle;

determining a first control decision based at least on the perceived road condition information and an autonomous driving decision logic;

controlling the vehicle to drive automatically according to the first control decision;

in response to detecting a driving assistance instruction, determining a second control decision, different from the first control decision, based at least on the perceived road condition information, the automated driving decision logic, and the driving assistance instruction; and

controlling the vehicle to drive automatically according to the second control decision.

2. The method of claim 1, wherein the driving assistance instructions are indicative of at least one of:

adjusting the running speed of the vehicle;

adjusting a driving lane of the vehicle; and

adjusting a drivable state of a surrounding road of the vehicle, the drivable state being capable of indicating whether the surrounding road is available for the vehicle to travel.

3. The method of claim 2, wherein adjusting the travelable state of the road around the vehicle comprises: adjusting a drivable state of a road around the vehicle from undrivable to drivable,

and wherein the surrounding road of the vehicle comprises at least one of: an oncoming lane, a lane separated by a prohibited lane change line, a lane different from a direction of travel of the vehicle, an emergency lane, a roadside parking space, and a non-lane road surface.

4. The method of claim 2, wherein determining a second control decision different from the first control decision comprises:

in response to detecting the driving assist instruction that can instruct adjustment of a travelable state of the peripheral road of the vehicle, determining a target position in the travelable peripheral road of the vehicle; and

determining the second control decision based on at least a current location of the vehicle, the target location, and a drivable state of a road surrounding the vehicle.

5. The method of claim 1, wherein the driving assistance instructions comprise at least one of: gesture instructions, voice instructions, physical key instructions, and virtual key instructions.

6. The method of claim 1, further comprising:

updating the autonomous driving decision logic based at least on the sensed road condition information of the vehicle and the second control decision.

7. The method of claim 1, further comprising:

sending the perceived road condition information and the second control decision to a server; and

synchronizing an autonomous driving decision logic from the server.

8. A method of updating automated driving decision logic, comprising:

receiving at least one set of perceived traffic information and control decisions from at least one vehicle, wherein the control decisions in each of the at least one set of perceived traffic information and control decisions are determined by an autonomous driving system of the respective vehicle in response to detecting the assisted driving instruction;

updating an automatic driving decision logic based on the at least one group of perceived road condition information and control decisions; and

synchronizing the updated autopilot decision logic to the at least one vehicle to enable an autopilot system of the vehicle to determine a control decision for controlling vehicle autopilot based on the autopilot decision logic.

9. The method of claim 8, wherein updating automated driving decision logic based on the at least one set of perceived road condition information and control decisions comprises:

and aiming at each group of the perception road condition information and the control decision in the at least one group of perception road condition information and control decision, executing the following construction operation:

constructing sample data by at least utilizing the information of the perceived road condition; and

constructing a sample label corresponding to the sample data by using the control decision; and training a machine learning model by using at least one group of sample data and sample labels which are in one-to-one correspondence with the at least one group of perceived road condition information and control decisions,

wherein synchronizing the updated autonomous driving decision logic to the at least one vehicle comprises:

synchronizing the machine learning model to the at least one vehicle.

10. A control device for autonomous driving, comprising:

an acquisition unit configured to acquire perceived road condition information around a vehicle;

a determination unit configured to determine a first control decision based at least on the perceived road condition information and an automatic driving decision logic; and

a control unit configured to control the vehicle to autonomously drive in accordance with the first control decision,

wherein the determination unit is further configured to determine, in response to detecting a driving assistance instruction, a second control decision different from the first control decision based on at least the perceived road condition information, the automatic driving decision logic, and the driving assistance instruction,

and wherein the control unit is further configured to control the vehicle to drive automatically in accordance with the second control decision.

11. The apparatus of claim 10, wherein the driving assistance instructions are capable of indicating at least one of:

adjusting the running speed of the vehicle;

adjusting a driving lane of the vehicle; and

adjusting a drivable state of a surrounding road of the vehicle, the drivable state being capable of indicating whether the surrounding road is available for the vehicle to travel.

12. The apparatus of claim 11, wherein adjusting the travelable state of the road around the vehicle comprises: adjusting a drivable state of a road around the vehicle from undrivable to drivable,

and wherein the surrounding road of the vehicle comprises at least one of: an oncoming lane, a lane separated by a prohibited lane change line, a lane different from a direction of travel of the vehicle, an emergency lane, a roadside parking space, and a non-lane road surface.

13. The apparatus of claim 11, the determining unit comprising:

a first determination subunit configured to determine a target position in a drivable peripheral road of the vehicle in response to detection of the driving assist instruction that can instruct adjustment of a drivable state of the peripheral road of the vehicle; and

a second determination subunit configured to determine the second control decision based on at least the current position of the vehicle, the target position, and a travelable state of a road around the vehicle.

14. The apparatus of claim 10, wherein the driving assistance instructions comprise at least one of: gesture instructions, voice instructions, physical key instructions, and virtual key instructions.

15. The apparatus of claim 10, further comprising:

an updating unit configured to update the autonomous driving decision logic based on at least the sensed road condition information of the vehicle and the second control decision.

16. The apparatus of claim 10, further comprising:

a sending unit configured to send the perception data and the second control decision to a server; and

a synchronization unit configured to synchronize an autonomous driving decision logic from the server.

17. An apparatus for updating automated driving decision logic, comprising:

a receiving unit configured to receive at least one set of perception data and control decisions from at least one vehicle, wherein the control decisions in each of the at least one set of perception data and control decisions are determined by an autonomous driving system in the corresponding vehicle in response to detecting a driving assistance instruction;

an update unit configured to update an autonomous driving decision logic based on the at least one set of perception data and a control decision; and

a transmission unit configured to synchronize the updated autonomous driving decision logic to the at least one vehicle.

18. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

19. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-9.

20. A computer program product comprising a computer program, wherein the computer program realizes the method of any one of claims 1-9 when executed by a processor.

Background

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. The artificial intelligence hardware technology generally comprises technologies such as a sensor, a special artificial intelligence chip, cloud computing, distributed storage, big data processing and the like, and the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge graph technology and the like.

With the rapid development of the field of automatic driving, the intelligence and autonomy of automatic driving are gradually improved, and the applicable scenes are more and more abundant. However, for vehicles such as buses, etc., which need to be guaranteed with priority to safety, under certain specific conditions, a safety guard still needs to intervene in the driving state of such vehicles.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, unless otherwise indicated, the problems mentioned in this section should not be considered as having been acknowledged in any prior art.

Disclosure of Invention

The present disclosure provides a control method for autonomous driving, an updating method of autonomous driving decision logic, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a control method for automatic driving, including: acquiring the information of the sensed road conditions around the vehicle; determining a first control decision based at least on the sensed road condition information and the autonomous driving decision logic; controlling the vehicle to drive automatically according to the first control decision; in response to detecting the auxiliary driving instruction, determining a second control decision different from the first control decision based at least on the sensed road condition information, the automatic driving decision logic, and the auxiliary driving instruction; and controlling the vehicle to drive automatically according to the second control decision.

According to another aspect of the present disclosure, there is provided an updating method of an automatic driving decision logic, including: receiving at least one set of perceived traffic information and control decisions from at least one vehicle, wherein the control decisions in each of the at least one set of perceived traffic information and control decisions are determined by an autonomous driving system of the respective vehicle in response to detecting the assisted driving instruction; updating an automatic driving decision logic based on at least one group of sensed road condition information and control decisions; and synchronizing the updated autopilot decision logic to the at least one vehicle to enable an autopilot system of the vehicle to determine a control decision for controlling the autopilot of the vehicle based on the autopilot decision logic.

According to another aspect of the present disclosure, there is provided a control apparatus for automatic driving, including: an acquisition unit configured to acquire perceived road condition information around a vehicle; a determination unit configured to determine a first control decision based at least on the sensed road condition information and the automatic driving decision logic; and a control unit configured to control the vehicle to autonomously drive according to a first control decision, wherein the determination unit is further configured to determine a second control decision different from the first control decision based on at least the sensed road condition information, the autonomous driving decision logic and the assisted driving instruction in response to detecting the assisted driving instruction, and wherein the control unit is further configured to control the vehicle to autonomously drive according to the second control decision.

According to another aspect of the present disclosure, there is provided an updating apparatus of an automatic driving decision logic, including: a receiving unit configured to receive at least one set of perception data and control decisions from at least one vehicle, wherein the control decisions in each of the at least one set of perception data and control decisions are determined by an autonomous driving system in the corresponding vehicle in response to detecting the auxiliary driving instruction; an update unit configured to update an autonomous driving decision logic based on at least one set of perception data and a control decision; and a transmission unit configured to synchronize the updated autonomous driving decision logic to the at least one vehicle.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the above-described control method for autonomous driving and updating method of autonomous driving decision logic.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the above-described control method for autonomous driving and the update method of autonomous driving decision logic.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements the above-described control method for autonomous driving and the update method of an autonomous driving decision logic.

According to one or more embodiments of the disclosure, by re-determining a control decision and controlling the automatic driving of the vehicle according to the control decision when an auxiliary driving instruction is detected during the automatic driving of the vehicle, the automatic driving system adjusts the control decision under the non-pipelining intervention of a security officer, improves the intelligence and the interactivity with the security officer, and simultaneously avoids the suspension of an automatic driving task caused by the pipelining intervention of the security officer and the inconvenience caused by the need of completely stopping the vehicle to restart the automatic driving task after the takeover.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;

FIG. 2 shows a flow chart of a control method for autonomous driving according to an exemplary embodiment of the present disclosure;

3A-3C show schematic diagrams of an assisted driving instruction adjusting a travel speed of a vehicle according to an exemplary embodiment of the present disclosure;

4A-4C illustrate schematic views of a secondary driving instruction adjusting a driving path of a vehicle according to an exemplary embodiment of the present disclosure;

5A-5B illustrate schematic views of a secondary driving instruction indicating adjustment of a drivable state of a surrounding road of a vehicle, according to an exemplary embodiment of the present disclosure;

FIG. 6 shows a schematic diagram of generating a stranded out trajectory according to an example embodiment of the present disclosure;

FIG. 7 illustrates a flow chart of an update method of automated driving decision logic according to an exemplary embodiment of the present disclosure;

FIG. 8 illustrates a flow chart for updating automated driving decision logic according to an exemplary embodiment of the present disclosure;

fig. 9 shows a block diagram of a control apparatus for automatic driving according to an exemplary embodiment of the present disclosure;

FIG. 10 illustrates a block diagram of an update apparatus for automated driving decision logic, according to an exemplary embodiment of the present disclosure; and

FIG. 11 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

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

It should be understood that the term "vehicle" or other similar terms as used herein generally includes motor vehicles, such as passenger vehicles including cars, Sport Utility Vehicles (SUVs), buses, vans, various commercial vehicles, watercraft including various boats, ships, aircraft, and the like, and includes hybrid vehicles, electric vehicles, plug-in hybrid electric vehicles, hydrogen powered vehicles, and other alternative fuel vehicles (e.g., fuels derived from sources other than petroleum).

As used herein, the phrase "vehicle/on-board system" refers to an integrated information system having information processing capabilities. These systems are sometimes referred to as in-vehicle information systems and are typically integrated with telematics services, in-vehicle sensors, entertainment systems, and/or navigation systems.

The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.

In the related art, according to the existing vehicle control method for autonomous driving, if a security officer desires to intervene in autonomous driving behavior, it is necessary to take over driving completely by directly controlling a steering wheel, a brake/accelerator pedal, and the like. Such an operation may result in suspension of the autonomous driving task, which needs to be performed with the vehicle completely stationary to restart the autonomous driving task.

In order to solve the problems, the control decision is determined again and the automatic driving of the vehicle is controlled according to the control decision when the auxiliary driving instruction is detected in the automatic driving process of the vehicle, so that the adjustment of the control decision by the automatic driving system under the non-junction type intervention of a safety worker is realized, the intelligence of the automatic driving system and the interchangeability with the safety worker are improved, the suspension of the automatic driving task caused by the junction type intervention of the safety worker is avoided, and the inconvenience caused by the fact that the vehicle needs to be completely stopped after the junction type intervention to restart the automatic driving task is avoided.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. Client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the server 120 may run one or more services or software applications that enable execution of an automated driving path planning method, an automated driving control decision determination method, an update method of automated driving decision logic, and the like.

In some embodiments, the server 120 may also provide other services or software applications that may include non-virtual environments and virtual environments. In certain embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of client devices 101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a client device 101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. Client devices 101, 102, 103, 104, 105, and/or 106 may also interact with server 120 without direct user involvement. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

Client devices 101, 102, 103, 104, 105, and/or 106 may interact with a server to obtain autonomous driving paths, autonomous driving control decisions, autonomous driving decision logic, and so on. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.

Client devices 101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as on-board computers for use in different types of automobiles, portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, various messaging devices, sensors or other sensing devices, and so forth. These computer devices may run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux, or Linux-like operating systems (e.g., Google Chrome OS); or include various Mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular telephones, smart phones, tablets, Personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays and other devices. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

In some implementations, the server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from the client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or a smart cloud computing server or a smart cloud host with artificial intelligence technology. The cloud Server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The data store 130 may reside in various locations. For example, the data store used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The data store 130 may be of different types. In certain embodiments, the data store used by the server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to the command.

In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or regular stores supported by a file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

According to an aspect of the present disclosure, a control method for automatic driving is provided. As shown in fig. 2, the control method includes: step S201, obtaining perception road condition information around a vehicle; step S202, determining a first control decision at least based on the sensed road condition information and the automatic driving decision logic; step S203, controlling the automatic driving of the vehicle according to the first control decision; step S204, responding to the detection of an auxiliary driving instruction, and determining a second control decision different from the first control decision at least based on the sensed road condition information, the automatic driving decision logic and the auxiliary driving instruction; and step S205, controlling the automatic driving of the vehicle according to the second control decision. Therefore, in the automatic driving process of the vehicle, when the auxiliary driving instruction is detected, the control decision is determined again and the automatic driving of the vehicle is controlled according to the control decision, so that the adjustment of the control decision by the automatic driving system under the non-connection type intervention of a security worker is realized, the intelligence of the automatic driving system and the interchangeability with the security worker are improved, the suspension of an automatic driving task caused by the connection type intervention of the security worker is avoided, and the inconvenience caused by the fact that the vehicle needs to be completely stopped after the connection is taken over to restart the automatic driving task is avoided.

According to some embodiments, in step S201, acquiring the sensed traffic information around the vehicle may include acquiring the driving state information of the vehicle and the traffic information around the vehicle through various sensors on the vehicle, and may also include acquiring the traffic information sensed by the road measurement device and other traffic related information through the internet of vehicles or through communication with the road measurement device, which is not limited herein.

According to some embodiments, the automatic driving decision logic used in step S202 may be, for example, an automatic driving algorithm applied in an automatic driving system of the vehicle, or an automatic driving algorithm on a server in the cloud. Control decisions for controlling the vehicle in the autonomous driving state can be determined using autonomous driving decision logic. In some embodiments, on the basis of sensing road condition information and an automatic driving decision logic, a control decision of a vehicle can be determined based on high-precision map data, so that more accurate automatic driving of the vehicle is realized.

According to some embodiments, in step S203, the vehicle is controlled to autonomously drive according to a first control decision determined based on at least the sensed road condition information and the autonomous driving decision logic. It is noted that the first control decision is an automatic driving control decision made by the automatic driving system on the basis of not receiving any instruction from the driver or the security officer.

According to some embodiments, in response to detecting the driving assistance instruction, a second control decision different from the first control decision is determined based on at least the sensed road condition information, the automatic driving decision logic, and the driving assistance instruction at step S204. In some embodiments, the detected driving assistance instructions can indicate at least one of: adjusting the running speed of the vehicle; adjusting a driving lane of the vehicle; and adjusting a travelable state of the surrounding road of the vehicle, the travelable state being capable of indicating whether the surrounding road is available for the vehicle to travel. Therefore, through the auxiliary driving instruction for indicating three different operations, the automatic driving system can complete three tasks of speed change, lane change and escaping/obstacle avoidance of the vehicle under the intervention of a safety worker, and can keep a state of not exiting the automatic driving, so that the hybrid decision of the automatic driving system and the safety worker on the vehicle is realized.

The three tasks described above will be specifically described below in connection with a number of exemplary embodiments.

Fig. 3A-3C illustrate an exemplary embodiment of an assisted driving instruction instructing to adjust a traveling speed of a vehicle. As shown in fig. 3A, when the vehicle 310 travels to an approaching intersection, the vehicle 310 acquires the sensed traffic information that the intersection signal lamp 320 is a yellow lamp, and determines the braking as the first control decision based on the sensed traffic information. However, as shown in fig. 3B, sudden braking in such a case may generate a very large reverse acceleration, and although the vehicle can be stopped before the stop line, the vehicle may have a bad riding experience for passengers in the vehicle, and may even cause a safety hazard. Thus, a security officer of the vehicle 310 may give a secondary driving instruction to increase the traveling speed of the vehicle, causing the vehicle to cross the stop line during a yellow light and turn the signal light to a red light when approaching the exit intersection. Upon receiving this assisted driving instruction, the autonomous driving system of the vehicle 310 determines a second control decision to accelerate through the intersection other than "braking", as shown in fig. 3C.

Fig. 4A-4C illustrate an exemplary embodiment in which the driving assistance instruction instructs to adjust the traveling road of the vehicle. As shown in fig. 4A, there is a slow moving vehicle 420 in the same lane in front of the vehicle 410. The autonomous driving system of vehicle 410 determines a first control decision to follow the preceding vehicle. However, since the vehicle 420 is traveling at a slower speed, the decision to follow the preceding vehicle, while safe, can significantly affect the speed of the vehicle 410. In addition, as shown in fig. 4B, after the decision is made on the vehicle before the following, the distance between the vehicle 410 and the vehicle 420 is shortened, and if the vehicle 410 makes a lane change decision again at this time, the lane change can be made only to the left directly or after the deceleration, the lane change can be made to the left again. However, changing lanes to the left directly may cause traffic hazards, and changing lanes to the left after deceleration may have a certain effect on the riding experience of passengers in the vehicle. Therefore, the safer of the vehicle 410 may give the driving assistance instruction to adjust the driving lane to the left in advance. Upon receiving this assisted driving instruction, the autonomous driving system of the vehicle 410 determines a second control decision to change lanes to the left, different from "follow-up ahead", as shown in fig. 4C.

Fig. 5A to 5B show an exemplary embodiment in which the driving assistance instruction instructs to adjust the travelable state of the peripheral road of the vehicle.

According to some embodiments, for example, in a task of getting out of trouble, adjusting a drivable state of a road around the vehicle may include: the drivable state of the road around the vehicle is adjusted from undrivable to drivable. The peripheral road of the vehicle may include at least one of: an oncoming lane, a lane separated by a prohibited lane change line, a lane different from the direction of travel of the vehicle, an emergency lane, a curb parking space, and a non-lane road surface. Therefore, under special conditions, in response to receiving an instruction sent by a safety worker for adjusting the drivable state of the road around the vehicle, the vehicle can get rid of the trouble by using the road around the vehicle which is unavailable under the normal state, and the flexibility of automatic driving is improved. And because the safety officer is not managing the driving, the automatic driving task is not suspended, so the vehicle does not need to be stopped and the automatic driving system does not need to be restarted, and the intelligence of the automatic driving system is improved.

In one exemplary embodiment, the driving direction of the vehicle is forward, and the left-turn-only lane and the right-turn-only lane are lanes different from the driving direction of the vehicle. In another exemplary embodiment, the off-road surface may include, for example, a shoulder, a ground marking area (e.g., a marking area near a ramp entrance), and the like. It is understood that the vehicle's perimeter road may also include more types of road surfaces and even non-road surfaces, all within the scope of the present disclosure.

In an exemplary embodiment, as shown in fig. 5A, a road congestion condition occurs ahead of the vehicle 510, multiple vehicles 520 are parked in the forward lane, and the autonomous driving system of the vehicle 510 determines "park waiting" as the first control decision. The drivable state of the road 530 around the vehicle 510 is drivable, and the drivable state of the oncoming road 540 is non-drivable. At this time, the security officer receives, for example, an instruction from a traffic police indicating that the oncoming lane can be used for getting out of trouble, and the security officer may give a driving assistance instruction to adjust the travelable state of the oncoming road 540 to travelable. Upon receiving this instruction, the vehicle 510 determines a second control decision to "change lanes to the left to get rid of the trouble" using the updated travelable road 550, as shown in fig. 5B.

According to some embodiments, for example, in an obstacle avoidance task, adjusting a travelable state of a road around a vehicle may include, for example: the travelable state of the road around the vehicle is adjusted from travelable to non-travelable. For example, obstacles may occur on a travelable road around a vehicle due to various reasons such as traffic accidents, traffic control, road maintenance, etc., and a sensing device or an automatic driving system of the vehicle may not recognize the obstacles in time due to a blind field of view, an unobvious obstacle, etc. In such a case, the security officer can adjust the drivable states of these roads from drivable to undrivable by means of the driving-assistance command, so as to avoid the vehicle from driving into the dangerous segment under the control of the automatic driving system. And because the safety officer is not managing the driving, the automatic driving task is not suspended, so the vehicle does not need to be stopped and the automatic driving system does not need to be restarted, and the intelligence of the automatic driving system is improved.

According to some embodiments, the step S204 of determining a second control decision different from the first control decision may comprise: determining a target position in a drivable peripheral road of the vehicle in response to detecting a supplementary driving instruction capable of instructing adjustment of a drivable state of the peripheral road of the vehicle; and determining a second control decision based on at least the current position of the vehicle, the target position, and a drivable state of a road surrounding the vehicle. Therefore, after an instruction for changing the drivable state of the surrounding roads is detected, the automatic driving system firstly determines a target position in the surrounding roads and then generates a escaping/obstacle avoiding path according to the current position, the target position and the drivable area. Therefore, a safety worker only needs to make an instruction for changing the driving state of the surrounding roads, and the automatic driving system can realize automatic escaping/obstacle avoidance, so that the operation requirement on the safety worker is reduced, and the intelligence of the automatic driving system is improved.

In one exemplary embodiment, as shown in FIG. 6, the initial position of the vehicle is 610 with a plurality of stopped vehicles 620 in front of the vehicle. In response to detection of the driving assist instruction to adjust the drivable state of the peripheral road, the drivable peripheral road 640 is determined, and the target position 630 where the vehicle is getting out of trouble is determined. Based on the initial position 610, the target position 630, a suitable trajectory for getting out of the car and a corresponding second control decision may be determined depending on whether or not reverse is allowed. More specifically, in the case where reverse is not allowed, the escape trajectory 650 based on the Dubins curve may be generated, and in the case where reverse is allowed, the escape trajectory 660 based on the Reeds-Shepp curve may be generated.

According to some embodiments, the above-described trapped trajectory may be generated based on a Hybrid a (Hybrid a) algorithm. The path evaluation function may be, for example:

Cost＝G+H

where G is the cost of movement from the starting point to the specified location and H is the cost of movement from the specified location to the ending point. Each of G and H may further include a corresponding path length cost, a driving direction switching cost, a gear switching cost, a steering wheel angle cost, and the like, which is not limited herein. By combining the hybrid A-x algorithm and the path evaluation function, the optimal escape tracks of the two scenes of allowing reversing and not allowing reversing can be obtained. It is understood that other curves may be used as the escape trajectory by those skilled in the art, or other algorithms may be used to generate the escape trajectory, which is not limited herein. The generation mode of the obstacle avoidance track is similar to that of the escaping track, and is not described herein.

According to some embodiments, the driving assistance instructions may comprise at least one of: gesture instructions, voice instructions, physical key instructions, and virtual key instructions. In some exemplary embodiments, the physical keys may include, for example, physical operable keys such as buttons, switches, levers, and knobs of the in-vehicle entity, and the virtual keys may include, for example, virtual operable keys such as buttons, switches, levers, and knobs of the in-vehicle touch screen, which is not limited herein.

The form of the driving assistance instruction and the operation that the instruction can instruct will be described below by way of several exemplary embodiments.

In some exemplary embodiments, for the auxiliary driving instruction capable of instructing to adjust the running speed of the vehicle, a physical key such as a deceleration button or a deceleration pedal may be provided, pressing the key indicates intervening in the vehicle speed for deceleration, pressing the key indicates the deceleration strength, and pressing the key indicates the deceleration intervening time. Similarly, a physical key such as an accelerator button or an accelerator pedal may be provided, which will not be described herein. In other exemplary embodiments, a virtual key such as a screen virtual deceleration button may be provided, where pressing the key indicates intervening in decelerating the vehicle speed, pressing the key indicates the magnitude of deceleration, and pressing the key for the duration indicates the duration of the deceleration intervening. Similarly, a virtual key such as a screen virtual accelerator button may be provided, which will not be described herein.

In some exemplary embodiments, a solid key such as a lane change button or a lane change lever may be provided for a driving assistance instruction capable of instructing to adjust a driving lane of the vehicle. Illustratively, the steering lever has three position states, an upper position state, a middle position state and a lower position state. When the deflector rod is positioned at the middle position, no intervention instruction exists; and when the shifting lever is positioned at the upper position or the lower position, triggering an auxiliary driving instruction for adjusting the lane rightwards or adjusting the lane leftwards. In other exemplary embodiments, a virtual key such as a virtual lane change button or a virtual stick may be provided, and the operation may be similar to the operation of the physical key, which is not described herein.

In some exemplary embodiments, for the driving assistance instruction capable of instructing to adjust the travelable state of the peripheral road of the vehicle, a corresponding physical key or screen virtual key may be set. For example, the security officer may adjust the travelable state of the road around the vehicle by indicating or drawing a road on which switching of the travelable state is desired on the display of the in-vehicle electronic apparatus by operating the physical key or the screen virtual key.

In some exemplary embodiments, the gesture command may be recorded through a camera in the vehicle or the voice command may be recorded through a voice collecting device, and then the command may be recognized by an electronic device such as a vehicle-mounted computer, so as to implement corresponding tasks of speed changing, lane changing, and getting rid of difficulties/avoiding obstacles.

According to some embodiments, the control method may further comprise updating the automatic driving decision logic based on at least the sensed road condition information of the vehicle and the second control decision. Therefore, the second control decision based on the auxiliary driving instruction and the corresponding perception road condition information are collected at the vehicle side, so that the automatic driving decision logic is updated, the driving logic of the vehicle is closer to the driving habit of a security officer, and the reliability, the reasonability and the safety of the automatic driving decision are improved.

According to some embodiments, the control method may further comprise sending the perceived traffic information and the second control decision to a server; and synchronizing the autonomous driving decision logic from the server. Therefore, the second control decision based on the auxiliary driving instruction of the mobile phone on the vehicle side and the corresponding perception road condition information are sent to the server, so that the server can collect a large amount of data for the security personnel to intervene in automatic driving, an automatic driving system is optimized by using richer driving data, the updated automatic driving decision logic is synchronized to each automatic driving vehicle, and the reliability, the reasonability and the safety of the automatic driving decision are further improved.

According to another aspect of the present disclosure, a method for updating an automated driving decision logic is also provided. As shown in fig. 7, the updating method includes: step S701, receiving at least one group of sensed road condition information and control decisions from at least one vehicle, wherein the control decisions in each group of the at least one group of sensed road condition information and control decisions are determined by an automatic driving system of the corresponding vehicle in response to the detection of an auxiliary driving instruction; step S702, updating an automatic driving decision logic based on at least one group of sensed road condition information and control decisions; and step S703 of synchronizing the updated autonomous driving decision logic to the at least one vehicle, so that an autonomous driving system of the vehicle can determine a control decision for controlling autonomous driving of the vehicle based on the autonomous driving decision logic. Therefore, the automatic driving decision logic is updated by utilizing the control decision made by the automatic driving system sent back by the vehicle after the auxiliary driving instruction is detected and the corresponding perception data, and the updated automatic driving decision logic is synchronized to each vehicle, so that the vehicles can make the control decision closer to a safety guard when facing similar scenes in the future.

According to some embodiments, as shown in fig. 8, the step S702 of updating the automatic driving decision logic based on at least one set of sensed road condition information and control decision may include: step S7021, executing construction operation aiming at each group of perception road condition information and control decision in at least one group of perception road condition information and control decision; s7022, constructing sample data by at least using the information of the sensed road condition; step S7023, constructing a sample label corresponding to the sample data by using the control decision; and step S7024, training a machine learning model by using at least one group of sample data and sample labels which are in one-to-one correspondence with at least one group of perceived road condition information and control decisions. Step S703 of synchronizing the updated autonomous driving decision logic to the at least one vehicle may include synchronizing the machine learning model to the at least one vehicle. Therefore, sample data and sample labels of training samples are constructed by using the sensed road condition information and the control decision, and the training samples are trained by using the machine learning model, so that a trained machine learning model, namely updated automatic driving decision logic can be obtained. By using the machine learning method, the driving habit of a security officer can be better learned, so that the reliability and the safety of the updated automatic driving decision logic are further improved.

According to some embodiments, step S7022 and step S7023 may be, for example, substeps in the construction operation described in step S7021.

According to some embodiments, the input of the machine learning model may include, for example, feature data generated based on contents of sensed road condition information (e.g., vehicle travel information such as a position, a posture, a speed, and an acceleration of a vehicle and obstacle information such as a vehicle, an obstacle, and a corresponding position, a speed, and an acceleration of the vehicle on a road), map data information (e.g., an ID, a width, a forward/backward distance, and the like of a lane), automatic driving task information (e.g., a start point, an end point, a passing point, and the like of an automatic driving task), and an auxiliary driving instruction, and the like. When the machine learning model is trained and predicted by using the machine learning model, if there is no corresponding information, the features of the part may be subjected to a padding process (e.g., a zero-padding process). For example, when the machine learning model is trained by using the second control decision and the perception data determined after the security officer intervention, the characteristic value related to the auxiliary driving instruction can be subjected to zero filling processing, so that the trained machine learning model can make the control decision according with the driving habit of the security officer under the condition that the trained machine learning model has no auxiliary driving instruction.

In other embodiments, the machine learning model may not include driving assistance instructions. In such a case, the first control decision generated by the machine learning model and the auxiliary driving instruction may be combined using a post-processing method to arrive at the second control decision. In addition, a machine learning model dedicated for use when an auxiliary driving instruction is detected may be additionally trained, such that when an intervention instruction from a security officer is detected, a control decision is generated using this additional machine learning model.

It will be appreciated that those skilled in the art may implement the method of machine learning or other methods of updating the automated driving decision logic based on control decisions made with intervention of a security officer and perceived road condition information in a more comprehensive manner, and are not limited herein.

According to another aspect of the present disclosure, there is also provided a control apparatus for automatic driving. As shown in fig. 9, the control device 900 includes: an obtaining unit 910 configured to obtain perceived traffic information around the vehicle; a determining unit 920 configured to determine a first control decision based at least on the perceived road condition information and the automatic driving decision logic; and a control unit 930 configured to control the vehicle autonomous driving according to the first control decision, wherein the determination unit 920 is further configured to determine a second control decision different from the first control decision based on at least the sensed road condition information, the autonomous driving decision logic and the assisted driving instruction in response to detecting the assisted driving instruction, and wherein the control unit 930 is further configured to control the vehicle autonomous driving according to the second control decision.

The operations of the units 910-930 of the control device 900 are similar to the operations of the steps S201-S205 of the control method, and are not described herein again.

According to some embodiments, the driving assistance instructions can indicate at least one of: adjusting the running speed of the vehicle; adjusting a driving lane of the vehicle; and adjusting a travelable state of the surrounding road of the vehicle, the travelable state being capable of indicating whether the surrounding road is available for the vehicle to travel.

According to some embodiments, the driving assistance instructions may comprise at least one of: gesture instructions, voice instructions, physical key instructions, and virtual key instructions.

According to some embodiments, adjusting the travelable state of the surrounding road of the vehicle may comprise: adjusting a travelable state of a road around the vehicle from non-travelable to travelable, and wherein the road around the vehicle may comprise at least one of: an oncoming lane, a lane separated by a prohibited lane change line, a lane different from the direction of travel of the vehicle, an emergency lane, a curb parking space, and a non-lane road surface.

According to some embodiments, the determining unit 920 may include: a first determination subunit configured to determine a target position in a drivable peripheral road of the vehicle in response to detection of a driving assist instruction that can instruct adjustment of a drivable state of the peripheral road of the vehicle; and a second determination subunit configured to determine a second control decision based on at least the current position of the vehicle, the target position, and a travelable state of a road around the vehicle.

According to some embodiments, the control device 900 may further include: an updating unit configured to update the autonomous driving decision logic based on at least the sensed road condition information of the vehicle and the second control decision.

According to some embodiments, the control device 900 may further include: a sending unit configured to send the perception data and the second control decision to a server; and a synchronization unit configured to synchronize the autonomous driving decision logic from the server.

According to another aspect of the present disclosure, there is also provided an updating apparatus of an automatic driving decision logic. As shown in fig. 10, the updating apparatus 1000 includes: a receiving unit 1010 configured to receive at least one set of perception data and control decisions from at least one vehicle, wherein the control decision in each of the at least one set of perception data and control decisions is determined by an autonomous driving system in the corresponding vehicle in response to detecting the assisted driving instruction; an updating unit 1020 configured to update the autonomous driving decision logic based on at least one set of perception data and a control decision; and a transmitting unit 1030 configured to synchronize the updated autonomous driving decision logic to the at least one vehicle.

The operations of the units 1010-1030 of the updating apparatus 1000 are similar to the operations of the steps S701-S703 of the updating method, and are not described herein again.

According to an embodiment of the present disclosure, there is also provided an electronic device, a readable storage medium, and a computer program product.

Referring to fig. 11, a block diagram of a structure of an electronic device 1100, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 11, the device 1100 comprises a computing unit 1101, which may perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1102 or a computer program loaded from a storage unit 1108 into a Random Access Memory (RAM) 1103. In the RAM1103, various programs and data necessary for the operation of the device 1100 may also be stored. The calculation unit 1101, the ROM 1102, and the RAM1103 are connected to each other by a bus 1104. An input/output (I/O) interface 1105 is also connected to bus 1104.

A number of components in device 1100 connect to I/O interface 1105, including: an input unit 1106, an output unit 1107, a storage unit 1108, and a communication unit 1109. The input unit 1106 may be any type of device capable of inputting information to the device 1100, and the input unit 1106 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote control. Output unit 1107 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 1108 may include, but is not limited to, a magnetic or optical disk. The communication unit 1109 allows the device 1100 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.

The computing unit 1101 can be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 1101 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and the like. The calculation unit 1101 performs the various methods and processes described above, such as control for autonomous driving and/or updating methods of autonomous driving decision logic. For example, in some embodiments, the control for autonomous driving and/or the update method of autonomous driving decision logic may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1108. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1100 via ROM 1102 and/or communication unit 1109. When the computer program is loaded into RAM1103 and executed by the computing unit 1101, one or more steps of the above described update method for the control of autonomous driving and/or the autonomous driving decision logic may be performed. Alternatively, in other embodiments, the computing unit 1101 may be configured by any other suitable means (e.g., by means of firmware) to perform an update method for the control of autonomous driving and/or autonomous driving decision logic.

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may 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 a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; 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 may be received in any form, including acoustic, speech, or tactile input.

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: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may 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 arises 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, also called a cloud computing Server or a cloud host, and is a host product in a cloud computing service system, so as to solve the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service ("Virtual Private Server", or simply "VPS"). The server may also be a server of a distributed system, or a server incorporating a blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.