WO2020133208A1

WO2020133208A1 - Control method for self-driving vehicle, and self-driving system

Info

Publication number: WO2020133208A1
Application number: PCT/CN2018/124848
Authority: WO
Inventors: 林伟; 冯威; 张宇; 石磊; 刘晓彤
Original assignee: 驭势科技（北京）有限公司
Priority date: 2018-12-28
Filing date: 2018-12-28
Publication date: 2020-07-02
Also published as: CN109709965A; CN109709965B

Abstract

Disclosed are a control method for a self-driving vehicle, and a self-driving system. The method comprises: acquiring real-time driving data of a self-driving vehicle by means of a vehicle-mounted self-driving system of the self-driving vehicle (S101); based on the real-time driving data, the vehicle-mounted self-driving system generating a first decision (S102); the vehicle-mounted self-driving system sending the real-time driving data to a remote data processing system (S103); the vehicle-mounted self-driving system receiving a second decision from the remote data processing system, wherein the second decision is generated by the remote data processing system on the basis of the real-time driving data (S104); performing checking calculation and comparison on the second decision and the first decision by means of the self-driving system (S105); and according to a checking calculation and comparison result, the vehicle-mounted self-driving system issuing a decision instruction to the self-driving vehicle (S106). The method and system improve the safety of a self-driving vehicle and can be applied to a 4G network environment, but are more suitable for a 5G network environment.

Description

Control method and automatic driving system of automatic driving vehicle

Technical field

The invention relates to the technical field of automatic driving, in particular to a control method and an automatic driving system of an automatic driving vehicle.

Background technique

With the development of science and technology, intelligent vehicles have become an important development direction for future automobiles. Autonomous vehicles can not only help improve people's travel convenience and travel experience, but also greatly improve people's travel efficiency. However, the safety of autonomous vehicles is still one of the main problems that need to be solved. Among the factors affecting the safety of autonomous vehicles, the decision-making and control of autonomous vehicles is one of the most critical factors, which directly affects their safety and rationality. Therefore, the sensitivity and accuracy of decision-making and control of autonomous vehicles are improved It is a key task to improve autonomous vehicles.

Existing automatic driving systems for automatic driving vehicles are limited to their data storage and processing capabilities. Generally, relatively simple algorithm models are used to calculate the driving information and environmental information of the automatic driving vehicles. The depth is subject to certain restrictions, which affects the accuracy of the decision instructions of the automatic driving system and the safety of the automatic driving vehicle.

Therefore, it is necessary to provide an automatic driving vehicle control method and an automatic driving system to solve the above technical problems.

Summary of the invention

The present application discloses a control method and an automatic driving system for an autonomous driving vehicle, which improves the accuracy of decision instructions of the autonomous driving vehicle and improves the driving safety of the autonomous driving vehicle.

An aspect of the present application proposes a method for controlling an autonomous driving vehicle, including: acquiring real-time driving data of the autonomous driving vehicle through an on-board automatic driving system of the autonomous driving vehicle; based on the real-time driving data, the on-board automatic driving The system generates a first decision; the vehicle-mounted automatic driving system sends the real-time driving data to a remote data processing system; the vehicle-mounted automatic driving system receives a second decision from the remote data processing system, and the second decision Generated for the remote data processing system based on the real-time driving data; checking and comparing the second decision with the first decision through the automatic driving system; based on the result of the checking and comparison, the vehicle-mounted automatic driving system A decision instruction is issued to the autonomous vehicle.

Wherein, the first decision is obtained by the vehicle-mounted automatic driving system using the real-time driving data through a first decision model.

Wherein, the second decision is obtained by the remote data processing system through the second decision model using the real-time driving data.

Wherein, the remote data processing system is a cloud server, and the communication means is 5G communication.

Wherein, according to the result of the verification calculation, the decision instruction issued by the in-vehicle automatic driving system to the autonomous vehicle includes: the difference between the first decision and the second decision is less than a preset threshold; according to the first decision Either the second decision or the third decision obtained based on the first decision and the second decision issues an instruction.

Wherein, according to the result of the verification calculation, the decision instruction issued by the vehicle-mounted automatic driving system to the self-driving vehicle includes: the difference between the first decision and the second decision is greater than a preset threshold, and the control module drives the The self-driving vehicle stops immediately or leaves the driving environment as soon as possible, and stops after entering a safe environment.

Wherein, according to the result of the verification calculation, the decision instruction issued by the vehicle-mounted automatic driving system to the self-driving vehicle includes: the difference between the first decision and the second decision is greater than a preset threshold, and the acquisition is performed again. The first decision and the second decision.

Wherein, according to the result of the verification calculation, the decision instruction issued by the vehicle-mounted automatic driving system to the self-driving vehicle includes: the difference between the first decision and the second decision is still greater than a preset threshold, and the control module drives The self-driving vehicle stops immediately or leaves the driving environment as soon as possible, and stops after entering a safe environment.

Wherein, the vehicle-mounted automatic driving system may also receive the perception result from the remote data processing system.

Another aspect of the present application provides an automatic driving system, including: a memory, the memory includes at least one set of instructions, the instructions are constructed to complete a driving strategy for an autonomous driving vehicle; a processor, read in a working state The at least one set of instructions in the memory, and according to the at least one set of instructions: acquiring real-time driving data of the autonomous vehicle; generating first decision information based on the real-time driving data; Send data to a remote data processing system; receive a second decision from the remote data processing system, the second decision is generated by the remote data processing system based on the real-time driving data; and the second decision and the first decision Perform a verification calculation comparison, and according to the results of the verification calculation comparison, issue a decision instruction to the autonomous vehicle.

In another aspect of the present application, there is also provided an automatic driving vehicle configured with the automatic driving system described in the present application.

In summary, this application proposes a control method and an automatic driving system for an autonomous driving vehicle, which optimizes the existing automatic driving control vehicle control system and method, and improves the accuracy of the decision instructions issued by the existing system and method. Improve the driving safety of the autonomous vehicle.

The control method and the automatic driving system of the automatic driving vehicle described in the present application have high requirements on network delay and data transmission speed. For example, the technology disclosed in this application can be applied in a 4G network environment, but is more suitable for a 5G network environment. The data transmission rate of 4G is on the order of 100Mbps, the delay is 30-50ms, the maximum number of connections per square kilometer is on the order of 10,000, the mobility is about 350KM/h, and the transmission rate of 5G is on the order of 10Gbps, the delay is 1ms, the maximum number of connections per square kilometer is on the order of millions, and the mobility is about 500km/h. 5G has higher transmission rates, shorter delays, more connections per square kilometer, and higher speed tolerance. Another change in 5G is the change in transmission paths. In the past, when we called or transmitted photos, the signal had to be transferred through the base station, but after 5G, the device could be directly transmitted between devices, without the need to pass through the base station. Therefore, although this application is also applicable to the 4G environment, running in the 5G environment will result in better technical performance and higher business value.

Additional features in this application will be explained in part in the following description. Through this description, the contents described in the following drawings and embodiments will be apparent to those of ordinary skill in the art. The inventive points in this application can be fully explained by practicing or using the methods, means, and combinations thereof set forth in the detailed examples discussed below.

BRIEF DESCRIPTION

The following drawings describe in detail the exemplary embodiments disclosed in the present application. The same reference numerals indicate similar structures in several views of the drawings. Those of ordinary skill in the art will understand that these embodiments are non-limiting and exemplary embodiments, and the drawings are for illustration and description purposes only, and are not intended to limit the scope of the present disclosure, and other ways of embodiment are also possible The intention of completing the invention in this application is the same. It should be understood that the drawings are not drawn to scale. among them:

FIG. 1 is an embodiment of a wireless communication system for mobile device network management in this application.

2 is a block diagram of an exemplary vehicle with automatic driving capabilities according to some embodiments of the present application.

FIG. 3 is a schematic diagram of an embodiment of a control method and an automatic driving system based on an automatic driving vehicle of the present application.

4 is a block diagram of an exemplary vehicle with automatic driving capabilities and an automatic driving system according to some embodiments of the present application.

5 is a schematic diagram of exemplary hardware and software components of the information processing unit in the present application.

6 is a process flow diagram of a method for controlling an autonomous driving vehicle of the present application.

7 is a structural block diagram of a method for controlling an automatic driving vehicle and a remote data processing system in an automatic driving system in this application.

detailed description

The present application discloses a control method and an automatic driving system for an automatic driving vehicle, and transmits real-time driving data of the automatic driving vehicle acquired by the automatic driving system of the automatic driving vehicle to a remote data processing system, using the remote data The processing system has more powerful information processing capabilities, forming a second decision, and comparing the second decision with the first decision to form a more optimized decision instruction, which improves the decision instruction issued by the existing automatic driving system and method Accuracy, and improve the driving safety of the autonomous vehicle.

In order to provide a person of ordinary skill in the art with a thorough understanding of the relevant disclosure, specific details of the present invention are illustrated by examples in the following detailed description. However, the content disclosed in this application should be understood to be consistent with the scope of protection of the claims, and is not limited to the details of the specific invention. For example, it will be obvious to those of ordinary skill in the art to make various modifications to the embodiments disclosed in this application; and without departing from the spirit and scope of this application, those of ordinary skill in the art may define here The general principle of is applied to other embodiments and applications. As another example, if these details are not disclosed below, a person of ordinary skill in the art can also practice this application without knowing these details. On the other hand, in order to avoid unnecessarily obscuring the content of the present application, the present application provides a general overview of well-known methods, processes, systems, components, and/or circuits without detailed description. Therefore, the content disclosed in this application is not limited to the illustrated embodiments, but is consistent with the scope of claims.

The terminology used in this application is for the purpose of describing particular example embodiments only and is not limiting. For example, unless the context clearly indicates otherwise, if an singular description is used for an element (for example, "one", "one", and/or equivalent description) in this application, multiple elements may also be included. The terms "including" and/or "comprising" used in this application refer to an open concept. For example, A includes/includes B only means that there is a B feature in A, but it does not exclude the possibility that other elements (such as C) exist or are added in A.

It should be understood that the terms used in this application, such as "system", "unit", "module" and/or "block", are used to distinguish different components, elements, parts, parts or components at different levels. Kinds of methods. However, if other terms can achieve the same purpose, the other terms may also be used in this application to replace the above terms.

The modules (or units, blocks, units) described in this application may be implemented as software and/or hardware modules. Unless the context clearly dictates otherwise, when a unit or module is described as "connected," "connected to" or "coupled to" another unit or module, the expression may mean that the unit or module is directly connected or linked Or coupled to the other unit or module, it may also mean that the unit or module is indirectly connected, connected, or coupled to the other unit or module in some form. In this application, the term "and/or" includes any and all combinations of one or more of the associated listed items.

In this application, the term "autonomous vehicle" may refer to the environment that can perceive its environment and automatically perceive, judge and then make an external environment without human input (or driver, pilot, etc.) and/or intervention Decision making vehicle. The terms "autonomous vehicle" and "vehicle" can be used interchangeably. The term "autonomous driving" may refer to the ability to make intelligent judgments on the surrounding environment and navigate without input by anyone (eg, driver, pilot, etc.).

Considering the following description, these and other features of the present application, as well as the operation and function of related elements of the structure, as well as the economics of assembly and manufacturing of components, can be significantly improved. With reference to the drawings, all of these form part of the application. However, it should be clearly understood that the drawings are for illustration and description purposes only, and are not intended to limit the scope of the present application. It should be understood that the drawings are not drawn to scale.

The flowchart used in this application shows the operations implemented by the system according to some embodiments in this application. It should be clearly understood that the operations of the flowchart can be implemented out of order. Instead, the operations can be performed in reverse order or simultaneously. In addition, one or more other operations can be added to the flowchart. One or more operations can be removed from the flowchart.

The positioning technology used in this application can be based on Global Positioning System (GPS), Global Navigation Satellite System (GLONASS), Compass Navigation System (COMPASS), Galileo Positioning System, Quasi-Zenith Satellite System (QZSS), Wireless Fidelity (WiFi) Positioning technology, etc., or any combination thereof. One or more of the above positioning systems can be used interchangeably in this application.

In addition, although the system and method in the present application mainly describe a control method and an automatic driving system of an autonomous vehicle, it should be understood that this is only an exemplary embodiment. The system or method of the present application can be applied to any other type of navigation system. For example, the system or method of the present application can be applied to transportation systems in different environments, including land, ocean, aerospace, etc., or any combination thereof. The self-driving vehicles of the transportation system may include taxis, private cars, trailers, buses, trains, bullet trains, high-speed railways, subways, ships, airplanes, spaceships, hot air balloons, autonomous vehicles, etc., or any combination thereof. In some embodiments, the system or method may find application in, for example, logistics warehouses and military affairs.

FIG. 1 is an embodiment of a wireless communication system 100 for network management of mobile devices. The mobile device network management system can be used as a supporting network application in the invention described in this disclosure.

The wireless communication system 100 includes

remote units

142, 144, 146, a base station 110, and

wireless communication links

115, 148. A specific number of

remote units

142, 144, 146, base station 110, and

wireless communication links

115, 148 are depicted in FIG. 1, but those skilled in the art will recognize that any number of remote units 142 may be included in the wireless communication system 100. 144, 146, base station 110 and

wireless communication links

115, 148.

In some embodiments, the

remote units

142, 144, 146 may be mobile devices, such as in-vehicle computers (including on-board computers for manual driving vehicles and or self-driving vehicles with automatic driving capabilities) 142, 144, and other mobile devices 146, Such as mobile phones, laptop computers, personal digital assistants ("PDA"), tablet computers, smart watches, fitness bands, optical head-mounted displays, etc. The

remote units

142, 144, 146 may also include non-mobile computing devices, such as desktop computers, smart TVs (eg, televisions connected to the Internet), set-top boxes, game consoles, security systems (including security cameras), fixed Network equipment (eg, routers, switches, modems), etc. In addition, mobile

remote units

142, 144, 146 may be referred to as mobile stations, mobile devices, users, terminals, mobile terminals, fixed terminals, user stations, UEs, user terminals, devices, or other terms used in the art.

The wireless link between the

remote units

142, 144, 146 is 148. The wireless link between the

remote units

142, 144, and 146 may be 5G communication interaction and other forms of wireless interaction, such as Bluetooth, Wifi, and so on. The base station 110 forms a radio access network (radio access network "RAN") 120. The wireless link between the base stations 110 is 115. The RAN 120 may be coupled to the mobile core network 130 through communication. The mobile core network 130 may be a 5G network, or a 4G, 3G, 2G, or other form of network. In the present disclosure, the 5G network is taken as an example to illustrate the present invention.

The 5G mobile core network 130 may belong to a single public land mobile network (single public land mobile network "PLMN"). For example, the mobile core network 130 can provide services with low latency and high reliability requirements, such as applications in the field of autonomous driving. The mobile core network 130 may also provide services for other application requirements. For example, the mobile core network 130 can provide services with high data rates and medium delay traffic, such as services for mobile devices such as mobile phones. For example, the mobile core network 130 may also provide services such as low mobility and low data rate.

The base station 110 may serve multiple

remote units

142, 144, 146 within the service area, such as cells or cell sectors, through wireless communication links. The base station 110 can directly communicate with one or more

remote units

142, 144, 146 via communication signals. The

remote units

142, 144, 146 can directly communicate with one or more base stations 110 via uplink (UL) communication signals. In addition, UL communication signals may be carried over

wireless communication links

115, 148. The base station 110 may also transmit downlink (DL "downlink") communication signals to serve the

remote units

142, 144, 146 in the time domain, frequency domain, and/or air domain. In addition, DL communication signals may be carried through the wireless communication link 115. The wireless communication link 115 may be any suitable carrier in the licensed or unlicensed radio spectrum. The wireless communication link 115 may communicate with one or more

remote units

142, 144, 146 and/or one or more base stations 110. In some embodiments, the wireless communication system 100 conforms to the long-term evolution (LTE) of the 3GPP protocol, in which the base station 110 uses an orthogonal frequency division multiplexing (OFDM) modulation scheme on the DL Send it. The

remote units

142, 144, 146 use a single-carrier frequency division multiple access (single-carrier frequency division multiple access "SC-FDMA") scheme to transmit on the UL. However, more generally, the wireless communication system 100 may implement some other open or proprietary communication protocols, for example, WiMAX, and other protocols. This disclosure is not intended to be limited to the implementation of any particular wireless communication system architecture or protocol.

The base station 110 and the

remote units

142, 144, 146 may be distributed over geographical areas. In some embodiments, base station 110 and

remote units

142, 144, 146 may also be referred to as access points, access terminals, or any other terms used in the art. Generally, two or more geographically adjacent base stations 110 or

remote units

142, 144, 146 are grouped together into a routing area. In some embodiments, the routing area may also be referred to as a location area, a paging area, a tracking area, or any other terminology used in the art. Each "routing area" has an identifier sent from its serving base station 110 to the

remote units

142, 144, 146 (or sent between the

remote units

142, 144, 146).

When the mobile

remote unit

142, 144, 146 moves to a new cell that broadcasts a different "routing area" (eg, moving within the range of the new base station 110), the mobile

remote unit

142, 144, 146 detects a change in the routing area. The RAN 120 in turn pages the mobile

remote units

142, 144, 146 in idle mode through the base station 110 in its current routing area. RAN 120 contains multiple routing areas. As is known in the art, the size of the routing area (eg, the number of base stations included in the routing area) can be selected to balance the routing area update signaling load and paging signaling load.

In some embodiments, the

remote units

142, 144, 146 may be attached to the core network 130. When the

remote unit

142, 144, 146 detects a mobile device network management event (e.g., a change in routing area), the

remote unit

142, 144, 146 may report to the core network 130 (e.g., low latency and high reliability required for autonomous driving) The required service or the high data rate and medium delay traffic required by the mobile phone) sends a mobile device network management request message. Thereafter, the core network 130 forwards the mobile device network management request to one or more auxiliary network slices connected to the

remote units

142, 144, 146 to provide corresponding services.

At a certain moment, the

remote units

142, 144, 146 may no longer need a certain network service (for example, the service with low latency and high reliability required for autonomous driving or the service with high data rate and medium delay traffic required by mobile phones) . In this case, the

remote units

142, 144, 146 may send a separation request message, such as a data connection release message, to separate from the network separation.

2 is a block diagram of an exemplary vehicle with automatic driving capabilities according to some embodiments of the present disclosure. The vehicle 200 with automatic driving capability may be

vehicles

142 and 144 in the wireless communication system 100 managed by the mobile device network shown in FIG. 1. For example, the vehicle 200 with automatic driving capability may include a control module, multiple sensors, a memory, an instruction module, and a controller area network (CAN) and an actuator.

The actuator may include, but is not limited to, drive execution of an accelerator, an engine, a braking system, and a steering system (including steering of tires and/or operation of turn signals).

The plurality of sensors may include various internal and external sensors that provide data to the vehicle 200. For example, as shown in FIG. 2, the plurality of sensors may include vehicle component sensors and environment sensors. The vehicle component sensor is connected to the actuator of the vehicle 200, and can detect the operating status and parameters of various components of the actuator.

The environmental sensor allows the vehicle to understand and potentially respond to its environment in order to assist the autonomous vehicle 200 in navigation, path planning, and to ensure the safety of passengers and people or property in the surrounding environment. The environmental sensor can also be used to identify, track and predict the movement of objects, such as pedestrians and other vehicles. The environment sensor may include a position sensor and an external object sensor.

The position sensor may include a GPS receiver, an accelerometer, and/or a gyroscope, a receiver. The position sensor can sense and/or determine more than 200 geographic locations and orientations of the autonomous vehicle. For example, determine the latitude, longitude and altitude of the vehicle.

The external object sensor can detect objects outside the vehicle, such as other vehicles, obstacles in the road, traffic signals, signs, trees, etc. External object sensors may include laser sensors, radar, cameras, sonar, and/or other detection devices.

The laser sensor can measure the distance between the vehicle and the surface of the object facing the vehicle by rotating on its axis and changing its spacing. Laser sensors can also be used to identify changes in surface texture or reflectivity. Therefore, the laser sensor may be configured to detect the lane line by distinguishing the amount of light reflected by the painted lane line relative to the unpainted dark road surface.

Radar sensors can be located on the front and rear of the car and on either side of the front bumper. In addition to using radar to determine the relative position of external objects, other types of radar can also be used for other purposes, such as traditional speed detectors. Shortwave radar can be used to determine the depth of snow on the road and determine the location and condition of the road surface.

The camera may capture visual images around the vehicle 200 and extract content therefrom. For example, the camera can photograph the signs on both sides of the road and recognize the meaning of these signs through the control module. For example, use the camera to determine the speed limit of the road. The vehicle 200 can also calculate the distance of surrounding objects from the vehicle 200 through the parallax of different images captured by multiple cameras.

The sonar can detect the distance between the vehicle 200 and the surrounding obstacles. For example, the sonar may be an ultrasonic rangefinder. The ultrasonic distance meters are installed on both sides and behind the vehicle, and are turned on when parking to detect obstacles around the parking space and the distance between the vehicle 200 and the obstacles.

After receiving the information sensed by the plurality of sensors, the control module may process information and/or data related to vehicle driving (eg, automatic driving) to perform one or more functions described in the present disclosure. In some embodiments, the control module may be configured to drive the vehicle autonomously. For example, the control module may output multiple control signals. Multiple control signals may be configured to be received by one or more electronic control units (ECUs) to control the driving of the vehicle. In some embodiments, the control module may determine the reference path and one or more candidate paths based on the environmental information of the vehicle.

In some embodiments, the control module may include one or more central processors (eg, single-core processors or multi-core processors). For example only, the control module may include a central processing unit (CPU), application-specific integrated circuit (ASIC), application-specific instruction-set processor (ASIP), graphics Processing unit (graphics, processing unit, GPU), physical processing unit (physics, processing unit, PPU), digital signal processor (DSP), field programmable gate array (field programmable gate array, FPGA), programmable logic Device (programmable logic, device, PLD), controller, microcontroller unit, reduced instruction-set computer (RISC), microprocessor (microprocessor), etc., or any combination thereof.

The memory may store data and/or instructions. In some embodiments, the memory may store data obtained from autonomous vehicle sensors. In some embodiments, the memory may store data and/or instructions that the control module may execute or use to perform the exemplary methods described in this disclosure. In some embodiments, the memory may include mass storage, removable memory, volatile read-and-write memory, read-only memory (ROM), etc., or any combination thereof. As an example, for example, mass storage may include magnetic disks, optical disks, solid-state drives, etc.; for example, removable storage may include flash drives, floppy disks, optical disks, memory cards, zipper disks, magnetic tape; for example, volatile read-write memory may include random access Memory (RAM); for example, RAM can include dynamic RAM (DRAM), double data rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM) and zero capacitor RAM (Z-RAM ); For example, ROM may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and Digital universal disk ROM, etc. In some embodiments, storage can be implemented on a cloud platform. For example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an inter-cloud cloud, a multi-cloud cloud, etc., or any combination thereof.

In some embodiments, the memory may be a local memory, that is, the memory may be part of the autonomous vehicle 200. In some embodiments, the memory may also be remote memory. The central processor may connect the remote memory through the network 100 to communicate with one or more components (eg, control module, sensor module) of the autonomous vehicle 200. One or more components in the autonomous vehicle 200 can access data or instructions stored remotely in a remote memory via the network 100. In some embodiments, the memory 420 may be directly connected to or communicate with one or more components in the autonomous vehicle 200 (eg, control module, sensor).

The command module receives the information from the control module and converts it into a command to drive the actuator to the Controller Area Network (Controller Area Network) CAN bus. For example, the control module sends the driving strategy (acceleration, deceleration, turning, etc.) of the autonomous vehicle 200 to the instruction module, and the instruction module receives the driving strategy and converts it into a driving instruction for the actuator (for throttle, braking Drive instructions for the mechanism and steering mechanism). At the same time, the instruction module then sends the instruction to the execution mechanism via the CAN bus. The execution of the instruction by the actuator is detected by the vehicle component sensor and fed back to the control module, thereby completing the closed-loop control and driving of the automatic driving vehicle 200.

FIG. 3 is a schematic diagram of an embodiment of a control system and method based on an autonomous driving vehicle in this application. As shown in FIG. 3, the autonomous driving vehicle 200 (hereinafter referred to as "vehicle") can travel on the road 321 along its autonomously set path 320 without people entering the path. The autonomous driving vehicle 200 must not violate the traffic rules of the road 321 when driving on the road 321, for example, the speed of the autonomous driving vehicle 200 cannot exceed the maximum speed limit of the road 321, or for example, driving to a traffic light intersection Do not run through the red light.

The autonomous vehicle 200 may include some conventional structures owned by non-autonomous vehicles, such as an engine, wheels, steering wheel, etc., and may also include a perception module 340, a control module 350, and a decision-making module 360.

At the intersection of the road 321, a traffic light 310, a parking line 311, a zebra crossing 312, and a sign 313 are provided. The self-driving vehicle 200 can recognize and obtain information about the intersection, including the status of the traffic light 310 (for example , The color of the traffic lights and the countdown time), the distance to the intersection parking line 311 and the zebra crossing 312, the content of the sign 313, etc. The sign 313 is a graphic symbol showing traffic regulations and road information, including but not limited to warning signs, prohibition signs, road signs, tourist area signs, road construction safety signs, speed limit signs (eg, maximum speed limit), etc. . During the process of driving to the intersection, the autonomous vehicle 200 may determine the driving speed of the vehicle based on the state of the traffic light 310, for example, based on the color of the traffic light 310 and the countdown time, and the parking line at the intersection Parameters such as the distance of 311, the current real-time speed, etc., to determine whether the vehicle can pass the intersection parking line 311, and generate and execute a corresponding driving strategy based on the judgment result, for example, when the traffic light 310 is green and the countdown time is sufficient For a long time, the autonomous vehicle 200 accelerates through the intersection parking line 311; for another example, when the traffic light 310 is red and the countdown time is long enough, the autonomous vehicle 200 decelerates and stops at the intersection Stop in front of line 311.

An embodiment of the present application provides a method for controlling an autonomous driving vehicle, as shown in FIG. 6, including:

Step S101: Acquire real-time driving data of the self-driving vehicle through the vehicle-mounted automatic driving system of the self-driving vehicle;

Step S102: Based on the real-time driving data, the vehicle-mounted automatic driving system generates a first decision;

Step S103: The vehicle-mounted automatic driving system sends the real-time driving data to a remote data processing system;

Step S104: The vehicle-mounted automatic driving system receives a second decision from the remote data processing system, the second decision is that the remote data processing system generates based on the real-time driving data;

Step S105: Checking and comparing the second decision with the first decision through the automatic driving system;

Step S106: According to the result of the verification calculation, the vehicle-mounted automatic driving system issues a decision instruction to the automatic driving vehicle.

The possible embodiments of the self-driving vehicle and the self-driving system are provided below with reference to FIGS. 2 to 4.

The self-driving vehicle described in the embodiments of the present application is, for example, the self-driving vehicle 200 illustrated in FIGS. 2 and 3. The on-board equipment of the self-driving vehicle includes all electronic and mechanical devices equipped in the self-driving vehicle, and can acquire all data and information detected, sensed or generated by the self-driving vehicle 200. In some embodiments of the present application, the on-board equipment of the automatic driving vehicle 200 includes the automatic driving system 400 of the automatic driving vehicle 200.

4 is a block diagram of an exemplary vehicle with automatic driving capabilities and an automatic driving system 400 according to some embodiments of the present application. As shown in FIG. 4, the automatic driving system 400 may include a perception module 340, a control module 350, and a decision-making module 360, a memory 420, a network 430, a gateway module 440, a controller area network (CAN) 450, and an engine management system ( EMS) 460, electric stability control (ESC) 470, electric power system (EPS) 480, steering column module (SCM) 490, throttle system 465, braking system 475 and steering system 495, etc.

The perception module 340 can collect the driving data and environment information of the vehicle, the driving data and environment information include but not limited to: the real-time speed of the vehicle, the distance between the vehicle and the target, the traveling route of the vehicle, and the traffic conditions in the traveling route of the vehicle , The color of traffic lights, the countdown time of traffic lights and the maximum speed limit of intersections, information of other vehicles or pedestrians in front of and behind the vehicle, visual information on both sides of the road, location information of vehicles, etc. In some embodiments, the perception module 340 may include a visual sensor 342, a distance sensor 344, a speed sensor 346, an acceleration sensor 348, and a positioning unit 349. The visual sensor 342 can detect the state of the traffic light 310 (including the color of the traffic light 310 and the countdown time), the lane line, the sign 313 and other vehicles, etc., and transmit the detected visual information to The judgment decision module 360. In some embodiments, the vision sensor 342 may use a binocular camera, a LIDAR system, etc., all vision systems known to those skilled in the art. The distance sensor 344 can measure the distance between the self-driving vehicle 200 and a specific target in the environment (for example, the intersection parking line 311, other vehicles around the self-driving vehicle 200), and transmit its measurement information to The judgment decision module 360. In some embodiments, the distance sensor 344 may measure the distance between the two based on the positioning information of the autonomous vehicle 200 and the location information of the target on the map. In some embodiments, the distance sensor 344 is a laser radar or a millimeter wave radar, and performs three-dimensional modeling on the surrounding environment of the autonomous vehicle 200. The speed sensor 346 can measure the real-time driving speed of the autonomous vehicle 200 and transmit the measurement information to the judgment and decision module 360. The acceleration sensor 348 can measure the real-time acceleration of the autonomous vehicle 200 and transmit the measurement information to the judgment and decision module 360. The positioning unit 349 may perform real-time positioning on the autonomous vehicle 200 and transmit positioning information to the judgment and decision module 360. In some embodiments, the positioning unit 349 is a high-precision GPS positioning unit.

The judgment and decision module 360 may receive the driving information and environment information such as traffic signal information, obstacle information, surrounding vehicle information, pedestrian information, etc., and generate judgment information and information for the judgment based on the driving information and environment information Driving decision information. In some embodiments, the judgment information includes but is not limited to: when the traffic light 310 is green, whether the self-driving vehicle 200 can pass the intersection parking line 311 within the countdown time of the corresponding traffic light; or when the traffic light When 310 is red or yellow respectively, can the self-driving vehicle 200 pass through the intersection parking line 311 within the time corresponding to the traffic light countdown; when there are obstacles, pedestrians or other vehicles in the vehicle's journey, the automatic The driving vehicle 200 should perform operations such as deceleration, detour, or parking. In some embodiments, the decision information includes but is not limited to: issuing a driving command to the autonomous vehicle 200 to maintain a constant speed in real time, accelerate, decelerate, or stop driving. In some embodiments, the accelerated travel command includes but is not limited to: uniform acceleration or variable acceleration. In some embodiments, the decelerating travel command includes but is not limited to: uniform deceleration or variable deceleration.

The control module 350 may process information and/or data related to vehicle driving (eg, automatic driving) to perform one or more functions described in this application. In some embodiments, the control module 350 may receive the decision information, and control the autonomous vehicle 200 to execute the decided driving instruction according to the decision information. In some embodiments, the control module 350 may be configured to autonomously drive the vehicle. For example, the control module 350 may output multiple control signals. Multiple control signals may be configured to be received by multiple electronic control units (ECUs) to control the driving of the vehicle. In some embodiments, the control module 350 may determine the driving speed of the vehicle based on the environmental information of the vehicle (eg, the status of the traffic light 310). In some embodiments, the control module 350 may include one or more processing engines (eg, a single-core processing engine or a multi-core processor). For example only, the control module 350 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), and an application-specific instruction-set processor (ASIP) ), graphics processing unit (GPU), physical processing unit (PPU), digital signal processor (DSP), field programmable gate array (FPGA), Programmable logic device (programmable logic device, PLD), controller, microcontroller unit, reduced instruction set computer (RISC), microprocessor (microprocessor), etc., or any combination thereof.

The memory 420 may store data and/or instructions. In some embodiments, the memory 420 may store data obtained from the autonomous vehicle 200 (eg, data measured by sensors in the perception module 340). In some embodiments, the memory 420 may store a high-precision map, which also includes information such as the number of lanes, the width of the lane, the curvature of the road, the gradient of the road, the maximum speed, and the recommended driving speed. In some embodiments, the memory 420 may store data and/or instructions that the control module 350 may execute or use to perform the exemplary methods described in this application. In some embodiments, the memory 420 may include a large-capacity memory, a removable memory, a volatile read-and-write memory, a read-only memory (ROM), etc., or any combination thereof. As an example, for example, mass storage may include magnetic disks, optical disks, solid-state drives, etc.; for example, removable storage may include flash drives, floppy disks, optical disks, memory cards, zipper disks, magnetic tape; for example, volatile read-write memory may include random access Memory (RAM); for example, RAM can include dynamic RAM (DRAM), double data rate synchronous dynamic RAM (DDR SDRAM), static RAM (SRAM), thyristor RAM (T-RAM) and zero capacitor RAM (Z-RAM ); For example, ROM may include mask ROM (MROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), compact disk ROM (CD-ROM), and Digital universal disk ROM, etc.

In some embodiments, the memory 420 may be connected to the network 430 to communicate with one or more components of the autonomous vehicle 200 (eg, control module 350, visual sensor 342). One or more components in the self-driving vehicle 200 can access data or instructions stored in the memory 420 via the network 430. In some embodiments, the memory 420 may be directly connected to or in communication with one or more components in the autonomous vehicle 200 (eg, control module 350, visual sensor 342). In some embodiments, the memory 420 may be part of the autonomous vehicle 200.

The network 430 may facilitate the exchange of information and/or data. In some embodiments, one or more components in the autonomous vehicle 200 (eg, control module 350, visual sensor 342) may send information and/or data to the autonomous vehicle 200 via the network 430 Other components. E.g. The control module 350 may obtain/acquire the dynamic situation of the vehicle and/or the environment information around the vehicle via the network 430. In some embodiments, the network 430 may be any type of wired or wireless network, or a combination thereof. For example only, the network 430 may include a wired network, a wired network, a fiber optic network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), and a metropolitan area network (MAN) , Wide area network (WAN), public switched telephone network (PSTN), Bluetooth network, ZigBee network, near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 430 may include one or more network access points. For example, the network 430 may include wired or wireless network access points, such as base stations and/or Internet exchange points 430-1, .... One or more components of the autonomous vehicle 200 may be connected to the network 430 to exchange data and/or information.

The gateway module 440 may determine the command sources of multiple ECUs (eg, EMS 460, EPS 480, ESC 470, SCM 490) based on the current driving state of the vehicle. The command source may come from a human driver, from the control module 350, etc., or any combination thereof.

The gateway module 440 may determine the current driving state of the vehicle. The driving state of the vehicle may include a manual driving state, a semi-automatic driving state, an automatic driving state, an error state, etc., or any combination thereof. For example, the gateway module 440 may determine the current driving state of the vehicle as a manual driving state based on input from a human driver. For another example, when the current road conditions are complicated, the gateway module 440 may determine the current driving state of the vehicle as a semi-automatic driving state. As yet another example, when an abnormality (eg, signal interruption, processor crash) occurs, the gateway module 440 may determine the current driving state of the vehicle as an error state.

In some embodiments, the gateway module 440 may determine that the current driving state of the vehicle is a manual driving state, and send the operation of the human driver to multiple ECUs. For example, after determining that the current driving state of the vehicle is a manual driving state, the gateway module 440 may respond to sending a pressing operation of the accelerator of the self-driving vehicle 200 performed by a human driver to the EMS 460. After determining that the current driving state of the vehicle is the automatic driving state, the gateway module 440 may respond to send the control signal of the control module 350 to multiple ECUs. For example, after determining that the current driving state of the vehicle is an automatic driving state, the gateway module 440 may respond to sending a control signal associated with a steering operation to the SCM 490. The gateway module 440 may send the operation of the human driver and the control signal of the control module 350 to multiple ECUs in response to the conclusion that the current driving state of the vehicle is a semi-automatic driving state. When it is determined that the current driving state of the vehicle is an error state, the gateway module 440 may respond to send an error signal to multiple ECUs.

The controller area network (CAN bus) 450 is a reliable vehicle bus standard (eg, message-based protocol), which allows microcontrollers (eg, control module 350) and devices (eg, EMS 460, (EPS480, ESC470, SCM490, etc.) communicate with each other in applications without a host computer. The CAN 450 may be configured to connect the control module 350 with multiple ECUs (eg, EMS 460, EPS 480, ESC 470, SCM 490).

The EMS 460 may determine the engine performance of the autonomous vehicle 200. In some embodiments, the EMS 460 may determine the engine performance of the autonomous vehicle 200 based on the control signal from the control module 350. E.g. When the current driving state is the automatic driving state, the EMS 460 may determine the engine performance of the automatic driving vehicle 200 based on the control signal associated with the acceleration from the control module 350. In some embodiments, the EMS 460 may determine the engine performance of the autonomous vehicle 200 based on the operation of a human driver. For example, when the current driving state is the manual driving state, the EMS 460 may determine the engine performance of the autonomous vehicle 200 based on the depression of the accelerator by the human driver.

The EMS 460 may include multiple sensors and at least one microprocessor. The multiple sensors may be configured to detect one or more physical signals and convert the one or more physical signals into electrical signals for processing. In some embodiments, the plurality of sensors may include various temperature sensors, air flow sensors, throttle position sensors, pump pressure sensors, speed sensors, oxygen sensors, load sensors, knock sensors, etc., or any combination thereof. The one or more physical signals may include, but are not limited to, engine temperature, engine air intake, cooling water temperature, engine speed, etc., or any combination thereof. The microprocessor may determine engine performance based on multiple engine control parameters. The microprocessor may determine multiple engine control parameters based on multiple electrical signals, and may determine multiple engine control parameters to optimize engine performance. The plurality of engine control parameters may include ignition timing, fuel delivery, idling airflow, etc., or any combination thereof.

The throttle system 465 can change the motion of the autonomous vehicle 200. For example, the throttle system 465 may determine the speed of the autonomous vehicle 200 based on engine output. As another example, the throttle system 465 may cause acceleration of the autonomous vehicle 200 based on engine output. The throttle system 465 may include fuel injectors, fuel pressure regulators, auxiliary air valves, temperature switches, throttles, idle speed motors, fault indicators, ignition coils, relays, etc., or any combination thereof. In some embodiments, the throttle system 465 may be an external actuator of the EMS 460. The throttle system 465 may be configured to control engine output based on a plurality of engine control parameters determined by EMS460.

The ESC 470 can improve the stability of the vehicle, and the ESC 470 can improve the stability of the vehicle by detecting and reducing traction loss. In some embodiments, the ESC 470 may control the operation of the braking system 475 to help maneuver the vehicle in response to determining that the ESC 470 detects a loss of steering control. For example, the ESC 470 can improve the stability of the braking system 475. When the vehicle starts ignition on an uphill slope, the brakes are used to prevent the vehicle from sliding down and help the vehicle ignite smoothly. In some embodiments, the ESC 470 can further control engine performance to improve vehicle stability. For example, the ESC 470 may reduce engine power when a possible loss of steering control occurs. Scenarios where loss of steering control may occur include: when the vehicle is coasting during an emergency avoidance turn, when the vehicle is poorly judged on a slippery road, and understeer or oversteer.

The braking system 475 can control the movement state of the autonomous vehicle 200. For example, the braking system 475 may decelerate the autonomous vehicle 200. As another example, the braking system 475 may stop the autonomous vehicle 200 from moving forward under one or more road conditions (eg, downhill). As yet another example, the braking system 475 may maintain the constant speed of the autonomous vehicle 200 when driving downhill. The braking system 475 may include mechanical control components, hydraulic units, power units (eg, vacuum pumps), actuator units, etc., or any combination thereof. Mechanical control components may include pedals, hand brakes, etc. The hydraulic unit may include hydraulic oil, hydraulic hose, brake pump, etc. The actuator unit may include brake calipers, brake pads, brake discs, etc.

The EPS 480 can control the power supply of the autonomous vehicle 200. The EPS 480 may supply, transmit, and/or store power to the autonomous vehicle 200. For example, the EPS 480 may include one or more batteries and an alternator. The alternator can charge the battery, and the battery can be connected to other parts of the autonomous vehicle 200 (for example, a starter to provide power). In some embodiments, the EPS 480 may control the power supply to the steering system 495. For example, when the self-driving vehicle 200 determines that a sharp turn is required (for example, the steering wheel is driven all the way to the left or all the way to the right), the EPS 480 may provide large power to the steering system 495 in response The self-driving vehicle 200 generates a large steering torque.

The SCM 490 can control the steering wheel of the vehicle. The SCM 490 can lock/unlock the steering wheel of the vehicle. The SCM 490 can lock/unlock the steering wheel of the vehicle based on the current driving state of the vehicle. For example, the SCM 490 may lock the steering wheel of the vehicle in response to determining that the current driving state is the automatic driving state. In response to determining that the current driving state is the automatic driving state, the SCM 490 may further retract the steering column shaft. As another example, the SCM 490 may unlock the steering wheel of the vehicle in response to determining that the current driving state is a semi-automatic driving state, a manual driving state, and/or an error state. The SCM 490 may control the steering of the autonomous vehicle 200 based on the control signal of the control module 350. The control signal may include information about the turning direction, turning position, turning angle, etc., or any combination thereof.

The steering system 495 can operate the autonomous vehicle 200. In some embodiments, the steering system 495 may manipulate the autonomous vehicle 200 based on the signal sent from the SCM 490. For example, the steering system 495 may guide the autonomous driving vehicle 200 based on the control signal of the control module 350 sent from the SCM 490 in response to determining that the current driving state is the autonomous driving state. In some embodiments, the steering system 495 may manipulate the autonomous vehicle 200 based on human driver operations. For example, when the human driver turns the steering wheel to the left in response to determining that the current driving state is the manual driving state, the steering system 495 may turn the autonomous vehicle 200 to the left.

FIG. 5 is a schematic diagram of exemplary hardware and software components of the information processing unit 500. The information processing unit 500 may carry and implement the control module 350, EMS 460, ESC 470, EPS 480, SCM 490, etc. For example, the control module 350 may be implemented on the information processing unit 500 to perform the functions of the control module 350 disclosed in the present application.

The information processing unit 500 may be a dedicated computer device specially designed to process signals from sensors and/or components of the autonomous vehicle 200 and send instructions to the sensors and/or components of the vehicle 200.

For example, the information processing unit 500 may include a COM port 550 connected to a network connected thereto to facilitate data communication. The information processing unit 500 may further include a processor 520 in the form of one or more processors for executing computer instructions. Computer instructions may include, for example, routines, programs, objects, components, data structures, processes, modules, and functions that perform specific functions described herein. For example, the processor 520 may obtain one or more path sample features related to multiple candidate paths. The one or more sample features related to the candidate path may include the path start position, the path destination, the path speed of the vehicle associated with the candidate path, the path acceleration of the vehicle, and the instantaneous curvature of the path of the candidate path. Or the like, or any combination thereof.

In some embodiments, the processor 520 may include one or more hardware processors, such as a microcontroller, microprocessor, reduced instruction set computer (RISC), application specific integrated circuit (ASIC), application-specific instructions -Assembly processor (ASIP), central processing unit (CPU), graphics processing unit (GPU), physical processing unit (PPU), microcontroller unit, digital signal processor (DSP), field programmable gate array (FPGA) , Advanced RISC machine (ARM), programmable logic device (PLD), any circuit or processor capable of performing one or more functions, etc., or any combination thereof.

The information processing unit 500 may include an internal communication bus 510, program storage and different forms of data storage (for example, a magnetic disk 570, a read only memory (ROM) 530, or a random access memory (RAM) 540) for processing by a computer And/or various data files sent. The information processing unit 500 may further include program instructions stored in the ROM 530, RAM 540, and/or other types of non-transitory storage media to be executed by the processor 520. The method and/or process of the present application may be implemented as program instructions. The information processing unit 500 also includes an I/O component 560 that supports input/output between the computer and other components (eg, user interface elements). The information processing unit 500 can also receive programming and data through network communication.

Just to illustrate the problem, only one processor is described in the information processing unit 500 described in this application. However, it should be noted that the information processing unit 500 in this application may also include multiple processors, therefore, the operations and/or method steps disclosed in this application may be performed by one processor as described in this application, or It can be executed jointly by multiple processors. For example, if the processor 520 of the information processing unit 500 executes steps A and B in this application, it should be understood that steps A and B may also be executed jointly or separately by two different processors in information processing (for example, The first processor performs step A, the second processor performs step B, or the first and second processors perform steps A and B together.

Based on the description of the above embodiments of the present application, step S101 is executed to obtain the real-time driving generated, sensed or detected by the autonomous driving vehicle 200 during driving through the vehicle-mounted device of the autonomous driving vehicle, such as the sensing module 340 of the automated driving system 400 Data, the real-time driving data is, for example, driving data and environmental information of an autonomous driving vehicle, and the driving data and environmental information include, but are not limited to: real-time speed of the autonomous driving vehicle, distance between the vehicle and the target, and the route of the vehicle, The traffic conditions on the vehicle's route, the color of the traffic lights, the countdown time of the traffic lights and the maximum speed limit of the intersection, other vehicles or pedestrians in front of and behind the vehicle, visual information on both sides of the road, vehicle positioning information, etc. In some embodiments of the present application, the driving data and the environment information may be obtained through the visual sensor 342, the distance sensor 344, the speed sensor 346, the acceleration sensor 348, the positioning unit 349, etc. of the perception module 340.

In an embodiment of the present application, the real-time driving data may be stored in the memory 420 of the automatic driving system 400. The real-time driving data storage can be realized by a capacity memory, a removable memory, a volatile read-write memory, a read-only memory, or any combination thereof. In some embodiments of the present application, the real-time driving data may also be stored in the cloud, that is to say, the memory 420 is a cloud memory.

Further, the real-time driving data is sent to the judgment and decision module 360 of the automatic driving system 400. In one embodiment of the present application, the judgment and decision module 360 may process the received real-time driving data to convert the real-time driving data into a file suitable for the judgment and decision module 360 to perform the judgment step format.

In an embodiment of the present application, the judgment and decision module 360 judges the driving state of the autonomous vehicle and the current environmental condition based on the received real-time driving data; and forms a The first decision to drive the autonomous vehicle 200 (step S102). For example, the first decision is to reduce or increase the speed of the vehicle, or the first decision is to control the autonomous vehicle to change lanes, or the first decision is to determine the automatic Accurate positioning of the driving vehicle, or the first decision is to control the vehicle to stop driving or enter a nearby parking lot.

In some embodiments of the present application, the judgment and decision module 360 processes the real-time driving data by executing an algorithm model set in the automatic driving system 400 of the automatic driving vehicle 200, and forms the first One decision. That is, the first decision is obtained by the vehicle-mounted automatic driving system through the first decision model using the real-time driving data. Because the real-time driving data may contain various information, for example, the driving route information of the vehicle, the driving speed information of the vehicle, the driving information of other vehicles around the vehicle during the driving process, the traffic light information, the road condition information, and the obstacles on the driving route Information, etc. Therefore, for different information and data, the first decision model adopted by the automatic driving system is also different.

For example, if the data is the information of the traffic light 310 identified by the perception module 340 when the intersection encounters a traffic light during the driving of the autonomous vehicle 200, then the first decision model executed by the decision module may be: Determine whether the distance between the front of the autonomous vehicle 200 and the intersection parking line 311 is greater than the deceleration zone, and if so, directly form a first decision. In some embodiments, the deceleration zone is expressed as: the taxi distance required when the autonomous vehicle 200 decelerates to zero at a current real-time speed according to a predetermined deceleration strategy. The first decision model can be expressed by the following formula to determine whether the distance between the front of the autonomous vehicle 200 and the intersection parking line 311 is greater than the deceleration zone:

Where D is the distance between the front of the self-driving vehicle and the intersection parking line 311, V is the prescribed taxi speed of the vehicle, and a is the acceleration during the parking phase.

In an embodiment of the present application, after the first decision is formed, the first decision is stored in the memory 420. However, the first decision is not directly sent to the control module 350.

Step S103 is executed: the vehicle-mounted automatic driving system 400 sends the real-time driving data to the remote data processing system 600, and processes the information and data to generate a second decision;

7 is a structural block diagram of the remote data processing system 600. The remote data processing system 600 at least includes: a data sending and receiving module 610; a second memory 620; a second judgment and decision module 630 and a network 640.

The data sending and receiving module 610 is used to receive real-time driving data sent from the automatic driving system 400 of the automatic driving vehicle 200, and used to send the processed real-time driving data and decision information back to the automatic driving system 400.

Second memory 620; said second memory 620 can store data and/or instructions. In some embodiments, the second memory 620 may store data sent from the autonomous vehicle. In some embodiments, the second memory 620 may store the information and data processed by the remote data processing system and the second decision obtained after processing by the remote data processing system to perform the description in the present disclosure Example method. In some embodiments, the storage function of the second memory 620 may be implemented on a cloud platform. As an example only, the cloud platform may

To include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, inter-cloud, multi-cloud, etc., or any combination thereof.

In some embodiments, the second storage 620 is a remote storage, and may include mass storage, removable storage, etc., or any combination thereof. As an example, for example, a large-capacity memory may include a magnetic disk, an optical disk, a solid state drive, etc.; for example, a removable memory may include a flash memory drive, a floppy disk, an optical disk, a memory card, a zipper disk, and a magnetic tape.

The second judgment decision module 630 may process the information and data sent by the automatic driving system and form a second decision. The information and data are, for example, real-time driving data of self-driving vehicles, such as traffic signal information around the vehicle, obstacle information during travel, surrounding vehicle information, pedestrian information, vehicle acceleration information, vehicle positioning information, vehicle travel Route information, etc.

In an embodiment of the present application, the second judgment decision module 630 judges the driving state of the automatic driving vehicle and the current environmental condition according to the received real-time driving data; and according to the judgment result, forms The second decision. For example, the second decision is to reduce or increase the speed of the vehicle, or the second decision is to control the autonomous vehicle to change lanes, or the second decision is to determine the automatic Accurate positioning of the driving vehicle, or the second decision is to control the vehicle to stop driving or drive into a nearby parking lot.

In some embodiments of the present application, the second judgment and decision module 630 is the same as the real-time driving data acquired during the driving process of the autonomous vehicle processed by the judgment and decision module 360 of the automatic driving system 400. The second decision and its first decision are also in one-to-one correspondence. For example, in actual operation, if the decision-making module 360 of the automatic driving system 400 is based on the information of the traffic light 310 recognized by the perception module 340 when the traffic light is encountered at the intersection during the driving of the automatic driving vehicle 200, the decision is made The first decision, the second judgment decision module 630 of the remote data processing system 600 will also make the decision based on the information of the traffic light 310 recognized by the perception module 340 when the traffic light is encountered at the intersection during the driving of the autonomous vehicle 200 The second decision.

In other embodiments of the present application, the amount of data processed by the second judgment and decision module 630 is greater than the real-time driving data acquired during the driving process of the autonomous vehicle processed by the judgment and decision module 360 of the automatic driving system 400. This is because the second decision module 630 may also store or obtain information from other data sources. For example, during the driving process of an automatic driving vehicle, the map information acquired by the vehicle's automatic driving system is limited to a certain distance around the vehicle body, and the remote data processing system 600 can also obtain from the cloud a farther range provided by other devices Traffic congestion information, road condition information, etc.

In some embodiments of the present application, the second judgment decision module 630 processes the information and data by executing the second decision model set in the remote data processing system 600, and forms the first Second decision. Because the information and data may contain a variety of information, for example, the driving route information of the vehicle, the driving speed information of the vehicle, the driving information of other vehicles around the vehicle during the driving process, the traffic light information, the road condition information, and the obstacles on the driving route Information, etc. Therefore, for different information and data, the second decision model adopted by the remote data processing system 600 is also different.

In some embodiments of the present application, because the decision-making module 360 and the second decision-making module 630 use different decision-making models for data processing, the first decision and the second decision may be the same or possible different. In some embodiments of the present invention, the depth, breadth, and fineness of the second judgment and decision module's processing of the data are greater than the judgment and decision module 360, which may make the accuracy of the second decision And the degree of refinement are greater than the first decision. This is because the judgment and decision module 360 is installed in the vehicle-mounted automatic driving system. Due to the limitation of the data storage capacity and data calculation capability of the vehicle-mounted automatic driving system, the first decision model is relatively simple compared to the second decision model The operation breadth, operation accuracy and operation depth are limited, and the data operation capability of the judgment and decision module 360 is less than the data operation capability of the second judgment and decision module 630. Based on this, in some embodiments of the present invention, the accuracy of the second decision is greater than the accuracy of the first decision. For example, when planning the driving route of an autonomous vehicle, the second decision model can integrate traffic jam information and road condition information at a longer distance. Therefore, the accuracy and practicability of the second decision is given. More accurate and practical than the first decision. Moreover, in some embodiments of the present application, the operation complexity of the second decision model, for example, the number of operation layers is also much higher than that of the first decision model.

In some specific embodiments of the present application, if the data is the information of the traffic light 310 identified by the perception module 340 when the intersection encounters a traffic light during the driving of the autonomous vehicle 200, then the second judgment decision The second decision model executed by the module is, for example:

If the self-driving vehicle 200 travels according to a predetermined acceleration strategy and accelerates from the current real-time speed to the maximum speed limit, is the time at the intersection parking line 311 of the self-driving vehicle 200 not greater than the countdown time of the green light. In some embodiments, the predetermined acceleration strategy may include, but is not limited to: uniformly accelerate to the maximum speed limit within a specified distance at the current real-time speed, or accelerate to the maximum speed limit at the current real-time speed (such as a triangle The function method will accelerate to the maximum speed limit of the road within the specified distance). The calculation method of the self-driving vehicle 200 through the intersection parking line may be calculated according to the vehicle heading through the intersection parking line 311, may also be calculated according to the vehicle body passing through the intersection parking line, or may be calculated according to the vehicle passing through the intersection parking line. For example, the second decision model judges that if the vehicle is accelerating to the maximum speed limit through the intersection parking line 311 at the end of the vehicle according to the uniform acceleration strategy (assuming that the green light turns to a red light at the end of the vehicle, the vehicle must pass the parking line in order to not cross the red light), Whether the time when the vehicle arrives at the intersection is greater than the remaining countdown time of the green light:

Where t _a is the countdown time corresponding to the green light, D is the distance between the front of the vehicle and the intersection, L _v is the length of the vehicle body, V is the real-time speed of the vehicle, and V _max is the maximum speed limit of the intersection.

The remote data processing system 600 further includes a network for transmission and exchange of the real-time driving data

640. In some embodiments of the present application, the network may be the same network as the network 430 in the automatic driving control system, or may be a different network, but when the network is a different network, it should be guaranteed Data can be transmitted and exchanged between different networks.

In some embodiments, the network 640 may be any type of wired or wireless network, or a combination thereof. For example only, the network 640 may include a wired network, a wired network, an optical fiber network, a telecommunications network, an intranet, the Internet, a local area network (LAN), a wide area network (WAN), a wireless local area network (WLAN), and a metropolitan area network (MAN) , Wide area network (WAN), public switched telephone network (PSTN), Bluetooth network, ZigBee network, near field communication (NFC) network, etc., or any combination thereof. In some embodiments, the network 640 may include one or more network access points.

In other embodiments of the present application, the remote data processing system 600 further includes a second perception module, which is used to deeply sense the driving data and environmental information collected by the perception module 340, and to The perception result is sent back to the vehicle-mounted automatic driving system. The driving data and environmental information include but are not limited to: the real-time speed of the vehicle, the distance between the vehicle and the target, the route of the vehicle, the traffic conditions in the vehicle's route, the color of the traffic light, the time of the traffic light countdown, and the highest intersection Speed limit, other vehicles or pedestrian information before and after the vehicle, visual information on both sides of the road, vehicle positioning information, etc. In some embodiments of the present application, the remote data processing system 600 has a wider range of perception of data. Therefore, the breadth and accuracy of the perception result is greater than the perception breadth and accuracy of the automatic driving system.

Step S104 is executed to send the second decision back to the automatic driving system 400 through the data sending and receiving module, and the control module 350 of the automatic driving system receives the second decision and converts the The second decision is stored in the memory 420.

Step S105 is executed, and the second decision and the first decision are checked and compared by the decision-making module 360 of the automatic driving system, and the checked comparison may also be called redundant comparison; in communication engineering , Redundancy points out the consideration of system safety and reliability, and artificially repeats some key components or functions. When the system fails, for example, a certain device is damaged, the redundantly configured components can be used as backups to intervene in time and undertake the work of the failed components, thereby reducing the system's failure time. Redundancy is especially used for emergency treatment. Redundancy can exist at different levels, such as network redundancy, server redundancy, disk redundancy, data redundancy, etc.

Step S106 is executed, and according to the result of the verification calculation, the vehicle-mounted automatic driving system issues a decision instruction to the automatic driving vehicle. In some embodiments of the present application, if the first decision and the second decision are the same, the control module 350 of the automatic driving system receives the first decision or the second decision and sends a request to the autonomous driving vehicle To issue decision-making instructions. In some embodiments, the control module 350 may be configured to autonomously drive the vehicle. For example, the control module 350 may output multiple control signals. Multiple control signals may be configured to be received by multiple electronic control units (ECUs) to control the driving of the vehicle.

In some embodiments of the present application, the control module 350 autonomously communicates to the gateway module 440, controller area network (CAN) 450, engine management system (EMS) 460, electric stability control (ESC) 470, An electric power system (EPS) 480, a steering column module (SCM) 490, a throttle system 465, a brake system 475, and a steering system 495 etc. issue execution instructions to control the autonomous vehicle to perform acceleration, deceleration, lane change, turning, etc. operating.

In other embodiments of the present application, there is a small difference between the first decision and the second decision (the difference between the first decision and the second decision is less than a preset threshold), for example, the first decision and the second decision Second decision There is a slight difference in the judgment of the coordinate position of the autonomous driving vehicle, the judgment of the operating speed and running route of the autonomous driving vehicle, etc. When the difference is less than the set threshold, the first decision can be directly selected Or the second decision. For different decision-making information, the choices will be different. For example, if the first decision and the second decision are judgments on the speed and body coordinates of the self-driving vehicle, because the accuracy of the second decision combing data is higher and the range of processing data is wider, then the decision The value of the second decision. In addition, in the case of traffic jams, when planning the driving route of autonomous vehicles, because the data range obtained by the second decision model is wider (obtained from other data acquisition centers), the amount of data processed may be larger. Therefore, the accuracy of the second decision is higher. When performing path planning to determine the expected arrival time of the vehicle, the accuracy of the second decision may also be higher.

If the first decision and the second decision are decisions about whether the traffic light intersection needs to be accelerated, the relatively safe decision instruction in the first decision and the second decision is adopted. In some embodiments, the average of the first decision and the second decision may also be used.

In the embodiment of the present application, the judgment on the difference between the first decision and the second decision instruction is based on empirical values and theoretical data judgment (pre-set threshold), for different types of decision information, the judgment on the instruction difference Methods and judgment standards are also different, and the difference judgment can be optimized and set with the accumulation of empirical data and the improvement of technical solutions.

In some embodiments of the present application, the decision may also be a third decision obtained based on the first decision and the second decision. For example, the third decision is a function of the first decision and the second decision.

In some other embodiments of the present application, if the difference between the first decision and the second decision is determined to be large (the difference between the first decision and the second decision is greater than a preset threshold), the decision is determined to be If the automatic driving vehicle and the automatic driving system are faulty, the control module issues a parking instruction to drive the automatic driving vehicle off the road as soon as possible, such as entering a parking lot or a roadside parking permit, and notifying the gateway module, or Issue early warning information.

In some other embodiments of the present application, if the difference between the first decision and the second decision is determined to be large (the difference between the first decision and the second decision is greater than a preset threshold), continue to repeat the execution The method for controlling an autonomous driving vehicle provided in the embodiments of the present application can avoid calculation errors that may be generated during the process of obtaining the first decision and the second decision and comparing them before. After performing the comparison calculation again, if the difference between the first decision and the second decision finally obtained is less than a preset threshold, the first decision or the second decision is selected. If the difference between the first decision and the second decision finally obtained is still greater than a preset threshold, the control module drives the autonomous vehicle to stop immediately or leave the driving environment as soon as possible, and enter the safe environment to stop.

An embodiment of the present application further provides an automatic driving system, including: a memory, the memory includes at least one set of instructions, the instructions are constructed to complete a driving strategy for an autonomous vehicle; a processor, reads the The at least one set of instructions in the memory, and according to the at least one set of instructions:

Acquiring real-time driving data of the self-driving vehicle;

Generating first decision information based on the real-time driving data;

Send the real-time driving data to a remote data processing system;

Receiving a second decision from the remote data processing system, the second decision being generated by the remote data processing system based on the real-time driving data;

Checking and comparing the second decision and the first decision, and according to the result of the checking and comparison, issuing a decision instruction to the autonomous vehicle.

An embodiment of the present application also provides an automatic driving vehicle equipped with the automatic driving system.

In summary, after reading this detailed disclosure, those skilled in the art may understand that the foregoing detailed disclosure may be presented by way of example only, and may not be limiting. Although not explicitly stated here, those skilled in the art can understand that this application is intended to include various reasonable changes, improvements, and modifications to the embodiments. These changes, improvements, and modifications are intended to be proposed by this application, and are within the spirit and scope of the exemplary embodiments of this application.

In addition, certain terms in this application have been used to describe embodiments of this application. For example, "one embodiment", "an embodiment" and/or "some embodiments" mean that a particular feature, structure or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. Therefore, it can be emphasized and understood that two or more references to "an embodiment" or "one embodiment" or "alternative embodiment" in various parts of this specification do not necessarily all refer to the same embodiment. In addition, specific features, structures, or characteristics may be appropriately combined in one or more embodiments of the present application.

It should be understood that, in the foregoing description of the embodiments of the present application, to help understand one feature, for the purpose of simplifying the present application, the present application sometimes combines various features in a single embodiment, drawings, or description thereof. Or, this application is to disperse various features in multiple embodiments of the present invention. However, this does not mean that the combination of these features is necessary, and it is entirely possible for those skilled in the art to extract some of the features as a separate embodiment when reading this application. In other words, the embodiments in this application can also be understood as the integration of multiple secondary embodiments. It is also true that the content of each secondary embodiment is less than all the features of a single foregoing disclosed embodiment.

In some embodiments, a number expressing the quantity or nature used to describe and claim certain embodiments of the present application should be understood as modified in some cases by the terms "about", "approximately", or "substantially." For example, unless stated otherwise, "about", "approximately", or "substantially" may represent a ±20% change in the value it describes. Therefore, in some embodiments, the numerical parameters listed in the written description and the appended claims are approximate values, which may vary depending on the desired properties sought by the particular embodiment. In some embodiments, the numerical parameter should be interpreted according to the number of significant digits reported and by applying ordinary rounding techniques. Although some embodiments that illustrate the present application list a wide range of numerical ranges and parameters are approximate values, specific examples list the most accurate numerical values possible.

Each patent, patent application, patent application publication, and other materials cited herein, such as articles, books, specifications, publications, documents, articles, etc., may be incorporated herein by reference. All content used for all purposes, except for the history of any prosecution documents related to it, may be inconsistent or conflict with any of this document, or any same prosecution document that may have a restrictive effect on the broadest scope of the claims history. Associated with this document now or in the future. For example, if there is any inconsistency or conflict between the descriptions, definitions, and/or use of terms associated with any contained material in relation to this document, use this document The terminology shall prevail.

Finally, it should be understood that the embodiments of the application disclosed herein are illustrative of the principles of the embodiments of the application. Other modified embodiments are also within the scope of this application. Therefore, the embodiments disclosed in this application are only examples and are not limiting. Those skilled in the art may adopt alternative configurations according to the embodiments in the present application to implement the invention in the present application. Therefore, the embodiments of the present application are not limited to which embodiments are precisely described in the application.

Claims

A method for controlling a self-driving vehicle is characterized by including:

Acquiring real-time driving data of the self-driving vehicle through the vehicle-mounted automatic driving system of the self-driving vehicle;

Based on the real-time driving data, the vehicle-mounted automatic driving system generates a first decision;

Sending the real-time driving data to the remote data processing system by the vehicle-mounted automatic driving system;

Receiving a second decision from the remote data processing system by the vehicle-mounted automatic driving system, where the second decision is generated by the remote data processing system based on the real-time driving data;

Checking and comparing the second decision with the first decision through the automatic driving system;

According to the result of the verification calculation, the vehicle-mounted automatic driving system issues a decision instruction to the automatic driving vehicle.
The method of claim 1, wherein the first decision is obtained by the vehicle-mounted automatic driving system using the real-time driving data through a first decision model.
The method of claim 1, wherein the second decision is obtained by the remote data processing system through the second decision model using the real-time driving data.
The method of claim 1, wherein the remote data processing system is a cloud server, and the communication means is 5G communication.
The method according to claim 1, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is less than a preset threshold;

The instruction is issued according to the first decision or the second decision or the third decision obtained based on the first decision and the second decision.
The method according to claim 1, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is greater than a preset threshold,

The control module drives the autonomous vehicle to stop immediately or drive away from the driving environment as soon as possible, and enter the safe environment to stop.
The method according to claim 1, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is greater than a preset threshold,

Obtain the first decision and the second decision again.
The method according to claim 7, wherein the issuing of a decision instruction for the autonomous vehicle by the vehicle-mounted automatic driving system according to the result of the verification calculation includes:

The difference between the first decision and the second decision is still greater than a preset threshold,

The control module drives the autonomous vehicle to stop immediately or drive away from the driving environment as soon as possible, and enter the safe environment to stop.
The method of claim 1, wherein the vehicle-mounted automatic driving system receives a perception result from the remote data processing system.
An automatic driving system is characterized by comprising:

A memory, the memory includes at least one set of instructions that are constructed to complete a driving strategy for an autonomous vehicle;

The processor reads the at least one set of instructions of the memory in a working state, and according to the at least one set of instructions:

Acquiring real-time driving data of the self-driving vehicle;

Generating first decision information based on the real-time driving data;

Send the real-time driving data to a remote data processing system;

Receiving a second decision from the remote data processing system, the second decision being generated by the remote data processing system based on the real-time driving data;

Checking and comparing the second decision and the first decision, and according to the result of the checking and comparison, issuing a decision instruction to the autonomous vehicle.
The automatic driving system according to claim 10, wherein the first decision is obtained by the vehicle-mounted automatic driving system using the real-time driving data through a first decision model.
The automatic driving system according to claim 10, wherein the second decision is obtained by the remote data processing system through the second decision model using the real-time driving data.
The automatic driving system according to claim 10, wherein the remote data processing system is a cloud server, and the communication means is 5G communication.
The automatic driving system according to claim 10, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is less than a preset threshold;

The instruction is issued according to the first decision or the second decision or the third decision obtained based on the first decision and the second decision.
The automatic driving system according to claim 10, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is greater than a preset threshold,

The control module drives the autonomous vehicle to stop immediately or drive away from the driving environment as soon as possible, and enter the safe environment to stop.
The automatic driving system according to claim 10, wherein, according to the result of the verification calculation, the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle includes:

The difference between the first decision and the second decision is greater than a preset threshold,

Obtain the first decision and the second decision again.
The automatic driving system according to claim 16, wherein the decision-making instruction issued by the vehicle-mounted automatic driving system to the automatic driving vehicle according to the result of the verification calculation includes:

The difference between the first decision and the second decision is still greater than a preset threshold,

The control module drives the autonomous vehicle to stop immediately or drive away from the driving environment as soon as possible, and enter the safe environment to stop.
The automatic driving system according to claim 10, wherein the vehicle-mounted automatic driving system receives a perception result from the remote data processing system.
An automatic driving vehicle, characterized in that the automatic driving vehicle is configured with the automatic driving system according to claims 9-16.