CN112249035B - Automatic driving method, device and equipment based on general data flow architecture - Google Patents
Automatic driving method, device and equipment based on general data flow architecture Download PDFInfo
- Publication number
- CN112249035B CN112249035B CN202011489832.6A CN202011489832A CN112249035B CN 112249035 B CN112249035 B CN 112249035B CN 202011489832 A CN202011489832 A CN 202011489832A CN 112249035 B CN112249035 B CN 112249035B
- Authority
- CN
- China
- Prior art keywords
- target function
- instruction
- target
- information
- data flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0002—Automatic control, details of type of controller or control system architecture
- B60W2050/0004—In digital systems, e.g. discrete-time systems involving sampling
- B60W2050/0005—Processor details or data handling, e.g. memory registers or chip architecture
Abstract
The embodiment of the invention provides an automatic driving method, device and equipment based on a general data flow architecture. The automatic driving method based on the universal data flow architecture comprises at least one pluggable application function algorithm component, and comprises the following steps: automatically arranging and combining to determine a target function instruction according to different driving scenes, or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component; responding to the target function instruction, and acquiring target function information corresponding to the target function instruction; and executing automatic driving operation corresponding to the target function information according to the target function information. According to the embodiment of the invention, software and hardware decoupling, and arrangement and combination of functions and algorithms can be realized, so that the flexibility of the system is improved.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to an automatic driving method and device based on a general data stream architecture, electronic equipment and a computer storage medium.
Background
The vehicle-mounted intelligent computing basic platform comprises an automatic driving operation system and heterogeneous distributed hardware, and is a key basic platform with mass production L3+ (compatible with L2) automatic driving and intelligent networking functions.
The automatic driving operation system is composed of system software and functional software, is uniformly adapted to various heterogeneous distributed hardware, and provides a software platform for third party/Original Equipment Manufacturers (OEMs) to establish upper-layer application, demonstration and volume production algorithms as required.
However, the existing vehicle automatic driving function development adopts a vertical closed industrial chain, and a total integration Tier1 supplier (a primary supplier) provides a scheme integrating hardware, software, sensor type selection and the like for OEMs, so that software and hardware are bound and decoupling is lacked, and further, the system is lacked in flexibility, long in development period, large in functional module reusability and repeatability and difficult to transplant, and development cost and market response time are increased.
Disclosure of Invention
The embodiment of the invention provides an automatic driving method, an automatic driving device, electronic equipment and a computer storage medium based on a universal data stream architecture, which can realize the decoupling of software and hardware, the arrangement and combination of functions and algorithms and further improve the flexibility of a system.
In a first aspect, an embodiment of the present invention provides an automatic driving method based on a generic data flow architecture, where the generic data flow architecture includes at least one pluggable application function algorithm component, and the method includes: automatically arranging and combining to determine a target function instruction according to different driving scenes, or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component; responding to the target function instruction, and acquiring target function information corresponding to the target function instruction; and executing automatic driving operation corresponding to the target function information according to the target function information.
Optionally, the generic data stream architecture further includes a stream data processing engine, which, in response to the target function instruction, acquires target function information corresponding to the target function instruction, including: and responding to the target function instruction, and acquiring target function information corresponding to the target function instruction by utilizing the streaming data processing engine.
Optionally, when the target function instruction is a perception environment information instruction, in response to the target function instruction, acquiring, by using the streaming data processing engine, target function information corresponding to the target function instruction, where the acquiring includes: responding to the perception environment information instruction, and acquiring environment information corresponding to the perception environment information instruction by utilizing a streaming data processing engine; the environment information includes at least one of road condition information and weather information.
Optionally, according to the target function information, performing an automatic driving operation corresponding to the target function information, including: and executing automatic driving operation corresponding to the environment information according to the environment information.
Optionally, according to the environment information, performing an automatic driving operation corresponding to the environment information, including: determining a planning track according to the environment information; based on the planned trajectory, an autonomous driving maneuver is performed.
Optionally, when the target function instruction is a vehicle platform information obtaining instruction, in response to the target function instruction, obtaining target function information corresponding to the target function instruction by using the streaming data processing engine, where the obtaining includes: and responding to the vehicle platform information acquisition instruction, and acquiring vehicle platform information corresponding to the vehicle platform information acquisition instruction by using the streaming data processing engine.
Optionally, the general data stream architecture further includes a functional application interface layer, and before automatically arranging and combining to determine the target function instruction according to different driving scenes or receiving the target function instruction input by the user, the method further includes: determining a target application function algorithm component corresponding to each driving scene according to different driving scenes; and accessing the target application function algorithm component by using the function application interface layer.
In a second aspect, an embodiment of the present invention provides an automatic driving device based on a generic data flow architecture, where the generic data flow architecture includes at least one pluggable application function algorithm component, and the device includes: the receiving module is used for automatically arranging and combining to determine a target function instruction according to different driving scenes or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component; the acquisition module is used for responding to the target function instruction and acquiring target function information corresponding to the target function instruction; and the execution module is used for executing the automatic driving operation corresponding to the target function information according to the target function information.
Optionally, the general data stream architecture further includes a stream data processing engine, and the obtaining module includes: and the acquisition unit is used for responding to the target function instruction and acquiring target function information corresponding to the target function instruction by using the streaming data processing engine.
Optionally, when the target function instruction is a perception environment information instruction, the obtaining unit includes: the first acquisition subunit is used for responding to the perception environment information instruction and acquiring environment information corresponding to the perception environment information instruction by utilizing the streaming data processing engine; the environment information includes at least one of road condition information and weather information.
Optionally, the execution module includes: and the execution unit is used for executing the automatic driving operation corresponding to the environment information according to the environment information.
Optionally, the execution unit includes: determining a sub-unit group, which is used for determining a planning track according to the environment information; and the execution subunit group is used for executing automatic driving operation based on the planned track.
Optionally, when the target function instruction is a vehicle platform information obtaining instruction, the obtaining unit includes: and the second acquisition subunit group is used for responding to the vehicle platform information acquisition instruction and acquiring the vehicle platform information corresponding to the vehicle platform information acquisition instruction by using the streaming data processing engine.
Optionally, the generic data stream architecture further includes a functional application interface layer, and the apparatus further includes: the determining module is used for determining a target application function algorithm component corresponding to each driving scene according to different driving scenes; and the access module is used for accessing the target application function algorithm component by utilizing the function application interface layer.
In a third aspect, an embodiment of the present invention provides an electronic device, where the device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the generic dataflow architecture based autopilot method of the first aspect or any of the alternative implementations of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer storage medium, where computer program instructions are stored on the computer storage medium, and when the computer program instructions are executed by a processor, the method for automatic driving based on a universal data stream architecture in the first aspect or any optional implementation manner of the first aspect is implemented.
The automatic driving method, the automatic driving device, the electronic equipment and the computer storage medium based on the universal data stream architecture can realize software and hardware decoupling, and further improve the flexibility of the system. The automatic driving method based on the universal data flow architecture comprises the steps that the universal data flow architecture comprises at least one pluggable application function algorithm component, after a target function instruction is determined according to automatic arrangement and combination of different driving scenes or the target function instruction input by a user is received, the target function instruction is related to the target application function algorithm component in the at least one pluggable application function algorithm component, so that target function information corresponding to the target function instruction can be obtained in response to the target function instruction, and then automatic driving operation corresponding to the target function information is executed according to the target function information. Therefore, as the universal data flow architecture comprises at least one pluggable application function algorithm component, software and hardware decoupling, and arrangement and combination of functions and algorithms can be realized, and the flexibility of the system is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of an automatic driving method based on a general dataflow architecture according to an embodiment of the present invention.
Fig. 2 is a schematic flow chart of an automatic driving operation system according to an embodiment of the present invention.
Fig. 3 is a schematic structural diagram of an automatic driving device based on a general dataflow architecture according to an embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Features and exemplary embodiments of various aspects of the present invention will be described in detail below, and in order to make objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not to be construed as limiting the invention. It will be apparent to one skilled in the art that the present invention may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the present invention by illustrating examples of the present invention.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
As can be seen from the background art, the existing automatic driving function development of vehicles adopts a vertical closed industrial chain, and an integrated Tier1 supplier (primary supplier) provides hardware, software, sensor type selection and other integrated schemes for OEMs, so that the software and hardware are bundled and are not decoupled, further the system is lack of flexibility, the development period is long, the reusability and repeatability of functional modules are high, and the transplantation is difficult, thereby increasing the development cost and the market response time.
In order to solve the problems in the prior art, embodiments of the present invention provide an automatic driving method and apparatus based on a universal data stream architecture, an electronic device, and a computer storage medium. First, an automatic driving method based on a general dataflow architecture according to an embodiment of the present invention will be described below.
Fig. 1 is a flow chart illustrating an automatic driving method based on a generic data flow architecture according to an embodiment of the present invention, wherein the generic data flow architecture includes at least one pluggable application function algorithm component. As shown in fig. 1, the automatic driving method based on the general dataflow architecture may include the following steps: s101, automatically arranging and combining according to different driving scenes to determine a target function instruction, or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component.
In one embodiment, the generic data stream architecture further comprises a functional application interface layer, and before the target functional instruction is determined according to different driving scene automatic arrangement combinations or the target functional instruction input by the user is received, the method further comprises: determining a target application function algorithm component corresponding to each driving scene according to different driving scenes; and accessing the target application function algorithm component by using the function application interface layer.
And S102, responding to the target function instruction, and acquiring target function information corresponding to the target function instruction.
In one embodiment, the generic data stream architecture further comprises a streaming data processing engine, responsive to the target function instruction, obtaining target function information corresponding to the target function instruction, including: and responding to the target function instruction, and acquiring target function information corresponding to the target function instruction by utilizing the streaming data processing engine.
In one embodiment, when the target function instruction is a context-aware information instruction, obtaining, with the streaming data processing engine, target function information corresponding to the target function instruction in response to the target function instruction includes: responding to the perception environment information instruction, and acquiring environment information corresponding to the perception environment information instruction by utilizing a streaming data processing engine; the environment information includes at least one of road condition information and weather information.
In one embodiment, when the target function instruction is a vehicle platform information acquisition instruction, acquiring target function information corresponding to the target function instruction by using the streaming data processing engine in response to the target function instruction, including: and responding to the vehicle platform information acquisition instruction, and acquiring vehicle platform information corresponding to the vehicle platform information acquisition instruction by using the streaming data processing engine.
And S103, executing automatic driving operation corresponding to the target function information according to the target function information.
In one embodiment, according to the target function information, performing an automatic driving operation corresponding to the target function information includes: and executing automatic driving operation corresponding to the environment information according to the environment information.
In one embodiment, according to the environment information, performing an automatic driving operation corresponding to the environment information includes: determining a planning track according to the environment information; based on the planned trajectory, an autonomous driving maneuver is performed.
The automatic driving method based on the universal data flow architecture comprises the steps that the universal data flow architecture comprises at least one pluggable application function algorithm component, after a target function instruction is determined according to automatic arrangement and combination of different driving scenes or the target function instruction input by a user is received, the target function instruction is related to the target application function algorithm component in the at least one pluggable application function algorithm component, so that target function information corresponding to the target function instruction can be obtained in response to the target function instruction, and then automatic driving operation corresponding to the target function information is executed according to the target function information. Therefore, as the universal data stream architecture comprises at least one pluggable application function algorithm component, software and hardware decoupling can be realized, and the flexibility of the system is improved.
The above generic data flow architecture is described below in one embodiment.
The general dataflow architecture in an autopilot operating system includes three major subsystems: the system comprises a streaming data processing engine, a pluggable application function algorithm component, a controller of the pluggable application function algorithm component and a functional application development interface. The basic functions of the three major subsystems are explained below.
1. A streaming data processing engine: the streaming data processing engine comprises a pipeline stage (pipeline stage) for sensing, fusing, planning, controlling and the like, and performs full-stack type calculation processing on different driving scene (ODD) definition function sets based on a rule and Artificial Intelligence (AI) model.
The stream data processing engine ensures high-performance real-time data processing, ensures the reliability of the whole data plane through various redundancy and function safety mechanisms, and ensures the system information and data safety through an information safety mechanism.
The streaming data processing engine decouples the underlying heterogeneous computing platform through the distributed system software layer. It provides a unified environment model and data/control/management plane interface to the application function development and algorithm function component controller through the integrated vehicle platform.
The streaming data processing engine is a backbone and core framework, and is connected with submodules of functions and algorithms in series, the functions of the streaming data processing engine also comprise functions of expanding and supporting more software-defined vehicles, and the functions from L1+ to L4 of self-driving can be understood as sensing, fusion, planning, control and the like. The universal data stream is a plurality of basic function data streams covering the self-driving function, and the application development of the self-driving function can arrange, combine, configure, insert and expand the basic function data streams. For example, the data flow comprises four basic function data flows of D (driving in lane), C (changing lane), E (emergency stop) and P (parking), which and atoms form basic units of application development, and the application development can configure, add and use the units to flexibly realize more complex applications.
The streaming data processing engine is a basic function framework, bears pluggable function algorithm components and provides a function application development interface for an application layer.
1.1, general data stream data plane: the generic data flow data plane essentially includes various engine service models that are instructed by control protocols and various algorithms and function controllers through the management plane. The data types of the streaming data processing engine include: (1) the data flow engine outputs information: sensed/fused environmental information such as lane lines, target objects, traffic signs, roads, etc.; vehicle platform information such as throttle, brake, door, handbrake, etc. (2) Management plane commands and monitoring statistics such as speed settings, function activation, etc. (3) The data flow engine inputs commands and information: algorithm plug-in (plug) outputs, such as Convolutional Neural Network Artificial Intelligence (CNNAI) target identification, and the like; and outputting functional components, such as planning tracks, functional states and the like.
1.2 streaming data engine control plane protocol: protocol path establishment, capability discovery and negotiation, configuration settings, component set (Profile) loading, and component loading.
2. Pluggable application function algorithm components and their controllers: it includes two aspects: basic functional and algorithmic components that support autopilot applications, component controllers as general data streams.
2.1, basic application function algorithm component framework: under this plug-in framework, the base application consists of basic atomic algorithm functional units: basic application framework set = { application atomic function algorithm, application atomic function algorithm group basic application } + { application rule, state machine/behavior tree/expert system/AI deep learning }.
The basic application definition can be based on the multi-level cooperation model of the existing application unit, and new functional application can be quickly and flexibly constructed and verified through various rules and constraint mechanisms.
2.1.1, atomic function algorithm unit: the unit is the basis of application definition, and defines basic function algorithm units of application functions, such as basic function units of collision detection, front-mounted vehicle detection and the like, based on a service model and a calling interface provided by a general data flow basic framework. The purpose of these base units is to serve as the fundamental component of the application function development references.
2.1.2, functional algorithm unit group: the functional algorithm units form a new complex function group unit through different rules and constraint conditions.
2.1.3, basic application: based on the functional units, the application is developed for the automatic driving service function, so that the OEM/Tier1 can be quickly adapted and developed to the self-driving service application.
2.2, algorithm component framework: the self-driving protocol stack comprises a plurality of algorithm units and different data stream processing units operating in the protocol stack, such as perception, fusion, positioning, planning and the like.
2.2.1, algorithm function library: the algorithm software for different streaming data plane functions implements the package.
2.2.2, algorithm component plugin interface: the method comprises the steps of defining a calling interface of an algorithm component aiming at the computing environment of a stream data algorithm processing unit, covering various algorithm scheduling modes such as simple function calling and complex chain processing modes including model preprocessing, model processing and model postprocessing.
2.3, general data flow control: the controller establishes a control path with the data engine by using a general data stream control protocol, and manages and sets data stream.
3. Functional application interface layer (AAL): the functional layer encapsulates a data stream engine, an algorithm and a basic functional component to form a uniform Application function development and operation Interface, which comprises an algorithm Application Programming Interface (API), a data Interface, system/function safety, a communication channel protocol, a data format standard and the like.
It provides Software Development Kit (SDK), tool chain and various functional algorithm Software packages required for self-driving application Development. The whole car factory can rapidly deduce a new advanced self-driving function or other series of functions surrounding self-driving for different car models and different driving scenes (ODD) based on the function service and toolkits of the AAL. For example, the system can be applied to self-driving of L2/3 such as ACC, TJC, AVP, HWC and the like, and can provide various applications such as internet connection, cloud control, high-precision maps and the like.
Fig. 2 is a schematic flow chart of an automatic driving operation system according to an embodiment of the present invention, where 203 in fig. 2 represents an operation domain, which is also called a real time domain, and is a processing pipeline stage of a general self-driving data stream processing engine, that is, an operation carrier and an environment for sensing, fusing, planning, and controlling. The elements that operate above include basic functional and algorithmic components that support the autopilot application. Development domain, 201 in fig. 2, is an environment that provides a car factory or other third party developer to develop advanced more complex self-driving applications. The two are called, used, arranged, modified and combined by the management plane and the interfaces of the SDK and the API to realize the development purpose of the basic function and algorithm components in the operation domain flexibly, quickly and conveniently. Fig. 2 at 202 includes a management protocol stack, a controller, and a management plane model and interface, which are described in detail below.
Managing a protocol stack: (1) the component controller negotiates and verifies with the generic data engine: the controller initiates negotiation, data flow response, dual-transmission interactive capability set, and the like.
(2) And (3) verifying and running an algorithm unit: the controller sends the algorithm component to the data flow engine via the capability set definition. And (4) verifying and loading the engine.
(3) Function (profile) verification load: the controller sends the functional application and the basic components to the data flow engine through the definition of the capability set. And (4) verifying and loading the engine.
(4) And (3) verifying and loading by the management plane: the controller sends management plane commands and parameters to the data flow engine through the definition of the capability set. And (4) verifying and loading the engine.
(5) Safe operation and upgrade of a streaming data system: the controller sends the operation related command to the data flow engine through the definition of the capability set. And (4) verifying the engine and loading and executing.
Managing the plane model and interfaces: (1) algorithm interface: perception: lane line identification, static/dynamic object identification, etc. Fusing: various fusion-related algorithms.
(2) Function interface: l2/3, etc.
(3) A security policy interface: function/information security, system redundancy, etc.
(4) And (4) other interfaces: vehicle to evolution (V2 x) maps, system/function parameters, and the like.
As shown in fig. 3, an embodiment of the present application further provides an automatic driving apparatus based on a generic data flow architecture, where the generic data flow architecture includes at least one pluggable application function algorithm component, and the apparatus includes: the receiving module 301 is configured to automatically arrange and combine to determine a target function instruction according to different driving scenes, or receive a target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component; an obtaining module 302, configured to, in response to a target function instruction, obtain target function information corresponding to the target function instruction; and the executing module 303 is configured to execute an automatic driving operation corresponding to the target function information according to the target function information.
Optionally, the general data stream architecture further includes a stream data processing engine, and the obtaining module 302 includes: and the acquisition unit is used for responding to the target function instruction and acquiring target function information corresponding to the target function instruction by using the streaming data processing engine.
Optionally, when the target function instruction is a perception environment information instruction, the obtaining unit includes: the first acquisition subunit is used for responding to the perception environment information instruction and acquiring environment information corresponding to the perception environment information instruction by utilizing the streaming data processing engine; the environment information includes at least one of road condition information and weather information.
Optionally, the executing module 303 includes: and the execution unit is used for executing the automatic driving operation corresponding to the environment information according to the environment information.
Optionally, the execution unit includes: determining a sub-unit group, which is used for determining a planning track according to the environment information; and the execution subunit group is used for executing automatic driving operation based on the planned track.
Optionally, when the target function instruction is a vehicle platform information obtaining instruction, the obtaining unit includes: and the second acquisition subunit group is used for responding to the vehicle platform information acquisition instruction and acquiring the vehicle platform information corresponding to the vehicle platform information acquisition instruction by using the streaming data processing engine.
Optionally, the generic data stream architecture further includes a functional application interface layer, and the apparatus further includes: the determining module is used for determining a target application function algorithm component corresponding to each driving scene according to different driving scenes; and the access module is used for accessing the target application function algorithm component by utilizing the function application interface layer.
Each module/unit in the apparatus shown in fig. 3 has a function of implementing each step in fig. 1, and can achieve the corresponding technical effect, and for brevity, the description is not repeated here.
Fig. 4 shows a schematic structural diagram of an electronic device according to an embodiment of the present invention.
The electronic device may include a processor 401 and a memory 402 storing computer program instructions.
Specifically, the processor 401 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement the embodiments of the present invention.
In one example, the Memory 402 may be a Read Only Memory (ROM). In one example, the ROM may be mask programmed ROM, programmable ROM (prom), erasable prom (eprom), electrically erasable prom (eeprom), electrically rewritable ROM (earom), or flash memory, or a combination of two or more of these.
The processor 401 reads and executes the computer program instructions stored in the memory 402 to implement the method in the embodiment shown in fig. 1, and achieve the corresponding technical effect achieved by the embodiment shown in fig. 1 executing the method/step thereof, which is not described herein again for brevity.
In one example, the electronic device may also include a communication interface 403 and a bus 410. As shown in fig. 4, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 410 to complete communication therebetween.
The communication interface 403 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present invention.
In addition, embodiments of the present invention may be implemented by providing a computer storage medium. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the above-described embodiments of a universal dataflow architecture-based autopilot method.
It is to be understood that the invention is not limited to the specific arrangements and instrumentality described above and shown in the drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present invention are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions or change the order between the steps after comprehending the spirit of the present invention.
The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic Circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the invention are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, Erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, Radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.
It should also be noted that the exemplary embodiments mentioned in this patent describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed simultaneously.
As described above, only the specific embodiments of the present invention are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present invention, and these modifications or substitutions should be covered within the scope of the present invention.
Claims (9)
1. An autopilot method based on a generic data flow architecture, wherein the generic data flow architecture includes at least one pluggable application function algorithm component, the method comprising:
automatically arranging and combining to determine a target function instruction according to different driving scenes, or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component;
responding to the target function instruction, and acquiring target function information corresponding to the target function instruction;
executing automatic driving operation corresponding to the target function information according to the target function information;
the general data flow architecture further comprises a functional application interface layer, and before the target function instruction is determined according to automatic arrangement and combination of different driving scenes or the target function instruction input by a user is received, the method further comprises the following steps:
determining a target application function algorithm component corresponding to each driving scene according to different driving scenes;
and accessing the target application function algorithm component by utilizing the function application interface layer.
2. The generic data flow architecture based autopilot method of claim 1 wherein the generic data flow architecture further comprises a streaming data processing engine, said retrieving target function information corresponding to the target function instruction in response to the target function instruction comprising:
and responding to the target function instruction, and acquiring target function information corresponding to the target function instruction by utilizing the streaming data processing engine.
3. The generic data flow architecture based autopilot method of claim 2 wherein said obtaining target function information corresponding to the target function instruction with the streaming data processing engine in response to the target function instruction when the target function instruction is a context-aware instruction comprises:
responding to the perception environment information instruction, and acquiring environment information corresponding to the perception environment information instruction by utilizing the streaming data processing engine; the environment information includes at least one of road condition information and weather information.
4. The automatic driving method based on the universal data flow architecture as claimed in claim 3, wherein the performing of the automatic driving operation corresponding to the target function information according to the target function information comprises:
and executing automatic driving operation corresponding to the environment information according to the environment information.
5. The automatic driving method based on the universal data flow architecture as claimed in claim 4, wherein the performing of the automatic driving operation corresponding to the environment information according to the environment information comprises:
determining a planning track according to the environment information;
and executing the automatic driving operation based on the planned track.
6. The generic data flow architecture based autopilot method of claim 2 wherein when the target function command is a vehicle platform information acquisition command, said acquiring target function information corresponding to the target function command with the streaming data processing engine in response to the target function command comprises:
and responding to the vehicle platform information acquisition instruction, and acquiring vehicle platform information corresponding to the vehicle platform information acquisition instruction by using the streaming data processing engine.
7. An autopilot device based on a generic data flow architecture, wherein the generic data flow architecture includes at least one pluggable application function algorithm component, the device comprising:
the receiving module is used for automatically arranging and combining to determine a target function instruction according to different driving scenes or receiving the target function instruction input by a user; wherein the target function instruction is associated with a target application function algorithm component of the at least one pluggable application function algorithm component;
the acquisition module is used for responding to the target function instruction and acquiring target function information corresponding to the target function instruction;
the execution module is used for executing automatic driving operation corresponding to the target function information according to the target function information;
the generic data flow architecture further comprises a functional application interface layer, the apparatus further comprising: the determining module is used for determining a target application function algorithm component corresponding to each driving scene according to different driving scenes; and the access module is used for accessing the target application function algorithm component by utilizing the function application interface layer.
8. An electronic device, characterized in that the electronic device comprises: a processor, and a memory storing computer program instructions;
the processor reads and executes the computer program instructions to implement the generic dataflow architecture based autopilot method according to any one of claims 1-6.
9. A computer storage medium having computer program instructions stored thereon that, when executed by a processor, implement the universal data stream architecture based autopilot method of any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011489832.6A CN112249035B (en) | 2020-12-16 | 2020-12-16 | Automatic driving method, device and equipment based on general data flow architecture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011489832.6A CN112249035B (en) | 2020-12-16 | 2020-12-16 | Automatic driving method, device and equipment based on general data flow architecture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112249035A CN112249035A (en) | 2021-01-22 |
| CN112249035B true CN112249035B (en) | 2021-03-16 |
Family
ID=74225813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011489832.6A Active CN112249035B (en) | 2020-12-16 | 2020-12-16 | Automatic driving method, device and equipment based on general data flow architecture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112249035B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115220787A (en) * | 2021-04-17 | 2022-10-21 | 华为技术有限公司 | Driving control instruction generation method, heterogeneous calculation method, related device and system |
| CN113237483B (en) * | 2021-07-08 | 2021-11-16 | 国汽智控(北京)科技有限公司 | Vehicle navigation method, device, electronic equipment and storage medium |
| CN115640059B (en) * | 2022-12-14 | 2023-05-30 | 清华大学 | Autopilot operating system, electronic device, and storage medium |
| CN116985830A (en) * | 2023-07-26 | 2023-11-03 | 小米汽车科技有限公司 | Vehicle mode operation method and device, vehicle and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809068A (en) * | 2014-12-31 | 2016-07-27 | 北京华虹集成电路设计有限责任公司 | High-speed storage control SOC chip supporting adoption of hardware encryption algorithm |
| CN108733049A (en) * | 2017-04-20 | 2018-11-02 | 通用汽车环球科技运作有限责任公司 | Adaptive self vehicle drive mode |
| CN108898536A (en) * | 2018-08-27 | 2018-11-27 | 深圳壹智云科技有限公司 | A kind of intelligent driving transportation system |
| CN109835278A (en) * | 2019-02-25 | 2019-06-04 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of vehicle computing platform |
| CN110091875A (en) * | 2019-05-14 | 2019-08-06 | 长沙理工大学 | Deep learning type intelligent driving context aware systems based on Internet of Things |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10671070B2 (en) * | 2018-05-23 | 2020-06-02 | Baidu Usa Llc | PID embedded LQR for autonomous driving vehicles (ADVS) |
-
2020
- 2020-12-16 CN CN202011489832.6A patent/CN112249035B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809068A (en) * | 2014-12-31 | 2016-07-27 | 北京华虹集成电路设计有限责任公司 | High-speed storage control SOC chip supporting adoption of hardware encryption algorithm |
| CN108733049A (en) * | 2017-04-20 | 2018-11-02 | 通用汽车环球科技运作有限责任公司 | Adaptive self vehicle drive mode |
| CN108898536A (en) * | 2018-08-27 | 2018-11-27 | 深圳壹智云科技有限公司 | A kind of intelligent driving transportation system |
| CN109835278A (en) * | 2019-02-25 | 2019-06-04 | 东软睿驰汽车技术（沈阳）有限公司 | A kind of vehicle computing platform |
| CN110091875A (en) * | 2019-05-14 | 2019-08-06 | 长沙理工大学 | Deep learning type intelligent driving context aware systems based on Internet of Things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112249035A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112249035B (en) | Automatic driving method, device and equipment based on general data flow architecture | |
| JP7050736B2 (en) | Methods, devices, equipment and media to control the autonomous driving of vehicles | |
| CN107571864B (en) | The collecting method and device of automatic driving vehicle | |
| CN110793784B (en) | Test method and device for automatic driving vehicle, storage medium and electronic device | |
| US11962664B1 (en) | Context-based data valuation and transmission | |
| CN109756548B (en) | Data processing method, system and device for intelligent networked automobile cloud control basic platform | |
| CN113848855B (en) | Vehicle control system test method, device, equipment, medium and program product | |
| JP6839846B2 (en) | Information processing equipment, information processing methods and programs | |
| US11628861B2 (en) | Method and apparatus for controlling vehicle, device and storage medium | |
| JP2024513679A (en) | Method and related device for retrieving files based on wireless OTA technology | |
| Vermesan et al. | Automotive intelligence embedded in electric connected autonomous and shared vehicles technology for sustainable green mobility | |
| CN113938528B (en) | Vehicle-enterprise custom data communication method and system between vehicle end and cloud end | |
| CN114684185A (en) | Vehicle safety response control hierarchy for automated vehicle safety control and corresponding method | |
| WO2022245916A1 (en) | Device health code broadcasting on mixed vehicle communication networks | |
| CN113377658B (en) | Vehicle controller debugging method and device | |
| EP3800518A1 (en) | System, device and method for testing autonomous vehicles | |
| Shi et al. | Computing Systems for Autonomous Driving | |
| CN112671487A (en) | Vehicle testing method, server and testing vehicle | |
| CN110823253A (en) | Data processing method, device and equipment based on unmanned vehicle technology and storage medium | |
| US20220371530A1 (en) | Device-level fault detection | |
| JP7465147B2 (en) | Vehicle control device, server, verification system | |
| CN114282380A (en) | Test method and device for automatic driving algorithm, electronic equipment and storage medium | |
| CN112230632A (en) | Method, apparatus, device and storage medium for automatic driving | |
| JP2018170728A (en) | Information processing apparatus, information processing method, and program | |
| CN110362086B (en) | Method and device for controlling an autonomous vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |