CN108594819A - Automatic Pilot vehicle computing resource management system and method - Google Patents
Automatic Pilot vehicle computing resource management system and method Download PDFInfo
- Publication number
- CN108594819A CN108594819A CN201810414692.2A CN201810414692A CN108594819A CN 108594819 A CN108594819 A CN 108594819A CN 201810414692 A CN201810414692 A CN 201810414692A CN 108594819 A CN108594819 A CN 108594819A
- Authority
- CN
- China
- Prior art keywords
- container
- resource
- service
- vehicle
- automatic pilot
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000013480 data collection Methods 0.000 claims abstract description 7
- 238000007726 management method Methods 0.000 claims description 81
- 230000006870 function Effects 0.000 claims description 19
- 230000001939 inductive effect Effects 0.000 claims description 16
- 230000007613 environmental effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000009467 reduction Effects 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 5
- 230000004044 response Effects 0.000 claims description 5
- 230000001133 acceleration Effects 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 238000013468 resource allocation Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 2
- 230000003993 interaction Effects 0.000 claims description 2
- 238000004088 simulation Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 238000002955 isolation Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 8
- 238000011161 development Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
- G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized resources
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
Abstract
Automatic Pilot vehicle computing method for managing resource of the present invention, it is related to automatic Pilot technical field, the hardware resource of vehicle computing unit is managed collectively using container technique, task and automatic Pilot intelligent decision control task are handled according to the real-time data collection of core sensor, dynamically distribute physical hardware resources, mutually isolated multiple containers running environment is generated, respective task is independently executed;According to actual operating state dynamic adjustresources, the intelligent coordinated of each automatic Pilot service application is realized;And a variety of Container Management strategies are grabbed by resource reservation, resource constraint, resource, complete the safety traffic of automatic driving vehicle.The present invention improves the utilization rate of computing resource while ensureing the isolation of calculating task performing environment, effectively reduces hardware energy consumption;Compared to single host mode, the risk that single machine failure is brought is reduced, promotes automatic Pilot overall security.The invention also provides automatic Pilot vehicle computing resource management systems.
Description
Technical field
The present invention relates to edge calculations, automatic Pilot and container technical field, specifically a kind of automatic Pilot is vehicle-mounted
Managing computing resources system and method.
Background technology
With the development of cloud computing, types of applications system turns to high in the clouds gradually, a large amount of object of high in the clouds site polymerization
Manage hardware resource, such as server, network, memory and storage, extracted using virtualization technology, convert after be in uniformly
Reveal and, realize the unified distribution, scheduling and management of heterogeneous network computing resource, construction data center is concentrated to greatly reduce
The cost for calculating and storing.Virtualization technology is as a kind of resource management techniques, effective solution high-performance physical hardware money
Source excess capacity is super to reuse problem with the too low recombination brought of problem and old hardware resource utilization, by bottom hardware physics
Transparent resource, to maximumlly utilize hardware resource.
In recent years, micro services framework comes into vogue, and the virtualization technology headed by heavy hypervisor relatively is very much
Under scene, substituted gradually by container technique.Container technique can build operation system example on demand, and be carried in a manner of process
Application is supplied to use, reduces basic overhead in this way, container technique realizes independence and the isolation of resource, provides
Lightweight, environment consistency running environment, have become a kind of physical hardware resources sharing mode being widely recognized as by everybody,
Great flexibility is provided for application developer and system operation maintenance personnel.
Automatic Pilot is automobile industry and artificial intelligence, vision calculating, Internet of Things, radar, high-precision map, high-performance calculation
Etc. generation information technologies depth integration product, the Main way for being Present Global automobile with the development of traffic trip field,
By vehicle-mounted core calculations unit, under the operation of nobody class active, automatic safe motor vehicles are operated.Compared to
Orthodox car, autonomous driving vehicle increase the core sensors such as high-definition camera, laser radar, high-precision positioner, and
By sensor real-time data collection, coordinate high-precision map, the inductive decision of real-time high-efficiency is carried out using vehicle computing unit, and
It feeds back to vehicle line control system and realizes automatic Pilot.In this course, vehicle-mounted core calculations unit needs to provide a large amount of calculate
Resource, meets the data structured demand of all kinds of sensing equipments, while to complete model reasoning and the control decision of vehicle.With this
Meanwhile being limited to the requirement of the volume and energy consumption of automobile so that vehicle-mounted core calculations unit can not use the solution party at cloud center
Case.In this case, how efficient computing resource effectively is provided for automatic driving vehicle using container technique, according to row
Parking lot scape reasonable distribution resource is realized to calculate and be optimized, and can guarantee the problem of driving safety becomes urgent need to resolve.
Invention content
The present invention is directed to the demand and shortcoming of current technology development, provides a kind of automatic Pilot vehicle computing resource pipe
Manage system and method.
Automatic Pilot vehicle computing resource management system of the present invention solves the technical solution that above-mentioned technical problem uses
It is as follows:Described to be based on automatic Pilot vehicle computing resource management system, system architecture includes core sensor, vehicle computing list
Member and vehicle string holes system;The hardware resource of vehicle computing unit is managed collectively using container technique, is passed according to core
The real-time data collection processing task and automatic Pilot intelligent decision control task of sensor, dynamically distribute physical hardware resources, raw
At mutually isolated multiple containers running environment, respective task is independently executed;It is real according to actual operating state dynamic adjustresources
Now each automatic Pilot service application is intelligent coordinated;And a variety of Container Managements are grabbed by resource reservation, resource constraint, resource
Strategy completes the safety traffic of automatic driving vehicle;Wherein,
The core sensor includes the sensing equipment realized Function for Automatic Pilot and used, and passes through the real-time collecting vehicle of core sensor
Running environment data;
The vehicle computing unit general frame is divided into four layers:Physical computing resources layer, ROS real time operating systems layer, business fortune
Row environmental chamber layer and application layer;Wherein, the physical computing resources layer, including multiple main frames, these hosts are to realize automatically
Drive the central module of function;
The ROS real time operating systems layer, is deployed on physical computing resources layer, for ensureing data acquisition and Decision Control
Real-time;The service operation environmental chamber layer is deployed on ROS real time operating system layers, is run for deployment container
Environment;The application layer, for running container management service and automatic Pilot service application;
The container management service will dynamically distribute and manage resource according to business demand, complete to sense using vehicle computing unit
The acquiring of data, the fusion and collaboration of a variety of sensing equipment data, and according to automatic Pilot Decision Control Model trained in advance
Real-time inductive decision is completed, vehicle line control system is fed back to by CAN bus, completes vehicle control response.
Specifically, the core sensor includes:Multi-path high-definition camera, laser radar, millimetre-wave radar, V2X sensings
Equipment, high-precision positioner;
Each host includes calculating, storage and network physical hardware resource and FPGA or GPU hardware acceleration components.
Specifically, the application layer specifically includes Container Management application, the application of high-precision map, Decision Control, emergency braking
Using the control of, CAN bus, data acquisition applications.
Specifically, the automatic Pilot vehicle computing resource management system carries out automatic Pilot computing resource initialization, it is interior
Appearance includes:
The vehicle computing unit loads preset Container Management configuration information, is based on ROS real time operating systems, completes container tube
The initialization of service is managed, wherein reserved part computing resource is used for emergency braking Mission critical applications;
The vehicle computing unit connects core sensor by container management service, matches confidence according to preset resource allocation
Breath loads application service container mirror image, starts container application service;The core sensor data acquisition applications service operation exists
In container, core sensor is connected, and acquire the environmental data from core sensor, carry out structuring processing;
The vehicle computing unit loads CAN bus vehicle condition data by container management service and acquires service container mirror image,
And start container application service;The CAN bus vehicle condition data acquires service operation in a reservoir, real-time collection vehicle shape
Condition data carry out structuring processing;
The vehicle computing unit loads high-precision map application service container mirror image by container management service, and starts container and answer
With service;The high-precision map application service operation in a reservoir, provides high-precision Map Services, is obtained in conjunction with high accurate positioning device
Surrounding enviroment data and road data;
The vehicle computing unit loads CAN bus vehicle control service container mirror image by container management service, and starts appearance
Device application service;The CAN bus vehicle control service operation in a reservoir, waits for control instruction;
The vehicle computing unit loads automatic Pilot Decision Control service container mirror image by container management service, and starts appearance
Device inductive decision controls application service;Automatic Pilot inductive decision control application service operation in a reservoir, and with it is each
Acquisition applications service interacts, and realizes in data set, and completes decision calculating task according to its automatic Pilot decision model, real
When feed back to the CAN bus vehicle control service;
The vehicle computing unit will load emergency braking service container mirror image by container management service at least two hosts,
And start application service;The emergency braking service operation in a reservoir, and keeps heartbeat with other application service container, in real time
Its resource and operation conditions are monitored, waits for and instructing while listening for port.
Specifically, the automatic Pilot vehicle computing resource management system carries out automatic Pilot managing computing resources, content
Including:
The vehicle computing unit is marked FPGA, GPU by container management service, for deep learning reasoning scene,
It is serviced using given host load vessel;
The vehicle computing unit monitors the container and hardware resource situation of autonomous driving vehicle by container management service;If holding
The allocated computing resource of device has reached critical value, inadequate resource phenomenon occurs, then preferential to be distributed using reserved to crucial calculate
Resource;When container resource utilization reaches saturation situation, if crucial application resource is insufficient, the money of non-key service application is grabbed
Source;If there is non-critical application container operation exception, turn off container Resource recovery, redistributes resource, load vessel mirror image
And start application;If there is crucial application container operation exception, priority scheduling executes emergency brake application service, completes automatic
The safe reduction of speed parking driven redistributes resource, load vessel mirror image simultaneously starts application, opens again after vehicle safety stops
Open Function for Automatic Pilot;
If hardware anomalies occurs in some host, priority scheduling executes emergency brake application service, completes the safety of automatic Pilot
Reduction of speed stops, and after vehicle safety stops, judging remaining available host quantity, is no less than two available hosts if existing, will break
The container mirror image of electric host operation is loaded into other hosts, reopens Function for Automatic Pilot;
The vehicle computing unit by container management service collect different vehicle driving scene computing resource data, and according to
Current driving situation individual scene dynamic optimization adjustresources.
The present invention also proposes automatic Pilot vehicle computing method for managing resource, using container technique by vehicle computing unit
Hardware resource is managed collectively, and task and automatic Pilot intelligent decision control are handled according to the real-time data collection of core sensor
Task processed dynamically distributes physical hardware resources, generates mutually isolated multiple containers running environment, independently execute respective task;
According to actual operating state dynamic adjustresources, the intelligent coordinated of each automatic Pilot service application is realized;And it is pre- by resource
It stays, a variety of Container Management strategies of resource constraint, resource plunder, completes the safety traffic of automatic driving vehicle;
The vehicle computing unit is made of multiple main frames, is the central module for realizing Function for Automatic Pilot, in vehicle computing list
On member, ROS real time operating systems are disposed to ensure the real-time of data acquisition and Decision Control, on ROS operating systems
Deployment container running environment, wherein operation container management service and automatic Pilot service application;The core sensor includes real
The sensing equipment that existing Function for Automatic Pilot is used;
The container management service will dynamically distribute and manage resource according to business demand, complete using the vehicle computing unit
At the acquiring of sensing data, the fusion and collaboration of a variety of sensing equipment data, and according to automatic Pilot decision control trained in advance
Simulation completes real-time inductive decision, feeds back to vehicle line control system by CAN bus, completes vehicle control response.
Specifically, the core sensor includes:Multi-path high-definition camera, laser radar, millimetre-wave radar, V2X sensings
Equipment, high-precision positioner;
Each host includes calculating, storage and network physical hardware resource and FPGA or GPU hardware acceleration components.
Specifically, the application layer specifically includes Container Management application, the application of high-precision map, Decision Control, emergency braking
Using the control of, CAN bus, data acquisition applications.
Automatic Pilot vehicle computing resource management system of the present invention and method, what is had compared with prior art is beneficial
Effect is:The present invention reasonably allocates management of automatic Pilot vehicle computing resource using container technique, and automatic Pilot is calculated root
According to scene, classification, many factors dynamic allocation of resources such as result influence degree are calculated, calculating task respectively in multiple containers
Independent operating, and can realize resource elastic telescopic according to scene changes;
While ensureing the isolation of calculating task performing environment, the utilization rate of computing resource is improved, and effectively reduce
Hardware energy consumption;Compare the mode of single host, and the mode of more host containers reduces the risk that single machine failure is brought, improves
Automatic Pilot overall security;The hypervisor that compares virtualizes mode, and containerization mode will occupy less computing resource,
The operational efficiency of significant increase automatic Pilot application, the container mode of more lightweight meet automatic Pilot ROS real-time operations
The container application of requirement of the system to real-time, micro services reduces failure recovery time, and it is whole to improve automated driving system
The robustness of body;In addition, more copies operation of crucial calculating task and specified, resource reservation, resource constraint, money by resource
A variety of Container Management strategies such as source plunder while efficiently utilizing resource, ensure that the high availability of crucial calculating, maximum journey
The driving safety for having ensured automatic driving vehicle of degree.
Description of the drawings
Illustrate the embodiment of the present invention or technology contents in the prior art in order to clearer, below to the embodiment of the present invention
Or required attached drawing does simple introduction in the prior art.It will be apparent that attached drawing disclosed below is only the one of the present invention
Section Example to those skilled in the art without creative efforts, can also be attached according to these
Figure obtains other attached drawings, but within protection scope of the present invention.
Attached drawing 1 is the schematic diagram of the automatic Pilot vehicle computing unit;
Attached drawing 2 is the flow chart of automatic Pilot computing resource initialization;
Attached drawing 3 is the flow chart of automatic Pilot managing computing resources.
Specific implementation mode
The technical issues of to make technical scheme of the present invention, solving and technique effect are more clearly understood, below in conjunction with tool
Body embodiment is checked technical scheme of the present invention, is completely described, it is clear that described embodiment is only this hair
Bright a part of the embodiment, instead of all the embodiments.Based on the embodiment of the present invention, those skilled in the art are not doing
All embodiments obtained under the premise of going out creative work, all within protection scope of the present invention.
Embodiment
The present embodiment proposes automatic Pilot vehicle computing resource management system, installs and uses in automatic driving vehicle, institute
It is the automobile for having Function for Automatic Pilot to state automatic driving vehicle;The framework packet of the automatic Pilot vehicle computing resource management system
It includes core sensor, vehicle computing unit and vehicle string holes system, core sensor to connect with vehicle computing unit, will collect
Vehicle running environment data transmission to vehicle computing unit, the inductive decision of real-time high-efficiency is carried out using vehicle computing unit,
Vehicle computing unit is connected to vehicle line control system, and obtained inductive decision result is fed back to vehicle line control system, realizes vehicle
Automatic Pilot;Wherein,
Core sensor includes the sensing equipment realized Function for Automatic Pilot and used, and further core sensor may include:It is more
Road high-definition camera, laser radar, millimetre-wave radar, V2X sensing equipments, high-precision positioner;Pass through core sensor reality
When collection vehicle running environment data;
As shown in Fig. 1, vehicle computing unit general frame is divided into four layers:Physical computing resources layer, ROS real time operating systems
Layer, service operation environmental chamber layer and application layer;Wherein, physical computing resources layer, including multiple main frames, these hosts are to realize
The central module of Function for Automatic Pilot;Further, each host includes the physical hardware resources such as calculating, storage and network, in addition,
Each host further includes the hardware-accelerated component such as FPGA or GPU;
ROS real time operating system layers, are deployed on physical computing resources layer, the reality for ensureing data acquisition and Decision Control
Shi Xing;Service operation environmental chamber layer is deployed on ROS real time operating system layers, is used for deployment container running environment;Using
Layer, for running container management service and automatic Pilot service application, further, application layer specifically include Container Management application,
High-precision map, Decision Control application, emergency brake application, CAN bus control, data acquisition applications etc.;
Container management service will dynamically distribute and manage resource according to business demand, and sensing data is completed using vehicle computing unit
Acquire, the fusion and collaboration of a variety of sensing equipment data, and completed according to automatic Pilot Decision Control Model trained in advance
Real-time inductive decision feeds back to vehicle line control system by CAN bus, completes vehicle control response.
The present embodiment proposes automatic Pilot vehicle computing resource management system, using container technique by vehicle computing unit
Hardware resource is managed collectively, and task and automatic Pilot intelligent decision control are handled according to the real-time data collection of core sensor
The tasks such as system dynamically distribute(Calculating, storage, network etc.)Physical hardware resources generate mutually isolated multiple containers operation ring
Border independently executes respective task;According to actual operating state dynamic adjustresources, automatic Pilot vehicle computing unit business is reduced
Interacting for operation, realizes the intelligent coordinated of each automatic Pilot service application.In addition, by resource reservation, resource constraint,
A variety of Container Management strategies such as resource plunder ensure the high availability that core key calculates, complete the safety of automatic driving vehicle
Traveling.
The present embodiment also proposed automatic Pilot vehicle computing method for managing resource, technical solution and above-mentioned automatic Pilot
Vehicle computing resource management system can be referred to mutually, it is necessary first to automatic Pilot computing resource initialization be carried out, such as attached drawing 2
Shown, the main realization process of this operation includes:
Step 1, autonomous driving vehicle start power supply system, power for vehicle computing unit, complete host supplying power and start;
Step 2, vehicle computing unit load ROS real time operating systems;
Step 3, vehicle computing unit load preset Container Management configuration information, are based on ROS real time operating systems, complete container
The initialization of management service, wherein by reserved part computing resource for Mission critical applications such as emergency brakings;
Step 4, vehicle computing unit connect core sensor by container management service, match confidence according to preset resource allocation
Breath loads application service container mirror image, and starts container application service respectively;
Step 5, core sensor data acquisition applications service operation in a reservoir, connect core sensor, and acquire and come from core
The environmental data of heart sensor carries out structuring processing;
Step 6, vehicle computing unit load CAN bus vehicle condition data by container management service and acquire service container mirror
Picture, and start container application service;
In a reservoir, real-time collection vehicle status data is tied for step 7, CAN bus vehicle condition data acquisition service operation
Structureization processing;
Step 8, vehicle computing unit load high-precision map application service container mirror image by container management service, and start container
Application service;
Step 9, high-precision map application service operation in a reservoir, provide high-precision Map Services, are obtained in conjunction with high accurate positioning device
Surrounding enviroment data and road data;
Step 10, vehicle computing unit load CAN bus vehicle control service container mirror image by container management service, and start
Container application service;
Step 11, CAN bus vehicle control service operation in a reservoir, wait for control instruction;
Step 12, vehicle computing unit load automatic Pilot Decision Control service container mirror image by container management service, and open
Visibly moved device inductive decision controls application service;
Step 13, automatic Pilot inductive decision control application service operation in a reservoir, and are serviced with each acquisition applications and are carried out
Interaction is realized in data set, and completes decision calculating task according to its automatic Pilot decision model, and Real-time Feedback is to described
CAN bus vehicle control service;
Step 14, vehicle computing unit will load emergency braking service container mirror by container management service at least two hosts
Picture, and start application service;
Step 15, emergency braking service operation in a reservoir, and keep heartbeat with other application service container, monitor its money in real time
Source and operation conditions are waited for while listening for port and being instructed;
Step 16, autonomous driving vehicle computing unit operating status are normal, and computing resource initialization is completed.
Using the present embodiment automatic Pilot vehicle computing method for managing resource, the initialization of automatic Pilot computing resource is completed
Afterwards, automatic Pilot managing computing resources are carried out, as shown in Fig. 3, this operating process specifically includes:
Step 1, vehicle computing unit are marked the specialized hardwares such as FPGA, GPU by container management service, are related to depth
The scenes such as reasoning are practised, then are serviced using given host load vessel;
Step 2, vehicle computing unit monitor the container and hardware resource situation of autonomous driving vehicle by container management service;
If the allocated computing resource of step 3, container has reached critical value, there is inadequate resource phenomenon, then it is preferential to key
It calculates distribution and uses reserved resource;
Step 4 reaches saturation situation when container resource utilization, if crucial application resource is insufficient, grabs non-key business
The resource of application ensures the operation of Core Feature;
Step 5, if there is non-critical application container operation exception, such as V2X sensing equipment data acquisition applications, some is backward
High-definition camera data acquisition applications etc., then turn off container Resource recovery, redistributes resource, and load vessel mirror image and starting is answered
With;
Step 6 is determined if there is crucial application container operation exception, such as preposition high-definition camera data acquisition service, reasoning
The safe reduction of speed parking of automatic Pilot is completed in plan service etc., then priority scheduling execution emergency brake application service, and vehicle safety stops
After only, resource is redistributed, load vessel mirror image simultaneously starts application, reopens Function for Automatic Pilot;
If hardware anomalies occur in step 7, some host, priority scheduling executes emergency brake application service, and completion is driven automatically
The safe reduction of speed parking sailed judges remaining available host quantity after vehicle safety stops, if there is no less than two available masters
The container mirror image for powering off host operation is then loaded into other hosts, reopens Function for Automatic Pilot by machine;
Step 8, vehicle computing unit collect the computing resource data of different vehicle driving scene, and root by container management service
According to current driving situation individual scene dynamic optimization adjustresources.
Use above specific case elaborates the principle of the present invention and embodiment, these embodiments are
It is used to help understand core of the invention technology contents, the protection domain being not intended to restrict the invention, technical side of the invention
Case is not limited in above-mentioned specific implementation mode.Based on the above-mentioned specific embodiment of the present invention, those skilled in the art
Without departing from the principle of the present invention, any improvement and modification to made by the present invention should all fall into the special of the present invention
Sharp protection domain.
Claims (10)
1. automatic Pilot vehicle computing resource management system, which is characterized in that its system architecture includes core sensor, vehicle-mounted
Computing unit and vehicle string holes system;The hardware resource of vehicle computing unit is managed collectively using container technique, according to
The real-time data collection processing task and automatic Pilot intelligent decision control task of core sensor, dynamically distribute physical hardware money
Source generates mutually isolated multiple containers running environment, independently executes respective task;According to actual operating state dynamic adjustment money
The intelligent coordinated of each automatic Pilot service application is realized in source;And a variety of appearances are grabbed by resource reservation, resource constraint, resource
Device management strategy completes the safety traffic of automatic driving vehicle;Wherein,
The core sensor includes the sensing equipment realized Function for Automatic Pilot and used, and passes through the real-time collecting vehicle of core sensor
Running environment data;
The vehicle computing unit general frame is divided into four layers:Physical computing resources layer, ROS real time operating systems layer, business fortune
Row environmental chamber layer and application layer;Wherein, the physical computing resources layer, including multiple main frames, these hosts are to realize automatically
Drive the central module of function;
The ROS real time operating systems layer, is deployed on physical computing resources layer, for ensureing data acquisition and Decision Control
Real-time;The service operation environmental chamber layer is deployed on ROS real time operating system layers, is run for deployment container
Environment;The application layer, for running container management service and automatic Pilot service application;
The container management service will dynamically distribute and manage resource according to business demand, complete to sense using vehicle computing unit
The acquiring of data, the fusion and collaboration of a variety of sensing equipment data, and according to automatic Pilot Decision Control Model trained in advance
Real-time inductive decision is completed, vehicle line control system is fed back to by CAN bus, completes vehicle control response.
2. automatic Pilot vehicle computing resource management system according to claim 1, which is characterized in that the core sensor
Including:Multi-path high-definition camera, laser radar, millimetre-wave radar, V2X sensing equipments, high-precision positioner;
Each host includes calculating, storage and network physical hardware resource and FPGA or GPU hardware acceleration components.
3. automatic Pilot vehicle computing resource management system according to claim 2, which is characterized in that the application layer is specific
Including Container Management application, high-precision map, Decision Control application, emergency brake application, CAN bus control, data acquisition applications.
4. automatic Pilot vehicle computing resource management system according to claim 3, which is characterized in that the automatic Pilot vehicle
It carries managing computing resources system and carries out automatic Pilot computing resource initialization, content includes:
The vehicle computing unit loads preset Container Management configuration information, is based on ROS real time operating systems, completes container tube
The initialization of service is managed, wherein reserved part computing resource is used for emergency braking Mission critical applications;
The vehicle computing unit connects core sensor by container management service, matches confidence according to preset resource allocation
Breath loads application service container mirror image, starts container application service;The core sensor data acquisition applications service operation exists
In container, core sensor is connected, and acquire the environmental data from core sensor, carry out structuring processing;
The vehicle computing unit loads CAN bus vehicle condition data by container management service and acquires service container mirror image,
And start container application service;The CAN bus vehicle condition data acquires service operation in a reservoir, real-time collection vehicle shape
Condition data carry out structuring processing;
The vehicle computing unit loads high-precision map application service container mirror image by container management service, and starts container and answer
With service;The high-precision map application service operation in a reservoir, provides high-precision Map Services, is obtained in conjunction with high accurate positioning device
Surrounding enviroment data and road data;
The vehicle computing unit loads CAN bus vehicle control service container mirror image by container management service, and starts appearance
Device application service;The CAN bus vehicle control service operation in a reservoir, waits for control instruction;
The vehicle computing unit loads automatic Pilot Decision Control service container mirror image by container management service, and starts appearance
Device inductive decision controls application service;Automatic Pilot inductive decision control application service operation in a reservoir, and with it is each
Acquisition applications service interacts, and realizes in data set, and completes decision calculating task according to its automatic Pilot decision model, real
When feed back to the CAN bus vehicle control service;
The vehicle computing unit will load emergency braking service container mirror image by container management service at least two hosts,
And start application service;The emergency braking service operation in a reservoir, and keeps heartbeat with other application service container, in real time
Its resource and operation conditions are monitored, waits for and instructing while listening for port.
5. automatic Pilot vehicle computing resource management system according to claim 4, which is characterized in that the automatic Pilot vehicle
It carries managing computing resources system and carries out automatic Pilot managing computing resources, content includes:
The vehicle computing unit is marked FPGA, GPU by container management service, for deep learning reasoning scene,
It is serviced using given host load vessel;
The vehicle computing unit monitors the container and hardware resource situation of autonomous driving vehicle by container management service;If holding
The allocated computing resource of device has reached critical value, inadequate resource phenomenon occurs, then preferential to be distributed using reserved to crucial calculate
Resource;When container resource utilization reaches saturation situation, if crucial application resource is insufficient, the money of non-key service application is grabbed
Source;If there is non-critical application container operation exception, turn off container Resource recovery, redistributes resource, load vessel mirror image
And start application;If there is crucial application container operation exception, priority scheduling executes emergency brake application service, completes automatic
The safe reduction of speed parking driven redistributes resource, load vessel mirror image simultaneously starts application, opens again after vehicle safety stops
Open Function for Automatic Pilot;
If hardware anomalies occurs in some host, priority scheduling executes emergency brake application service, completes the safety of automatic Pilot
Reduction of speed stops, and after vehicle safety stops, judging remaining available host quantity, is no less than two available hosts if existing, will break
The container mirror image of electric host operation is loaded into other hosts, reopens Function for Automatic Pilot;
The vehicle computing unit by container management service collect different vehicle driving scene computing resource data, and according to
Current driving situation individual scene dynamic optimization adjustresources.
6. automatic Pilot vehicle computing method for managing resource, which is characterized in that utilize container technique by the hard of vehicle computing unit
Part resource is managed collectively, and handles task according to the real-time data collection of core sensor and automatic Pilot intelligent decision controls
Task dynamically distributes physical hardware resources, generates mutually isolated multiple containers running environment, independently execute respective task;Root
According to actual operating state dynamic adjustresources, the intelligent coordinated of each automatic Pilot service application is realized;And by resource reservation,
Resource constraint, resource grab a variety of Container Management strategies, complete the safety traffic of automatic driving vehicle;
The vehicle computing unit is made of multiple main frames, is the central module for realizing Function for Automatic Pilot, in vehicle computing list
On member, ROS real time operating systems are disposed to ensure the real-time of data acquisition and Decision Control, on ROS operating systems
Deployment container running environment, wherein operation container management service and automatic Pilot service application;The core sensor includes real
The sensing equipment that existing Function for Automatic Pilot is used;
The container management service will dynamically distribute and manage resource according to business demand, complete using the vehicle computing unit
At the acquiring of sensing data, the fusion and collaboration of a variety of sensing equipment data, and according to automatic Pilot decision control trained in advance
Simulation completes real-time inductive decision, feeds back to vehicle line control system by CAN bus, completes vehicle control response.
7. automatic Pilot vehicle computing method for managing resource according to claim 6, which is characterized in that the core sensor
Including:Multi-path high-definition camera, laser radar, millimetre-wave radar, V2X sensing equipments, high-precision positioner;
Each host includes calculating, storage and network physical hardware resource and FPGA or GPU hardware acceleration components.
8. automatic Pilot vehicle computing method for managing resource according to claim 7, which is characterized in that the application layer is specific
Including Container Management application, high-precision map, Decision Control application, emergency brake application, CAN bus control, data acquisition applications.
9. automatic Pilot vehicle computing method for managing resource according to claim 8, which is characterized in that carry out automatic Pilot meter
Initializing resource is calculated, this operating process includes:
Step 1, autonomous driving vehicle start power supply system, power for vehicle computing unit, complete host supplying power and start;
Step 2, vehicle computing unit load ROS real time operating systems;
Step 3, vehicle computing unit load preset Container Management configuration information, are based on ROS real time operating systems, complete container
The initialization of management service, wherein by reserved part computing resource for Mission critical applications such as emergency brakings;
Step 4, vehicle computing unit connect core sensor by container management service, match confidence according to preset resource allocation
Breath loads application service container mirror image, and starts container application service respectively;
Step 5, core sensor data acquisition applications service operation in a reservoir, connect core sensor, and acquire and come from core
The environmental data of heart sensor carries out structuring processing;
Step 6, vehicle computing unit load CAN bus vehicle condition data by container management service and acquire service container mirror
Picture, and start container application service;
In a reservoir, real-time collection vehicle status data is tied for step 7, CAN bus vehicle condition data acquisition service operation
Structureization processing;
Step 8, vehicle computing unit load high-precision map application service container mirror image by container management service, and start container
Application service;
Step 9, high-precision map application service operation in a reservoir, provide high-precision Map Services, are obtained in conjunction with high accurate positioning device
Surrounding enviroment data and road data;
Step 10, vehicle computing unit load CAN bus vehicle control service container mirror image by container management service, and start
Container application service;
Step 11, CAN bus vehicle control service operation in a reservoir, wait for control instruction;
Step 12, vehicle computing unit load automatic Pilot Decision Control service container mirror image by container management service, and open
Visibly moved device inductive decision controls application service;
Step 13, automatic Pilot inductive decision control application service operation in a reservoir, and are serviced with each acquisition applications and are carried out
Interaction is realized in data set, and completes decision calculating task according to its automatic Pilot decision model, and Real-time Feedback is to described
CAN bus vehicle control service;
Step 14, vehicle computing unit will load emergency braking service container mirror by container management service at least two hosts
Picture, and start application service;
Step 15, emergency braking service operation in a reservoir, and keep heartbeat with other application service container, monitor its money in real time
Source and operation conditions are waited for while listening for port and being instructed;
Step 16, autonomous driving vehicle computing unit operating status are normal, and computing resource initialization is completed.
10. automatic Pilot vehicle computing method for managing resource according to claim 9, which is characterized in that carry out automatic Pilot
Managing computing resources, this operating process include:
Step 1, vehicle computing unit are marked the specialized hardwares such as FPGA, GPU by container management service, are related to depth
The scenes such as reasoning are practised, then are serviced using given host load vessel;
Step 2, vehicle computing unit monitor the container and hardware resource situation of autonomous driving vehicle by container management service;
If the allocated computing resource of step 3, container has reached critical value, there is inadequate resource phenomenon, then it is preferential to key
It calculates distribution and uses reserved resource;
Step 4 reaches saturation situation when container resource utilization, if crucial application resource is insufficient, grabs non-key business
The resource of application ensures the operation of Core Feature;
Step 5, if there is non-critical application container operation exception, such as V2X sensing equipment data acquisition applications, some is backward
High-definition camera data acquisition applications etc., then turn off container Resource recovery, redistributes resource, and load vessel mirror image and starting is answered
With;
Step 6 is determined if there is crucial application container operation exception, such as preposition high-definition camera data acquisition service, reasoning
The safe reduction of speed parking of automatic Pilot is completed in plan service etc., then priority scheduling execution emergency brake application service, and vehicle safety stops
After only, resource is redistributed, load vessel mirror image simultaneously starts application, reopens Function for Automatic Pilot;
If hardware anomalies occur in step 7, some host, priority scheduling executes emergency brake application service, and completion is driven automatically
The safe reduction of speed parking sailed judges remaining available host quantity after vehicle safety stops, if there is no less than two available masters
The container mirror image for powering off host operation is then loaded into other hosts, reopens Function for Automatic Pilot by machine;
Step 8, vehicle computing unit collect the computing resource data of different vehicle driving scene, and root by container management service
According to current driving situation individual scene dynamic optimization adjustresources.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810414692.2A CN108594819A (en) | 2018-05-03 | 2018-05-03 | Automatic Pilot vehicle computing resource management system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810414692.2A CN108594819A (en) | 2018-05-03 | 2018-05-03 | Automatic Pilot vehicle computing resource management system and method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108594819A true CN108594819A (en) | 2018-09-28 |
Family
ID=63619615
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810414692.2A Pending CN108594819A (en) | 2018-05-03 | 2018-05-03 | Automatic Pilot vehicle computing resource management system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108594819A (en) |
Cited By (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109377778A (en) * | 2018-11-15 | 2019-02-22 | 济南浪潮高新科技投资发展有限公司 | A kind of collaboration automated driving system and method based on multichannel RDMA and V2X |
CN109408197A (en) * | 2018-09-29 | 2019-03-01 | 上海理想信息产业(集团)有限公司 | A kind of implementation method and device of edge calculations engine |
CN109445959A (en) * | 2018-10-17 | 2019-03-08 | 北京技德终端技术有限公司 | A kind of sensing data processing real time operating system |
CN109649395A (en) * | 2018-12-29 | 2019-04-19 | 驭势科技(北京)有限公司 | A kind of automatic Pilot method of adjustment and mobile unit based on computing resource |
CN109714422A (en) * | 2018-12-28 | 2019-05-03 | 深圳市易成自动驾驶技术有限公司 | Computing resource sharing method, system and readable storage medium storing program for executing based on automatic Pilot |
CN109739222A (en) * | 2018-12-12 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | A kind of Edge Computing Rack platform, system and method applied to autonomous driving vehicle |
CN109739650A (en) * | 2018-12-28 | 2019-05-10 | 驭势科技(北京)有限公司 | A kind of method and device for distributing data processing resources |
CN109885392A (en) * | 2019-01-03 | 2019-06-14 | 北京百度网讯科技有限公司 | Distribute the method and device of vehicle computing resource |
CN109941211A (en) * | 2019-03-22 | 2019-06-28 | 清华大学 | A kind of Intelligent Vehicle Driving System structure common type framework and construction method |
CN109951561A (en) * | 2019-03-28 | 2019-06-28 | 浙江数值跳跃网络科技有限公司 | Decentralization basis running environment cater system based on cloud container technique |
CN110001660A (en) * | 2018-12-17 | 2019-07-12 | 蔚来汽车有限公司 | A kind of distributed multi-core heterogeneous system |
CN110022349A (en) * | 2019-01-17 | 2019-07-16 | 重庆邮电大学 | A kind of isomery industrial network device configuration micro services method based on edge calculations |
CN110070181A (en) * | 2019-04-30 | 2019-07-30 | 深圳朴生智能科技有限公司 | A kind of optimization method of the deep learning for edge calculations equipment |
CN110310512A (en) * | 2019-07-10 | 2019-10-08 | 中国联合网络通信集团有限公司 | A kind of parking lot FIXED MANAGEMENT method and system based on 5g Internet of Things container technique |
CN110568852A (en) * | 2019-10-12 | 2019-12-13 | 深圳市布谷鸟科技有限公司 | Automatic driving system and control method thereof |
CN110955886A (en) * | 2019-11-08 | 2020-04-03 | 广州供电局有限公司 | Sandbox-based data security fusion service device and method thereof |
CN111240751A (en) * | 2019-12-27 | 2020-06-05 | 深圳市众鸿科技股份有限公司 | Hardware isolation method and system based on vehicle-mounted intelligent cabin |
CN111666133A (en) * | 2019-03-05 | 2020-09-15 | 北京图森智途科技有限公司 | Vehicle-mounted infrastructure for automatically driving vehicle |
CN111831391A (en) * | 2020-06-08 | 2020-10-27 | 北京百度网讯科技有限公司 | Method and device for managing preset container in automatic driving simulation system |
CN111882665A (en) * | 2020-09-28 | 2020-11-03 | 蘑菇车联信息科技有限公司 | Vehicle driving assistance system and method |
CN112261584A (en) * | 2020-10-13 | 2021-01-22 | 恒大新能源汽车投资控股集团有限公司 | Geographic fence determination method and device and electronic equipment |
WO2021022987A1 (en) * | 2019-08-05 | 2021-02-11 | 腾讯科技(深圳)有限公司 | Vehicle-road cooperation apparatus and method, electronic device and storage medium |
CN112579253A (en) * | 2020-12-02 | 2021-03-30 | 科东(广州)软件科技有限公司 | Method and system for managing container |
CN112585583A (en) * | 2020-07-17 | 2021-03-30 | 华为技术有限公司 | Data processing method and device and intelligent vehicle |
CN113348646A (en) * | 2018-12-20 | 2021-09-03 | 大众汽车股份公司 | Method for operating a vehicle while transferring computational power from the vehicle to at least one edge cloud computer |
CN113460085A (en) * | 2021-06-28 | 2021-10-01 | 东风汽车集团股份有限公司 | Service-oriented automatic driving network design and communication method and computer equipment |
CN113873623A (en) * | 2021-09-03 | 2021-12-31 | 许继集团有限公司 | Power transmission node equipment based on container technology and low-power-consumption control method |
WO2022063148A1 (en) * | 2020-09-23 | 2022-03-31 | Qualcomm Incorporated | Resource selection under congested conditions |
CN115118725A (en) * | 2022-06-28 | 2022-09-27 | 国汽智控(北京)科技有限公司 | Dynamic vehicle cloud computing method and device, electronic equipment and storage medium |
CN115509726A (en) * | 2022-11-17 | 2022-12-23 | 南京芯驰半导体科技有限公司 | Sensor data access system |
WO2024036618A1 (en) * | 2022-08-19 | 2024-02-22 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Dynamic signal transfer configuration for driverless vehicle remote monitoring |
WO2024098333A1 (en) * | 2022-11-10 | 2024-05-16 | 华为技术有限公司 | Method and apparatus for adjusting computing resources, and intelligent driving device |
WO2024116627A1 (en) * | 2022-11-28 | 2024-06-06 | 株式会社デンソー | Control device, resource management method, and resource management program |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105490860A (en) * | 2015-12-24 | 2016-04-13 | 北京奇虎科技有限公司 | Method, device and system for deploying application program operation environment |
WO2018014282A1 (en) * | 2016-07-21 | 2018-01-25 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Efficient communications amongst computing nodes for operating autonomous vehicles |
WO2018068427A1 (en) * | 2016-10-13 | 2018-04-19 | 北京百度网讯科技有限公司 | Method and device for developing driverless vehicle application |
-
2018
- 2018-05-03 CN CN201810414692.2A patent/CN108594819A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105490860A (en) * | 2015-12-24 | 2016-04-13 | 北京奇虎科技有限公司 | Method, device and system for deploying application program operation environment |
WO2018014282A1 (en) * | 2016-07-21 | 2018-01-25 | Baidu.Com Times Technology (Beijing) Co., Ltd. | Efficient communications amongst computing nodes for operating autonomous vehicles |
WO2018068427A1 (en) * | 2016-10-13 | 2018-04-19 | 北京百度网讯科技有限公司 | Method and device for developing driverless vehicle application |
Non-Patent Citations (7)
Title |
---|
JEFF NICKOLOFF: "《Docker实战》", 31 January 2017, 电子工业出版社 * |
PHILIP MASEK 等: "Systematic evaluation of sandboxed software deployment for real-time software on the example of a self-driving heavy vehicle", 《2016 IEEE 19TH INTERNATIONAL CONFERENCE ON INTELLIGENT TRANSPORTATION SYSTEMS (ITSC)》 * |
SHAOSHAN LIU: "A Unified Cloud Platform for Autonomous Driving", 《COMPUTER》 * |
何承 等: "《城市交通大数据》", 31 January 2015, 上海科学技术出版社 * |
刘纪原: "《自然灾害与空间信息体系》", 30 September 2013, 中国宇航出版社 * |
张鑫: "《Hadoop源代码分析》", 31 August 2014, 中国铁道出版社 * |
高登: "《云计算与Hadoop应用技术研究》", 31 December 2017, 吉林大学出版社 * |
Cited By (49)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109408197A (en) * | 2018-09-29 | 2019-03-01 | 上海理想信息产业(集团)有限公司 | A kind of implementation method and device of edge calculations engine |
CN109445959A (en) * | 2018-10-17 | 2019-03-08 | 北京技德终端技术有限公司 | A kind of sensing data processing real time operating system |
CN109377778A (en) * | 2018-11-15 | 2019-02-22 | 济南浪潮高新科技投资发展有限公司 | A kind of collaboration automated driving system and method based on multichannel RDMA and V2X |
CN109377778B (en) * | 2018-11-15 | 2021-04-06 | 浪潮集团有限公司 | Collaborative automatic driving system and method based on multipath RDMA and V2X |
CN109739222A (en) * | 2018-12-12 | 2019-05-10 | 济南浪潮高新科技投资发展有限公司 | A kind of Edge Computing Rack platform, system and method applied to autonomous driving vehicle |
CN110001660A (en) * | 2018-12-17 | 2019-07-12 | 蔚来汽车有限公司 | A kind of distributed multi-core heterogeneous system |
CN113348646A (en) * | 2018-12-20 | 2021-09-03 | 大众汽车股份公司 | Method for operating a vehicle while transferring computational power from the vehicle to at least one edge cloud computer |
CN113348646B (en) * | 2018-12-20 | 2023-08-11 | 大众汽车股份公司 | Method for operating a vehicle, control device for a vehicle, and vehicle |
CN109739650B (en) * | 2018-12-28 | 2021-04-16 | 驭势科技(北京)有限公司 | Method and device for distributing data processing resources |
WO2020133205A1 (en) * | 2018-12-28 | 2020-07-02 | 驭势科技(北京)有限公司 | Method and apparatus for allocating data processing resources |
CN109739650A (en) * | 2018-12-28 | 2019-05-10 | 驭势科技(北京)有限公司 | A kind of method and device for distributing data processing resources |
CN109714422A (en) * | 2018-12-28 | 2019-05-03 | 深圳市易成自动驾驶技术有限公司 | Computing resource sharing method, system and readable storage medium storing program for executing based on automatic Pilot |
CN109649395B (en) * | 2018-12-29 | 2023-12-01 | 驭势科技(北京)有限公司 | Automatic driving adjustment method based on computing resources and vehicle-mounted equipment |
CN109649395A (en) * | 2018-12-29 | 2019-04-19 | 驭势科技(北京)有限公司 | A kind of automatic Pilot method of adjustment and mobile unit based on computing resource |
CN109885392A (en) * | 2019-01-03 | 2019-06-14 | 北京百度网讯科技有限公司 | Distribute the method and device of vehicle computing resource |
CN110022349A (en) * | 2019-01-17 | 2019-07-16 | 重庆邮电大学 | A kind of isomery industrial network device configuration micro services method based on edge calculations |
CN111666133A (en) * | 2019-03-05 | 2020-09-15 | 北京图森智途科技有限公司 | Vehicle-mounted infrastructure for automatically driving vehicle |
CN109941211A (en) * | 2019-03-22 | 2019-06-28 | 清华大学 | A kind of Intelligent Vehicle Driving System structure common type framework and construction method |
CN109951561A (en) * | 2019-03-28 | 2019-06-28 | 浙江数值跳跃网络科技有限公司 | Decentralization basis running environment cater system based on cloud container technique |
CN110070181A (en) * | 2019-04-30 | 2019-07-30 | 深圳朴生智能科技有限公司 | A kind of optimization method of the deep learning for edge calculations equipment |
CN110310512B (en) * | 2019-07-10 | 2021-02-19 | 中国联合网络通信集团有限公司 | Parking lot positioning management method and system based on 5g Internet of things container technology |
CN110310512A (en) * | 2019-07-10 | 2019-10-08 | 中国联合网络通信集团有限公司 | A kind of parking lot FIXED MANAGEMENT method and system based on 5g Internet of Things container technique |
WO2021022987A1 (en) * | 2019-08-05 | 2021-02-11 | 腾讯科技(深圳)有限公司 | Vehicle-road cooperation apparatus and method, electronic device and storage medium |
KR102567204B1 (en) * | 2019-08-05 | 2023-08-14 | 텐센트 테크놀로지(센젠) 컴퍼니 리미티드 | Vehicle-road cooperation apparatus and method, electronic device and storage medium |
US11974201B2 (en) | 2019-08-05 | 2024-04-30 | Tencent Technology (Shenzhen) Company Limited | Vehicle-road collaboration apparatus and method, electronic device, and storage medium |
KR20210130213A (en) * | 2019-08-05 | 2021-10-29 | 텐센트 테크놀로지(센젠) 컴퍼니 리미티드 | Vehicle-road cooperation apparatus and method, electronic device and storage medium |
CN110568852A (en) * | 2019-10-12 | 2019-12-13 | 深圳市布谷鸟科技有限公司 | Automatic driving system and control method thereof |
CN110955886A (en) * | 2019-11-08 | 2020-04-03 | 广州供电局有限公司 | Sandbox-based data security fusion service device and method thereof |
CN110955886B (en) * | 2019-11-08 | 2022-06-21 | 广州供电局有限公司 | Sandbox-based data security fusion service device and method |
CN111240751B (en) * | 2019-12-27 | 2024-06-07 | 深圳市众鸿科技股份有限公司 | Hardware isolation method and system based on vehicle-mounted intelligent cabin |
CN111240751A (en) * | 2019-12-27 | 2020-06-05 | 深圳市众鸿科技股份有限公司 | Hardware isolation method and system based on vehicle-mounted intelligent cabin |
CN111831391B (en) * | 2020-06-08 | 2023-09-22 | 北京百度网讯科技有限公司 | Method and device for managing preset containers in automatic driving simulation system |
CN111831391A (en) * | 2020-06-08 | 2020-10-27 | 北京百度网讯科技有限公司 | Method and device for managing preset container in automatic driving simulation system |
CN112585583B (en) * | 2020-07-17 | 2021-12-03 | 华为技术有限公司 | Data processing method and device and intelligent vehicle |
CN112585583A (en) * | 2020-07-17 | 2021-03-30 | 华为技术有限公司 | Data processing method and device and intelligent vehicle |
WO2022063148A1 (en) * | 2020-09-23 | 2022-03-31 | Qualcomm Incorporated | Resource selection under congested conditions |
CN111882665A (en) * | 2020-09-28 | 2020-11-03 | 蘑菇车联信息科技有限公司 | Vehicle driving assistance system and method |
CN112261584A (en) * | 2020-10-13 | 2021-01-22 | 恒大新能源汽车投资控股集团有限公司 | Geographic fence determination method and device and electronic equipment |
CN112579253A (en) * | 2020-12-02 | 2021-03-30 | 科东(广州)软件科技有限公司 | Method and system for managing container |
CN112579253B (en) * | 2020-12-02 | 2021-10-19 | 科东(广州)软件科技有限公司 | Method and system for managing container |
CN113460085A (en) * | 2021-06-28 | 2021-10-01 | 东风汽车集团股份有限公司 | Service-oriented automatic driving network design and communication method and computer equipment |
CN113873623A (en) * | 2021-09-03 | 2021-12-31 | 许继集团有限公司 | Power transmission node equipment based on container technology and low-power-consumption control method |
CN113873623B (en) * | 2021-09-03 | 2024-04-16 | 许继集团有限公司 | Power transmission node equipment based on container technology and low-power consumption control method |
CN115118725A (en) * | 2022-06-28 | 2022-09-27 | 国汽智控(北京)科技有限公司 | Dynamic vehicle cloud computing method and device, electronic equipment and storage medium |
WO2024036618A1 (en) * | 2022-08-19 | 2024-02-22 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Dynamic signal transfer configuration for driverless vehicle remote monitoring |
WO2024098333A1 (en) * | 2022-11-10 | 2024-05-16 | 华为技术有限公司 | Method and apparatus for adjusting computing resources, and intelligent driving device |
CN115509726B (en) * | 2022-11-17 | 2023-03-14 | 南京芯驰半导体科技有限公司 | Sensor data access system |
CN115509726A (en) * | 2022-11-17 | 2022-12-23 | 南京芯驰半导体科技有限公司 | Sensor data access system |
WO2024116627A1 (en) * | 2022-11-28 | 2024-06-06 | 株式会社デンソー | Control device, resource management method, and resource management program |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108594819A (en) | Automatic Pilot vehicle computing resource management system and method | |
CN112925657A (en) | Vehicle road cloud cooperative processing system and method | |
US20200082304A1 (en) | Method, Apparatus and Device for Scheduling Unmanned Vehicles and Storage Medium | |
CN102541069B (en) | Loss of separation avoidance maneuvering | |
CN108428357A (en) | A kind of parallel remote driving system for intelligent network connection vehicle | |
CN110428161A (en) | A kind of unmanned mine car cloud intelligent dispatching method based on end edge cloud framework | |
CN107444393A (en) | Brakes control method and device | |
CN109783225B (en) | Tenant priority management method and system of multi-tenant big data platform | |
CN105739531A (en) | Unmanned plane control system based on unmanned plane air management platform | |
CN111158900B (en) | Lightweight distributed parallel computing system and method | |
CN111105155B (en) | Role-based group unmanned system collaborative task management method | |
CN106020970A (en) | Heterogeneous virtualization platform management framework in private cloud environment | |
Bächle et al. | Model predictive control allocation in electric vehicle drive trains | |
CN109941211A (en) | A kind of Intelligent Vehicle Driving System structure common type framework and construction method | |
CN112849230B (en) | Magnetic suspension traffic ground partition integrated control method, device and application system thereof | |
Delprat et al. | High order sliding mode control for hybrid vehicle stability | |
CN111703418A (en) | Multi-vehicle distributed cooperative collision avoidance method and device based on vehicle-vehicle communication | |
CN109697880A (en) | Unmanned vehicle parking space allocation method, apparatus, equipment and storage medium | |
CN104512403B (en) | For showing the method and system of the regenerative braking efficiency of Cleaning Equipment | |
CN114884998B (en) | Cooperative software defined vehicle-mounted network system, scheduling method and CACC | |
CN105210324B (en) | Strategy and charging rule functions virtual method, apparatus and system | |
CN110442428A (en) | The coordination approach of Docker container | |
CN113511203B (en) | Vehicle formation following driving control method, system, equipment and storage medium | |
CN109969176A (en) | A kind of method and system of autonomous driving vehicle emergency braking control | |
CN102556339A (en) | Method for managing a ground movement of an aircraft |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |
|
RJ01 | Rejection of invention patent application after publication |