CN110471411A - Automatic Pilot method and servomechanism - Google Patents

Automatic Pilot method and servomechanism Download PDF

Info

Publication number
CN110471411A
CN110471411A CN201910691859.4A CN201910691859A CN110471411A CN 110471411 A CN110471411 A CN 110471411A CN 201910691859 A CN201910691859 A CN 201910691859A CN 110471411 A CN110471411 A CN 110471411A
Authority
CN
China
Prior art keywords
driving
history
control parameter
traffic information
target
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
Application number
CN201910691859.4A
Other languages
Chinese (zh)
Inventor
王华卿
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to CN201910691859.4A priority Critical patent/CN110471411A/en
Publication of CN110471411A publication Critical patent/CN110471411A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions

Abstract

The embodiment of the present application discloses a kind of automatic Pilot method and servomechanism, is related to artificial intelligence field, and in particular to automatic Pilot field, the automatic Pilot method can include: servomechanism obtains current traffic information；According to the current traffic information, inquiry is with the presence or absence of the target Driving control parameter to match with the current traffic information from database；If it exists, then the target Driving control parameter is obtained, and is driven according to the target Driving control parameter with target driving style；If it does not exist, then it is driven according to real-time Driving control parameter with current driving style；The real-time Driving control parameter is the Driving control parameter that the servomechanism goes out according to default decision-making mechanism decision.In the embodiment of the present application, servomechanism is driven according to the Driving control parameter to match in history Driving control parameter with current road conditions, and the driving behavior that can be executed under automatic driving mode to the servomechanism optimizes.

Description

Automatic Pilot method and servomechanism
Technical field
This application involves automatic Pilot field more particularly to a kind of automatic Pilot method and servomechanisms.
Background technique
Artificial intelligence (Artificial Intelligence, AI) is to utilize digital computer or digital computer control Machine simulation, extension and the intelligence for extending people of system, perception environment obtain knowledge and the reason using Knowledge Acquirement optimum By, method, technology and application system.In other words, artificial intelligence is a branch of computer science, it attempts to understand intelligence Essence, and produce a kind of new intelligence machine that can be reacted in such a way that human intelligence is similar.Artificial intelligence is also It is the design principle and implementation method for studying various intelligence machines, machine is made to have the function of perception, reasoning and decision.
Automatic Pilot is a kind of mainstream applications of artificial intelligence field, automatic Pilot technology by computer vision, radar, Motor vehicles can be realized certainly in the case where not needing mankind's active operation for the cooperative cooperatings such as monitoring device and global positioning system It is dynamic to drive.The vehicle of automatic Pilot helps from a position to transport passenger to another location using various computing systems.One A little automatic driving vehicles may require some initial inputs from operator (such as, navigator, driver or passenger) or Person continuously inputs.Automatic driving vehicle permits operator and is switched to automatic driving mode or between the two from manual modulo operation formula Between mode.Since automatic Pilot technology carrys out driving maneuver vehicle without the mankind, so theoretically can effectively avoid the mankind Faulty drive, reduce traffic accident, and can be improved the conevying efficiency of highway.Therefore, automatic Pilot technology is more next More it is taken seriously.
Currently, automatic driving vehicle under automatic driving mode according to the traffic information of acquisition and navigation information, according to Preset driving rule executes driver behavior.However, the driver behavior pair that automatic driving vehicle executes under automatic driving mode It is frequently not optimal for passenger.How to optimize the driver behavior that automatic driving vehicle executes under automatic driving mode with The driving habit for preferably meeting passenger is problem to be solved.
Summary of the invention
The embodiment of the present application discloses a kind of automatic Pilot method and servomechanism, can optimize automatic driving vehicle The driver behavior executed under automatic driving mode, and then preferably meet the driving habit of user.
In a first aspect, the embodiment of the present application provides a kind of automatic Pilot method, this method can include: servomechanism Obtain current traffic information；According to the current traffic information, inquiry whether there is and the current traffic information phase from database Matched target Driving control parameter；If it exists, then the target Driving control parameter is obtained, and is joined according to the target Driving control Number is driven with target driving style；The target Driving control parameter includes the history Driving control parameter of target vehicle, should History Driving control parameter includes the Driving control parameter that the target vehicle is driven according to the target driving style；If It is not present, is then driven according to real-time Driving control parameter with current driving style；The real-time Driving control parameter is should be certainly The Driving control parameter that dynamic pilot instrument goes out according to default decision-making mechanism decision.
The history Driving control parameter of the target vehicle, which can be driver and drive the target vehicle in a manual mode, to be obtained The history drive parameter arrived.The target vehicle can be the servomechanism, may not be the servomechanism.It is optional , the history Driving control parameter of the target vehicle can be by reference Driving control Parameter Switch, and it is automatic to can be used as this The history Driving control parameter of pilot instrument.This is that driver drives the target carriage in a manual mode with reference to Driving control parameter Obtained history drive parameter.If should be understood that, the history Driving control parameter of target vehicle cannot be directly as automatic Pilot The history Driving control parameter of device, then the history Driving control Parameter Switch of the target vehicle can be to be somebody's turn to do by servomechanism The history Driving control parameter of servomechanism.In practical application, if servomechanism and target vehicle use it is identical The driver behavior that Driving control parameter is realized is distinct, i.e., the servomechanism cannot directly use the driving of target vehicle Control parameter, then the history Driving control Parameter Switch of the target vehicle can be the servomechanism by the servomechanism History Driving control parameter.
In the embodiment of the present application, servomechanism is inquiring the target Driving control parameter to match with current road conditions Afterwards, it is driven according to the target Driving control parameter, when not inquiring the target Driving control parameter according to its current decision Driving control parameter out is driven；The history Driving control parameter for enabling the servomechanism to utilize passenger previous The driver behavior gone out to its current decision optimizes.Since target Driving control parameter is to meet the driving habit of passenger to go through History Driving control parameter optimizes the driver behavior of the servomechanism using these history Driving control parameters, can To better meet the driving habit of passenger.
In an optional implementation, before obtaining target Driving control parameter, this method further include: determine One driving behavior, first driving behavior are the driving behaviors that the servomechanism presets that decision-making mechanism decision goes out according to this； Determine the second driving behavior to match in the database with the current traffic information, the driving behavior in the database includes should The historical driving behavior that target vehicle is driven according to the target driving style；Judge that first driving behavior second is driven with this Whether identical sail behavior, if they are the same, then the step of executing the acquisition target Driving control parameter.
The historical driving behavior to match with current traffic information can be the driving control to match with current traffic information The corresponding driving behavior of parameter processed.If being appreciated that the current matched historical driving behavior of traffic information and currently determination Pending driving behavior is different under current traffic information, then the Driving control parameter pair to match with current traffic information The driving behavior answered is also different from the driving behavior pending under current traffic information currently determined.If in this way according to work as The Driving control parameter that preceding traffic information matches is driven, it is likely that does not meet safe driving standard or traffic law. In this implementation, the matched historical driving behavior of current traffic information with currently determine under current road conditions it is pending The identical situation of driving behavior under, obtain the Driving control parameter to match with the current road conditions；It is possible to prevente effectively from automatic The driving behavior that pilot instrument executes does not meet safe driving standard or hands over rule.
In an optional implementation, determine that match in driving style database with the current road conditions second drives The behavior of sailing includes: the target traffic information for including the case where matching with the current traffic information in the driving style database Under, determine that the corresponding driving behavior of target traffic information is second driving behavior in the driving style database；The driving It is corresponding with driving behavior that style data library includes at least one of at least one history traffic information, and this history traffic information Relationship, which includes the target traffic information.
In this implementation, the second driving behavior to match with current road conditions can be accurately and rapidly determined.
In an optional implementation, according to the current traffic information, from database inquiry with the presence or absence of with Before the target Driving control parameter that the current traffic information matches, this method further include: obtain driving data file；Judgement Whether the driving data file includes history traffic information, history that the target vehicle is driven according to the target driving style At least one of in Driving control parameter and historical driving behavior, if so, executing this according to the current traffic information, from number The step of according to inquiry in library with the presence or absence of the target Driving control parameter to match with the current traffic information.
Servomechanism is only capable of being driven according to real-time Driving control parameter before obtaining the driving data file It sails；After obtaining the driving data file, history traffic information, the history driving that the driving data file includes can use Control parameter and historical driving behavior are driven according to target driving style.In this implementation, driving number is being obtained After file, determination is driven according to the target driving style；It can guarantee to be driven according to target driving style It has obtained carrying out driving required history driving data according to target driving style before, it is highly-safe.
In an optional implementation, obtaining driving data file includes: to receive the driving from first terminal Data file；Alternatively, obtaining the driving data file from server after receiving the first instruction from second terminal；It should First instruction is used to indicate the servomechanism and obtains the driving data file from the server.
In this implementation, servomechanism can rapidly obtain driving data file in several ways, with Convenient for meeting the needs of different user.
In an optional implementation, determine that drive according to target driving style includes: to receive user In the case where the third instruction of input or the 4th instruction from third terminal, determination is driven according to the target driving style It sails；Third instruction and the 4th instruction are used to indicate that the servomechanism is driven according to the target driving style. The servomechanism is stored with the history Driving control parameter.
In this implementation, user can quickly and easily indicate servomechanism according to target driving style into Row drives, and user experience is good.
In an optional implementation, driving packet is carried out with target driving style according to the target Driving control parameter It includes: in the case where the target Driving control parameter meets safe driving standard and hands over rule, according to the target Driving control parameter It is driven.
In this implementation, servomechanism can be effectively ensured to be driven according to target Driving control parameter, Safe driving standard can be met and hand over rule.
In an optional implementation, after obtaining target Driving control parameter, this method further include: in the mesh In the case that mark Driving control parameter does not meet safe driving standard or hands over rule, driven according to real-time Driving control parameter It sails, which is the Driving control parameter that the servomechanism current decision goes out.
Servomechanism drive according to real-time Driving control parameter to meet safe driving standard and handing over and be advised.In In the implementation, it is ensured that the driving behavior of servomechanism meets safe driving standard and hands over rule.
In an optional implementation, which is to believe the historical driving behavior, the history road conditions Breath and the history Driving control parameter store in the database as a whole, and the history traffic information and the history drive Control parameter is respectively the traffic information that the target vehicle acquires during driver's manual drive and Driving control ginseng Number, the history traffic information is corresponding in time dimension with the history Driving control parameter, which is the target The driving behavior that vehicle is determined according to the history traffic information and the history Driving control parameter.
In this implementation, historical driving behavior is determined according to history traffic information and history Driving control parameter, into And historical driving behavior, history traffic information and history Driving control parameter are stored as a whole to obtain driving number According to file；The driving data file comprising user's driving style can efficiently be generated.
Second aspect, the embodiment of the present application provide a kind of servomechanism, the servomechanism can include: sensing Device, memory and processor；The sensor is for acquiring current traffic information；The memory is used for store code；The processing Device is by reading the code stored in the memory to be used to perform the following operations: according to the current traffic information, from data Inquiry is with the presence or absence of the target Driving control parameter to match with the current traffic information in library；If it exists, then the target is obtained Driving control parameter, and driven according to the target Driving control parameter with target driving style；Target Driving control ginseng Number includes the history Driving control parameter of target vehicle, which includes that the target vehicle is driven according to the target The Driving control parameter that sailing lattice are driven；If it does not exist, then according to real-time Driving control parameter currently to drive wind Lattice are driven；The real-time Driving control parameter is the Driving control that the servomechanism goes out according to default decision-making mechanism decision Parameter.
In an optional implementation, processor is also used to determine that the first driving behavior, first driving behavior are The servomechanism presets the driving behavior that decision-making mechanism decision goes out according to this；It determines in the database and believes with the current road conditions Matched second driving behavior of manner of breathing, the driving behavior in the database include the target vehicle according to the target driving style into The historical driving behavior that row drives；Judge whether first driving behavior and second driving behavior are identical, if they are the same, then execute The step of acquisition target Driving control parameter.
In an optional implementation, processor, specifically for including believing in the database with the current road conditions In the case where the matched target traffic information of manner of breathing, determine that the corresponding driving behavior of target traffic information is to be somebody's turn to do in the database Second driving behavior；The database includes at least one history traffic information, and is somebody's turn to do at least one history traffic information and drives The corresponding relationship of behavior is sailed, which includes the target traffic information.
In an optional implementation, the device further include: communication interface, for obtaining or receiving driving data text Part；
Processor, be also used to judge the driving data file whether include the target vehicle according to the target driving style into At least one of in history traffic information, history Driving control parameter and the historical driving behavior that row drives, if so, executing This is according to the current traffic information, and inquiry drives with the presence or absence of the target to match with the current traffic information and controls from database The step of parameter processed.
In an optional implementation, communication interface, specifically for receiving the driving data from first terminal File；Alternatively, the communication interface, specifically for after receiving the first instruction from second terminal, obtaining from server should Driving data file；First instruction is used to indicate the servomechanism and obtains the driving data file from the server.
In an optional implementation, the device further include: communication interface, the third for receiving user's input refer to It enables or the from third terminal the 4th instructs；The processor, specifically for the receiving unit receive the third instruction or In the case that person the 4th instructs, determination is driven according to the target driving style；Third instruction and the 4th instruction are equal The servomechanism is used to indicate to be driven according to the target driving style.
In an optional implementation, the processor, specifically for meeting safety in the target Driving control parameter In the case where driving standard and friendship rule, controls the servomechanism and driven according to the target Driving control parameter.
In an optional implementation, which is also used to not meet safety in the target Driving control parameter In the case where driving standard or friendship rule, controls the servomechanism and driven according to real-time Driving control parameter；The reality When Driving control parameter be the servomechanism current decision go out Driving control parameter.
In an optional implementation, which is to believe the historical driving behavior, the history road conditions Breath and the history Driving control parameter are stored in as a whole in the database, and the history traffic information and the history are driven Sailing control parameter is respectively the traffic information and Driving control that the target vehicle acquires during driver's manual drive Parameter, the history traffic information is corresponding in time dimension with the history Driving control parameter, which is the mesh Mark the driving behavior that vehicle is determined according to the history traffic information and the history Driving control parameter.
The third aspect, the embodiment of the present application provide a kind of computer readable storage medium, which deposits Computer program is contained, which includes program instruction, which makes the processor when being executed by a processor The method for executing above-mentioned first aspect and any optional implementation.
Fourth aspect, the embodiment of the present application provide a kind of computer program product, which includes journey Sequence instruction, the program instruction make the letter processor execute above-mentioned first aspect and any optional when being executed by a processor The method of implementation.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application or in background technique below will be implemented the application Attached drawing needed in example or background technique is illustrated.
Fig. 1 is the functional block diagram of servomechanism 100 provided by the embodiments of the present application；
Fig. 2 is a kind of structural schematic diagram of automated driving system provided by the embodiments of the present application；
Fig. 3 is a kind of automatic Pilot method flow diagram provided by the embodiments of the present application；
Fig. 4 is a kind of road conditions matching provided by the embodiments of the present application and the matched schematic diagram of driving behavior；
Fig. 5 is another automatic Pilot method flow diagram provided by the embodiments of the present application；
Fig. 6 is a kind of driving data document generating method flow chart provided by the embodiments of the present application；
Fig. 7 is provided by the embodiments of the present application a kind of to obtain the schematic diagram of driving behavior by neural network learning；
Fig. 8 obtains the schematic diagram of driving behavior by neural network learning for another kind provided by the embodiments of the present application；
Fig. 9 is a kind of structural schematic diagram of servomechanism provided by the embodiments of the present application；
Figure 10 is a kind of structural schematic diagram of driving data file creating apparatus provided by the embodiments of the present application；
Figure 11 is a kind of structural schematic diagram of computer program product provided by the embodiments of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand the embodiment of the present application scheme, implement below in conjunction with the application Attached drawing in example, technical solutions in the embodiments of the present application is explicitly described, it is clear that described embodiment is only The embodiment of the application a part, instead of all the embodiments.
The description of the present application embodiment and claims and the term " first " in above-mentioned attached drawing, " second " and " Three " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.In addition, term " includes " " having " and their any deformation, it is intended that cover it is non-exclusive include, for example, containing series of steps or list Member.Method, system, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include unclear Other step or units that ground is listed or intrinsic for these process, methods, product or equipment.
Control module (motion in the automatic Pilot research institution of mainstream and manufacturer, in automated driving system Planner) for exporting the speed and angle of vehicle.And the output conduct of the decision-making module (behavior planner) of upstream The input of control module, input of the output of upstream task module (mission planner) as decision-making module.Each layer of mould Block can all receive the output of sensory perceptual system (perception system) as input.Each module is according to the output of up-stream module It is independent to calculate output with the input of sensing module.Each module will not upstream module feedback oneself output, entire automatic Pilot System is in pipeline system from top to bottom.The output of all modules is several under identical input in the automated driving system of such form There is the probability of deviation close to zero in all fixed values.That is, automatic driving vehicle is pressed under automatic driving mode Driver behavior is executed according to preset driving rule (i.e. default driving style).Automatic driving vehicle drives according to default style and carries out When driving, demand of the rider to comfort level has also thoroughly been abandoned while guaranteeing safety, can not advanced optimize it The driver behavior executed under automatic driving mode.Therefore, how to optimize automatic driving vehicle to execute under automatic driving mode Driver behavior to meet the needs of different user be current problem to be solved.Automatic Pilot provided by the embodiments of the present application Method can be applied to automatic Pilot scene.Automatic Pilot scene is simply introduced below.
Automatic Pilot scene 1: servomechanism (such as autonomous driving vehicle) is receiving user's input or user's hair After the instruction that the instruction servomechanism sent is driven according to certain driving style, driven according to the driving style It sails.
Automatic Pilot scene 2: driving data file is directed into using mobile phone or other portable equipments and is driven automatically by user Device is sailed, the automated driving system run on the servomechanism combines the history driving data pair in the driving data file Driver behavior advanced optimizes, and then improves experiencing by bus for the user.
Automatic Pilot scene 3: user is sent to servomechanism by terminal (such as mobile phone) and is instructed, the automatic Pilot Device obtains driving data file, the automated driving system knot run on the servomechanism from Cloud Server according to the instruction The history driving data closed in the driving data file advanced optimizes driver behavior, and then improves the body by bus of the user It tests.
Fig. 1 is the functional block diagram of servomechanism 100 provided by the embodiments of the present application.It in one embodiment, will be certainly Dynamic pilot instrument 100 is configured to completely or partially automatic driving mode.For example, servomechanism 100 can be in the portion of being in Itself is controlled while dividing in automatic driving mode, and can determine servomechanism 100 and its week by manual operation The current state of surrounding environment determines the probable behavior of other vehicles of at least one of surrounding enviroment, and determines other vehicles The corresponding confidence level of a possibility that executing probable behavior, servomechanism 100 is controlled based on identified information.In When servomechanism 100 is in automatic driving mode, servomechanism 100 can be set in no and people interaction In the case of operate.In one embodiment, servomechanism 100 is configured into manual drive mode.In servomechanism 100 When in manual drive mode, servomechanism 100 can be set to and be travelled under the control of people.
Servomechanism 100 may include each subsystem, such as advance system 102, sensing system 104, control system System 106, one or more peripheral equipments 108 and power supply 110, computer system 112 and user interface 116.Optionally, automatically Pilot instrument 100 may include more or fewer subsystems, and each subsystem may include multiple element.In addition, driving automatically The each subsystem and element for sailing device 100 can be by wired or radio interconnected.
Advance system 102 may include providing the component of dynamic movement for servomechanism 100.In one embodiment, Propulsion system 102 may include engine 118, energy source 119, transmission device 120 and tire/wheel 121.Engine 118 can be interior Fire engine, motor, air compression engine or the combination of other kinds of engine, for example, petrol engine and motor unit at it is mixed The mixed dynamic engine of dynamic engine, internal combustion engine and air compression engine composition.Energy source 119 is converted into mechanical energy by engine 118.
The example of energy source 119 include gasoline, diesel oil, other fuel based on petroleum, propane, other be based on compressed gas Fuel, ethyl alcohol, solar panel, battery and other power sources.Energy source 119 or servomechanism 100 Other systems provide energy.
Machine power from engine 118 can be transmitted to wheel 121 by transmission device 120.Transmission device 120 may include Gearbox, differential mechanism and drive shaft.In one embodiment, transmission device 120 can also include other devices, such as clutch Device.Wherein, drive shaft may include the one or more axis that can be coupled to one or more wheels 121.
Sensing system 104 may include several biographies for the information for sensing the environment about 100 periphery of servomechanism Sensor.For example, sensing system 104 may include that (positioning system can be global location (global to positioning system 122 Positioning system, GPS) system, be also possible to dipper system or other positioning systems), Inertial Measurement Unit (inertial measurement unit, IMU) 124, radar 126, laser range finder 128 and camera 130.Sensor system System 104 may also include monitored servomechanism 100 built-in system sensor (for example, in-car air quality monitor, Fuel ga(u)ge, oil thermometer etc.).Sensing data from one or more of these sensors can be used for test object And its individual features (position, shape, direction, speed etc.).This detection and identification are the safety of autonomous servomechanism 100 The key function of operation.
Positioning system 122 can be used for estimating the geographical location of servomechanism 100.IMU124 is used to accelerate based on inertia It spends to sense the variation of the position and orientation of servomechanism 100.In one embodiment, IMU124 can be accelerometer and The combination of gyroscope.
Radar 126 can sense the object in the surrounding enviroment of servomechanism 100 using radio signal.
Laser range finder 128 can sense the object in the environment that servomechanism 100 is located at using laser.One In a little embodiments, laser range finder 128 may include one or more laser sources, laser scanner and one or more detections Device and other systems component.In some embodiments, other than sensing object, laser range finder 128 can be laser thunder Up to (light detection and ranging, LiDAR).Laser radar, be with emit the position of detecting laser beam target, The radar system of the characteristic quantities such as speed.Laser radar can be to target (i.e. barrier) or some direction emission detection signal (laser Beam), the reflected signal of slave target (target echo) received is compared with transmitting signal then, makees proper treatment Afterwards, so that it may obtain target for information about, such as indicate the point cloud of the surface characteristic of target.Point cloud is in the same space referential The magnanimity point set of lower expression object space distribution and target surface characteristic.Point cloud in the application can be according to laser measurement The point cloud that principle obtains, the three-dimensional coordinate including each point.
Camera 130 can be used for capturing the multiple images of the surrounding enviroment of servomechanism 100.Camera 130 can be quiet State camera or video camera.Camera 130 can in real time or periodically capture the multiple of the surrounding enviroment of servomechanism 100 Image.
Control system 106 is to control the operation of servomechanism 100 and its component.Control system 106 may include various Element, including steering system 132, throttle 134, brake unit 136, computer vision system 140, route control system 142 and barrier avoid system 144.
Steering system 132 is operable to the direction of advance of adjustment servomechanism 100.Such as in one embodiment may be used Think steering wheel system.
Throttle 134 is used to control the service speed of engine 118 and controls the speed of servomechanism 100 in turn.
Brake unit 136 is for controlling the deceleration of servomechanism 100.Frictional force can be used to slow down in brake unit 136 Wheel 121.In other embodiments, the kinetic energy of wheel 121 can be converted to electric current by brake unit 136.Brake unit 136 can also Other forms are taken to slow down 121 revolving speed of wheel to control the speed of servomechanism 100.
Computer vision system 140 can handle and analyze the image that is captured by camera 130 to identify that automatic Pilot fills Set the object and/or feature in 100 surrounding enviroment.The object and/or feature may include traffic signals, road boundary and obstacle Object.Computer vision system 140 can be used object recognition algorithm, automatic Pilot method, restore structure (Structure in movement From Motion, SFM) algorithm, video tracking and other computer vision techniques.In some embodiments, computer vision system System 140 can be used for for paint environment map, tracking object, the speed for estimating object etc..Computer vision system 140 can make The image for the ambient enviroment that the point cloud and camera obtained with laser radar obtains, positions the position of barrier.
Route control system 142 is used to determine the travel route of servomechanism 100.In some embodiments, route Control system 142 is in combination with the data from sensor 138, GPS 122 and one or more predetermined maps for automatic Pilot Device 100 determines travel route.
Barrier avoid system 144 for identification, assess and avoid or otherwise cross servomechanism 100 Environment in potential barrier.
Certainly, in an example, control system 106 can increase or alternatively include in addition to shown or described that Component other than a little.Or a part of above-mentioned component shown can also be reduced.
Servomechanism 100 by peripheral equipment 108 and external sensor, other vehicles, other computer systems or It is interacted between user.Peripheral equipment 108 may include wireless communication system 146, vehicle-mounted computer 148, microphone 150 and/or Loudspeaker 152.
In some embodiments, the user that peripheral equipment 108 provides servomechanism 100 interacts with user interface 116 Means.For example, vehicle-mounted computer 148 can provide information to the user of servomechanism 100.User interface 116 can also operate Vehicle-mounted computer 148 receives the input of user.Vehicle-mounted computer 148 can be operated by touch screen.In other cases, outside Peripheral equipment 108 can provide the means communicated for servomechanism 100 with the other equipment for being located at car.For example, microphone 150 can receive audio (for example, voice command or other audio inputs) from the user of servomechanism 100.Similarly, loudspeaking Device 152 can export audio to the user of servomechanism 100.
Wireless communication system 146 can to wirelessly communicate with one or more equipment directly or via communication network. For example, 3G cellular communication or 4G cellular communication, such as LTE 5G cellular communication can be used in wireless communication system 146.Nothing Line communication system 146 can be communicated using WiFi and WLAN (wireless local area network, WLAN).In In some embodiments, wireless communication system 146 can utilize infrared link, bluetooth or ZigBee and equipment direct communication.Other nothings Wire protocol, such as various vehicular communication systems, for example, wireless communication system 146 may include one or more dedicated short-range communication (dedicated short range communications, DSRC) equipment, these equipment may include vehicle and/or roadside platform Public and/or private data communication between standing.
Power supply 110 can provide electric power to the various assemblies of servomechanism 100.In one embodiment, power supply 110 can Think rechargable lithium ion or lead-acid battery.It is to drive automatically that the one or more battery group of this battery, which can be configured to power supply, The various assemblies for sailing device 100 provide electric power.In some embodiments, power supply 110 and energy source 119 can be realized together, such as In some all-electric cars like that.
Some or all functions of servomechanism 100 are controlled by computer system 112.Computer system 112 can wrap At least one processor 113 is included, the execution of processor 113 is stored in non-transient computer as such as data storage device 114 Instruction 115 in readable medium.Computer system 112 can also be using distributed way control servomechanism 100 Multiple calculating equipment of individual components or subsystem.
Processor 113 can be any conventional processor, such as commercially available central processing unit (central Processing unit, CPU).As an alternative, which can be the special of the hardware based processor of such as ASIC or other Use equipment.Although Fig. 1 functionally illustrates other members of processor, memory and the computer system 112 in same block Part, but it will be apparent to an ordinarily skilled person in the art that the processor, computer or memory can actually include can be with Or multiple processors, computer or memory in identical physical enclosure can be not stored in.For example, memory can be with It is hard disk drive or other storage mediums in the shell for being different from computer system 112.Therefore, to processor or meter The reference of calculation machine will be understood to comprise to can or can not the processor of parallel work-flow or the collection of computer or memory The reference of conjunction.Step described herein, such as steering assembly and reduction assemblies are executed different from the use of single processor Some components each may have the processor of their own, which only carries out relevant to the function specific to component It calculates.
In various aspects described herein, processor can be located remotely from the servomechanism and automatic with this Pilot instrument carries out wireless communication.In other aspects, some operations in process described herein are driven automatically being arranged in It sails and is executed on the processor in device and other, executed by teleprocessing unit, the necessary step of single operating is executed including taking Suddenly.
In some embodiments, data storage device 114 may include instruction 115 (for example, programmed logic), and instruction 115 can It is executed by processor 113 to execute the various functions of servomechanism 100, including those described above function.Data are deposited Storage device 114 also may include additional instruction, including to propulsion system 102, sensing system 104, control system 106 and periphery One or more instructions for sending data, receiving from it data, interacting and/or control it in equipment 108.
Other than instruction 115, data storage device 114 can also storing data, such as road-map, route information, vehicle Position, direction, speed and other information.These information can servomechanism 100 autonomous, semi-autonomous and/or It is used during being operated in manual mode by servomechanism 100 and computer system 112.
User interface 116, for providing information to the user of servomechanism 100 or receiving from it information.Optionally, User interface 116 may include one or more input-output apparatus in the set of peripheral equipment 108, such as wirelessly communicate System 146, vehicle-mounted computer 148, microphone 150 and loudspeaker 152.
Computer system 112 can be based on from each subsystem (for example, advance system 102, sensing system 104 and control System 106) and control the function of servomechanism 100 from the received input of user interface 116.For example, department of computer science System 112 can utilize the input from control system 106 so as to control steering unit 132 avoid by sensing system 104 and barrier The barrier for hindering object that system 144 is avoided to detect.In some embodiments, computer system 112 is operable to automatic Pilot Many aspects of device 100 and its subsystem provide control.
Optionally, one or more of these above-mentioned components can be installed separately or be associated with servomechanism 100.Example Such as, data storage device 114 can be separately present with servomechanism 100 partially or completely.Said modules can be by having Line and/or wireless mode are communicatively coupled together.
Optionally, said modules are an example, and in practical application, the component in above-mentioned modules is possible to basis Actual needs increases or deletes, and Fig. 1 should not be construed as the limitation to the embodiment of the present application.
In the autonomous driving vehicle that road is advanced, such as servomechanism 100 above, can identify in its ambient enviroment Object to determine adjustment to present speed.The object can be other vehicles, traffic control equipment or other types Object.In some instances, it can independently consider the object of each identification, and the respective characteristic based on object, it is all Such as its present speed, acceleration, the spacing with vehicle, may be used to determine the autonomous driving vehicle speed to be adjusted.
Optionally, servomechanism 100 or the calculating equipment (meter of such as Fig. 1 associated with servomechanism 100 Calculation machine system 112, computer vision system 140, data storage device 114) it can characteristic based on the object identified and week The state (for example, traffic, rain, the ice on road etc.) in collarette border predicts the behavior of the object of the identification.Optionally, often One object identified all relies on mutual behavior, therefore all can also consider to come together by all objects identified Predict the behavior of the object individually identified.Servomechanism 100 can the behavior based on the object of the identification of prediction come Adjust its speed.In other words, autonomous driving vehicle can determine vehicle by needs based on the behavior for the object predicted (for example, accelerate, slow down or stop) what stable state be adjusted to.In this process, it is also contemplated that other factors come Determine the speed of servomechanism 100, such as, lateral position of the servomechanism 100 in the road of traveling, road Curvature, static state and degree of approach of dynamic object etc..
Other than providing the instruction of speed of adjustment autonomous driving vehicle, calculating equipment can also provide modification and drive automatically The instruction of the steering angle of device 100 is sailed, so that autonomous driving vehicle follows given track and/or maintains and automatic Pilot vapour The horizontal and vertical distance of safety of object (for example, car in adjacent lane on road) near vehicle.
Above-mentioned servomechanism 100 can for car, truck, motorcycle, bus, ship, aircraft, helicopter, Grass trimmer, entertainment car, recreation ground vehicle, construction equipment, electric car, golf cart, train and trolley etc., the present invention are implemented Example is not particularly limited.
Fig. 1 describes the functional block diagram of servomechanism 100, and a kind of automated driving system 101 is described below.Fig. 2 is A kind of structural schematic diagram of automated driving system provided by the embodiments of the present application.Fig. 1 and Fig. 2 be from different angles come describe from Dynamic pilot instrument 100.As shown in Fig. 2, computer system 101 includes processor 103,105 coupling of processor 103 and system bus It closes.Processor 103 can be one or more processor, wherein each processor can include one or more processing Device core.Display adapter (video adapter) 107, display adapter can drive display 109, display 109 and system Bus 105 couples.System bus 105 is coupled by bus bridge 111 and input and output (I/O) bus 113.I/O interface 115 and I/ The coupling of O bus.I/O interface 115 and a variety of I/O equipment are communicated, for example input equipment 117 is (such as: keyboard, mouse, touch screen Deng), multimedia disc (media tray) 121, for example, CD-ROM, multimedia interface etc..Transceiver 123 (can send and/or connect By radiocommunication signals), camera 155 (can capture scape field and dynamic digital video image) and external USB interface 125. The interface being optionally connected with I/O interface 115 can be USB interface.
Wherein, processor 103 can be any conventional processors, including reduced instruction set computing (" RISC ") processor, Complex instruction set calculation (" CISC ") processor or combinations of the above.Optionally, processor can be such as specific integrated circuit The dedicated unit of (" ASIC ").Optionally, processor 103 can be neural network processor (Neural-network ProcessingUnit, NPU) either neural network processor and above-mentioned conventional processors combination.Optionally, processor 103 are mounted with a neural network processor.
Computer system 101 can be communicated by network interface 129 and software deployment service device 149.Network interface 129 is Hardware network interface, for example, network interface card.Network 127 can be external network, such as internet, be also possible to internal network, such as Ethernet or virtual private net.Optionally, network 127 can also be wireless network, such as WiFi network, cellular network Deng.
Hard disk drive interface and system bus 105 couple.Hardware driving interface is connected with hard disk drive.Installed System Memory 135 and system bus 105 couple.The data for operating in Installed System Memory 135 may include the operating system of computer system 101 137 and application program 143.
Operating system includes shell (Shell) 139 and kernel (kernel) 141.Shell 139 is between user and operating system Kernel (kernel) between an interface.Shell 139 is outmost one layer of operating system.Shell 139 manages user and operation Interaction between system: waiting the input of user, and the input of user is explained to operating system, and handles various The output result of operating system.
Kernel 141 in operating system for managing those of memory, file, peripheral hardware and system resource part by forming. Directly interacted with hardware, operating system nucleus usually runs process, and provides the communication between process, provide CPU time slice management, Interruption, memory management, IO management etc..
Application program 141 includes automatic Pilot relative program, for example, management servomechanism and the interaction of road barrier Program, control the traffic route of servomechanism or the program of speed, control servomechanism 100 and road other The program of servomechanism interaction.Application program 141 exists in software deployment service device (deploying server) 149 System on.In one embodiment, when needing to be implemented application program 141, computer system 101 can take from software deployment Business device 149 downloads application program 141.
Sensor 153 is associated with computer system 101.Sensor 153 is used to detect the ring around computer system 101 Border.For example, sensor 153 can be with detecting animal, automobile, barrier and crossing etc., and further sensor can be with Detect above-mentioned animal, automobile, the environment around the objects such as barrier and crossing, such as: the environment around animal, for example, Other animals occurred around animal, weather condition, the brightness etc. of ambient enviroment.Optionally, if computer system 101 In on servomechanism, sensor be can be camera (i.e. camera), laser radar, infrared inductor, chemical detector, Microphone etc..The letter that sensor 153 will be sensed in activation according to preset interval sensitive information and real-time or near real-time Breath is supplied to computer system 101.Optionally, sensor may include laser radar, which can be in real time or close The point cloud that will acquire in real time is supplied to computer system 101.Optionally, camera is in real time or the figure that will acquire of near real-time ground As being supplied to computer system 101.
Optionally, in various embodiments described herein, computer system 101 can be located remotely from servomechanism Place, and can be carried out wireless communication with servomechanism.Transceiver 123 can acquire automatic Pilot task, sensor 153 Sensing data and other data be sent to computer system 101；The control that the transmission of computer system 101 can also be received refers to It enables.The received control instruction from computer system 101 of transceiver can be performed in servomechanism, and executes corresponding drive Operation.In other aspects, some processes as described herein execute on the processor being arranged in automatic driving vehicle, Qi Tayou Teleprocessing unit executes, and executes the required movement of single manipulation including taking.
Optionally, servomechanism acquires traffic information by multiple sensors during automatic Pilot；According to working as Preceding road conditions and navigation information drive according to the target driving style that user indicates.In the embodiment of the present application, user can be with Correspondingly driving style is selected according to their own needs, and servomechanism drives according to the driving style that user selects. For example, servomechanism has a variety of driving styles such as radical, careful and common, and the servomechanism is different The driving behavior executed under driving style is not exactly the same.Optionally, user can by driving data file from portable equipment or Person's server is directed into servomechanism, and the automated driving system run on the servomechanism combines driving data text History driving data in part advanced optimizes driving behavior, and then improves experiencing by bus for the user.Be described below how The automatic Pilot method driven according to the target driving style that user indicates.
Fig. 3 is a kind of automatic Pilot method flow diagram provided by the embodiments of the present application, as shown in figure 3, this method can include:
301, servomechanism obtains current traffic information.
Servomechanism can acquire traffic information by multiple sensors in driving procedure, and to current collected Various traffic informations are integrated to obtain the current traffic information.Specifically, the servomechanism is in the process of moving, it can To collect telecommunication flow information and surface conditions, such as traffic sign, traffic lights, lane by the multiple sensors installed from vehicle The initial data such as line, surrounding vehicles, pedestrian and obstacle information.In the application, refer to servomechanism from vehicle.Automatically it drives The sensor for sailing device installation may include laser radar, millimetre-wave radar, ultrasonic radar, monocular or binocular camera shooting head etc..Respectively Information of road surface can reflect different road conditions.Traffic sign can indicate the road speed limit upper limit, speed limit lower limit, and front stops Driving etc..Traffic lights may indicate whether to stop, and turns left or turns right.Lane line can indicate vehicle heading, turning half Diameter, both sides track direction, if allow lane-change etc..Vehicle, pedestrian and barrier can indicate barrier with respect to car's location, Lane information, relative velocity etc..Servomechanism, which obtains current traffic information, can be the servomechanism to current All initial data (i.e. original traffic information) that moment is collected into the working processes such as are merged, are clustered, are abstracted to be worked as The traffic information inscribed when preceding, i.e., current traffic information.
302, servomechanism is according to current traffic information, and inquiry whether there is and current traffic information from database The target Driving control parameter to match.
The target Driving control parameter includes the history Driving control parameter of target vehicle, the history Driving control parameter packet Include the Driving control parameter that the target vehicle is driven according to target driving style.The target is stored in the database The history Driving control parameter of vehicle, one or more traffic informations and the current traffic information and the target Driving control The matching relationship of parameter.In practical applications, various road conditions information and these traffic information phases can be stored in database The Driving control parameter matched determines the Driving control parameter to match with current traffic information by inquiring the database.
The target vehicle can be the servomechanism, may not be the servomechanism.Automatic Pilot dress It sets before executing step 302, be stored with or get the history Driving control parameter and the history from other equipment The matching relationship of Driving control parameter and traffic information in Driving control parameter.Driving control parameter may include longitudinal speed The parameters such as degree, lateral velocity, acceleration, corner.In some embodiments, history Driving control parameter can be target vehicle and exist Collected Driving control parameter during driver's manual drive is also possible to drive the target vehicle manually in driver The Driving control parameter that collected Driving control parameter is further processed during sailing.Optionally, to automatic Pilot The Driving control parameter of user of the device under manual drive mode is further processed including deleting some duplicate Driving controls Parameter etc..
303, if it exists, then servomechanism obtains target Driving control parameter, and according to target Driving control parameter It is driven with target driving style.
Servomechanism drive with target driving style according to the target Driving control parameter can be this automatically Automated driving system on pilot instrument is controlled according to the target Driving control parameter from vehicle.In practical applications, multiply Visitor can select corresponding driving style according to the driving habit of oneself, and servomechanism matches according to the driving style History driving data currently performed driving strategy is advanced optimized.
In some embodiments, servomechanism is driven according to target Driving control parameter with target driving style It can be in the case where the target Driving control parameter meets safe driving standard and hands over rule, joined according to the target Driving control Number is driven with target driving style.In some embodiments, safe driving standard is not met in target Driving control parameter Or in the case where handing over rule, servomechanism is driven according to real-time Driving control parameter, which is should The Driving control parameter that servomechanism goes out in current decision.In practical applications, servomechanism is getting and is working as After the target Driving control parameter that preceding road conditions match, judge whether the target Driving control parameter meets safe driving standard It is advised with handing over；If so, being driven according to the target Driving control parameter, if it is not, then being carried out according to real-time Driving control parameter It drives.
304, if it does not exist, then servomechanism is driven according to real-time Driving control parameter with current driving style It sails.
The real-time Driving control parameter is that the servomechanism is joined according to the Driving control that default decision-making mechanism decision goes out Number.Specifically, the real-time Driving control parameter can be the automated driving system of servomechanism operation currently current The Driving control parameter that road conditions making policy decision goes out.In practical applications, if not there is no the mesh to match with current road conditions in database When marking Driving control parameter, then servomechanism is determined according to the automated driving system (corresponding to default decision-making mechanism) of its operation The real-time Driving control parameter that plan goes out is driven.In the application, current driving style corresponds to following default driving style. It is according to current driving style that servomechanism, which drive according to the Driving control parameter that default decision-making mechanism decision goes out, It is driven.Currently, servomechanism is to determine in real time under automatic Pilot model according to the automated driving system of its operation The Driving control parameter that plan goes out is driven.That is, servomechanism is certainly in currently employed automatic Pilot technology The driver behavior executed under dynamic model formula is controlled by automated driving system completely, does not take into account that the driving habit of passenger.
In the embodiment of the present application, servomechanism is inquiring the target Driving control parameter to match with current road conditions Afterwards, it is driven according to the target Driving control parameter, rather than is driven according to the Driving control parameter that its current decision goes out It sails；Enable the servomechanism using previous history Driving control parameter to its current decision go out driver behavior into Row optimization.Since target Driving control parameter is to meet the history Driving control parameter of the driving habit of passenger, gone through using these History Driving control parameter optimizes the driver behavior of the servomechanism, and the driving that can better meet passenger is practised It is used.
It is not described in detail in the method for Fig. 1 and how to determine and driven according to target driving style, automatic Pilot dress is described below Set some optional implementations for determining and being driven according to target driving style.
In an optional implementation, it is automatic to determine that the case where being driven according to target driving style may is that Pilot instrument receive user input third instruction or from third terminal the 4th instruction in the case where, determine according to The target driving style is driven.Third instruction and the 4th instruction are used to indicate the servomechanism according to the mesh Mark driving style is driven.Optionally, user is defeated by other input interfaces on vehicle-mounted computer or servomechanism Enter third instruction.The third terminal can be the portable equipments such as mobile phone, tablet computer.In practical applications, the third terminal It is communicated by wirelessly or non-wirelessly mode with servomechanism, and sends the 4th instruction to the servomechanism.It can Choosing, servomechanism supports a variety of driving styles, such as venture, with caution, the driving styles such as default, user can be by the Three instructions or the 4th instruction select the target driving style in a variety of driving styles.It is appreciated that servomechanism branch In a variety of driving styles held, each driving style in addition to defaulting driving style is corresponded under a kind of manual drive mode History driving data (corresponding to driving style file hereafter).Optionally, the driving style database of servomechanism In include multiple driving data files, the corresponding label of each driving data file, each label shows its corresponding driving The driving style that data file represents, passenger can enter driving style selection interface when using automated driving system, on the boundary Face selects certain driving data file according to demand.Wherein, passenger can select certain driving by the driving style selection interface Data file.The driving style selection interface can be the interface that the display equipment on servomechanism is shown, be also possible to The interface that the terminal for establishing communication connection with the servomechanism is shown.Servomechanism is carried out according to default driving style The automated driving system that driving can be on the servomechanism is driven according to current road conditions and navigation information completely, Without considering the history driving data under manual drive mode.
In this implementation, servomechanism is stored with it and drives according to the history that target driving style is driven Data, user only need to select required driving style from a variety of driving styles that the servomechanism is supported, operation letter It is single.
In an optional implementation, determines that the case where being driven according to target driving style may is that and obtaining After obtaining driving data file, determination is driven according to the target driving style.The driving data file includes that this drives automatically It sails history traffic information, history Driving control parameter and history that device is driven according to the target driving style and drives row At least one of in.History traffic information, history Driving control parameter and historical driving behavior can be understood as history and drive Sail data.Optionally, the mode for obtaining driving data file, which can be, receives the driving data file from first terminal；It can also To be to obtain the driving data file from server after receiving the first instruction from second terminal.Wherein, first finger Order is used to indicate the servomechanism and obtains the driving data file from the server.The first terminal and the second terminal can To be the portable equipments such as mobile phone, tablet computer.Optionally, after first terminal and servomechanism establish communication connection, to this Servomechanism imports the driving data file.For example, first terminal is connect by the USB that data line connects servomechanism Mouthful, and driving data file is imported to the servomechanism by the USB interface.Optionally, server is stored at least one Kind driving data file, every kind of driving data file includes that user drives some servomechanism under manual drive mode History driving data；Servomechanism can obtain corresponding drive from the server according to the instruction from second terminal Data file.Optionally, the history driving data that the driving data file that servomechanism obtains includes is another vehicle History driving data of the same servomechanism under manual drive mode, the servomechanism can be used directly History Driving control parameter optimization its driver behavior in the driving data file.Optionally, what servomechanism obtained drives Sail the history of servomechanism that history driving data that data file includes is another model under manual drive mode Driving data, which converts the history Driving control parameter in the driving data file can to obtain it Directly as the history Driving control parameter of reference.For example, the first servomechanism corresponds to the first vehicle, this first drives automatically The driving data file for sailing device acquisition includes history of the second servomechanism of the second vehicle under manual drive mode History Driving control Parameter Switch in the driving data file is the first vehicle by driving data, first servomechanism Corresponding history Driving control parameter, wherein first vehicle is different with second vehicle.First servomechanism in this way Its driver behavior directly can be optimized using the history Driving control parameter after conversion.
In this implementation, driving data file is directed into servomechanism by user, in order to the automatic Pilot Device advanced optimizes the driver behavior under automatic driving mode according to the history driving data in the driving data file, can To meet the driving style of different user.
The target Driving control parameter for how obtaining and matching with current road conditions is not described in detail in the method for Fig. 1, i.e., is not described in detail The implementation of step 302.The implementation for obtaining the target Driving control parameter to match with current road conditions is described below.
In some embodiments, servomechanism obtain the target Driving control parameter that matches with current road conditions can be with It is: first determines the target traffic information to match in history traffic information with current traffic information；History Driving control is obtained again The Driving control parameter to match in parameter with the target traffic information, to obtain the target Driving control parameter.Automatic Pilot Device is stored with the history traffic information and the history Driving control parameter, alternatively, the servomechanism is executing step 302 Before, from other equipment, such as Cloud Server, the history traffic information and the history Driving control parameter are got.Optionally, The history traffic information and the history Driving control parameter are stored in the driving style data of servomechanism.
The target traffic information for how determining and matching in history traffic information with current traffic information is first introduced below.
Optionally, servomechanism determines the target road conditions letter to match in history traffic information with current traffic information Breath, which may is that, to be determined in the history traffic information with the current traffic information similarity highest and similarity is more than similarity threshold A history traffic information, as the target traffic information to match with the current traffic information.The target traffic information can Think a history traffic information in the driving style database.The current traffic information and the target traffic information include Entry is identical.That is, the current traffic information is identical as the content that the target traffic information includes.For example, currently Traffic information includes characterizing the first kind parameter of current road conditions to the tenth class parameter, and target traffic information also includes first kind ginseng It counts to the tenth class parameter.It in practical applications, include a plurality of history traffic information, every history road in driving style database Condition information is identical as the entry that current traffic information includes.Table 1 illustrates history traffic information and real-time road condition information (current road Condition information) one citing.
Table 1
As it can be seen from table 1 history traffic information is identical with the entry that current traffic information includes.Servomechanism exists Determine driven according to target driving style after, can by current traffic information respectively with every in driving style data History traffic information is matched, to find out the target traffic information to match with the current traffic information.The target road conditions Information can be in the driving style database with the current highest history traffic information of traffic information similarity.It is optional , carrying out matched process to a history traffic information in current traffic information and driving style database may is that meter The similarity for calculating each item data in current traffic information and this history traffic information, if the similarity of every item data is more than The similarity threshold, it is determined that the current traffic information and this history traffic information match.The similarity threshold can be 0.8,0.9,095 etc..Optionally, the corresponding similarity threshold of every item data is different.For example, front truck is away from corresponding first threshold Value, navigation direction drift angle correspond to second threshold, and the first threshold is different with the second threshold.If including in driving style database Two or more history traffic information to match with current traffic information, then will be with the current traffic information similarity most A high history traffic information is as the target traffic information.
The Driving control ginseng for how obtaining and matching in history Driving control parameter with the target traffic information is described below Number.
In some embodiments, servomechanism obtain the target Driving control parameter that matches with current road conditions can be with It is to obtain the Driving control parameter to match in history Driving control parameter with the target traffic information, to obtain target driving Control parameter.Optionally, servomechanism can store each history road conditions and history in history traffic information and drive control The corresponding relationship of each Driving control parameter in parameter processed can determine any bar history traffic information pair using the corresponding relationship The history Driving control parameter answered.Table 2 is the mapping table of history traffic information and history Driving control parameter.
Table 2
History traffic information History Driving control parameter
First history traffic information First history Driving control parameter
Second history traffic information Second history Driving control parameter
…… …….
M history traffic information M history Driving control parameter
Into last line, every row includes a history traffic information and believes with this history road conditions second row of table 2 The matched history Driving control parameter of manner of breathing.That is, the first history traffic information to M history traffic information successively Match with the first history Driving control parameter to M history Driving control parameter.M is the integer greater than 1.In practical application In, servomechanism can first determine the history traffic information to match in history traffic information with current traffic information, The history Driving control parameter to match in history Driving control parameter with this history traffic information is determined again.For example, Servomechanism determines that current traffic information matches with the second history traffic information, it is determined that the second history traffic information (i.e. target traffic information) corresponding second history Driving control parameter is the target Driving control ginseng to match with current road conditions Number.
In this implementation, servomechanism can quickly and accurately obtain the driving to match with current road conditions Control parameter.
Servomechanism is carried out driving under current road conditions according to target Driving control parameter and be may be implemented: along current road Road traveling, to the left road lane-change, to the right road lane-change parking, follow the bus, are reversed end for end, are parked, avoidance etc. in emergency brake, road Driving behavior.However, when servomechanism carry out driving under current road conditions according to target Driving control parameter it is achievable Second driving behavior and automated driving system drive according to first for meeting safe driving standard and handing over rule that current road conditions determine When behavior difference, executes second driving behavior and be likely to not meet safe driving standard or hand over rule.Being described below a kind of can have Effect avoids carrying out under current road conditions by target Driving control parameter driving do not meet safe driving standard or hand over rule in the way of.
Optionally, servomechanism performs the following operations before executing step 303: determining and drives according to the default Style carries out driving the first pending driving behavior under road conditions in this prior；Determine in driving style database with the current road The second driving behavior that condition matches, second driving behavior are that the servomechanism is deserving according to the target driving style The historical driving behavior driven under preceding road conditions；In first driving behavior situation identical with second driving behavior, Obtain the target Driving control parameter to match with the current road conditions.If be appreciated that first driving behavior and this second Driving behavior is different, then the Driving control parameter to match with current road conditions is obtained not from history Driving control parameter, but It is driven according to default driving style.Optionally, the classification of the historical driving behavior in driving style database with drive automatically The classification for sailing the driving behavior (i.e. system driving behavior) that system can be made according to current road conditions is identical.That is, history is driven The classification for sailing behavior is consistent with the classification of system driving behavior, every kind of classification by digital representation, such as: 0 indicate along present road It travels, 1 indicates to survey road lane-change to the left, and road lane-change, 3 expressions are stopped to the right for 2 expressions, and 4 indicate follow the buses, and 5 indicate to reverse end for end, 6 Expression is parked, and 7 indicate emergency brake, and 8 indicate avoidance etc. in road.In practical applications, if indicate automated driving system according to The number for the driving behavior that current road conditions are made is different with the number of the current matched historical driving behavior of road conditions from expression, then System driving behavior is different from historical driving behavior.
In this implementation, the matched historical driving behavior of current road conditions with currently determine under current road conditions to In the identical situation of the driving behavior of execution, the Driving control parameter to match with the current road conditions is obtained；It is possible to prevente effectively from The driving behavior that servomechanism executes does not meet safe driving standard or hands over rule, can avoid from history Driving control parameter yet The operation for the Driving control parameter that middle acquisition matches with current road conditions.
The second driving behavior for how determining and matching with current road conditions is described below.A kind of optional implementation is such as Under: in the case where in the driving style database including the target traffic information to match with the current traffic information, determine Corresponding second driving behavior of the target traffic information in the driving style database；The driving style database includes at least One history traffic information, and it is somebody's turn to do the corresponding relationship of at least one history traffic information and driving behavior.Servomechanism Corresponding second driving behavior of the target traffic information can be determined according to the corresponding relationship.Since previous embodiment has been retouched The implementation for having stated the determining target traffic information to match with current traffic information mainly describes how to determine driving below Corresponding second driving behavior of the target traffic information in style data library.Table 3 is that a kind of history traffic information and history drive The mapping table of behavior.
Table 3
History traffic information Historical driving behavior
First history traffic information First historical driving behavior
Second history traffic information Second historical driving behavior
…… …….
M history traffic information M historical driving behavior
3 second row of table into last line, every row include a history traffic information and with this history traffic information The historical driving behavior to match.That is, the first history traffic information is to M history traffic information successively with first Historical driving behavior to M historical driving behavior matches.M is the integer greater than 1.In practical applications, servomechanism It can first determine the history traffic information to match in history traffic information with current traffic information, then determine that history drives row The historical driving behavior to match in this history traffic information.For example, if servomechanism determination is worked as Preceding traffic information matches with the second history traffic information, then the second history traffic information (i.e. target traffic information) is corresponding Second historical driving behavior is the second driving behavior to match with current road conditions.Optionally, 3 second row of table is into last line The history traffic information that any two row includes is different, and 3 second row of the table history that any two row includes into last line drives Behavior is identical or different.That is, the different corresponding historical driving behaviors of history traffic information can be identical.
Optionally, servomechanism can be stored with history traffic information and history Driving control parameter corresponding relationship, The correspondence of the corresponding relationship and history Driving control parameter and historical driving behavior of history traffic information and historical driving behavior Relationship.Table 4 is the mapping table of a kind of history traffic information, historical driving behavior and history Driving control parameter.It is optional , servomechanism obtain driving data file includes these three corresponding relationships.
Table 4
History traffic information History Driving control parameter Historical driving behavior
First history traffic information First history Driving control parameter First historical driving behavior
Second history traffic information Second history Driving control parameter Second historical driving behavior
…… ……. …….
M history traffic information M history Driving control parameter M historical driving behavior
Table 4 contains the corresponding relationship of history traffic information Yu history Driving control parameter, history Driving control parameter with The corresponding relationship of historical driving behavior and the corresponding relationship of history traffic information and historical driving behavior correspond to pass for totally three kinds System.Optionally, servomechanism can store the table 4 or characterize the content for three kinds of corresponding relationships that the table 4 includes.It answers Understand, servomechanism can quickly and accurately determine that any history traffic information is corresponding according to these three corresponding relationships Historical driving behavior and the corresponding history Driving control parameter of any history traffic information.
In this implementation, servomechanism can quickly and accurately obtain the driving to match with current road conditions Controlling behavior.
Servomechanism is obtaining the target Driving control ginseng to match with current road conditions it can be seen from foregoing description Before number, need current traffic information being matched (i.e. road conditions matching) with history road conditions in driving style database to obtain Target traffic information, and the first driving behavior pending under current road conditions and the target that servomechanism is determined Corresponding second driving behavior of traffic information is matched (i.e. driving behavior matching).Below with reference to road conditions matching and driving behavior Matched schematic diagram, to further describe the two matching process.
Fig. 4 is a kind of road conditions matching provided by the embodiments of the present application and the matched schematic diagram of driving behavior.In Fig. 4, black Rectangle indicates that, from vehicle, arrow indicates the driving direction of vehicle.In the left-half of Fig. 4, in current road conditions and history road conditions The matching of target road conditions, automated driving system drive in the driving behavior history corresponding with the target road conditions of current road conditions making policy decision Behavior matching, servomechanism obtain the target Driving control parameter to match with current road conditions and drive according to the target and control Parameter processed is driven.In the right half part of Fig. 4, current road conditions are matched with the reference road conditions in history road conditions, automatic Pilot System is mismatched with this with reference to the corresponding historical driving behavior of road conditions in the driving behavior of current road conditions making policy decision, automatic Pilot dress It sets and is driven according to the driving behavior of automated driving system decision.It should be understood that the matching process in Fig. 4 is only a kind of example. From fig. 4, it can be seen that servomechanism before obtaining target Driving control parameter, needs to complete road conditions matching and drives row For matching.
In this implementation, the matched historical driving behavior of current road conditions with currently determine under current road conditions to In the identical situation of the driving behavior of execution, the Driving control parameter to match with the current road conditions is obtained；It is possible to prevente effectively from The driving behavior that servomechanism executes does not meet safe driving standard or hands over rule.
Optionally, servomechanism can be checked and be driven under current road conditions according to target before executing step 303 Whether control parameter meets safe driving standard and hands over rule.Optionally, the moderator on servomechanism is according to two elements Judge whether target Driving control parameter is used as last output, an element is traffic specification, another element is safety. In the case where the two elements all meet, servomechanism (is driven according to target and is controlled using history Driving control parameter Parameter processed is driven), otherwise, using automated driving system output Driving control parameter (i.e. according to default drive parameter into Row drives).Optionally, the function of moderator is realized by computer system 112.Be described below how to check under current road conditions by It is driven whether to meet safe driving standard and hand over according to target Driving control parameter and be advised.
1, traffic specification inspection: the friendship rule of present frame (i.e. current time) are by speed limit, lower limit, vehicle towards range, The series of parameters such as vehicle position section indicate that the above parameter is calculated according to current road condition data.
Speed inspection: the velocity amplitude in target Driving control parameter is being handed in rule speed interval；
Vehicle is towards inspection: the direction of next frame vehicle opposite lane is calculated according to target Driving control parameter, judgement is It is no towards in range；
Vehicle location inspection: the relative position in lane where calculating next frame vehicle according to target Driving control parameter is sentenced Break whether in the section of position.
2, security inspection: security inspection calculates next frame vehicle and other barriers according to target Driving control parameter Relative distance.Relative distance is greater than minimum threshold and then meets safety.When minimum threshold is reacted by current vehicle speed and system maximum Between be calculated.Emergency brake is implemented in value expression from vehicle in great distance range can guarantee from vehicle safety.Above-mentioned friendship Logical normalized checking and security inspection are only a kind of examples provided by the embodiments of the present application, it should be understood that other check that target drives control Whether parameter processed meets safe driving standard and the mode of rule is handed over to also belong to the protection scope of the application.Offer one is provided The judgement example of arbiter.Table 5 illustrates current road conditions and system information.Table 6 illustrates target Driving control parameter.
Table 5
Table 6
Longitudinal velocity Acceleration Drift angle
35 1.3 1.3
According to above data, arbiter can determine that the longitudinal velocity in target Driving control parameter is less than road limit Speed does not violate friendship rule；Front obstacle calculates according to longitudinal speed and system maximum response time at a distance of 10 meters, does not there is safety Risk.Therefore, arbiter judges that target Driving control parameter meets safe driving standard and hands over rule, which is joined Number is sent to control system 106, in order to which control system 106 is driven according to the target Driving control parameter.Optionally, if Arbiter judges that target Driving control parameter does not meet safe driving standard or hands over rule, then servomechanism is automatic according to it The Driving control parameter of control loop decision is driven.It should be understood that servomechanism is according to its automated driving system decision Driving control parameter drive must meet safe driving standard and hand over rule.
Servomechanism is by checking whether meet safe driving according to target Driving control parameter under current road conditions Standard and friendship rule, in order to which its driver behavior meets safe driving standard and hands over rule.
Foregoing examples describe the modes that servomechanism combination history driving data realizes automatic Pilot method.For More clearly describe how to optimize automatic Pilot in conjunction with history driving data of the servomechanism under manual drive mode The driver behavior of system is further described below by specific example.
Fig. 5 is another automatic Pilot method flow diagram provided by the embodiments of the present application, as shown in figure 5, this method can wrap It includes:
501, servomechanism acquires current traffic information.
Optionally, which acquires traffic information by multiple sensors, and to collected original road Condition information does working process, to obtain to accurately reflect the current traffic information of current road conditions.
502, the automated driving system on servomechanism goes out pending first driving behavior according to current road conditions decision.
503, the automated driving system on servomechanism goes out pending default Driving control according to current road conditions decision Parameter.
Step 501 to step 503 is the operation that automated driving system is realized.In the application, Driving control parameter is defaulted It is identical concept with real-time Driving control parameter, is the Driving control that servomechanism goes out according to default decision-making mechanism decision Parameter.
504, servomechanism judges in history traffic information with the presence or absence of the target road conditions to match with current road conditions Information.
If so, executing step 505；If it is not, executing step 510.
505, servomechanism determines the second driving behavior to match in historical driving behavior with target traffic information.
506, servomechanism judges whether the first driving behavior and the second driving behavior are identical.
If so, executing step 507；If it is not, executing step 510.
507, servomechanism obtain history Driving control parameter in target traffic information and/or the second driving behavior The target Driving control parameter to match.
508, servomechanism judges to be driven whether meet safe driving standard according to target Driving control parameter It is advised with handing over.
If so, executing step 509；If it is not, executing step 510.
509, servomechanism is driven according to target Driving control parameter.
510, servomechanism is driven according to default Driving control parameter.
From fig. 5, it can be seen that step 501 to step 503, step 510 is servomechanism according to automated driving system The driving behavior of decision and Driving control parameter are driven, corresponding default driving style；Step 504 to step 509 is certainly Dynamic pilot instrument is driven according to history driving data, corresponding target driving style.In this embodiment, servomechanism In motion according to current road condition data, system driving behavior (i.e. the driving behavior of automated driving system decision) and history road Condition data, historical driving behavior are matched one by one；After after successful match, current time corresponding history control is judged by moderator Whether data processed meet safety and traffic rules, meet and then control data to vehicle traction transmission control instruction, no according to history Meet and then sends automatic Pilot control instruction to vehicle traction.
The embodiment of the present application, servomechanism combination history Driving control advanced optimize its driver behavior, are protecting Demonstrate,prove its driver behavior meet safe driving standard and hand over rule under the premise of, the personalized driving requirement of different user can be met.
Foregoing examples describe the automatic Pilot method for the driver behavior for how optimizing servomechanism, retouches below The method for how obtaining the file of the driving data in previous embodiment stated.
Fig. 6 is a kind of driving data document generating method flow chart provided by the embodiments of the present application, as shown in fig. 6, the party Method can include:
601, servomechanism obtains history traffic information and history Driving control parameter.
The history traffic information and the history Driving control parameter are respectively servomechanism in driver's manual drive During the traffic information that acquires and Driving control parameter, the history traffic information and the history Driving control parameter when Between dimension it is corresponding.Optionally, the executing subject of Fig. 6 method is electronic equipment, such as Cloud Server, which can be from certainly Dynamic pilot instrument obtains history traffic information and history Driving control parameter, and executes step 602 and step 603 to be driven Sail data file.
602, servomechanism determines that history drives row according to the history traffic information and the history Driving control parameter For.
Optionally, which includes N traffic information, which includes that N item drives control Parameter processed, the N traffic information and the N Driving control parameter correspond；This is according to the history traffic information and the history Driving control parameter determines that historical driving behavior includes: according to reference traffic information and to refer to Driving control parameter, determines reference Driving behavior.Wherein, this is contained in the historical driving behavior with reference to driving behavior；This is contained in the N road with reference to road conditions packet Condition information, this with reference to Driving control parameter be contained in the N Driving control parameter and with this with reference to traffic information it is corresponding, N is Integer greater than 1.Optionally, servomechanism can according to a history traffic information and with this history traffic information Corresponding history Driving control parameter determines a historical driving behavior.Optionally, servomechanism can basis A plurality of history traffic information and a plurality of history Driving control parameter corresponding with a plurality of history traffic information determine one Historical driving behavior.
Optionally, servomechanism is determined according to reference traffic information and with reference to Driving control parameter with reference to driving row For following operation can be performed before: being closed according to the history traffic information and the history Driving control parameter in the corresponding of time dimension System, establishes target database (i.e. key-value database)；This is obtained from the target database with reference to traffic information and the ginseng Examine Driving control parameter.Wherein, which includes the N traffic information and a pair for the N Driving control parameter It should be related to.Above-mentioned table 3 can be a kind of example of the target database.
603, servomechanism is by the historical driving behavior, the history traffic information and the history Driving control parameter It stores as a whole, to obtain driving data file.
Optionally, servomechanism stores the historical driving behavior to the target according to the format of the target database Database, to obtain the driving data file.Wherein, which believes with the history road conditions respectively sequentially in time Breath and the history Driving control parameter are corresponding.Table 4 can be a kind of example of driving data file.In practical applications, Servomechanism can according to the format of key-value database store history traffic information, history Driving control parameter and Historical driving behavior, every data includes history traffic information, history Driving control parameter and historical driving behavior at this time, referred to as Driving data file.
In the embodiment of the present application, historical driving behavior is determined according to history traffic information and history Driving control parameter, into And historical driving behavior, history traffic information and history Driving control parameter are stored as a whole to obtain driving number According to file；The driving data file comprising user's driving style can efficiently be generated.
The side how servomechanism obtains history traffic information and history Driving control parameter is described first below Formula.In one embodiment, following steps can be performed to obtain history traffic information and history and drive control in servomechanism Parameter processed:
Step 1: servomechanism passes through the multiple sensors of installation, including laser thunder during user drives It reaches, millimetre-wave radar, ultrasonic radar, monocular or binocular camera etc. equipment, collects telecommunication flow information and information of road surface, example Such as traffic sign, traffic lights, lane line, surrounding vehicles, the initial data such as pedestrian and obstacle information.Meanwhile automatic Pilot Device records the acquisition time of every a kind of data, chronomere can be it is wonderful, Various types of data is stored according to time dimension.Each road surface The different road condition data of message reflection.For example, traffic sign: the road speed limit upper limit, speed limit lower limit, front stop row Vehicle etc.；Whether traffic lights: stopping, and turns left or turns right；Lane line: vehicle heading, turning radius, both sides track direction, Whether lane-change etc. is allowed；Vehicle, pedestrian and barrier: opposite car's location, lane information, relative velocity etc..
Step 2: servomechanism operates all initial data being collected by fusion, cluster etc., take out each When the traffic information inscribed, be stored in memory according to chronomere, this (also becomes history road conditions for history road condition data Information).For example, this process can be used clustering algorithm, including K mean value (K-Means) clustering algorithm, DBSCAN algorithm, Density-Peek Clustering algorithm clusters the point cloud data of acquisition, so that it is determined that the position of each barrier.Table 7 illustrate an example of the history traffic information that servomechanism handles the initial data of collection.
Table 7
Second row of table 7 every row into last line includes a history traffic information, wherein any two history road conditions Information is different or different.It in practical applications, include a plurality of history traffic information, every history road conditions letter in history traffic information Breath characterizes a kind of road conditions.In table 7, history traffic information stores sequentially in time, the time of adjacent two history traffic informations Between be divided into 20s.Table 7 is only a kind of example, and in practical applications, the time interval of adjacent two history traffic informations can be 1s, 2s, 5s, 10s, 15s etc., the embodiment of the present application is not construed as limiting.
Step 3: while servomechanism passes through sensor collection data, using GPS navigation system and from interior Control data when control collector (such as IMU and interior control device sensor) acquisition user drives, and according to same Chronomere deposits in memory for data are controlled.
Optionally, GPS navigation system is collected from vehicle location information, including is currently located lane and coordinate points, according to every two The positional distance of a time frame calculates the speed of former frame.IMU is measurement from vehicle triaxial attitude angle (or angular speed) and accelerates The device of degree.One IMU contains three uniaxial accelerometers and three uniaxial gyros, and accelerometer detection object is carrying The acceleration signal of independent three axis of body coordinate system, and angular velocity signal of the gyro detection carrier relative to navigational coordinate system, are surveyed The angular speed and acceleration from vehicle in three dimensions are measured, and resolves the posture for coming from vehicle with this.Sensor is controlled, as wheel speed passes Sensor is also used for collecting vehicle velocity and acceleration data.The data type of the above sensor collection includes: longitudinal speed, is added Speed/deceleration, angular speed etc..This data is that history controls data, also referred to as history Driving control parameter.Table 8, which illustrates, to be gone through One example of history control data.
Table 8
Time frame (s) Acceleration Corner (degree) Speed (km/h) ……
100 2 30 20 ……
120 2 29.5 20 ……
…… …… …… …… ……
Second row of table 8 every row into last line includes that a history controls data (i.e. history Driving control parameter). Since the chronomere of servomechanism storage history control data is identical as the storage chronomere of history traffic information, often One history traffic information respectively corresponds a history control data.That is, each history traffic information and each history It is identical to control data corresponding time point.For example, in table 7 in the history traffic information of second row and table 8 second row history control Corresponding point (i.e. the time frame) at the same time of data processed.
Step 4: having collected a large amount of history road conditions number in the memory of servomechanism when user terminates to drive Data are controlled according to history, by history road condition data and history control data according to the corresponding relationship of time dimension, establish one Key-value database.Above-mentioned table 2 can be an example of key-value database, each data packet in the database Include a history traffic information and a history Driving control parameter.Following two steps are executed for the key-value database It is rapid:
Step 1: repetition and/or invalid partial data entry are automatically deleted by manual or automatic pilot instrument.
1) invalid data entry: a certain item parameter value be it is empty or and normal parameters deviation it is larger.Lead to the problem The reason of mostly sensor output distortion.For example, the barrier car speed in a certain data is 30, next frame data Jumping is 40, then can conclude that perception data is distorted, delete this wrong data.
2) repeated data entry: such data entry judges according to similarity, if all parameter values of multinomial data entry Similarity retains a wherein data 95% or more, deletes remainder data.Optionally, if the history road of any two data Same type data can then delete wherein one compared to similarity all 95% or more in condition data and/or history control data Data retains another.For example, the first data is compared with the data of same type in Article 10 data in database Similarity then deletes first data or the Article 10 data all 95% or more.Again for example, Article 2 in database The history traffic information part of data compared with the history traffic information part of Article 9 data, the data of same type it is similar Degree deletes second data or the Article 9 data more than 90%.Table 9 and table 10 are that key-value database includes Partial data.
Table 9
Time frame (s) Acceleration (m/s2) Corner (degree) Speed (km/h) ……
100 2 30 20 ……
120 2 29.5 20 ……
Table 10
A data in second row of table 9 and the second row composition key-value database of table 10, the third line of table 9 The data in key-value database is also formed with the third line of table 10.
From table 9 and table 10 as can be seen that the road condition data in the 100th frame and the road condition data in control data and 120 frames With control similarity all 95% or more, one can be deleted.
Step 2: the data compaction after screening is at a new key-value database.The new key-value data History traffic information and history control data in library are respectively that servomechanism executes the history road conditions letter that step 601 obtains Breath and history Driving control parameter.It is appreciated that servomechanism successively executes the above-mentioned first step to the 4th and step One can obtain history traffic information and history Driving control parameter to step 2.It is any in the new key-value database Two datas are different, and a data by history road condition data and history controls data two parts in key-value database Composition, sees table 2.
Servomechanism can accurately and rapidly obtain it under manual drive mode by executing above-mentioned steps History traffic information and history Driving control parameter.In addition, by entry invalid or duplicate in delete target database, it can Effectively the target database is simplified and be improved, accurately in order to the data in the later use target database Determine historical driving behavior.
The mode for how generating driving data file is described below.
Every data of the key-value database is as input, by deep learning network, learns driving for driver out Sail behavior.It is specific as follows: every data in key-value database being input to the driving behavior that training obtains and predicts network It is handled, obtains the corresponding historical driving behavior of every data.Driving behavior prediction network can be convolutional neural networks, It is also possible to other kinds of neural network.Fig. 7 is that one kind provided by the embodiments of the present application is driven by neural network learning Sail the schematic diagram of behavior.Wherein, each data in key-value database is as the defeated of driving behavior prediction network Enter, that is, the dimension inputted is equal with the data class in the data.Optionally, using CNN (convolutional neural networks) as training Model, because input data has local correlations, such as speed, the data such as distance are larger to output weighing factor.The driving row To predict that the output of network is the behaviour decision making space of automated driving system, which is discrete value, represents automatic Pilot System at a time calculated driving behavior, including travelled in road, lane-change is parked, u-turn, parking etc..Fig. 8 is this Shen Please embodiment provide another kind the schematic diagram of driving behavior is obtained by neural network learning.In Fig. 8 two road condition datas and Data are controlled, are all lane-change (changelane) by the result that training learns out.In practical applications, by key-value number Driving behavior prediction network is input to according to every data in library to be handled, and is obtained the corresponding history of every data and is driven Behavior.Finally, the driving behavior data obtained are also stored in database, at this time according to the format of key-value database Every data includes history road condition data, and history controls data and driving behavior data, referred to as driving data file.
For different drivers, repeating above step can get a large amount of driving data files, and can be to file to drive wind Lattice classification can be divided into caution, the different types such as normal and radical.Driving style is generally by according to following distance, acceleration and deceleration width Degree etc. factor classification.Such as 1-2 parking stall of following distance is normal；3-4 parking stall of following distance is careful；Following distance is small It is radical in 1 parking stall.Servomechanism can obtain different types of driving data file in this way, in order to passenger's choosing Select different driving styles.
Optionally, which is uploaded to service after obtaining driving data file by servomechanism Device, alternatively, the driving data file is sent to target terminal, alternatively, storing the driving data file to memory.
In this implementation, driving data file is uploaded to server or driving data file is sent to target Terminal, in order to which the driving data file is loaded onto servomechanism from the server or the target terminal by user, in turn So that the servomechanism is driven according to the driving habit of oneself.
Describe how to carry out the process of automatic Pilot below with reference to the structure of servomechanism.Fig. 9 is that the application is real The structural schematic diagram that a kind of servomechanism of example offer is provided, as shown in figure 9, the servomechanism includes: sensor 901, memory 902, processor 903 and bus 904；Wherein, sensor 901, memory 902, processor 903 pass through bus Communication connection between 904 realizations.
Sensor 901, for acquiring current traffic information；
Memory 902 is used for store code；
Processor 903 is by reading the code stored in the memory to be used to perform the following operations: current according to this Traffic information, inquiry is with the presence or absence of the target Driving control parameter to match with the current traffic information from database；If depositing The target Driving control parameter is then being obtained, and driven with target driving style according to the target Driving control parameter；It should Target Driving control parameter includes the history Driving control parameter of target vehicle, which includes the target carriage The Driving control parameter driven according to the target driving style；If it does not exist, then joined according to real-time Driving control Number is driven with current driving style；The real-time Driving control parameter is that the servomechanism is determined according to default decision-making mechanism The Driving control parameter that plan goes out.
Optionally, sensor 901 corresponds to the sensing system 104 in Fig. 1；Processor 903 corresponds to the processing in Fig. 1 Device 113；Memory 902 corresponds to the memory 114 in Fig. 1.In some embodiments, sensor 901 can acquire original road Condition information, the traffic information that processor 903 can be original to this do working process to obtain the current traffic information.Optionally, locate Reason device 903 can control servomechanism according to real-time Driving control parameter or target Driving control by control system 106 Parameter is driven.
During specific implementation, sensor 901 is specifically used for executing the method being previously mentioned in step 301 and can wait With the method for replacement；Processor 903 is specifically used for executing the method being previously mentioned in step 302 to step 304 and can be equal The method of replacement.
In an optional implementation, the servomechanism further include:
Communication interface 905, for obtaining or receiving driving data file；
Processor 903 is also used to judge whether the driving data file includes the target vehicle according to target driving wind At least one of in history traffic information, history Driving control parameter and the historical driving behavior that lattice are driven, if so, This is executed according to the current traffic information, inquiry is driven with the presence or absence of the target to match with the current traffic information from database The step of sailing control parameter.
Optionally, communication interface 905 corresponds to the user interface 116 in Fig. 1.For example, the control wireless communication of processor 113 System 146 obtains the driving data file from Cloud Server.
In this implementation, after obtaining driving data file, determination is driven according to the target driving style； It can guarantee to have obtained carrying out according to target driving style before being driven according to target driving style driving required go through History driving data, it is highly-safe.
In an optional implementation, communication interface 905, for receiving the third instruction of user's input or coming from 4th instruction of third terminal；
Processor 903, specifically for the case where communication interface 905 receives third instruction or the 4th instruction Under, determination is driven according to the target driving style；Third instruction and the 4th instruction are used to indicate the automatic Pilot Device is driven according to the target driving style.
Optionally, communication interface 905 is the user interface 116 or vehicle-mounted computer 148 in Fig. 1.For example, user interface 116 In wireless communication system 146 receive the 4th instruction.In another example servomechanism receives user by vehicle-mounted computer 148 The third of input instructs.
In this implementation, user can quickly and easily indicate servomechanism according to target driving style into Row drives, and user experience is good.
Describe how to generate the process of driving data file below with reference to the structure of driving data file creating apparatus.Figure 10 be a kind of structural schematic diagram of driving data file creating apparatus provided by the embodiments of the present application, as shown in Figure 10, the driving Generating Data File device includes: memory 1001, processor 1002 and bus 1003；Memory 1001 is for storing generation Code, history traffic information and history Driving control parameter；Wherein, memory 1001, processor 1002 are real by bus 1003 Communication connection between now；Processor 1002 is by reading the code stored in the memory to be used to execute following behaviour Make: obtaining history traffic information and history Driving control parameter from memory 1001；The history traffic information and the history are driven Sailing control parameter is respectively the traffic information and drive control that servomechanism acquires during driver's manual drive Parameter processed, the history traffic information are corresponding in time dimension with the history Driving control parameter；According to the history traffic information With the history Driving control parameter, historical driving behavior is determined；By the historical driving behavior, the history traffic information and this go through History Driving control parameter stores as a whole, to obtain driving data file.The driving data file creating apparatus can be with It is servomechanism, is also possible to the computer equipment of other executable data processings, such as server etc..
During specific implementation, processor 1002 is specifically used for executing the method being previously mentioned in step 601 to step 603 And it can be in the method for equivalent replacement.
In an optional implementation, driving data file creating apparatus further include:
Processor 1002 is also used to pair according to the history traffic information and the history Driving control parameter in time dimension It should be related to, establish target database；The target database include the N traffic information and the N Driving control parameter one by one Corresponding relationship；
Processor 1002 refers to Driving control with this with reference to traffic information specifically for obtaining this from the target database Parameter.
In this implementation, it is closed according to history traffic information and history Driving control parameter in the corresponding of time dimension System, establishes target database, in order to determine historical driving behavior according to history traffic information and history Driving control parameter, behaviour Make simple.
In an optional implementation, driving data file creating apparatus further include:
Communication interface 1003, for receiving history traffic information and history Driving control ginseng from servomechanism Number, alternatively, obtaining history traffic information and history Driving control parameter from server.
It should be understood that the division of each unit in the above positioning device and servomechanism is only a kind of logic function The division of energy, can completely or partially be integrated on a physical entity in actual implementation, can also be physically separate.For example, Above each unit can be the processing element individually set up, and also can integrate and realize in some chip of terminal, in addition, It can also be stored in the form of program code in the memory element of controller, be called simultaneously by some processing element of processor Execute the function of above each unit.Furthermore each unit can integrate together, can also independently realize.Here processing elements Part can be a kind of IC chip, the processing capacity with signal.During realization, each step of the above method or with Upper each unit can be completed by the integrated logic circuit of the hardware in processor elements or the instruction of software form.At this Reason element can be general processor, such as central processing unit (English: central processing unit, abbreviation: CPU), It can also be the one or more integrated circuits for being configured to implement above method, such as: one or more specific integrated circuits (English: application-specific integrated circuit, referred to as: ASIC), or, one or more micro processs Device (English: digital signal processor, referred to as: DSP), or, one or more field programmable gate array (English Text: field-programmable gate array, referred to as: FPGA) etc..
In some embodiments, disclosed method may be embodied as being coded in machine readable format computer-readable Computer program instructions that are on storage medium or being coded on other non-transient media or product.Figure 11 is schematic Ground shows the conceptual partial view for the example computer program product arranged according at least some embodiments shown here, The example computer program product includes the computer program for executing computer processes on the computing device.Implement at one In example, example computer program product 1100 is provided using signal bearing medium 1101.The signal bearing medium 1101 It may include one or more program instructions 1102, can provide when being run by one or more processors above in relation to figure The function or partial function of 9- Figure 10 description.Thus, for example, the embodiment with reference to shown in Fig. 9, the one of box 901-905 The realization of a or multiple function can be undertaken by one or more instructions associated with signal bearing medium 1101.This Outside, the program instruction 1102 in Figure 11 also describes example instruction.
In some embodiments, realization when above procedure instruction 1102 is executed by processor: current traffic information is obtained；It obtains Take current traffic information；According to the current traffic information, inquiry whether there is and the current traffic information phase from database The target Driving control parameter matched；If it exists, then the target Driving control parameter is obtained, and according to the target Driving control parameter It is driven with target driving style；The target Driving control parameter includes the history Driving control parameter of target vehicle, this is gone through History Driving control parameter includes the Driving control parameter that the target vehicle is driven according to the target driving style；If no In the presence of then being driven according to real-time Driving control parameter with current driving style；The real-time Driving control parameter is that this is automatic The Driving control parameter that pilot instrument goes out according to default decision-making mechanism decision.
In some embodiments, 1102 realization when being executed by processor of above procedure instruction: obtain history traffic information and History Driving control parameter；The history traffic information and the history Driving control parameter are respectively servomechanism in driver The traffic information and Driving control parameter acquired during manual drive, the history traffic information and the history Driving control Parameter is corresponding in time dimension；According to the history traffic information and the history Driving control parameter, historical driving behavior is determined； The historical driving behavior, the history traffic information and the history Driving control parameter are stored as a whole, to obtain Driving data file.
In some instances, signal bearing medium 1101 may include computer-readable medium 1103, such as, but not limited to, Hard disk drive, compact disc (CD), digital video disk (DVD), digital magnetic tape, memory, read-only memory (Read- Only Memory, ROM) or random access memory (Random Access Memory, RAM) etc..In some embodiments In, signal bearing medium 1101 may include computer recordable media 1104, such as, but not limited to, memory, read/write (R/ W) CD, R/W DVD, etc..In some embodiments, signal bearing medium 1101 may include communication media 1105, such as But be not limited to, number and/or analogue communication medium (for example, fiber optic cables, waveguide, wired communications links, wireless communication link, Etc.).Thus, for example, signal bearing medium 1101 can be by the communication media 1105 of wireless (for example, abiding by IEEE The wireless communication medium of 802.11 standards or other transport protocols) Lai Chuanda.One or more program instructions 1102 can be, For example, computer executable instructions or logic implement instruction.It in some instances, such as can for the processor of Fig. 1 description To be configured as, in response to passing through computer-readable medium 1103, computer recordable media 1104, and/or communication media One or more of 1105 are passed to the program instruction 1102 of processor, provide various operations, function or movement.It should Understand, arrangement described herein is only used for exemplary purpose.Thus, it will be understood by those skilled in the art that it is other arrangement and Other elements (for example, machine, interface, function, sequence and functional group etc.) can instead be used, and some Element can as expected result and omit together.In addition, many in described element be may be implemented as from Function that is scattered or distributed component or combining other components to implement with position in any suitable combination is real Body.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.
The present invention be according to the method for the embodiment of the present invention, the flow chart of equipment (system) and computer program product and/ Or block diagram describes.It should be understood that each process that can be realized by computer program instructions in flowchart and/or the block diagram and/ Or the combination of the process and/or box in box and flowchart and/or the block diagram.It can provide these computer program instructions To general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices processor to generate one A machine so that by the instruction that the processor of computer or other programmable data processing devices executes generate for realizing The device for the function of being specified in one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right It is required that protection scope subject to.

Claims (13)

1. a kind of automatic Pilot method characterized by comprising
Servomechanism obtains current traffic information；
According to the current traffic information, inquiry is with the presence or absence of the target to match with the current traffic information from database Driving control parameter；If it exists, then the target Driving control parameter is obtained, and according to the target Driving control parameter with mesh Mark driving style is driven；The target Driving control parameter includes the history Driving control parameter of target vehicle, described to go through History Driving control parameter includes the Driving control parameter that the target vehicle is driven according to the target driving style；
If it does not exist, then it is driven according to real-time Driving control parameter with current driving style；The real-time Driving control ginseng Number is the Driving control parameter that the servomechanism goes out according to default decision-making mechanism decision.
2. the method according to claim 1, wherein it is described obtain the target Driving control parameter before, institute State method further include:
Determine that the first driving behavior, first driving behavior are that the servomechanism is determined according to the default decision-making mechanism The driving behavior that plan goes out；
Determine the second driving behavior to match in the database with the current traffic information, the driving in the database Behavior includes the historical driving behavior that the target vehicle is driven according to the target driving style；
Judge whether first driving behavior and second driving behavior are identical, if they are the same, then execute described in the acquisition The step of target Driving control parameter.
3. according to the method described in claim 2, it is characterized in that, believing in the determination database with the current road conditions Matched second driving behavior of manner of breathing includes:
In the case where in the database including the target traffic information to match with the current traffic information, described in determination The corresponding driving behavior of target traffic information described in database is second driving behavior；The database includes at least one The corresponding relationship of item history traffic information and described at least one history traffic information and driving behavior, the history road conditions Information includes the target traffic information.
4. method according to any one of claims 1 to 3, which is characterized in that it is described according to the current traffic information, from Before inquiry is with the presence or absence of the target Driving control parameter to match with the current traffic information in database, the method is also Include:
Obtain driving data file；
Judge whether the driving data file includes that the target vehicle is gone through according to what the target driving style was driven At least one of in history traffic information, history Driving control parameter and historical driving behavior, if so, executing described according to institute Current traffic information is stated, inquiry is joined with the presence or absence of the target Driving control to match with the current traffic information from database Several steps.
5. according to the method described in claim 4, it is characterized in that, the acquisition driving data file includes:
Receive the driving data file from first terminal；
Alternatively,
After receiving the first instruction from second terminal, the driving data file is obtained from server；Described first refers to Order is used to indicate the servomechanism and obtains the driving data file from the server.
6. according to the method described in claim 4, it is characterized in that, the driving data file is to drive the history to go It is stored as a whole in the database for, the history traffic information and the history Driving control parameter, institute It states history traffic information and the history Driving control parameter is respectively process of the target vehicle in driver's manual drive The traffic information and Driving control parameter of middle acquisition, the history traffic information and the history Driving control parameter are in the time Dimension is corresponding, and the historical driving behavior is the target vehicle according to the history traffic information and history driving control The driving behavior that parameter processed determines.
7. a kind of servomechanism characterized by comprising sensor, memory and processor；The sensor is used for Acquire current traffic information；The memory is used for store code；The processor is stored in the memory by reading The code is with for performing the following operations: according to the current traffic information, from database inquiry with the presence or absence of with it is described The target Driving control parameter that current traffic information matches；If it exists, then the target Driving control parameter is obtained, and according to The target Driving control parameter is driven with target driving style；The target Driving control parameter includes target vehicle History Driving control parameter, the history Driving control parameter include that the target vehicle is carried out according to the target driving style Drive obtained Driving control parameter；
If it does not exist, then it is driven according to real-time Driving control parameter with current driving style；The real-time Driving control ginseng Number is the Driving control parameter that the servomechanism goes out according to default decision-making mechanism decision.
8. device according to claim 7, which is characterized in that
The processor, is also used to determine the first driving behavior, first driving behavior be the servomechanism according to The driving behavior that the default decision-making mechanism decision goes out；
Determine the second driving behavior to match in the database with the current traffic information, the driving in the database Behavior includes the historical driving behavior that the target vehicle is driven according to the target driving style；
Judge whether first driving behavior and second driving behavior are identical, if they are the same, then execute described in the acquisition The step of target Driving control parameter.
9. device according to claim 8, which is characterized in that
The processor, specifically in the database including that the target road conditions to match with the current traffic information are believed In the case where breath, determine that the corresponding driving behavior of target traffic information described in the database is second driving behavior； The database includes pair of at least one history traffic information and described at least one history traffic information and driving behavior It should be related to, the history traffic information includes the target traffic information.
10. device according to any one of claims 7 to 9, which is characterized in that described device further include:
Communication interface, for obtaining or receiving driving data file；
The processor is also used to judge whether the driving data file includes that the target vehicle drives according to the target At least one of in history traffic information, history Driving control parameter and the historical driving behavior that style is driven, if so, Then execute described according to the current traffic information, inquiry with the current traffic information with the presence or absence of matching from database Target Driving control parameter the step of.
11. device according to claim 9, which is characterized in that
The communication interface, specifically for receiving the driving data file from first terminal；
Alternatively,
The communication interface, specifically for receive from second terminal first instruction after, from server obtain described in drive Sail data file；First instruction is used to indicate the servomechanism and obtains the driving data text from the server Part.
12. device according to claim 10, which is characterized in that the driving data file is to drive the history to go It is stored as a whole in the database for, the history traffic information and the history Driving control parameter, institute It states history traffic information and the history Driving control parameter is respectively process of the target vehicle in driver's manual drive The traffic information and Driving control parameter of middle acquisition, the history traffic information and the history Driving control parameter are in the time Dimension is corresponding, and the historical driving behavior is the target vehicle according to the history traffic information and history driving control The driving behavior that parameter processed determines.
13. a kind of computer readable storage medium, which is characterized in that be stored with computer in the computer readable storage medium Program, the computer program include program instruction, and described program instructs when being executed by a processor, execute the processor Such as method as claimed in any one of claims 1 to 6.
CN201910691859.4A 2019-07-26 2019-07-26 Automatic Pilot method and servomechanism Pending CN110471411A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910691859.4A CN110471411A (en) 2019-07-26 2019-07-26 Automatic Pilot method and servomechanism

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910691859.4A CN110471411A (en) 2019-07-26 2019-07-26 Automatic Pilot method and servomechanism

Publications (1)

Publication Number Publication Date
CN110471411A true CN110471411A (en) 2019-11-19

Family

ID=68509057

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910691859.4A Pending CN110471411A (en) 2019-07-26 2019-07-26 Automatic Pilot method and servomechanism

Country Status (1)

Country Link
CN (1) CN110471411A (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110989622A (en) * 2019-12-25 2020-04-10 腾讯科技（深圳）有限公司 Automatic driving control method, device, storage medium and computer equipment
CN111506067A (en) * 2020-04-20 2020-08-07 上海电子信息职业技术学院 Intelligent model car
CN111522348A (en) * 2020-05-27 2020-08-11 杭州野乐科技有限公司 Self-walking control method and system for scooter
CN111612140A (en) * 2020-04-01 2020-09-01 广东中科臻恒信息技术有限公司 Automatic driving safety discrimination method, equipment and storage medium based on road side unit
CN111619576A (en) * 2020-06-03 2020-09-04 中国第一汽车股份有限公司 Control method, device, equipment and storage medium
CN112214026A (en) * 2020-10-26 2021-01-12 广州小鹏自动驾驶科技有限公司 Driving obstacle detection method and device, vehicle and readable medium
CN112654548A (en) * 2020-05-09 2021-04-13 华为技术有限公司 Method and device for adaptively optimizing automatic driving system
WO2021098222A1 (en) * 2019-11-20 2021-05-27 华为技术有限公司 Vehicle driving control method and related device
WO2021129156A1 (en) * 2019-12-28 2021-07-01 华为技术有限公司 Control method, device and system of intelligent car
CN113159105A (en) * 2021-02-26 2021-07-23 北京科技大学 Unsupervised driving behavior pattern recognition method and data acquisition monitoring system
CN113238237A (en) * 2021-07-12 2021-08-10 天津天瞳威势电子科技有限公司 Library position detection method and device
CN113495555A (en) * 2020-03-20 2021-10-12 际络科技(上海)有限公司 Driving rule extraction device and method, formulation device and method, and storage medium
CN113704116A (en) * 2021-08-30 2021-11-26 阿波罗智联(北京)科技有限公司 Data processing method, device, electronic equipment and medium for automatic driving vehicle
CN113968224A (en) * 2021-12-06 2022-01-25 武汉路特斯汽车有限公司 Control method and control system for automatically adjusting driving mode and vehicle
WO2022022344A1 (en) * 2020-07-31 2022-02-03 华为技术有限公司 Automatic driving control method and apparatus
EP4083959A1 (en) * 2021-04-26 2022-11-02 Nio Technology (Anhui) Co., Ltd Traffic flow machine-learning modeling system and method applied to vehicles
CN115534981A (en) * 2022-12-05 2022-12-30 广汽埃安新能源汽车股份有限公司 Automatic driving mode adjusting method and device for vehicle
WO2023103692A1 (en) * 2021-12-07 2023-06-15 阿里巴巴达摩院(杭州)科技有限公司 Decision planning method for autonomous driving, electronic device, and computer storage medium
CN113968224B (en) * 2021-12-06 2024-04-26 宁波路特斯机器人有限公司 Control method and control system for automatically adjusting driving mode and vehicle

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106143490A (en) * 2015-04-07 2016-11-23 上海汽车集团股份有限公司 Adaptive cruise control method and device
CN106184223A (en) * 2016-09-28 2016-12-07 北京新能源汽车股份有限公司 A kind of automatic Pilot control method, device and automobile
CN106875511A (en) * 2017-03-03 2017-06-20 深圳市唯特视科技有限公司 A kind of method for learning driving style based on own coding regularization network
CN107329466A (en) * 2017-08-28 2017-11-07 北京华清智能科技有限公司 A kind of automatic Pilot compact car
CN108357496A (en) * 2018-02-12 2018-08-03 北京小马智行科技有限公司 Automatic Pilot control method and device
CN108891422A (en) * 2018-07-09 2018-11-27 深圳市易成自动驾驶技术有限公司 Control method, device and the computer readable storage medium of intelligent vehicle
CN109383523A (en) * 2017-08-07 2019-02-26 奥迪股份公司 Auxiliary driving method and system for vehicle
CN109703567A (en) * 2019-01-25 2019-05-03 安徽酷哇机器人有限公司 Control method for vehicle

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106143490A (en) * 2015-04-07 2016-11-23 上海汽车集团股份有限公司 Adaptive cruise control method and device
CN106184223A (en) * 2016-09-28 2016-12-07 北京新能源汽车股份有限公司 A kind of automatic Pilot control method, device and automobile
CN106875511A (en) * 2017-03-03 2017-06-20 深圳市唯特视科技有限公司 A kind of method for learning driving style based on own coding regularization network
CN109383523A (en) * 2017-08-07 2019-02-26 奥迪股份公司 Auxiliary driving method and system for vehicle
CN107329466A (en) * 2017-08-28 2017-11-07 北京华清智能科技有限公司 A kind of automatic Pilot compact car
CN108357496A (en) * 2018-02-12 2018-08-03 北京小马智行科技有限公司 Automatic Pilot control method and device
CN108891422A (en) * 2018-07-09 2018-11-27 深圳市易成自动驾驶技术有限公司 Control method, device and the computer readable storage medium of intelligent vehicle
CN109703567A (en) * 2019-01-25 2019-05-03 安徽酷哇机器人有限公司 Control method for vehicle

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李曙光: "《法大研究生》", 31 July 2017, 北京：中国政法大学出版社 *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021098222A1 (en) * 2019-11-20 2021-05-27 华为技术有限公司 Vehicle driving control method and related device
CN110989622B (en) * 2019-12-25 2022-06-03 腾讯科技（深圳）有限公司 Automatic driving control method, device, storage medium and computer equipment
CN110989622A (en) * 2019-12-25 2020-04-10 腾讯科技（深圳）有限公司 Automatic driving control method, device, storage medium and computer equipment
WO2021129156A1 (en) * 2019-12-28 2021-07-01 华为技术有限公司 Control method, device and system of intelligent car
CN113495555A (en) * 2020-03-20 2021-10-12 际络科技(上海)有限公司 Driving rule extraction device and method, formulation device and method, and storage medium
CN111612140B (en) * 2020-04-01 2023-08-25 广东中科臻恒信息技术有限公司 Automatic driving safety judging method, equipment and storage medium based on road side unit
CN111612140A (en) * 2020-04-01 2020-09-01 广东中科臻恒信息技术有限公司 Automatic driving safety discrimination method, equipment and storage medium based on road side unit
CN111506067A (en) * 2020-04-20 2020-08-07 上海电子信息职业技术学院 Intelligent model car
CN112654548B (en) * 2020-05-09 2022-04-05 华为技术有限公司 Method and device for adaptively optimizing automatic driving system
CN112654548A (en) * 2020-05-09 2021-04-13 华为技术有限公司 Method and device for adaptively optimizing automatic driving system
CN111522348A (en) * 2020-05-27 2020-08-11 杭州野乐科技有限公司 Self-walking control method and system for scooter
CN111619576A (en) * 2020-06-03 2020-09-04 中国第一汽车股份有限公司 Control method, device, equipment and storage medium
CN111619576B (en) * 2020-06-03 2021-06-25 中国第一汽车股份有限公司 Control method, device, equipment and storage medium
CN114056346A (en) * 2020-07-31 2022-02-18 华为技术有限公司 Automatic driving control method and device
WO2022022344A1 (en) * 2020-07-31 2022-02-03 华为技术有限公司 Automatic driving control method and apparatus
CN112214026A (en) * 2020-10-26 2021-01-12 广州小鹏自动驾驶科技有限公司 Driving obstacle detection method and device, vehicle and readable medium
CN113159105A (en) * 2021-02-26 2021-07-23 北京科技大学 Unsupervised driving behavior pattern recognition method and data acquisition monitoring system
CN113159105B (en) * 2021-02-26 2023-08-08 北京科技大学 Driving behavior unsupervised mode identification method and data acquisition monitoring system
EP4083959A1 (en) * 2021-04-26 2022-11-02 Nio Technology (Anhui) Co., Ltd Traffic flow machine-learning modeling system and method applied to vehicles
CN113238237B (en) * 2021-07-12 2021-10-01 天津天瞳威势电子科技有限公司 Library position detection method and device
CN113238237A (en) * 2021-07-12 2021-08-10 天津天瞳威势电子科技有限公司 Library position detection method and device
CN113704116A (en) * 2021-08-30 2021-11-26 阿波罗智联(北京)科技有限公司 Data processing method, device, electronic equipment and medium for automatic driving vehicle
CN113968224A (en) * 2021-12-06 2022-01-25 武汉路特斯汽车有限公司 Control method and control system for automatically adjusting driving mode and vehicle
CN113968224B (en) * 2021-12-06 2024-04-26 宁波路特斯机器人有限公司 Control method and control system for automatically adjusting driving mode and vehicle
WO2023103692A1 (en) * 2021-12-07 2023-06-15 阿里巴巴达摩院(杭州)科技有限公司 Decision planning method for autonomous driving, electronic device, and computer storage medium
CN115534981A (en) * 2022-12-05 2022-12-30 广汽埃安新能源汽车股份有限公司 Automatic driving mode adjusting method and device for vehicle
CN115534981B (en) * 2022-12-05 2023-03-07 广汽埃安新能源汽车股份有限公司 Automatic driving mode adjusting method and device for vehicle

Similar Documents

Publication Publication Date Title
CN110471411A (en) Automatic Pilot method and servomechanism
US20210262808A1 (en) Obstacle avoidance method and apparatus
US20220332348A1 (en) Autonomous driving method, related device, and computer-readable storage medium
CN106458218B (en) Handle system, method and the computer-readable medium of driving information map
WO2021102955A1 (en) Path planning method for vehicle and path planning apparatus for vehicle
CN109901574A (en) Automatic Pilot method and device
CN110379193A (en) The conduct programming method and conduct programming device of automatic driving vehicle
CN107943016A (en) Colony's driving style learning framework for autonomous vehicle
CN109814520A (en) System and method for determining the security incident of autonomous vehicle
CN110371132A (en) Driver's adapter tube appraisal procedure and device
EP3965004A1 (en) Automatic lane changing method and device, and storage medium
WO2022142839A1 (en) Image processing method and apparatus, and intelligent vehicle
WO2022016901A1 (en) Method for planning driving route of vehicle, and intelligent vehicle
US20230048680A1 (en) Method and apparatus for passing through barrier gate crossbar by vehicle
CN113835421A (en) Method and device for training driving behavior decision model
CN113498529B (en) Target tracking method and device
WO2019088977A1 (en) Continual planning and metareasoning for controlling an autonomous vehicle
CN112810603B (en) Positioning method and related product
WO2022017307A1 (en) Autonomous driving scenario generation method, apparatus and system
US20230031130A1 (en) Open door reconstruction for sensor simulation
CN112829762A (en) Vehicle running speed generation method and related equipment
US20230054974A1 (en) Intersection Risk Indicator
CN113741384B (en) Method and device for detecting automatic driving system
CN116324662B (en) System for performing structured testing across an autonomous fleet of vehicles
CN113552869A (en) Method for optimizing decision rules, method for controlling vehicle driving and related device

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
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20191119