CN107515607A - Control method and device for unmanned vehicle - Google Patents
Control method and device for unmanned vehicle Download PDFInfo
- Publication number
- CN107515607A CN107515607A CN201710791661.4A CN201710791661A CN107515607A CN 107515607 A CN107515607 A CN 107515607A CN 201710791661 A CN201710791661 A CN 201710791661A CN 107515607 A CN107515607 A CN 107515607A
- Authority
- CN
- China
- Prior art keywords
- avoidance
- unmanned vehicle
- parameter
- deep learning
- learning model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013136 deep learning model Methods 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000004590 computer program Methods 0.000 claims description 7
- 230000006399 behavior Effects 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000004888 barrier function Effects 0.000 claims 1
- 230000006870 function Effects 0.000 description 11
- 230000006854 communication Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
This application discloses the control method and device for unmanned vehicle.One embodiment of this method includes：Obtain the data of at least two sensors collection；By the avoidance deep learning model of acquired data input training in advance, wherein, the avoidance deep learning model is used to characterizing the corresponding relation of the data that sensor gathered and the avoidance parameter of unmanned vehicle；The avoidance parameter of the unmanned vehicle of avoidance deep learning model output is obtained, to be controlled based on the avoidance parameter to the unmanned vehicle.The embodiment of the present application obtains avoidance parameter by avoidance deep learning model, realizes the driving to unmanned vehicle and is controlled.
Description
Technical field
The application is related to field of computer technology, and in particular to Internet technical field, more particularly, to unmanned vehicle
Control method and device.
Background technology
Unmanned vehicle is one kind of intelligent automobile, also referred to as wheeled mobile robot, rely primarily on in-car with department of computer science
Intelligent driving instrument based on system realizes unpiloted target.
Unmanned vehicle can be detected during traveling by sensor road pavement situation.But in prior art
In, detected using single-sensor, testing result is easily poor by surrounding environment influence, stability.
The content of the invention
The purpose of the application is to propose a kind of improved control method and device for unmanned vehicle, carried on the back to solve the above
The technical problem that scape technology segment is mentioned.
In a first aspect, the embodiment of the present application provides a kind of control method for unmanned vehicle, this method includes：Unmanned vehicle
At least two sensors are installed, method includes：Obtain the data of at least two sensors collection；By acquired data input
The avoidance deep learning model of training in advance, wherein, avoidance deep learning model be used to characterizing data that sensor gathered with
The corresponding relation of the avoidance parameter of unmanned vehicle；Obtain the avoidance parameter of the unmanned vehicle of avoidance deep learning model output, with based on
Avoidance parameter is controlled to unmanned vehicle.
In certain embodiments, avoidance parameter includes braking parameters and/or turn around parameters.
In certain embodiments, at least two sensors include camera, laser radar and millimetre-wave radar.
In certain embodiments, avoidance deep learning model trains to obtain in a manner of end to end.
In certain embodiments, before the data of at least two sensors collection are obtained, this method also includes：Obtain extremely
The data of few two sensors collection, and the current avoidance parameter of unmanned vehicle is obtained, avoidance parameter is the driving behavior by user
Generation；Using acquired data and current avoidance parameter as the input and output of avoidance deep learning model, with
Avoidance deep learning model is trained.
Second aspect, the embodiment of the present application provide a kind of control device for unmanned vehicle, and the device includes：Unmanned vehicle
At least two sensors are installed, device includes：Acquiring unit, it is configured to obtain the data of at least two sensors collection；
Input block, it is configured to the avoidance deep learning model of acquired data input training in advance, wherein, the avoidance is deep
Degree learning model is used to characterizing the corresponding relation of the data that sensor gathered and the avoidance parameter of unmanned vehicle；Control unit, match somebody with somebody
The avoidance parameter of the unmanned vehicle for obtaining the avoidance deep learning model output is put, with based on the avoidance parameter pair
The unmanned vehicle is controlled.
In certain embodiments, avoidance parameter includes braking parameters and/or turn around parameters.
In certain embodiments, at least two sensors include camera, laser radar and millimetre-wave radar.
In certain embodiments, avoidance deep learning model trains to obtain in a manner of end to end.
In certain embodiments, device also includes：Parameter acquiring unit, it is configured to obtain the collection of at least two sensors
Data, and obtain the current avoidance parameter of unmanned vehicle, avoidance parameter is generated by the driving behavior of user；Training unit,
It is configured to using acquired data and current avoidance parameter as the input and output of avoidance deep learning model, with
Avoidance deep learning model is trained.
The third aspect, the embodiment of the present application provide a kind of unmanned vehicle, including：One or more processors；Storage device,
For storing one or more programs, when one or more programs are executed by one or more processors so that one or more
Processor realizes the method as being used for any embodiment in the control method of unmanned vehicle.
Fourth aspect, the embodiment of the present application provide a kind of computer-readable recording medium, are stored thereon with computer journey
Sequence, the method as being used for any embodiment in the control method of unmanned vehicle is realized when the program is executed by processor.
The control method and device for unmanned vehicle that the embodiment of the present application provides, unmanned vehicle are provided with least two sensings
Device, method include：The data of at least two sensors collection are obtained first.Afterwards, by acquired data input training in advance
Avoidance deep learning model, wherein, avoidance deep learning model is used to characterizing the data that sensor gathered and unmanned vehicle
The corresponding relation of avoidance parameter.Finally, the avoidance parameter of the unmanned vehicle of avoidance deep learning model output is obtained, with based on avoidance
Parameter is controlled to unmanned vehicle.The embodiment of the present application obtains avoidance parameter by avoidance deep learning model, realizes to nothing
The driving of people's car is controlled.
Brief description of the drawings
By reading the detailed description made to non-limiting example made with reference to the following drawings, the application's is other
Feature, objects and advantages will become more apparent upon：
Fig. 1 is that the application can apply to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the control method for unmanned vehicle of the application；
Fig. 3 is the schematic diagram according to an application scenarios of the control method for unmanned vehicle of the application；
Fig. 4 is the flow chart according to another embodiment of the control method for unmanned vehicle of the application；
Fig. 5 is the structural representation according to one embodiment of the control device for unmanned vehicle of the application；
Fig. 6 is adapted for the structural representation of the computer system of the unmanned vehicle for realizing the embodiment of the present application.
Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Be easy to describe, illustrate only in accompanying drawing to about the related part of invention.
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1, which is shown, can apply the control method for unmanned vehicle of the application or the control device for unmanned vehicle
The exemplary system architecture 100 of embodiment.
As shown in figure 1, system architecture 100 can include unmanned vehicle 101, network 102 and server 103.Network 102 to
The medium of communication link is provided between unmanned vehicle 101 and server 103.Network 102 can include various connection types, such as
Wired, wireless communication link or fiber optic cables etc..
User can be interacted using unmanned vehicle 101 by the server 103 of network 102, to receive or send message etc..Nobody
Various telecommunication customer end applications can be installed on car 101.
Unmanned vehicle 101 can be supported image to obtain and can carry out the various electronic equipments of image procossing, can be nothing
People's car etc..
Server 103 can be to provide the server of various services.Server 103 can carry out the processing such as analyzing, and will
Result feeds back to unmanned vehicle.
It should be noted that the image processing method for unmanned vehicle that the embodiment of the present application is provided is typically by unmanned vehicle
101 are performed, and correspondingly, the image processing apparatus for unmanned vehicle is generally positioned in unmanned vehicle 101.
It should be understood that the number of the terminal device, network and server in Fig. 1 is only schematical.According to realizing need
Will, can have any number of terminal device, network and server.
With continued reference to Fig. 2, the flow of one embodiment of the control method for unmanned vehicle according to the application is shown
200.This is used for the control method of unmanned vehicle, comprises the following steps：
Step 201, the data of at least two sensors collection are obtained.
In the present embodiment, unmanned vehicle is provided with least two sensors, and the control method for unmanned vehicle runs on it
On unmanned vehicle can be by wired connection mode on either radio connection obtains from local or other electronic equipments
The data at least two sensors collection stated.Herein, the quantity of every kind of sensor can be one or two or
It is more than person.
In some optional implementations of the present embodiment, at least two sensors can include camera, laser thunder
Reach and millimetre-wave radar.
Specifically, camera can gather view data or video stream data.Laser radar is detected using laser,
The data of the return collected are also laser signal.Millimetre-wave radar is detected using millimeter wave, the return collected
Data be millimeter-wave signal.
Step 202, by the avoidance deep learning model of acquired data input training in advance.
In the present embodiment, above-mentioned unmanned vehicle can be by the avoidance deep learning mould of acquired data input training in advance
Type, so that the avoidance deep learning model is exported according to the data of input.Wherein, avoidance deep learning model is used to characterize
The data and the corresponding relation of the avoidance parameter of unmanned vehicle that sensor is gathered.Avoidance parameter is involved by unmanned vehicle avoiding obstacles
And parameter.Here avoidance parameter is the data that unmanned vehicle uses immediately.
Above-mentioned avoidance deep learning model can be SVMs (Support Vector Machine, SVM), simplicity
The training of the graders (Classifier) such as Bayesian model (Naive Bayesian Model, NBM) model obtains.In addition,
Above-mentioned image processing model can also be based on some classification functions (such as softmax functions etc.) and training in advance forms.
In some optional implementations of the present embodiment, avoidance deep learning model is trained in a manner of end to end
Obtain.
In the present embodiment, the model that end-to-end mode is trained can using data that sensor collects as input, and
Export the unmanned vehicle avoidance parameter to be used.
Avoidance deep learning model is a kind of deep neural network, can directly generate vehicle according to the data of collection
Avoidance parameter.Specifically, in the training process of the model, employ which kind of data is trained as input and output, then
In the application process of model, it becomes possible to according to this kind of input data, obtain corresponding output data.
In some optional implementations of the present embodiment, avoidance deep learning model includes：
Feature extraction component, the characteristics of image of the image of extraction camera collection, the data of extraction laser radar collection
First data characteristics, the second data characteristics of the data of extraction millimetre-wave radar collection.
In the present embodiment, feature extraction can be carried out in the following ways, and figure is extracted from the image of camera collection
As feature, the first data characteristics, and the millimeter wave gathered from millimetre-wave radar are extracted from the laser data of laser radar collection
The data characteristics of extracting data second.
It should be noted that " first " and " second " here and the implication without ranking, simply to special to data
Sign makes a distinction.
Step 203, obtain the avoidance parameter of the unmanned vehicle of avoidance deep learning model output, with based on avoidance parameter to nothing
People's car is controlled.
In the present embodiment, above-mentioned unmanned vehicle obtains nobody that avoidance deep learning model exported according to the data of input
The avoidance parameter of car, to be controlled based on avoidance parameter to unmanned vehicle.
In some optional implementations of the present embodiment, avoidance parameter includes braking parameters and/or turn around parameters.
In the present embodiment, parameter used by braking parameters is brakes, the size of the deceleration of unmanned vehicle can be included,
The direction of the deceleration of unmanned vehicle can also be included simultaneously.As a rule, the direction of unmanned vehicle deceleration is opposite with direct of travel.
The speed of driving can be controlled by braking parameters.Turn around parameters are the parameter that unmanned vehicle is turned to, and can be steering angles,
Such as steering wheel angle etc..The direction of driving can be controlled by turn around parameters.Above-mentioned unmanned vehicle can be by limiting or adjusting
Any one of whole above-mentioned two avoidance parameter, to carry out avoidance operation.
With continued reference to Fig. 3, Fig. 3 is shown according to one of the application scenarios of the control method for unmanned vehicle of the present embodiment
It is intended to.In Fig. 3 application scenarios, the above-mentioned acquisition of unmanned vehicle 301 is installed at least two sensors collection of the unmanned vehicle
Data 302.Afterwards, above-mentioned unmanned vehicle is by the avoidance deep learning model of acquired data input training in advance, avoidance depth
Learning model is used to characterizing the corresponding relation of the data that sensor gathered and the avoidance parameter of unmanned vehicle.Obtain avoidance depth
The avoidance parameter 303 of the unmanned vehicle of model output is practised, to be controlled 304 to unmanned vehicle based on avoidance parameter.
The method that above-described embodiment of the application provides obtains avoidance parameter by avoidance deep learning model, realizes pair
The control of driving.
With further reference to Fig. 4, it illustrates the flow 400 of another embodiment of the control method for unmanned vehicle.Should
For the flow 400 of the control method of unmanned vehicle, comprise the following steps：
Step 401, the data of at least two sensors collection are obtained, and obtain the current avoidance parameter of unmanned vehicle.
In the present embodiment, model can be trained before application model.Unmanned vehicle can obtain at least two
The data of sensor collection, and obtain current avoidance parameter.Above-mentioned braking parameters are generated by the driving behavior of user,
That is user is when driving the unmanned vehicle, the avoidance parameter of vehicle caused by the brake behavior taken.Unmanned vehicle herein can
To be that the unmanned vehicle specified can also be arbitrarily carrying out the unmanned vehicle of model training.Here at least two sensors peace
Loaded on the unmanned vehicle.
Step 402, using acquired data and current avoidance parameter as the input of avoidance deep learning model
And output, to be trained to avoidance deep learning model.
In the present embodiment, above-mentioned unmanned vehicle using the data acquired in step 401 and current avoidance parameter as
The input and output of above-mentioned avoidance deep learning model, to be trained to the avoidance deep learning model.
Step 403, the data of at least two sensors collection are obtained.
In the present embodiment, unmanned vehicle is provided with least two sensors, and the control method for unmanned vehicle runs on it
On unmanned vehicle can be by wired connection mode on either radio connection obtains from local or other electronic equipments
The data at least two sensors collection stated.Herein, the quantity of every kind of sensor can be one or two or
It is more than person.
In some optional implementations of the present embodiment, at least two sensors can include camera, laser thunder
Reach and millimetre-wave radar.
Specifically, camera can gather view data or video stream data.Laser radar is detected using laser,
The data of the return collected are also laser signal.Millimetre-wave radar is detected using millimeter wave, the return collected
Data be millimeter-wave signal.
Step 404, by the avoidance deep learning model of acquired data input training in advance.
In the present embodiment, above-mentioned unmanned vehicle can be by the avoidance deep learning mould of acquired data input training in advance
Type, so that the avoidance deep learning model is exported according to the data of input.Wherein, avoidance deep learning model is used to characterize
The data and the corresponding relation of the avoidance parameter of unmanned vehicle that sensor is gathered.Avoidance parameter is involved by unmanned vehicle avoiding obstacles
And parameter.Here avoidance parameter is the data that unmanned vehicle uses immediately.
Above-mentioned avoidance deep learning model can be SVMs (Support Vector Machine, SVM), simplicity
The training of the graders (Classifier) such as Bayesian model (Naive Bayesian Model, NBM) model obtains.In addition,
Above-mentioned image processing model can also be based on some classification functions (such as softmax functions etc.) and training in advance forms.
In some optional implementations of the present embodiment, avoidance deep learning model is trained in a manner of end to end
Obtain.
In the present embodiment, the model that end-to-end mode is trained can using data that sensor collects as input, and
Export the unmanned vehicle avoidance parameter to be used.
Avoidance deep learning model is a kind of deep neural network, can directly generate vehicle according to the data of collection
Avoidance parameter.Specifically, in the training process of the model, employ which kind of data is trained as input and output, then
In the application process of model, it becomes possible to according to this kind of input data, obtain corresponding output data.
Step 405, obtain the avoidance parameter of the unmanned vehicle of avoidance deep learning model output, with based on avoidance parameter to nothing
People's car is controlled.
In the present embodiment, above-mentioned unmanned vehicle obtains nobody that avoidance deep learning model exported according to the data of input
The avoidance parameter of car, to be controlled based on avoidance parameter to unmanned vehicle.
In some optional implementations of the present embodiment, avoidance parameter includes braking parameters and/or turn around parameters.
In the present embodiment, parameter used by braking parameters is brakes, the size of the deceleration of unmanned vehicle can be included,
The direction of the deceleration of unmanned vehicle can also be included simultaneously.As a rule, the direction of unmanned vehicle deceleration is opposite with direct of travel.
Turn around parameters are the parameter that is turned to of unmanned vehicle, can be steering angles, such as steering wheel angle etc..Above-mentioned unmanned vehicle can
With by limiting or adjusting any one of above-mentioned two avoidance parameter, to carry out avoidance operation.
The present embodiment, can be in the application process of model by being trained end-to-end to avoidance deep learning model
Avoidance parameter is obtained exactly.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, this application provides one kind to be used for unmanned vehicle
Control device one embodiment, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, and the device specifically can be with
Applied in various electronic equipments.
As shown in figure 5, the control device 500 for unmanned vehicle of the present embodiment includes：Acquiring unit 501, input block
502 and control unit 503.Wherein, acquiring unit 501, it is configured to obtain the data of at least two sensors collection；Input is single
Member 502, is configured to the avoidance deep learning model of acquired data input training in advance, wherein, the avoidance depth
Learning model is used to characterizing the corresponding relation of the data that sensor gathered and the avoidance parameter of unmanned vehicle；Control unit 503, matches somebody with somebody
The avoidance parameter of the unmanned vehicle for obtaining the avoidance deep learning model output is put, with based on the avoidance parameter pair
The unmanned vehicle is controlled.
In the present embodiment, acquiring unit 501 can by wired connection mode or radio connection from local or
The data of above-mentioned at least two sensors collection are obtained on other electronic equipments of person.Herein, the quantity of every kind of sensor can
Be one or two or more than.
In the present embodiment, input block 502 can be by the avoidance deep learning of acquired data input training in advance
Model, so that the avoidance deep learning model is exported according to the data of input.Wherein, avoidance deep learning model is used for table
The data and the corresponding relation of the avoidance parameter of unmanned vehicle that sign sensor is gathered.Avoidance parameter is unmanned vehicle avoiding obstacles institute
The parameter being related to.Here avoidance parameter is the data that unmanned vehicle uses immediately.
In the present embodiment, control unit 503 obtains the nothing that avoidance deep learning model is exported according to the data of input
The avoidance parameter of people's car, to be controlled based on avoidance parameter to unmanned vehicle.
In some optional implementations of the present embodiment, avoidance parameter includes braking parameters and/or turn around parameters.
In some optional implementations of the present embodiment, at least two sensors include camera, laser radar and
Millimetre-wave radar.
In some optional implementations of the present embodiment, avoidance deep learning model is trained in a manner of end to end
Obtain.
In some optional implementations of the present embodiment, device also includes：Parameter acquiring unit, it is configured to obtain
The data of at least two sensors collection, and the current avoidance parameter of unmanned vehicle is obtained, avoidance parameter is the driving row by user
For generation；Training unit, it is configured to using acquired data and current avoidance parameter as avoidance deep learning
The input and output of model, to be trained to avoidance deep learning model.
Below with reference to Fig. 6, it illustrates suitable for for realizing the computer system 600 of the unmanned vehicle of the embodiment of the present application
Structural representation.Unmanned vehicle shown in Fig. 6 is only an example, should not be to the function and use range band of the embodiment of the present application
Carry out any restrictions.
As shown in fig. 6, computer system 600 includes CPU (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 or be loaded into program in random access storage device (RAM) 603 from storage part 608 and
Perform various appropriate actions and processing.In RAM 603, also it is stored with system 600 and operates required various programs and data.
CPU 601, ROM 602 and RAM 603 are connected with each other by bus 604.Input/output (I/O) interface 605 is also connected to always
Line 604.
I/O interfaces 605 are connected to lower component：Importation 606 including keyboard, mouse etc.；Penetrated including such as negative electrode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.；Storage part 608 including hard disk etc.；
And the communications portion 609 of the NIC including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net performs communication process.Driver 610 is also according to needing to be connected to I/O interfaces 605.Detachable media 611, such as
Disk, CD, magneto-optic disk, semiconductor memory etc., it is arranged on as needed on driver 610, in order to read from it
Computer program be mounted into as needed storage part 608.
Especially, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable medium
On computer program, the computer program include be used for execution flow chart shown in method program code.In such reality
To apply in example, the computer program can be downloaded and installed by communications portion 609 from network, and/or from detachable media
611 are mounted.When the computer program is performed by CPU (CPU) 601, perform what is limited in the present processes
Above-mentioned function.It should be noted that the computer-readable medium of the application can be computer-readable signal media or calculating
Machine readable storage medium storing program for executing either the two any combination.Computer-readable recording medium for example can be --- but it is unlimited
In system, device or the device of --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than combination.Calculate
The more specifically example of machine readable storage medium storing program for executing can include but is not limited to：Electrically connecting, be portable with one or more wires
Formula computer disk, hard disk, random access storage device (RAM), read-only storage (ROM), erasable programmable read only memory
(EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memory device or
The above-mentioned any appropriate combination of person.In this application, computer-readable recording medium can be any includes or storage program
Tangible medium, the program can be commanded execution system, device either device use or it is in connection.And in this Shen
Please in, computer-readable signal media can include in a base band or as carrier wave a part propagation data-signal, its
In carry computer-readable program code.The data-signal of this propagation can take various forms, and include but is not limited to
Electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computer-readable
Any computer-readable medium beyond storage medium, the computer-readable medium can send, propagate or transmit for by
Instruction execution system, device either device use or program in connection.The journey included on computer-readable medium
Sequence code can be transmitted with any appropriate medium, be included but is not limited to：Wirelessly, electric wire, optical cable, RF etc., or it is above-mentioned
Any appropriate combination.
Flow chart and block diagram in accompanying drawing, it is illustrated that according to the system of the various embodiments of the application, method and computer journey
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
The part of one module of table, program segment or code, the part of the module, program segment or code include one or more use
In the executable instruction of logic function as defined in realization.It should also be noted that marked at some as in the realization replaced in square frame
The function of note can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actually
It can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.Also to note
Meaning, the combination of each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart can be with holding
Function as defined in row or the special hardware based system of operation are realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hard
The mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bag
Include acquiring unit, input block and control unit.Wherein, the title of these units is not formed to the unit under certain conditions
The restriction of itself, for example, acquiring unit is also described as " unit for obtaining the data of at least two sensors collection ".
As on the other hand, present invention also provides a kind of computer-readable medium, the computer-readable medium can be
Included in device described in above-described embodiment；Can also be individualism, and without be incorporated the device in.Above-mentioned calculating
Machine computer-readable recording medium carries one or more program, when said one or multiple programs are performed by the device so that should
Device：Obtain the data of at least two sensors collection；By the avoidance deep learning mould of acquired data input training in advance
Type, wherein, avoidance deep learning model is used to characterize the data pass corresponding with the avoidance parameter of unmanned vehicle that sensor is gathered
System；The avoidance parameter of the unmanned vehicle of avoidance deep learning model output is obtained, to be controlled based on avoidance parameter to unmanned vehicle.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the art
Member should be appreciated that invention scope involved in the application, however it is not limited to the technology that the particular combination of above-mentioned technical characteristic forms
Scheme, while should also cover in the case where not departing from foregoing invention design, carried out by above-mentioned technical characteristic or its equivalent feature
The other technical schemes for being combined and being formed.Such as features described above has similar work(with (but not limited to) disclosed herein
The technical scheme that the technical characteristic of energy is replaced mutually and formed.
Claims (12)
1. a kind of control method for unmanned vehicle, it is characterised in that the unmanned vehicle is provided with least two sensors, described
Method includes：
Obtain the data of at least two sensors collection；
By the avoidance deep learning model of acquired data input training in advance, wherein, the avoidance deep learning model is used
The data and the corresponding relation of the avoidance parameter of unmanned vehicle gathered in sign sensor；
Obtain the avoidance parameter of the unmanned vehicle of avoidance deep learning model output, with based on the avoidance parameter to institute
Unmanned vehicle is stated to be controlled.
2. the control method according to claim 1 for unmanned vehicle, it is characterised in that the avoidance parameter includes brake
Parameter and/or turn around parameters.
3. the control method according to claim 1 for unmanned vehicle, it is characterised in that at least two sensor bag
Include camera, laser radar and millimetre-wave radar.
4. the control method according to claim 1 for unmanned vehicle, it is characterised in that the avoidance deep learning model
Train to obtain in a manner of end to end.
5. the control method according to claim 1 for unmanned vehicle, it is characterised in that described in the acquisition at least two
Before the data of individual sensor collection, methods described also includes：
Obtain the data of at least two sensors collection, and obtain the current avoidance parameter of unmanned vehicle, the avoidance parameter be by
The driving behavior generation of user；
Using acquired data and current avoidance parameter as the input and output of the avoidance deep learning model, with
The avoidance deep learning model is trained.
6. a kind of control device for unmanned vehicle, it is characterised in that the unmanned vehicle is provided with least two sensors, described
Device includes：
Acquiring unit, it is configured to obtain the data of at least two sensors collection；
Input block, it is configured to the avoidance deep learning model of acquired data input training in advance, wherein, it is described to keep away
Barrier deep learning model is used to characterizing the corresponding relation of the data that sensor gathered and the avoidance parameter of unmanned vehicle；
Control unit, it is configured to obtain the avoidance parameter of the unmanned vehicle of the avoidance deep learning model output, with base
The unmanned vehicle is controlled in the avoidance parameter.
7. the control device according to claim 6 for unmanned vehicle, it is characterised in that the avoidance parameter includes brake
Parameter and/or turn around parameters.
8. the control device according to claim 6 for unmanned vehicle, it is characterised in that at least two sensor bag
Include camera, laser radar and millimetre-wave radar.
9. the control device according to claim 6 for unmanned vehicle, it is characterised in that the avoidance deep learning model
Train to obtain in a manner of end to end.
10. the control device according to claim 6 for unmanned vehicle, it is characterised in that described device also includes：
Parameter acquiring unit, is configured to obtain the data of at least two sensors collection, and obtains the current avoidance of unmanned vehicle
Parameter, the avoidance parameter are generated by the driving behavior of user；
Training unit, it is configured to using acquired data and current avoidance parameter as the avoidance deep learning mould
The input and output of type, to be trained to the avoidance deep learning model.
11. a kind of unmanned vehicle, including：
One or more processors；
Storage device, for storing one or more programs,
When one or more of programs are by one or more of computing devices so that one or more of processors are real
The now method as described in any in claim 1-5.
12. a kind of computer-readable recording medium, is stored thereon with computer program, it is characterised in that the program is by processor
The method as described in any in claim 1-5 is realized during execution.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710791661.4A CN107515607A (en) | 2017-09-05 | 2017-09-05 | Control method and device for unmanned vehicle |
| PCT/CN2018/098630 WO2019047643A1 (en) | 2017-09-05 | 2018-08-03 | Control method and device for unmanned vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710791661.4A CN107515607A (en) | 2017-09-05 | 2017-09-05 | Control method and device for unmanned vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107515607A true CN107515607A (en) | 2017-12-26 |
Family
ID=60725124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710791661.4A Pending CN107515607A (en) | 2017-09-05 | 2017-09-05 | Control method and device for unmanned vehicle |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107515607A (en) |
| WO (1) | WO2019047643A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109141911A (en) * | 2018-06-26 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | The acquisition methods and device of the control amount of unmanned vehicle performance test |
| CN109324608A (en) * | 2018-08-31 | 2019-02-12 | 百度在线网络技术（北京）有限公司 | Unmanned vehicle control method, device, equipment and storage medium |
| WO2019047643A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术（北京）有限公司 | Control method and device for unmanned vehicle |
| CN109693672A (en) * | 2018-12-28 | 2019-04-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling pilotless automobile |
| WO2019179094A1 (en) * | 2018-03-23 | 2019-09-26 | 广州汽车集团股份有限公司 | Method and apparatus for maintaining driverless driveway, computer device, and storage medium |
| CN110967991A (en) * | 2018-09-30 | 2020-04-07 | 百度（美国）有限责任公司 | Method and device for determining vehicle control parameters, vehicle-mounted controller and unmanned vehicle |
| CN113705381A (en) * | 2021-08-11 | 2021-11-26 | 北京百度网讯科技有限公司 | Target detection method and device in foggy days, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106292704A (en) * | 2016-09-07 | 2017-01-04 | 四川天辰智创科技有限公司 | The method and device of avoiding barrier |
| CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
| CN106742717A (en) * | 2016-11-15 | 2017-05-31 | 江苏智石科技有限公司 | A kind of intelligent magazine transport vehicle based on 3D cameras |
| CN106873566A (en) * | 2017-03-14 | 2017-06-20 | 东北大学 | A kind of unmanned logistic car based on deep learning |
| CN106950964A (en) * | 2017-04-26 | 2017-07-14 | 北京理工大学 | Nobody electronic university student's equation motorcycle race and its control method |
| CN107065890A (en) * | 2017-06-02 | 2017-08-18 | 北京航空航天大学 | A kind of unmanned vehicle intelligent barrier avoiding method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009089369A1 (en) * | 2008-01-08 | 2009-07-16 | Raytheon Sarcos, Llc | Point and go navigation system and method |
| CN105843229B (en) * | 2016-05-17 | 2018-12-18 | 中外合资沃得重工（中国）有限公司 | Unmanned intelligent carriage and control method |
| CN106080590B (en) * | 2016-06-12 | 2018-04-03 | 百度在线网络技术（北京）有限公司 | The acquisition methods and device of control method for vehicle and device and decision model |
| CN106292666A (en) * | 2016-08-29 | 2017-01-04 | 无锡卓信信息科技股份有限公司 | Pilotless automobile barrier-avoiding method based on ultrasonic distance detection and system |
| CN206231471U (en) * | 2016-10-11 | 2017-06-09 | 深圳市招科智控科技有限公司 | A kind of unmanned bus of taxi pattern |
| CN106515728A (en) * | 2016-12-22 | 2017-03-22 | 深圳市招科智控科技有限公司 | System and method for avoiding collision and obstacle for a driverless bus |
| CN107515607A (en) * | 2017-09-05 | 2017-12-26 | 百度在线网络技术（北京）有限公司 | Control method and device for unmanned vehicle |
-
2017
- 2017-09-05 CN CN201710791661.4A patent/CN107515607A/en active Pending
-
2018
- 2018-08-03 WO PCT/CN2018/098630 patent/WO2019047643A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106394555A (en) * | 2016-08-29 | 2017-02-15 | 无锡卓信信息科技股份有限公司 | Unmanned automobile obstacle avoidance system and method based on 3D camera |
| CN106292704A (en) * | 2016-09-07 | 2017-01-04 | 四川天辰智创科技有限公司 | The method and device of avoiding barrier |
| CN106742717A (en) * | 2016-11-15 | 2017-05-31 | 江苏智石科技有限公司 | A kind of intelligent magazine transport vehicle based on 3D cameras |
| CN106873566A (en) * | 2017-03-14 | 2017-06-20 | 东北大学 | A kind of unmanned logistic car based on deep learning |
| CN106950964A (en) * | 2017-04-26 | 2017-07-14 | 北京理工大学 | Nobody electronic university student's equation motorcycle race and its control method |
| CN107065890A (en) * | 2017-06-02 | 2017-08-18 | 北京航空航天大学 | A kind of unmanned vehicle intelligent barrier avoiding method and system |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019047643A1 (en) * | 2017-09-05 | 2019-03-14 | 百度在线网络技术（北京）有限公司 | Control method and device for unmanned vehicle |
| WO2019179094A1 (en) * | 2018-03-23 | 2019-09-26 | 广州汽车集团股份有限公司 | Method and apparatus for maintaining driverless driveway, computer device, and storage medium |
| US11505187B2 (en) | 2018-03-23 | 2022-11-22 | Guangzhou Automobile Group Co., Ltd. | Unmanned lane keeping method and device, computer device, and storage medium |
| CN109141911A (en) * | 2018-06-26 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | The acquisition methods and device of the control amount of unmanned vehicle performance test |
| US11148674B2 (en) | 2018-06-26 | 2021-10-19 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for acquiring control amount for performance test of unmanned vehicle |
| CN109324608A (en) * | 2018-08-31 | 2019-02-12 | 百度在线网络技术（北京）有限公司 | Unmanned vehicle control method, device, equipment and storage medium |
| US11320818B2 (en) | 2018-08-31 | 2022-05-03 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Method, apparatus, device and storage medium for controlling unmanned vehicle |
| CN110967991A (en) * | 2018-09-30 | 2020-04-07 | 百度（美国）有限责任公司 | Method and device for determining vehicle control parameters, vehicle-mounted controller and unmanned vehicle |
| CN109693672A (en) * | 2018-12-28 | 2019-04-30 | 百度在线网络技术（北京）有限公司 | Method and apparatus for controlling pilotless automobile |
| CN109693672B (en) * | 2018-12-28 | 2020-11-06 | 百度在线网络技术（北京）有限公司 | Method and device for controlling an unmanned vehicle |
| CN113705381A (en) * | 2021-08-11 | 2021-11-26 | 北京百度网讯科技有限公司 | Target detection method and device in foggy days, electronic equipment and storage medium |
| CN113705381B (en) * | 2021-08-11 | 2024-02-02 | 北京百度网讯科技有限公司 | Target detection method and device for foggy days, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019047643A1 (en) | 2019-03-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107515607A (en) | Control method and device for unmanned vehicle | |
| US11427215B2 (en) | Systems and methods for generating a task offloading strategy for a vehicular edge-computing environment | |
| EP3451230A1 (en) | Method and apparatus for recognizing object | |
| CN107063711A (en) | Method and apparatus for testing unmanned vehicle | |
| CN110654381B (en) | Method and device for controlling a vehicle | |
| CN112001287B (en) | Point cloud information generation method and device for obstacle, electronic equipment and medium | |
| CN109455180A (en) | Method and apparatus for controlling unmanned vehicle | |
| CN110390237A (en) | Processing Method of Point-clouds and system | |
| CN111598006B (en) | Method and device for labeling objects | |
| CN109878512A (en) | Automatic Pilot control method, device, equipment and computer readable storage medium | |
| US20210089792A1 (en) | Method and apparatus for outputting information | |
| CN107521500A (en) | Information acquisition method and device | |
| CN107830869A (en) | Information output method and device for vehicle | |
| CN115761702B (en) | Vehicle track generation method, device, electronic equipment and computer readable medium | |
| CN110696826A (en) | Method and device for controlling a vehicle | |
| CN112622923B (en) | Method and device for controlling a vehicle | |
| CN107527074A (en) | Image processing method and device for vehicle | |
| CN107622241A (en) | Display methods and device for mobile device | |
| CN110654380A (en) | Method and device for controlling a vehicle | |
| CN112649011B (en) | Vehicle obstacle avoidance method, device, equipment and computer readable medium | |
| CN109784129A (en) | Information output method and device | |
| CN110321854B (en) | Method and apparatus for detecting target object | |
| CN117218187A (en) | Pedestrian position information generation method, device, equipment and computer readable medium | |
| CN114523985B (en) | Unmanned vehicle motion decision method and device based on sensing result of sensor | |
| CN114724116B (en) | Vehicle traffic information generation method, device, equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171226 |
|
| RJ01 | Rejection of invention patent application after publication |