Embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouchedThe 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 toBe easy to description, 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 phaseMutually combination.Describe the application in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can be using the method for controlling a vehicle of the application or for the example for the device for controlling vehicleSexual system framework 100.
As shown in figure 1, system architecture 100, which can include system architecture 100, can include vehicle 101, network 102 and to car101 provide the server 103 supported.Vehicle intelligent equipment 104 can be provided with vehicle 101.Network 102 is used in terminalThe medium of communication link is provided between equipment 101 and server 103.Network 102 can include various connection types, for example, haveLine, wireless communication link or fiber optic cables etc..
The control system of vehicle 101 is installed, it can obtain regarding of being installed on vehicle 101 in vehicle intelligent equipment 104Feel the image on the direct of travel for the vehicle 101 that sensor is gathered, and determine whether deposited on the direct of travel of vehicle according to imageIn barrier；Then there is barrier on the direct of travel in response to determining vehicle, the position of barrier is determined according to imageInformation, and positional information and the positional information of vehicle according to barrier, adjust the route planning information of the vehicle obtained in advanceThe expectation driving trace included, finally controls vehicle to be travelled according to the expectation driving trace after adjustment.Vehicle intelligent equipment 104It can also be interacted by network 102 with server 103, with RX path planning information, control instruction etc..
Vehicle 101 is also equipped with various sensors, for example, vision sensor, gyroscope, accelerometer etc..Driven eachDigital encoder for measuring angular displacement can be installed in driving wheel, digital encoder can determine the traveling of driving wheel away fromFrom.Herein, the type of drive of vehicle 101 can be the mode of two-wheeled Differential Driving.It should be noted that vehicle 101 can pacifyEquipped with all kinds and the sensor of function in addition to above-mentioned enumerate, it will not be repeated here.
Server 103 can be to provide the server of various services, for example, vehicle 101 is managed and distributes taskManagement server, management server can send the information such as straight movement control instruction to vehicle intelligent equipment 104, so that vehicle intelligentEquipment 104 is controlled to vehicle 101.
It is pointed out that the sensor that the instruction of above-mentioned straight movement control can also be installed in vehicle 101 detect it is a certainTriggered automatically during information, now, network 102 and server 103 can be not present in said system framework 100.
It should be noted that the method for controlling a vehicle that the embodiment of the present application is provided is general by vehicle intelligent equipment104 are performed, and correspondingly, the device for controlling vehicle is generally positioned in vehicle intelligent equipment 104.
It should be understood that the number of the vehicle, vehicle intelligent equipment, network and server in Fig. 1 is only schematical.RootFactually now need, can have any number of vehicle, vehicle intelligent equipment, network and server.
With continued reference to Fig. 2, the flow of one embodiment of method for controlling a vehicle according to the application is shown200.The method for controlling a vehicle, comprises the following steps：
With continued reference to Fig. 2, the flow of one embodiment of method for controlling a vehicle according to the application is shown200.The method for controlling a vehicle, comprises the following steps：
Step 201, the image on the direct of travel for the vehicle for obtaining the vision sensor collection installed on vehicle.
In the present embodiment, the electronic equipment of method for controlling a vehicle operation thereon is (such as vehicle-mounted shown in Fig. 1Smart machine) image on the direct of travel for the vehicle that the vision sensor installed on vehicle is gathered can be obtained first.VehicleCan utilize information interchange, carry out independent planning, adjust and perform the vehicle of its action, such as autonomous vehicle(Autonomous Vehicle).Vision sensor can obtain external environment condition image letter using optical element and imaging deviceThe instrument of breath, its major function is to obtain enough NI Vision Builder for Automated Inspection most original images to be processed.Vision sensor can be withIt is various picture pick-up devices, for example, CCD (Charge Coupled Device, charge coupling device) video camera, digital camera.Image on the direct of travel of vehicle can be the image of vehicle front, can also be the image of rear view of vehicle during reversing.VehicleHeadstock and the tailstock one or more vision sensors can be installed.
Step 202, determined to whether there is barrier on the direct of travel of vehicle according to image.
In the present embodiment, above-mentioned electronic equipment can determine the traveling side of vehicle according to the image obtained in step 201It whether there is barrier upwards.The target area in the image that collects can be determined using machine vision, target area canTo be interpreted as larger possibility as the region of the image of barrier.Some image processing methods can be used to the image that getsHandled, image processing method can include image rectification, image filtering, image gray processing, image enhaucament etc..Then can be withImage segmentation is carried out, image segmentation is exactly to divide the image into several regions specific, with unique properties.Image segmentation sideMethod mainly includes the dividing method based on threshold value, the dividing method based on region, the dividing method based on edge and based on spyDividing method of theorem opinion etc..
In deep learning field, multilayer neural network model, such as deep neural network, convolutional Neural net can be usedNetwork, to carry out the segmentation of image.The image of moving object can also be partitioned into by motion detecting technology, can be based on particle filterRipple algorithm carries out the tracking of target area.As an example, system model and observation can be set up according to target area actual motionModel, calculates color, the gradient of target area, and constructs similarity function.And worked as by particle filter acquisition target areaPreceding observation, is handled the state average and covariance of particle collection using Kalman filtering, produces new Gaussian Profile,Then according to the new particle collection of the Gaussian Profile of generation sampling, weights and output are calculated, last resampling particle collection completes visionTracking process.By the tracking to target area, the row of vehicle in the image subsequently obtained can be more accurately and efficiently determinedEnter and whether there is barrier on direction.
In some optional implementations of the present embodiment, determined according to image on the direct of travel of vehicle with the presence or absence of barrierHinder thing, including：Image segmentation is carried out to image and obtains at least one subgraph；Determined based on the image classification model pre-establishedIt whether there is obstructions chart picture, pair that image classification model is used between phenogram picture and image tag at least one subgraphIt should be related to, image tag is used to indicate whether image is obstructions chart picture；Exist in response to determining at least one subgraphObstructions chart picture, determines there is barrier on the direct of travel of vehicle.
, can be to the image of the real-time collection of vision sensor in this implementation, or pass through some image processing methodsTreated image carries out image segmentation, using the subgraph after segmentation as input, regard the label of subgraph as output, trainingInitial model-naive Bayesian (Naive Bayesian Model, NBM) or SVMs (Support VectorMachine, SVM) etc. be used for classify model, obtain image classification model.Image classification model can also be technical staff's basePre-establish in the statistics to substantial amounts of image and image tag, pair of be stored with image or characteristics of image and image tagThe mapping table that should be related to；It equally can be the video by gathering different scenes in road, form positive and negative sample database,Positive negative sample is learnt using feature extraction and mode identification method training, obtains characterizing road barrier feature, for barrierThe model for hindering object image and non-obstructions chart picture to be classified.
In some optional implementations of the present embodiment, determined according to image on the direct of travel of vehicle with the presence or absence of barrierHinder thing, including：Semantic segmentation is carried out to image, collection of each subgraph included by image for the probability of obstructions chart picture is obtainedClose；Set in response to determining probability includes the probability more than predetermined threshold value, determines there is barrier on the direct of travel of vehicleHinder thing.
In the present embodiment, the semantic segmentation of image, is exactly briefly a given pictures, to each on picturePixel is classified, and for the detection of barrier, the scope where color value that can be by judging the pixel in image is determinedGo out the probable value that each pixel belongs to barrier.Can by image import training in advance full convolutional network model, obtain withThe corresponding region of the pixel of each in image is the probability of barrier region.Optionally, can also using the pixel of each in image asNode in condition random field, and using the relation in image between pixel and pixel as the side in condition random field, according to the 3rdProbability and the conditional random field models of training in advance determine the first probability.
In this implementation, can the framework based on deep learning, training data, instruction are used as using the image that manually marksPractice an efficient Road image segmentation model based on full convolutional network.Full convolutional network model compares traditional convolution nerve netNetwork model, eliminates the full articulamentum in network structure, greatly reduces the parameter of model, while the side for passing through up-samplingMethod, divides the image into the forecasting problem for being transformed into a pixel-wise (pixel for pixel), compared to traditional patch-wiseThe method of (block of pixels is to block of pixels) has saved the calculating time.Then, CRF (conditional random can be usedField algorithm, condition random field) and image enhaucament the further optimization processing result of method.
Step 203, there is barrier on the direct of travel in response to determining vehicle, the position of barrier is determined according to imageConfidence ceases.
In the present embodiment, there is barrier on direct of travel of the above-mentioned electronic equipment in response to determining vehicle in step 202Hinder thing, the positional information of barrier is determined according to image.It is determined that in the absence of in the case of barrier, the motion of vehicle completely byPath planning is guided, that is, conventional path following strategy.When there is barrier, above-mentioned electronic equipment can utilize angle pointDetection method calculates target area in the position of image slices vegetarian refreshments.By the inside and outside parameter for the vision sensor demarcated in advance, asRelation between plain plane coordinate system, photo coordinate system, camera coordinates system and world coordinate system carries out three-dimensional reconstruction, finally may be usedTo obtain coordinate of the barrier under world coordinate system.
In some optional implementations of the present embodiment, there is obstacle on the direct of travel in response to determining vehicleThing, the positional information of barrier is determined according to image, including：Figure is shown according to the calibrating parameters and barrier of vision sensorPosition as in, determines the positional information of barrier.The external parameter of vision sensor can be determined using three line calibration methods, withExemplified by vision sensor is video camera, the external parameter of video camera can include video camera with respect to the angle of heel of car body, the angle of pitch,The lateral separation of height and video camera photocentre away from the car body longitudinal axis of deflection, video camera in car body from the ground.Need explanationIt is that above-mentioned three line calibration method is widely studied at present and application known technology, be will not be repeated here.
Step 204, according to the positional information of barrier and the positional information of vehicle, the path of the vehicle obtained in advance is adjustedThe expectation driving trace that planning information includes.
In the present embodiment, above-mentioned electronic equipment can be according to the positional information and car of the barrier obtained in step 203Positional information, adjust the expectation driving trace that the route planning information of vehicle obtained in advance includes.Path planning is believedBreath can the above-mentioned electronic equipment in vehicle management direction issue, above-mentioned electronic equipment can using Bayes' assessment, extensionThe information fusion methods such as Kalman filtering method, neutral net and fuzzy reasoning method, by the information and path planning of vision sensorInformation fusion, obtains road precise information, to make accurate road decision-making.
In the present embodiment, above-mentioned electronic equipment can be primarily based on vehicle and seat of the barrier under world coordinate systemMark, calculates the laterally and longitudinally distance of vehicle and barrier.Longitudinal direction can refer to vehicle traveling direction, can laterally refer toThe vertical direction in direction of vehicle traveling.The lateral separation and fore-and-aft distance of vehicle and barrier are also based on, vehicle is calculatedWith the angular deviation of barrier.Angular deviation can be calculated by below equation：
θ=arctan (W/N) (1)
Wherein, θ represents the angular deviation of vehicle and barrier；W represents the lateral separation of barrier relative vehicle, barrierIn vehicle right side for just, left side is negative；N represents the fore-and-aft distance of barrier relative vehicle, and barrier is in front of vehicle travelingJust, vehicle traveling rear is negative.
In some optional implementations of the present embodiment, according to the positional information of barrier and the positional information of vehicle,The expectation driving trace that the route planning information of the vehicle obtained in advance includes is adjusted, including：Believed according to the position of barrierThe positional information of breath and vehicle, determines the distance between vehicle and barrier information；Melted using the information based on Bayesian EstimationConjunction method, driving trace is expected according to range information adjustment.Specifically, can be carried out to the characteristics of motion of motor-driven barrier effectiveState precognition, the method that combining target Bayesian forecasting carries out real-time route planning draws to adjust by local repeatedly weight-normalityExpect driving trace.First to the key node of vehicle row track, using dangerous cost constraints is quantified, set upSynthetic threat assess database, will threaten center as Wo Ruonuoyi (VORONOI) figure point, using threaten size asThe distance measure of VORONOI figure adjacent domains, builds the VORONOI figures for threatening configuration.Then dijkstra's algorithm (single source is usedShortest path first), Double-Sweeping (Double swap algorithm) scheduling algorithm search out it is optimal between target point and vehiclePath or sub-optimal path, it is established that the feasible path of vehicle.Optionally, neutral net-EKF can also be utilizedDriving trace is expected in method (NNEKF, Neural network Extended Kalman Filter) adjustment.
Step 205, control vehicle is travelled according to the expectation driving trace after adjustment.
In the present embodiment, above-mentioned electronic equipment can control vehicle according to the desired row obtained after being adjusted through step 204Sail track traveling.Based on the model- following control strategy for taking aim at a method in advance or in the prior art other model- following control strategies, essence can be usedReally the speed and steering angle of control vehicle, accurately evade road barrier.
The vehicle for the vision sensor collection that the method that above-described embodiment of the application is provided is installed by obtaining on vehicleDirect of travel on image, and determined according to image to whether there is barrier on the direct of travel of vehicle；Then in response to trueMake and there is barrier on the direct of travel of vehicle, the positional information of barrier is determined according to image, and according to the position of barrierConfidence ceases the positional information with vehicle, adjusts the expectation driving trace that the route planning information of the vehicle obtained in advance includes,Finally control vehicle is travelled according to the expectation driving trace after adjustment, improves the efficiency of wagon control.
With continued reference to Fig. 3, Fig. 3 is a signal of the application scenarios of the method for controlling a vehicle according to the present embodimentFigure.In Fig. 3 application scenarios, the vehicle intelligent equipment for controlling vehicle 301 gets the path planning of server transmissionInformation 304, starts to control vehicle 301 to travel according to the expectation driving trace in route planning information, due to can on direct of travelCan there can be barrier, so needing to obtain the traveling side for the vehicle that the vision sensor 302 installed on vehicle 301 is gathered in real timeUpward image 305, and determined according to image 305 on the direct of travel of vehicle with the presence or absence of barrier；Then in response to determiningGo out and there is barrier on the direct of travel of vehicle, the positional information of barrier is determined according to image, and according to the position of barrierThe positional information of information and vehicle, adjusts the expectation driving trace that the route planning information of the vehicle obtained in advance includes, mostControl vehicle is travelled according to the expectation driving trace after adjustment afterwards, realizes the avoidance of vehicle.
With continued reference to Fig. 4, the flow of one embodiment of method for controlling a vehicle according to the application is shown400.The method for controlling a vehicle, comprises the following steps：
Step 401, the image on the direct of travel for the vehicle for obtaining the vision sensor collection installed on vehicle.
In the present embodiment, the electronic equipment of method for controlling a vehicle operation thereon is (such as vehicle-mounted shown in Fig. 1Smart machine) image on the direct of travel for the vehicle that the vision sensor installed on vehicle is gathered can be obtained first.
Step 402, determined to whether there is barrier on the direct of travel of vehicle according to image.
In the present embodiment, above-mentioned electronic equipment can determine the traveling side of vehicle according to the image obtained in step 401It whether there is barrier upwards.
Step 403, there is barrier on the direct of travel in response to determining vehicle, the position of barrier is determined according to imageConfidence ceases.
In the present embodiment, there is barrier on direct of travel of the above-mentioned electronic equipment in response to determining vehicle in step 402Hinder thing, the positional information of barrier is determined according to image.
Step 404, according to the positional information of barrier and the positional information of vehicle, the path of the vehicle obtained in advance is adjustedThe expectation driving trace that planning information includes.
In the present embodiment, above-mentioned electronic equipment can be according to the positional information and car of the barrier obtained in step 403Positional information, adjust the expectation driving trace that the route planning information of vehicle obtained in advance includes.
Step 405, control vehicle is travelled according to the expectation driving trace after adjustment.
In the present embodiment, above-mentioned electronic equipment can control vehicle according to the desired row obtained after being adjusted through step 404Sail track traveling.It can use based on the model- following control strategy for taking aim at a method in advance or other model- following control strategies, accurately control vehicleSpeed and steering angle, accurately evade road barrier.Based on the model- following control strategy for taking aim at a method in advance, i.e., in road ahead oneThe local setting one of set a distance is pre- to be taken aim at a little, by the pre- lateral separation taken aim at a little with expectation road of control, to realize to expecting roadThe tracking in footpath.
In the present embodiment, the rate-determining steps in step 405 resolve into 5 following sub-steps, i.e.,：Step 4051, stepRapid 4052, step 4053, step 4054 and step 4055.
Step 4051, the wheelbase based on the current posture information of the driving trace after adjustment, vehicle and vehicle, is determined nextThe target position information of vehicle in individual default driving cycle.
In the present embodiment, above-mentioned electronic equipment can be based on the current posture information of the driving trace after adjustment, vehicleWith the wheelbase of vehicle, the target position information of vehicle in next default driving cycle is determined.The current posture information of vehiclePositional information, speed and the course angle of vehicle can be included, posture information can be obtained from the integrated navigation system of vehicle.Driving trace after adjustment is discrete, can be represented with matrix Z.The target location of vehicle in next default driving cycleIt can be the pre- position taken aim at a little, in order to realize more accurate wagon control, system delay can be taken into account.
The radius of turn of last driving cycle vehicle can be calculated by equation below：
Wherein, R0The radius of turn of last driving cycle vehicle is represented, L represents vehicle wheelbase, δ0Represent last driving cycleThe corner of wheel.
Because the software and hardware system of vehicle can have system delay, vehicle can be predicted due to delay meeting by equation belowTraveling position extremely, and in delay time course angle variable quantity：
I0=V0t0 (3)
Wherein, t0Represent system delay time, V0Represent last driving cycle Vehicle Speed, I0Represent t0Interior vehicleThe arc length of traveling, D0Represent I0Corresponding chord length, ω0Represent the course angle of last driving cycle vehicle, (XC, YC) represent prediction bitsPut the coordinate of relative vehicle position, (XW, YW) coordinate of the predicted position under world coordinate system is represented, Δ ω represents delay timeThe variable quantity of interior course angle.
According to coordinate (XW, YW) predicted position and the distance of all points nearby on the driving trace after adjustment can be calculated, fromMiddle coordinate (the X for obtaining closest pointZ, YZ), the pre- seat taken aim at a little can be obtained according to the preview distance k of setting, and matrix ZMark (XP, YP)。
Step 4052, according to target position information and posture information, driving parameters of the vehicle in driving cycle are determined, OKSailing parameter includes travel speed and steering angle.
In the present embodiment, above-mentioned electronic equipment can determine vehicle at this according to target position information and posture informationThe driving parameters of driving cycle, driving parameters include travel speed and steering angle of wheel.Travel speed can be according to vehicle rowThe road conditions sailed are determined, for example, road conditions are poor, or the driving trace degree of crook after adjustment is larger can suitably relatively low vehicleSpeed.
Vehicle location can be determined by equation below and a position lateral deviation is taken aim in advance：
BIAS=(XP-XW)·sin(π+ω+Δω)-(YP-YW)·cos(π+ω+Δω)(10)
Wherein, BIAS represents vehicle location and takes aim at a position lateral deviation in advance, and ω represents the course angle of vehicle.
Then, steering angle of wheel in this driving cycle can be determined by equation below：
Wherein, δ represents the steering angle of wheel of this driving cycle, and l represents the vehicle location of this driving cycle and taken aim at a little in advanceAir line distance.
Step 4053, control vehicle is travelled in driving cycle according to driving parameters.
In the present embodiment, above-mentioned electronic equipment can control vehicle to be travelled in driving cycle according to driving parameters.OnStating electronic equipment can be by the control to devices such as vehicular electric machine, steering wheels so that vehicle is joined in driving cycle according to travelingSail for several rows.
Step 4054, determine whether vehicle is located at the land for expecting driving trace.
In the present embodiment, above-mentioned electronic equipment can determine whether vehicle is located at the land for expecting driving trace.If it is, into step 4055, if it is not, then into step 4056.
Step 4055, if it is, stopping performing wagon control step.
In the present embodiment, above-mentioned electronic equipment can expect traveling rail in response to determining that vehicle is located in step 4054The land of mark, stops performing wagon control step.Above-mentioned electronic equipment can also be used to indicate vehicle in response to receivingStop the instruction for being used to change vehicle running state that traveling or other vehicle management sides are sent, stop performing wagon control stepSuddenly.
Step 406, if it is not, then continuing executing with wagon control step.
In the present embodiment, above-mentioned electronic equipment can expect traveling in response to determining that vehicle is not located in step 4054The land of track, continues executing with wagon control step.Above-mentioned electronic equipment can determine this traveling week by equation belowSome parameters in phase, so that next traveling computation of Period is used.
It is possible, firstly, to determine this driving cycle inside turn radius and traveling arc length by equation below：
Wherein, R represents the radius of turn and arc length in this driving cycle, and I represents the traveling arc length in this driving cycle.
Secondly, it can determine that vehicle drives to the pre- running time taken aim at a little, formula in this driving cycle by equation belowIt is as follows：
Wherein, t represents that vehicle drives to the pre- running time taken aim at a little in this driving cycle, and V is represented in this driving cycleTravel speed.
Then, wheel steering angle variable quantity in this driving cycle can be determined by equation below, formula is as follows：
Wherein, Δ δ represents wheel steering angle variable quantity in this driving cycle.
Finally, it can determine that vehicle is taking aim at course angle a little in advance in this driving cycle by equation below：
ω1=ω0+Δδ (16)
Wherein, ω1Represent that vehicle is taking aim at course angle a little in advance in this driving cycle.
In the present embodiment, above-mentioned electronic equipment can determine the course angle that is embodied of driving trace and one's own profession after adjustmentSail vehicle in the cycle and, in the deviation for taking aim at course angle a little in advance, regard the minimum wheel steering angle of the deviation determined as this driving cycleWheel steering angle.Parameter that then can be by more than in this driving cycle, as the parameter of last driving cycle in step 4051,Start to perform step 4051 again to determine that the pre- of next driving cycle takes aim at a position.
Figure 4, it is seen that compared with the corresponding embodiments of Fig. 2, the method for controlling a vehicle in the present embodimentFlow 400 highlight control vehicle the step of travelled according to the expectation driving trace after adjustment.Thus, the present embodiment is describedScheme can realize more accurate wagon control.
With further reference to Fig. 5, as the realization to the above method, this application provides a kind of device for being used to control vehicleOne embodiment, the device embodiment is corresponding with the embodiment of the method shown in Fig. 2, and the device specifically can apply to variousIn electronic equipment.
As shown in figure 5, the present embodiment be used for control the device 500 of vehicle to include：Acquiring unit 501, first determines listMember 502, the second determining unit 503, adjustment unit 504, control unit 505, wherein, acquiring unit 501, for obtaining vehicleImage on the direct of travel of the vehicle of the vision sensor collection of installation；First determining unit 502, for being determined according to imageIt whether there is barrier on the direct of travel of vehicle；Second determining unit 503, for the direct of travel in response to determining vehicleOn there is barrier, the positional information of barrier is determined according to image；Adjustment unit 504, for being believed according to the position of barrierThe positional information of breath and vehicle, adjusts the expectation driving trace that the route planning information of the vehicle obtained in advance includes；ControlUnit 505, for controlling vehicle to be travelled according to the expectation driving trace after adjustment.
In the present embodiment, acquiring unit 501, the first determining unit 502, the second determining unit 503, adjustment unit 504,The specific processing of control unit 505 may be referred to Fig. 2 correspondence embodiments step 201, step 202, step 203, step 204, stepRapid 205 detailed description, will not be repeated here.
In some optional implementations of the present embodiment, the first determining unit 502, including：First segmentation subelement (figureNot shown in), obtain at least one subgraph for carrying out image segmentation to image；First determination subelement (is not shown in figureGo out), for determining to whether there is obstructions chart picture, image at least one subgraph based on the image classification model pre-establishedThe corresponding relation that disaggregated model is used between phenogram picture and image tag, image tag is used to indicate whether image is barrierImage；Second determination subelement (not shown), in response to determining at least one subgraph there is obstructions chartPicture, determines there is barrier on the direct of travel of vehicle.
In some optional implementations of the present embodiment, the first determining unit 502, including：Second segmentation subelement (figureNot shown in), for carrying out semantic segmentation to image, obtain the probability that each subgraph included by image is obstructions chart pictureSet；3rd determination subelement (not shown), includes being more than default threshold for the set in response to determining probabilityThe probability of value, determines there is barrier on the direct of travel of vehicle.
In some optional implementations of the present embodiment, the second determining unit 503 is further configured to：According to regardingFeel that the calibrating parameters and barrier of sensor show position in the picture, determine the positional information of barrier.
In some optional implementations of the present embodiment, adjustment unit 504, including：4th subelement (does not show in figureGo out), for the positional information and the positional information of vehicle according to barrier, determine the distance between vehicle and barrier information；Subelement (not shown) is adjusted, for utilizing the information fuse device based on Bayesian Estimation, is adjusted according to range informationExpect driving trace.
In some optional implementations of the present embodiment, control unit 505 is further configured to：Execution is such as got offRate-determining steps：Wheelbase based on the current posture information of the driving trace after adjustment, vehicle and vehicle, is determined next defaultDriving cycle in vehicle target position information；According to target position information and posture information, determine vehicle in driving cycleInterior driving parameters, driving parameters include travel speed and steering angle；Control vehicle in driving cycle according to driving parametersTraveling；Determine whether vehicle is located at the land for expecting driving trace, if it is, stopping performing wagon control step；Such asIt is really no, then continue executing with wagon control step.
From figure 5 it can be seen that be used to controlling the device 500 of vehicle to install on vehicle by obtaining in the present embodiment regardsFeel sensor collection vehicle direct of travel on image, and determined according to image on the direct of travel of vehicle with the presence or absence of barrierHinder thing；Then there is barrier on the direct of travel in response to determining vehicle, the positional information of barrier determined according to image,And positional information and the positional information of vehicle according to barrier, adjusting the route planning information of the vehicle obtained in advance includesExpectation driving trace, finally control vehicle according to after adjustment expectation driving trace travel, improve the efficiency of wagon control.
Below with reference to Fig. 6, it illustrates suitable for for the department of computer science for the vehicle intelligent equipment for realizing the embodiment of the present applicationThe structural representation of system 600.Vehicle intelligent equipment shown in Fig. 6 is only an example, should not be to the work(of the embodiment of the present applicationAnd any limitation can be carried out using range band.
As shown in fig. 6, computer system 600 includes CPU (CPU) 601, it can be read-only according to being stored inProgram in memory (ROM) 602 or be loaded into program in random access storage device (RAM) 603 from storage part 608 andPerform various appropriate actions and processing.In RAM 603, the system that is also stored with 600 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 alwaysLine 604.
I/O interfaces 605 are connected to lower component：Importation 606 including keyboard, mouse etc.；Penetrated including such as negative electrodeThe 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 becauseThe network of spy's net performs communication process.Driver 610 is also according to needing to be connected to I/O interfaces 606.Detachable media 611, such asDisk, CD, magneto-optic disk, semiconductor memory etc., are arranged on driver 610, in order to read from it as neededComputer program be mounted into as needed storage part 608.
Especially, in accordance with an embodiment of the present disclosure, the process described above with reference to flow chart may be implemented as computerSoftware program.For example, embodiment of the disclosure includes a kind of computer program product, it includes being carried on computer-readable mediumOn computer program, the computer program include be used for execution flow chart shown in method program code.In such realityApply in example, the computer program can be downloaded and installed by communications portion 609 from network, and/or from detachable media611 are mounted.When the computer program is performed by CPU (CPU) 601, perform what is limited in the present processesAbove-mentioned functions.It should be noted that computer-readable medium described herein can be computer-readable signal media orComputer-readable recording medium either the two any combination.Computer-readable recording medium for example can be --- butBe not limited to --- electricity, magnetic, optical, electromagnetic, system, device or the device of infrared ray or semiconductor, or it is any more than combination.The more specifically example of computer-readable recording medium can include but is not limited to：Electrical connection with one or more wires,Portable computer diskette, hard disk, random access storage device (RAM), read-only storage (ROM), erasable type may be programmed read-only depositReservoir (EPROM or flash memory), optical fiber, portable compact disc read-only storage (CD-ROM), light storage device, magnetic memoryPart or above-mentioned any appropriate combination.In this application, computer-readable recording medium can any be included or storeThe tangible medium of program, the program can be commanded execution system, device or device and use or in connection.AndIn the application, computer-readable signal media can include believing in a base band or as the data of carrier wave part propagationNumber, wherein carrying computer-readable program code.The data-signal of this propagation can take various forms, including but notIt is limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be computerAny computer-readable medium beyond readable storage medium storing program for executing, the computer-readable medium can send, propagate or transmit useIn by the use of instruction execution system, device or device or program in connection.Included on computer-readable mediumProgram code any appropriate medium can be used to transmit, include but is not limited to：Wirelessly, electric wire, optical cable, RF etc., Huo ZheshangAny appropriate combination stated.
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 journeyArchitectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generationThe part of one unit of table, program segment or code, a part for the unit, program segment or code is comprising one or moreExecutable instruction for realizing defined logic function.It should also be noted that in some realizations as replacement, institute in square frameThe function of mark can also be with different from the order marked in accompanying drawing generation.For example, two square frames succeedingly represented are actualOn can perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is depending on involved function.AlsoIt is noted that the combination of each square frame in block diagram and/or flow chart and the square frame in block diagram and/or flow chart, Ke YiyongPerform the special hardware based system of defined function or operation to realize, or can be referred to specialized hardware with computerThe combination of order is realized.
Being described in unit involved in the embodiment of the present application can be realized by way of software, can also be by hardThe mode of part is realized.Described unit can also be set within a processor, for example, can be described as：A kind of processor bagInclude acquiring unit, the first determining unit, the second determining unit, adjustment unit, control unit.Wherein, the title of these units existsThe restriction to the unit in itself is not constituted in the case of certain, for example, acquiring unit is also described as " obtaining and pacifying on vehicleThe unit of image on the direct of travel of the vehicle of the vision sensor collection of dress ".
As on the other hand, present invention also provides a kind of nonvolatile computer storage media, the non-volatile calculatingMachine storage medium can be the nonvolatile computer storage media included in device described in above-described embodiment；Can also beIndividualism, without the nonvolatile computer storage media in supplying server.Above-mentioned nonvolatile computer storage mediaBe stored with one or more program, when one or more of programs are performed by an equipment so that the equipment：ObtainThe image picked up the car on a direct of travel for the vehicle of the upper vision sensor collection installed；The traveling side of vehicle is determined according to imageIt whether there is barrier upwards；There is barrier on direct of travel in response to determining vehicle, barrier is determined according to imagePositional information；According to the positional information of barrier and the positional information of vehicle, the path planning of the vehicle obtained in advance is adjustedThe expectation driving trace that information includes；Vehicle is controlled to be travelled according to the expectation driving trace after adjustment.
Above description is only the preferred embodiment of the application and the explanation to institute's application technology principle.People in the artMember should be appreciated that invention scope involved in the application, however it is not limited to the technology of the particular combination of above-mentioned technical characteristicScheme, while should also cover in the case where not departing from the inventive concept, is carried out by above-mentioned technical characteristic or its equivalent featureOther technical schemes formed by any combination.Such as features described above has similar work(with (but not limited to) disclosed hereinThe technical characteristic of energy carries out technical scheme formed by replacement mutually.