Summary of the invention
The embodiment of the present invention provides prediction technique, device, storage medium and the terminal device of a kind of decision of driving a vehicle, to solveOr alleviate above one or more technical problems in the prior art.
In a first aspect, the embodiment of the invention provides a kind of prediction techniques of decision of driving a vehicle, comprising:
Obtain the predicted motion track and real motion track of the barrier that vehicle encounters in the process of moving；
According to the predicted motion track and real motion track got, the accuracy rate of the predicted motion track is calculatedAnd/or recall rate；And
According to the accuracy rate and/or the recall rate, the driving decision of the vehicle is adjusted.
In one embodiment, it is described calculate the accuracy rate for predicting the prediction algorithm of the predicted motion track and/orRecall rate, comprising:
For each predicted motion track, according to multiple moment points of setting, the predicted motion rail is counted respectivelyRange difference of the mark with corresponding real motion track in the moment point；
According to the range difference of the multiple moment point, determine whether the predicted motion track predicts accurately；And
According to the prediction result of each predicted motion track, the quantity of the predicted motion track got and getThe quantity of real motion track calculates the accuracy rate and/or recall rate of the predicted motion track.
In one embodiment, the accuracy rate and/or recall rate for calculating the prediction algorithm, comprising:
According to the prediction result of each predicted motion track, the quantity of accurate prediction result is counted；
By the ratio of the quantity of the accurate prediction result and the quantity of the predicted motion track got, asThe accuracy rate of the predicted motion track；And/or
By the ratio of the quantity of the accurate prediction result and the quantity of the real motion track got, asThe recall rate of the predicted motion track.
In one embodiment, the driving decision of the adjustment vehicle, comprising:
If the accuracy rate is greater than the accuracy rate threshold value of setting, relax the error model of the driving decision of the vehicleIt encloses；
If the accuracy rate is less than the accuracy rate threshold value of setting, the error model of the driving decision of the vehicle is tightenedIt encloses；Or
If the recall rate is greater than the accuracy rate, the pre- measuring and calculating for predicting the predicted motion track is correctedMethod, and in conjunction with the motion profile that revised prediction algorithm is predicted, determine the driving decision of the vehicle.
Second aspect, the embodiment of the present invention provide a kind of prediction meanss of decision of driving a vehicle, comprising:
Track obtains module, for obtaining the predicted motion track of the barrier that vehicle encounters in the process of moving and trueMotion profile；
Computing module, for calculating the predicted motion according to the predicted motion track and real motion track gotThe accuracy rate and/or recall rate of track；And
Decision of driving a vehicle adjusts module, for adjusting the driving of the vehicle according to the accuracy rate and/or the recall rateDecision.
In one embodiment, the computing module includes:
Range difference statistic unit, for being directed to each predicted motion track, according to multiple moment points of setting, respectivelyCount range difference of the predicted motion track with corresponding real motion track in the moment point；
It determines prediction result unit, for the range difference according to the multiple moment point, determines the predicted motionWhether predict accurately track；And
Accuracy rate recall rate computing unit, for according to the prediction result of each predicted motion track, get it is pre-The quantity of real motion track surveying the quantity of motion profile and getting, calculate the predicted motion track accuracy rate and/Or recall rate.
In one embodiment, the accuracy rate recall rate computing unit includes:
Quantity statistics subelement counts accurately prediction knot for the prediction result according to each predicted motion trackThe quantity of fruit；
Accuracy rate computation subunit, for by the quantity of the accurate prediction result and the predicted motion gotThe ratio of the quantity of track, the accuracy rate as the predicted motion track；And/or
Recall rate computation subunit, for by the quantity of the accurate prediction result and the real motion gotThe ratio of the quantity of track, the recall rate as the predicted motion track.
In one embodiment, the driving decision adjustment module includes:
Error relaxes unit, if being greater than the accuracy rate threshold value of setting for the accuracy rate, relaxes the vehicleThe error range for decision of driving a vehicle；
Error tightens unit, if being less than the accuracy rate threshold value of setting for the accuracy rate, tightens the vehicleThe error range for decision of driving a vehicle；Or
Decision determination unit corrects the prediction algorithm, and tie if being greater than the accuracy rate for the recall rateThe motion profile that revised prediction algorithm is predicted is closed, determines the driving decision of the vehicle.
The third aspect, the embodiment of the invention provides a kind of prediction meanss of decision of driving a vehicle, the function of described device can be withBy hardware realization, corresponding software realization can also be executed by hardware.The hardware or software include it is one or more withThe corresponding module of above-mentioned function.
It include processor and memory, the memory in the pre- geodesic structure for decision of driving a vehicle in a possible designPrediction meanss for decision of driving a vehicle execute the Prediction program of above-mentioned driving decision, the processor is configured to for executing instituteState the program stored in memory.The prediction meanss of the driving decision can also include communication interface, for decision of driving a vehiclePrediction meanss and other equipment or communication.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, the prediction for decision of driving a vehicleComputer software instructions used in device, including program involved in the prediction technique for executing above-mentioned driving decision.
Any one technical solution in above-mentioned technical proposal have the following advantages that or the utility model has the advantages that
The embodiment of the present invention can use predicted motion track and real motion track to determine the accuracy rate of prediction algorithmAnd recall rate, the driving decision of vehicle is then adjusted according to accuracy rate and recall rate, can effectively improve the standard of driving decisionExactness.And the effect of assessment prediction can be carried out from two dimensions of accuracy rate and recall rate.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing descriptionSchematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is furtherAspect, embodiment and feature, which will be, to be readily apparent that.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize thatLike that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Referring to Fig. 1, the embodiment of the invention provides a kind of prediction techniques of decision of driving a vehicle.The present embodiment can be by followingMotor vehicle executes, comprising: the motor vehicle of the two-wheeleds such as electric bicycle, motorcycle, the four-wheels such as electronic, mixed dynamic or gasoline it is motor-drivenThe transit equipments such as vehicle and aircraft, steamer.The present embodiment may include step S100 to S400, as follows:
S100 obtains the predicted motion track and real motion track of the barrier that vehicle encounters in the process of moving.
In the present embodiment, barrier may include the traffic participants such as vehicle, pedestrian, bicycle and traffic street lamp,Static buildings etc..Predicted motion track can predict the motion profile of barrier in the process of moving by prediction algorithm.ExampleSuch as, pass through the parameters such as position, speed, the appearance of barrier in the sensor sensing external world of vehicle.Then, prediction algorithm benefitWith these parameters, the motion profile of barrier is constructed.Real motion track refers to that barrier moves true in environmentTrack, the GPS positioning data that each barrier can be obtained by GPS system construct the real motion track of each barrier.
S200 calculates the accuracy rate of predicted motion track according to the predicted motion track and real motion track gotAnd/or recall rate.
Wherein, accuracy rate indicates that for all predicted motion tracks, the order of accuarcy of predicted motion track is recalledRate indicates the order of accuarcy of predicted motion track for all real motion tracks.In the present embodiment, it predicts andPredicted motion track and real motion track not necessarily coincide.For example, vehicle predicted during sailing comeMotion profile has 12, and there was only 10 actually by the motion profile that GPS system determines.It is so more accurate for predictingThe probability that is determined relative to real motion track of track, recall rate can be described.
S300 adjusts the driving decision of vehicle according to accuracy rate and/or recall rate.
In some embodiments, it can use accuracy rate, adjust the error range of the algorithm of the driving decision of decision vehicle,Improve the reasonability of driving decision.
Specifically, if the accuracy rate of predicted motion track is greater than the accuracy rate threshold value of setting, relax the driving of vehicleThe error range of decision.If the accuracy rate of predicted motion track is less than the accuracy rate threshold value of setting, the driving of vehicle is tightenedThe error range of decision.
Illustratively, it is assumed that accuracy rate threshold value is 95%, if the accuracy rate of prediction algorithm is 98%, illustrates that traffic is joinedIt is travelled with person substantially according to prediction locus, error is small, can be with the error range of uncomfortable full line vehicle decision or by this errorRange is relaxed.Such as former error range is ± 2%, after relaxing, is adjusted to ± 5%.So that the selectivity of driving decision canWith larger.If the accuracy rate of prediction algorithm is 93%, illustrate that the trajectory error of traffic participant traveling is big, main vehicle isThe generation for avoiding accident, can tighten or correct prediction algorithm by this error range, to improve the safety of driving decision.
In some embodiments, accuracy rate or recall rate be can use to determine whether prediction algorithm needs to correct.ThenUsing revised prediction algorithm again predicted motion track, then, the driving for the motion profile adjustment vehicle newly predicted is utilizedDecision.
Specifically, if the recall rate of predicted motion track is greater than accuracy rate, amendment is used for predicted motion trajectory predictionsAlgorithm, and in conjunction with the motion profile that revised prediction algorithm is predicted, determine the driving decision of vehicle.
Illustratively, if the recall rate of prediction algorithm is 90%, but accuracy rate is 80%, at this point, predicting the fortune comeThe quantity of dynamic rail mark is higher than the quantity of real motion track, and accuracy rate is lower than accuracy rate threshold value 95%.If continuing to continue to useCurrent data carry out driving decision, it is possible to lead to safety accident.Therefore, in order to improve the accuracy of follow-up decision withAnd safety, prediction algorithm is modified.Then new prediction algorithm predicts the motion profile of barrier again, and using newlyThe motion profile of prediction carries out driving decision.
In some embodiments, referring to fig. 2, the process that accuracy rate and recall rate are calculated in above-mentioned steps S200, can be withIt is as follows including step S210 to step S230:
S210, for each predicted motion track, according to multiple moment points of setting, difference statistical forecast campaign railRange difference of the mark with corresponding real motion track in moment point.
S220 determines whether predicted motion track predicts accurately according to the range difference of multiple moment points.
S230 according to the prediction result of each predicted motion track, the quantity of the predicted motion track got and is gotReal motion track quantity, calculate predicted motion track accuracy rate and/or recall rate.
It is exemplary, the predicted motion of each moment point can be calculated separately on the 1st second, the 4th second and the 9th second at the time of pointThe range difference of track and corresponding real motion track.Such as: the 1st second range difference is 1.8m, the 4th second range difference is1.4m, the 9th second range difference are 1.7m.If range difference is less than 1.5m, then it is assumed that the prediction of prediction locus is accurate.IfRange difference is greater than or equal to 1.5m, then it is assumed that the prediction of prediction locus is inaccurate.It can be by counting this predicted motion railThe range difference at multiple moment of mark is greater than or equal to the quantity of 1.5m.If quantity is greater than the threshold value of setting, it may be considered that thisPredicted motion trajectory predictions are accurate.If quantity is less than given threshold, it may be considered that this predicted motion trajectory predictions mistake.
In some embodiments, it can calculate separately prediction algorithm according to the classification of barrier and predict such other movementThen the accuracy rate and recall rate of track according to the accuracy rate and recall rate of all categories for calculating prediction algorithm, adjust vehicleDriving decision.For example, sub-category adjustment prediction algorithm, predicts the motion profile of the barrier of respective classes again, it is then sharpDriving decision is carried out with the new predicted motion track of barrier of all categories.
Illustratively, classify respectively by pedestrian, motor vehicle, bicycle to motion profile.Then, prediction is calculated separatelyThe accuracy rate and recall rate of the motion profile of pedestrian, predict motor vehicle motion profile accuracy rate and recall rate and predictionThe accuracy rate and recall rate of the motion profile of bicycle.Then, distinguish according to accuracy rate determined by three kinds of classifications and recall rateThe adjustment that predicted motion track is carried out according to respective demand, then carries out driving decision again.
In some embodiments, it referring to Fig. 3, in above-mentioned steps S230, calculates the accuracy rate of predicted motion track and recallsRate may include step S232 to step S236, as follows:
S232 counts the quantity of accurate prediction result according to the prediction result of each predicted motion track.
S234, by the ratio of the quantity of accurate prediction result and the quantity of the predicted motion track got, as pre-Survey the accuracy rate of motion profile.
S236, by the ratio of the quantity of accurate prediction result and the quantity of the real motion track got, as pre-Survey the recall rate of motion profile.
Illustratively, if there are 10 real traces in this driving conditions predicts 12 in advance by prediction algorithmSurvey motion profile.If the judgement in 12 prediction locus there are 6 predicted motion tracks through the foregoing embodiment, it is believed that itsIt is that accurately, then accuracy rate is equal to 50% divided by 12 for 6, and recall rate is equal to 60% divided by 10 for 6.
Referring to fig. 4, the embodiment of the present invention provides a kind of prediction meanss of decision of driving a vehicle, comprising:
Track obtain module 100, for obtain the barrier that vehicle encounters in the process of moving predicted motion track andReal motion track；
Computing module 200, for calculating the prediction fortune according to the predicted motion track and real motion track gotThe accuracy rate and/or recall rate of dynamic rail mark；And
Decision of driving a vehicle adjusts module 300, for adjusting the vehicle according to the accuracy rate and/or the recall rateDriving decision.
In one embodiment, the computing module 200 includes:
Range difference statistic unit, for being directed to each predicted motion track, according to multiple moment points of setting, respectivelyCount range difference of the predicted motion track with corresponding real motion track in the moment point；
It determines prediction result unit, for the range difference according to the multiple moment point, determines the predicted motionWhether predict accurately track；And
Accuracy rate recall rate computing unit, for according to the prediction result of each predicted motion track, get it is pre-The quantity of real motion track surveying the quantity of motion profile and getting, calculate the predicted motion track accuracy rate and/Or recall rate.
In one embodiment, the accuracy rate recall rate computing unit includes:
Quantity statistics subelement counts accurately prediction knot for the prediction result according to each predicted motion trackThe quantity of fruit；
Accuracy rate computation subunit, for by the quantity of the accurate prediction result and the predicted motion gotThe ratio of the quantity of track, the accuracy rate as the predicted motion track；And/or
Recall rate computation subunit, for by the quantity of the accurate prediction result and the real motion gotThe ratio of the quantity of track, the recall rate as the predicted motion track.
In one embodiment, the driving decision adjustment module 300 includes:
Error relaxes unit, if being greater than the accuracy rate threshold value of setting for the accuracy rate, relaxes the vehicleThe error range for decision of driving a vehicle；
Error tightens unit, if being less than the accuracy rate threshold value of setting for the accuracy rate, tightens the vehicleThe error range for decision of driving a vehicle；Or
Decision determination unit corrects the prediction algorithm, and tie if being greater than the accuracy rate for the recall rateThe motion profile that revised prediction algorithm is predicted is closed, determines the driving decision of the vehicle.
The function of described device can also execute corresponding software realization by hardware realization by hardware.It is describedHardware or software include one or more modules corresponding with above-mentioned function.
It include processor and memory, the memory in the pre- geodesic structure for decision of driving a vehicle in a possible designPrediction meanss for decision of driving a vehicle execute the Prediction program of above-mentioned first aspect middle rolling car decision, the processor is configured toFor executing the program stored in the memory.The prediction meanss of the driving decision can also include communication interface, be used forThe prediction meanss and other equipment or communication for decision of driving a vehicle.
The embodiment of the present invention also provides a kind of prediction terminal device of decision of driving a vehicle, as shown in figure 5, the equipment includes: to depositReservoir 21 and processor 22, being stored in memory 21 can be in the computer program on processor 22.Processor 22 executes calculatingThe prediction technique of the driving decision in above-described embodiment is realized when machine program.The quantity of memory 21 and processor 22 can be oneIt is a or multiple.
The equipment further include:
Communication interface 23, for the communication between processor 22 and external equipment.
Memory 21 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatileMemory), a for example, at least magnetic disk storage.
If memory 21, processor 22 and the independent realization of communication interface 23, memory 21, processor 22 and communication are connectMouth 23 can be connected with each other by bus and complete mutual communication.Bus can be industry standard architecture (ISA,Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral Component) be totalLine or extended industry-standard architecture (EISA, Extended Industry Standard Component) bus etc..AlwaysLine can be divided into address bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 5, but simultaneously convenient for indicatingOnly a bus or a type of bus are not indicated.
Optionally, in specific implementation, if memory 21, processor 22 and communication interface 23 are integrated in chip pieceOn, then memory 21, processor 22 and communication interface 23 can complete mutual communication by internal interface.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically showThe description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or examplePoint is included at least one embodiment of the present invention or example.Moreover, particular features, structures, materials, or characteristics describedIt may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, thisThe technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examplesSign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importanceOr implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hiddenIt include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwiseClear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includesIt is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portionPoint, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitableSequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the inventionEmbodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered useIn the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, forInstruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instructionThe instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or setIt is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicating, propagating or passingDefeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipmentIt sets.
The computer-readable medium of the embodiment of the present invention can be computer-readable signal media or computer-readable depositStorage media either the two any combination.The more specific example at least (non-exclusive of computer readable storage mediumList) include the following: there is the electrical connection section (electronic device) of one or more wirings, portable computer diskette box (magnetic dressSet), random access memory (RAM), read-only memory (ROM), erasable edit read-only storage (deposit by EPROM or flashReservoir), fiber device and portable read-only memory (CDROM).In addition, computer readable storage medium can even is thatCan the paper of print routine or other suitable media on it because can for example be swept by carrying out optics to paper or other mediaIt retouches, is then edited, interprets or handled when necessary with other suitable methods electronically to obtain program, then willIt is stored in computer storage.
In embodiments of the present invention, computer-readable signal media may include in a base band or as carrier wave a partThe data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety ofForm, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is alsoIt can be any computer-readable medium other than computer readable storage medium, which can send, passIt broadcasts or transmits for instruction execution system, input method or device use or program in connection.Computer canThe program code for reading to include on medium can transmit with any suitable medium, including but not limited to: wirelessly, electric wire, optical cable, penetrateFrequently (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentionedIn embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storageOr firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardwareAny one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signalDiscrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), sceneProgrammable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carriesIt suddenly is the program that relevant hardware can be instructed to complete by program, which can store in a kind of computer-readable storageIn medium, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing moduleIt is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mouldBlock both can take the form of hardware realization, can also be realized in the form of software function module.If integrated module withThe form of software function module is realized and when sold or used as an independent product, also can store computer-readable at oneIn storage medium.Storage medium can be read-only memory, disk or CD etc..
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar withThose skilled in the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement, theseIt should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claimsIt is quasi-.