CN110316186A - Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing - Google Patents

Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing Download PDF

Info

Publication number
CN110316186A
CN110316186A CN201910586830.XA CN201910586830A CN110316186A CN 110316186 A CN110316186 A CN 110316186A CN 201910586830 A CN201910586830 A CN 201910586830A CN 110316186 A CN110316186 A CN 110316186A
Authority
CN
China
Prior art keywords
vehicle
time
anticollision
strategy
road scene
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201910586830.XA
Other languages
Chinese (zh)
Inventor
杨凡
朱帆
吕雷兵
马霖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Baidu Online Network Technology Beijing Co Ltd
Beijing Baidu Netcom Science and Technology Co Ltd
Original Assignee
Beijing Baidu Netcom Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Baidu Netcom Science and Technology Co Ltd filed Critical Beijing Baidu Netcom Science and Technology Co Ltd
Priority to CN201910586830.XA priority Critical patent/CN110316186A/en
Publication of CN110316186A publication Critical patent/CN110316186A/en
Pending legal-status Critical Current

Links

Classifications

    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
    • B60W30/08Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09Taking automatic action to avoid collision, e.g. braking and steering
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/105Speed

Abstract

This application provides a kind of vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing.This method includes the present road scene information for obtaining vehicle, according to the present road scene information, determine the anticipation time, according to the anticipation time, determine anticollision strategy, the vehicle is controlled to travel according to the anticollision strategy, so that vehicle can prejudge the appearance of barrier associated with the barrier in present road scene according to present road scene information, it makes in advance and evades collision decision, guarantee the generation that vehicle has enough reaction time and respond to avoid traffic accident, further improves the intelligent level of automatic driving vehicle.

Description

Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing
Technical field
The invention relates to unmanned technical field more particularly to a kind of vehicle collision avoidance pre-judging method, device, Equipment and readable storage medium storing program for executing.
Background technique
With the development of computer technology and artificial intelligence, pilotless automobile (referred to as: unmanned vehicle) traffic, military affairs, Logistic storage, daily life etc. have broad application prospects.Unmanned technology mainly includes the perception of environmental information, The parts such as the motion control of the intelligent decision of driving behavior, the planning in collisionless path and vehicle.
Existing unmanned vehicle only closes the barrier in the current environment perceived in the perception of environmental information Note, if the relative distance of unmanned vehicle and barrier is less than prediction collision distance, unmanned vehicle is braked and is stopped immediately, to keep away Exempt to collide.
Existing unmanned vehicle can not predict the appearance of barrier associated with the barrier in current environment, when associated When barrier occurs, unmanned vehicle often has little time to stop, and causes traffic accident.
Summary of the invention
The embodiment of the present application provides a kind of vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing, with can Vehicle is set to prejudge the appearance of barrier associated with the barrier in current environment, the generation to avoid traffic accident.
The embodiment of the present application first aspect provides a kind of vehicle collision avoidance pre-judging method, comprising:
Obtain the present road scene information of vehicle;
According to the present road scene information, the anticipation time is determined;
According to the anticipation time, anticollision strategy is determined;
The vehicle is controlled to travel according to the anticollision strategy.
In one possible implementation, described according to described current in the above method provided by the embodiments of the present application Road scene information determines the anticipation time, specifically includes:
The corresponding prediction obstacle information of the present road scene information is carried out using trained identification model Identification;
According to the current vehicle speed of recognition result and vehicle, the anticipation time is determined;
Wherein, the trained identification model be according to different road scene information and with the road scene Information predicts what barrier training obtained correspondingly;
Wherein, the prediction barrier is the barrier predicted according to the present road scene information.
In one possible implementation, described according to recognition result in the above method provided by the embodiments of the present application With the current vehicle speed of vehicle, determines the anticipation time, specifically includes:
Obtain the relative distance of the prediction barrier in the vehicle and the recognition result;
According to the relative distance of the current vehicle speed of the vehicle and the vehicle and the prediction barrier, anticipation is determined Time.
In one possible implementation, described according to the anticipation in the above method provided by the embodiments of the present application Time determines anticollision strategy, specifically includes:
If the anticipation time is less than at the first time, it is determined that the anticollision strategy used is the first anticollision strategy;
If the anticipation time is more than or equal at the first time and was less than or equal to for the second time, it is determined that the anticollision plan of use Slightly the second anticollision strategy;
If the anticipation time was greater than for the second time, it is determined that the anticollision strategy used is third anticollision strategy.
In one possible implementation, in the above method provided by the embodiments of the present application, the control vehicle It travels, specifically includes according to the anticollision strategy:
If the anticollision strategy is the first anticollision strategy, controls the vehicle and stop traveling;
If the anticollision strategy is the second anticollision strategy, controls the vehicle and travelled according to First Speed;
If the anticollision strategy is third anticollision strategy, controls the vehicle and travelled according to second speed;
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
In one possible implementation, described to obtain working as vehicle in the above method provided by the embodiments of the present application Preceding road scene information, specifically includes:
Using the Video stream information in camera acquisition present road scene;
The barrier and the vehicle in the video flowing are acquired using comprehensive millimetre-wave radar and/or laser radar The velocity information of range information and the barrier.
The embodiment of the present application second aspect provides a kind of vehicle collision avoidance anticipation device, comprising:
Scene obtains module, for obtaining the present road scene information of vehicle;
Time determining module, for determining the anticipation time according to the present road scene information;
Tactful determining module, for determining anticollision strategy according to the anticipation time;
Control module is travelled for controlling the vehicle according to the anticollision strategy.
In one possible implementation, in above-mentioned apparatus provided by the embodiments of the present application, the time determining module, Include:
Recognition unit, for being hindered using trained identification model to the corresponding prediction of the present road scene information Object information is hindered to be identified;
Determination unit determines the anticipation time for the current vehicle speed according to recognition result and vehicle;
Wherein, the trained identification model be according to different road scene information and with the road scene Information predicts what barrier training obtained correspondingly;
Wherein, the prediction barrier is the barrier predicted according to the present road scene information.
In one possible implementation, in above-mentioned apparatus provided by the embodiments of the present application,
The determination unit, specifically for obtain the prediction barrier in the vehicle and the recognition result it is opposite away from From;According to the relative distance of the current vehicle speed of the vehicle and the vehicle and the prediction barrier, the anticipation time is determined.
In one possible implementation, in above-mentioned apparatus provided by the embodiments of the present application, the strategy determining module, Include:
First determination unit, if for the anticipation time be less than first time, it is determined that the anticollision strategy used for First anticollision strategy;
Second determination unit, if being more than or equal at the first time and being less than or equal to the second time for the anticipation time, Determine the anticollision strategy used for the second anticollision strategy;
Third determination unit, if for the anticipation time greater than the second time, it is determined that the anticollision strategy used for Third anticollision strategy.
In one possible implementation, in above-mentioned apparatus provided by the embodiments of the present application, the control module, packet It includes:
First control unit controls the vehicle and stops if being the first anticollision strategy for the anticollision strategy Traveling;
Second control unit, if for the anticollision strategy be the second anticollision strategy, control the vehicle according to First Speed traveling;
Third control unit, if for the anticollision strategy be third anticollision strategy, control the vehicle according to Second speed traveling;
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
In one possible implementation, in above-mentioned apparatus provided by the embodiments of the present application, the scene obtains module, Include:
First acquisition unit, for using the Video stream information in camera acquisition present road scene;
Second acquisition unit, for being acquired in the video flowing using comprehensive millimetre-wave radar and/or laser radar Barrier and the range information of the vehicle and the velocity information of the barrier.
The embodiment of the present application third aspect provides a kind of electronic equipment, comprising: memory, processor and computer journey Sequence;
Wherein, the computer program stores in the memory, and is configured as being executed by the processor with reality The now method as described in above-mentioned first aspect.
The embodiment of the present application fourth aspect provides a kind of computer readable storage medium, is stored thereon with computer program, The program is executed by processor to realize the method as described in above-mentioned first aspect.
Based on aspects above, the embodiment of the present application is worked as by the present road scene information of acquisition vehicle according to described Preceding road scene information determines that the anticipation time according to the anticipation time determines anticollision strategy, control the vehicle according to The anticollision strategy traveling, so that vehicle can prejudge and the obstacle in present road scene according to present road scene information Object is associated the appearance of barrier, makes evade collision decision in advance, guarantee that vehicle has enough reaction time and respond Come the generation to avoid traffic accident, the intelligent level of automatic driving vehicle is further improved.
It should be appreciated that content described in foregoing invention content part is not intended to limit the pass of embodiments herein Key or important feature, it is also non-for limiting scope of the present application.Other features will become to hold by description below It is readily understood.
Detailed description of the invention
Fig. 1 is running environment schematic diagram provided by the embodiments of the present application;
Fig. 2 is the flow chart for the vehicle collision avoidance pre-judging method that the embodiment of the present application one provides;
Fig. 3 is the flow chart for the vehicle collision avoidance pre-judging method that the embodiment of the present application two provides;
Fig. 4 is the structural schematic diagram that the vehicle collision avoidance that the embodiment of the present application three provides prejudges device;
Fig. 5 is the structural schematic diagram that the vehicle collision avoidance that the embodiment of the present application four provides prejudges device;
Fig. 6 is the structural schematic diagram for the electronic equipment that the embodiment of the present application five provides.
Specific embodiment
Embodiments herein is more fully described below with reference to accompanying drawings.Although showing that the application's is certain in attached drawing Embodiment, it should be understood that, the application can be realized by various forms, and should not be construed as being limited to this In the embodiment that illustrates, providing these embodiments on the contrary is in order to more thorough and be fully understood by the application.It should be understood that It is that being given for example only property of the accompanying drawings and embodiments effect of the application is not intended to limit the protection scope of the application.
The specification and claims of the embodiment of the present application and the term " first " in above-mentioned attached drawing, " second ", " Three ", the (if present)s such as " 4th " are to be used to distinguish similar objects, without for describing specific sequence or successive time Sequence.It should be understood that the data used in this way are interchangeable under appropriate circumstances, so as to the embodiment of the present application described herein as can The enough sequence implementation with other than those of illustrating or describe herein.In addition, term " includes " and " having " and they Any deformation, it is intended that cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, being System, product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or For the intrinsic other step or units of these process, methods, product or equipment.
Fig. 1 shows the running environment being applicable according to the method, apparatus, equipment and readable storage medium storing program for executing of the embodiment of the present application Schematic diagram.The environment that scene is two-way two lane is illustrated, has two moving traffics 1 and vehicle 2 in the environment, Both sides of the road parked vehicle 3 to 8, pedestrian P1 and P2, ball F1.Wherein, vehicle 1 and vehicle 2 are oneself of the embodiment of the present application It is dynamic to drive vehicle, it is blocked due to stationary vehicle or barrier, vehicle 1 and vehicle 2 cannot during travelling current driving Detect pedestrian P1 and P2, be equipped on vehicle 1 and vehicle 2 one for the camera of automatic Pilot, several millimetre-wave radars, Laser radar and other equipment.Uniformly distributed multiple millimetre-wave radars around vehicle body are laid in roof central position At least one laser radar, with guarantee can be with all standing around vehicle body.Laser radar uses light detection and ranging (LIDAR) Technology, more than one laser radar can more completely and quickly scan entire 360 degree of visual fields.Camera passes through shooting video Or image, millimetre-wave radar and laser radar are by measurement with other vehicles or barrier at a distance from and the movement of barrier is fast Road environment information, is supplied to vehicle-mounted automated driving system by degree, by automated driving system according to current road conditions and movement The information such as the distance of barrier generate control information, and control information acts on each equipment of automobile, component then to accelerate, slow down Or stop automatic Pilot.
Vehicle is shown in Fig. 1, and two scenes that can be encountered are travelled on road.Referring to Fig. 1, in scene 1, vehicle 1 is Straight trip, stopping close to the roadside of vehicle 1 has vehicle 6,7,8, and pedestrian P2 preparation traverses to road opposite, but due to the screening of vehicle 7 Gear, vehicle 1 cannot detect pedestrian P2, and in existing automatic Pilot control method, vehicle 1 continues according to currently higher speed row It sails.In scene 2, vehicle 2 is just kept straight in another opposite lane, and stopping close to the roadside of vehicle 2 has vehicle 3,4,5, and vehicle 2 detects There is a ball F1 to road center, but prepares to pick up the pedestrian P1 of ball F1 since barrier blocks not detecting, it is existing automatic In driving control method, vehicle 2 continues to travel according to currently higher speed.
In existing automatic Pilot control method, in order to avoid collision, when automatic driving vehicle and the barrier detected Relative distance be less than prediction collision distance Shi Caihui and braked and stopped immediately, therefore for above two scene or similar In scene, emergent pedestrian is kept into higher speed due to not detecting, often has little time to brake and touch Hit accident.Hereinafter reference will be made to the drawings to specifically describe embodiments herein.
Embodiment one
Fig. 2 is the flow chart for the vehicle collision avoidance pre-judging method that the embodiment of the present application one provides, as shown in Fig. 2, the application The executing subject of embodiment is that vehicle collision avoidance prejudges device, and vehicle collision avoidance anticipation device can integrate in automatic Pilot system In system.Then vehicle collision avoidance pre-judging method provided in this embodiment including the following steps:
S101, the present road scene information for obtaining vehicle.
Specifically, automatic driving vehicle travelled on present road can by the camera that configures, millimetre-wave radar and/ Or laser radar and other awareness apparatus can obtain in real time and identify present road scene information, the current road scene information May include the vehicle or obstacle information for resting in roadside, road roll ball or it is other may barrier associated with pedestrian Hinder the athletic posture information of object, scene 1 and scene 2 as shown in Figure 1.
S102, according to the present road scene information, determine the anticipation time.
Specifically, can according to present road scene information predict it is possible that it is related to present road scene information The pedestrian of connection or other kinds of barrier, different road scenes correspond to the different prediction of appearance position, probability and type Barrier, according to the difference of appearance position, probability and type, it can be determined that the anticipation time point to collide, and then determine energy The size of the enough anticipation time that collision is reacted, such as 0.5 second, 2 seconds or 5 seconds.It, can according to the application embodiment To learn above-mentioned corresponding relationship using deep learning or neural network.
For example, in two scenes as shown in Figure 1, due to the appearance of ball F1 in scene 2, barrier pedestrian is predicted The probability that P1 occurs is greater than the probability that pedestrian P2 occurs in scene 1, therefore the risk that scene 2 collides occurs and be greater than out Live scape 1, the reaction time of automated driving system is just shorter in scene 2, therefore the corresponding anticipation time of scene 2 can be 0.5 Second, the corresponding anticipation time of scene 1 can be 2 seconds.
S103, according to the anticipation time, determine anticollision strategy.
Specifically, the long short reaction of the time size of risk of collision is prejudged.When the anticipation time is shorter, risk of collision is just Larger, when the anticipation time is longer, risk of collision is just smaller.It therefore, can be according to length, that is, risk of collision of anticipation time Size selects anticollision strategy.For example, the anticipation time is 0.5 second, then parking strategy is taken to be avoided, the anticipation time is 5 Second, then the strategy taken is first to have decelerated to enough reaction time reply collisions to return again to just after confirmation will not collide Constant velocity traveling.
S104, the control vehicle are travelled according to the anticollision strategy.
Specifically, vehicle driving, generation to avoid collision are controlled according to the anticollision strategy determined, or are avoided The generation of this car owner duty.
Vehicle collision avoidance pre-judging method provided in this embodiment, by obtaining the present road scene information of vehicle, according to Present road scene information determines the anticipation time, according to the anticipation time, determines anticollision strategy, controls vehicle according to anticollision Strategy traveling, so that vehicle can prejudge barrier associated with the barrier in present road scene according to present road scene information Hinder the appearance of object, make evade collision decision in advance, guarantees that vehicle has enough reaction time and respond to avoid traffic The generation of accident further improves the intelligent level of automatic driving vehicle.
Embodiment two
Fig. 3 is the flow chart for the vehicle collision avoidance pre-judging method that the embodiment of the present application two provides, as shown in figure 3, this implementation The vehicle collision avoidance pre-judging method that example provides, be on the basis of the application embodiment of the method one, to step S101-S104 into Step refining, then method provided in this embodiment the following steps are included:
S201, using camera acquisition present road scene in Video stream information, using comprehensive millimetre-wave radar and/ Or laser radar acquires barrier and the range information of the vehicle and the velocity information of the barrier in the video flowing.
Specifically, automatic driving vehicle travelled on present road can by the camera that configures, millimetre-wave radar and/ Or laser radar and other awareness apparatus can obtain in real time and identify present road scene information, such as be worked as using camera acquisition Video stream information in preceding road scene, using the obstacle in comprehensive millimetre-wave radar and/or laser radar acquisition video flowing Object and the range information of this vehicle and the velocity information of barrier.
S202, using trained identification model to the corresponding prediction obstacle information of the present road scene information It is identified.
Specifically, prediction barrier is the barrier predicted according to present road scene information.Trained identification Model is to predict that barrier training obtains correspondingly according to different road scene information and with road scene information. In practical application, identification model can use deep learning or neural network, and the application is it is not limited here.
S203, according to the current vehicle speed of recognition result and vehicle, determine the anticipation time.
Specifically, the relative distance of the prediction barrier in the vehicle and the recognition result is obtained.According to the vehicle Current vehicle speed and the vehicle and it is described prediction barrier relative distance, determine anticipation the time.
Specifically, according to the available prediction obstacle information of present road scene information, predict that obstacle information includes There is position in the road to get having arrived vehicle and having predicted the relative distance of barrier, further according to vehicle in prediction barrier Current vehicle speed, then available time point to collide, it can determine the anticipation time.
Step S103, can specifically include:
If the anticipation time is less than at the first time, it is determined that the anticollision strategy used is the first anticollision strategy.
If the anticipation time is more than or equal at the first time and was less than or equal to for the second time, it is determined that the anticollision plan of use Slightly the second anticollision strategy.
If the anticipation time was greater than for the second time, it is determined that the anticollision strategy used is third anticollision strategy.
Correspondingly, step S104, can specifically include:
If the anticollision strategy is the first anticollision strategy, controls the vehicle and stop traveling.
If the anticollision strategy is the second anticollision strategy, controls the vehicle and travelled according to First Speed.
If the anticollision strategy is third anticollision strategy, controls the vehicle and travelled according to second speed.
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
In practical application, corresponding collision strategy can be preset according to anticipation time threshold, for example, default be at the first time 0.5 second, the second time was 3 seconds.When obtaining the anticipation time less than 0.5 second, then it is assumed that must be tight there are larger risk of collision Emergency stop vehicle uses the first anticollision strategy.When the anticipation time is more than or equal to 0.5 second and is less than or equal to 3 seconds, then it is assumed that collision wind Danger be it is medium, vehicle present speed can be kept at a slow speed, such as 30 km of speed per hour hereinafter, i.e. use the second anticollision strategy.When The time is prejudged greater than 3 seconds, then it is assumed that risk of collision is lower, vehicle present speed can be kept to medium level, such as speed per hour 30,000 Meter or more, 60 kms hereinafter, i.e. use third anticollision strategy.
Wherein, First Speed can be 30 km of speed per hour and hereinafter, second speed can be 30 km of speed per hour or more, 60,000 Meter or less.
Vehicle collision avoidance pre-judging method provided in this embodiment, by using the view in camera acquisition present road scene Frequency stream information acquires barrier and the vehicle in the video flowing using comprehensive millimetre-wave radar and/or laser radar Range information and the barrier velocity information, using trained identification model to the present road scene information Corresponding prediction obstacle information is identified, according to the current vehicle speed of recognition result and vehicle, determines anticipation time, root According to the anticipation time, anticollision strategy is determined, control vehicle is travelled according to anticollision strategy, so that vehicle is according to present road scene Information can prejudge the appearance of barrier associated with the barrier in present road scene, make evade collision decision in advance, Guarantee the generation that vehicle has enough reaction time and respond to avoid traffic accident, further improves automatic Pilot vehicle Intelligent level.
Embodiment three
Fig. 4 is the structural schematic diagram that the vehicle collision avoidance that the embodiment of the present application three provides prejudges device, as shown in figure 4, this Embodiment provide device include:
Scene obtains module 410, for obtaining the present road scene information of vehicle.
Time determining module 420, for determining the anticipation time according to the present road scene information.
Tactful determining module 430, for determining anticollision strategy according to the anticipation time.
Control module 440 is travelled for controlling the vehicle according to the anticollision strategy.
Device provided in this embodiment can execute the technical solution of embodiment of the method shown in Fig. 2, realization principle and skill Art effect is similar, and details are not described herein again.
Example IV
Fig. 5 is the structural schematic diagram that the vehicle collision avoidance that the embodiment of the present application four provides prejudges device, as shown in figure 5, this The device that embodiment provides is on the basis of the device that the embodiment of the present application three provides, further, the time determining module 420, comprising:
Recognition unit 421, for corresponding pre- to the present road scene information using trained identification model Obstacle information is surveyed to be identified.
Determination unit 422 determines the anticipation time for the current vehicle speed according to recognition result and vehicle.
Wherein, the trained identification model be according to different road scene information and with the road scene Information predicts what barrier training obtained correspondingly.
Wherein, the prediction barrier is the barrier predicted according to the present road scene information.
Further, the determination unit 422 hinders specifically for the prediction obtained in the vehicle and the recognition result Hinder the relative distance of object.According to the relative distance of the current vehicle speed of the vehicle and the vehicle and the prediction barrier, Determine the anticipation time.
Further, the tactful determining module 430, comprising:
First determination unit 431, if being less than at the first time for the anticipation time, it is determined that the anticollision strategy of use For the first anticollision strategy.
Second determination unit 432, if being more than or equal at the first time and being less than or equal to the second time for the anticipation time, Then determine the anticollision strategy used for the second anticollision strategy.
Third determination unit 433, if being greater than for the second time for the anticipation time, it is determined that the anticollision strategy of use For third anticollision strategy.
Further, the control module 440, comprising:
First control unit 441 controls the vehicle and stops if being the first anticollision strategy for the anticollision strategy Only travel.
Second control unit 442 controls the vehicle and presses if being the second anticollision strategy for the anticollision strategy It is travelled according to First Speed.
Third control unit 443 controls the vehicle and presses if being third anticollision strategy for the anticollision strategy It is travelled according to second speed.
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
Further, the scene obtains module 410, comprising:
First acquisition unit 411, for using the Video stream information in camera acquisition present road scene.
Second acquisition unit 412, for being acquired in the video flowing using comprehensive millimetre-wave radar and/or laser radar Barrier and the range information of the vehicle and the velocity information of the barrier.
Device provided in this embodiment can execute the technical solution of embodiment of the method shown in Fig. 3, realization principle and skill Art effect is similar, and details are not described herein again.
Embodiment five
Fig. 6 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present application five provides, as shown in fig. 6, the present embodiment The electronic equipment of offer includes: memory 610, processor 620 and computer program;
Wherein, the computer program is stored in the memory 610, and is configured as being held by the processor 620 Row is to realize such as the vehicle collision avoidance pre-judging method in the embodiment of the present application one or the vehicle collision avoidance in the embodiment of the present application two Pre-judging method.
Related description can correspond to the corresponding associated description and effect of the step of referring to Fig. 1 to Fig. 2 and be understood, herein It does not do and excessively repeats.
Embodiment six
The embodiment of the present application also provides a kind of computer readable storage medium, is stored thereon with computer program, the program It is executed by processor to realize in vehicle collision avoidance pre-judging method or the embodiment of the present application two in such as the embodiment of the present application one Vehicle collision avoidance pre-judging method.
Computer readable storage medium provided in this embodiment, by obtaining the present road scene information of vehicle, according to The present road scene information determines the anticipation time, according to the anticipation time, determines anticollision strategy, and then control vehicle and press It is travelled according to the anticollision strategy, to enable the vehicle to be prejudged and the barrier in current scene according to present road scene information The appearance of associated barrier, makes evade collision decision in advance, guarantees that vehicle has enough reaction time and respond The generation to avoid traffic accident further improves the intelligent level of automatic driving vehicle.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of module, only A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple module or components can combine or Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or module It connects, can be electrical property, mechanical or other forms.
Module may or may not be physically separated as illustrated by the separation member, show as module Component may or may not be physical module, it can and it is in one place, or may be distributed over multiple networks In module.Some or all of the modules therein can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, can integrate in a processing module in each functional module in each embodiment of the application It is that modules physically exist alone, can also be integrated in two or more modules in a module.Above-mentioned integrated mould Block both can take the form of hardware realization, can also realize in the form of hardware adds software function module.
For implement the present processes program code can using any combination of one or more programming languages come It writes.These program codes can be supplied to the place of general purpose computer, special purpose computer or other programmable data processing units Device or controller are managed, so that program code makes defined in flowchart and or block diagram when by processor or controller execution Function/operation is carried out.Program code can be executed completely on machine, partly be executed on machine, as stand alone software Is executed on machine and partly execute or executed on remote machine or server completely on the remote machine to packet portion.
In the context of this application, machine readable media can be tangible medium, may include or is stored for The program that instruction execution system, device or equipment are used or is used in combination with instruction execution system, device or equipment.Machine can Reading medium can be machine-readable signal medium or machine-readable storage medium.Machine readable media can include but is not limited to electricity Son, magnetic, optical, electromagnetism, infrared or semiconductor system, device or equipment or above content any conjunction Suitable combination.The more specific example of machine readable storage medium will include the electrical connection of line based on one or more, portable meter Calculation machine disk, hard disk, random access memory (RAM), read-only memory (ROM), Erasable Programmable Read Only Memory EPROM (EPROM Or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage facilities or Any appropriate combination of above content.
Although this should be understood as requiring operating in this way with shown in addition, depicting each operation using certain order Certain order out executes in sequential order, or requires the operation of all diagrams that should be performed to obtain desired result. Under certain environment, multitask and parallel processing be may be advantageous.Similarly, although containing several tools in being discussed above Body realizes details, but these are not construed as the limitation to the scope of the present disclosure.In the context of individual embodiment Described in certain features can also realize in combination in single realize.On the contrary, in the described in the text up and down individually realized Various features can also realize individually or in any suitable subcombination in multiple realizations.
Although having used specific to this theme of the language description of structure feature and/or method logical action, answer When understanding that theme defined in the appended claims is not necessarily limited to special characteristic described above or movement.On on the contrary, Special characteristic described in face and movement are only to realize the exemplary forms of claims.

Claims (14)

1. a kind of vehicle collision avoidance pre-judging method characterized by comprising
Obtain the present road scene information of vehicle;
According to the present road scene information, the anticipation time is determined;
According to the anticipation time, anticollision strategy is determined;
The vehicle is controlled to travel according to the anticollision strategy.
2. determination is pre- the method according to claim 1, wherein described according to the present road scene information Sentence the time, specifically include:
The corresponding prediction obstacle information of the present road scene information is identified using trained identification model;
According to the current vehicle speed of recognition result and vehicle, the anticipation time is determined;
Wherein, the trained identification model be according to different road scene information and with the road scene information What one-to-one prediction barrier training obtained;
Wherein, the prediction barrier is the barrier predicted according to the present road scene information.
3. according to the method described in claim 2, it is characterized in that, described work as front truck according to recognition result and vehicle Speed determines the anticipation time, specifically includes:
Obtain the relative distance of the prediction barrier in the vehicle and the recognition result;
According to the relative distance of the current vehicle speed of the vehicle and the vehicle and the prediction barrier, when determining anticipation Between.
4. according to the method described in claim 2, it is characterized in that, described determine anticollision strategy according to the anticipation time, It specifically includes:
If the anticipation time is less than at the first time, it is determined that the anticollision strategy used is the first anticollision strategy;
If the anticipation time be more than or equal at the first time and be less than or equal to the second time, it is determined that the anticollision strategy used for Second anticollision strategy;
If the anticipation time was greater than for the second time, it is determined that the anticollision strategy used is third anticollision strategy.
5. according to the method described in claim 4, it is characterized in that, the control vehicle is according to the anticollision policy line It sails, specifically includes:
If the anticollision strategy is the first anticollision strategy, controls the vehicle and stop traveling;
If the anticollision strategy is the second anticollision strategy, controls the vehicle and travelled according to First Speed;
If the anticollision strategy is third anticollision strategy, controls the vehicle and travelled according to second speed;
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
6. method according to any one of claims 1-5, which is characterized in that the present road scene for obtaining vehicle Information specifically includes:
Using the Video stream information in camera acquisition present road scene;
Barrier in the video flowing is acquired at a distance from the vehicle using comprehensive millimetre-wave radar and/or laser radar The velocity information of information and the barrier.
7. a kind of vehicle collision avoidance prejudges device characterized by comprising
Scene obtains module, for obtaining the present road scene information of vehicle;
Time determining module, for determining the anticipation time according to the present road scene information;
Tactful determining module, for determining anticollision strategy according to the anticipation time;
Control module is travelled for controlling the vehicle according to the anticollision strategy.
8. device according to claim 7, which is characterized in that the time determining module, comprising:
Recognition unit, for using trained identification model to the corresponding prediction barrier of the present road scene information Information is identified;
Determination unit determines the anticipation time for the current vehicle speed according to recognition result and vehicle;
Wherein, the trained identification model be according to different road scene information and with the road scene information What one-to-one prediction barrier training obtained;
Wherein, the prediction barrier is the barrier predicted according to the present road scene information.
9. device according to claim 8, which is characterized in that
The determination unit, specifically for obtaining the relative distance of the prediction barrier in the vehicle and the recognition result; According to the relative distance of the current vehicle speed of the vehicle and the vehicle and the prediction barrier, the anticipation time is determined.
10. device according to claim 8, which is characterized in that the strategy determining module, comprising:
First determination unit, if being less than first time for the anticipation time, it is determined that the anticollision strategy used is first Anticollision strategy;
Second determination unit, if being more than or equal at the first time for the anticipation time and being less than or equal to for the second time, it is determined that The anticollision strategy used is the second anticollision strategy;
Third determination unit, if being greater than for the second time for the anticipation time, it is determined that the anticollision strategy used is third Anticollision strategy.
11. device according to claim 10, which is characterized in that the control module, comprising:
First control unit controls the vehicle and stops traveling if being the first anticollision strategy for the anticollision strategy;
Second control unit controls the vehicle according to first if being the second anticollision strategy for the anticollision strategy Speed traveling;
Third control unit controls the vehicle according to second if being third anticollision strategy for the anticollision strategy Speed traveling;
Wherein, First Speed is less than second speed, and second speed is less than current vehicle speed.
12. device according to any one of claims 7-11, which is characterized in that the scene obtains module, comprising:
First acquisition unit, for using the Video stream information in camera acquisition present road scene;
Second acquisition unit, for acquiring the obstacle in the video flowing using comprehensive millimetre-wave radar and/or laser radar Object and the range information of the vehicle and the velocity information of the barrier.
13. a kind of electronic equipment characterized by comprising memory, processor and computer program;
Wherein, the computer program stores in the memory, and is configured as being executed by the processor to realize such as Method of any of claims 1-6.
14. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor It executes to realize such as method of any of claims 1-6.
CN201910586830.XA 2019-07-01 2019-07-01 Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing Pending CN110316186A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910586830.XA CN110316186A (en) 2019-07-01 2019-07-01 Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910586830.XA CN110316186A (en) 2019-07-01 2019-07-01 Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing

Publications (1)

Publication Number Publication Date
CN110316186A true CN110316186A (en) 2019-10-11

Family

ID=68122163

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910586830.XA Pending CN110316186A (en) 2019-07-01 2019-07-01 Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing

Country Status (1)

Country Link
CN (1) CN110316186A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110827578A (en) * 2019-10-23 2020-02-21 江苏广宇协同科技发展研究院有限公司 Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation
CN111703302A (en) * 2020-06-18 2020-09-25 北京航迹科技有限公司 Vehicle window content display method and device, electronic equipment and readable storage medium
CN111722617A (en) * 2020-06-29 2020-09-29 史秋虹 Automatic driving automobile performance judgment system and method based on big data
CN113071495A (en) * 2021-03-09 2021-07-06 合创汽车科技有限公司 Event detection method and device based on vehicle-mounted multi-mode data, computer equipment and storage medium
CN113348119A (en) * 2020-04-02 2021-09-03 华为技术有限公司 Vehicle blind area identification method, automatic driving assistance system and intelligent driving vehicle comprising system
CN114464013A (en) * 2022-04-11 2022-05-10 青岛慧拓智能机器有限公司 Multi-vehicle cooperative collision avoidance method, device, system, storage medium and terminal

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2400473A1 (en) * 2010-06-28 2011-12-28 Audi AG Method and device for supporting a driver of a vehicle
CN105774809A (en) * 2014-12-26 2016-07-20 中国移动通信集团公司 Traveling dead zone prompting method and device
CN109624972A (en) * 2018-12-06 2019-04-16 北京百度网讯科技有限公司 Vehicle prevents method, apparatus, equipment and the readable storage medium storing program for executing of collision
CN109801508A (en) * 2019-02-26 2019-05-24 百度在线网络技术(北京)有限公司 The motion profile prediction technique and device of barrier at crossing
CN109817021A (en) * 2019-01-15 2019-05-28 北京百度网讯科技有限公司 A kind of laser radar trackside blind area traffic participant preventing collision method and device
CN109878512A (en) * 2019-01-15 2019-06-14 北京百度网讯科技有限公司 Automatic Pilot control method, device, equipment and computer readable storage medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP2400473A1 (en) * 2010-06-28 2011-12-28 Audi AG Method and device for supporting a driver of a vehicle
CN105774809A (en) * 2014-12-26 2016-07-20 中国移动通信集团公司 Traveling dead zone prompting method and device
CN109624972A (en) * 2018-12-06 2019-04-16 北京百度网讯科技有限公司 Vehicle prevents method, apparatus, equipment and the readable storage medium storing program for executing of collision
CN109817021A (en) * 2019-01-15 2019-05-28 北京百度网讯科技有限公司 A kind of laser radar trackside blind area traffic participant preventing collision method and device
CN109878512A (en) * 2019-01-15 2019-06-14 北京百度网讯科技有限公司 Automatic Pilot control method, device, equipment and computer readable storage medium
CN109801508A (en) * 2019-02-26 2019-05-24 百度在线网络技术(北京)有限公司 The motion profile prediction technique and device of barrier at crossing

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110827578A (en) * 2019-10-23 2020-02-21 江苏广宇协同科技发展研究院有限公司 Vehicle anti-collision prompting method, device and system based on vehicle-road cooperation
CN113348119A (en) * 2020-04-02 2021-09-03 华为技术有限公司 Vehicle blind area identification method, automatic driving assistance system and intelligent driving vehicle comprising system
CN111703302A (en) * 2020-06-18 2020-09-25 北京航迹科技有限公司 Vehicle window content display method and device, electronic equipment and readable storage medium
CN111703302B (en) * 2020-06-18 2021-07-02 北京航迹科技有限公司 Vehicle window content display method and device, electronic equipment and readable storage medium
CN111722617A (en) * 2020-06-29 2020-09-29 史秋虹 Automatic driving automobile performance judgment system and method based on big data
CN111722617B (en) * 2020-06-29 2021-08-10 航天探索太空(北京)技术产业有限公司 Automatic driving automobile performance judgment system and method based on big data
CN113071495A (en) * 2021-03-09 2021-07-06 合创汽车科技有限公司 Event detection method and device based on vehicle-mounted multi-mode data, computer equipment and storage medium
CN114464013A (en) * 2022-04-11 2022-05-10 青岛慧拓智能机器有限公司 Multi-vehicle cooperative collision avoidance method, device, system, storage medium and terminal

Similar Documents

Publication Publication Date Title
CN110316186A (en) Vehicle collision avoidance pre-judging method, device, equipment and readable storage medium storing program for executing
CN106740864B (en) A kind of driving behavior is intended to judgement and prediction technique
US11235763B2 (en) Method, apparatus, device and readable storage medium for preventing vehicle collision
EP3091370A1 (en) Method and arrangement for determining safe vehicle trajectories
US7974748B2 (en) Driver assistance system with vehicle states, environment and driver intention
US11048253B2 (en) Agent prioritization for autonomous vehicles
CN113165652B (en) Verifying predicted trajectories using a mesh-based approach
CN109808709A (en) Vehicle driving support method, device, equipment and readable storage medium storing program for executing
WO2019106789A1 (en) Processing device and processing method
US20210261123A1 (en) Autonomous Vehicle Operation with Explicit Occlusion Reasoning
CN106218612B (en) A kind of method, apparatus and terminal of vehicle safety travel
CN111459168A (en) Fused automatic-driving automobile pedestrian crossing track prediction method and system
Guo et al. Human-like behavior generation for intelligent vehicles in urban environment based on a hybrid potential map
Zhang et al. Situation analysis and adaptive risk assessment for intersection safety systems in advanced assisted driving
CN112955361A (en) Prediction of expected driving behavior
Yang et al. Driving behavior assessment and anomaly detection for intelligent vehicles
CN111882924A (en) Vehicle testing system, driving behavior judgment control method and accident early warning method
CN110316185A (en) Control method, device, equipment and the readable storage medium storing program for executing of car speed
CN111186433A (en) Method for selecting and accelerating an implementation action response
Zhang et al. Prediction of Pedestrian Risky Level for Intelligent Vehicles
KR102355431B1 (en) AI based emergencies detection method and system
Benterki et al. Driving Intention Prediction and State Recognition on Highway
Wang et al. Online Safety Assessment of Automated Vehicles Using Silent Testing
US20210300350A1 (en) Vehicle control device, vehicle control method, and storing medium
Laugier Situation Awareness & Decision-making for Autonomous Driving

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination