CN107097781A - Vehicular automatic driving method, system, storage medium and autonomous driving vehicle - Google Patents
Vehicular automatic driving method, system, storage medium and autonomous driving vehicle Download PDFInfo
- Publication number
- CN107097781A CN107097781A CN201710265210.7A CN201710265210A CN107097781A CN 107097781 A CN107097781 A CN 107097781A CN 201710265210 A CN201710265210 A CN 201710265210A CN 107097781 A CN107097781 A CN 107097781A
- Authority
- CN
- China
- Prior art keywords
- automatic pilot
- safe class
- driving system
- automated driving
- driver
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000009471 action Effects 0.000 claims abstract description 37
- 230000004927 fusion Effects 0.000 claims description 6
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 14
- 238000013459 approach Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 239000000523 sample Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000001419 dependent effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000003756 stirring Methods 0.000 description 2
- 241000736199 Paeonia Species 0.000 description 1
- 235000006484 Paeonia officinalis Nutrition 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W30/00—Purposes 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0001—Details of the control system
- B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT 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
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W2050/0062—Adapting control system settings
- B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The application provides a kind of method of automatic Pilot, and it includes:Automated driving system is persistently determined to automatic Pilot safe class S, automated driving system sends request driver according to the automatic Pilot safe class S measured and performs the requirement that checking is acted, automated driving system judges whether driver correctly performs checking action, if correctly performing checking action, then continue to control vehicle to carry out automatic Pilot, if driver exits automatic driving mode and/or the pulling over observing in the case where ensureing safety without checking action, request is correctly performed.This automatic Pilot method of the application requires that automated driving system persistently determines automatic Pilot safe class, based on the safe class, it is required that driver performs checking action, so as to realize man-machine interaction, ensure that driver can keep enough notice and vigilance to driving environment, so as to improve the security of automatic Pilot.
Description
Technical field
The application belongs to automatic driving technical field, and in particular to a kind of method of automatic Pilot, using it is this from
The automated driving system of dynamic drive manner, and corresponding autonomous driving vehicle.
Background technology
As automated driving system is more and more reliable, people are also increasingly dependent on automated driving system and carried out in trip
Car steering.However, current automated driving system is often equipment of the design applied to semi-automatic driving.Document
CN104540701A, CN105818812A and CN106043311A describe the certain methods related to automatic Pilot, wherein relating to
And arrived to driver status progress machine judgement, but judgement of the machine to driver status not can determine that driver's is true
Real state.Some traffic accidents at automatic Pilot initial stage, partly cause comes from equipment quilt of the design applied to semi-automatic driving
Driver uses as unmanned equipment.During long-term semi-automatic driving, not to whether meeting safety half certainly
Dynamic riving condition carries out repeated authentication, and driver loses vigilance, when being unsatisfactory for safe automatic Pilot condition, had little time
Adapter control loop, causes irremediable accident occur.
The content of the invention
In order to solve problem above of the prior art, present inventor proposes a kind of with higher driving safety
Property automatic Pilot method, and using the automated driving system of this automatic Pilot method, and corresponding automatic Pilot
Automobile.
The present invention includes herein below:
A kind of method of the Vehicular automatic driving of embodiment 1., it includes:
Automated driving system is persistently determined to automatic Pilot safe class S,
Automated driving system sends request driver according to the automatic Pilot safe class S measured and performs wanting for checking action
Ask,
Automated driving system judges whether driver correctly performs checking action, if correctly performing checking action, after
Continuous control vehicle carries out automatic Pilot, if driver exits automatic driving mode without checking action, request is correctly performed
And/or ensure safety in the case of pulling over observing.
Method of the embodiment 2. according to embodiment 1, wherein
The automated driving system includes multiple sensors,
" the carrying out persistently determining to automatic Pilot safe class S " includes:
Δ t, determines following at least one at a certain time interval:Each sensor of the automated driving system is being worked as
Adaptability under preceding environment, the fusion uniformity of the multiple sensor, safe class and the automatic Pilot safety of road environment
Confidence level;
Calculate automatic Pilot safe class S.
Method of the embodiment 3. according to embodiment 2, wherein the sensor includes being selected from following at least one
Kind:Vision sensor, GPS, laser radar, and millimetre-wave radar.
Method of the embodiment 4. according to embodiment 2, wherein the road safety level is according to following factor
Calculate:Bicycle on pedestrian on driving path, driving path, if traveling is in fastlink, and road is set with the presence or absence of V2X
Standby, whether front takes a sudden turn, the quantity of surrounding car and the truck situation apart from situation, and surrounding.
Method of the embodiment 5. according to embodiment 2, wherein described " calculate automatic Pilot safe class S " bags
Include:Result to measure is weighted summation, wherein the weight of each measured value is the measured value to automatic Pilot safe class S
Influence size.
Method of the embodiment 6. according to embodiment 2, wherein the time interval is:20ms to 200ms.
Method of the embodiment 7. according to embodiment any one of 2-6, wherein described " according to the automatic Pilot measured
Safe class S sends the requirement that request driver performs checking action " include:
Accumulative acquisition aggregate-value P is carried out to the automatic Pilot safe class S of measure, please when the aggregate-value exceedes threshold value
Ask driver to make defined checking action, P values are zeroed.
Method of the embodiment 8. according to embodiment 7, wherein the burst feelings during automatic Pilot is detected
During condition, the value of the safe confidence level of automatic Pilot is set greater than or equal to the threshold value.
Method of the embodiment 9. according to embodiment 7, wherein checking action includes as defined in described:Driver exists
Any one or more following actions are completed in the defined time:
Stir at least one in steering indicating light, dipped headlight, high beam and double flashing lights;
Steering indicating light, dipped headlight, any combination of high beam and double flashing lights are stirred according to certain beat.
Method of the embodiment 10. according to embodiment 7, wherein checking action as defined in described is random appearance
's.
Method of the embodiment 11. according to embodiment 4, wherein the emergency case include selected from it is following at least
It is a kind of:Sample, the front car that brake hard, appearance were not trained are brought to a halt, pedestrian jaywalks, front car is incorporated to works as by force
Preceding track.
Being stored with computer on a kind of automated driving system of embodiment 12., including memory and processor, memory can
Execute instruction, the instruction is operable to perform the method any one of embodiment 1 to 11 when being executed by a processor.
A kind of autonomous driving vehicle of embodiment 13., it is provided with the automated driving system described in embodiment 12.
Embodiment 14, a kind of computer-readable recording medium, be above stored with computer executable instructions, and the instruction is worked as
It is operable to perform the method any one of embodiment 1 to 11 when being executed by processor.
This automatic Pilot method of the application requires that automated driving system persistently determines automatic Pilot safe class, is based on
The safe class, it is desirable to which driver performs checking action, so as to realize man-machine interaction, it is ensured that driver can protect to driving environment
Enough notices and vigilance are held, so as to improve the security of automatic Pilot.
Brief description of the drawings
In order to illustrate more clearly of the technical scheme of the embodiment of the present disclosure, the accompanying drawing of embodiment will be simply situated between below
Continue, it should be apparent that, drawings in the following description merely relate to some embodiments of the present disclosure, rather than limitation of this disclosure.
Fig. 1 shows a kind of flow chart of the method for automatic Pilot according to the application.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present disclosure clearer, below in conjunction with the embodiment of the present disclosure
Accompanying drawing, the technical scheme to the embodiment of the present disclosure is clearly and completely described.Obviously, described embodiment is this public affairs
A part of embodiment opened, rather than whole embodiments.Based on described embodiment of the disclosure, ordinary skill
The every other embodiment that personnel are obtained on the premise of without creative work, belongs to the scope of disclosure protection.
As automated driving system is more and more reliable, people are also increasingly dependent on automated driving system and carried out in trip
Car steering.If however, driver is overly dependent upon automated driving system, there are the feelings that automated driving system can not be handled
During condition, driver can not intervene in time, cause accident occur.If driver depends on automated driving system for a long time, it is negligent of
Concern to control loop, when danger arriving tends not to processing in time.Inventors herein have recognized that, if driver can
Follow up driving environment at any time, then can just get involved in car steering, the danger that processing automated driving system can not be handled in time
Dangerous situation condition, so as to reduce the incidence of accident.Based on considerations above, present inventor proposes a kind of new automatic
Drive manner.
In some embodiments, the application provides a kind of method of automatic Pilot, and it includes:Automated driving system is to certainly
Dynamic driving safety grade S is persistently determined;Automated driving system sends request according to the automatic Pilot safe class S measured and driven
The person of sailing performs the requirement of checking action;Automated driving system judges whether driver correctly performs checking action, if correctly held
Row checking is acted, then continues to control vehicle to carry out automatic Pilot, if driver moves back without checking action, request is correctly performed
Go out automatic driving mode and/or the pulling over observing in the case where ensureing safety.Fig. 1 shows a kind of stream of embodiment of the application
Cheng Tu.This automatic Pilot method of the application requires that automated driving system persistently determines automatic Pilot safe class, based on this
Safe class, it is desirable to which driver performs checking action, so as to realize man-machine interaction, it is ensured that driver can keep to driving environment
Enough notices and vigilance, so as to improve the security of automatic Pilot.
In some embodiments of approach described above, the automated driving system includes multiple sensors, described " right
Automatic Pilot safe class S persistently determine " include:Δ t, determines following at least one at a certain time interval:Institute
State the adaptability of automated driving system each sensor under the present circumstances, the fusion uniformity of the multiple sensor, road
The safe confidence level of safe class and automatic Pilot of environment;Calculate automatic Pilot safe class S.Automated driving system is often wrapped
Multiple sensors are included for the driving environment around probe vehicle.These sensors are according to installed in the position of body of a motor car and spy
Survey purpose difference, can include Chinese herbaceous peony forward sense device, roof forward sense device, right front sensor, left front sensor,
Right back sensor, left back sensor, rear sensor, left sensor, right sensor etc..These sensors according to
The difference of its own principle can include vision sensor, ultrasonic sensor, millimetre-wave radar, the type such as laser radar.Depending on
Feel that sensor also includes the wide-angle camera with target identification function.These sensors have respective advantage, and apply office
Sex-limited and defect.Therefore, automatic vehicle control system usually includes the combination of multiple sensors.
Vision sensor is general using camera as main representative products, can be divided into camera with detection identification function with
The camera of identification function is not detected.The former inside modules carry software, and the target in image is extracted and handled,
Obtain the position and movement information of target.For example, the wide-angle camera with target identification function is with detection identification function
One kind in vision sensor.The camera of identification function is not detected, only can record and transmit the image obtained by shooting is used for
Subsequent treatment.Two kinds of vision sensor is all limited to that longitudinal probing is closer to the distance, dynamic range is limited, target movement letter
Cease the shortcomings of detection accuracy is not enough.
Ultrasonic sensor detection range is general to have some superiority within 10m for nearby target acquisition, but can not
Undertake the task of long-range target acquisition.The detection of ultrasonic sensor is easily by environment (such as temperature, humidity) bar simultaneously
The influence of part, causes the unstable of performance.
Millimetre-wave radar sensor has longitudinal probing distance remote, the characteristics of environmental suitability is good, but its distinctive number
It is different target to be easily caused according to processing mode by same target identification.Meanwhile, millimetre-wave radar sensing data needs fabulous
Filtering algorithm, otherwise in the intensive region of radar reflection point, its target acquisition performance easily produce fluctuation in addition by mistake detect.
The detection accuracy of laser radar sensor is high, and relatively far away from, application is wider for detection range.But laser radar
Sensor is under haze goods rainstorm weather, because ambient noise is excessively strong, and the detection performance of laser radar is under similar scene
Larger missing is had, is unfavorable for the detection of target.
In the present processes, " carrying out persistently determining to automatic Pilot safe class S " includes:With between the regular hour
Every Δ t, following at least one is determined:The adaptability of the automated driving system each sensor under the present circumstances, it is described
The fusion uniformity of multiple sensors, the safe confidence level of safe class and automatic Pilot of road environment;Calculate automatic Pilot peace
Congruent level S.Described Δ t is not particularly limited, and motor vehicle environment is detected in time under motoring condition as long as ensure that
Driving environment, it is however generally that its scope is 10ms to 1 seconds.For example, if running car were slower, the preferable situation of road conditions
Under, Δ t can be 1 second, 0.5 second, or 0.1 second.And it is very fast in running car, in the case that road conditions are more complicated, Δ t can be
50ms, 40ms, 30ms, 20ms, even 10ms.It should be noted that except need consider road conditions in addition to, Δ t it is specific when
Between length also need to consider sensor performance, and processing sensor obtain information processor performance, processor
Performance is higher, and Δ t can be shorter, and the performance of processor is lower, and Δ t needs more long.What the method for the present invention was determined
The content of measure is not particularly limited, as long as the driving environment of automobile can be accurately reflected.In general, the content determined
Including:Interoperability between weather conditions, Road Factor, and automated driving system and the factor.Specifically, determine
Content include the adaptability of the automated driving system each sensor under the present circumstances, the fusion of the multiple sensor
Uniformity, the safe confidence level of safe class and automatic Pilot of road environment;With calculating automatic Pilot safe class S.
" automated driving system each sensor adaptability " under the present circumstances is based on the weather conditions measured
Adaptability between sensor, for example, can specifically be set as that each sensor adaptability (adap) is multiplied by weight coefficient
(weight) sum.The detection of such as ultrasonic sensor is easily influenceed, caused by environment (such as temperature, humidity) condition
Performance it is unstable.As camera adaptability under strong backlight environment is relatively low, GPS blocked in tunnel or high building in the case of signal
Weaker, laser radar detection range under the conditions of thick fog is restricted, and these adaptability (adap) mostly can be defeated by sensor
Go out to obtain, each sensor weighted value (weight) is obtained by each sensor effectiveness by calculating and experiment.
" the fusion uniformity of the multiple sensor " refers to that different sensors overlap the part of redundancy, knot in result of detection
Whether fruit is consistent.In the case where multiple sensors have search coverage coincidence, the result of detection in overlapping region is melted
Need to investigate uniformity during conjunction, if there is it is inconsistent when, accepted or rejected according to the characteristics of each sensor.
" safe class of road environment " is the security reflection of road environment (i.e. road conditions), including:Whether there is row on road
Person bicycle etc., whether be fastlink, road whether there is V2X equipment, front whether take a sudden turn, surrounding car quantity and apart from, week
It is with no truck etc..
" the safe confidence level of automatic Pilot " is that " carrying out persistently determining to automatic Pilot safe class S " one in step can
Option, it refers to automated driving system according to current driving environment to commenting that the security for proceeding automatic Pilot is carried out
Valency, for example its can include the confidence evaluation of emergency case.Machine driving safety confidence level (trust) is the defeated of black box
Go out, different driving schemes there can be respective computational methods.In some cases, " the safe confidence level of automatic Pilot " include to
The evaluation of lower situation:Brake hard or meet the sample category do not trained in automatic Pilot way and (detect object still
Can not Classification and Identification into recognizable classification, the truck that such as tesla is knocked).
In some embodiments, sensor described above includes being selected from following at least one:Vision sensor, GPS,
Laser radar, and millimetre-wave radar.The specific feature of these sensors is described above, and here is omitted.This area
Technical staff can be selected the particular type of sensor as needed.
In some embodiments of approach described above, the road safety level includes following at least one:OK
Sail the bicycle on the pedestrian on path, driving path, if traveling whether there is V2X equipment, front in fastlink, road
Whether take a sudden turn, the quantity of surrounding car and the truck situation apart from situation, and surrounding.As elucidated before " road environment
Safe class " is the security reflection of road conditions, and to enumerate be that the specific of road conditions security is enumerated for each of the above, contains reflection
The major consideration of road conditions, but not limited to this.
In this application, the specific method for calculating automatic Pilot safe class S is not limited, as long as can be anti-on the whole
Reflect automatic Pilot safe class S.It is described " to calculate automatic Pilot safety in some embodiments of approach described above
Grade S " includes:Result to measure is weighted summation, wherein the weight of each measured value is the measured value to automatic Pilot
Safe class S influence size.It is a kind of method of simple possible to the method that each influence factor is weighted summation, it is desirable to
Amount of calculation it is smaller, and simple, intuitive, reflection is overall safe class situation.
But the invention is not restricted to this, it would however also be possible to employ other method is calculated.Such as, can be independent to each factor
It is weighted accumulative, it is automatic Pilot safe class S to take in the aggregate-value of each factor highest, that is to say, that as some side
When the danger in face reaches critical value, that is, require that driver performs checking action.
It is as described above, it is not particularly limited in the application for time interval.In a preferred embodiment, it is described
Time interval is:20ms to 200ms.In such time interval, the disposal ability of processor can either be met, can be expired again
The common drive speed of foot and driving environment.In the time range, the time interval can also be 30ms, 40ms,
50ms, 60ms, 70ms, 80ms, 90ms, 100ms, 110ms, 120ms, 130ms, 140ms, 150ms, 160ms, 170ms,
180ms, 190ms etc..
It is described " to be sent out according to the automatic Pilot safe class S measured in some embodiments of approach described above
Go out to ask driver to perform the requirement of checking action " include:The automatic Pilot safe class S of measure added up
Value P, when the aggregate-value exceedes threshold value, request driver makes defined checking action, and P values are zeroed.Requiring driver
Make after checking action, P values are zeroed, to add up automatic Pilot safe class S (or aggregate-value P) again.The threshold value
Size is not restricted, but needs according to the specific method for calculating aggregate-value P, and actual automatic Pilot experience comes specific
Selection, those skilled in the art can make suitable selection according to actual conditions.Automatic Pilot safe class S concrete numerical value
Can specific design as needed, be not particularly limited.Safe class S numerical value can be such as set to the number between 0 and 1
Value, 0 represents definitely dangerous, and 1 represents to be perfectly safe, and in this case, aggregate-value P calculating can be that the value of (1-S) is entered
Row is accumulative.On the other hand, safe class S numerical value can be set to positive number, numerical value is bigger to represent more dangerous, the smaller table of numerical value
Show safer, so, aggregate-value P calculating can be that S value is summed., can be with a kind of specific embodiment
The following automatic Pilot safe class S to measure is added up:Pi=Pi-1+ S, wherein Pi-1Refer to the accumulative of a measure moment
Value, PiRefer to the aggregate-value at current time.In some cases, the sensor of automated driving system carries out the time of information detection
Interval is that not necessarily, namely each Δ t is likely to be change.In such a case, it is possible to which following drive to the automatic of measure
Safe class S is sailed to be added up:Pi=Pi-1+S*Δti, wherein Pi-1Refer to the aggregate-value at a measure moment, PiRefer to current
The aggregate-value at moment.
On the other hand, safe class S numerical value can be set to real number, in the case that S is negative, absolute value is bigger
Represent more dangerous, in the case that S is positive number, absolute value is bigger to represent safer, and so, aggregate-value P calculating can be to S
Value is summed, when aggregate-value P reaches larger negative value (i.e. threshold value), that is, shows that the aggregate-value exceedes threshold value.In brief,
" aggregate-value exceedes threshold value " described herein is not the direct numerical values recited represented between aggregate-value and threshold value, and is referred to
Degree of danger represented by aggregate-value is beyond the degree of danger set by threshold value.
It can also coordinate various other sides by way of automatic Pilot safe class S aggregate-value P reminds degree of danger
Formula reminds the driver to note.Light can such as be designed associated with aggregate-value P, when aggregate-value P becomes closer to threshold value,
In-car is taken care using the light of red (or close to red) come alerting drivers.Music can such as be designed with adding up
Value P is associated, when aggregate-value P becomes closer to threshold value, in-car to be taken care using nervous music come alerting drivers.This
Any limitation is not done in application for other modes.
In some embodiments of approach described above, the calculating of the safe confidence level of automatic Pilot is not limited especially
System.In a kind of specific embodiment, when the emergency case during detecting automatic Pilot, the automatic Pilot safety
The value of confidence level is set greater than or equal to the threshold value, emergency case here is, for example, the sample for running into and not training
Situation, now requires that driver intervenes, therefore directly the value of the safe confidence level of automatic Pilot is set greater than or equal to threshold value.
In the present processes, it is not particularly limited for the defined checking action.Preferred embodiment
In, it is desirable to the primary condition that checking action as defined in described should be met is not influence the automatic Pilot of vehicle;More preferable situation
Under, checking action should be conducive to the safe driving of vehicle.It is described in some embodiments of approach described above
Defined checking action includes:Driver completes any one or more following actions within the defined time:Stir steering
At least one in lamp, dipped headlight, high beam and double flashing lights;One group of combination is stirred according to certain beat.It is dynamic as defined in these
Making directly not produce the automatic Pilot of vehicle either influences or the vehicle of surrounding can be played used in warning, is conducive to
The automatic Pilot of vehicle.
In the present processes, do not limited for the particular content of the compulsory exercise, can be same regulation
Act or according to time or the difference of environment, provide different compulsory exercises.In some tools of approach described above
In body embodiment, the defined intervention action (or checking action) occurs at random.It is random defined intervene occur
Action enables to driver to have too many preparation to defined action, it is necessary in the case where keeping enough notices
Each action request could accurately be completed, it is ensured that the notice of driver obtains the accurate judgement of automated driving system.
In some embodiments of approach described above, the emergency case includes being selected from following at least one
Kind:Sample, the front car that brake hard, appearance were not trained are brought to a halt, pedestrian is jaywalked, front car is incorporated to currently by force
Track.When there is emergency case, it can be set greater than or wait by directly by the value of the safe confidence level of the automatic Pilot
System is caused to enter the state of request driver's intervention in the threshold value.
Automatic Pilot method based on the application, the application also provides a kind of automated driving system, its be configured to perform with
Upper described any automatic Pilot method.
Automatic Pilot method and corresponding automated driving system based on the application, the application also provide one kind and driven automatically
Automobile is sailed, it is provided with automated driving system provided herein or it uses automatic Pilot side provided herein
Method.
Described above is only the exemplary embodiment of the disclosure, not for the protection domain of the limitation disclosure, this public affairs
The protection domain opened is determined by appended claim.
Claims (10)
1. a kind of method of Vehicular automatic driving, it includes:
Automated driving system is persistently determined to automatic Pilot safe class S,
Automated driving system sends request driver according to the automatic Pilot safe class S measured and performs the requirement that checking is acted,
Automated driving system judges whether driver correctly performs checking action, if correctly performing checking action, continues to control
Vehicle processed carries out automatic Pilot, if driver is without correctly performing checking action, request exit automatic driving mode and/or
The pulling over observing in the case where ensureing safety.
2. according to the method described in claim 1, wherein
The automated driving system includes multiple sensors,
" the carrying out persistently determining to automatic Pilot safe class S " includes:
Δ t, determines following at least one at a certain time interval:Each sensor of the automated driving system is working as front ring
Adaptability under border, the fusion uniformity of the multiple sensor, the safe confidence of safe class and automatic Pilot of road environment
Degree;
Calculate automatic Pilot safe class S.
3. method according to claim 2, wherein the sensor includes being selected from following at least one:Visual sensing
Device, GPS, laser radar, and millimetre-wave radar.
4. method according to claim 2, wherein the road safety level is calculated according to following factor:Driving path
On pedestrian, the bicycle on driving path, whether travel whether fastlink, road anxious with the presence or absence of V2X equipment, front
Turn, the quantity of surrounding car and apart from situation and the truck situation of surrounding.
5. method according to claim 2, wherein described, " calculating automatic Pilot safe class S " includes:To the knot of measure
Fruit is weighted summation, wherein the weight of each measured value is influence size of the measured value to automatic Pilot safe class S.
6. method according to claim 2, wherein the time interval is:20ms to 200ms.
7. the method according to claim any one of 2-6, wherein described " send out according to the automatic Pilot safe class S measured
Go out to ask driver to perform the requirement of checking action " include:
Accumulative acquisition aggregate-value P is carried out to the automatic Pilot safe class S of measure, when the aggregate-value exceedes threshold value, request is driven
The person of sailing makes defined checking action, and P values are zeroed.
8. be stored with computer executable instructions on a kind of automated driving system, including memory and processor, memory, described
Instruction is operable to the method any one of perform claim requirement 1 to 7 when being executed by a processor.
9. a kind of autonomous driving vehicle, it is provided with the automated driving system described in claim 8.
10. a kind of computer-readable recording medium, be above stored with computer executable instructions, and the instruction, which is worked as, to be executed by processor
When be operable to perform claim requirement 1 to 7 any one of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710265210.7A CN107097781B (en) | 2017-04-21 | 2017-04-21 | Vehicular automatic driving method, system, storage medium and autonomous driving vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710265210.7A CN107097781B (en) | 2017-04-21 | 2017-04-21 | Vehicular automatic driving method, system, storage medium and autonomous driving vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107097781A true CN107097781A (en) | 2017-08-29 |
CN107097781B CN107097781B (en) | 2019-04-19 |
Family
ID=59656782
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710265210.7A Active CN107097781B (en) | 2017-04-21 | 2017-04-21 | Vehicular automatic driving method, system, storage medium and autonomous driving vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107097781B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062101A (en) * | 2017-12-20 | 2018-05-22 | 驭势科技(北京)有限公司 | The intelligent personal vehicles and its control method, dispatching method and storage medium |
CN109085829A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of sound state target identification method |
CN109374310A (en) * | 2018-09-07 | 2019-02-22 | 百度在线网络技术(北京)有限公司 | Automatic driving vehicle test method, device and storage medium |
CN109849677A (en) * | 2019-04-15 | 2019-06-07 | 上汽大众汽车有限公司 | Autonomous driving vehicle energy management and low capacity prompt system and method |
CN110550024A (en) * | 2019-09-16 | 2019-12-10 | 上海拿森汽车电子有限公司 | vehicle operation control method and device based on automatic driving |
WO2020042859A1 (en) * | 2018-08-29 | 2020-03-05 | 上海商汤智能科技有限公司 | Smart driving control method and apparatus, vehicle, electronic device, and storage medium |
CN111142528A (en) * | 2019-12-31 | 2020-05-12 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Vehicle dangerous scene sensing method, device and system |
CN111376905A (en) * | 2018-12-27 | 2020-07-07 | 北京图森智途科技有限公司 | Parking control method, device and system for transport tool, transport tool and vehicle |
CN112092827A (en) * | 2020-09-23 | 2020-12-18 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
CN112590797A (en) * | 2019-10-01 | 2021-04-02 | 现代自动车株式会社 | Device and method for monitoring a driver and system comprising such a device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1802273A (en) * | 2003-06-06 | 2006-07-12 | 沃尔沃技术公司 | Method and arrangement for controlling vehicular subsystems based on interpreted driver activity |
CN101823487A (en) * | 2009-03-06 | 2010-09-08 | 通用汽车环球科技运作公司 | Detecting hand of driver in lane change or road become automatically in the operation grips or decontrols |
WO2011064825A1 (en) * | 2009-11-27 | 2011-06-03 | トヨタ自動車株式会社 | Drive assistance device and drive assistance method |
CN106335544A (en) * | 2015-07-07 | 2017-01-18 | 丰田自动车株式会社 | Driving Support Device For Vehicle And Driving Support Method For Vehicle |
-
2017
- 2017-04-21 CN CN201710265210.7A patent/CN107097781B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1802273A (en) * | 2003-06-06 | 2006-07-12 | 沃尔沃技术公司 | Method and arrangement for controlling vehicular subsystems based on interpreted driver activity |
CN101823487A (en) * | 2009-03-06 | 2010-09-08 | 通用汽车环球科技运作公司 | Detecting hand of driver in lane change or road become automatically in the operation grips or decontrols |
WO2011064825A1 (en) * | 2009-11-27 | 2011-06-03 | トヨタ自動車株式会社 | Drive assistance device and drive assistance method |
CN106335544A (en) * | 2015-07-07 | 2017-01-18 | 丰田自动车株式会社 | Driving Support Device For Vehicle And Driving Support Method For Vehicle |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108062101A (en) * | 2017-12-20 | 2018-05-22 | 驭势科技(北京)有限公司 | The intelligent personal vehicles and its control method, dispatching method and storage medium |
CN109085829A (en) * | 2018-08-09 | 2018-12-25 | 北京智行者科技有限公司 | A kind of sound state target identification method |
CN109085829B (en) * | 2018-08-09 | 2022-03-08 | 北京智行者科技有限公司 | Dynamic and static target identification method |
WO2020042859A1 (en) * | 2018-08-29 | 2020-03-05 | 上海商汤智能科技有限公司 | Smart driving control method and apparatus, vehicle, electronic device, and storage medium |
CN109374310A (en) * | 2018-09-07 | 2019-02-22 | 百度在线网络技术(北京)有限公司 | Automatic driving vehicle test method, device and storage medium |
US11520684B2 (en) | 2018-09-07 | 2022-12-06 | Apollo Intelligent Driving Technology (Beijing) Co., Ltd. | Method and apparatus for testing autonomous vehicle, and storage medium |
CN111376905A (en) * | 2018-12-27 | 2020-07-07 | 北京图森智途科技有限公司 | Parking control method, device and system for transport tool, transport tool and vehicle |
CN109849677A (en) * | 2019-04-15 | 2019-06-07 | 上汽大众汽车有限公司 | Autonomous driving vehicle energy management and low capacity prompt system and method |
CN110550024B (en) * | 2019-09-16 | 2021-08-06 | 上海拿森汽车电子有限公司 | Vehicle operation control method and device based on automatic driving |
CN110550024A (en) * | 2019-09-16 | 2019-12-10 | 上海拿森汽车电子有限公司 | vehicle operation control method and device based on automatic driving |
CN112590797A (en) * | 2019-10-01 | 2021-04-02 | 现代自动车株式会社 | Device and method for monitoring a driver and system comprising such a device |
CN111142528A (en) * | 2019-12-31 | 2020-05-12 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Vehicle dangerous scene sensing method, device and system |
CN111142528B (en) * | 2019-12-31 | 2023-10-24 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Method, device and system for sensing dangerous scene for vehicle |
CN112092827A (en) * | 2020-09-23 | 2020-12-18 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
CN112092827B (en) * | 2020-09-23 | 2022-04-22 | 北京百度网讯科技有限公司 | Automatic driving function control method, automatic driving function control device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107097781B (en) | 2019-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107097781B (en) | Vehicular automatic driving method, system, storage medium and autonomous driving vehicle | |
CN101978404B (en) | Intersection visibility determination device, vehicle with intersection visibility determination device, and method for determining intersection visibility | |
Dagan et al. | Forward collision warning with a single camera | |
CN105848981B (en) | Driver assistance method and system for vehicle | |
CN104477167B (en) | A kind of intelligent driving system and its control method | |
CN110533900B (en) | Method for assisting the driving of at least one motor vehicle, assistance system and motor vehicle | |
US10395527B2 (en) | Method and control and detection device for a plausibility check of a wrong-way driving incident of a motor vehicle | |
US20170108865A1 (en) | Method for selecting an optimized trajectory | |
GB2604514A (en) | Systems and methods for determining road safety | |
CN104943689B (en) | Control method for active automobile anti-collision system | |
CN109572693A (en) | Vehicle obstacle-avoidance householder method, system and vehicle | |
CN112154455B (en) | Data processing method, equipment and movable platform | |
CN106043299A (en) | Vehicle control apparatus | |
CN108189835A (en) | The collision avoidance control method and system of a kind of automatic Pilot | |
CN108001450B (en) | Method, system and computer program product for identifying a possible lane change and vehicle | |
CN105929823A (en) | Automatic driving system and driving method based on existing map | |
CN105501288B (en) | Power steering control device and power steering control method | |
CN110155044A (en) | Controller of vehicle | |
CN107813817A (en) | Unmanned Systems, unmanned method and vehicle | |
CN102442248A (en) | System and method for alarming front impact danger coupled with driver viewing direction and vehicle using same | |
CN109278754A (en) | The method and apparatus of adjustment for the driver assistance function based on environment | |
US10522041B2 (en) | Display device control method and display device | |
CN107082071A (en) | For preventing the unexpected method and servicing unit for leaving runway | |
CN108602483A (en) | For the system and method based on object height near phase machine testing vehicle | |
CN110456758A (en) | The outer reporting device of vehicle |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |