CN107919027A - Predict the methods, devices and systems of vehicle lane change - Google Patents
Predict the methods, devices and systems of vehicle lane change Download PDFInfo
- Publication number
- CN107919027A CN107919027A CN201711004099.2A CN201711004099A CN107919027A CN 107919027 A CN107919027 A CN 107919027A CN 201711004099 A CN201711004099 A CN 201711004099A CN 107919027 A CN107919027 A CN 107919027A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- mrow
- msub
- lane
- target track
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
This disclosure relates to a kind of methods, devices and systems for predicting vehicle lane change, to solve the problems, such as that lane change prediction is not accurate enough in correlation technique, the described method includes：Obtain the running data information that multiple vehicles are sent；The track of each vehicle current driving in same a road section is determined according to the running data information of each vehicle；Analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section according to the running data information consolidation of all vehicles on the section.
Description
Technical field
A kind of this disclosure relates to traffic information field, and in particular, to methods, devices and systems for predicting vehicle lane change.
Background technology
Vehicle travels on the road of multilane, probably due to speed traveling in track is slower, or occurs in front of the track
Accident needs lane change, it is necessary to be travelled on lane change to another unimpeded track.And drive originally on the unimpeded track
Driver, it is necessary to pay attention to observe front and back whether there is other vehicle lane change to drive into the track, avoid vehicle with just in the car of lane change
Occur scraping collision, knock into the back.
Driver judges a front and rear left side while road ahead is paid close attention to by observing main rearview mirror and left and right rearview mirror
Whether the right side has other vehicles just in lane change.If it was found that there is vehicle lane change, control vehicle accelerates or slows down so that car and car it
Between keep safe distance.Can the driving experience for whether having vehicle lane change and driver around prejudging have much relations.Separately
Outside, it is obstructed in some complicated highway sections, pilot's line of vision, whether have vehicle lane change, add road friendship if can not prejudge in time
Logical security risk.
Whether have when occurring in correlation technique by analyzing change lane and play steering indicating light to prompt whether to carry out safe change
Road, however, this only determine whether that the method for safe lane change is too simple by analysing whether to play steering indicating light, it is impossible to true
Real road safety situation when embodying lane change, does not have the effect of Risk-warning.
The content of the invention
The disclosure provides a kind of methods, devices and systems for predicting vehicle lane change, is predicted with solving lane change in correlation technique
The problem of not accurate enough.
To achieve these goals, in a first aspect, the disclosure provides a kind of method for predicting vehicle lane change, the method bag
Include：
Obtain the running data information that multiple vehicles are sent；
The track of each vehicle current driving in same a road section is determined according to the running data information of each vehicle；
Analyzing to obtain target track on the section according to the running data information consolidation of all vehicles on the section has
The probabilistic information that vehicle lane change is driven into.
Optionally, the running data information includes the speed information of vehicle, described according to all vehicles on the section
Running data information consolidation analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section, including：
According to the speed information of each vehicle in described same a road section, the average speed in each track is determined；
The average speed of the average speed in the target track first lane adjacent with the target track is compared
It is right；
If the average speed of the first lane is less than the average speed in the target track, according to the first lane
Average speed and the target track average speed between speed difference, calculate car of the traveling on the first lane
The first turning probability driven into the target lane.
Optionally, if the average speed of the first lane is less than the average speed in the target track, basis
Speed difference between the average speed of the first lane and the average speed in the target track, calculates traveling described the
The first turning probability that vehicle on one track drives into the target lane, including：
The first turning probability f is calculated according to equation below1(x):
X=| LS0-LS1 |/max (Ls0, Ls1)；
f1(x)=LCSP+1-f (x；μ1,σ1)；
Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1、
LCSP is the calibration probability calculation factor in advance.
Optionally, the running data information includes the location information of vehicle, described according to all vehicles on the section
Running data information consolidation analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section, including：
According to the first vehicle and the location information of the second vehicle that traveling is followed on the target track, described first is determined
Spacing between vehicle and second vehicle；
According to the spacing between first vehicle and second vehicle, calculating the target track has vehicle lane change to sail
The second turning probability entered.
Optionally, the spacing according between first vehicle and second vehicle, calculates the target track
There is the second turning probability that vehicle lane change is driven into, including：
The second turning probability f is calculated according to equation below2(x):
f1(x)=LCDP+1-f (x；μ2,σ2)；
Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is first vehicle and the second vehicle
Between spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
Optionally, the running data information includes the location information and transmits information of vehicle, described in the basis
The running data information consolidation of all vehicles analyzes to obtain target track on the section to have vehicle lane change to drive into general on section
Rate information, including：
According to the location information and transmits information of threeth vehicle of the traveling on the adjacent lane of the target track, really
Angle between the travel direction of fixed 3rd vehicle and the target track adjacent lane direction；
According to the angle, the 3rd turning probability that the 3rd vehicle drives into the target lane is determined.
Optionally, the running data information includes the steering indicating light information of vehicle, described according to all cars on the section
Running data information consolidation analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section, including：
According to the steering indicating light information of fourth vehicle of the traveling on the adjacent lane of the target track, the 4th car is judged
Pre- lane change direction；
When being directed toward the target track in the pre- lane change direction, determine the 4th vehicle to the target lane
The 4th turning probability driven into is predetermined probabilities value.
Second aspect, the disclosure provide a kind of device for predicting vehicle lane change, and described device includes：
Acquisition module, the running data information sent for obtaining multiple vehicles；
Determining module, for determining that each vehicle is current in same a road section according to the running data information of each vehicle
The track of traveling；
Analysis module, for analyzing to obtain the section according to the running data information consolidation of all vehicles on the section
There is the probabilistic information that vehicle lane change is driven into upper target track.
Optionally, the analysis module, for the speed information according to each vehicle in described same a road section, determines described
The average speed in each track；
The average speed of the average speed in the target track first lane adjacent with the target track is compared
It is right；
If the average speed of the first lane is less than the average speed in the target track, according to the first lane
Average speed and the target track average speed between speed difference, calculate car of the traveling on the first lane
The first turning probability driven into the target lane.
Optionally, the analysis module includes the first calculating sub module, for calculating described first turn according to equation below
To probability f1(x):
X=| LS0-LS1 |/max (Ls0, Ls1)；
f1(x)=LCSP+1-f (x；μ1,σ1)；
Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1、
LCSP is the calibration probability calculation factor in advance.
Optionally, the analysis module, for according to the first vehicle and the second car that traveling is followed on the target track
Location information, determine the spacing between first vehicle and second vehicle；
According to the spacing between first vehicle and second vehicle, calculating the target track has vehicle lane change to sail
The second turning probability entered.
Optionally, the analysis module includes the second calculating sub module, for calculating described second turn according to equation below
To probability f2(x):
f1(x)=LCDP+1-f (x；μ2,σ2)；
Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is first vehicle and the second vehicle
Between spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
Optionally, the analysis module, for the 3rd vehicle according to traveling on the adjacent lane of the target track
Location information and transmits information, determine the travel direction of the 3rd vehicle and the target track adjacent lane direction it
Between angle；
According to the angle, the 3rd turning probability that the 3rd vehicle drives into the target lane is determined.
Optionally, the analysis module, for the 4th vehicle according to traveling on the adjacent lane of the target track
Steering indicating light information, judges the pre- lane change direction of the 4th vehicle；
When being directed toward the target track in the pre- lane change direction, determine the 4th vehicle to the target lane
The 4th turning probability driven into is predetermined probabilities value.
The third aspect, the disclosure provide a kind of system for predicting vehicle lane change, the system comprises Cloud Server and are placed in
Mobile unit on each vehicle；
The Cloud Server includes the device that vehicle lane change is predicted any one of above-mentioned second aspect；
The mobile unit is used for the running data information of collection vehicle, and the running data information is uploaded to described
Cloud Server.
Through the above technical solutions, the running data information sent by obtaining multiple vehicles, and according to each car
Running data information determine the track of each vehicle current driving in same a road section, further according to all vehicles on the section
Running data information consolidation analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section.In this way, can
The probability that obtaining target track with the multiple vehicle operation data information analyses considered on track has vehicle lane change to drive into is believed
Breath, makes the result of change trace analysis more accurate.
Other feature and advantage of the disclosure will be described in detail in subsequent specific embodiment part.
Brief description of the drawings
Attached drawing is for providing further understanding of the disclosure, and a part for constitution instruction, with following tool
Body embodiment is used to explain the disclosure together, but does not form the limitation to the disclosure.In the accompanying drawings：
Fig. 1 is a kind of flow chart of the method for prediction vehicle lane change shown in one exemplary embodiment of the disclosure.
Fig. 2 is a kind of implement scene schematic diagram shown in one exemplary embodiment of the disclosure.
Fig. 3 is a kind of device block diagram of prediction vehicle lane change shown in one exemplary embodiment of the disclosure.
Fig. 4 is a kind of system block diagram of prediction vehicle lane change shown in one exemplary embodiment of the disclosure.
Embodiment
The embodiment of the disclosure is described in detail below in conjunction with attached drawing.It should be appreciated that this place is retouched
The embodiment stated is only used for describing and explaining the disclosure, is not limited to the disclosure.
Fig. 1 is a kind of flow chart of the method for prediction vehicle lane change shown in one exemplary embodiment of the disclosure.The side
Method can be applied to Cloud Server, the described method includes：
S11, obtains the running data information that multiple vehicles are sent.
When it is implemented, being mounted with mobile unit OBU (On Board Unit) on each vehicle, which can be with vehicle
Cloud Server establishes communication link, and the information exchange work(with Cloud Server is realized by built-in uploading module and download module
Energy.For example, the OBU can have the function of V2X T-BOX (TelematicsBOX).
In addition, locating module is further included in vehicle-mounted OBU, such as, it is possible to achieve resolution ratio is the difference of the positioning of Centimeter Level
Locating module.Further include CAN bus data acquisition module, can from CAN bus real-time collection vehicle running data.
To ensure the timeliness of data, data collection cycle and upload cycle can adjust according to actual conditions, the disclosure
Do not limit herein.For example, OBU can be with the cycle CAN bus data of 100ms, and the vehicle operation data that will be collected in 1s
Transmit to Cloud Server.It can include longitude, latitude, travel speed, travel direction, the height above sea level of vehicle in the data of packing
Highly, sampling instant, steering angle, brake number, acceleration etc..If in addition, include doubling blind area auxiliary mould on the vehicle
Block (BSM), OBU can also gather doubling blind area mould message data in the block, and the message data is uploaded to Cloud Server.
Cloud Server, can be to invalid number therein after the running data information that the OBU for getting multiple vehicles is sent
According to data fusion cleaning is carried out, invalid data are rejected.For example, the continuous sampling that the running data uploaded is included in 1s obtains
100 different sampled point speeds, wherein, have that the difference between the speed and neighbouring sample point speed of individual sample point is excessive,
Then it is proposed that the data of these sampled points.
S12, the car of each vehicle current driving in same a road section is determined according to the running data information of each vehicle
Road.
It is possible, firstly, to section division is carried out to road according to speed.For example the road speed limit is 60Km/h, i.e. 16m/s,
The vehicle road vehicle can travel 48m in 3s, then it is 48m to set every a road section on the road.So set be in order to
The operation information amount of every a road section can be simplified in follow-up calculate, improve system operations efficiency.By upper, can obtain dividing
Section set R { Ri | i=1,2,3 ..., n }.
Then, lane location is carried out to the vehicle travelled on every a road section Ri.Specifically, the longitude and latitude of each vehicle is believed
Breath and transmits information, it is superimposed with the electronic map demarcated in advance, it can so judge each vehicle on the Ri of section
The track being currently located.For example, as shown in Fig. 2, road is divided into section R1, section R2, section R3, there are three per a road section
Track is track 1, track 2, track 3 respectively.Vehicle A is understood after positioning on section R2 tracks 2, vehicle B is in section R1 tracks 3
On, vehicle C will drive into section R3 on track 3, therefore can position vehicle C to the track 3 of section R3.
S13, analyzes to obtain target carriage on the section according to the running data information consolidation of all vehicles on the section
There is the probabilistic information that vehicle lane change is driven into road.
In the first optional embodiment, the running data information includes the speed information of vehicle, described in the basis
The running data information consolidation of all vehicles analyzes to obtain target track on the section to have vehicle lane change to drive into general on section
Rate information, including：According to the speed information of each vehicle in described same a road section, the average speed in each track is determined；
The average speed of the average speed in the target track first lane adjacent with the target track is compared；It is if described
The average speed of first lane is less than the average speed in the target track, then according to the average speed of the first lane and institute
The speed difference between the average speed in target track is stated, calculates vehicle of the traveling on the first lane to the target carriage
The first turning probability that road lane change is driven into.
Specifically, the speed information read with vehicle all on each track in a road section can be traveled through, then calculate this
The average speed in each track on section.What deserves to be explained is the average speed difference between two adjacent lanes is bigger, then at a slow speed
The probability that vehicle lane change on track drives into express lane is bigger.Therefore, can be according to the average speed between two adjacent lanes
Difference, calculates the probability that the vehicle lane change at a slow speed on track drives into express lane.
Wherein, if the average speed of the first lane is less than the average speed in the target track, according to institute
The speed difference between the average speed of first lane and the average speed in the target track is stated, calculates traveling described first
The first turning probability that vehicle on track drives into the target lane, including：
The first turning probability f is calculated according to equation below1(x):
X=| LS0-LS1 |/max (Ls0, Ls1)；
f1(x)=LCSP+1-f (x；μ1,σ1)；
Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1、
LCSP is the calibration probability calculation factor in advance.Illustratively, μ1=0, σ1 2=0.2, LCSP can be set as constant 30%.For not
Same road scene, the value of LCSP can adjust accordingly, and the disclosure does not limit herein.
Work as f1(x) when result of calculation is more than the first predetermined probabilities threshold value, Cloud Server can be to current driving in the mesh
All vehicles on mark track issue lane change prompting message.After vehicle receives the prompting message, prompt tone or instruction can be passed through
The traveling prompting driver of lamp notices whether front has vehicle lane change to drive into.
In the second optional embodiment, the running data information includes the location information of vehicle, described in the basis
The running data information consolidation of all vehicles analyzes to obtain target track on the section to have vehicle lane change to drive into general on section
Rate information, including：According to the first vehicle and the location information of the second vehicle that traveling is followed on the target track, determine described
Spacing between first vehicle and second vehicle；According to the spacing between first vehicle and second vehicle, meter
Calculate the second turning probability that the target track has vehicle lane change to drive into.
What deserves to be explained is target track goes forward to get over followed by the spacing between the first vehicle and the second vehicle of traveling
Greatly, the probability that the vehicle lane change on adjacent lane is driven between the two cars is bigger.If there is vehicle lane change to drive into, it is located behind
Second vehicle needs to slow down in time, and avoiding knocking into the back with lane change vehicle scratches.
Specifically, the spacing according between first vehicle and second vehicle, calculates the target track
There is the second turning probability that vehicle lane change is driven into, including：
The second turning probability f is calculated according to equation below2(x):
f1(x)=LCDP+1-f (x；μ2,σ2)；
Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is first vehicle and the second vehicle
Between spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
Illustratively, if average length of wagon is 2.5m, VL can be twice of the average length of wagon, i.e. 5m.μ1=
0, σ1 2=0.2, LCDP can be set as constant 40%.For different road scenes, the value of LCDP can adjust accordingly, this
It is open not limit herein.
Work as f2(x) when result of calculation is more than the second predetermined probabilities threshold value, Cloud Server can be to current driving in target carriage
Second vehicle on road issues lane change prompting message.After second vehicle receives the prompting message, prompting can be passed through
The traveling of sound or indicator light prompting driver notices whether front has vehicle lane change to drive into.
In the 3rd optional embodiment, the running data information includes the location information and travel direction letter of vehicle
Breath, the running data information consolidation according to all vehicles on the section, which analyzes to obtain target track on the section, car
The probabilistic information that lane change is driven into, including：Believed according to the positioning of threeth vehicle of the traveling on the adjacent lane of the target track
Breath and transmits information, determine the folder between the travel direction of the 3rd vehicle and the target track adjacent lane direction
Angle；According to the angle, the 3rd turning probability that the 3rd vehicle drives into the target lane is determined.
What deserves to be explained is when the 3rd vehicle on the adjacent lane in the target track when driving, if the row of the 3rd vehicle
When sailing the angle between direction and the adjacent lane direction and being more than certain angle, the 3rd vehicle may turn to.Therefore, may be used
To pre-set the correspondence of the angle and the 3rd turning probability, more big then the 3rd turning probability of angle is bigger.For example, according to
The travel direction that the angle judges to obtain vehicle is directed toward the target track, and the angle is equal to the first default angle value, then
It is 40% to determine the 3rd turning probability.If the angle is more than the described first default angle value and becomes larger, with
The angle value the 3rd turning probability determined that becomes larger also gradually increases.
When the 3rd turning probability is more than the 3rd predetermined probabilities threshold value, Cloud Server can be to current driving described
Vehicle on target track issues lane change prompting message.
In the 4th optional embodiment, the running data information includes the steering indicating light information of vehicle, described according to institute
The running data information consolidation for stating all vehicles on section analyzes to obtain target track on the section and has what vehicle lane change was driven into
Probabilistic information, including：According to the steering indicating light information of fourth vehicle of the traveling on the adjacent lane of the target track, described in judgement
The pre- lane change direction of 4th vehicle；When being directed toward the target track in the pre- lane change direction, determine the 4th vehicle to institute
It is predetermined probabilities value to state the 4th turning probability that target lane drives into.
What deserves to be explained is steering indicating light can reflect the driving intention of driver.OBU can be gathered in car body controller
Light data, and the light data is uploaded to Cloud Server.
, can be by above-mentioned four kinds of optional implementation in the method for the optional prediction vehicle lane change of another kind that the disclosure provides
Mode combines, the turning probability weighted sum that each embodiment is obtained, to obtain final total turning probability.
To reduce the operand of server, server handles data according to cycle T and calculates total turning probability.At this
When total turning probability is more than default total probability threshold value, to target track on the vehicle set that is influenced by lane change issue lane change prompting and disappear
Breath.
Through the above technical solutions, the running data information sent by obtaining multiple vehicles, and according to each car
Running data information determine the track of each vehicle current driving in same a road section, further according to all vehicles on the section
Running data information consolidation analyze to obtain the probabilistic information that target track has vehicle lane change to drive on the section.In this way, can
The probability that obtaining target track with the multiple vehicle operation data information analyses considered on track has vehicle lane change to drive into is believed
Breath, makes the result of change trace analysis more accurate.
Fig. 3 is a kind of device 300 of prediction vehicle lane change shown in one exemplary embodiment of the disclosure, described device 300
Including：
Acquisition module 310, the running data information sent for obtaining multiple vehicles；
Determining module 320, for determining each vehicle in same a road section according to the running data information of each vehicle
The track of current driving；
Analysis module 330, for according to the running data information consolidation of all vehicles on the section is analyzed to obtain
There is the probabilistic information that vehicle lane change is driven into target track on section.
Above device 300, the running data information sent by obtaining multiple vehicles, and according to the row of each vehicle
The track that data message determines each vehicle current driving in same a road section is sailed, further according to the traveling of all vehicles on the section
Data message Conjoint Analysis obtains the probabilistic information that target track has vehicle lane change to drive on the section.In this way, it can integrate
Consider that multiple vehicle operation data information analyses on track obtain the probabilistic information that target track has vehicle lane change to drive into, make change
The result of trace analysis is more accurate.
In the first optional embodiment, the analysis module 330, for according to each vehicle in described same a road section
Speed information, determine the average speed in each track；
The average speed of the average speed in the target track first lane adjacent with the target track is compared
It is right；
If the average speed of the first lane is less than the average speed in the target track, according to the first lane
Average speed and the target track average speed between speed difference, calculate car of the traveling on the first lane
The first turning probability driven into the target lane.
Specifically, the analysis module 330 includes the first calculating sub module, for calculating described first according to equation below
Turning probability f1(x):
X=| LS0-LS1 |/max (Ls0, Ls1)；
f1(x)=LCSP+1-f (x；μ1,σ1)；
Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1、
LCSP is the calibration probability calculation factor in advance.
In the second optional embodiment, the analysis module 330, for following traveling according on the target track
The first vehicle and the second vehicle location information, determine the spacing between first vehicle and second vehicle；
According to the spacing between first vehicle and second vehicle, calculating the target track has vehicle lane change to sail
The second turning probability entered.
Specifically, the analysis module 330 includes the second calculating sub module, for calculating described second according to equation below
Turning probability f2(x):
f1(x)=LCDP+1-f (x；μ2,σ2)；
Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is first vehicle and the second vehicle
Between spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
In the 3rd optional embodiment, the analysis module 330, for adjacent in the target track according to travelling
The location information and transmits information of the 3rd vehicle on track, determine the travel direction of the 3rd vehicle and the target
Angle between the adjacent lane direction of track；According to the angle, determine that the 3rd vehicle is sailed to the target lane
The 3rd turning probability entered.
In the 4th optional embodiment, the analysis module 330, for adjacent in the target track according to travelling
The steering indicating light information of the 4th vehicle on track, judges the pre- lane change direction of the 4th vehicle；Refer in the pre- lane change direction
During to the target track, determine that the 4th turning probability that the 4th vehicle drives into the target lane is default general
Rate value.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in related this method
Embodiment in be described in detail, explanation will be not set forth in detail herein.
The disclosure also provides a kind of system for predicting vehicle lane change, as shown in figure 4, the system comprises Cloud Server 400
With the mobile unit 500 being placed on each vehicle；The Cloud Server 400 includes the device of prediction vehicle lane change described above
300；The mobile unit 500 is used for the running data information of collection vehicle, and the running data information is uploaded to described
Cloud Server 400.
The mobile unit 500 can be vehicle-mounted OBU equipment described above.Specifically, the Cloud Server 400 also wraps
Include result release module；The mobile unit 500 includes acquisition module, data uploading module, data reception module；The collection
Module is used for the running data information of collection vehicle；The data uploading module is used to the running data information being uploaded to institute
State Cloud Server 400；The data reception module is used to receive the lane change prompting message that the result release module issues.
The preferred embodiment of the disclosure is described in detail above in association with attached drawing, still, the disclosure is not limited to above-mentioned reality
The detail in mode is applied, in the range of the technology design of the disclosure, a variety of letters can be carried out to the technical solution of the disclosure
Monotropic type, these simple variants belong to the protection domain of the disclosure.
It is further to note that each particular technique feature described in above-mentioned embodiment, in not lance
In the case of shield, can be combined by any suitable means, in order to avoid unnecessary repetition, the disclosure to it is various can
The combination of energy no longer separately illustrates.
In addition, it can also be combined between a variety of embodiments of the disclosure, as long as it is without prejudice to originally
Disclosed thought, it should equally be considered as disclosure disclosure of that.
Claims (15)
- A kind of 1. method for predicting vehicle lane change, it is characterised in that the described method includes：Obtain the running data information that multiple vehicles are sent；The track of each vehicle current driving in same a road section is determined according to the running data information of each vehicle；Analyzing to obtain target track on the section according to the running data information consolidation of all vehicles on the section has vehicle The probabilistic information that lane change is driven into.
- 2. according to the method described in claim 1, it is characterized in that, the running data information includes the speed information of vehicle, The running data information consolidation according to all vehicles on the section, which analyzes to obtain target track on the section, vehicle The probabilistic information that lane change is driven into, including：According to the speed information of each vehicle in described same a road section, the average speed in each track is determined；The average speed of the average speed in the target track first lane adjacent with the target track is compared；If the average speed of the first lane is less than the average speed in the target track, according to the flat of the first lane Speed difference between equal speed and the average speed in the target track, calculate vehicle of the traveling on the first lane to The first turning probability that the target lane drives into.
- 3. if according to the method described in claim 2, it is characterized in that, the average speed of the first lane is less than described The average speed in target track, then according between the average speed of the first lane and the average speed in the target track Speed difference, calculates the first turning probability that vehicle of the traveling on the first lane drives into the target lane, Including：The first turning probability f is calculated according to equation below1(x):X=| LS0-LS1 |/max (Ls0, Ls1)；<mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>;</mo> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>,</mo> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <msqrt> <mrow> <mn>2</mn> <mi>&pi;</mi> </mrow> </msqrt> </mrow> </mfrac> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <msup> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mrow> <mn>2</mn> <msup> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <mn>2</mn> </msup> </mrow> </mfrac> <mo>)</mo> </mrow> <mo>;</mo> </mrow>f1(x)=LCSP+1-f (x；μ1,σ1)；Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1, LCSP be The calibration probability calculation factor in advance.
- 4. according to the method described in claim 1, it is characterized in that, the running data information includes the location information of vehicle, The running data information consolidation according to all vehicles on the section, which analyzes to obtain target track on the section, vehicle The probabilistic information that lane change is driven into, including：According to the first vehicle and the location information of the second vehicle that traveling is followed on the target track, first vehicle is determined Spacing between second vehicle；According to the spacing between first vehicle and second vehicle, calculating the target track has what vehicle lane change was driven into Second turning probability.
- 5. according to the method described in claim 4, it is characterized in that, it is described according to first vehicle and second vehicle it Between spacing, calculate the second turning probability that the target track has vehicle lane change to drive into, including：The second turning probability f is calculated according to equation below2(x):<mrow> <mi>X</mi> <mo>=</mo> <mfrac> <mrow> <mi>V</mi> <mi>L</mi> </mrow> <mrow> <mi>L</mi> <mi>D</mi> <mi>i</mi> </mrow> </mfrac> <mo>;</mo> </mrow><mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>;</mo> <msub> <mi>&mu;</mi> <mn>2</mn> </msub> <mo>,</mo> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <msqrt> <mrow> <mn>2</mn> <mi>&pi;</mi> </mrow> </msqrt> </mrow> </mfrac> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <msup> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mrow> <mn>2</mn> <msup> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <mn>2</mn> </msup> </mrow> </mfrac> <mo>)</mo> </mrow> <mo>;</mo> </mrow>f1(x)=LCDP+1-f (x；μ2,σ2)；Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is between first vehicle and the second vehicle Spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
- 6. according to claim 1-5 any one of them methods, it is characterised in that the running data information includes determining for vehicle Position information and transmits information, described in the running data information consolidation according to all vehicles on the section is analyzed to obtain There is the probabilistic information that vehicle lane change is driven into target track on section, including：According to the location information and transmits information of threeth vehicle of the traveling on the adjacent lane of the target track, institute is determined State the angle between the travel direction of the 3rd vehicle and the target track adjacent lane direction；According to the angle, the 3rd turning probability that the 3rd vehicle drives into the target lane is determined.
- 7. according to claim 1-5 any one of them methods, it is characterised in that the running data information includes turning for vehicle To lamp information, the running data information consolidation according to all vehicles on the section is analyzed to obtain target carriage on the section There is the probabilistic information that vehicle lane change is driven into road, including：According to the steering indicating light information of fourth vehicle of the traveling on the adjacent lane of the target track, the 4th vehicle is judged Pre- lane change direction；When being directed toward the target track in the pre- lane change direction, determine that the 4th vehicle drives into the target lane The 4th turning probability be predetermined probabilities value.
- 8. a kind of device for predicting vehicle lane change, it is characterised in that described device includes：Acquisition module, the running data information sent for obtaining multiple vehicles；Determining module, for determining each vehicle current driving in same a road section according to the running data information of each vehicle Track；Analysis module, for analyzing to obtain mesh on the section according to the running data information consolidation of all vehicles on the section There is the probabilistic information that vehicle lane change is driven into mark track.
- 9. device according to claim 8, it is characterised in that the analysis module, for according to described same a road section The speed information of each vehicle, determines the average speed in each track；The average speed of the average speed in the target track first lane adjacent with the target track is compared；If the average speed of the first lane is less than the average speed in the target track, according to the flat of the first lane Speed difference between equal speed and the average speed in the target track, calculate vehicle of the traveling on the first lane to The first turning probability that the target lane drives into.
- 10. device according to claim 9, it is characterised in that the analysis module includes the first calculating sub module, is used for The first turning probability f is calculated according to equation below1(x):X=| LS0-LS1 |/max (Ls0, Ls1)；<mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>;</mo> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>,</mo> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <msqrt> <mrow> <mn>2</mn> <mi>&pi;</mi> </mrow> </msqrt> </mrow> </mfrac> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <msup> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>1</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mrow> <mn>2</mn> <msup> <msub> <mi>&sigma;</mi> <mn>1</mn> </msub> <mn>2</mn> </msup> </mrow> </mfrac> <mo>)</mo> </mrow> <mo>;</mo> </mrow>f1(x)=LCSP+1-f (x；μ1,σ1)；Wherein, LS0 be the target track average speed, LS1 be the first lane average speed, μ1、σ1, LCSP be The calibration probability calculation factor in advance.
- 11. device according to claim 8, it is characterised in that the analysis module, for according to the target track The first vehicle of traveling and the location information of the second vehicle are followed, between determining between first vehicle and second vehicle Away from；According to the spacing between first vehicle and second vehicle, calculating the target track has what vehicle lane change was driven into Second turning probability.
- 12. according to the devices described in claim 11, it is characterised in that the analysis module includes the second calculating sub module, uses According to equation below calculating the second turning probability f2(x):<mrow> <mi>X</mi> <mo>=</mo> <mfrac> <mrow> <mi>V</mi> <mi>L</mi> </mrow> <mrow> <mi>L</mi> <mi>D</mi> <mi>i</mi> </mrow> </mfrac> <mo>,</mo> </mrow><mrow> <mi>f</mi> <mrow> <mo>(</mo> <mi>x</mi> <mo>;</mo> <msub> <mi>&mu;</mi> <mn>2</mn> </msub> <mo>,</mo> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mrow> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <msqrt> <mrow> <mn>2</mn> <mi>&pi;</mi> </mrow> </msqrt> </mrow> </mfrac> <mi>exp</mi> <mrow> <mo>(</mo> <mo>-</mo> <mfrac> <msup> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>&mu;</mi> <mn>2</mn> </msub> <mo>)</mo> </mrow> <mn>2</mn> </msup> <mrow> <mn>2</mn> <msup> <msub> <mi>&sigma;</mi> <mn>2</mn> </msub> <mn>2</mn> </msup> </mrow> </mfrac> <mo>)</mo> </mrow> <mo>;</mo> </mrow>f1(x)=LCDP+1-f (x；μ2,σ2)；Wherein, VL is the length value demarcated in advance according to average length of wagon, and LDi is between first vehicle and the second vehicle Spacing, μ2、σ2, LCDP in advance calibration the probability calculation factor.
- 13. according to claim 8-12 any one of them devices, it is characterised in that the analysis module, for according to traveling The location information and transmits information of the 3rd vehicle on the adjacent lane of the target track, determine the 3rd vehicle Angle between travel direction and the target track adjacent lane direction；According to the angle, the 3rd turning probability that the 3rd vehicle drives into the target lane is determined.
- 14. according to claim 8-12 any one of them devices, it is characterised in that the analysis module, for according to traveling The steering indicating light information of the 4th vehicle on the adjacent lane of the target track, judges the pre- lane change direction of the 4th vehicle；When being directed toward the target track in the pre- lane change direction, determine that the 4th vehicle drives into the target lane The 4th turning probability be predetermined probabilities value.
- 15. a kind of system for predicting vehicle lane change, it is characterised in that the system comprises Cloud Server and be placed on each vehicle Mobile unit；The Cloud Server includes the device that vehicle lane change is predicted any one of the claims 8-14；The mobile unit is used for the running data information of collection vehicle, and the running data information is uploaded to the cloud and is taken Business device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711004099.2A CN107919027B (en) | 2017-10-24 | 2017-10-24 | Method, device and system for predicting lane change of vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711004099.2A CN107919027B (en) | 2017-10-24 | 2017-10-24 | Method, device and system for predicting lane change of vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107919027A true CN107919027A (en) | 2018-04-17 |
| CN107919027B CN107919027B (en) | 2020-04-28 |
Family
ID=61895711
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711004099.2A Active CN107919027B (en) | 2017-10-24 | 2017-10-24 | Method, device and system for predicting lane change of vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107919027B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108437796A (en) * | 2018-05-18 | 2018-08-24 | 北京汽车集团有限公司 | Control method for vehicle, device and vehicle |
| CN108471607A (en) * | 2018-05-22 | 2018-08-31 | 奇瑞汽车股份有限公司 | A kind of interacted system that T-BOX is merged with V2X |
| CN108520639A (en) * | 2018-06-15 | 2018-09-11 | 中国安全生产科学研究院 | A kind of method for early warning and system preventing vehicle collision |
| CN109345870A (en) * | 2018-09-07 | 2019-02-15 | 北京邮电大学 | The method for early warning and device for preventing vehicle collision |
| CN110110029A (en) * | 2019-05-17 | 2019-08-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for matching lane |
| CN110400490A (en) * | 2019-08-08 | 2019-11-01 | 腾讯科技（深圳）有限公司 | Trajectory predictions method and apparatus |
| CN110920622A (en) * | 2019-12-06 | 2020-03-27 | 格物汽车科技(苏州)有限公司 | Prediction method before vehicle changes lane to target lane in automatic driving |
| CN111275972A (en) * | 2020-02-22 | 2020-06-12 | 长安大学 | Automobile lane change early warning method and device based on V2V |
| CN111428943A (en) * | 2020-04-23 | 2020-07-17 | 福瑞泰克智能系统有限公司 | Method, device and computer device for predicting obstacle vehicle track |
| CN111754816A (en) * | 2020-06-04 | 2020-10-09 | 纵目科技（上海）股份有限公司 | Moving object intention identification method, system, terminal and storage medium |
| WO2020249122A1 (en) * | 2019-06-14 | 2020-12-17 | 华为技术有限公司 | Lane change method and device for vehicle |
| WO2021073389A1 (en) * | 2019-10-16 | 2021-04-22 | 腾讯科技（深圳）有限公司 | Vehicle automatic control method and lane change intention prediction network training method |
| CN112703506A (en) * | 2020-04-22 | 2021-04-23 | 华为技术有限公司 | Lane line detection method and device |
| CN114424264A (en) * | 2019-09-19 | 2022-04-29 | 华为云计算技术有限公司 | Device for synchronizing position information |
| WO2022099526A1 (en) * | 2020-11-12 | 2022-05-19 | 深圳元戎启行科技有限公司 | Method for training lane change prediction regression model, and lane change predicton method and apparatus |
| WO2023123456A1 (en) * | 2021-12-31 | 2023-07-06 | 深圳市大疆创新科技有限公司 | Vehicle location prediction method and apparatus, and vehicle and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004157731A (en) * | 2002-11-06 | 2004-06-03 | Nissan Motor Co Ltd | Vehicular recommended control input generation system |
| JP2006178714A (en) * | 2004-12-22 | 2006-07-06 | Nissan Motor Co Ltd | Traveling supporting device |
| CN103065501A (en) * | 2012-12-14 | 2013-04-24 | 清华大学 | Automobile lane changing early-warning method and lane changing early-warning system |
| CN105957399A (en) * | 2016-05-31 | 2016-09-21 | 于德芳 | Traffic safety monitoring method |
| CN106297340A (en) * | 2016-08-17 | 2017-01-04 | 上海电机学院 | A kind of driving vehicle pre-warning system for monitoring and method |
| CN106314431A (en) * | 2015-06-29 | 2017-01-11 | 比亚迪股份有限公司 | Cruise control system and method for vehicles |
| CN106327896A (en) * | 2016-09-06 | 2017-01-11 | 中国第汽车股份有限公司 | Lane selection system and method for autonomous vehicle |
| CN107204128A (en) * | 2017-05-04 | 2017-09-26 | 南京工程学院 | Vehicle anticollision early warning system and method based on ZigBee communication |
-
2017
- 2017-10-24 CN CN201711004099.2A patent/CN107919027B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004157731A (en) * | 2002-11-06 | 2004-06-03 | Nissan Motor Co Ltd | Vehicular recommended control input generation system |
| JP2006178714A (en) * | 2004-12-22 | 2006-07-06 | Nissan Motor Co Ltd | Traveling supporting device |
| CN103065501A (en) * | 2012-12-14 | 2013-04-24 | 清华大学 | Automobile lane changing early-warning method and lane changing early-warning system |
| CN106314431A (en) * | 2015-06-29 | 2017-01-11 | 比亚迪股份有限公司 | Cruise control system and method for vehicles |
| CN105957399A (en) * | 2016-05-31 | 2016-09-21 | 于德芳 | Traffic safety monitoring method |
| CN106297340A (en) * | 2016-08-17 | 2017-01-04 | 上海电机学院 | A kind of driving vehicle pre-warning system for monitoring and method |
| CN106327896A (en) * | 2016-09-06 | 2017-01-11 | 中国第汽车股份有限公司 | Lane selection system and method for autonomous vehicle |
| CN107204128A (en) * | 2017-05-04 | 2017-09-26 | 南京工程学院 | Vehicle anticollision early warning system and method based on ZigBee communication |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108437796A (en) * | 2018-05-18 | 2018-08-24 | 北京汽车集团有限公司 | Control method for vehicle, device and vehicle |
| CN108471607A (en) * | 2018-05-22 | 2018-08-31 | 奇瑞汽车股份有限公司 | A kind of interacted system that T-BOX is merged with V2X |
| CN108520639A (en) * | 2018-06-15 | 2018-09-11 | 中国安全生产科学研究院 | A kind of method for early warning and system preventing vehicle collision |
| CN108520639B (en) * | 2018-06-15 | 2023-10-27 | 中国安全生产科学研究院 | Early warning method and system for preventing vehicle collision |
| CN109345870A (en) * | 2018-09-07 | 2019-02-15 | 北京邮电大学 | The method for early warning and device for preventing vehicle collision |
| CN110110029A (en) * | 2019-05-17 | 2019-08-09 | 百度在线网络技术（北京）有限公司 | Method and apparatus for matching lane |
| CN110110029B (en) * | 2019-05-17 | 2021-08-24 | 百度在线网络技术（北京）有限公司 | Method and device for lane matching |
| WO2020249122A1 (en) * | 2019-06-14 | 2020-12-17 | 华为技术有限公司 | Lane change method and device for vehicle |
| CN110400490A (en) * | 2019-08-08 | 2019-11-01 | 腾讯科技（深圳）有限公司 | Trajectory predictions method and apparatus |
| CN114424264B (en) * | 2019-09-19 | 2024-05-17 | 华为云计算技术有限公司 | Device for synchronizing position information |
| CN114424264A (en) * | 2019-09-19 | 2022-04-29 | 华为云计算技术有限公司 | Device for synchronizing position information |
| WO2021073389A1 (en) * | 2019-10-16 | 2021-04-22 | 腾讯科技（深圳）有限公司 | Vehicle automatic control method and lane change intention prediction network training method |
| CN110920622A (en) * | 2019-12-06 | 2020-03-27 | 格物汽车科技(苏州)有限公司 | Prediction method before vehicle changes lane to target lane in automatic driving |
| CN111275972A (en) * | 2020-02-22 | 2020-06-12 | 长安大学 | Automobile lane change early warning method and device based on V2V |
| CN112703506A (en) * | 2020-04-22 | 2021-04-23 | 华为技术有限公司 | Lane line detection method and device |
| CN111428943B (en) * | 2020-04-23 | 2021-08-03 | 福瑞泰克智能系统有限公司 | Method, device and computer device for predicting obstacle vehicle track |
| CN111428943A (en) * | 2020-04-23 | 2020-07-17 | 福瑞泰克智能系统有限公司 | Method, device and computer device for predicting obstacle vehicle track |
| CN111754816A (en) * | 2020-06-04 | 2020-10-09 | 纵目科技（上海）股份有限公司 | Moving object intention identification method, system, terminal and storage medium |
| WO2022099526A1 (en) * | 2020-11-12 | 2022-05-19 | 深圳元戎启行科技有限公司 | Method for training lane change prediction regression model, and lane change predicton method and apparatus |
| CN114945961A (en) * | 2020-11-12 | 2022-08-26 | 深圳元戎启行科技有限公司 | Lane-changing prediction regression model training method, lane-changing prediction method and device |
| CN114945961B (en) * | 2020-11-12 | 2024-03-08 | 深圳元戎启行科技有限公司 | Lane changing prediction regression model training method, lane changing prediction method and apparatus |
| WO2023123456A1 (en) * | 2021-12-31 | 2023-07-06 | 深圳市大疆创新科技有限公司 | Vehicle location prediction method and apparatus, and vehicle and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107919027B (en) | 2020-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107919027A (en) | Predict the methods, devices and systems of vehicle lane change | |
| CN106940933B (en) | A kind of intelligent vehicle decision lane-change method based on intelligent transportation system | |
| CN205943100U (en) | HMI shows system for V2X scene | |
| Tsugawa et al. | An automated truck platoon for energy saving | |
| CN107331191B (en) | Abnormal running vehicle positioning method, cloud server and system | |
| CN106706341B (en) | Test method and test field for lane changing capability of automatic driving vehicle | |
| Dagan et al. | Forward collision warning with a single camera | |
| CN102295004B (en) | Lane departure warning method | |
| CN103465907B (en) | A kind of automotive correlation prevention device and method | |
| CN103164962B (en) | Mountain road sharp turn section real-time vehicle speed early warning method | |
| CN104680841B (en) | Driving early warning method | |
| CN205334746U (en) | On -vehicle virtual road status display system based on bus or train route is technique in coordination | |
| CN103153748B (en) | Method and information system for informing a vehicle driver about conditions of a planned passing maneuver | |
| CN109801494A (en) | A kind of crossing dynamic guiding system and method based on V2X | |
| CN106394559A (en) | Multi-target driving behavior evaluation analytical method based on environmental perception information | |
| CN105774800A (en) | Collision relieving method and device between vehicles in hybrid vehicle queue | |
| CN107000750A (en) | For the improved device and method of vehicle economy | |
| CN106128137A (en) | Urban road traffic intersection in-vehicle traffic information lamp early warning method and system based on Internet of vehicles | |
| CN109849785B (en) | Lane change judgment system and method based on Internet of vehicles | |
| CN104325978A (en) | Safety anti-collision early warning method based on vehicular ad-hoc network | |
| CN204055561U (en) | Vehicle safe driving caution system | |
| CN113763740A (en) | Big data traffic guidance system and guidance method | |
| CN106251666A (en) | Under the foggy environment of intelligent network connection automobile, expressway safety speed guides system and method | |
| CN107972664A (en) | Drive assistance device and driving assistance method | |
| CN114898578B (en) | Vehicle guiding method, device and system for expressway |
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 |