CN107945574A - A kind of vehicle collision prewarning method, device and equipment - Google Patents
A kind of vehicle collision prewarning method, device and equipment Download PDFInfo
- Publication number
- CN107945574A CN107945574A CN201711015264.4A CN201711015264A CN107945574A CN 107945574 A CN107945574 A CN 107945574A CN 201711015264 A CN201711015264 A CN 201711015264A CN 107945574 A CN107945574 A CN 107945574A
- Authority
- CN
- China
- Prior art keywords
- target vehicle
- collision
- vehicle
- history
- priori
- 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
- G08G1/164—Centralised systems, e.g. external to vehicles
Abstract
The embodiment of the present application discloses a kind of vehicle collision prewarning method, by the real time running state for obtaining target vehicle, and the mapping relations of history transport condition and priori collision threat coefficient, then, according to the real time running state of the target vehicle and the mapping relations, obtain the priori collision threat coefficient of the target vehicle, then, according to the posteriority collision threat coefficient of the real time running state computation of the target vehicle target vehicle, finally, collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, judge whether to need to carry out early warning to target vehicle.Since priori collision coefficient can reflect the possibility that trained vehicle collides under history transport condition, so the combination of priori collision threat coefficient and posteriority collision threat coefficient can more accurately predict the possibility of other vehicle collisions of target vehicle Yu surrounding, so as to reduce the early warning fault rate to target vehicle.
Description
Technical field
This application involves intelligent vehicle field, more particularly to a kind of vehicle collision prewarning method, device and equipment.
Background technology
In order to reduce the generation of traffic accident, between speed of the prior art based on vehicle, travel direction and vehicle
The real time running such as relative distance state parameter estimates the time collided between vehicle, if the collision time that estimation obtains is small
In or equal to some threshold value, then early warning is carried out, to remind driver to take corresponding anticollision measure.
But this of the prior art carries out the mode early warning effect of anti-collision warning simultaneously based on real-time vehicle running state
It is bad, it is pre- it is possible to cause because vehicle can not represent the traveling trend of vehicle in operating status sometime
Alert error.For example, if vehicle is larger in instantaneous velocity sometime so that the collision time being calculated is less than threshold value,
Early warning is carried out at this time;And speed is smaller within ensuing a period of time so that the collision time being calculated is more than threshold value,
So just without early warning.It can be seen that early warning is just slipped up for early warning caused by instantaneous velocity is larger.
The content of the invention
In order to solve the problems, such as that prior art early warning is inaccurate, this application provides a kind of vehicle collision prewarning method, dress
Put and equipment, to realize the more accurate possibility of other vehicle collisions of prediction target vehicle Yu surrounding, so as to reduce to mesh
Mark the early warning fault rate of vehicle
In a first aspect, this application provides a kind of vehicle collision prewarning method, the described method includes:
The real time running state of target vehicle is obtained, and history transport condition and the mapping of priori collision threat coefficient are closed
System, the priori collision threat coefficient reflect several collision possibilities of training vehicle under the history transport condition;
According to the real time running state of the target vehicle and the mapping relations, the priori for obtaining the target vehicle is touched
Hit threat coefficient;
It is described according to the posteriority collision threat coefficient of target vehicle described in the real time running state computation of the target vehicle
Posteriority collision threat coefficient reflects the possibility that other vehicles of the target vehicle and Current ambient collide;
Collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, is carried out to the target vehicle
Early warning.
Optionally, the acquisition history transport condition and the mapping relations of priori collision threat coefficient include:
Obtain the history transport condition and history collision result of several training vehicles;
Obtain travelling in the history with history collision result according to the history transport condition of several training vehicles
Priori collision threat coefficient under state, so that the mapping for obtaining the history transport condition and priori collision threat coefficient is closed
System.
Optionally, several described training vehicles include the first training vehicle and the second training vehicle;
The history transport condition is included under history running environment, the first training vehicle and the second training car
Relative velocity, relative distance and opposite travel direction between.
Optionally, the real time running state of the target vehicle is included under current driving environment, the target vehicle with
Relative velocity, relative distance and opposite travel direction between other vehicles of surrounding.
Optionally, the history running environment and the current driving environment include following at least one respectively:
Weather conditions, road shape and pavement behavior.
Optionally, the road shape includes:Straight line, turning or intersection.
Optionally, the history collision result includes following one of which:
Collision and do not eject air bag, collision and pop-up air bag, do not collide and carry out emergency braking, do not collide and
Do not collide by brake deceleration to 0 and and brake and be not decelerated to 0.
Optionally, the real time running state of the target vehicle includes real-time position information;
The posteriority collision threat coefficient of target vehicle described in the real time running state computation according to the target vehicle
Including:
According to the real time position of other vehicles around the real-time position information of the target vehicle and the target vehicle
Information, predicts the collision time of the target vehicle and other vehicles of surrounding;
The posteriority collision threat coefficient is obtained according to the collision time.
Optionally, it is described according to other vehicles around the real-time position information of the target vehicle and the target vehicle
Real-time position information, predict the target vehicle and it is described around the collision times of other vehicles include:
The position that the target vehicle according to the prediction of the real-time position information of the target vehicle in following predetermined time reaches
Put, and based on the safety zone of target vehicle described in the location determination reached in target vehicle described in the following predetermined time;
Around according to the real-time position information prediction of other vehicles around described in the following predetermined time other
The position that vehicle reaches, and based on surrounding described in the location determination that other vehicles reach around described in the following predetermined time
The safety zone of other vehicles;
If the safety zone of the target vehicle is overlapping with the safety zone of other vehicles of surrounding, by current time
It is determined as the collision time to the period between the following predetermined time.
Optionally, the real time running state of the target vehicle further includes:The velocity information of the target vehicle, yaw letter
Breath and current driving environmental information;
The target vehicle according to the prediction of the real-time position information of the target vehicle in following predetermined time reaches
Position include:
It is pre- according to the real-time position information of the target vehicle, velocity information, yaw information and current driving environmental information
Survey in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle,
The current driving environmental information includes ground friction coefficient;
It is described to be believed according to the real-time position information of the target vehicle, velocity information, yaw information and current driving environment
Breath prediction includes in the position that target vehicle described in following predetermined time reaches:
If target vehicle straight trip, according to the present speed, the current acceleration, the yaw angle and described
Ground friction coefficient, is predicted in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle and
Yaw rate, the current driving environmental information include ground friction coefficient;
It is described to be believed according to the real-time position information of the target vehicle, velocity information, yaw information and current driving environment
Breath prediction includes in the position that target vehicle described in following predetermined time reaches:
If the target vehicle is turned, according to the present speed, current acceleration, the yaw angle, described
Yaw rate and the ground friction coefficient, are predicted in the position that target vehicle described in following predetermined time reaches.
Second aspect, this application provides a kind of vehicle collision prewarning device, described device includes:
First acquisition unit, for obtaining the real time running state of target vehicle, and history transport condition is touched with priori
The mapping relations for threatening coefficient are hit, the priori collision threat coefficient reflects several training vehicles in the history transport condition
Under collision possibility;
Second acquisition unit, for the real time running state according to the target vehicle and the mapping relations, obtains institute
State the priori collision threat coefficient of target vehicle;
Computing unit, the posteriority for target vehicle described in the real time running state computation according to the target vehicle collide
Coefficient is threatened, the posteriority collision threat coefficient reflects the possibility that other vehicles of the target vehicle and Current ambient collide
Property;
Prewarning unit, threatens collision threat coefficient, to the mesh according to the priori collision threat coefficient and the posteriority
Mark vehicle and carry out early warning.
Optionally, the first acquisition unit includes:
First obtains subelement, and the history transport condition for obtaining several training vehicles is tied with history collision
Fruit;
Second obtains subelement, for the history transport condition according to several training vehicles and history collision result
The priori collision threat coefficient under the history transport condition is obtained, is collided so as to obtain the history transport condition with priori
Threaten the mapping relations of coefficient.
Optionally, several described training vehicles include the first training vehicle and the second training vehicle;
The history transport condition is included under history running environment, the first training vehicle and the second training car
Relative velocity, relative distance and opposite travel direction between.
Optionally, the real time running state of the target vehicle is included under current driving environment, the target vehicle with
Relative velocity, relative distance and opposite travel direction between other vehicles of surrounding.
Optionally, the history running environment and the current driving environment include following at least one respectively:
Weather conditions, road shape and pavement behavior.
Optionally, the road shape includes:Straight line, turning or intersection.
Optionally, the history collision result includes following one of which:
Collision and do not eject air bag, collision and pop-up air bag, do not collide and carry out emergency braking, do not collide and
Do not collide by brake deceleration to 0 and and brake and be not decelerated to 0.
Optionally, the real time running state of the target vehicle includes real-time position information;
The computing unit includes:
Predict subelement, for around the real-time position information according to the target vehicle and the target vehicle other
The real-time position information of vehicle, predicts the collision time of the target vehicle and other vehicles of surrounding;
3rd obtains subelement, for obtaining the posteriority collision threat coefficient according to the collision time.
Optionally, the prediction subelement includes:
First prediction module, described according to the prediction of the real-time position information of the target vehicle in following predetermined time
The position that target vehicle reaches;
First determining module, for based on first prediction module predict in target described in the following predetermined time
The safety zone of target vehicle described in the location determination that vehicle reaches;
Second prediction module, for the real-time position information prediction according to other vehicles of surrounding described following default
The position that other vehicles reach around described in moment;
Second determining module, for based on second prediction module predict around described in the following predetermined time
The safety zone of other vehicles around described in the location determination that other vehicles reach;
3rd determining module, if safety zone and the safety zone of other vehicles of surrounding for the target vehicle
It is overlapping, then current time to the period between the following predetermined time is determined as the collision time.
Optionally, the real time running state of the target vehicle further includes:The velocity information of the target vehicle, yaw letter
Breath and current driving environmental information;
First prediction module, specifically for the real-time position information according to the target vehicle, velocity information, yaw
Information and the prediction of current driving environmental information are in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle,
The current driving environmental information includes ground friction coefficient;
First prediction module includes:
First prediction submodule, if keeping straight on for the target vehicle, according to the present speed, described works as preacceleration
Degree, the yaw angle and the ground friction coefficient, are predicted in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle and
Yaw rate, the current driving environmental information include ground friction coefficient;
First prediction module includes:
Second prediction submodule, if turning for the target vehicle, according to the present speed, described works as preacceleration
Degree, the yaw angle, the yaw rate and the ground friction coefficient, are predicted in target vehicle described in following predetermined time
The position of arrival.
The third aspect, this application provides a kind of vehicle collision prewarning equipment, the equipment includes:
Processor and the memory having program stored therein;
Wherein when the processor performs described program, following operation is performed:
The real time running state of target vehicle is obtained, and history transport condition and the mapping of priori collision threat coefficient are closed
System, the priori collision threat coefficient reflect several collision possibilities of training vehicle under the history transport condition;
According to the real time running state of the target vehicle and the mapping relations, the priori for obtaining the target vehicle is touched
Hit threat coefficient;
It is described according to the posteriority collision threat coefficient of target vehicle described in the real time running state computation of the target vehicle
Posteriority collision threat coefficient reflects the possibility that other vehicles of the target vehicle and Current ambient collide;
Collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, is carried out to the target vehicle
Early warning.
The embodiment of the present application is by obtaining the real time running state of target vehicle, and history transport condition is collided with priori
The mapping relations of coefficient are threatened, then, according to the real time running state of the target vehicle and the mapping relations, obtain the target carriage
Priori collision threat coefficient, then, touched according to the posteriority of the real time running state computation of the target vehicle target vehicle
Hit threat coefficient, finally, collision threat coefficient threatened according to the priori collision threat coefficient and the posteriority, judge whether to need to
Target vehicle carries out early warning.As it can be seen that the application is not only with reference to the reflection target vehicle and surrounding obtained according to real time running state
The posteriority of other vehicle collision possibilities threatens collision threat coefficient, but also with reference to according to the identical or phase with real time running state
As the corresponding priori collision threat coefficient of history transport condition, since priori collision coefficient can reflect trained vehicle in history
The possibility collided under transport condition, so the combination of priori collision threat coefficient and posteriority collision threat coefficient can be more accurate
The true possibility for predicting other vehicle collisions of target vehicle Yu surrounding, so as to reduce the early warning fault rate to target vehicle.
Brief description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments described in application, for those of ordinary skill in the art, without creative efforts,
Other attached drawings can also be obtained according to these attached drawings.
Fig. 1 is a kind of configuration diagram for hardware scene that the application provides;
Fig. 2 is a kind of flow diagram for vehicle collision prewarning method that the application provides;
Fig. 3 is the schematic diagram that a kind of proof two lines section that the application provides intersects;
Fig. 4 is a kind of structure diagram for vehicle collision prewarning device that the application provides.
Embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction with the embodiment of the present application
Attached drawing, is clearly and completely described the technical solution in the embodiment of the present application, it is clear that described embodiment is only this
Apply for part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
All other embodiments obtained under the premise of creative work are not made, shall fall in the protection scope of this application.
With reference to concrete application scene, application scheme is introduced, for example, the scene of the embodiment of the present application
One of, it can be applied among hardware scene as shown in Figure 1, the hardware includes:Roadside unit (Road Side
Unit, abbreviation RSU) 101, board units (On board Unit, abbreviation OBU) 102, CAN bus module
(Controller Area Network, abbreviation CAN) 103 and GPS module (Global Positioning
System, abbreviation GPS) 104.
Roadside unit 101, can be used for the transport condition for obtaining vehicular traffic, such as, roadside unit 101 can utilize special
With short-range communication technology (Dedicated Short Range Communications, abbreviation DSRC) to the vehicle of vehicular traffic
Information is acquired, and can also be communicatively coupled with board units 102, is directly obtained the information of vehicles of vehicular traffic, its
In, which can include train safety information and vehicle running state.After the information of vehicles of vehicular traffic is got,
The roadside unit 101 can also utilize these information of vehicles to obtain the priori collision threat coefficient and posteriority collision prestige of vehicular traffic
Coefficient is coerced, and according to the priori collision threat coefficient and the posteriority collision threat coefficient, judges whether to need to board units 102
Alert.
CAN bus module 103, can be used for obtain vehicle train safety information, such as vehicle whether
Whether brake, start emergency braking or air bag, and the train safety information is sent to board units 102.
GPS module 104, can be used for collection vehicle transport condition, for example, the speed of vehicle, real time position,
Travel direction, and the vehicle running state is sent to board units 102.
Board units 102, can be used for the train safety information of 103 transmission of reception CAN bus module, GPS module 104 is sent out
The vehicle running state sent, and these information are sent to roadside unit 101;And receive the alarm that roadside unit 101 is sent
Information, and car alarming is carried out according to the warning message.
Wherein, it can be established and communicated to connect by DSRC technology between roadside unit 101 and board units 102.
It should be noted that in one implementation, the function of above-mentioned roadside unit 101 can also be by board units
102 realize.It is understood that above application scene is for only for ease of the principle for understanding the application and shows, do not have to
In restriction technical solution provided by the embodiments of the present application.
Next, it will be described with accompanying drawings vehicle collision prewarning method provided by the embodiments of the present application.
Referring to Fig. 2, which is a kind of flow diagram of vehicle collision prewarning method provided by the embodiments of the present application, the party
Method can be applied in roadside unit 101 or board units 102, and specifically, this method may include steps of:
S201:Obtain the real time running state of target vehicle, and history transport condition and priori collision threat coefficient
Mapping relations, the priori collision threat coefficient reflect that several collisions of training vehicle under the history transport condition may
Property.
S201 includes two sub-steps in the present embodiment, and one of sub-step is to obtain the real time running of target vehicle
State, another sub-step are to obtain the mapping relations of history transport condition and priori collision threat coefficient.Wherein, history row
The history transport condition of vehicles can be trained according to several and go through by sailing the mapping relations of state and priori collision threat coefficient
History collision result obtains, and what it reflected is priori collision possibility.And the real time running state of target vehicle is in current driving
The transport condition got under environment, the posteriority collision threat coefficient to collide for calculating target vehicle are that is, following to occur
The possibility of collision.By combining priori collision threat coefficient and posteriority collision threat coefficient, enable to target vehicle
The prediction for colliding possibility is more accurate.
Wherein, in the present embodiment, the real time running state of target vehicle can be included under current driving environment, the mesh
Mark relative velocity, relative distance and the opposite travel direction between vehicle and its Current ambient other vehicles.
Specifically, the relative velocity between the target vehicle and its Current ambient other vehicles can be the target vehicle with
Relative distance between speed of the vehicle of its Current ambient as object of reference, the target vehicle and its Current ambient other vehicles
Can be the line distance between the target vehicle and the vehicle of its Current ambient, the target vehicle and other cars of its Current ambient
Opposite travel direction between can be expressed as the course angle of other vehicles of the course angle of the target vehicle with its Current ambient
Between angle.
It is understood that history transport condition can be included under history running environment, between several training vehicles
Relative velocity, relative distance and opposite travel direction.Wherein, this several training vehicle can be at the same time and empty
Interior mutually adjacent training vehicle, for example this several training vehicles are within the same time, at same crossing.
Wherein, priori collision threat coefficient can be discrete indicator, and for assessing several training vehicles in history row
Sail the possibility to collide under state.The priori collision threat coefficient is bigger, then illustrates that this several training vehicle is gone through at this
The possibility to collide under history transport condition is bigger, conversely, then illustrating this several training vehicle in the history transport condition
Under the possibility that collides it is smaller.
Since priori collision threat coefficient can reflect that several collisions of training vehicle under the history transport condition can
Can property.Therefore, be obtain history transport condition and priori collision threat coefficient mapping relations, it is necessary to first obtain several training
Priori collision threat coefficient of the vehicle under the history transport condition.For obtaining history transport condition and priori collision threat system
The specific method of several mapping relations will subsequently describe in detail.
S202:According to the real time running state of the target vehicle and the mapping relations, the target vehicle is obtained
Priori collision threat coefficient.
, can be first true according to the real time running state of the target vehicle to obtain the priori collision threat coefficient of target vehicle
Make with the same or similar history transport condition of the real time running state, it is necessary to illustrate, the history transport condition institute is right
The history running environment answered can be identical with the current driving environment corresponding to the real time running state, such as history traveling shape
State can be collected with the real time running state at same crossing, alternatively, the history row corresponding to the history transport condition
Sailing environment can be similar to the current driving environment corresponding to the real time running state, for example the history transport condition is real-time with this
Transport condition can be collected respectively in the crossroad of two different locations.
Then, can be according to the history transport condition and the history transport condition pre-established and priori collision threat
The mapping relations of coefficient, obtain a priori collision threat coefficient, which can be as the target vehicle
Priori collision threat coefficient.It should be noted that obtaining the specific implementation of priori collision threat coefficient, will subsequently carry out
It is discussed in detail.
S203:According to the posteriority collision threat system of target vehicle described in the real time running state computation of the target vehicle
Number.
Wherein, posteriority collision threat coefficient can reflect target vehicle under real time running state with other cars of Current ambient
The possibility to collide.The posteriority collision threat coefficient is bigger, then illustrates the target vehicle and other cars of the Current ambient
The possibility to collide under real time running state is bigger, conversely, then illustrate the target vehicle and the Current ambient other
The possibility that vehicle collides under real time running state is smaller.
First, after getting the real time running state of target vehicle by performing S201, that is, get in current driving
Under environment, relative velocity, relative distance and opposite travel direction between the target vehicle and its Current ambient other vehicles can
According to the relative velocity between the target vehicle and its Current ambient other vehicles, relative distance and opposite travel direction, to obtain
To the collision time of other vehicles of the target vehicle and its Current ambient.
Wherein, the collision time of other vehicles of target vehicle and its Current ambient can be current time to future it is default when
Period between quarter, at the time of which collides for the target vehicle with its Current ambient other vehicles.
The collision time is shorter, then illustrates that the target vehicle and the possibility that its Current ambient other vehicles collide are bigger, conversely,
Then illustrate that the target vehicle and the possibility that its Current ambient other vehicles collide are smaller.
Specifically predict the mode of the collision time, will subsequently describe in detail.
Secondly, it is predicted that target vehicle and around it after collision time of other vehicles, can obtain according to the collision time
To the posteriority collision threat coefficient of the target vehicle.
Specifically, if the collision time is greater than or equal to a predetermined threshold value, it may be considered that target vehicle and surrounding other
The possibility very little that vehicle collides, at this time, the posteriority collision threat coefficient D of the target vehicle can be 0.
If the collision time is less than the predetermined threshold value, it may be considered that what target vehicle collided with other surrounding vehicles
Possibility is higher, can utilize the posteriority collision threat coefficient of the Collision time calculation target vehicle at this time.For example, it can use
Equation below calculates the posteriority collision threat coefficient of target vehicle:
D=1/lgt, wherein, D represents posteriority collision threat coefficient, and t represents target vehicle and other vehicles of its Current ambient
Collision time.
As an example it is assumed that relative velocity between target vehicle and a vehicle of its Current ambient be 20m/s, it is opposite away from
From being 0 degree for 100m and opposite travel direction, and predetermined threshold value is 10s.Can be with according to the real time running state of the target vehicle
The collision time t that the target vehicle and the vehicle is calculated is 5s, since collision time t is less than predetermined threshold value 10s,
The posteriority collision threat coefficient D that target vehicle collides with the surrounding vehicle is 1.42 (1/lg5).
It should be noted that the predetermined threshold value can be obtained according to history transport condition, the tool of predetermined threshold value is obtained
Body implementation, will subsequently describe in detail.In a kind of possible embodiment, when predicting target vehicle and its week
When enclosing the collision times of other vehicles and being more than predetermined threshold value, due to can consider that other vehicles of the target vehicle and surrounding touch
The possibility hit is minimum, therefore, it may not be necessary to according to after the real time running state computation of the target vehicle target vehicle
Collision threat coefficient is tested, so as to reduce the calculation amount in whole prealarming process.
S204:According to the priori collision threat coefficient and the posteriority collision threat coefficient, to the target vehicle into
Row early warning.
, can since target vehicle can not represent in real time running state sometime the traveling trend of the target vehicle
The collision time that is obtained according to the real time running state of target vehicle can be caused too small, if only relying on collision time to judge
The possibility that vehicle collides may there are error.
And in the present embodiment, after not colliding possibility only with reference to the reflection target vehicle obtained according to real time running state
Collision threat coefficient is tested, but also with reference to according to priori corresponding with the same or similar history transport condition of real time running state
Collision coefficient, obtains since priori collision coefficient collides result according to history, so priori collision threat coefficient and posteriority
The combination of collision threat coefficient can more accurately predict the possibility of other vehicle collisions of target vehicle Yu surrounding, so as to drop
The low early warning fault rate to target vehicle.
In a kind of embodiment of the embodiment of the present application, it can be collided according to the priori collision threat coefficient and the posteriority
Coefficient is threatened to obtain a synthetic threat collision probability, such as, which can utilize priori collision prestige
Side of body coefficient and the posteriority collision threat coefficient are calculated based on Bayes' theorem, specifically, can be used and are based on Bayes as follows
The formula of theorem calculates the synthetic threat collision probability of target vehicle:
Wherein, X represents synthetic threat collision probability, and D represents posteriority collision threat system
Number, P represent priori collision threat coefficient, and * represents dot product.
The synthetic threat collision probability X obtained according to above-mentioned formula is bigger, then illustrates the probability that target vehicle collides
It is bigger, conversely, then illustrating that the probability that target vehicle collides is smaller.If synthetic threat collision probability is less than first threshold,
It may be considered that the target vehicle collision threat is smaller, it is not necessary to carries out early warning to the target vehicle;If more than first threshold and
Less than or equal to second threshold, it may be considered that the target vehicle is threatened with slight degree of crash, and carried out gently to the target vehicle
Spend early warning;If more than second threshold and it is less than or equal to the 3rd threshold value, it may be considered that the target vehicle has moderate collision prestige
The side of body, and carry out moderate early warning to the target vehicle;If more than the 3rd threshold value, it may be considered that the target vehicle is collided with severe
Threaten, and severe early warning is carried out to the target vehicle.Wherein, first threshold, second threshold and the 3rd threshold value can be user's roots
It is pre-set according to historical experience, for example first threshold can be 0.3, second threshold can be 0.5, and the 3rd threshold value can be
0.7。
In the embodiment of the present application, in order to obtain the mapping relations of history transport condition and priori collision threat coefficient,
The step of mapping relations of history transport condition and priori collision threat coefficient " obtain " in S201, can specifically include following
Step:
Step A:Obtain the history transport condition and history collision result of several training vehicles.
In the present embodiment, history transport condition and the history collision result of several training vehicles can be led to using DSRC
Letter technology is acquired vehicular traffic obtained or is directly obtained from associated mechanisms, can also be in mould
Intend what is collected in vehicle collision experiment.The acquisition modes of history transport condition and history collision result are not carried out herein
Limit.
It should be noted that if can include two trained vehicles in dry training vehicle, the two training vehicles are in phase
It is mutually adjacent in same time and space.For ease of description, the two training vehicles can be referred to as the first training vehicle
With second training vehicle, such as, at a time in, may be respectively referred to as the first training with two trained cars at a crossing
Vehicle and the second training vehicle.
History transport condition can be included under history running environment, between the first training vehicle and the second training vehicle
Relative velocity, relative distance and opposite travel direction.
It is understood that the relative velocity between the first training vehicle and the second training vehicle can be first training
Speed of the vehicle using the second training vehicle as object of reference, it is opposite between the first training vehicle and the second training vehicle
Distance can be this first training vehicle and this second training vehicle between line distance, this first training vehicle and this second
Opposite travel direction between training vehicle can be by the course angle of the first training vehicle and the course of the second training vehicle
Angle between angle represents.
And the history collision result of each training vehicle can be the collision of the training vehicle under history transport condition
As a result, history collision result can include following one of which:Collision and do not eject air bag, collision and pop-up substitute
Capsule, do not collide and carry out emergency braking, do not collide and do not collide by brake deceleration to 0 and and brake and be not decelerated to 0.
Step B:Obtain going through described with history collision result according to the history transport condition of several training vehicles
Priori collision threat coefficient under history transport condition, so as to obtain reflecting for the history transport condition and priori collision threat coefficient
Penetrate relation.
Since training vehicle is during traveling, the history transport condition of training vehicle can change, for that can obtain
To the corresponding priori collision threat coefficient of more accurately history transport condition, it is necessary to obtain the history transport condition in different situations
Under priori collision threat coefficient, therefore, history transport condition can be divided into a variety of situations.
By mentioned in step A first training vehicle and second training vehicle exemplified by, can by first training vehicle and
Second training vehicle between relative velocity be divided into multiple situations, be specifically as follows section A (0,20m/s], interval B (20m/
S, 25m/s], section C (25m/s, 28m/s], and section D (28m/s, 30m/s], section E (30m/s, ∞);Vehicle is trained by first
And second training vehicle between relative distance be divided into multiple situations, be specifically as follows section a (0,40m], section b (40m,
60m], section c (60m, 80m], and section d (80m, 100m], section e (100m, ∞);By the first training vehicle and the second training car
Opposite travel direction between is divided into multiple situations, the angle of travel direction be specifically as follows section 1 (0,30 °], section 2
(30 °, 60 °], section 3 (60 °, 90 °], section 4 (90 °, 180 °].
Due to each training vehicle correspond under the different situations of history transport condition same history collide as a result,
Therefore, several training vehicles history collision result corresponding under the different situations of history transport condition can first be obtained.
If it should be noted that result is collided by analysis of history it is known that the collision result of a training vehicle is to touch
Hit and do not eject air bag, then the corresponding priori collision threat coefficient of the collision result is 1;If the collision knot of a training vehicle
Fruit is collision and pop-up air bag, then the corresponding priori collision threat coefficient of the collision result is 1;If a training vehicle touches
Result is hit not collide and carrying out emergency braking, then the corresponding priori collision threat coefficient of the collision result is 0.9;An if training
The collision result of vehicle is does not collide and by brake deceleration to 0, then the corresponding priori collision threat coefficient of the collision result is
0.5;If the collision result of a training vehicle is not decelerated to 0 not collide and braking, the corresponding priori collision of the collision result
It is 0 to threaten coefficient.
So can be by the elder generation corresponding to history collision result of the training vehicle under the different situations of history transport condition
Test the training set sample of collision threat coefficient as history transport condition in varied situations.That is, history transport condition
Training set sample standard deviation in varied situations includes the priori collision threat coefficient corresponding to several history collision result.
Continue by taking the above-mentioned first training vehicle and the second training vehicle as an example, it is assumed that history transport condition is included in history
Under running environment, the relative velocity between the first training vehicle and the second training vehicle is 23m/s, relative distance 50m
It is 20 ° with opposite travel direction, and collides result not collide and corresponding by brake deceleration to 0, i.e. the collision result
Priori collision threat coefficient is 0.5, and when the speed of first, second training vehicle is 0, which is 10m.
Since during training vehicle deceleration, which can be progressively smaller until that for 0, which also can
It is gradually reduced as 10m, and opposite travel direction is constant.Therefore, can be using the 0.5 of the priori collision threat coefficient as when first
Training vehicle and second training vehicle relative velocity be respectively section A (0,20m/s], interval B (20m/s, 25m/s] when training
Sample data, can also be used as when relative distance be respectively section a (0,40m], section b (40m, 60m] when number of training
According to, be also used as when opposite travel direction for section 1 (0,30 °] when training sample data.
, can be according to number of training after the training sample data of history transport condition in varied situations are collected
The priori collision threat coefficient corresponding to several history collision result in, obtains history transport condition in varied situations
Priori collision threat coefficient, for example, can utilize as follows based on Bayesian formula calculate history transport condition not
The corresponding priori collision threat coefficient with the case of:
Wherein, YjRepresent jth kind history transport condition, xiRepresent jth kind history transport condition
I-th of training sample data, I represents the number of the training sample data of jth kind history transport condition, P (X | Yj) represent jth
The corresponding priori collision threat coefficient of kind history transport condition.
History transport condition is being obtained in varied situations after corresponding priori collision threat coefficient, can be according to going through
The history transport condition priori that corresponding priori collision threat coefficient is obtained corresponding to history transport condition in varied situations is touched
Threat coefficient is hit, that is, obtains the mapping relations of the history transport condition and the priori collision threat coefficient.For example, due to history row
It is mutually independent to sail between the different situations of state, therefore, can utilize that calculated as follows based on Bayesian formula should
Priori collision threat coefficient corresponding to history transport condition:
P(X|Y1,Y2,…,Yj)=P (X | Y1)P(X|Y2)…P(X|Yj), wherein, P (X | Y1,Y2,…,Yi) represent this and go through
Priori collision threat coefficient corresponding to history transport condition, YjRepresent the jth kind situation of history transport condition, and P (X | Yj) represent
The priori collision threat coefficient of j kind situations, j represent the different situations number of history transport condition.
, can be according to history after mapping relations of the history transport condition with the priori collision threat coefficient are obtained
Transport condition and its mapping relations between priori collision threat coefficient, obtain priori collision threat coefficient.Next, will
How specific introduce according to history transport condition obtains priori collision threat coefficient.
Since the history transport condition of each trained vehicle corresponds to same history collision result and history collision
As a result corresponding priori collision threat coefficient.Therefore, get a training vehicle history transport condition i.e. relative velocity,
After relative distance and opposite travel direction, can first it be determined according to the relative velocity, the relative distance and the opposite travel direction
Go out each corresponding section, and determine that history of the training vehicle under the history transport condition collides knot according to the section
Priori collision threat coefficient corresponding to fruit and history collision result.
Continue by taking the above-mentioned first training vehicle and the second training vehicle as an example, due to having been set up the first training vehicle pair
The mapping relations of the history transport condition answered and priori collision threat coefficient.Therefore, when get this first training with other instruction
The history transport condition of practice be relative velocity be 15m/s, relative distance 20m, opposite travel direction be when being 15 °, can be with
Determine the corresponding sections of relative velocity 15m/s be section A (0,20m/s], the corresponding sections of relative distance 20m be section
A (0,40m], this with respect to 15 ° of corresponding sections of travel direction for section 1 (0,30 °];Then, can be according to section A (0,20m/
S], section a (0,40m] and section 1 (0,30 °] determine corresponding history collision result and history collision result
Corresponding priori collision threat coefficient, history collision result and the priori collision threat coefficient are the first training car
And other training vehicles relative velocity be 15m/s, relative distance 20m, opposite travel direction be 30 ° when history collision
As a result.
Next, will introduce how predetermined threshold value obtained according to history transport condition.
Since the history transport condition of training vehicle can be divided into a variety of situations, and each case is also one corresponding
Collision time, and each case also corresponds to a priori collision threat coefficient.Therefore, each collision time also corresponds to one
Prior threat collision coefficient.
In the present embodiment, the collision time of vehicle can be divided into a variety of situations, such as section one can be divided into
(0,2s], section two (2s, 5s], section three (5m/s, 8s], and section four (8s, 10s], section five (10s, ∞).Touched due to each
Hit a time corresponding prior threat collision coefficient, therefore, the priori collision threat system corresponding to each collision time section
Number can be the average value of the corresponding priori collision threat coefficient of each collision time in the section.
When priori collision threat coefficient is 0, it may be considered that the possibility that vehicle collides is minimum, so, can be with
In the collision time section that all priori collision threat coefficients are 0, a collision time is determined, and the collision time is made
For time shortest collision time in predetermined threshold value, such as the collision time section.
Since the difference of history running environment also influences whether collision possibility of the vehicle under history transport condition.Such as
When history running environment includes weather conditions, if weather conditions are fine, the visual sight of driver is preferable, can quickly sentence
Disconnected vehicle front situation, so that driver can judge whether that needs brake in advance;If weather conditions for rain, snow,
During haze, then the visual visual line of sight of driver is smaller, it is difficult to judge vehicle front situation, driver can not judge whether in advance
Need to brake, so as to increase the possibility that vehicle collides.
In another example when history running environment includes road shape, if road shape is straight line, driver compares appearance
Easily observation vehicle front situation, so that driver can judge whether that needs brake in advance;If road shape for turn or
During intersection, then driver can not observe vehicle front situation in advance, cause driver can not judge whether that needs are stopped in advance
Car, so as to increase the possibility that vehicle collides.
For another example when history running environment includes pavement behavior, due to different surface conditions (such as hill path, paint
Road, moist road surface) friction coefficient be all different, can cause vehicle under different surface conditions by brake deceleration extremely
0 duration is all different, so as to be impacted to the possibility that vehicle collides.
Therefore, for collision threat coefficient that is more accurate, tallying with the actual situation can be obtained, implement in one kind of the application
In mode, it can be obtained according to the history transport condition of several training vehicles, history collision result and history running environment
Collision threat coefficient under the history transport condition.
Specifically, the priori collision threat coefficient of history transport condition in varied situations, and various history are being obtained
, can be according to the priori collision threat of history transport condition in varied situations after the priori collision threat coefficient of running environment
Coefficient, and the priori collision threat coefficient of various history running environments obtain the priori collision corresponding to the history transport condition
Coefficient is threatened, that is, obtains the mapping relations of the history transport condition and the priori collision threat coefficient.For example, due to given
It is mutually independent in the case of history running environment, between the different situations of the history transport condition, therefore, can utilizes such as
Under priori collision threat coefficient corresponding to the history transport condition is calculated based on Bayesian formula:
P(X|Z1,…,Zm,Y1,Y2,…,Yj)=P (X | Z1,…,Zm,Y1)P(X|Z1,…,Zm,Y2)…P(X|Z1,…,
Zm,Yj), wherein, P (X | Z1,…,Zm,Y1,Y2,…,Yj) represent priori collision threat system corresponding to the history transport condition
Number, YjRepresent the jth kind situation of history transport condition, ZmRepresent m kind history running environments, and P (X | Z1,…,Zm,Yj) represent
Given Z1,…ZmUnder the conditions of history transport condition jth kind situation priori collision threat coefficient, j represents history transport condition
Different situations number, m represents the number of various history running environment situations.
Next, the acquisition modes of posteriority collision threat coefficient will be specifically introduced.The one of the embodiment of the present application
, can be by predicting target vehicle and collision time of other vehicles obtains the target vehicle around it in kind of embodiment
Posteriority collision threat coefficient, wherein, the real time running state of the target vehicle can include the real time position letter of the target vehicle
Breath, correspondingly, " prestige is collided in S203 according to the posteriority of target vehicle described in the real time running state computation of the target vehicle
The step of side of body coefficient ", specifically may comprise steps of:
Step a:According to the reality of other vehicles around the real-time position information of the target vehicle and the target vehicle
When positional information, predict the target vehicle and it is described around other vehicles collision time;
Step b:The posteriority collision threat coefficient is obtained according to the collision time.
The wherein concrete implementation mode of step b is identical with the implementation in S203, refers to the phase in above-mentioned S203
Close and introduce, which is not described herein again.
The implementation of step a is specifically introduced below.
In the present embodiment, the collision times of other vehicles of target vehicle and surrounding can be understood as current time to following pre-
If the period between the moment, which is the reality of other vehicles of the real-time position information Yu surrounding of the target vehicle
When positional information at the time of overlap.
Wherein, real-time position information can be the latitude and longitude information of vehicle, for example the real-time position information of target vehicle can
Think (lat1, lon1), wherein, lat1 is the longitude of target vehicle, and lon1 is the latitude of target vehicle.
Since the latitude and longitude information of the latitude and longitude information Yu surrounding of target vehicle other vehicles can reflect the target vehicle
With the position relationship of surrounding other vehicles.Therefore, can be by judging the latitude and longitude information of the target vehicle and other cars of surrounding
Latitude and longitude information whether overlap.If so, it may be considered that other vehicles of the target vehicle and surrounding are collided,
And as following predetermined time at the time of colliding, so as to predict touching for the target vehicle and other vehicles of surrounding
Hit the time;If it is not, it may be considered that other vehicles of the target vehicle and surrounding do not collide.
But the real-time position information of vehicle is a coordinate information, it can not reflect the reality of the vehicle exactly
Size, such as when two vehicles have occurred that collision, but the real-time position information of two vehicles does not overlap.
, can in order to predict the following predetermined time that the target vehicle and surrounding other vehicles collide exactly
With the real-time position information of other vehicles of the real-time position information based on target vehicle Yu surrounding, be target vehicle and surrounding other
Vehicle pre-sets a safety zone.Wherein, which can be the region for including vehicle real-time position information, than
Such as, can be using the coordinate information of target vehicle as midpoint, one length of setting is 5 meters, the safety zone that width is 2 meters.In this way, can
With the following predetermined time to be overlapped by predicting the safety zone of other vehicles of the safety zone Yu surrounding of target vehicle, from
And determine the collision time of other vehicles of the target vehicle Yu surrounding.
So in a kind of implementation of the present embodiment, above-mentioned steps a may comprise steps of:
Step a1:According to the prediction of the real-time position information of the target vehicle in the target vehicle arrival of following predetermined time
Position, and based on the place of safety of target vehicle described in the location determination reached in target vehicle described in the following predetermined time
Domain;
Step a2:According to the real-time position information prediction of other vehicles around this same following predetermined time around this its
The position that his vehicle reaches, and based on surrounding described in the location determination that other vehicles reach around described in the future predetermined time
The safety zone of other vehicles;
Step a3:If the safety zone of the target vehicle is overlapping with the safety zone of other vehicles around this, can incite somebody to action
Current time is determined as the target vehicle and around this during the collision of other vehicles to the period between the future predetermined time
Between.
Due to predicting in the method for the position that following predetermined time target vehicle reaches and prediction in following predetermined time week
The method for enclosing the position of other vehicles arrival is identical, i.e. step a1 is identical with the specific implementation of step a2.Therefore, next
By by taking the target vehicle in step a1 as an example, method of the prediction in the position of following predetermined time target vehicle arrival is carried out
It is specific to introduce, and step a2 may refer to the related introduction of step a1, repeat no more herein.
In the present embodiment, the real time running state of target vehicle can also include:Target vehicle velocity information (such as
The present speed of target vehicle, current acceleration), yaw information (such as the course angle of target vehicle, yaw rate) and work as
Preceding traveling environmental information (such as weather conditions, road shape, pavement behavior, ground friction coefficient).
First, after the real-time position information of target vehicle is got, since real-time position information is the warp of target vehicle
The latitude and longitude information, for the ease of calculating, can be converted to the coordinate information easy to calculate, for example can be flat by latitude information
The coordinate value of face rectangular coordinate system.
Specifically, can be using the site of road around target vehicle as the origin of plane right-angle coordinate, such as can
Be the midpoint of intersection, target vehicle and surrounding other vehicles centre position etc..Then, according to the warp of the target vehicle
The position relationship of latitude information (lat1, lon1) and the latitude and longitude information (lat2, lon2) of the site of road, can obtain the mesh
Vehicle is marked using the site of road as the coordinate value (x in the plane right-angle coordinate of origin1, y1), and by the target vehicle
Course angle θ is converted to the coordinate value (x1, y1) with the plane right-angle coordinate in X-axis positive axis angle thetax。
Since the target vehicle is in different motion states, for example, straight trip, turning, the real time position letter of the target vehicle
The variation tendency of breath is different, i.e., coordinate value variation tendency of the target vehicle in the plane right-angle coordinate is different
's.Therefore, predicting the target vehicle before the position that following predetermined time is reached, it is necessary to first judge the target vehicle
Motion state.
In a kind of implementation of the present embodiment, the target vehicle can be determined according to the radius of curvature of the target vehicle
Motion state, such as the radius of curvature that equation below calculates the target vehicle can be first passed through:
R=(V/ γ)
Wherein, r represents the current radius of curvature of the target vehicle, and V represents the present speed of the target vehicle, and γ is represented should
The yaw rate of target vehicle.
It should be noted that when the target vehicle motion state for straight trip when, it is believed that the target vehicle around
The earth to be moved.Since the height above sea level of each position of earth surface is different,, should when target vehicle is kept straight on
The radius of curvature of target vehicle should be greater than or equal to the radius of curvature (r of the earthGround=32767), the i.e. curvature of the target vehicle
Radius should be greater than or equal to 32767.
When the motion state of the target vehicle is turns, it is believed that the target vehicle is around some ground location
Turn.Since the center of circle that the target vehicle is surrounded is the ground location, distance of the target vehicle apart from the center of circle
Earth radius can be less than.So the target vehicle, when turning, the radius of curvature of the target vehicle should be less than the curvature of the earth
The radius of curvature of radius, the i.e. target vehicle should be less than 32767.
Secondly, can be according to the real time running state of the target vehicle after the motion state of the target vehicle is determined
Predict the target vehicle in the position that following predetermined time is reached and safety zone.
Specifically, can be according to the real-time position information of the target vehicle, current when the target vehicle is in straight-line travelling
Speed, current acceleration, yaw angle and ground friction coefficient, are predicted in following predetermined time, the position which is reached
Put.
The target vehicle first can be determined according to the present speed of the target vehicle, current acceleration and ground friction coefficient
In the displacement of following predetermined time, for example, can be calculated with equation below:
S=v*t+0.5* (a-fg) * t2
Wherein, t represents following predetermined time;Displacement of the behalf target vehicle in following predetermined time t;V is represented should
The present speed of target vehicle;A represents the current acceleration of the target vehicle;G represents acceleration of gravity;F represents present road
Friction coefficient, it can be obtained according to current driving environmental information such as weather conditions, road shape, pavement behavior.
It should be noted that since different weather conditions can cause the humidity condition on road surface different, weather conditions
It can be embodied by pavement humidity situation, for example, when weather conditions are the rainy day, then the humidity condition on road surface can be humidity, when
When weather conditions are fine day, then the humidity condition on road surface can be drying;And pavement behavior can usually include surface conditions, road
Face usage time, specifically, surface conditions can be the material on road surface, such as pitch, sandstone or concrete, and normal conditions
Under, the pavement usage time is longer, then road friction coefficient is lower.Wherein, road friction coefficient and surface conditions, pavement humidity feelings
Correspondence between condition and pavement usage time can be obtained from table 1.
Table 1
Surface conditions | Dry or is moist | The pavement usage time | Road friction coefficient |
Pitch | It is dry | New road | 0.85 |
Pitch | It is dry | 1 year to 3 years | 0.75 |
Pitch | It is dry | More than 3 years | 0.70 |
Pitch | It is moist | New road | 0.80 |
Pitch | It is moist | 1 year to 3 years | 0.65 |
Pitch | It is moist | More than 3 years | 0.60 |
Concrete | It is dry | New road | 0.90 |
Concrete | It is dry | 1 year to 3 years | 0.78 |
Concrete | It is dry | More than 3 years | 0.70 |
Concrete | It is moist | New road | 0.78 |
Concrete | It is moist | 1 year to 3 years | 0.70 |
Concrete | It is moist | More than 3 years | 0.62 |
Sandstone | It is dry | Less than 10 years | 0.68 |
, can be according to the displacement and the reality of the target vehicle in the definite target vehicle after the displacement of following predetermined time
When positional information determine the target vehicle in the position of the future predetermined time, for example, the target can be calculated with equation below
Vehicle is in the position of the future predetermined time:
(xt,yt)=(x1-s*cosθx,y1-s*sinθx)
Wherein, t represents following predetermined time;Displacement of the behalf target vehicle in following predetermined time t;xtRepresent
Abscissa value of the target vehicle in future predetermined time t;ytThe target vehicle is represented in future predetermined time t
Ordinate value;x1Represent abscissa value of the target vehicle at current time;y1Represent vertical seat of the target vehicle at current time
Scale value;θxRepresent the coordinate value (xt,yt) with the plane right-angle coordinate in X-axis positive axis angle.
Then, the target vehicle can be obtained in the future according to the target vehicle in the position of the future predetermined time
The safety zone of predetermined time, for example, the safety zone can be the region surrounded by following four coordinate value:
(xt+A/2,yt+ B/2), (xt+A/2,yt- B/2), (xt-A/2,yt+ B/2), (xt-A/2,yt-B/2)
Wherein, t represents following predetermined time;xtRepresent abscissa value of the target vehicle in future predetermined time t;
ytRepresent ordinate value of the target vehicle in future predetermined time t;A represents the width of default safety zone;B is represented
The length of default safety zone.
When the target vehicle is in turning driving, can according to the real-time position information of the target vehicle, present speed, when
Preacceleration, yaw angle, yaw rate and ground friction coefficient, predict that, in following predetermined time, which is reached
Position.
The target vehicle first can be determined according to the present speed of the target vehicle, current acceleration and ground friction coefficient
In the displacement of following predetermined time, and projection of the displacement in X, Y direction, for example, can be calculated with following 4 formula
Displacement and its projection X, Y direction in of the target vehicle in following predetermined time:
S=v*t+0.5* (a-fg) * t2, arc_angle=s/r,
Arc_liner_x=r*sin (arc_angle), arc_liner_y=r*cos (arc_angle)
Wherein, t represents following predetermined time;Displacement of the behalf target vehicle in following predetermined time t;V is represented should
The present speed of target vehicle;A represents the current acceleration of the target vehicle;G represents acceleration of gravity;F represents Current terrestrial
Friction coefficient, its can foundation and current driving environmental information such as weather conditions, road shape, pavement behavior from table 1
Arrive;R represents the current radius of curvature of the target vehicle;Arc_angle represents rotation of the target vehicle in following predetermined time t
Gyration;Arc_liner_x represents the projections of displacement s in the X-axis direction;Arc_liner_y represents displacement s in Y-axis side
Upward projection.
After projection of displacement and the displacement of the target vehicle in following predetermined time in X, Y direction is determined,
The target can be determined according to the displacement, the projection in X, Y direction of real-time position information and the displacement of the target vehicle
Vehicle is in the position of the future predetermined time, for example, the target vehicle can be calculated with equation below in the future predetermined time
Position:
xt=x1+(arc_liner_x*cos(θx)-y1*sin(θx)),
yt=y1+(arc_liner_x*sin(θx)+arc_liner_y*cos(θx))
Wherein, t represents following predetermined time;xtRepresent abscissa value of the target vehicle in future predetermined time t;
ytRepresent ordinate value of the target vehicle in future predetermined time t;x1Represent horizontal seat of the target vehicle at current time
Scale value;y1Represent ordinate value of the target vehicle at current time;θxRepresent the coordinate value (xt,yt) sat with the flat square
The angle of X-axis positive axis in mark system;Arc_liner_x represents the projections of displacement s in the X-axis direction;Arc_liner_y generations
The projections of table displacement s in the Y-axis direction.
Then, the target vehicle can be obtained in the future according to the target vehicle in the position of the future predetermined time
The safety zone of predetermined time, for example, the safety zone can be by following four coordinate value area defined:
(xt+A/2,yt+ B/2), (xt+A/2,yt- B/2), (xt-A/2,yt+ B/2), (xt-A/2,yt-B/2)
Wherein, t represents following predetermined time;xtRepresent abscissa value of the target vehicle in future predetermined time t;
ytRepresent ordinate value of the target vehicle in future predetermined time t;A represents the width of default safety zone;B is represented
The length of default safety zone.
The implementation of step a3 is specifically introduced below.
By performing step a1, a2, it can obtain in following predetermined time, the position and place of safety that target vehicle reaches
Domain, and the position of surrounding other vehicles arrival and home.
Since the safety zone of target vehicle with surrounding other vehicles is surrounded by four line segments, if the peace of the target vehicle
Any one line segment in region-wide, has with any one line segment in the safety zone of other vehicles around this and intersects, then can recognize
For the following predetermined time corresponding to the safety zone be the target vehicle and around this other vehicles collision moment.This
When, current time to the period between the future predetermined time can be determined as the target vehicle and other vehicles around this
Collision time.
Illustrate how to judge that two lines section intersects below in conjunction with Fig. 3.
As shown in figure 3, by taking line segment A, B as an example, the two-end-point of line segment A respectively distinguish by point P1, the two-end-point of point P2, line segment B
For point P3, point P4.
It is possible, firstly, to point P3 is carried out line with point P1, point P2 respectively forms line segment C, D, wherein, the vector v 1 of line segment C
Direction be by P3 to P1, the direction of the vector v 2 of line segment D is that the direction of the vector v 3 of line segment B is by P3 to P4 by P3 to P2.
It is then possible to judge whether line segment A, B intersect according to vector v 1, v2, v3, for example, equation below can be passed through
To judge whether A, B intersect:
Z=(v1 × v3) * (v2 × v3)
Wherein, if Z is less than or equal to 0, illustrate that line segment A, B intersect, conversely, then illustrating that line segment A, B be not intersecting.
A kind of vehicle collision prewarning method provided based on above example, the embodiment of the present application additionally provide a kind of vehicle
Collision warning device, describes its operation principle in detail below in conjunction with the accompanying drawings.
Referring to Fig. 4, which is a kind of structure diagram of vehicle collision prewarning device provided by the embodiments of the present application.
A kind of vehicle collision prewarning device device provided in this embodiment can include:
First acquisition unit 401, for obtaining the real time running state of target vehicle, and history transport condition and priori
The mapping relations of collision threat coefficient, the priori collision threat coefficient reflect that several training vehicles travel shape in the history
Collision possibility under state;
Second acquisition unit 402, for the real time running state according to the target vehicle and the mapping relations, obtains
The priori collision threat coefficient of the target vehicle;
Computing unit 403, the posteriority for target vehicle described in the real time running state computation according to the target vehicle
Collision threat coefficient, the posteriority collision threat coefficient reflect what other vehicles of the target vehicle and Current ambient collided
Possibility;
Prewarning unit 404, collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, to described
Target vehicle carries out early warning.
Optionally, the first acquisition unit 401 includes:
First obtains subelement, and the history transport condition for obtaining several training vehicles is tied with history collision
Fruit;
Second obtains subelement, for the history transport condition according to several training vehicles and history collision result
The priori collision threat coefficient under the history transport condition is obtained, is collided so as to obtain the history transport condition with priori
Threaten the mapping relations of coefficient.
Optionally, several described training vehicles include the first training vehicle and the second training vehicle;
The history transport condition is included under history running environment, the first training vehicle and the second training car
Relative velocity, relative distance and opposite travel direction between.
Optionally, the real time running state of the target vehicle is included under current driving environment, the target vehicle with
Relative velocity, relative distance and opposite travel direction between other vehicles of surrounding.
Optionally, the history running environment and the current driving environment include following at least one respectively:
Weather conditions, road shape and pavement behavior.
Optionally, the road shape includes:Straight line, turning or intersection.
Optionally, the history collision result includes following one of which:
Collision and do not eject air bag, collision and pop-up air bag, do not collide and carry out emergency braking, do not collide and
Do not collide by brake deceleration to 0 and and brake and be not decelerated to 0.
Optionally, the real time running state of the target vehicle includes real-time position information;
The computing unit 403 includes:
Predict subelement, for around the real-time position information according to the target vehicle and the target vehicle other
The real-time position information of vehicle, predicts the collision time of the target vehicle and other vehicles of surrounding;
3rd obtains subelement, for obtaining the posteriority collision threat coefficient according to the collision time.
Optionally, the prediction subelement includes:
First prediction module, described according to the prediction of the real-time position information of the target vehicle in following predetermined time
The position that target vehicle reaches;
First determining module, for based on first prediction module predict in target described in the following predetermined time
The safety zone of target vehicle described in the location determination that vehicle reaches;
Second prediction module, for the real-time position information prediction according to other vehicles of surrounding described following default
The position that other vehicles reach around described in moment;
Second determining module, for based on second prediction module predict around described in the following predetermined time
The safety zone of other vehicles around described in the location determination that other vehicles reach;
3rd determining module, if safety zone and the safety zone of other vehicles of surrounding for the target vehicle
It is overlapping, then current time to the period between the following predetermined time is determined as the collision time.
Optionally, the real time running state of the target vehicle further includes:The velocity information of the target vehicle, yaw letter
Breath and current driving environmental information;
First prediction module, specifically for the real-time position information according to the target vehicle, velocity information, yaw
Information and the prediction of current driving environmental information are in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle,
The current driving environmental information includes ground friction coefficient;
First prediction module includes:
First prediction submodule, if keeping straight on for the target vehicle, according to the present speed, described works as preacceleration
Degree, the yaw angle and the ground friction coefficient, are predicted in the position that target vehicle described in following predetermined time reaches.
Optionally, the velocity information includes:Present speed and current acceleration, the yaw information include yaw angle and
Yaw rate, the current driving environmental information include ground friction coefficient;
First prediction module includes:
Second prediction submodule, if turning for the target vehicle, according to the present speed, described works as preacceleration
Degree, the yaw angle, the yaw rate and the ground friction coefficient, are predicted in target vehicle described in following predetermined time
The position of arrival.
A kind of vehicle collision prewarning method and device provided based on above example, the embodiment of the present application additionally provide one
Kind vehicle collision prewarning equipment, the equipment include:
Processor and the memory having program stored therein;
Wherein when the processor performs described program, following operation is performed:
The real time running state of target vehicle is obtained, and history transport condition and the mapping of priori collision threat coefficient are closed
System, the priori collision threat coefficient reflect several collision possibilities of training vehicle under the history transport condition;
According to the real time running state of the target vehicle and the mapping relations, the priori for obtaining the target vehicle is touched
Hit threat coefficient;
It is described according to the posteriority collision threat coefficient of target vehicle described in the real time running state computation of the target vehicle
Posteriority collision threat coefficient reflects the possibility that other vehicles of the target vehicle and Current ambient collide;
Collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, is carried out to the target vehicle
Early warning.
In order to make those skilled in the art more fully understand application scheme, below in conjunction with the embodiment of the present application
Attached drawing, is clearly and completely described the technical solution in the embodiment of the present application, it is clear that described embodiment is only this
Apply for part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
All other embodiments obtained under the premise of creative work are not made, shall fall in the protection scope of this application.
When introducing the element of various embodiments of the application, article "a", "an", "this" and " described " are intended to
Indicate one or more elements.Word " comprising ", "comprising" and " having " are all inclusive and mean except listing
Outside element, there can also be other elements.
It should be noted that one of ordinary skill in the art will appreciate that realize the whole in above method embodiment or portion
Split flow, is that relevant hardware can be instructed to complete by computer program, the program can be stored in a computer
In read/write memory medium, the program is upon execution, it may include such as the flow of above-mentioned each method embodiment.Wherein, the storage
Medium can be magnetic disc, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random
Access Memory, RAM) etc..
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment stressed is the difference with other embodiment.It is real especially for device
For applying example, since it is substantially similar to embodiment of the method, so describing fairly simple, related part is referring to embodiment of the method
Part explanation.Device embodiment described above is only schematical, wherein described be used as separating component explanation
Unit and module may or may not be it is physically separate.Furthermore it is also possible to it is selected according to the actual needs
In some or all of unit and module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying
In the case of creative work, you can to understand and implement.
The above is only the embodiment of the application, it is noted that for the ordinary skill people of the art
For member, on the premise of the application principle is not departed from, some improvements and modifications can also be made, these improvements and modifications also should
It is considered as the protection domain of the application.
Claims (10)
- A kind of 1. vehicle collision prewarning method, it is characterised in that the described method includes:The real time running state of target vehicle, and the mapping relations of history transport condition and priori collision threat coefficient are obtained, The priori collision threat coefficient reflects several collision possibilities of training vehicle under the history transport condition;According to the real time running state of the target vehicle and the mapping relations, the priori collision prestige of the target vehicle is obtained Coerce coefficient;According to the posteriority collision threat coefficient of target vehicle described in the real time running state computation of the target vehicle, the posteriority Collision threat coefficient reflects the possibility that other vehicles of the target vehicle and Current ambient collide;Collision threat coefficient is threatened according to the priori collision threat coefficient and the posteriority, is carried out to the target vehicle pre- It is alert.
- 2. according to the method described in claim 1, it is characterized in that, the acquisition history transport condition and priori collision threat system Several mapping relations include:Obtain the history transport condition and history collision result of several training vehicles;Obtained according to the history transport condition of several training vehicles with history collision result in the history transport condition Under priori collision threat coefficient, so as to obtain the mapping relations of the history transport condition and priori collision threat coefficient.
- 3. according to the method described in claim 2, it is characterized in that, it is described several training vehicles include first training vehicle and Second training vehicle;The history transport condition is included under history running environment, it is described first training vehicle and it is described second training vehicle it Between relative velocity, relative distance and opposite travel direction.
- 4. according to the method described in claim 3, it is characterized in that, the real time running state of the target vehicle is included in currently Under running environment, relative velocity, relative distance and opposite travel direction between the target vehicle and around other vehicles.
- 5. according to the method described in claim 4, it is characterized in that, the history running environment and the current driving environment point Bao Kuo not following at least one:Weather conditions, road shape and pavement behavior.
- 6. according to the method described in claim 5, it is characterized in that, the road shape includes:Straight line, turning or intersection.
- 7. method according to claim 2, it is characterised in that the history collision result includes following one of which:Collision and do not eject air bag, collision and pop-up air bag, do not collide and carry out emergency braking, do not collide and pass through Brake deceleration is to 0 and does not collide and brakes and is not decelerated to 0.
- 8. according to the method described in claim 1, it is characterized in that, the real time running state of the target vehicle includes real-time position Confidence ceases;The posteriority collision threat coefficient of target vehicle described in the real time running state computation according to the target vehicle includes:According to the real-time position information of other vehicles around the real-time position information of the target vehicle and the target vehicle, Predict the collision time of the target vehicle and other vehicles of surrounding;The posteriority collision threat coefficient is obtained according to the collision time.
- 9. according to the method described in claim 8, it is characterized in that, the real-time position information according to the target vehicle and The real-time position information of other vehicles around the target vehicle, predict the target vehicle and it is described around other vehicles Collision time includes:The position that the target vehicle according to the prediction of the real-time position information of the target vehicle in following predetermined time reaches, and Safety zone based on target vehicle described in the location determination reached in target vehicle described in the following predetermined time;Other vehicles around according to the real-time position information prediction of other vehicles of surrounding in the following predetermined time The position of arrival, and based on described in the location determination that other vehicles reach around described in the following predetermined time around other The safety zone of vehicle;If the safety zone of the target vehicle is overlapping with the safety zone of other vehicles of surrounding, by current time to institute Stating the period between following predetermined time is determined as the collision time.
- 10. according to the method described in claim 9, it is characterized in that, the real time running state of the target vehicle further includes:Institute State velocity information, yaw information and the current driving environmental information of target vehicle;The position that the target vehicle according to the prediction of the real-time position information of the target vehicle in following predetermined time reaches Put including:Existed according to the prediction of the real-time position information of the target vehicle, velocity information, yaw information and current driving environmental information The position that target vehicle described in following predetermined time reaches.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711015264.4A CN107945574B (en) | 2017-10-25 | 2017-10-25 | Vehicle collision early warning method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711015264.4A CN107945574B (en) | 2017-10-25 | 2017-10-25 | Vehicle collision early warning method, device and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107945574A true CN107945574A (en) | 2018-04-20 |
CN107945574B CN107945574B (en) | 2020-04-10 |
Family
ID=61935655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711015264.4A Active CN107945574B (en) | 2017-10-25 | 2017-10-25 | Vehicle collision early warning method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107945574B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118787A (en) * | 2018-08-20 | 2019-01-01 | 浙江工业大学 | A kind of car speed prediction technique based on deep neural network |
CN109582022A (en) * | 2018-12-20 | 2019-04-05 | 驭势科技(北京)有限公司 | A kind of automatic Pilot strategic decision-making System and method for |
CN109859528A (en) * | 2019-02-27 | 2019-06-07 | 中国第一汽车股份有限公司 | A kind of corner vehicle location classification method based on V2X car networking |
CN110053622A (en) * | 2019-04-18 | 2019-07-26 | 江苏理工学院 | Vehicle and its active brake control method and device |
CN110379155A (en) * | 2018-09-30 | 2019-10-25 | 长城汽车股份有限公司 | For determining the method and system of road target coordinate |
CN111368017A (en) * | 2020-03-10 | 2020-07-03 | 无锡物联网创新中心有限公司 | Data screening method for intelligent networked automobile |
CN111506692A (en) * | 2020-04-21 | 2020-08-07 | 成都路行通信息技术有限公司 | Collision detection method based on target behaviors |
CN111613059A (en) * | 2020-05-30 | 2020-09-01 | 腾讯科技(深圳)有限公司 | Data processing method and equipment |
CN111932942A (en) * | 2020-08-28 | 2020-11-13 | 英华达(南京)科技有限公司 | Vehicle collision early warning method and device, terminal device and computer readable storage medium |
CN112202890A (en) * | 2020-09-30 | 2021-01-08 | 腾讯科技(深圳)有限公司 | Early warning method and device for vehicle driving risk and computer equipment |
CN112258838A (en) * | 2020-10-20 | 2021-01-22 | 腾讯科技(深圳)有限公司 | Driving risk prompting method and device, storage medium and equipment |
CN113335311A (en) * | 2021-07-22 | 2021-09-03 | 中国第一汽车股份有限公司 | Vehicle collision detection method and device, vehicle and storage medium |
CN113519018A (en) * | 2019-03-12 | 2021-10-19 | 三菱电机株式会社 | Mobile body control device and mobile body control method |
CN114387821A (en) * | 2022-01-27 | 2022-04-22 | 中国第一汽车股份有限公司 | Vehicle collision early warning method and device, electronic equipment and storage medium |
US11926339B2 (en) | 2018-09-30 | 2024-03-12 | Great Wall Motor Company Limited | Method for constructing driving coordinate system, and application thereof |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1618646A (en) * | 2003-11-20 | 2005-05-25 | 日产自动车株式会社 | Assisting system for driver |
JP2012238151A (en) * | 2011-05-11 | 2012-12-06 | Toyota Motor Corp | Periphery monitoring device and periphery monitoring method, and driving support device |
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
CN104882025A (en) * | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
US20150262486A1 (en) * | 2013-03-14 | 2015-09-17 | Microsoft Technology Licensing, Llc | Enriching driving experience with cloud assistance |
JP2015212944A (en) * | 2014-05-06 | 2015-11-26 | トヨタ モーター エンジニアリング アンド マニュファクチャリング ノース アメリカ,インコーポレイティド | Method and apparatus for determining lane identifier in roadway |
CN105206108A (en) * | 2015-08-06 | 2015-12-30 | 同济大学 | Early warning method against vehicle collision based on electronic map |
CN106056972A (en) * | 2016-06-29 | 2016-10-26 | 江苏科技大学 | Security anti-collision early-warning method based on vehicle driving speed and position information fusion |
CN106157695A (en) * | 2016-08-03 | 2016-11-23 | 奇瑞汽车股份有限公司 | The based reminding method of dangerous driving behavior and device |
CN106781692A (en) * | 2016-12-01 | 2017-05-31 | 东软集团股份有限公司 | The method of vehicle collision prewarning, apparatus and system |
-
2017
- 2017-10-25 CN CN201711015264.4A patent/CN107945574B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1618646A (en) * | 2003-11-20 | 2005-05-25 | 日产自动车株式会社 | Assisting system for driver |
JP2012238151A (en) * | 2011-05-11 | 2012-12-06 | Toyota Motor Corp | Periphery monitoring device and periphery monitoring method, and driving support device |
US20150262486A1 (en) * | 2013-03-14 | 2015-09-17 | Microsoft Technology Licensing, Llc | Enriching driving experience with cloud assistance |
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
JP2015212944A (en) * | 2014-05-06 | 2015-11-26 | トヨタ モーター エンジニアリング アンド マニュファクチャリング ノース アメリカ,インコーポレイティド | Method and apparatus for determining lane identifier in roadway |
CN104182618A (en) * | 2014-08-06 | 2014-12-03 | 西安电子科技大学 | Rear-end early warning method based on Bayesian network |
CN104882025A (en) * | 2015-05-13 | 2015-09-02 | 东华大学 | Crashing detecting and warning method based on vehicle network technology |
CN105206108A (en) * | 2015-08-06 | 2015-12-30 | 同济大学 | Early warning method against vehicle collision based on electronic map |
CN106056972A (en) * | 2016-06-29 | 2016-10-26 | 江苏科技大学 | Security anti-collision early-warning method based on vehicle driving speed and position information fusion |
CN106157695A (en) * | 2016-08-03 | 2016-11-23 | 奇瑞汽车股份有限公司 | The based reminding method of dangerous driving behavior and device |
CN106781692A (en) * | 2016-12-01 | 2017-05-31 | 东软集团股份有限公司 | The method of vehicle collision prewarning, apparatus and system |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109118787A (en) * | 2018-08-20 | 2019-01-01 | 浙江工业大学 | A kind of car speed prediction technique based on deep neural network |
CN110379155A (en) * | 2018-09-30 | 2019-10-25 | 长城汽车股份有限公司 | For determining the method and system of road target coordinate |
US11926339B2 (en) | 2018-09-30 | 2024-03-12 | Great Wall Motor Company Limited | Method for constructing driving coordinate system, and application thereof |
CN109582022A (en) * | 2018-12-20 | 2019-04-05 | 驭势科技(北京)有限公司 | A kind of automatic Pilot strategic decision-making System and method for |
CN109582022B (en) * | 2018-12-20 | 2021-11-02 | 驭势科技(北京)有限公司 | Automatic driving strategy decision system and method |
CN109859528A (en) * | 2019-02-27 | 2019-06-07 | 中国第一汽车股份有限公司 | A kind of corner vehicle location classification method based on V2X car networking |
CN109859528B (en) * | 2019-02-27 | 2021-12-10 | 中国第一汽车股份有限公司 | V2X Internet of vehicles-based method for classifying positions of vehicles at curves |
CN113519018A (en) * | 2019-03-12 | 2021-10-19 | 三菱电机株式会社 | Mobile body control device and mobile body control method |
CN113519018B (en) * | 2019-03-12 | 2023-01-03 | 三菱电机株式会社 | Mobile body control device and mobile body control method |
CN110053622A (en) * | 2019-04-18 | 2019-07-26 | 江苏理工学院 | Vehicle and its active brake control method and device |
CN111368017A (en) * | 2020-03-10 | 2020-07-03 | 无锡物联网创新中心有限公司 | Data screening method for intelligent networked automobile |
CN111506692A (en) * | 2020-04-21 | 2020-08-07 | 成都路行通信息技术有限公司 | Collision detection method based on target behaviors |
CN111506692B (en) * | 2020-04-21 | 2023-05-26 | 成都路行通信息技术有限公司 | Collision detection method based on target behaviors |
CN111613059A (en) * | 2020-05-30 | 2020-09-01 | 腾讯科技(深圳)有限公司 | Data processing method and equipment |
CN111613059B (en) * | 2020-05-30 | 2023-08-18 | 腾讯科技(深圳)有限公司 | Data processing method and device |
CN111932942A (en) * | 2020-08-28 | 2020-11-13 | 英华达(南京)科技有限公司 | Vehicle collision early warning method and device, terminal device and computer readable storage medium |
CN112202890A (en) * | 2020-09-30 | 2021-01-08 | 腾讯科技(深圳)有限公司 | Early warning method and device for vehicle driving risk and computer equipment |
CN112258838A (en) * | 2020-10-20 | 2021-01-22 | 腾讯科技(深圳)有限公司 | Driving risk prompting method and device, storage medium and equipment |
CN112258838B (en) * | 2020-10-20 | 2023-10-13 | 腾讯科技(深圳)有限公司 | Driving risk prompting method, device, storage medium and equipment |
CN113335311B (en) * | 2021-07-22 | 2022-09-23 | 中国第一汽车股份有限公司 | Vehicle collision detection method and device, vehicle and storage medium |
CN113335311A (en) * | 2021-07-22 | 2021-09-03 | 中国第一汽车股份有限公司 | Vehicle collision detection method and device, vehicle and storage medium |
CN114387821A (en) * | 2022-01-27 | 2022-04-22 | 中国第一汽车股份有限公司 | Vehicle collision early warning method and device, electronic equipment and storage medium |
CN114387821B (en) * | 2022-01-27 | 2023-08-22 | 中国第一汽车股份有限公司 | Vehicle collision early warning method, device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107945574B (en) | 2020-04-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107945574A (en) | A kind of vehicle collision prewarning method, device and equipment | |
US11734473B2 (en) | Perception error models | |
CN111951606B (en) | Ship collision risk assessment and early warning method and system | |
US11625513B2 (en) | Safety analysis framework | |
US11351995B2 (en) | Error modeling framework | |
CN106133805B (en) | Driving assistance method and system for collision elimination | |
CN103155015B (en) | Moving-object prediction device, virtual-mobile-object prediction device, program module, mobile-object prediction method, and virtual-mobile-object prediction method | |
CN109658700A (en) | Intersection anti-collision prewarning apparatus and method for early warning | |
US10232849B2 (en) | Collision mitigation and avoidance | |
US11518381B2 (en) | Enhanced threat selection | |
Raju et al. | Performance of open autonomous vehicle platforms: Autoware and Apollo | |
CN108062600A (en) | A kind of vehicle collision prewarning method and device based on rectangle modeling | |
US11648939B2 (en) | Collision monitoring using system data | |
US11697412B2 (en) | Collision monitoring using statistic models | |
CN108022026A (en) | A kind of traffic security early warning method of traffic control, device and the system including the device | |
CN105699964A (en) | Road multi-target tracking method based on automobile anti-collision radar | |
US11884252B2 (en) | Enhanced threat assessment | |
CN108806018A (en) | A kind of data processing method, data processing equipment and intelligent automobile | |
CN107784708A (en) | It is a kind of based on different road conditions come judge drive risk method | |
US11709260B2 (en) | Data driven resolution function derivation | |
WO2021061488A1 (en) | Safety analysis framework | |
CN109345870A (en) | The method for early warning and device for preventing vehicle collision | |
US11392128B1 (en) | Vehicle control using directed graphs | |
CN106218612A (en) | A kind of method of vehicle safety travel, device and terminal | |
CN114787894A (en) | Perceptual error model |
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 |