CN105761548B - Intersection collision avoidance method based on dynamic bayesian network - Google Patents
Intersection collision avoidance method based on dynamic bayesian network Download PDFInfo
- Publication number
- CN105761548B CN105761548B CN201610230227.4A CN201610230227A CN105761548B CN 105761548 B CN105761548 B CN 105761548B CN 201610230227 A CN201610230227 A CN 201610230227A CN 105761548 B CN105761548 B CN 105761548B
- Authority
- CN
- China
- Prior art keywords
- intersection
- time
- driver
- vehicle
- state
- 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.)
- Active
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention discloses a kind of intersection collision avoidance method based on dynamic bayesian network, intersection complexity road layout can not be adapted to very well by mainly solving existing algorithm, need to carry out substantial amounts of data processing, the problem of causing high computation complexity and time complexity.Implementation step is：1) vehicle-state, road conditions and driving behavior information are determined, and vehicle-state is developed using dynamic bayesian network and is modeled；2) target vehicle safe driving behavior is determined according to present circumstances；3) derive intention behavior of the driver in intersection, and risk assessment is carried out by contrasting safe driving behavior and intention behavior, in the presence of detecting and being potentially dangerous, take different measures to be avoided to carry out collision according to actual conditions.Present invention, avoiding the track of vehicle of complexity to predict process, reduces amount of calculation, vehicle collision that can be neatly to other scenes avoids, available in intelligent transportation system.
Description
Technical Field
The invention belongs to the field of traffic information and control, and further relates to a road intersection collision early warning and avoiding method in an intelligent traffic system, which can be used in the intelligent traffic system.
Background
As is well known, traffic accidents cause great loss to people's lives and properties and traffic efficiency, and in order to reduce traffic accidents, researchers have designed collision avoidance systems based on radar, sensing, video and communication technologies to avoid vehicle collisions. Most of the technical means consider that the overlapping of the vehicle positions is avoided through the track prediction, which puts high requirements on the precision indexes of various technologies.
The influence of traffic accidents at intersections on the performance of a traffic network is particularly important, and the movement conditions of vehicles at the intersections are complex, which not only relate to the geographical positions of the vehicles, but also relate to the admission of drivers to laws and regulations and the psychological factors of the drivers at the intersections. Current collision avoidance systems for intersections focus on calculations of the geographic position of the vehicle using techniques that involve mainly the following two types:
1. the position is calculated from data collected by the vehicle itself. For example, a researcher a.m. miller calculates a vehicle position to find a vehicle collision region and warn a driver, (a.m. miller and r.a. Trombey, "collision avoidance with adaptive collision dimensions," United States Patent, 2013.), and the calculation of such a collision region can only perform a broad warning function and cannot perform a targeted treatment on a dangerous situation.
2. And exchanging information among the vehicles to predict risks. For example, researchers such as t.h.shue and others have proposed a vehicle position prediction system that exchanges GPS information with each other based on vehicle-to-vehicle communication to deal with dangerous situations, (t.h.shue and h.jihua, "DGPS-based vehicle-to-vehicle co-operational compatibility warning: engineering ease points," IEEE Transactions on Intelligent Transportation Systems, vol.7, no.4, pp.415-428, 2006), but this method does not take into account the influence of human factors of the driver on the vehicle collision.
At the same time, researchers have begun to consider the impact of the driver's condition on the collision. For example, researchers g.s.aoude, etc. learn a lot of data using a neural network to predict a collision event, (g.s.aoude, v.r.desaraju, l.h.stephens, and j.p.how, "Driver noise classification at observations and evaluation on large national data set," IEEE Transactions on Intelligent transfer Systems, vol.13, no.2, pp.724-736, 2012.), but this approach will result in a lot of computational overhead.
The first two prior arts consider the geographical position information of the vehicle unilaterally, and cannot well deal with the problem of collision avoidance at the intersection. The third type of technology comprehensively considers the influence of the vehicle position information and the driver state on the vehicle collision at the intersection, but requires a complex calculation process, which brings a large amount of calculation overhead. In addition, the above prior art is based on vehicle trajectory prediction, and requires a large amount of data processing, which leads to high computational complexity and time complexity problems.
Disclosure of Invention
The present invention is directed to provide a method for avoiding collision at an intersection based on a dynamic bayesian network, so as to reduce the amount of calculation and avoid vehicle collision.
The technical idea for realizing the purpose of the invention is as follows: the method comprises the steps of establishing a vehicle state evolution model according to current state information, driver behavior information and traffic light states of a vehicle, determining safety behaviors and driver operation intentions, carrying out risk assessment by judging whether the intention behaviors of the driver at the intersection are safe or not, and sending out danger warnings or taking measures to avoid collision if potential dangers are detected. The implementation steps comprise:
(1) Recording the Current vehicle State O t And driver behavior D t Establishing a vehicle state evolution model as follows:
P(D 0:t ,O 0:t )＝P(D t |D t-1 )P(O t |D t O t-1 )P(D 0:t-1 ,O 0:t-1 )
where t denotes the current recording time, t-1 denotes the previous recording time, 0 t denotes a time period from the start time 0 to the time t, 0 t-1 denotes a time period from the start time 0 to the time t-1, and P (D t |D t-1 ) Representing the probability of a state transition of the driver's behavior from time t-1 to time t, P (O) t |D t O t-1 ) Represents the state transition probability from time t-1 to time t of the vehicle state, P (D) 0:t-1 ,O 0:t-1 ) Representing the joint probability of the vehicle state and the driver behavior in the time period from the starting time 0 to the t-1;
P(D t |D t-1 )＝P(M t |M t-1 )P(L t |M t-1 L t-1 I t-1 B t-1 A t-1 )P(I t |I t-1 B t-1 A t-1 )P(B t |B t-1 )
wherein the driver behavior D t The method comprises the following steps: driver can execute operation M at intersection t And the running distance L after the vehicle exceeds the stop line of the intersection t Driver's intention behavior at crossroads I t Driver state B t Safe driving behavior at crossroads E t ，P(M t |M t-1 ) Representing the probability of a state transition from time t-1 to time t of an operation that the driver can perform at the intersection, P (L) t |M t-1 L t-1 I t-1 B t-1 A t-1 ) Represents the state transition probability P (I) of the driving distance from t-1 to t after the vehicle exceeds the stop line of the intersection t |I t-1 B t-1 A t-1 ) Representing the probability of a state transition from time t-1 to time t of the driver's intended behavior at the intersection, P (B) t |B t-1 ) Representing the state transition probability of the driver state from the t-1 moment to the t moment;
P(O t |D t O t-1 )＝P(P t |M t L t )P(V t |M t L t-1:t I t-1 B t-1 V t-1 )P(A t |C t A t-1 )P(T t |M t-1:t )
wherein the vehicle state O t The method comprises the following steps: vehicle position P t Speed of driving V t Acceleration A t State of turn signal lamp T t Road State C t T-1 t |M t L t ) Indicates the state transition probability, P (V), of the vehicle position at time t t |M t L t-1:t I t-1 B t-1 V t-1 ) Represents the state transition probability of the traveling speed from t-1 to t, P (A) t |C t A t-1 ) Represents the probability of the state transition of the acceleration from time T-1 to time T, P (T) t |M t-1:t ) Representing the state transition probability of the state of the steering lamp at the time t;
(2) According to the current vehicle state O t Traffic light status and traffic regulations determining safe driving at intersectionsAction E t And calculating the executable operation M of the driver at the intersection according to the vehicle state evolution model in the step (1) t And the running distance L after the vehicle exceeds the stop line of the intersection t And a running speed V t Under the condition(s), safe driving behavior E of the driver at the intersection t To the probability of needing to stop:
wherein p represents the probability of requiring parking, and 1-p represents the probability of not requiring parking;
(3) According to the current vehicle state O t And driver state B t Determining driver's intended behavior I at an intersection t Comparing the safe driving behavior E in the step (2) t And the driver's intention behavior at the intersection I t Calculating the intention behavior I of the driver at the intersection t Probability of risk:
wherein i represents the ith driving operation which is intently executed by the driver at the intersection, j represents the jth safety behavior which is performable by the driver at the intersection, q represents the probability of risk of the intention operation of the driver at the intersection, and 1-q represents the probability of no risk;
(4) According to the risk assessment result in the step (3), when a potential danger is detected, different measures are taken to avoid the collision by comparing the time to collision TTC, the time to avoid collision TTA and the average driver reaction time T:
when TTC-TTA is greater than T, warning information is issued to the target vehicle S, and the driver adjusts the driving state by himself to avoid collision;
when T is greater than TTC-TTA and greater than 0, taking emergency braking measures to the target vehicle S to avoid collision;
when TTC = TTA, an emergency braking measure is taken for the target vehicle S in the collision area and a warning message is issued to the other vehicle X for collision avoidance.
Compared with the prior art, the invention has the following advantages:
1. the invention adopts the dynamic Bayesian network to carry out vehicle state evolution modeling, so that the invention can process some uncertain factors such as driver behaviors and overcome the defect that the prior model needs to know the current all state information of the vehicle.
2. According to the invention, the intention and safety behavior of the driver at the intersection are distinguished for risk assessment, so that a complex vehicle track prediction process is avoided.
3. According to the real traffic scene of the current city, the traffic light, road condition and other factors under the actual traffic scene are fully considered, and human factors related to drivers are considered, so that the simulation degree of the real scene is greatly improved.
Drawings
FIG. 1 is a flow chart of an implementation of the present invention;
FIG. 2 is a graph comparing the performance of the present invention with a prior art target vehicle based collision avoidance algorithm.
Detailed Description
The steps and effects of the present invention will be further described in detail with reference to the accompanying drawings.
Step 1, establishing a vehicle state evolution model.
A vehicle state evolution model for simulating the relationship between the variables and the state evolution of the vehicle near the intersection, primarily by the vehicle state O t And driver behavior D t The method utilizes the dynamic Bayesian network to establish a vehicle state evolution model, and the mathematical expression of the method is as follows:
P(D 0:t ,O 0:t )＝P(D t |D t-1 )P(O t |D t O t-1 )P(D 0:t-1 ,O 0:t-1 )
where t denotes the current recording time, t-1 denotes the previous recording time, 0 t denotes a time period from the start time 0 to the time t, 0 t-1 denotes a time period from the start time 0 to the time t-1, and P (D t |D t-1 ) Representing the probability of a state transition of the driver's behavior from time t-1 to time t, P (O) t |D t O t-1 ) Represents the state transition probability from time t-1 to time t of the vehicle state, P (D) 0:t-1 ,O 0:t-1 ) Representing the joint probability of the vehicle state and the driver behavior in the time period from the starting time 0 to the t-1;
P(D t |D t-1 )＝P(M t |M t-1 )P(L t |M t-1 L t-1 I t-1 B t-1 A t-1 )P(I t |I t-1 B t-1 A t-1 )P(B t |B t-1 )
wherein the driver behavior D t The method comprises the following steps: driver can execute operation M at intersection t And the running distance L after the vehicle exceeds the stop line of the intersection t Driver's intention behavior at crossroads I t Driver state B t Safe driving behavior at crossroads E t ，P(M t |M t-1 ) Representing the probability of a state transition of the driver at the intersection from time t-1 to time t of the executable operation, P (L) t |M t-1 L t-1 I t-1 B t-1 A t-1 ) Represents the state transition probability P (I) of the driving distance from t-1 to t after the vehicle exceeds the stop line of the intersection t |I t-1 B t-1 A t-1 ) Representing the probability of a transition of the driver's intended behavior at the intersection from time t-1 to time t, P (B) t |B t-1 ) Representing the state transition probability of the driver state from the t-1 moment to the t moment;
P(O t |D t O t-1 )＝P(P t |M t L t )P(V t |M t L t-1:t I t-1 B t-1 V t-1 )P(A t |C t A t-1 )P(T t |M t-1:t )
wherein the vehicle state O t The method comprises the following steps: vehicle position P t Speed of driving V t Acceleration A t State of turn signal lamp T t Road State C t T-1 t |M t L t ) Indicates the state transition probability, P (V), of the vehicle position at time t t |M t L t-1:t I t-1 B t-1 V t-1 ) Represents the state transition probability of the traveling speed from the time t-1 to the time t, P (A) t |C t A t-1 ) Represents the probability of the state transition of the acceleration from time T-1 to time T, P (T) t |M t-1:t ) Indicating the state transition probability of the turn signal state at time t.
And 2, determining safe driving behaviors of the intersection and the probability that a driver needs to stop at the intersection.
2a) According to the current vehicle state O t Traffic light status and traffic regulations determine the safe driving behavior E of the driver at the intersection t The rule is as follows:
if the traffic light state is green light and the remaining state conversion time t enables the target vehicle S to pass through the intersection at the constant speed at the current speed when the target vehicle S reaches the intersection, the uniform speed and the accelerated passing through the intersection are safe driving behaviors, otherwise, if the traffic light state is green light and the remaining state conversion time t does not enable the target vehicle S to pass through the intersection at the constant speed at the current speed;
if the traffic light state is green light and the remaining state transition time t cannot enable the target vehicle S to pass through the intersection at the constant speed at the current speed when the target vehicle S reaches the intersection, stopping as safe driving behavior;
2b) Calculating an executable operation M at a driver at an intersection t And the running distance L after the vehicle exceeds the stop line of the intersection t And the running speed V t Under the condition of (2), safe driving behavior E of the driver at the intersection t Probability of parking required:
where p represents the probability that parking is required and 1-p represents the probability that parking is not required.
And step 3, risk assessment.
3a) According to the current vehicle state O t And driver state B t Determining driver's intended behavior at an intersection I t I.e. first according to the speed V t And acceleration A t The change of the speed is used for deducing whether the driver has the intention of accelerating to pass through, passing through at a constant speed or stopping at the intersection; then according to the state T of the steering lamp t Deducing whether the driver has the intention of turning at the intersection;
3b) Comparison of safe Driving behavior E t And the driver's intention behavior at the intersection I t ：
If I t ＝E t There is no collision risk;
if I t ≠E t Then the following classification discussion is made:
when E is t For driving at a constant speed, if I t For acceleration of the vehicle, there is no risk of collision, if I t In the case of deceleration driving, there is a risk of collision;
when E is t For acceleration, if I t The vehicle runs at a constant speed or at a reduced speed, so that collision risks exist;
when E is t For deceleration, if I t No collision risk exists for acceleration and uniform speed running;
when E is t For stopping, if I t If the vehicle is not stopped, collision risks exist;
3c) Calculating the probability that the intention behavior of the driver at the intersection is at risk:
wherein i represents the i-th driving behavior which is intently executed by the driver at the intersection, j represents the j-th safety behavior which is intensely executed by the driver at the intersection, q represents the probability that the intention behavior of the driver at the intersection has risk, and 1-q represents the probability that the risk does not exist.
And 4, collision avoidance.
4a) Calculating the time to collision TTC and the time to avoid TTA when the existence of the potential danger is detected according to the risk assessment:
wherein v is S Indicates the traveling speed, v, of the target vehicle S X Represents the traveling speed of the other vehicle X, d represents the distance between the target vehicle and the other vehicle, μ represents the road surface friction factor, g represents the gravitational acceleration, a represents the average braking reaction time, b represents the average communication time;
4b) According to the comparison collision time TTC, the avoidance time TTA and the longest reaction time T of the driver, different measures are taken to avoid the collision:
when TTC-TTA > T, warning information is issued to the target vehicle S, and a driver can adjust the driving state by himself to avoid collision;
when T is greater than TTC-TTA >0, taking emergency braking measures to the target vehicle S to avoid collision;
when TTC = TTA, an emergency braking measure is taken for the target vehicle S in the collision area and a warning message is issued to the other vehicle X for collision avoidance.
The effects of the present invention can be further illustrated by the following simulations:
1. simulation conditions
Simulation software: adopting MATLAB;
simulation scene: two vehicles in different directions move to the intersection in a scene of the intersection controlled by the two-way traffic light, the scene is provided with the intersection controlled by the two-way traffic light, and all lanes are two-way lanes;
vehicle initial position distribution: randomly distributed between the intersection and the road edge;
moving the vehicle: moving to the intersection at a constant speed;
the simulation setup parameters are shown in the following table.
| Parameter(s) | Parameter value |
| Width w of vehicle | 1.75m |
| Length of vehicle l | 4m |
| Width a of single lane | 3.5m |
| Intersection turning radius r | 3.5m |
| Road surface friction factor mu | 0.1～0.9 |
2. Emulated content and results
By using the simulation scenario and the simulation conditions, the present invention and the existing collision avoidance method which only takes measures for the target vehicle are simulated to obtain a performance comparison graph, as shown in fig. 2.
The abscissa in fig. 2 represents the driver reaction time in seconds, and the ordinate represents the probability of successful collision avoidance. In fig. 2, a curve indicated by a circle is a result curve of a simulation using a conventional collision avoidance method of taking measures only for a target vehicle, and a curve indicated by a square is a result curve of a simulation using the collision avoidance method of the present invention.
As can be seen from fig. 2, as the reaction time of the driver increases, the success rate is significantly reduced when the existing curve marked with a circle is used for collision avoidance only by taking measures for the target vehicle, and the success rate is still maintained at a higher level when the curve marked with a square is used for collision avoidance by using the present invention. The reason is that: for some emergency scenes, such as long reaction time is needed when the state of a driver is poor, longer braking time is needed when only measures are taken for a target vehicle, and accidents cannot be successfully avoided; the invention considers the operation of other vehicles, and takes different measures according to the actual situation to ensure that the vehicles of the two vehicles cooperate with each other so as to avoid accidents, so the accident avoidance success rate of the invention is always kept at a higher level.
Simulation shows that the method can improve the simulation degree, reflect the actual traffic scene more truly, and adopt different measures to avoid the occurrence of accidents according to the actual situation, thereby being flexibly applied to the collision avoidance of other scenes.
While the invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (4)
1. A crossroad collision avoidance method based on a dynamic Bayesian network comprises the following steps:
(1) Recording the current vehicle state O t And driver behavior D t Establishing a vehicle state evolution model as follows:
P(D 0:t ,O 0:t )＝P(D t |D t-1 )P(O t |D t O t-1 )P(D 0:t-1 ,O 0:t-1 )
where t denotes the current recording time, t-1 denotes the previous recording time, 0 t denotes a time period from the start time 0 to the time t, 0 t-1 denotes a time period from the start time 0 to the time t-1, and P (D t |D t-1 ) Representing the probability of a state transition of the driver's behavior from time t-1 to time t, P (O) t |D t O t-1 ) Representing the probability of a state transition of the vehicle state from time t-1 to time t, P (D) 0:t-1 ,O 0:t-1 ) Representing the joint probability of the vehicle state and the driver behavior in the time period from the starting time 0 to the t-1;
P(D t |D t-1 )＝P(M t |M t-1 )P(L t |M t-1 L t-1 I t-1 B t-1 A t-1 )P(I t |I t-1 B t-1 A t-1 )P(B t |B t-1 )
wherein the driver behavior D t The method comprises the following steps: driver can execute operation M at intersection t And the running distance L after the vehicle exceeds the stop line of the intersection t Driver's intention behavior at crossroads I t Driver state B t Safe driving behavior at crossroads E t ，P(M t |M t-1 ) Representing the probability of a state transition of the driver at the intersection from time t-1 to time t of the executable operation, P (L) t |M t-1 L t-1 I t-1 B t-1 A t-1 ) Represents the state transition probability P (I) of the driving distance from t-1 to t after the vehicle exceeds the stop line of the intersection t |I t-1 B t-1 A t-1 ) Representing the probability of a transition of the driver's intended behavior at the intersection from time t-1 to time t, P (B) t |B t-1 ) Indicating driver's shapeThe state transition probability of the state from the t-1 moment to the t moment;
P(O t |D t O t-1 )＝P(P t |M t L t )P(V t |M t L t-1:t I t-1 B t-1 V t-1 )P(A t |C t A t-1 )P(T t |M t-1:t )
wherein the vehicle state O t The method comprises the following steps: vehicle position P t Speed of driving V t Acceleration A t State of turn signal lamp T t Road condition C t T-1 t |M t L t ) Indicates the state transition probability, P (V), of the vehicle position at time t t |M t L t-1:t I t-1 B t-1 V t-1 ) Represents the state transition probability of the traveling speed from the time t-1 to the time t, P (A) t |C t A t-1 ) Represents the probability of the state transition of the acceleration from time T-1 to time T, P (T) t |M t-1:t ) Representing the state transition probability of the state of the steering lamp at the time t;
(2) According to the current vehicle state O t Traffic light status and traffic regulations determining safe driving behavior E of an intersection t And calculating the executable operation M of the driver at the intersection according to the vehicle state evolution model in the step (1) t And the running distance L after the vehicle exceeds the stop line of the intersection t And the running speed V t Under the condition of (2), safe driving behavior E of the driver at the intersection t Probability of parking required:
wherein p represents the probability of requiring parking, and 1-p represents the probability of not requiring parking;
(3) According to the current vehicle state O t And driver state B t Determining driver's intended behavior at an intersection I t Comparing the safe driving behavior E in the step (2) t At the intersection with the driverIntention behavior of intersection I t Calculating the intention behavior I of the driver at the intersection t Probability of risk:
wherein i represents the i-th driving operation performed by the driver at the intersection, j represents the j-th safety behavior performed by the driver at the intersection, q represents the probability of risk of the driver at the intersection, and 1-q represents the probability of no risk;
(4) According to the risk evaluation result of the step (3), when a potential danger is detected, taking different measures to avoid the collision by comparing the time to collision TTC, the time to avoid the collision TTA and the average driver reaction time T:
when TTC-TTA is larger than T, warning information is issued to the target vehicle S, and the driver adjusts the driving state by himself to avoid collision;
when T is more than TTC and TTA is more than 0, taking emergency braking measures to the target vehicle S to avoid collision;
when TTC = TTA, an emergency braking measure is taken for the target vehicle S in the collision area and a warning message is issued to the other vehicle X for collision avoidance.
2. The method of claim 1, wherein step (2) is based on a current vehicle state O t Traffic light status and traffic regulations determining safe driving behavior E of an intersection t The method comprises the following steps:
if the traffic light state is green light and the remaining state conversion time t enables the target vehicle S to pass through the intersection at the constant speed at the current speed when the target vehicle S reaches the intersection, the uniform speed and the accelerated passing through of the intersection are both safe driving behaviors;
and if the traffic light state is green when the target vehicle S reaches the intersection and the residual state transition time t cannot enable the target vehicle S to pass through the intersection at the constant speed at the current speed, stopping to be safe driving behavior.
3. The method of claim 1, wherein step (3) is based on a current vehicle state O t And driver state B t Determining driver's intended behavior I at an intersection t Firstly according to the driving speed V t And acceleration A t Deducing whether the driver has the intention of accelerating to pass through, passing through at a constant speed or stopping at the intersection or not according to the state T of the steering lamp t It is inferred whether the driver has an intention to turn at the intersection.
4. The method according to claim 1, wherein the time to collision TTC in step (4) is a time period from the beginning of collision to the occurrence of collision, when the two vehicles keep the original speed difference unchanged; the time to collision avoidance TTA is a time period from the start of taking measures to the complete avoidance of collision, and is calculated as follows:
wherein v is S Indicates the traveling speed, v, of the target vehicle S X Represents the traveling speed of the other vehicle X, d represents the distance between the target vehicle and the other vehicle, μ represents the road surface friction factor, g represents the gravitational acceleration, a represents the average braking reaction time, and b represents the average communication time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230227.4A CN105761548B (en) | 2016-04-14 | 2016-04-14 | Intersection collision avoidance method based on dynamic bayesian network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610230227.4A CN105761548B (en) | 2016-04-14 | 2016-04-14 | Intersection collision avoidance method based on dynamic bayesian network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105761548A CN105761548A (en) | 2016-07-13 |
| CN105761548B true CN105761548B (en) | 2018-03-06 |
Family
ID=56335006
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610230227.4A Active CN105761548B (en) | 2016-04-14 | 2016-04-14 | Intersection collision avoidance method based on dynamic bayesian network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105761548B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106777907A (en) * | 2016-11-25 | 2017-05-31 | 东软集团股份有限公司 | Driving behavior methods of marking and device |
| CN108275158B (en) * | 2017-01-05 | 2020-09-15 | 大唐高鸿信息通信(义乌)有限公司 | Driving behavior evaluation method of vehicle-mounted short-distance communication network |
| CN108694859B (en) * | 2017-02-28 | 2019-11-12 | 大唐高鸿信息通信研究院（义乌）有限公司 | A kind of trackside node high risk vehicle alarm prompt method suitable for vehicle-mounted short distance communication network |
| CN106950956B (en) * | 2017-03-22 | 2020-02-14 | 合肥工业大学 | Vehicle track prediction system integrating kinematics model and behavior cognition model |
| CN109801511B (en) * | 2017-11-16 | 2021-01-05 | 华为技术有限公司 | Collision early warning method and device |
| CN108109379B (en) * | 2018-01-26 | 2020-06-16 | 东南大学 | Safety evaluation method for expressway exit ramp area |
| KR102139590B1 (en) * | 2018-02-27 | 2020-07-30 | 주식회사 만도 | Autonomous emergency braking system and method for vehicle at intersection |
| CN108986541B (en) * | 2018-06-22 | 2020-12-18 | 东华大学 | Vehicle anti-collision routing method based on VANETs |
| CN108806332A (en) * | 2018-06-25 | 2018-11-13 | 中国移动通信集团西藏有限公司 | A kind of spacing management system based on bluetooth, GSM |
| CN108986461B (en) * | 2018-07-13 | 2021-09-10 | 西安理工大学 | Intersection vehicle collision probability analysis method based on time |
| US20220057803A1 (en) * | 2018-12-04 | 2022-02-24 | Duke University | Apparatus, method and article to facilitate motion planning in an environment having dynamic objects |
| CN109544934A (en) * | 2018-12-19 | 2019-03-29 | 同济大学 | Efficiency safety monitoring system based on urban intersection mixed traffic flow three-dimensional track |
| CN110688611B (en) * | 2019-10-13 | 2023-03-07 | 重庆交通大学 | Method and device for evaluating driving safety of in-service tunnel by environmental factors |
| CN112991789A (en) * | 2019-11-29 | 2021-06-18 | 奥迪股份公司 | Vehicle safety driving assistance system, vehicle comprising same, method and medium |
| CN112002144B (en) * | 2020-09-02 | 2022-03-01 | 中国科学技术大学 | Method and system for evaluating driving risk situation of signalless intersection |
| CN112258895A (en) * | 2020-10-22 | 2021-01-22 | 东风汽车集团有限公司 | T-shaped intersection collision judgment method based on V2X |
| CN113096411A (en) * | 2021-03-17 | 2021-07-09 | 武汉大学 | Vehicle collision early warning method at intersection based on Internet of vehicles environmental system |
| CN113538909A (en) * | 2021-07-13 | 2021-10-22 | 公安部道路交通安全研究中心 | Traffic incident prediction method and device for automatic driving vehicle |
| CN113658451B (en) * | 2021-07-30 | 2022-11-22 | 三一专用汽车有限责任公司 | Vehicle collision early warning control method and device, vehicle and readable storage medium |
| CN114662967B (en) * | 2022-04-07 | 2023-04-07 | 西南交通大学 | Unmanned driving collision risk assessment method and system based on dynamic Bayesian network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005033495A1 (en) * | 2005-07-19 | 2007-01-25 | Daimlerchrysler Ag | Traffic adaptive road vehicle motion assistance system uses synchronised control based upon speed and time distance calculations |
| CN101283387A (en) * | 2005-09-09 | 2008-10-08 | 国立计算机与自动化研究所 | Vehicle steering aid method and improved related device |
| 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 |
| WO2015062994A1 (en) * | 2013-10-31 | 2015-05-07 | Inria Institut National De Recherche En Informatique Et En Automatique | Method and system of driving assistance for collision avoidance |
| EP2950294A1 (en) * | 2014-05-30 | 2015-12-02 | Honda Research Institute Europe GmbH | Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis |
-
2016
- 2016-04-14 CN CN201610230227.4A patent/CN105761548B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005033495A1 (en) * | 2005-07-19 | 2007-01-25 | Daimlerchrysler Ag | Traffic adaptive road vehicle motion assistance system uses synchronised control based upon speed and time distance calculations |
| CN101283387A (en) * | 2005-09-09 | 2008-10-08 | 国立计算机与自动化研究所 | Vehicle steering aid method and improved related device |
| WO2015062994A1 (en) * | 2013-10-31 | 2015-05-07 | Inria Institut National De Recherche En Informatique Et En Automatique | Method and system of driving assistance for collision avoidance |
| EP2950294A1 (en) * | 2014-05-30 | 2015-12-02 | Honda Research Institute Europe GmbH | Method and vehicle with an advanced driver assistance system for risk-based traffic scene analysis |
| 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 |
Non-Patent Citations (1)
| Title |
|---|
| 赵金宝 等.基于贝叶斯网络的城市道路交通事故分析.《东南大学学报（自然科学版）》.2011,第41卷(第6期),第1300-1306页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105761548A (en) | 2016-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105761548B (en) | Intersection collision avoidance method based on dynamic bayesian network | |
| CN112416004B (en) | Control method and device based on automatic driving, vehicle and related equipment | |
| Jeong et al. | Is vehicle automation enough to prevent crashes? Role of traffic operations in automated driving environments for traffic safety | |
| CN110155046A (en) | Automatic emergency brake hierarchical control method and system | |
| Lengyel et al. | Conflicts of automated driving with conventional traffic infrastructure | |
| Park et al. | A vehicle speed harmonization strategy for minimizing inter-vehicle crash risks | |
| Li et al. | A collision-free car-following model for connected automated vehicles | |
| EP4043309A1 (en) | Vehicle control method, device, controller and intelligent vehicle | |
| TW201544377A (en) | Regional planning algorithms and trajectory optimization avoidance system of automated vehicle domain-wide risk analysis | |
| Lu et al. | Multiple‐Vehicle Longitudinal Collision Mitigation by Coordinated Brake Control | |
| Lee et al. | Development of a driving behavior-based collision warning system using a neural network | |
| Tran et al. | Improved responsibility-sensitive safety algorithm through a partially observable Markov decision process framework for automated driving behavior at non-signalized intersection | |
| Woo et al. | Advanced adaptive cruise control based on collision risk assessment | |
| Zhou et al. | Evasive behavior-based method for threat assessment in different scenarios: A novel framework for intelligent vehicle | |
| Ding et al. | Research on safety lane change warning method based on potential angle collision point | |
| US11955006B2 (en) | Traffic light indication system with suppressed notification for a vehicle | |
| Hirose et al. | A study on modeling of driver's braking action to avoid rear-end collision with time delay neural network | |
| Fu et al. | A novel warning/avoidance algorithm for intersection collision based on Dynamic Bayesian Networks | |
| CN113548049B (en) | Intelligent vehicle driving behavior decision method and system based on finite-state machine | |
| Tomar et al. | Collision avoidance warning for safe lane change | |
| Wang et al. | Novel cooperative collision avoidance model for connected vehicles | |
| Li et al. | Fuzzy based collision avoidance control strategy considering crisis index in low speed urban area | |
| Lv et al. | A novel rear-end collision warning algorithm in VANET | |
| Zhang et al. | A lane change prediction algorithm based on probabilistic modeling | |
| Imaseki et al. | Predicting the severity of driving scenario for rear-end and cut-in collisions using potential risk indicator extracted from near-miss video database |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |