CN114537385A - Dangerous target screening method based on traffic target sensing result - Google Patents

Dangerous target screening method based on traffic target sensing result Download PDF

Info

Publication number
CN114537385A
CN114537385A CN202210226337.9A CN202210226337A CN114537385A CN 114537385 A CN114537385 A CN 114537385A CN 202210226337 A CN202210226337 A CN 202210226337A CN 114537385 A CN114537385 A CN 114537385A
Authority
CN
China
Prior art keywords
target
vehicle
lane
ttc
dangerous
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
Application number
CN202210226337.9A
Other languages
Chinese (zh)
Other versions
CN114537385B (en
Inventor
丁明慧
雍文亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chongqing Changan Automobile Co Ltd
Original Assignee
Chongqing Changan Automobile Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Chongqing Changan Automobile Co Ltd filed Critical Chongqing Changan Automobile Co Ltd
Priority to CN202210226337.9A priority Critical patent/CN114537385B/en
Publication of CN114537385A publication Critical patent/CN114537385A/en
Application granted granted Critical
Publication of CN114537385B publication Critical patent/CN114537385B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/095—Predicting travel path or likelihood of collision
    • B60W30/0956—Predicting travel path or likelihood of collision the prediction being responsive to traffic or environmental parameters
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to a dangerous target screening method based on a traffic target perception result, which comprises the following steps: 1) acquiring a sensing result based on a multi-sensor information fusion technology; 2) defining a traffic target as a longitudinal driving target or a transverse driving target; 3) dividing an interesting area, and calculating the time TTC of collision between the vehicle and a traffic target; 4) selecting a dangerous target CIPV1 from longitudinal driving targets in the region of interest, and selecting a dangerous target CIPV2 from transverse driving targets in the region of interest; 5) the hazardous target CIPV1 or hazardous target CIPV2 is selected as the most hazardous target CIPV output. The screening method divides the sensed traffic targets into longitudinal driving targets and transverse driving targets, and selects the most dangerous targets by respectively adopting a more targeted screening strategy according to the motion characteristics of each traffic target; therefore, the problems that the false detection rate and the missed detection rate of the dangerous target are high, the dangerous target is easy to jump, the output is unstable and the like are solved.

Description

Dangerous target screening method based on traffic target sensing result
Technical Field
The invention belongs to the technical field of automatic driving of automobiles, and particularly relates to a dangerous target screening method based on a traffic target sensing result.
Background
The intelligent driving auxiliary system can provide active safety early warning and safety auxiliary control for a driver, reduce misoperation of the driver and improve driving safety. The environment perception technology in the intelligent auxiliary driving system is a precondition for realizing key technologies such as vehicle motion control, path planning and decision making. The environment perception technology comprises traffic target perception, wherein the traffic target perception mainly comprises the steps of obtaining the position, the speed, the acceleration, the type of a target and the like of a traffic target through various sensors; screening dangerous targets in the driving process from a plurality of traffic targets is one of key technologies of the intelligent driving assistance system.
At present, the screening methods of dangerous targets mainly comprise two methods: firstly, the dangerous target of the vehicle road is screened depending on the lane line, and secondly, the dangerous target is screened depending on the motion state of the vehicle according to the running track of the vehicle. Chinese patent 201710696755.3 discloses a method and apparatus for detecting dangerous objects in a driving assistance system, wherein the method uses a preset camera as an origin, divides an image outside a vehicle body by a set horizontal distance threshold and a set vertical distance threshold, divides the image into 12 regions, and divides the 12 regions into 8 distance categories in consideration of the symmetry of the objects; according to the scheme, a uniform screening strategy is adopted in the screening process, the danger difference in the left and right directions caused by the steering motion of the target is not considered, so that the intelligent driving auxiliary system has the problems that the false detection rate and the missing detection rate of the dangerous target are high, the dangerous target is easy to jump and output unstably, and the like. Chinese patent 202010307385.1 automatic driving danger target determination method and device, the scheme is based on the motion state data of a first vehicle, sets a danger area and screens danger targets according to the driving track of the vehicle; however, in the scheme, the dangerous targets are screened under the condition of not considering the lane lines at all, so that when the vehicle turns in different ranges, the traffic targets of adjacent curves are mistakenly identified, and the vehicle is mistakenly braked.
In summary, in the screening process of the dangerous targets, the lane lines or the driving paths of the vehicle are excessively depended on, and meanwhile, a unified screening strategy is adopted, and the dangerous difference caused by the moving direction of the traffic target is not considered, so that the intelligent driving assistance system has the problems that the false detection rate and the missing detection rate of the dangerous targets are high, the dangerous targets are easy to jump and output unstably, and the like, further the vehicle has more false braking and missing braking, and the use experience of a user is seriously influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a dangerous target screening method based on a traffic target perception result, solve the problems of high false detection rate and high missed detection rate of the screening of dangerous targets at present, and achieve the effects of reducing false braking and missed braking of vehicles and improving the use experience of users.
In order to solve the technical problems, the invention adopts the following technical scheme:
a dangerous target screening method based on traffic target perception results comprises the following steps:
1) acquiring a sensing result based on a multi-sensor information fusion technology, wherein the sensing result comprises lane line information, vehicle information and target information corresponding to traffic targets around the vehicle;
2) defining the corresponding traffic target as a longitudinal driving target or a transverse driving target according to the target information;
3) dividing an interesting area according to the vehicle information, and calculating the Time To Collision (TTC) between the vehicle and the traffic target according to the vehicle information and the target information;
4) selecting a dangerous target CIPV1 from longitudinal driving targets in the region of interest and selecting a dangerous target CIPV2 from transverse driving targets in the region of interest according to the Time To Collision (TTC), the vehicle information, the lane line information and preset dangerous parameters;
5) the dangerous target CIPV1 or the dangerous target CIPV2 is selected as the most dangerous target CIPV output according to the time to collision TTC and a preset weight coefficient.
Further, in step 1), the lane line information includes a lane line of the own lane, a lane line of a left lane, and a lane line of a right lane; the vehicle information comprises vehicle speed, vehicle acceleration and vehicle turning radius, and the vehicle speed comprises vehicle longitudinal speed and vehicle transverse speed; the target information includes a target vehicle speed, a target acceleration, a longitudinal distance and a transverse distance between the corresponding traffic target and the host vehicle.
Further, in step 2), the longitudinal driving target refers to a traffic target which drives in the same direction or opposite direction to the host vehicle, and the transverse driving target refers to a traffic target with a transverse movement tendency.
Further, in the step 3), the time to collision TTC between the vehicle and the traffic target is calculated according to the vehicle information and the target information and a kinematic formula is adopted; in step 3), the operation of dividing the region of interest according to the vehicle information is as follows:
obtaining a driving direction line passing through the center of the vehicle according to the turning radius of the vehicle, and establishing a plane rectangular coordinate system taking the center of the vehicle as an origin and taking the front of the vehicle as a Y-axis forward direction;
l meters are taken out along the Y axis of an area obtained by respectively translating the driving direction line by W/2 meters to the positive direction and the negative direction of the X axis to serve as an interested area, the part of the interested area on the positive half shaft of the Y axis is a forward area, the length of the forward area on the Y axis is Lf meters, the part of the interested area on the negative half shaft of the Y axis is a backward area, and the length of the backward area on the Y axis is Lr meters.
Further, in step 4), the operation of selecting the dangerous object CIPV1 from the longitudinal driving objects in the region of interest is as follows:
respectively translating the driving direction line leftwards and rightwards by 1.5m to obtain a driving path of the vehicle, and acquiring the steering lamp information of the vehicle; judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the vehicle is driven forwards and the left turn light of the vehicle is on, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a vehicle driving path, the vehicle lane and a left lane as a dangerous target CIPV 1;
when the vehicle is driven forwards and the right steering lamp of the vehicle is turned on, selecting a longitudinal driving target with the minimum longitudinal distance with the vehicle from a forward area, a vehicle driving path, a common area of the vehicle lane and a right lane as a dangerous target CIPV 1;
when the vehicle is in forward driving and the steering lamp of the vehicle is not lighted, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a driving path of the vehicle and a lane as a dangerous target CIPV 1;
when the host vehicle is driven in reverse, a longitudinal driving target with the smallest longitudinal distance to the host vehicle is selected from a common region of a backward region and a driving path of the host vehicle as a dangerous target CIPV 1.
Further, in step 4), the risk parameters include a collision time boundary and a lateral distance boundary, the collision time boundary includes TLL, TLR, TRL, TRR, TCL and TCR, and the lateral distance boundary includes DLL, DLR, DRL, DRR, DCL and DCR.
Further, in step 4), the operation of selecting the dangerous object CIPV2 from the lateral driving objects in the region of interest is as follows:
judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the left turn light of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common region of the region of interest, the lane and the left lane is less than or equal to TLL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TLR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLR; selecting a corresponding primary target with the minimum Time To Collision (TTC) as a dangerous target CIPV 2;
when the right steering lamp of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common area of the interested area, the lane and the left lane is less than or equal to TRL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TRR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRR; selecting a preliminary target with the minimum TTC corresponding to the collision time as a dangerous target CIPV 2;
when the steering lamp of the vehicle is not on, taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interesting area, the lane and the left lane is less than or equal to TCL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TCR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCR; the preliminary target with the smallest time to collision TTC is selected as the hazard target CIPV 2.
Further, in step 4), when the lane line information is valid, the vehicle lane is a lane with the lane line of the vehicle lane as a boundary, the left lane is a lane with the lane line of the left lane as a boundary, and the right lane is a lane with the lane line of the right lane as a boundary;
when the lane line information is invalid, the vehicle traveling path is taken as the own lane, the vehicle traveling path is shifted to the left by 3 meters to be taken as the left lane, and the vehicle traveling path is shifted to the right by 3 meters to be taken as the right lane.
Further, in step 5), the weight coefficients include a right-turn weight coefficient atr, a left-turn weight coefficient atl, a reverse driving weight coefficient ar, and a forward straight-driving weight coefficient as.
Further, in step 5), the operation of selecting the dangerous target CIPV1 or the dangerous target CIPV2 as the most dangerous target CIPV output according to the time to collision TTC and the preset weight coefficient is as follows:
defining the time of collision between the vehicle and the longitudinal driving target as TTCCIPV1Defining the time of collision between the vehicle and the lateral running target as TTCCIPV2；
When the vehicle is running forward and the left turn signal is on, if atl × TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if atl × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if atr × TTC is present when the vehicle is traveling forward and the right turn light is onCIPV2≤TTCCIPV1Then select the hazardous target CIPV2 as the most hazardousOutputting a risk target CIPV; if atr × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if as × TTC when the vehicle is traveling forward and the turn signal is not onCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if as × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
when the vehicle is running in reverse, if ar is multiplied by TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if ar x TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output.
Compared with the prior art, the invention has the following beneficial effects:
1. the screening method divides the sensed traffic targets into longitudinal driving targets and transverse driving targets, and selects the most dangerous targets by respectively adopting a more targeted screening strategy according to the motion characteristics of each traffic target; therefore, the problems that the false detection rate and the missed detection rate of the dangerous target are high, the dangerous target is easy to jump, the output is unstable and the like are solved; in addition, the transverse driving target is considered independently, so that the identification of the transverse driving target is improved, and the risk of scenes such as 'ghost probes' is reduced.
2. The screening method determines the interested areas of the longitudinal driving target and the transverse driving target according to the motion state (back running, forward straight running, left turning and right turning) of the vehicle, and further screens based on the interested areas, so that the probability of mistaken identification and missed identification of the system can be effectively reduced, and the problem of too late identification of dangerous targets is solved.
3. According to the screening method, in the process of screening the dangerous targets CIPV1 from the longitudinal driving targets, the lane lines and the driving track of the vehicle are simultaneously referred, so that the failure of an algorithm caused by serious dependence on the lane lines when no lane lines exist is avoided, and meanwhile, the problems of mistaken identification and the like of the dangerous targets in the steering process caused by serious dependence on the driving track of the vehicle can be avoided; the advantages of the two methods can be effectively integrated, and the disadvantages of the two methods are avoided.
4. According to the screening method, when the dangerous target CIPV2 is screened, the method is irrelevant to a lane line, and only the transverse distance between a transverse driving target and the vehicle, the collision time and the driving direction of the vehicle are concerned; in the process of screening the dangerous target CIPV2 from the transverse driving targets, dangerous parameters under different motion states (reverse driving, forward straight driving, left turning and right turning) of the vehicle are set, so that the dangerous target CIPV2 can be screened more accurately.
5. According to the screening method, different weights are added to the collision time corresponding to the dangerous target CIPV2 according to different dangerous degrees of different motion states (reverse driving, forward straight driving, left turning and right turning) of the vehicle, so that the accuracy of screening the most dangerous target in different scenes can be effectively improved.
Drawings
Fig. 1 is a flowchart of a dangerous object screening method based on a traffic object perception result according to an embodiment;
FIG. 2 is a schematic diagram of a forward straight corresponding region of interest of a host vehicle and a travel path of the host vehicle according to an embodiment;
FIG. 3 is a schematic diagram of a region of interest corresponding to left turning of a host vehicle and a driving path of the host vehicle according to an embodiment;
fig. 4 is a schematic diagram of a region of interest corresponding to right turning of a host vehicle and a travel path of the host vehicle according to the embodiment.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Example (b):
referring to fig. 1, a method for screening dangerous targets based on traffic target perception results includes the following steps:
1) acquiring a sensing result based on a multi-sensor information fusion technology, wherein the sensing result comprises lane line information, vehicle information and target information corresponding to traffic targets around the vehicle;
the lane line information comprises a lane line of the lane, a lane line of a left lane and a lane line of a right lane; the vehicle information comprises the vehicle longitudinal speed, the vehicle transverse speed, the vehicle longitudinal acceleration, the vehicle transverse acceleration and the vehicle turning radius of the vehicle; the target information includes a target longitudinal speed, a target lateral speed, a target longitudinal acceleration, a target lateral acceleration, a longitudinal distance and a lateral distance between the corresponding traffic target and the vehicle.
2) Defining the corresponding traffic target as a longitudinal driving target or a transverse driving target according to the target information; the longitudinal driving target is a traffic target which drives in the same direction or opposite direction with the vehicle, and the transverse driving target is a traffic target with a transverse movement tendency.
3) Dividing an interesting area according to the vehicle information, and calculating the Time To Collision (TTC) between the vehicle and a traffic target according to the vehicle information and the target information based on a kinematic formula;
referring to fig. 2 to 4, the operation of dividing the region of interest according to the vehicle information is as follows: obtaining a driving direction line passing through the center of the vehicle according to the turning radius of the vehicle;
establishing a plane rectangular coordinate system which takes the center of the vehicle as an origin and takes the front of the vehicle as the forward direction of a Y axis; respectively translating the driving direction line to the positive direction and the negative direction of the X axis by W/2 meters to obtain an area, and intercepting L meters along the Y axis to serve as an interested area, wherein the total width of the interested area is W meters, and the total length of the interested area is L meters; the part of the region of interest on the Y-axis positive half shaft is a forward region, the length of the forward region on the Y-axis is Lf meters, the part of the region of interest on the Y-axis negative half shaft is a backward region, and the length of the backward region on the Y-axis is Lr meters;
in addition, the driving direction line is respectively translated to the left and the right by 1.5m to obtain a driving path of the vehicle; fig. 2-4 are schematic diagrams of a forward straight corresponding region of interest and a running path of the host vehicle, a left turn corresponding region of interest and a running path of the host vehicle, and a right turn corresponding region of interest and a running path of the host vehicle, respectively.
4) Selecting a dangerous target CIPV1 from longitudinal driving targets in the region of interest and selecting a dangerous target CIPV2 from transverse driving targets in the region of interest according to the time to collision TTC, the vehicle information, the lane line information and preset dangerous parameters; the risk parameters include a collision time boundary and a lateral distance boundary, the collision time boundary including TLL, TLR, TRL, TRR, TCL and TCR, the lateral distance boundary including DLL, DLR, DRL, DRR, DCL and DCR;
wherein TLL represents the collision time boundary of the longitudinal traveling target at the left part of the region of interest when the left turn light of the vehicle is on, TLR represents the collision time boundary of the longitudinal traveling target at the right part of the region of interest when the left turn light of the vehicle is on, TRL represents the collision time boundary of the longitudinal traveling target at the left part of the region of interest when the right turn light of the vehicle is on, TRR represents the collision time boundary of the longitudinal traveling target at the right part of the region of interest when the right turn light of the vehicle is on, TCL represents the collision time boundary of the longitudinal traveling target at the left part of the region of interest when the turn light of the vehicle is not on, and TCR represents the collision time boundary of the longitudinal traveling target at the right part of the region of interest when the turn light of the vehicle is not on; in the embodiment, values of TLL, TLR, TRL, TRR, TCL and TCR are all 3 seconds;
DLL represents the transverse distance boundary of the longitudinal driving target at the left part of the region of interest when the left turn light of the vehicle is on, DLR represents the transverse distance boundary of the longitudinal driving target at the right part of the region of interest when the left turn light of the vehicle is on, DRL represents the transverse distance boundary of the longitudinal driving target at the left part of the region of interest when the right turn light of the vehicle is on, DRR represents the transverse distance boundary of the longitudinal driving target at the right part of the region of interest when the right turn light of the vehicle is on, DCL represents the transverse distance boundary of the longitudinal driving target at the left part of the region of interest when the turn light of the vehicle is not on, and DCR represents the transverse distance boundary of the longitudinal driving target at the right part of the region of interest when the turn light of the vehicle is not on; in this embodiment, the DLL value is 4 meters, the DLR value is 2 meters, the DRL value is 2 meters, the DRR value is 4 meters, the DCL value is 3 meters, and the DCR value is 3 meters.
The selection of the dangerous object CIPV1 from the longitudinal driving objects in the region of interest is as follows:
respectively translating the driving direction line leftwards and rightwards by 1.5m to obtain a driving path of the vehicle, and acquiring the steering lamp information of the vehicle; judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the vehicle is driven forwards and the left turn light of the vehicle is on, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a vehicle driving path, the vehicle lane and a left lane as a dangerous target CIPV 1;
when the vehicle is driven forwards and the right steering lamp of the vehicle is turned on, selecting a longitudinal driving target with the minimum longitudinal distance with the vehicle from a forward area, a vehicle driving path, a common area of the vehicle lane and a right lane as a dangerous target CIPV 1;
when the vehicle is in forward driving and the steering lamp of the vehicle is not lighted, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a driving path of the vehicle and a lane as a dangerous target CIPV 1;
when the host vehicle is driven in reverse, a longitudinal driving target with the smallest longitudinal distance to the host vehicle is selected from a common region of a backward region and a driving path of the host vehicle as a dangerous target CIPV 1.
The selection of the dangerous object CIPV2 from the lateral driving objects in the region of interest is as follows:
judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the left turn light of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common region of the region of interest, the lane and the left lane is less than or equal to TLL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TLR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLR; selecting a corresponding primary target with the minimum Time To Collision (TTC) as a dangerous target CIPV 2;
when the right steering lamp of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common area of the interested area, the lane and the left lane is less than or equal to TRL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TRR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRR; selecting a preliminary target with the minimum TTC corresponding to the collision time as a dangerous target CIPV 2;
when the steering lamp of the vehicle is not on, taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interesting area, the lane and the left lane is less than or equal to TCL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TCR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCR; the preliminary target with the smallest time to collision TTC is selected as the hazard target CIPV 2.
When the lane line information is valid, the lane is a lane with the lane line of the lane as a boundary, the left lane is a lane with the lane line of the left lane as a boundary, and the right lane is a lane with the lane line of the right lane as a boundary;
when the lane line information is invalid, the vehicle traveling path is taken as the own lane, the vehicle traveling path is shifted to the left by 3 meters to be taken as the left lane, and the vehicle traveling path is shifted to the right by 3 meters to be taken as the right lane.
5) Selecting a dangerous target CIPV1 or a dangerous target CIPV2 as a most dangerous target CIPV output according to the time to collision TTC and a preset weight coefficient; the weight coefficients comprise a right turn weight coefficient atr, a left turn weight coefficient atl, a reverse driving weight coefficient ar and a forward straight driving weight coefficient as; in this embodiment, atr is 0.9, atl is 0.9, ar is 0.85, and as is 0.95.
The operation of selecting either the hazardous target CIPV1 or the hazardous target CIPV2 as the most hazardous target CIPV output is as follows:
defining the time of collision between the vehicle and a longitudinal running target as TTCCIPV1Defining the time of collision between the vehicle and the transverse driving target as TTCCIPV2；
When the vehicle is running forward and the left turn light is on, if atl × TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if atl × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if atr × TTC is present when the vehicle is traveling forward and the right turn light is onCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if atr × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if as × TTC when the vehicle is traveling forward and the turn signal is not onCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if as × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if the vehicle is running in reverse, if ar is multiplied by TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if ar x TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.

Claims (10)

1. A dangerous target screening method based on traffic target perception results is characterized in that: the method comprises the following steps:
1) acquiring a sensing result based on a multi-sensor information fusion technology, wherein the sensing result comprises lane line information, vehicle information and target information corresponding to traffic targets around the vehicle;
2) defining the corresponding traffic target as a longitudinal driving target or a transverse driving target according to the target information;
3) dividing an interesting area according to the vehicle information, and calculating the Time To Collision (TTC) between the vehicle and the traffic target according to the vehicle information and the target information;
4) selecting a dangerous target CIPV1 from longitudinal driving targets in the region of interest and selecting a dangerous target CIPV2 from transverse driving targets in the region of interest according to the time to collision TTC, the vehicle information, the lane line information and preset dangerous parameters;
5) the dangerous target CIPV1 or the dangerous target CIPV2 is selected as the most dangerous target CIPV output according to the time to collision TTC and a preset weight coefficient.
2. The method for screening dangerous targets based on traffic target perception results according to claim 1, wherein: in the step 1), the lane line information comprises a lane line of the lane, a lane line of a left lane and a lane line of a right lane; the vehicle information comprises vehicle speed, vehicle acceleration and vehicle turning radius, and the vehicle speed comprises longitudinal vehicle speed and transverse vehicle speed; the target information includes a target vehicle speed, a target acceleration, a longitudinal distance and a transverse distance between the corresponding traffic target and the host vehicle.
3. The method for screening dangerous targets based on traffic target perception results according to claim 1, wherein: in step 2), the longitudinal driving target is a traffic target which runs in the same direction or opposite direction to the vehicle, and the transverse driving target is a traffic target with a transverse movement tendency.
4. The method for screening dangerous targets based on traffic target perception results according to claim 2, wherein: in the step 3), calculating the time TTC of collision between the vehicle and the traffic target according to the vehicle information and the target information by adopting a kinematic formula; in step 3), the operation of dividing the region of interest according to the vehicle information is as follows:
obtaining a driving direction line passing through the center of the vehicle according to the turning radius of the vehicle, and establishing a plane rectangular coordinate system taking the center of the vehicle as an origin and taking the front of the vehicle as a Y-axis forward direction;
l meters are taken out along the Y axis of an area obtained by respectively translating the driving direction line by W/2 meters to the positive direction and the negative direction of the X axis to serve as an interested area, the part of the interested area on the positive half shaft of the Y axis is a forward area, the length of the forward area on the Y axis is Lf meters, the part of the interested area on the negative half shaft of the Y axis is a backward area, and the length of the backward area on the Y axis is Lr meters.
5. The method for screening dangerous targets based on traffic target perception results according to claim 4, wherein: in step 4), the operation of selecting the dangerous target CIPV1 from the longitudinal driving targets in the region of interest is as follows:
respectively translating the driving direction line leftwards and rightwards by 1.5m to obtain a driving path of the vehicle, and acquiring the steering lamp information of the vehicle; judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the vehicle is driven forwards and the left turn light of the vehicle is on, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a vehicle driving path, the vehicle lane and a left lane as a dangerous target CIPV 1;
when the vehicle is driven forwards and the right steering lamp of the vehicle is turned on, selecting a longitudinal driving target with the minimum longitudinal distance with the vehicle from a forward area, a vehicle driving path, a common area of the vehicle lane and a right lane as a dangerous target CIPV 1;
when the vehicle is in forward driving and the steering lamp of the vehicle is not turned on, selecting a longitudinal driving target with the minimum longitudinal distance from the vehicle from a common region of a forward region, a driving path of the vehicle and a lane as a dangerous target CIPV 1;
when the host vehicle is driven in reverse, a longitudinal driving target with the smallest longitudinal distance to the host vehicle is selected from a common region of a backward region and a driving path of the host vehicle as a dangerous target CIPV 1.
6. The method for screening dangerous targets based on traffic target perception results according to claim 5, wherein: in step 4), the risk parameters include a collision time boundary and a lateral distance boundary, the collision time boundary includes TLL, TLR, TRL, TRR, TCL and TCR, and the lateral distance boundary includes DLL, DLR, DRL, DRR, DCL and DCR.
7. The method for screening dangerous targets based on traffic target perception results according to claim 6, wherein: in step 4), the operation of selecting the dangerous target CIPV2 from the lateral driving targets in the region of interest is as follows:
judging whether the vehicle runs in a reverse mode or in a forward mode according to the longitudinal vehicle speed of the vehicle, when the longitudinal vehicle speed Ve of the vehicle is larger than or equal to 0km/h, the vehicle runs in the forward mode, and the region of interest of the vehicle is a forward region; when the longitudinal speed Ve of the vehicle is less than 0km/h, the vehicle runs in a reverse mode, and the region of interest of the vehicle is a backward region;
when the left turn light of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common region of the region of interest, the lane and the left lane is less than or equal to TLL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TLR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DLR; selecting a corresponding primary target with the minimum Time To Collision (TTC) as a dangerous target CIPV 2;
when the right steering lamp of the vehicle is turned on, taking a transverse driving target as a preliminary target, wherein the collision time TTC corresponding to the common area of the interested area, the lane and the left lane is less than or equal to TRL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TRR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DRR; selecting a preliminary target with the minimum TTC corresponding to the collision time as a dangerous target CIPV 2;
when the steering lamp of the vehicle is not on, taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interesting area, the lane and the left lane is less than or equal to TCL, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCL; taking a transverse driving target as a preliminary target, wherein the corresponding collision time TTC in the common area of the interested area, the lane and the right lane is less than or equal to TCR, and the absolute value of the transverse distance between the transverse driving target and the vehicle is less than DCR; the preliminary target with the smallest time to collision TTC is selected as the hazard target CIPV 2.
8. The method for screening dangerous targets based on traffic target perception results according to claim 7, wherein: in step 4), when the lane line information is valid, the lane is a lane with the lane line of the lane as a boundary, the left lane is a lane with the lane line of the left lane as a boundary, and the right lane is a lane with the lane line of the right lane as a boundary;
when the lane line information is invalid, the vehicle traveling path is taken as the own lane, the vehicle traveling path is shifted to the left by 3 meters to be taken as the left lane, and the vehicle traveling path is shifted to the right by 3 meters to be taken as the right lane.
9. The method for screening dangerous targets based on traffic target perception results according to claim 8, wherein: in step 5), the weight coefficients include a right-turn weight coefficient atr, a left-turn weight coefficient atl, a reverse driving weight coefficient ar, and a forward straight-driving weight coefficient as.
10. The method for screening dangerous targets based on traffic target perception results according to claim 9, wherein: in step 5), the operation of selecting the dangerous target CIPV1 or the dangerous target CIPV2 as the most dangerous target CIPV output according to the time to collision TTC and the preset weight coefficient is as follows:
defining the time of collision between the vehicle and the longitudinal driving target as TTCCIPV1Defining the time of collision between the vehicle and the lateral running target as TTCCIPV2；
When the vehicle is running forward and the left turn light is on, if atl × TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if atl × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if atr × TTC is present when the vehicle is traveling forward and the right turn light is onCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if atr × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if as × TTC when the vehicle is traveling forward and the turn signal is not onCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if as × TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output;
if the vehicle is running in reverse, if ar is multiplied by TTCCIPV2≤TTCCIPV1Then the hazardous target CIPV2 is selected as the most hazardous target CIPV output; if ar x TTCCIPV2＞TTCCIPV1Then the hazardous target CIPV1 is selected as the most hazardous target CIPV output.
CN202210226337.9A 2022-03-09 2022-03-09 Dangerous target screening method based on traffic target perception result Active CN114537385B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210226337.9A CN114537385B (en) 2022-03-09 2022-03-09 Dangerous target screening method based on traffic target perception result

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210226337.9A CN114537385B (en) 2022-03-09 2022-03-09 Dangerous target screening method based on traffic target perception result

Publications (2)

Publication Number Publication Date
CN114537385A true CN114537385A (en) 2022-05-27
CN114537385B CN114537385B (en) 2024-05-07

Family

ID=81664104

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210226337.9A Active CN114537385B (en) 2022-03-09 2022-03-09 Dangerous target screening method based on traffic target perception result

Country Status (1)

Country Link
CN (1) CN114537385B (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060190175A1 (en) * 2003-01-28 2006-08-24 Toyoto Jidosha Kabushiki Kaisha Collision predicting apparatus and collision predicting method
CN109849910A (en) * 2018-12-21 2019-06-07 重庆长安汽车股份有限公司 Automatic driving vehicle multiobjective decision-making control method, device and computer readable storage medium
CN110588648A (en) * 2019-10-25 2019-12-20 北京行易道科技有限公司 Method and device for identifying collision danger during vehicle running, vehicle and storage medium
CN112026756A (en) * 2020-08-31 2020-12-04 重庆长安汽车股份有限公司 Dangerous target selection method and system based on tracking target and vehicle
CN112124313A (en) * 2020-09-29 2020-12-25 重庆长安汽车股份有限公司 Target vehicle selection method based on automatic driving lane changing, vehicle and storage medium
CN112634354A (en) * 2020-12-21 2021-04-09 紫清智行科技(北京)有限公司 Road side sensor-based networking automatic driving risk assessment method and device
US20210261119A1 (en) * 2020-02-21 2021-08-26 Toyota Jidosha Kabushiki Kaisha Driving assist system
CN113370977A (en) * 2021-05-06 2021-09-10 上海大学 Intelligent vehicle forward collision early warning method and system based on vision
US20210291825A1 (en) * 2020-03-18 2021-09-23 Denso Corporation Systems and methods for adapting activation of alerts according to curvature of a target path
US20210300360A1 (en) * 2020-03-27 2021-09-30 Aptiv Technologies Limited Warning System for a Host Automotive Vehicle
US20210394752A1 (en) * 2018-09-28 2021-12-23 Hitachi Automotive Systems, Ltd. Traveling Control Device, Vehicle, and Traveling Control Method
CN114132311A (en) * 2021-12-28 2022-03-04 联创汽车电子有限公司 Method and module for screening dangerous targets for automatic emergency braking of vehicle

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060190175A1 (en) * 2003-01-28 2006-08-24 Toyoto Jidosha Kabushiki Kaisha Collision predicting apparatus and collision predicting method
US20210394752A1 (en) * 2018-09-28 2021-12-23 Hitachi Automotive Systems, Ltd. Traveling Control Device, Vehicle, and Traveling Control Method
CN109849910A (en) * 2018-12-21 2019-06-07 重庆长安汽车股份有限公司 Automatic driving vehicle multiobjective decision-making control method, device and computer readable storage medium
CN110588648A (en) * 2019-10-25 2019-12-20 北京行易道科技有限公司 Method and device for identifying collision danger during vehicle running, vehicle and storage medium
US20210261119A1 (en) * 2020-02-21 2021-08-26 Toyota Jidosha Kabushiki Kaisha Driving assist system
US20210291825A1 (en) * 2020-03-18 2021-09-23 Denso Corporation Systems and methods for adapting activation of alerts according to curvature of a target path
US20210300360A1 (en) * 2020-03-27 2021-09-30 Aptiv Technologies Limited Warning System for a Host Automotive Vehicle
CN112026756A (en) * 2020-08-31 2020-12-04 重庆长安汽车股份有限公司 Dangerous target selection method and system based on tracking target and vehicle
CN112124313A (en) * 2020-09-29 2020-12-25 重庆长安汽车股份有限公司 Target vehicle selection method based on automatic driving lane changing, vehicle and storage medium
CN112634354A (en) * 2020-12-21 2021-04-09 紫清智行科技(北京)有限公司 Road side sensor-based networking automatic driving risk assessment method and device
CN113370977A (en) * 2021-05-06 2021-09-10 上海大学 Intelligent vehicle forward collision early warning method and system based on vision
CN114132311A (en) * 2021-12-28 2022-03-04 联创汽车电子有限公司 Method and module for screening dangerous targets for automatic emergency braking of vehicle

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘军;高雪婷;王利明;晏晓娟;: "基于OpenCV的前方车辆检测和前撞预警算法研究", 汽车技术, no. 06, 24 June 2017 (2017-06-24) *
孟柯;吴超仲;陈志军;吕能超;邓超;刘钢;: "人车碰撞风险识别及智能车辆控制系统", 交通信息与安全, no. 06, 28 December 2016 (2016-12-28) *

Also Published As

Publication number Publication date
CN114537385B (en) 2024-05-07

Similar Documents

Publication Publication Date Title
JP3860061B2 (en) Outside-of-vehicle monitoring device and travel control device equipped with this out-of-vehicle monitoring device
US9613533B2 (en) Parking space detector
JP7103753B2 (en) Collision avoidance device
US7742864B2 (en) Vehicle surroundings monitoring apparatus and traveling control system incorporating the apparatus
JP3845548B2 (en) Control system for speed and inter-vehicle distance when changing lanes of an automatic vehicle
US10901078B2 (en) Monitoring device and monitoring method
CN109733392B (en) Obstacle avoidance method and device
US20040176900A1 (en) Vehicle drive assist system
CN107010064A (en) A kind of fleet's formation drive manner and system
CN110816540B (en) Traffic jam determining method, device and system and vehicle
JP4442520B2 (en) Course estimation device for vehicle
US20220135165A1 (en) Drive assistance device for saddle riding-type vehicle
JP4541609B2 (en) Stop line recognition device and vehicle driving support device using the stop line recognition device
CN112026761A (en) Automobile auxiliary driving method based on data sharing
CN108021861A (en) A kind of intelligent vehicle right-hand bend object detection method based on machine vision
JP2002160598A (en) Outside car control device
CN112277799B (en) Automobile blind area detection alarm method and system
CN114537385B (en) Dangerous target screening method based on traffic target perception result
JP2006160032A (en) Driving state determination device and its method
CN113844439B (en) Low-speed auxiliary brake auxiliary decision-making method, system and computer readable storage medium for auxiliary driving
JP2004164187A (en) Vehicle warning device
JP6206036B2 (en) Parking lot judgment device, parking lot judgment method
KR20200119068A (en) Vehicle and method for controlling thereof
JP5682302B2 (en) Traveling road estimation device, method and program
JP2000057498A (en) Method for controlling drive of vehicle

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant