CN114194215B - Intelligent vehicle obstacle avoidance lane change track planning method and system - Google Patents
Intelligent vehicle obstacle avoidance lane change track planning method and system Download PDFInfo
- Publication number
- CN114194215B CN114194215B CN202111661902.6A CN202111661902A CN114194215B CN 114194215 B CN114194215 B CN 114194215B CN 202111661902 A CN202111661902 A CN 202111661902A CN 114194215 B CN114194215 B CN 114194215B
- Authority
- CN
- China
- Prior art keywords
- track
- vehicle
- obstacle avoidance
- lane change
- index
- 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
- 230000008859 change Effects 0.000 title claims abstract description 55
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 230000001133 acceleration Effects 0.000 claims description 37
- 238000012937 correction Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 230000036461 convulsion Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 2
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0011—Planning or execution of driving tasks involving control alternatives for a single driving scenario, e.g. planning several paths to avoid obstacles
-
- 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
- B60W30/0953—Predicting travel path or likelihood of collision the prediction being responsive to vehicle dynamic 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
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—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
- B60W2554/40—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)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
Abstract
The application discloses an intelligent vehicle obstacle avoidance track planning method and system, which are used for generating a feasible track cluster based on an initial return point of an operation stability limit and a polynomial curve according to road environment, obstacle information and current vehicle speed, carrying out pre-collision detection on track replacement in the feasible track cluster, and screening and removing tracks which do not meet the pre-collision detection condition to obtain a collision-free track cluster; establishing a cost function of three evaluation indexes of comfort, obstacle avoidance efficiency and sideslip on the basis of a collision-free track cluster; and determining weights of three evaluation indexes by fuzzy reasoning, and searching out an optimal obstacle avoidance lane change return point by solving a multi-objective optimization problem, namely planning a final obstacle avoidance lane change track. Meanwhile, the application also provides an intelligent vehicle obstacle avoidance and lane change track planning system, which can maximize performance indexes of the track, such as comfort, obstacle avoidance efficiency and the like, and effectively improve riding experience of passengers while taking safety, instantaneity and curvature continuity into consideration.
Description
Technical Field
The invention belongs to the technical field of intelligent driving vehicle planning, and particularly relates to an intelligent vehicle obstacle avoidance lane change track planning method.
Background
At present, the maintenance amount of motor vehicles in China is in an increasing trend year by year, so that the problems of traffic safety, road congestion and the like are increasingly outstanding. The research shows that the artifacts such as inattention of drivers or insufficient driving experience are the main reasons for traffic accidents. Thus, intelligent driving vehicles are rapidly evolving and advancing, which can bear more burden and pressure on human drivers, thereby improving road safety, key technologies including perception, positioning, decision making, planning and control.
At present, active obstacle avoidance strategies of intelligent vehicles are mainly divided into two types, namely braking obstacle avoidance and steering obstacle avoidance. However, when the vehicle is running at a high speed, the active obstacle avoidance based on braking requires a longer braking distance, and still has high collision risk, and even rear-end collision of the rear vehicle can be caused. Therefore, collision avoidance by braking is more suitable for urban roads with low vehicle speeds and more obstacle vehicles; and if the vehicle is on a highway with a clear lane, steering is more suitable for avoiding collision. Therefore, when an emergency obstacle avoidance is performed, it is important to rapidly plan a reasonable road changing path.
The intelligent vehicle motion planning refers to searching a track with detailed path and speed information in corresponding time and space according to the behavior intention input by a decision layer, meeting all constraint conditions, and finally sending the track to a control module for tracking. Motion planning originally originated in the robot field and is mainly divided into three types: a method based on sampling, a method based on curve interpolation and a method based on numerical optimization. Wherein, the real-time property of the sampling-based method is general and the generated curve may have curvature mutation; the curve interpolation method has good real-time performance and continuous curvature, but has poor flexibility; the numerical optimization method needs to deal with the multi-constraint search problem, and has high calculation cost. Each planning method has the characteristics, and the single method cannot realize the optimization.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides an intelligent vehicle obstacle avoidance lane change track planning method and system. The safety, the curvature continuity and the real-time performance are guaranteed, so that the vehicle can avoid the obstacle smoothly, the requirements of passengers are met to the maximum extent, and the flexibility of planning the track is improved.
The technical scheme adopted by the invention is as follows:
An intelligent vehicle obstacle avoidance lane change track planning method comprises the following steps:
S1, obtaining a generalized lane change track by adopting a polynomial curve, obtaining an expression of reference lateral acceleration relative to time from the generalized lane change track, obtaining a maximum lateral acceleration a y_rmax under the reference track by obtaining an extremum from the reference lateral acceleration, and defining a threshold value by combining the current road surface condition with a lateral acceleration related standard:
i a y_rmax|≤aymax =fμg, where the coefficient f <1
Wherein a ymax is the maximum lateral acceleration, the coefficient f <1, mu is the road adhesion coefficient; g is gravity acceleration;
calculating a lane change starting return point according to the maximum lateral acceleration threshold value; equidistant iteration is carried out on the channel changing initial correction points in the transverse direction, N-1 channel changing correction points are obtained through sampling, and the N-1 channel changing correction points are brought into a polynomial curve generalized track formula to obtain a feasible track cluster;
s2, pre-collision detection is carried out on N track changing tracks in the feasible track clusters, tracks which can collide without meeting the pre-collision detection conditions are screened and removed, and collision-free track clusters are obtained;
S3, establishing a cost function of three evaluation indexes, namely a comfort index, an obstacle avoidance efficiency index and a sideslip index, on the basis of a collision-free track cluster; and determining weights of three evaluation indexes, namely a comfort index, an obstacle avoidance efficiency index and a sideslip index by adopting fuzzy reasoning, and finally searching out an optimal obstacle avoidance lane change return positive point X T_R by solving a multi-objective optimization problem, namely planning a final obstacle avoidance lane change track.
Further, the cost function established in S3 is expressed as:
Wherein w C、wE、wS is the weight value of the comfort index, the obstacle avoidance efficiency index and the sideslip index respectively; j C is a comfort index, J E is an obstacle avoidance efficiency index, and J S is a sideslip index.
Further, the method for determining the weights of the three evaluation indexes, namely the comfort index, the obstacle avoidance efficiency index and the sideslip index by adopting fuzzy reasoning comprises the following steps:
Firstly, representing the dangerous degree by adopting the inverse TTC of the pre-collision time, and representing the current road surface condition by adopting the road surface adhesion coefficient mu; taking the reciprocal pre-collision time TTC -1 and the road adhesion coefficient mu as input and w C、wE、wS as output; the following fuzzy rules are designed:
Rule 1) if TTC -1is B andμis B,then(wC is B)(wE is S)(wS is S)
Rule 2) if TTC -1is B andμis S,then(wC is S)(wE is S)(wS is B)
Rule 3) if TTC -1is M andμis B,then(wC is M)(wE is M)(wS is S)
Rule 4) if TTC -1is M andμis S,then(wC is S)(wE is M)(wS is M
Rule 5) if TTC -1is S andμis B,then(wC is S)(wE is B)(wS is S
Rule 6) if TTC -1is S andμis S,then(wC is S)(wE is M)(wS is M
Wherein S is small, M is medium, and B is large.
Further, the comfort index, obstacle avoidance efficiency index, and sideslip index are respectively expressed as follows:
JE=T
Wherein: j y_r is the desired lateral jerk; a y_r is the desired lateral acceleration; t is the time required for the whole process.
Further, the pre-collision detection procedure in S2 is as follows:
1) When the right front corner of the own vehicle is equal to the abscissa of the front obstacle vehicle tail, i.e., X (a 1) =x (B), a collision starts, which is denoted as t1.
In the method, in the process of the invention,The course angle at the time t can be calculated by a track formula. x f(t1)、Bf is the position of the mass center of the front obstacle vehicle and the distance between the mass center and the tail of the front obstacle vehicle, respectively, and can be obtained by sensing information. A ego、Wego is the distance from the center of mass to the head of the vehicle and the width of the vehicle. Solving to obtain t 1 as a pre-collision detection starting time point.
2) When the right rear corner of the own vehicle is equal to the abscissa of the front obstacle vehicle tail, i.e., X (a 2) =x (B), the risk of collision is completely removed, which is denoted as t2.
Wherein B ego is the distance from the center of mass to the tail of the vehicle. Solving to obtain t 2 as a collision detection termination point.
3) At time point t 1、t2, a pre-crash detection is performed. The collision-free condition is that the vertical distance from the left rear corner point of the front obstacle vehicle to the vehicle axis is greater than a set threshold value, namely: d CB≥dmin.
Wherein d min is the minimum value of the vertical distance, and the track which can collide without meeting the pre-collision detection condition is screened and removed to obtain a collision-free track cluster.
Further, the generalized lane change track in S1:
Wherein: establishing a coordinate system by using a self-vehicle, wherein the vehicle advancing direction is an x-axis, the direction vertical to the vehicle body is a y-axis, and x (t) and y (t) are respectively an x coordinate and a y coordinate at the moment t; v is the vehicle speed, w is the lane width, t is the time variable, and X T is the desired position of the lane change return point.
Further, the expression of the reference lateral acceleration with respect to time is obtained by solving the two-order derivative of the generalized lane-change trajectory:
obtaining the maximum lateral acceleration under the reference track by the extremum value:
Time,/>
Further, calculating a lane change starting return point according to the maximum lateral acceleration threshold value:
And (3) carrying out equidistant iteration on the channel changing initial return points in the transverse direction, sampling to obtain N-1 channel changing return points, and taking the N-1 channel changing return points into a polynomial curve generalized track formula to obtain a feasible track cluster.
XTn=XT1+(n-1)d,n=2,3,…,N
Wherein X Tn is the position of the n-th lane change return point, and d is the iteration distance.
An intelligent vehicle obstacle avoidance lane change track planning system comprises an environment sensing module, a candidate track generating module, a scene analyzing module and a candidate track screening module;
The environment sensing module is used for acquiring road environment information and obstacle vehicle motion information and inputting the acquired information to other three modules;
The candidate track generation module generates a track changing track with a stability limit based on a polynomial curve by a maximum lateral acceleration threshold according to road environment information and combining vehicle state information, generates a feasible track cluster through iteration, and inputs the feasible track cluster to the candidate track screening module;
The scene analysis module analyzes the current road surface condition and the dangerous degree according to the road environment information and the obstacle vehicle motion information, and obtains the weight value of each evaluation index in the current scene through fuzzy decision; inputting the weight value to a candidate track screening module;
The candidate track screening module performs pre-collision detection by combining obstacle vehicle motion information, screens out tracks which are likely to collide to obtain collision-free track clusters, and further establishes cost functions of three evaluation indexes of comfort, obstacle avoidance efficiency and sideslip index; and searching to obtain an optimal return point based on the weight value corresponding to each evaluation index output by the scene analysis module, and planning a final obstacle avoidance track.
Further, the environment sensing module specifically comprises various environment sensing sensors such as cameras, laser radars, millimeter wave radars, GPS and inertial navigation.
The invention has the following beneficial effects:
The invention relates to an intelligent vehicle obstacle avoidance lane change track planning method and system. The multi-objective optimization track planning method is designed on the basis of the curve interpolation method by combining the advantages of the sampling method and the numerical optimization method, the problem that target points commonly existing in the curve interpolation method are difficult to select is effectively solved, and the flexibility of the planned track is improved. In the aspect of practical application, the track planning method provided by the invention can maximize the performance indexes of the track, such as comfort, obstacle avoidance efficiency and the like, and effectively improve the riding experience of passengers while taking the safety, the instantaneity and the curvature continuity into consideration.
Drawings
FIG. 1 is a general block diagram of an obstacle avoidance lane change trajectory planning system;
FIG. 2 is a schematic diagram of polynomial curve based feasible trajectory cluster generation;
FIG. 3 is a schematic diagram of collision-free trajectory cluster generation;
FIG. 4 is a schematic diagram of generation of an optimal obstacle avoidance lane change trajectory;
Fig. 5 and 6 are schematic views of a pre-collision detection flow.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in FIG. 1, the invention provides an intelligent vehicle obstacle avoidance lane change track planning system. Wherein the overall structure of the system comprises: the system comprises an environment sensing module, a candidate track generating module, a scene analyzing module and a candidate track screening module.
The environment sensing module is used for acquiring road environment information and obstacle vehicle motion information and inputting the acquired information to the other three modules. The environment sensing module specifically comprises various environment sensing sensors such as cameras, laser radars, millimeter wave radars, GPS, inertial navigation and the like. The road environment information comprises a lane center line, a lane width, the geometric dimensions of obstacle vehicles and the like; the obstacle vehicle motion information includes a position, a speed, and the like at each time.
And the candidate track generation module generates a steering stability limit track change track based on a polynomial curve by a maximum lateral acceleration threshold according to road environment information and combining vehicle state information, generates a feasible track cluster through iteration, and inputs the feasible track cluster to the candidate track screening module.
The scene analysis module analyzes the current road surface condition and the dangerous degree according to the road environment information and the obstacle vehicle motion information, and obtains the weight value of each evaluation index in the current scene through fuzzy decision. And finally, inputting the weight value into a candidate track screening module.
The candidate track screening module performs pre-collision detection by combining obstacle vehicle motion information, screens out tracks which are likely to collide to obtain collision-free track clusters, and further establishes cost functions of three evaluation indexes of comfort, obstacle avoidance efficiency and sideslip index; and searching to obtain an optimal return point based on the weight value corresponding to each evaluation index output by the scene analysis module, and planning a final obstacle avoidance track.
An intelligent vehicle obstacle avoidance lane change track planning method comprises the following steps:
s1, obtaining lane information and vehicle state information based on a sensing sensor. A polynomial curve is adopted to obtain a generalized lane change track:
Wherein: establishing a coordinate system by using a self-vehicle, wherein the vehicle advancing direction is an x-axis, the direction vertical to the vehicle body is a y-axis, and x (t) and y (t) are respectively an x coordinate and a y coordinate at the moment t; v is the vehicle speed, w is the lane width, t is the time variable, and X T is the desired position of the lane change return point.
Wherein, in order to maximize the longitudinal comfort of the vehicle, the above ensures that the longitudinal acceleration (d 2x/dt2) is 0, so the planned vehicle speed is constant in the ground coordinate system, namely: dx/dt=v, X T =vt, T being the time required for the whole course of the obstacle avoidance transition. By adjusting the position of the return point X T, different track changing tracks can be obtained. In order to determine the specific position of the lane changing positive point X T, the following iterative and searching method is adopted to find the optimal obstacle avoidance lane changing positive point X T_R.
Taking the two derivatives from the above trajectory curve expression yields an expression of the reference lateral acceleration with respect to time:
obtaining the maximum lateral acceleration under the reference track by the extremum value:
Time,/>
Since the lateral acceleration reflects the steering stability of the vehicle at the time of track following, it is necessary to ensure that it is within a reasonable range, otherwise the track cannot be traced. The threshold value is defined by the current road surface condition in combination with the lateral acceleration related criterion:
|ay_rmax|≤aymax=fμg,
Wherein a ymax is the maximum lateral acceleration, the coefficient f <1, mu is the road adhesion coefficient; g is gravitational acceleration.
Calculating a lane change starting return point according to the maximum lateral acceleration threshold value:
The initial return point obtained according to the formula is used for generating a first lane change track, namely a steering stability limit lane change track, which represents the maximum steering obstacle avoidance potential of the vehicle under the current road surface condition and the vehicle speed. The farther the return point is from the rear, the smaller the reference lateral acceleration limit of the track is, and the more stable the vehicle tracking is.
Equidistant iteration is carried out on the initial return points of the channel change in the transverse direction, and (N-1) channel change return points are obtained through sampling and are brought into a polynomial curve generalized track formula to obtain a feasible track cluster, as shown in figure 2.
XTn=XT1+(n-1)d,n=2,3,…,N
Wherein X Tn is the position of the n-th lane change return point, and d is the iteration distance.
S2, searching N track changing tracks in the feasible track clusters to find an optimal track. The preliminary screening method is pre-collision detection. The information obtained by the sensing sensor predicts the track of the front vehicle, solves the possible collision moment according to the relative motion information between the vehicle and the obstacle vehicle by combining the expected position of the vehicle in each feasible track at the future moment, and defines the pre-collision detection condition according to the geometric characteristics of the vehicle and the obstacle vehicle, as shown in fig. 5 and 6.
Assuming that the obstacle avoidance is performed to the left, the pre-collision detection flow is as follows:
1) When the right front corner of the own vehicle is equal to the abscissa of the front obstacle vehicle tail, i.e., X (a 1) =x (B), a collision starts, which is denoted as t1.
In the method, in the process of the invention,The course angle at the time t can be calculated by a track formula. x f(t1)、Bf is the position of the mass center of the front obstacle vehicle and the distance between the mass center and the tail of the front obstacle vehicle, respectively, and can be obtained by sensing information. A ego、Wego is the distance from the center of mass to the head of the vehicle and the width of the vehicle. Solving to obtain t 1 as a pre-collision detection starting time point.
2) When the right rear corner of the own vehicle is equal to the abscissa of the front obstacle vehicle tail, i.e., X (a 2) =x (B), the risk of collision is completely removed, which is denoted as t2.
Wherein B ego is the distance from the center of mass to the tail of the vehicle. Solving to obtain t 2 as a collision detection termination point.
3) At time point t 1、t2, a pre-crash detection is performed. The collision-free condition is that the vertical distance from the left rear corner point of the front obstacle vehicle to the vehicle axis is greater than a set threshold value, namely: d CB≥dmin.
Wherein d min is the minimum value of the vertical distance, and the track which can collide without meeting the pre-collision detection condition is screened and removed, so as to obtain a collision-free track cluster, as shown in fig. 3.
S3, establishing cost functions of three evaluation indexes on the basis of collision-free track clusters, and obtaining an optimal obstacle avoidance track change track through searching, wherein the three evaluation indexes are comfort indexes, obstacle avoidance efficiency indexes and sideslip indexes respectively, and are expressed as follows:
wherein/>
JE=T
Wherein: j C is a comfort index, J y_r is expressed as the derivative of the desired lateral acceleration, i.e. lateral jerk; a y_r is the desired lateral acceleration; j E is an obstacle avoidance efficiency index, and is expressed as time T required by the whole process; j S is a sideslip performance index, expressed as the utilization of lateral acceleration under the current road conditions.
Based on the comfort index, the obstacle avoidance efficiency index and the sideslip index, the following cost function is established:
Wherein w C、wE、wS is the weight value of the comfort index, the obstacle avoidance efficiency index and the sideslip index respectively.
Wherein the three weight values are related to the current hazard level and the road surface condition. For example, when the danger is high and the distance from the front obstacle vehicle is relatively short, the psychological stress of the passenger is maximum, and the obstacle vehicle needs to be avoided as soon as possible, so the weight value of the obstacle avoidance efficiency should be higher; when the road surface condition is not good, the sideslip index of the vehicle during obstacle avoidance cannot be too high, otherwise, the risk of instability exists; finally, when the risk level is not too high and the road surface condition is good, the passenger does not have too much psychological stress, the steering stability of the vehicle is good, and therefore the weight of the comfort index can be higher. Because each weight value is related to the current specific scene, but no quantitative relation exists, fuzzy reasoning is adopted to determine the specific weights of the three indexes.
Road information and obstacle vehicle information are obtained by the sensing sensor, and the current road surface condition and the dangerous degree are analyzed.
The risk level is characterized by the reciprocal of the time to pre-collision (TTC):
Wherein V ego is the current own vehicle speed, and V f is the current obstacle vehicle speed; d ob is the distance from the obstacle vehicle in front at this point. The current road surface condition is characterized by the road adhesion coefficient μ.
The following fuzzy rule is designed. Inputting a pre-collision time reciprocal TTC -1 and a road adhesion coefficient mu; the output is w C、wE、wS.
Rule 1) if TTC -1is B andμis B,then(wC is B)(wE is S)(wS is S)
Rule 2) if TTC -1is B andμis S,then(wC is S)(wE is S)(wS is B)
Rule 3) if TTC -1is M andμis B,then(wC is M)(wE is M)(wS is S)
Rule 4) if TTC -1is M andμis S,then(wC is S)(wE is M)(wS is M
Rule 5) if TTC -1is S andμis B,then(wC is S)(wE is B)(wS is S
Rule 6) if TTC -1is S andμis S,then(wC is S)(wE is M)(wS is M
Wherein S is small, M is medium, and B is large.
And inputting each weight value determined by fuzzy reasoning into a candidate track screening module, obtaining a specific cost function according to the current specific scene and the road surface condition, and finally searching out an optimal obstacle avoidance lane change correction point X T_R by solving a multi-objective optimization problem, namely planning out a final obstacle avoidance lane change track, as shown in figure 4.
The above embodiments are merely for illustrating the design concept and features of the present invention, and are intended to enable those skilled in the art to understand the content of the present invention and implement the same, the scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications according to the principles and design ideas of the present invention are within the scope of the present invention.
Claims (9)
1. An intelligent vehicle obstacle avoidance lane change track planning method is characterized by comprising the following steps:
s1, obtaining a generalized lane change track by adopting a polynomial curve, wherein the generalized lane change track is obtained by adopting the polynomial curve:
wherein: establishing a coordinate system by using a self-vehicle, wherein the vehicle advancing direction is an x-axis, the direction vertical to the vehicle body is a y-axis, and x (t) and y (t) are respectively an x coordinate and a y coordinate at the moment t; v is the vehicle speed, w is the lane width, t is the time variable, and X T is the expected position of the lane change return point;
obtaining an expression of reference lateral acceleration relative to time from a generalized lane change track, obtaining maximum lateral acceleration a y_rmax under the reference track by extremuing the reference lateral acceleration, and defining a threshold value by combining the current road surface condition with a lateral acceleration related standard:
i a y_rmax|≤aymax =fμg, where the coefficient f <1
Wherein a ymax is the maximum lateral acceleration, the coefficient f <1, mu is the road adhesion coefficient; g is gravity acceleration;
calculating a lane change starting return point according to the maximum lateral acceleration threshold value; equidistant iteration is carried out on the channel changing initial correction points in the transverse direction, N-1 channel changing correction points are obtained through sampling, and the N-1 channel changing correction points are brought into a polynomial curve generalized track formula to obtain a feasible track cluster;
s2, pre-collision detection is carried out on N track changing tracks in the feasible track clusters, tracks which can collide without meeting the pre-collision detection conditions are screened and removed, and collision-free track clusters are obtained;
S3, establishing a cost function of three evaluation indexes, namely a comfort index, an obstacle avoidance efficiency index and a sideslip index, on the basis of a collision-free track cluster; and determining weights of three evaluation indexes, namely a comfort index, an obstacle avoidance efficiency index and a sideslip index by adopting fuzzy reasoning, and finally searching out an optimal obstacle avoidance lane change return positive point X T_R by solving a multi-objective optimization problem, namely planning a final obstacle avoidance lane change track.
2. The intelligent vehicle obstacle avoidance lane change trajectory planning method according to claim 1, wherein the cost function established in S3 is expressed as:
Wherein w C、wE、wS is the weight value of the comfort index, the obstacle avoidance efficiency index and the sideslip index respectively; j C is a comfort index, J E is an obstacle avoidance efficiency index, and J S is a sideslip index.
3. The intelligent vehicle obstacle avoidance lane change track planning method according to claim 2, wherein the method for determining weights of three evaluation indexes, namely a comfort index, an obstacle avoidance efficiency index and a sideslip index, by fuzzy reasoning is as follows:
Firstly, representing the dangerous degree by adopting the inverse TTC of the pre-collision time, and representing the current road surface condition by adopting the road surface adhesion coefficient mu; taking the reciprocal pre-collision time TTC -1 and the road adhesion coefficient mu as input and w C、wE、wS as output; the following fuzzy rules are designed:
Rule 1) if TTC -1is B andμis B,then(wC is B)(wE is S)(wS is S)
Rule 2) if TTC -1is B andμis S,then(wC is S)(wE is S)(wS is B)
Rule 3) if TTC -1is M andμis B,then(wC is M)(wE is M)(wS is S)
Rule 4) if TTC -1is M andμis S,then(wC is S)(wE is M)(wS is M
Rule 5) if TTC -1is S andμis B,then(wC is S)(wE is B)(wS is S
Rule 6) if TTC -1is S andμis S,then(wC is S)(wE is M)(wS is M
Wherein S is small, M is medium, and B is large.
4. A method for planning an obstacle avoidance and lane change trajectory of an intelligent vehicle according to claim 1, 2 or 3, wherein the comfort index, the obstacle avoidance efficiency index and the sideslip index are respectively expressed as follows:
JE=T
Wherein: j y_r is the desired lateral jerk; a y_r is the desired lateral acceleration; t is the time required for the whole process.
5. The intelligent vehicle obstacle avoidance lane change trajectory planning method according to claim 4, wherein the pre-collision detection procedure in S2 is as follows:
1) When the right front corner of the vehicle is equal to the abscissa of the tail of the front obstacle vehicle, namely X (a 1) =x (B), collision starts, and the moment is marked as t 1;
In the method, in the process of the invention, The course angle at the time t can be calculated by a track formula; x f(t1)、Bf is the position of the mass center of the front obstacle vehicle and the distance between the mass center and the tail of the front obstacle vehicle, and can be obtained by sensing information; a ego、Wego is the distance from the mass center of the vehicle to the vehicle head of the vehicle and the vehicle width of the vehicle respectively; solving to obtain t 1 as a pre-collision detection starting time point;
2) When the right rear corner point of the vehicle is equal to the abscissa of the tail of the front obstacle vehicle, namely, X (a 2) =x (B), the collision risk is completely separated, and the moment is marked as t 2;
wherein B ego is the distance from the mass center of the vehicle to the tail of the vehicle; solving to obtain t 2 as a collision detection termination point;
3) At time point t 1、t2, pre-crash detection is performed; the collision-free condition is that the vertical distance from the left rear corner point of the front obstacle vehicle to the vehicle axis is greater than a set threshold value, namely: d CB≥dmin:
T1:
T2:
Wherein d min is the minimum value of the vertical distance, and the track which can collide without meeting the pre-collision detection condition is screened and removed to obtain a collision-free track cluster.
6. The intelligent vehicle obstacle avoidance lane change trajectory planning method according to claim 1, wherein the expression of the reference lateral acceleration with respect to time is obtained by taking two derivatives of the generalized lane change trajectory:
obtaining the maximum lateral acceleration under the reference track by the extremum value:
Time,/>
7. The intelligent vehicle obstacle avoidance lane change trajectory planning method according to claim 1 or 6, wherein a lane change start return point is calculated according to a maximum lateral acceleration threshold:
Equidistant iteration is carried out on the channel changing initial correction points in the transverse direction, N-1 channel changing correction points are obtained through sampling, and the N-1 channel changing correction points are brought into a polynomial curve generalized track formula to obtain a feasible track cluster;
XTn=XT1+(n-1)d,n=2,3,…,N
Wherein X Tn is the position of the n-th lane change return point, and d is the iteration distance.
8. An intelligent vehicle obstacle avoidance lane change track planning system based on the intelligent vehicle obstacle avoidance lane change track planning method according to claim 1, which is characterized by comprising an environment sensing module, a candidate track generating module, a scene analyzing module and a candidate track screening module;
The environment sensing module is used for acquiring road environment information and obstacle vehicle motion information and inputting the acquired information to other three modules;
The candidate track generation module generates a track changing track with a stability limit based on a polynomial curve by a maximum lateral acceleration threshold according to road environment information and combining vehicle state information, generates a feasible track cluster through iteration, and inputs the feasible track cluster to the candidate track screening module;
The scene analysis module analyzes the current road surface condition and the dangerous degree according to the road environment information and the obstacle vehicle motion information, and obtains the weight value of each evaluation index in the current scene through fuzzy decision; inputting the weight value to a candidate track screening module;
The candidate track screening module performs pre-collision detection by combining obstacle vehicle motion information, screens out tracks which are likely to collide to obtain collision-free track clusters, and further establishes cost functions of three evaluation indexes of comfort, obstacle avoidance efficiency and sideslip index; and searching to obtain an optimal return point based on the weight value corresponding to each evaluation index output by the scene analysis module, and planning a final obstacle avoidance track.
9. The intelligent vehicle obstacle avoidance lane change trajectory planning system of claim 8, wherein said environmental awareness module comprises an environmental awareness sensor comprising a camera, lidar, millimeter wave radar, GPS, inertial navigation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111661902.6A CN114194215B (en) | 2021-12-30 | 2021-12-30 | Intelligent vehicle obstacle avoidance lane change track planning method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111661902.6A CN114194215B (en) | 2021-12-30 | 2021-12-30 | Intelligent vehicle obstacle avoidance lane change track planning method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114194215A CN114194215A (en) | 2022-03-18 |
CN114194215B true CN114194215B (en) | 2024-05-10 |
Family
ID=80657616
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111661902.6A Active CN114194215B (en) | 2021-12-30 | 2021-12-30 | Intelligent vehicle obstacle avoidance lane change track planning method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114194215B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115071698A (en) * | 2022-06-21 | 2022-09-20 | 重庆长安汽车股份有限公司 | Collision avoidance control method and system based on lowest collision cost |
CN115195743B (en) * | 2022-09-16 | 2022-12-23 | 毫末智行科技有限公司 | Automatic lane changing method, device, equipment and medium for vehicle based on unmanned driving |
CN115489548B (en) * | 2022-09-20 | 2024-06-04 | 重庆大学 | Intelligent automobile park road path planning method |
CN117141489B (en) * | 2023-11-01 | 2024-01-09 | 吉林大学 | Intelligent vehicle track layered planning method based on minimum action quantity principle |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
CN110286681A (en) * | 2019-07-05 | 2019-09-27 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track of variable curvature bend |
CN110362096A (en) * | 2019-08-13 | 2019-10-22 | 东北大学 | A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality |
IT201800011029A1 (en) * | 2018-12-12 | 2020-06-12 | Milano Politecnico | Process and route planning system for a ground vehicle for fast reacting obstacle avoidance, particularly in an autonomous driving scenario. |
CN111750887A (en) * | 2020-06-11 | 2020-10-09 | 上海交通大学 | Unmanned vehicle trajectory planning method and system for reducing accident severity |
CN112572443A (en) * | 2020-12-22 | 2021-03-30 | 北京理工大学 | Real-time collision-avoidance trajectory planning method and system for lane changing of vehicles on highway |
WO2021077725A1 (en) * | 2019-10-21 | 2021-04-29 | 南京航空航天大学 | System and method for predicting motion state of surrounding vehicle based on driving intention |
CN112947469A (en) * | 2021-03-16 | 2021-06-11 | 安徽卡思普智能科技有限公司 | Automobile track-changing track planning and dynamic track tracking control method |
CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
CN113276848A (en) * | 2021-04-09 | 2021-08-20 | 江苏大学 | Intelligent driving lane changing and obstacle avoiding track planning and tracking control method and system |
-
2021
- 2021-12-30 CN CN202111661902.6A patent/CN114194215B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106926844A (en) * | 2017-03-27 | 2017-07-07 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track based on real time environment information |
IT201800011029A1 (en) * | 2018-12-12 | 2020-06-12 | Milano Politecnico | Process and route planning system for a ground vehicle for fast reacting obstacle avoidance, particularly in an autonomous driving scenario. |
CN110286681A (en) * | 2019-07-05 | 2019-09-27 | 西南交通大学 | A kind of dynamic auto driving lane-change method for planning track of variable curvature bend |
CN110362096A (en) * | 2019-08-13 | 2019-10-22 | 东北大学 | A kind of automatic driving vehicle dynamic trajectory planing method based on local optimality |
WO2021077725A1 (en) * | 2019-10-21 | 2021-04-29 | 南京航空航天大学 | System and method for predicting motion state of surrounding vehicle based on driving intention |
CN111750887A (en) * | 2020-06-11 | 2020-10-09 | 上海交通大学 | Unmanned vehicle trajectory planning method and system for reducing accident severity |
CN112572443A (en) * | 2020-12-22 | 2021-03-30 | 北京理工大学 | Real-time collision-avoidance trajectory planning method and system for lane changing of vehicles on highway |
CN112965489A (en) * | 2021-02-05 | 2021-06-15 | 北京理工大学 | Intelligent vehicle high-speed lane change planning method based on collision detection |
CN112947469A (en) * | 2021-03-16 | 2021-06-11 | 安徽卡思普智能科技有限公司 | Automobile track-changing track planning and dynamic track tracking control method |
CN113276848A (en) * | 2021-04-09 | 2021-08-20 | 江苏大学 | Intelligent driving lane changing and obstacle avoiding track planning and tracking control method and system |
Non-Patent Citations (2)
Title |
---|
基于前车轨迹预测的高速智能车运动规划;张一鸣;周兵;吴晓建;崔庆佳;柴天;;汽车工程;20200525(05);12-18 * |
面向低速自动驾驶车辆的避障规划研究;肖宏宇;付志强;陈慧勇;;同济大学学报(自然科学版);20191215(S1);170-176 * |
Also Published As
Publication number | Publication date |
---|---|
CN114194215A (en) | 2022-03-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114194215B (en) | Intelligent vehicle obstacle avoidance lane change track planning method and system | |
CN113386795B (en) | Intelligent decision-making and local track planning method for automatic driving vehicle and decision-making system thereof | |
CN109501799B (en) | Dynamic path planning method under condition of Internet of vehicles | |
CN109669461B (en) | Decision-making system for automatically driving vehicle under complex working condition and track planning method thereof | |
CN111273668B (en) | Unmanned vehicle motion track planning system and method for structured road | |
CN113291308B (en) | Vehicle self-learning lane-changing decision-making system and method considering driving behavior characteristics | |
Khodayari et al. | A historical review on lateral and longitudinal control of autonomous vehicle motions | |
US20220080961A1 (en) | Control system and control method for sampling based planning of possible trajectories for motor vehicles | |
CN112193244B (en) | Automatic driving vehicle motion planning method based on linear constraint | |
CN110379203B (en) | Driving steering collision early warning method | |
CN106371439B (en) | Unified automatic driving transverse planning method and system | |
CN112896188B (en) | Automatic driving decision control system considering front vehicle encounter | |
JP7313298B2 (en) | VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD, AND PROGRAM | |
CN113085852A (en) | Behavior early warning method and device for automatic driving vehicle and cloud equipment | |
CN115520218B (en) | Four-point turning track planning method for automatic driving vehicle | |
CN114074681A (en) | Lane change decision and movement planning system and method based on probability | |
CN112224202B (en) | Multi-vehicle cooperative collision avoidance system and method under emergency working condition | |
CN111002993A (en) | Automatic driving low-oil-consumption movement planning method and system based on scene recognition | |
Ma et al. | Collision-avoidance lane change control method for enhancing safety for connected vehicle platoon in mixed traffic environment | |
CN113570747A (en) | Driving safety monitoring system and method based on big data analysis | |
CN112650064B (en) | Intelligent automobile convergence control system and method suitable for mixed roads | |
CN111376901A (en) | Vehicle control method and device and vehicle | |
CN113460080A (en) | Vehicle control device, vehicle control method, and storage medium | |
CN115848363A (en) | Collision avoidance and loss reduction trajectory planning method | |
JP7125969B2 (en) | VEHICLE CONTROL DEVICE, VEHICLE CONTROL METHOD, AND PROGRAM |
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 |