CN114537381A - Lane obstacle avoidance method and device for automatic driving vehicle - Google Patents
Lane obstacle avoidance method and device for automatic driving vehicle Download PDFInfo
- Publication number
- CN114537381A CN114537381A CN202011329935.6A CN202011329935A CN114537381A CN 114537381 A CN114537381 A CN 114537381A CN 202011329935 A CN202011329935 A CN 202011329935A CN 114537381 A CN114537381 A CN 114537381A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- lane
- obstacle
- obstacle avoidance
- reference point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000008859 change Effects 0.000 claims abstract description 15
- 238000004590 computer program Methods 0.000 claims description 7
- 230000003068 static effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims 1
- 230000006399 behavior Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000010187 selection method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
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
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/50—Barriers
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention relates to a lane obstacle avoidance method and device for an automatic driving vehicle, belonging to the technical field of intelligent vehicle driving, wherein the method comprises the following steps: judging the state of an obstacle in front of a lane; setting a path planning reference point according to the state of the obstacle and by combining the distance between the vehicle and the obstacle; substituting the path planning reference point into a set Bezier curve equation to plan a reference driving path based on a Bezier curve; and controlling the vehicle to run according to the reference running path to realize obstacle avoidance running. The lane obstacle avoidance method and the lane obstacle avoidance device can enable a vehicle to carry out obstacle avoidance driving along the current lane when encountering an obstacle, avoid unnecessary obstacle avoidance and lane change behaviors as much as possible, and improve the instantaneity, the reasonability and the safety of behavior decision; under the working condition of double lanes, obstacle avoidance returning is preferentially selected, and when the obstacle avoidance returning cannot be achieved, an obstacle avoidance and lane changing strategy is provided, so that the flexibility of obstacle avoidance is improved.
Description
Technical Field
The invention belongs to the technical field of intelligent vehicle driving, and particularly relates to a lane obstacle avoidance method and device for an automatic driving vehicle.
Background
At present, an automatic driving vehicle has intelligent environment sensing capability, analyzes the current road condition by identifying a path, and detects obstacles by combining the position of the vehicle to realize real-time early warning. However, in a real environment, when an autonomous logistics vehicle runs in a given path of a global plan, the autonomous logistics vehicle is often influenced by random obstacles, and at this time, a real-time obstacle avoidance method needs to be adopted to safely complete a running task.
For example, chinese patent application publication No. CN109987092A discloses a method for determining vehicle obstacle avoidance and lane change timing and a method for controlling obstacle avoidance and lane change, which determine whether a lane change condition is satisfied between obstacles around a vehicle and the vehicle by acquiring information of obstacles around the vehicle and road conditions, determine that the vehicle can perform obstacle avoidance and lane change when the set condition is satisfied, and perform curve fitting according to coordinates of a starting point, coordinates of a target point, and a road heading angle to obtain a path from the starting point to the target point.
However, the existing lane obstacle avoidance methods are all methods for changing lanes when a vehicle encounters an obstacle in a current lane, and for an automatically-driven logistics vehicle, under the condition that there are few lanes and many vehicles on the lanes, in order to avoid the obstacle in the current lane for changing lanes, other vehicles which travel logistics often encounter other vehicles, and after lane changing, the vehicles either become obstacles of other vehicles on the lane or other vehicles on the lane serve as obstacles, so the existing obstacle avoidance methods adopting lane changing cannot solve the problem of obstacle avoidance under the driving environment of the automatically-driven logistics vehicle.
Disclosure of Invention
The invention aims to provide a lane obstacle avoidance method and device for an automatic driving vehicle, which are used for solving the problem that the existing obstacle avoidance method adopting lane changing cannot solve the obstacle avoidance problem under the driving environment of the automatic driving logistics vehicle.
Based on the purpose, the technical scheme of the lane obstacle avoidance method for the automatic driving vehicle is as follows:
1) judging the state of an obstacle in front of a lane;
2) setting a path planning reference point according to the state of the obstacle and by combining the distance Dis _ obs between the vehicle and the obstacle;
the state of the obstacle comprises static state, and in the state, the setting rule of the path planning reference point is as follows: selecting n reference points, n is more than or equal to 5, and the abscissa of all the reference points is [0, Dis _ obs ]]The 1 st reference point is selected as the current coordinate of the vehicle, and the vertical coordinate of the nth reference point is (W)l+Wl'/2) or (W)r+Wr′/2)，WlIs the ordinate, W, of the left side of the obstaclel' is the remaining width of the left side of the obstacle on the lane, WrIs the ordinate, W, of the right side of the obstacler' is the remaining width of the right side of the obstacle on the lane; the ordinate of each of the remaining reference points is [0, W ]l+Wl′/2]Setting the range from small to large;
3) substituting the path planning reference point into a set Bezier curve equation to plan a reference driving path based on the Bezier curve;
4) and controlling the vehicle to run according to the reference running path to realize obstacle avoidance running.
Based on the above purpose, the technical scheme of the lane obstacle avoidance device for the automatic driving vehicle is as follows:
the system comprises a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor is coupled with the memory, and the processor executes the computer program to realize the lane obstacle avoidance method of the automatic driving vehicle.
The two technical schemes have the beneficial effects that:
the lane obstacle avoidance method and the lane obstacle avoidance device can plan the reference driving path according to the set plurality of path planning reference points when the vehicle encounters an obstacle; and according to the reference driving path, obstacle avoidance driving is carried out along the current lane, unnecessary obstacle avoidance and lane changing behaviors are avoided as much as possible, and the real-time performance, the reasonability and the safety of behavior decision are improved.
Further, in order to facilitate smoother vehicle obstacle avoidance driving, before selecting the ordinate of the nth reference point in step 2), the method further includes: judging the left and right left width W of the obstacle on the lanel′、Wr' the width between the left and right sides of the obstacle and the remaining width W of the lanel′、WrAll of which are equal to or greater than the vehicle width, W is selectedl′、WrThe larger of' participates in the calculation of the nth reference point ordinate; and if the residual width of one of the left side and the right side of the obstacle on the lane is larger than the vehicle width, selecting the residual width to participate in the calculation of the vertical coordinate of the nth reference point.
Further, when the vehicle is in a double lane, the vehicle preferentially carries out single lane obstacle avoidance driving according to the contents in the step 2) and the step 3), and when the left side and the right side of the obstacle are on the left and the right of the remaining width W of the lanel′、WrWhen the vehicle width is smaller than the vehicle width, obstacle avoidance and lane change driving are carried out;
when the state of the obstacle is a static state, the setting rule of the path planning reference point is as follows: selecting n reference points, wherein n is more than or equal to 5, the abscissa of all the reference points is arranged at intervals in the range of [0, Dis _ obs ], the 1 st reference point selects the current coordinate of the vehicle, the ordinate of the nth reference point is the lane width W, and the ordinate of the other reference points is set in sequence from small to large in the range of [0, W ].
The effect is as follows: if the vehicle is in a double-lane working condition, obstacle avoidance returning and obstacle avoidance and lane changing strategies are provided, so that the vehicle can change lanes and avoid obstacles under the condition that the vehicle cannot carry out single-lane obstacle avoidance driving, and the driving target is completed.
Further, the state of the obstacle includes a static state, the state of the obstacle also includes a same-direction driving state, a reverse driving state and a lane crossing state, for the case that the state of the obstacle is the same-direction driving state, the vehicle keeps the same speed as the obstacle to drive on the current path, and the path planning reference point selection rule is as follows: selecting n reference points along the current linear direction, wherein the distances between every two adjacent reference points are the same; when the obstacle crosses the lane or runs in the reverse direction, the vehicle is controlled to keep the current path and stop at a certain distance from the obstacle, and the selection rule of the path planning reference point is the same as that of the equidirectional running condition.
In order to enable the vehicle to stably travel on the reference travel path, the vehicle further includes: controlling the vehicle to run according to the set real-time vehicle speed, wherein the real-time vehicle speed is calculated according to the following formula:
where v is the real-time vehicle speed, DlimitFor maximum allowable deviation path distance, VmaxAt maximum speed, VminAt minimum speed, d is the distance the vehicle deviates from the reference travel path, i.e. the distance the vehicle is from the reference path.
The effect is as follows: and the speed is planned in real time according to the distance between the vehicle and the path, so that the stable change of the speed can be ensured, and the running stability of the vehicle is realized.
To determine the reference travel path, the expression of the bezier curve equation is as follows:
wherein, PiThe characteristic points of the Bezier curve, namely the coordinates of each path planning reference point, are formed, n is the order of the Bezier curve, and t is a normalization parameter.
Drawings
Fig. 1 is a flowchart of a lane obstacle avoidance method for an autonomous vehicle according to embodiment 1 of the present invention;
fig. 2 is a schematic diagram of the vehicle in embodiment 1 of the method of the present invention in a single lane and without obstacle avoidance return;
fig. 3 is a schematic diagram of the vehicle in embodiment 1 of the method of the present invention in a single lane with obstacle avoidance and return;
fig. 4 is a schematic diagram of the method of embodiment 1 of the present invention in which the host vehicle is in a single lane and has obstacle avoidance returning and obstacle avoidance lane changing;
fig. 5 is a flowchart of a lane obstacle avoidance method for an autonomous vehicle according to embodiment 2 of the present invention.
Detailed Description
The following further describes embodiments of the present invention with reference to the drawings.
Method example 1:
the embodiment provides a lane obstacle avoidance method for an automatic vehicle, the overall flow is shown in fig. 1, and the implementation idea of the method is as follows: according to the movement condition of the obstacle, a reference driving path based on a Bezier curve is planned on the current lane; and enabling the vehicle to avoid obstacles to run on the current lane according to the planned reference running path. The method comprises the following specific steps:
1) judging the state of an obstacle in front of the lane, wherein the state of the obstacle comprises the following steps: static, co-directional driving, reverse driving and crossing lanes.
2) And setting a path planning reference point according to different states of the obstacle and combining the distance Dis _ obs between the vehicle and the obstacle. The following methods are respectively adopted for setting:
and when the obstacle state is the same-direction driving condition:
when an obstacle in front of the vehicle running direction of the road runs in the same direction as the vehicle, the vehicle keeps running on the current path at the same speed as the obstacle, and the selection rule of the path planning reference point is as follows: several reference points are selected along the current linear direction, for example, five reference points are selected, and the distance between each two adjacent reference points is the same, for example, Dis _ obs/4, and the specific setting of each reference point is shown in fig. 2. As other embodiments, the abscissas of all the reference points are arranged at intervals in sequence within the range of [0, Dis _ obs ], the set transverse intervals are flexible, and the reference points can be set at equal intervals in the transverse direction and also can be set at unequal intervals in the transverse direction.
In fig. 2, the first point p1(x1, y1) selects the current coordinates of the vehicle, and the second point p2(x2, y2) selects the point on the path where the closest point Close _ a extends backward (Dis _ obs/4) by 1 meter; the third point p3(x3, y3) selects a point on the path at which the closest point Close _ a extends rearward (Dis _ obs/4) × 2 meters, the fourth point p4(x4, y4) selects a point on the path at which the closest point Close _ a extends rearward (Dis _ obs/4) × 3 meters, and the fifth point p5(x5, y5) selects a point on the path at which the closest point Close _ a extends rearward (Dis _ obs/4) × 4 meters.
And when the obstacle state is a lane crossing and reverse driving condition:
when the barrier crosses the lane or runs reversely, in order to avoid unnecessary lane change and ensure the running safety of the vehicle, the vehicle keeps the current path and stops at a certain distance from the barrier, and the path planning reference point selection rule is the same as the reference point selection rule of the same-direction running condition.
For the obstacle state being a stationary case:
the path reference point setting method in this case is classified into the following two cases:
in the first situation, when the obstacle located in front of the vehicle in the own lane is stationary and the own vehicle is in a single lane, it is first determined whether the vehicle can avoid the obstacle in the single lane. That is, the width of the remaining width of one side obtained by subtracting the width of the obstacle from the width of the lane is compared with the width of the vehicle, and the remaining width W of one side is determinedl′、Wr' greater than the vehicle width, it is determined that one-lane obstacle avoidance is possible.
The path planning reference point selection rule is as follows: selecting a plurality of reference points, for example, selecting n (n ≧ 5) reference points, the lateral distance between each adjacent reference point is Dis _ obs/(n-1), the 1 st reference point selects the current coordinates of the vehicle, the 2 nd reference point selects the point on the lane line with the lateral distance from the 1 st reference point being Dis _ obs/(n-1), the lateral distance from the nth reference point to the 1 st reference point is Dis _ obs, and the nth reference point is the residual width W on one sidel′、Wr' 1/2, e.g. taking the left residual width Wl' 1/2, then the ordinate of the reference point is (W)l+Wl′/2)，WlIs the ordinate of the left side of the obstacle; if the left side residual width W is takenr' 1/2, then the ordinate of the reference point is (W)r+Wr′/2)，WrIs the ordinate of the right side of the obstacle; longitudinal of the remaining reference points (No. 3, …, n-1 reference points)Coordinates are [0, W ]l+Wl′/2]Within the range, the setting can be performed according to a setting rule from small to large. As another embodiment, the ordinate of the 2 nd reference point may not be set to zero, that is, the increasing setting of the ordinate is performed from the 2 nd reference point to the (n-1) th reference point in sequence.
Taking setting 5 reference points as an example, as shown in fig. 2, the path planning reference point is selected as follows: the first point p1(x1, y1) selects the current coordinate of the vehicle, the second point p2(x2, y2) selects the point with the coordinate (1,0) in the vehicle coordinate system, the third point p3(x3, y3) selects the middle point of the first point and the fifth point, namely ((x1+ x5)/2, (y1+ y5)/2), and the selection of the fourth point and the fifth point needs to compare the residual width of the lane
And
if the remaining width Wl′、WrAll of which are equal to or greater than the vehicle width, W is selectedl′、WrThe larger of the' involves in the calculation of the 4 th and 5 th reference point ordinate, i.e. the fourth and fifth point choices are taken on the path points p4 and p5 verticals (max (W)l′,Wr')/2. As shown in fig. 2, there are two sets of upper and lower reference points that are selectable, so that one of the reference points can be selected to provide a set of reference points with a larger remaining width for more convenient vehicle passing; if this problem is not considered, as another embodiment, when both the remaining widths of the two sides are greater than the vehicle width, one of the groups of reference points may be selected as the path planning reference point.
In FIG. 2, if one of the remaining widths W is Wl' or Wr' greater than vehicle width, the fourth point and the fifth point are selected to take W on the perpendicular lines of the path points p4 and p5l'/2 or WrPoint of'/2; if the residual width is smaller than the vehicle width and the obstacle is in a single lane, no standby path exists, and the path reference point selection mechanism is the same as the selection rule of the same-direction running condition of the obstacle.
The above is a path planning reference with 5 reference pointsThe point selection method includes, if 6 reference points need to be selected, the transverse distances between the reference points are equally distributed, and the selection principles of the vertical coordinates of the 1 st, 2 nd, 5 th and 6 th reference points correspond to the selection methods of the vertical coordinates of the 1 st, 2 nd, 4 th and 5 th reference points, respectively, and are not repeated, and it is to be described that the selection methods of the vertical coordinates of the 3 rd and 4 th reference points are the same, for example, Y is (W) according to the vertical coordinate of the last reference pointl+Wl'/2) according to (0, W)l+Wl'/2) from small to large, selecting the ordinate of the 3 rd reference point as Y/3 and the ordinate of the 4 th reference point as 2Y/3.
And in the second situation, when the obstacle in front of the vehicle running direction of the vehicle in the road is static and the vehicle is in the double lanes, the path planning reference point selects the method in the first situation of priority reference, selects single-lane obstacle avoidance return as much as possible (the obstacle avoidance return refers to the situation that the vehicle bypasses the obstacle to return to the original route on the single lane), and if the remaining width W is larger than the preset valuel′、WrWhen the distance between the two lanes is less than the vehicle width and the obstacle avoidance and the return cannot be realized, and when no obstacle exists in the front of the vehicle running direction of the other lane, the obstacle avoidance and the lane change can be provided, and the rule for selecting the path planning reference point is as follows: taking n reference points as an example, the transverse distance between the reference points is Dis _ obs/(n-1), the 1 st reference point selects the current coordinate of the vehicle, the 2 nd reference point selects a point on the lane line which is the transverse distance Dis _ obs/(n-1) from the 1 st reference point, the transverse distances between the reference points are Dis _ obs/(n-1), the vertical coordinates of the n-1 th reference point and the nth reference point are lane widths W, and the vertical coordinates of the rest reference points are set in sequence according to a setting rule from small to large in the range of (0, W).
To illustrate by setting 5 reference points as an example, as shown in fig. 3, the first point p1(x1, y1) selects the current coordinates of the vehicle, the second point p2(x2, y2) selects a point having coordinates (1,0) in the vehicle coordinate system, the third point p3(x3, y3) selects the midpoint between the first point and the fifth point, i.e., (x1+ x5)/2, (y1+ y5)/2), the fourth point p4(x4, y4) selects a point on the path where the closest point Close _ B extends backward by (N/4) × 3 meters, and the fifth point p5(x5, y5) selects a point on the path where the closest point Close _ B extends backward by (N/4) × 4 meters.
3) And planning a reference driving path based on the Bezier curve according to the path planning reference point determined in the step.
Taking five path planning reference points as an example, the coordinates of the five reference points are substituted into the constructed Bezier curve equation, so that the reference driving path can be obtained. Wherein, the adopted Bezier curve equation is as follows:
wherein, PiThe characteristic points forming the bezier curve, i.e. the respective path planning reference points, n is the order of the bezier curve, n is 4 in this example, and t is the normalization parameter.
4) And controlling the vehicle to run according to the reference running path according to the obtained reference running path, so as to realize obstacle avoidance running.
The lane obstacle avoidance method of the embodiment has the following characteristics:
firstly, making vehicle behavior decisions according to the states of obstacles in front of the vehicle in different scenes, and selecting reasonable path planning points to plan paths so as to realize the automatic driving function of the vehicle; unnecessary obstacle avoidance behaviors are avoided as much as possible, and the real-time performance, the reasonability and the safety of behavior decision are improved.
Secondly, under the working condition of double lanes, an obstacle avoidance returning and obstacle avoidance lane changing strategy is provided. Under the working condition of double lanes, obstacle avoidance and return are preferentially selected, and when the obstacle avoidance and return cannot be achieved by the lane, an obstacle avoidance and lane change strategy is provided, so that the flexibility of obstacle avoidance is improved.
Method example 2:
the embodiment provides a lane obstacle avoidance method for an automatically driven vehicle, the overall flow is shown in fig. 5, and the specific steps are as follows:
the method comprises the following steps: and calculating reference path information by using a navigation positioning system, wherein the reference path information comprises a positioning solution state, transverse and longitudinal coordinates, a course angle, curvature change information and the like of the path point set.
Step two: and judging whether the decision front end input (information such as perception and positioning) meets the automatic driving condition. The specific judgment content comprises: judging a positioning solution; and (4) positioning communication fault judgment and sensing fault judgment, and entering an automatic driving mode when positioning and sensing are correct and the positioning solution enters an optimal state.
Step three: and judging whether the vehicle is in a single lane or a double lane at present and has a lane changing condition or not according to the vehicle pose and the reference path. The specific judgment method comprises the following steps: according to the vehicle position and the heading angle information, the closest points (namely Close-A and Close-B in figure 4) away from the two reference paths are searched, and if the distance between the closest points of the two paths is greater than or equal to the preset minimum two-lane distance, the vehicle is in two lanes, and the lane change condition is met. Otherwise, the vehicle is in a single lane, with no backup path.
Step four: and carrying out vehicle driving behavior strategy decision based on the state that the vehicle is in a single lane or a double lane, the vehicle pose, the reference path and the obstacle, and selecting a path planning reference point.
As shown in FIGS. 2, 3 and 4, the arrows indicate the traveling direction of the vehicle, and the lane width W and the vehicle body width W are set asV＝Wl+WrThe distance between the nearest obstacle in front of the vehicle in the road is Dis _ obs, and the closest points of the vehicle to the two paths are respectively Close _ A, Close _ B. The rule for selecting the path planning reference point refers to the record in step 2) in the above method embodiment 1, and this embodiment is not described again.
Step five: based on the path planning reference point, the path planning is performed by using the bezier curve, and the path planning method refers to the record of step 3) in method embodiment 1, which is not described again.
Step six: and performing real-time speed planning according to the distance between the vehicle and the reference path, the maximum allowable speed and the like, wherein the relation between the real-time vehicle speed v and the distance d of the vehicle deviating from the path is as follows:
where v is the real-time vehicle speed, DlimitFor maximum allowable deviation path distance, VmaxAt maximum speed, VminAt minimum speed, d is the vehicle departure path distance, i.e., the distance of the vehicle from the reference path.
Step seven: and outputting the path information and the speed information to a control end for transverse and longitudinal control to realize automatic driving of the vehicle.
The lane obstacle avoidance method can not only carry out vehicle behavior decision according to the state of the obstacle in front of the vehicle in different scenes, but also select reasonable path planning points to carry out path and speed planning, thereby realizing the automatic driving function of the vehicle; and the speed can be planned in real time according to the distance between the vehicle and the path, so that the stable change of the speed is ensured, and the running stability of the vehicle is realized.
The embodiment of the device is as follows:
the embodiment provides a lane obstacle avoidance device of an autonomous vehicle, which includes a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor is coupled with the memory, and is configured to run program instructions stored in the memory to implement the lane obstacle avoidance method in method embodiment 1 or method embodiment 2, and as the description of the method in method embodiment 1 and method embodiment 2 is sufficiently clear and complete, the description of the method in this embodiment is not repeated.
That is, the method in the above method embodiments should be understood that the flow of the master-side and slave-side robot control method can be implemented by computer program instructions. These computer program instructions may be provided to a processor (e.g., a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus), such that the instructions, which execute via the processor, create means for implementing the functions specified in the method flow.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (7)
1. A lane obstacle avoidance method of an autonomous vehicle is characterized by comprising the following steps:
1) judging the state of an obstacle in front of a lane;
2) setting a path planning reference point according to the state of the obstacle and by combining the distance Dis _ obs between the vehicle and the obstacle;
the state of the barrier comprises static state, and in the state, the setting rule of the path planning reference point is as follows: selecting n reference points, n is more than or equal to 5, and the abscissa of all the reference points is [0, Dis _ obs ]]The 1 st reference point is selected as the current coordinate of the vehicle, and the vertical coordinate of the nth reference point is (W)l+Wl'/2) or (W)r+Wr′/2)，WlIs the ordinate, W, of the left side of the obstaclel' is the remaining width of the left side of the obstacle on the lane, WrIs the ordinate, W, of the right side of the obstacler' is the remaining width of the right side of the obstacle on the lane; the ordinate of each of the remaining reference points is [0, W ]l+Wl′/2]Setting the range from small to large;
3) substituting the path planning reference point into a set Bezier curve equation to plan a reference driving path based on the Bezier curve;
4) and controlling the vehicle to run according to the reference running path to realize obstacle avoidance running.
2. A lane obstacle avoidance method for an autonomous vehicle as claimed in claim 1, wherein in step 2), before selecting the ordinate of the nth reference point, the method further comprises: judging the left and right left width W of the obstacle on the lanel′、Wr' the width between the left and right sides of the obstacle and the remaining width W of the lanel′、WrAll of which are equal to or greater than the vehicle width, W is selectedl′、WrThe larger of' participates in the calculation of the nth reference point ordinate; if onlyAnd if the residual width of one of the left side and the right side of the obstacle on the lane is larger than the vehicle width, selecting the residual width to participate in the calculation of the vertical coordinate of the nth reference point.
3. The method as claimed in claim 2, wherein when the vehicle is in a dual lane, the vehicle is preferentially driven for single lane obstacle avoidance according to the contents of step 2) and step 3), and when the left and right sides of the obstacle are left and right, the remaining width W of the lane is determinedl′、WrWhen the vehicle width is smaller than the vehicle width, obstacle avoidance and lane change driving are carried out;
when the state of the obstacle is a static state, the setting rule of the path planning reference point is as follows: selecting n reference points, wherein n is more than or equal to 5, the abscissa of all the reference points is arranged at intervals in the range of [0, Dis _ obs ], the 1 st reference point selects the current coordinate of the vehicle, the ordinate of the nth reference point is the lane width W, and the ordinate of the other reference points is set in sequence from small to large in the range of [0, W ].
4. A lane obstacle avoidance method for an autonomous vehicle according to any of claims 1 to 3, characterized in that the states of the obstacles further include co-directional driving, reverse driving, crossing lanes, and for the case that the state of the obstacle is co-directional driving, the vehicle keeps the same speed as the obstacle to drive on the current path, and the path planning reference point selection rule is as follows: selecting a plurality of n reference points along the current linear direction, wherein the distances between every two adjacent reference points are the same; when the obstacle crosses the lane or runs in the reverse direction, the vehicle is controlled to keep the current path and stop at a certain distance from the obstacle, and the selection rule of the path planning reference point is the same as that of the equidirectional running condition.
5. A lane obstacle avoidance method for an autonomous vehicle according to any of claims 1-3, characterized by further comprising: controlling the vehicle to run according to the set real-time vehicle speed, wherein the real-time vehicle speed is calculated according to the following formula:
where v is the real-time vehicle speed, DlimitFor maximum allowable deviation path distance, VmaxAt maximum speed, VminAt minimum speed, d is the distance the vehicle deviates from the reference travel path, i.e. the distance the vehicle is from the reference path.
6. A lane obstacle avoidance method for an autonomous vehicle according to any of claims 1-3, characterized in that the expression of the bezier curve equation is as follows:
wherein, PiThe characteristic points of the Bezier curve, namely the coordinates of each path planning reference point, are formed, n is the order of the Bezier curve, and t is a normalization parameter.
7. A lane obstacle avoidance arrangement for an autonomous vehicle, comprising a memory and a processor, and a computer program stored on the memory and run on the processor, the processor being coupled to the memory, characterized in that the processor, when executing the computer program, implements the lane obstacle avoidance method for an autonomous vehicle as claimed in any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329935.6A CN114537381B (en) | 2020-11-24 | 2020-11-24 | Lane obstacle avoidance method and device for automatic driving vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011329935.6A CN114537381B (en) | 2020-11-24 | 2020-11-24 | Lane obstacle avoidance method and device for automatic driving vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114537381A true CN114537381A (en) | 2022-05-27 |
| CN114537381B CN114537381B (en) | 2024-05-31 |
Family
ID=81660271
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011329935.6A Active CN114537381B (en) | 2020-11-24 | 2020-11-24 | Lane obstacle avoidance method and device for automatic driving vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114537381B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115123310A (en) * | 2022-08-31 | 2022-09-30 | 中汽数据(天津)有限公司 | Unmanned vehicle obstacle avoidance local path planning method, device and storage medium |
| CN115357034A (en) * | 2022-10-21 | 2022-11-18 | 上海伯镭智能科技有限公司 | Unmanned mine car steering control method based on intelligent traffic |
| CN115571164A (en) * | 2022-11-03 | 2023-01-06 | 中科天极(新疆)空天信息有限公司 | Obstacle avoidance method and system based on automatic driving |
Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1684142A1 (en) * | 2005-01-20 | 2006-07-26 | Robert Bosch Gmbh | Method of predicting possible future course in driver assisting system |
| KR20120054879A (en) * | 2010-11-22 | 2012-05-31 | 고려대학교 산학협력단 | Method for planing collision avoidance path of car-like mobile robot and parking assist system using the same |
| US20150094945A1 (en) * | 2013-09-27 | 2015-04-02 | Transoft Solutions, Inc. | Method and apparatus for generating a vehicle path |
| CN104773171A (en) * | 2014-01-10 | 2015-07-15 | 财团法人工业技术研究院 | Vehicle collision early warning device and method |
| US20150353082A1 (en) * | 2014-06-05 | 2015-12-10 | Carnegie Mellon University | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver |
| US9229453B1 (en) * | 2014-08-29 | 2016-01-05 | GM Global Technology Operations LLC | Unified motion planner for autonomous driving vehicle in avoiding the moving obstacle |
| CN106882185A (en) * | 2017-03-10 | 2017-06-23 | 南京林业大学 | A kind of focus containing driver takes aim at the vehicle self-steering control method of model in advance |
| US20170236422A1 (en) * | 2014-09-29 | 2017-08-17 | Hitachi Construction Machinery Co., Ltd. | Obstacle avoidance system |
| US20170316684A1 (en) * | 2016-04-29 | 2017-11-02 | Ford Global Technologies, Llc | Vehicle lane map estimation |
| US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
| US20180186373A1 (en) * | 2016-12-30 | 2018-07-05 | Neusoft Corporation | Method, device and apparatus for planning vehicle speed |
| DE102017200218A1 (en) * | 2017-01-09 | 2018-07-12 | Bayerische Motoren Werke Aktiengesellschaft | Control unit and method for taking into account obstacles in a reversing assistance system |
| CN108290540A (en) * | 2015-11-04 | 2018-07-17 | 祖克斯有限公司 | Internal security system for independently driving vehicle |
| CN109177974A (en) * | 2018-08-28 | 2019-01-11 | 清华大学 | A kind of man-machine type lane of driving altogether of intelligent automobile keeps householder method |
| CN109712421A (en) * | 2019-02-22 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
| CN109808685A (en) * | 2019-01-07 | 2019-05-28 | 南京航空航天大学 | A kind of automatic collision avoidance control method of automobile early warning based on assessment of risks |
| CN109976329A (en) * | 2017-12-28 | 2019-07-05 | 郑州宇通客车股份有限公司 | A kind of planing method in vehicle obstacle-avoidance lane-change path |
| CN110466516A (en) * | 2019-07-11 | 2019-11-19 | 北京交通大学 | A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming |
| CN110531749A (en) * | 2018-05-24 | 2019-12-03 | 百度（美国）有限责任公司 | Determine the driving path for avoiding the automatic Pilot of moving obstacle |
| US20200033871A1 (en) * | 2016-09-29 | 2020-01-30 | Honda Motor Co., Ltd. | Vehicle control device |
| CN110893849A (en) * | 2018-08-22 | 2020-03-20 | 郑州宇通客车股份有限公司 | Obstacle avoidance and lane change control method and device for automatic driving vehicle |
| CN111238520A (en) * | 2020-02-06 | 2020-06-05 | 北京百度网讯科技有限公司 | Lane change path planning method and device, electronic equipment and computer readable medium |
| CN111338340A (en) * | 2020-02-21 | 2020-06-26 | 天津大学 | Model prediction-based unmanned automobile local path planning method |
| CN111332285A (en) * | 2018-12-19 | 2020-06-26 | 长沙智能驾驶研究院有限公司 | Method and device for vehicle to avoid obstacle, electronic equipment and storage medium |
| CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
| US20200216059A1 (en) * | 2019-01-04 | 2020-07-09 | Toyota Motor Engineering & Manfacuring North America, Inc. | System, method, and computer-readable storage medium for vehicle collision avoidance on the highway |
| CN111401208A (en) * | 2020-03-11 | 2020-07-10 | 北京百度网讯科技有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
| CN111750886A (en) * | 2020-05-12 | 2020-10-09 | 北京智行者科技有限公司 | Local path planning method and device |
-
2020
- 2020-11-24 CN CN202011329935.6A patent/CN114537381B/en active Active
Patent Citations (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1684142A1 (en) * | 2005-01-20 | 2006-07-26 | Robert Bosch Gmbh | Method of predicting possible future course in driver assisting system |
| KR20120054879A (en) * | 2010-11-22 | 2012-05-31 | 고려대학교 산학협력단 | Method for planing collision avoidance path of car-like mobile robot and parking assist system using the same |
| US20150094945A1 (en) * | 2013-09-27 | 2015-04-02 | Transoft Solutions, Inc. | Method and apparatus for generating a vehicle path |
| CN104773171A (en) * | 2014-01-10 | 2015-07-15 | 财团法人工业技术研究院 | Vehicle collision early warning device and method |
| US20150353082A1 (en) * | 2014-06-05 | 2015-12-10 | Carnegie Mellon University | Unified motion planning algorithm for autonomous driving vehicle in obstacle avoidance maneuver |
| US9229453B1 (en) * | 2014-08-29 | 2016-01-05 | GM Global Technology Operations LLC | Unified motion planner for autonomous driving vehicle in avoiding the moving obstacle |
| US20170236422A1 (en) * | 2014-09-29 | 2017-08-17 | Hitachi Construction Machinery Co., Ltd. | Obstacle avoidance system |
| CN108290540A (en) * | 2015-11-04 | 2018-07-17 | 祖克斯有限公司 | Internal security system for independently driving vehicle |
| US20170316684A1 (en) * | 2016-04-29 | 2017-11-02 | Ford Global Technologies, Llc | Vehicle lane map estimation |
| US20170364083A1 (en) * | 2016-06-21 | 2017-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Local trajectory planning method and apparatus for smart vehicles |
| US20200033871A1 (en) * | 2016-09-29 | 2020-01-30 | Honda Motor Co., Ltd. | Vehicle control device |
| US20180186373A1 (en) * | 2016-12-30 | 2018-07-05 | Neusoft Corporation | Method, device and apparatus for planning vehicle speed |
| DE102017200218A1 (en) * | 2017-01-09 | 2018-07-12 | Bayerische Motoren Werke Aktiengesellschaft | Control unit and method for taking into account obstacles in a reversing assistance system |
| CN106882185A (en) * | 2017-03-10 | 2017-06-23 | 南京林业大学 | A kind of focus containing driver takes aim at the vehicle self-steering control method of model in advance |
| CN109976329A (en) * | 2017-12-28 | 2019-07-05 | 郑州宇通客车股份有限公司 | A kind of planing method in vehicle obstacle-avoidance lane-change path |
| CN110531749A (en) * | 2018-05-24 | 2019-12-03 | 百度（美国）有限责任公司 | Determine the driving path for avoiding the automatic Pilot of moving obstacle |
| CN110893849A (en) * | 2018-08-22 | 2020-03-20 | 郑州宇通客车股份有限公司 | Obstacle avoidance and lane change control method and device for automatic driving vehicle |
| CN109177974A (en) * | 2018-08-28 | 2019-01-11 | 清华大学 | A kind of man-machine type lane of driving altogether of intelligent automobile keeps householder method |
| CN111332285A (en) * | 2018-12-19 | 2020-06-26 | 长沙智能驾驶研究院有限公司 | Method and device for vehicle to avoid obstacle, electronic equipment and storage medium |
| CN111383474A (en) * | 2018-12-29 | 2020-07-07 | 长城汽车股份有限公司 | Decision making system and method for automatically driving vehicle |
| US20200216059A1 (en) * | 2019-01-04 | 2020-07-09 | Toyota Motor Engineering & Manfacuring North America, Inc. | System, method, and computer-readable storage medium for vehicle collision avoidance on the highway |
| CN109808685A (en) * | 2019-01-07 | 2019-05-28 | 南京航空航天大学 | A kind of automatic collision avoidance control method of automobile early warning based on assessment of risks |
| CN109712421A (en) * | 2019-02-22 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
| CN110466516A (en) * | 2019-07-11 | 2019-11-19 | 北京交通大学 | A kind of curved road automatic vehicle lane-change method for planning track based on Non-Linear Programming |
| CN111238520A (en) * | 2020-02-06 | 2020-06-05 | 北京百度网讯科技有限公司 | Lane change path planning method and device, electronic equipment and computer readable medium |
| CN111338340A (en) * | 2020-02-21 | 2020-06-26 | 天津大学 | Model prediction-based unmanned automobile local path planning method |
| CN111401208A (en) * | 2020-03-11 | 2020-07-10 | 北京百度网讯科技有限公司 | Obstacle detection method and device, electronic equipment and storage medium |
| CN111750886A (en) * | 2020-05-12 | 2020-10-09 | 北京智行者科技有限公司 | Local path planning method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115123310A (en) * | 2022-08-31 | 2022-09-30 | 中汽数据(天津)有限公司 | Unmanned vehicle obstacle avoidance local path planning method, device and storage medium |
| CN115357034A (en) * | 2022-10-21 | 2022-11-18 | 上海伯镭智能科技有限公司 | Unmanned mine car steering control method based on intelligent traffic |
| CN115571164A (en) * | 2022-11-03 | 2023-01-06 | 中科天极(新疆)空天信息有限公司 | Obstacle avoidance method and system based on automatic driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114537381B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114537381A (en) | Lane obstacle avoidance method and device for automatic driving vehicle | |
| US11409288B2 (en) | Lane changing method, device for driverless vehicle and computer-readable storage medium | |
| CN107992050B (en) | Method and device for planning local path motion of unmanned vehicle | |
| Kuwata et al. | Motion planning for urban driving using RRT | |
| CN110268457B (en) | Method for determining a collective maneuver of at least two vehicles, computer program product, computer-readable medium, controller and vehicle comprising the controller | |
| WO2018176593A1 (en) | Local obstacle avoidance path planning method for unmanned bicycle | |
| Andersen et al. | Trajectory optimization for autonomous overtaking with visibility maximization | |
| CN109557912A (en) | A kind of decision rule method of automatic Pilot job that requires special skills vehicle | |
| CN113085850B (en) | Vehicle obstacle avoidance method and device, electronic equipment and storage medium | |
| CN113009918B (en) | Path planning method, device, system and readable storage medium | |
| CN111426326A (en) | Navigation method, device, equipment, system and storage medium | |
| WO2022062349A1 (en) | Vehicle control method, apparatus, storage medium, and electronic device | |
| Kala et al. | Planning of multiple autonomous vehicles using rrt | |
| Ferguson et al. | A reasoning framework for autonomous urban driving | |
| CN114435405A (en) | Vehicle lane changing method, device, equipment and storage medium | |
| CN113532448A (en) | Navigation method and system for automatically driving vehicle and driving control equipment | |
| CN114370874B (en) | Vehicle, vehicle path planning method and device | |
| Chang et al. | Multi-point turn decision making framework for human-like automated driving | |
| CN113548039B (en) | Automatic parking method, automatic parking device, vehicle and storage medium | |
| CN107851374B (en) | Scene assesses device, driving assist system, scene appraisal procedure | |
| Sarkar et al. | Generalized dynamic cognitive hierarchy models for strategic driving behavior | |
| CN114519931B (en) | Method and device for predicting behavior of target vehicle in intersection environment | |
| WO2020233222A1 (en) | Unmanned vehicle path control method, apparatus, and system | |
| Kala et al. | Multi-vehicle planning using RRT-connect | |
| Kala et al. | Heuristic based evolution for the coordination of autonomous vehicles in the absence of speed lanes |
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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: No. 6, Yutong Road, Guancheng Hui District, Zhengzhou, Henan 450061 Applicant after: Yutong Bus Co.,Ltd. Address before: No.1, Shibali Heyu Road, Guancheng Hui District, Zhengzhou City, Henan Province Applicant before: ZHENGZHOU YUTONG BUS Co.,Ltd. Country or region before: China |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |