CN115685992A - Automatic driving vehicle path planning method, device, vehicle and medium - Google Patents
Automatic driving vehicle path planning method, device, vehicle and medium Download PDFInfo
- Publication number
- CN115685992A CN115685992A CN202211191993.6A CN202211191993A CN115685992A CN 115685992 A CN115685992 A CN 115685992A CN 202211191993 A CN202211191993 A CN 202211191993A CN 115685992 A CN115685992 A CN 115685992A
- Authority
- CN
- China
- Prior art keywords
- reference point
- path
- vehicle
- constraint information
- local
- 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 61
- 238000005457 optimization Methods 0.000 claims abstract description 25
- 230000006870 function Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 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
- 238000011160 research Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a path planning method for an automatic driving vehicle, which comprises the steps of taking the center of a rear axle of the vehicle as a first reference point and the center of a front bumper of the vehicle as a second reference point, and acquiring a local reference path with a preset length on a target driving path of the vehicle; acquiring boundary constraint information of a first reference point at a preset position on a local reference path and boundary constraint information of the second reference point at the same moment; determining a drivable area of the vehicle on a local reference path based on the boundary constraint information of the first reference point and the second reference point at each preset position and considering the turning radius of the vehicle; and in the travelable area, performing dynamic optimization on the transverse offset and the path smoothness of the first reference point and the second reference point at the preset positions on the local reference path to generate the current local planned path of the vehicle. The scheme provided by the embodiment of the disclosure plans the vehicle path in real time, ensures that the vehicle body does not collide with the obstacle, and meets the smooth path of the kinematic constraint of the vehicle.
Description
Technical Field
The present disclosure relates to the field of autonomous vehicle control, and in particular, to a method, an apparatus, a vehicle, and a medium for planning a route of an autonomous vehicle.
Background
When the automatic driving vehicle runs in an actual road traffic environment, the local path planning is required to be executed in real time according to the current position of the vehicle and the condition of the surrounding environment sensed by the sensor, so that the automatic driving vehicle can safely and smoothly bypass various obstacles around the vehicle while meeting the requirement of a structured road running boundary. Because the automatic driving vehicle has a certain volume and is an incomplete constraint system, the vehicle cannot move along any direction, and therefore, local path planning needs to ensure that any part of the vehicle body cannot collide with an obstacle on a planned driving path.
In the prior art, different methods are adopted for planning aiming at the problem of local path planning, however, the following problems exist:
(1) Planning is carried out based on a random sampling method, a series of feasible path points from a planning starting point to a planning end point are searched and connected to form a planning path, the method is uncertain in time consumption and low in efficiency due to the characteristic of random sampling, the planned path is not smooth enough, and after two adjacent feasible path points are connected, collision posterior check still needs to be carried out on line segments between the two feasible path points to determine the legality of the planned path.
(2) Planning is based on optimization methods which replace the autonomous vehicle (ADV) with a reference point, which obviously does not guarantee that the entire body will not collide when travelling along the path.
(3) Enveloping the outline of the automatic driving vehicle based on the elliptic enveloping curve, and finally solving the planned path by using a model predictive control method, wherein the method has high time consumption, millisecond-level real-time planning is difficult to realize, and on the other hand, the constraint of the elliptical envelope curve structure is conservative, so that the solution is easy to fail when the road traffic environment is slightly complex.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide a method, an apparatus, a vehicle and a medium for planning a path of an autonomous vehicle, so as to ensure that a vehicle body does not collide with an obstacle and a smooth path that satisfies kinematic constraints of the vehicle itself.
The embodiment of the disclosure provides a method for planning a path of an automatic driving vehicle, which takes the center of a rear axle of the vehicle as a first reference point and the center of a front bumper of the vehicle as a second reference point, and comprises the following steps: acquiring a local reference path with a preset length of an automatic driving vehicle on a target driving path; acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same moment, wherein the boundary constraint information comprises barrier boundary constraint and road boundary constraint; based on the boundary constraint information of the first reference point and the second reference point at each preset position, and considering the turning radius of the vehicle, determining a travelable region of the autonomous vehicle on the local reference path so that the vehicle does not collide; within the drivable region of the autonomous vehicle, and performing dynamic optimization on the lateral offset and the path smoothness of the first reference point and the second reference point at the preset position on the local reference path relative to the local reference path to generate the current local planned path of the vehicle.
Optionally, the obtaining a local reference path of a preset length of the autonomous vehicle on the target driving path includes: and acquiring lane central points of the target driving path and sequentially connecting the lane central points to form a local reference path with a preset length.
Alternatively to this, the first and second parts may, the obtaining of the boundary constraint information of the first reference point at a preset position on the local reference path, and boundary constraint information of the second reference point at the same time, including: acquiring boundary constraint information of the positions of the first reference point every other preset step length by taking a preset step length as a sampling period; acquiring the position of the second reference point at the same moment based on the position of the first reference point and by considering the orientation variable of the vehicle; determining boundary constraint information of the second reference point based on the second reference point location.
Optionally, the determining, based on boundary constraint information of the first reference point and the second reference point at each preset position, a travelable region of the autonomous vehicle on the local reference path includes: acquiring obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the automatic driving vehicle at each preset position based on boundary constraint information and vehicle width geometric information of the first reference point and the second reference point at each preset position; converting the obstacle avoidance constraint information of the two front wheels into collision avoidance constraint information of a first reference point; converting the obstacle avoidance constraint information of the two rear wheels into collision avoidance constraint information of a second reference point; and determining a drivable area of the automatic driving vehicle on the local reference path based on the obstacle avoidance constraint information of the first reference point and the obstacle avoidance constraint information of the second reference point at each preset position.
Optionally, the obtaining obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the autonomous vehicle at each preset position based on the boundary constraint information of the first reference point and the second reference point at each preset position includes: determining the positions of two rear wheels of the automatic driving vehicle according to the position of the first reference point and the vehicle width geometrical information; and depending on the current position of said second reference point, determining the positions of two front wheels of the autonomous vehicle; respectively acquiring obstacle avoidance constraint information of the positions of the two rear wheels based on the boundary constraint information of the first reference point; and respectively acquiring obstacle avoidance constraint information of the positions of the two front wheels based on the boundary constraint information of the second reference point.
Optionally, in a travelable area of the autonomous vehicle, performing dynamic optimization on a lateral offset and a path smoothness of the first reference point and the second reference point in the autonomous vehicle with respect to a local reference path, and generating a current local planned path of the vehicle, includes: a path cost function is constructed that is, the path cost function includes: taking a plurality of preset positions of the first reference point and the second reference point along a reference path as optimization variables, and taking the smoothness of the path formed by the first reference point and the second reference point and the transverse offset of the local reference path as optimization targets; and solving the path cost function in the travelable area to generate the current local planned path of the vehicle.
Optionally, the method further includes: and the automatic driving vehicle drives along the local planned path, and when the automatic driving vehicle moves to the next preset position, the local reference path of the current position is optimized again to obtain the local planned path of the current position.
As another alternative embodiment, an embodiment of the present disclosure provides an automatic driving vehicle path planning apparatus, which uses a center of a rear axle of a vehicle as a first reference point and uses a center of a front bumper of the vehicle as a second reference point, including: the system comprises a reference path acquisition module, a target driving path acquisition module and a control module, wherein the reference path acquisition module is used for acquiring a local reference path with a preset length of an automatic driving vehicle on the target driving path; the boundary information acquisition module is used for acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same moment, wherein the boundary constraint information comprises barrier boundary constraint and road boundary constraint; the area calculation module is used for determining a drivable area of the automatic driving vehicle within a preset length on a target driving path based on the boundary constraint information of the first reference point and the second reference point at each preset position and considering the turning radius of the vehicle so as to prevent the vehicle from colliding; and the path planning module is used for performing dynamic optimization on the transverse offset and the path smoothness of the first reference point and the second reference point at preset positions on the local reference path in the travelable area of the automatic driving vehicle to generate the current local planned path of the vehicle.
As another alternative, the disclosed embodiment provides an autonomous vehicle, including a processor and a memory, where the memory stores computer program instructions executable by the processor, and the processor implements any of the above method steps when executing the computer program instructions.
As another alternative, the disclosed embodiments provide a non-transitory computer-readable storage medium characterized by computer program instructions stored thereon, which, when invoked and executed by a processor, implement any of the method steps described above.
Compared with the prior art, the invention at least has the following technical effects:
according to the method for planning the path of the automatic driving vehicle, the boundary constraint of a first reference point and a second reference point of the vehicle is introduced, the definition of the minimum complete boundary constraint of the real outline of the automatic driving vehicle is realized, the minimum complete boundary constraint is combined with an optimization method to obtain the optimal path, the optimal path obtained by planning is necessarily free of collision, collision posterior test detection is not needed, and the traffic capacity of the automatic driving vehicle is ensured to the maximum extent; in addition, the scale of the optimization method is determined by the preset length and the preset position in the local planning path, and the two can be configured in real time by combining with the actual situation, so that the planning of the collision-free path is ensured and the real-time performance is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present disclosure, and other drawings can be obtained according to the drawings without creative efforts for those skilled in the art.
Fig. 1 is a schematic flow chart of a method for planning a route of an autonomous vehicle according to an embodiment of the present disclosure;
fig. 2 is a flowchart illustrating a method for acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same time in the method provided by the embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating a method for determining a drivable area of the autonomous vehicle on a local reference path in the method provided by the embodiment of the disclosure;
fig. 4 is a schematic flow chart of a method for acquiring obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the autonomous vehicle at each preset position in the method provided by the embodiment of the disclosure;
fig. 5 is a schematic flow chart of a method for generating a current local planned path of a vehicle in the method provided by the embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a path planning apparatus for an autonomous vehicle according to an embodiment of the present disclosure;
fig. 7 is a schematic view of a connection structure of an electronic device according to an embodiment of the disclosure.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are some, but not all embodiments of the present disclosure. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present disclosure without any inventive step, are intended to be within the scope of the present disclosure.
The terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It should be understood that the term "and/or" as used herein is merely one type of association that describes an associated object, meaning that three relationships may exist, e.g., a and/or B may mean: a exists singly, A and B exist simultaneously, there are three cases of B alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
It should be understood that although the terms first, second, third, etc. may be used to describe relationships in embodiments of the invention, they should not be limited to these terms. These terms are only used to distinguish one relationship from another. For example, a first step may also be referred to as a second step, and similarly, a second step may also be referred to as a first step, without departing from the scope of embodiments of the present invention.
The words "if", as used herein may be interpreted as "at a time" or "when a time" or "in response to a determination" or "in response to a detection", depending on the context. Similarly, the phrases "if determined" or "if detected (a stated condition or event)" may be interpreted as "when determined" or "in response to a determination" or "when detected (a stated condition or event)" or "in response to a detection (a stated condition or event)", depending on the context.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, an element defined by the phrase "comprising" does not exclude the presence of other like elements in the article or device in which the element is included.
Autonomous vehicles refer to vehicles that may be configured to be in an autonomous driving mode in which the vehicle navigates through the environment with little or no input from the driver. Such autonomous vehicles may include a sensor system having one or more sensors, such as cameras, lidar, and the like, configured to detect information related to the operating environment of the vehicle. The vehicle and its associated controller use the detected information to navigate through the environment. Autonomous vehicles may operate in a manual mode, in a fully autonomous mode, or in a partially autonomous mode.
In one embodiment, the autonomous vehicle includes, but is not limited to, a perception and planning system, a vehicle control system, a wireless communication system, a user interface system, and a sensor system. Autonomous vehicles may also include certain common components included in a common vehicle, such as: the engine, wheels, steering wheel, transmission, etc., which may be controlled by the vehicle control system 111 and/or the sensory and planning system 110 using various communication signals and/or commands, such as, for example, acceleration signals or commands, deceleration signals or commands, steering signals or commands, braking signals or commands, etc.
The inventor finds out through research that: the automatic driving vehicle has the advantages that when the path planning is carried out, the whole contour of the vehicle is ensured not to collide with surrounding obstacles, and in the related technology, the vehicle contour is simplified into mass points or expanded and is not the whole contour of the vehicle, so that a method depending on the whole contour of the vehicle is required to be designed for path planning, the vehicle is ensured not to collide with the obstacles necessarily, and the intelligence and the safety of the automatic driving vehicle are improved.
An alternative embodiment of the present invention is described in detail below with reference to the drawings.
Referring to fig. 1, a method for planning a path of an autonomous vehicle according to an embodiment of the disclosure is shown, where the method can be applied to the sensing and planning system. In fig. 1, the route planning method for an autonomous vehicle provided by the embodiment of the disclosure at least includes S100 to S106, which are described in detail below.
S100 acquiring a local reference path with a preset length of an automatic driving vehicle on a target driving path;
in an alternative embodiment, the planner acquires the lane center points of the target driving path and connects them in turn, a local reference path of a preset length S1 is formed. Optionally, the target driving path is an optimal global path S obtained by performing a search according to a road topology, and the process does not need to consider information of various obstacles on a lane. The local reference path is a partial length path of the optimal global path, the preset length is set according to actual requirements, and illustratively, the local reference path is selected as a section of the optimal global path from the starting point S =0 to S =100 meters.
S102, with the center of a rear axle of a vehicle as a first reference point and the center of a front bumper of the vehicle as a second reference point, acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same moment, wherein the boundary constraint information comprises obstacle boundary constraint and road boundary constraint;
wherein the center of the vehicle rear axle is the midpoint of the axes of the two rear wheels, the position sensor is fixed at the center of the vehicle rear axle, the position sensor can obtain the position information of the first reference point; the vehicle front bumper is positioned at the forefront of the vehicle, a position sensor is not installed under the engine hood, and the central position of the vehicle front bumper is indirectly obtained through the first reference point position. The obstacle boundary constraint refers to boundary information of various obstacles on the lane, the outer contour of obstacles such as pedestrians, vehicles, cones; the road boundary constraint is a range formed by the coordinate information of the left and right boundaries of the lane.
In an optional embodiment, as shown in fig. 2, the acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same time includes:
s1021, taking a preset step length as a sampling period, and acquiring boundary constraint information of positions of the first reference point at intervals of the preset step length;
the preset step length d is a sampling step length, and every other preset step length corresponds to a preset position. That is, there are a plurality of preset positions, e.g., d, 2d, 3d, 4d, etc., on the local reference path, and each preset position is a sampling position of the first reference point.
It should be noted that the preset lengths may be the same or different when two path plans are executed, and the preset step lengths are the same and can be changed in real time in the planning process. The specific data of the preset length and the preset step length can be configured in real time according to actual conditions, and the flexibility is high, so that the path planning process has real-time performance.
In an alternative embodiment, the road boundary constraint information when the first reference point is at each preset position is obtained through map data. Specifically, the map data includes a lane center line coordinate series ({ (x) 0 ,y 0 ),(x 1 ,y 1 ),...,(x k ,y k ) }), lane left boundary coordinate series ({ (x) L0 ,y L0 ),(x L1 ,y L1 ),...,(x Lk ,y Lk ) }), lane right boundary coordinate series ({ (x) R0 ,y R0 ),(x R1 ,y R1 ),...,(x Rk ,y Rk ) }) which are in one-to-one correspondence, that is, a lane center coordinate corresponds to a lane left boundary coordinate and a lane right boundary coordinate. It is understood that each such coordinate pair corresponds to a cross section perpendicular to the lane direction. And obtaining the road boundary constraint information of the preset position based on the corresponding relation between the preset position and the lane center coordinate.
And simultaneously, acquiring obstacle boundary constraint information when the first reference point is at each preset position through the laser radar. Specifically, scanning the periphery of the current preset position by a laser radar to obtain obstacle point cloud information; and obtaining one or more obstacle constraints of the first reference point in the S-L space at the current position based on the obstacle point cloud information. Wherein, S in the S-L space represents a distance from the geometric center position of the current obstacle to the starting point position of the local reference path (S = 0), and L represents a lateral offset of the boundary where the center position of the obstacle is located from the local reference path, i.e., a distance perpendicular to the lane direction. Illustratively, the barrier constraints may be represented as 7-s-woven and-1-l-woven.
S1022, acquiring the position of the second reference point at the same moment based on the position of the first reference point and considering the orientation variable of the vehicle;
specifically, when the first reference point is located at the preset position, the position of the second reference point is unknown, and at this time, the position of the second reference point is obtained based on the position of the first reference point, but since the position of the second reference point is also related to the vehicle heading, the position of the second reference point is calculated based on the first reference point and the current heading of the vehicle. Alternatively, the orientation variable of the vehicle may be obtained by a lateral offset of the first reference point relative to the local reference path at the position and a change rate thereof, where the change rate is a ratio of a lateral offset amount (Δ L) of the first reference point and the local reference path twice before and after the first reference point to a travel distance (Δ S).
S1023, determining boundary constraint information of the second reference point based on the position of the second reference point.
As an optional embodiment, after the second reference point location is obtained, obtaining the road boundary constraint of the corresponding location through the map data; meanwhile, the obstacle boundary constraint of the position where the second reference point is located is obtained through the laser radar, which is specifically referred to in step S1021 for the calculation process of the road boundary constraint and the obstacle boundary constraint of the first reference point, and details are not repeated here.
In steps S1021 to S1023, for each preset position, a set of boundary constraint information of the first reference point and a set of boundary constraint information of the second reference point are obtained, that is, boundary constraint information of the first reference point and the second reference point at all preset positions on the local reference path is obtained, and the data is used as basic data for subsequently calculating obstacle avoidance constraint information of the first reference point and the second reference point.
S104, determining a travelable area of the automatic driving vehicle within a preset length on a target traveling path based on the boundary constraint information of the first reference point and the second reference point at each preset position and considering the turning radius of the vehicle so as to prevent the vehicle from colliding;
in the step, when the travelable area of the automatic driving vehicle is calculated, the second reference point is introduced without depending on the first reference point, so that the calculated travelable area is more accurate and no collision occurs. As an optional embodiment, according to boundary constraint information of the first reference point and the second reference point, obstacle avoidance constraint information of positions of a left front wheel, a right front wheel, a left rear wheel and a right rear wheel of the vehicle is obtained respectively, and then the obstacle avoidance constraint information of the four wheels is described by using constraints of the first reference point and the second reference point.
Specifically, as shown in fig. 3, the determining a travelable area of the autonomous vehicle on the local reference path based on the boundary constraint information of the first reference point and the second reference point at each preset position includes:
s1041, acquiring obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the automatic driving vehicle at each preset position based on boundary constraint information of the first reference point and the second reference point at each preset position;
specifically, as shown in fig. 4, step S1041 further includes:
s10411, determining the positions of two rear wheels of the automatic driving vehicle according to the position of the first reference point and the vehicle width geometrical information; determining the positions of two front wheels of the automatic driving vehicle according to the current position of the second reference point and the vehicle width geometric information;
the vehicle width geometric information refers to the width of the vehicle, and after the central position of a rear axle of the vehicle is known, the positions of the left rear wheel and the right rear wheel can be obtained by combining the vehicle width of the half vehicle.
S10412, respectively acquiring obstacle avoidance constraint information of the positions of the two rear wheels based on the boundary constraint information of the first reference point; respectively acquiring obstacle avoidance constraint information of the positions of the two front wheels based on the boundary constraint information of the second reference point;
and the obstacle avoidance constraint information comprises constraint conditions that the wheels cannot collide with the obstacle/road boundary when being positioned in the S-L space constrained by the obstacle boundary. In the step, boundary constraint information of the corresponding position of each wheel is obtained according to the positions of the four wheels, then the boundary constraint information of each wheel is integrated to obtain the condition which needs to be met when each wheel does not collide, the obstacle avoidance constraint information of the four wheels jointly constructs the minimum complete boundary constraint of the driving area of the automatic driving vehicle, and the process does not need to calculate the envelope curve of the automatic driving vehicle, and is more efficient and accurate.
It should be noted that one obstacle or multiple obstacles may exist at each preset position, and when calculating obstacle avoidance constraint information of two rear wheels and two front wheels, one or multiple obstacle avoidance constraint information and road boundary constraint information need to be considered at the same time.
S1042, based on the vehicle width geometric information, converting the obstacle avoidance constraint information of the two front wheels into collision avoidance constraint information of a first reference point; converting the obstacle avoidance constraint information of the two rear wheels into collision avoidance constraint information of a second reference point;
specifically, four wheel positions are known, and the distances of the wheels from the first reference point/the second reference point are also known as the vehicle width half, and position conversion can be performed based on both of the relationships. The step describes the obstacle avoidance constraint information of four wheels at the left, the right, the front and the rear of the automatic driving vehicle by the constraint at a first reference point (the center of a rear axle of the vehicle) and a second reference point (the center of a front bumper of the vehicle), and the method is considered in the path planning problem, so that the path obtained by planning is ensured to be collision-free.
And S1043, determining a travelable area of the automatic driving vehicle on the local reference path based on the obstacle avoidance constraint information of the first reference point and the obstacle avoidance constraint information of the second reference point at each preset position.
It can be understood that after obtaining the obstacle avoidance constraint information of the four wheels at each preset position, the obstacle avoidance constraint information of the first reference point and the obstacle avoidance constraint information of the second reference point at each preset position can be obtained. The set of the obstacle avoidance constraint information of the first reference point at all the preset positions and the set of all the obstacle avoidance constraint information of the second reference point form a travelable area of the automatic driving vehicle, that is, the automatic driving vehicle travels in the travelable area and cannot collide with a road boundary or an obstacle necessarily.
When the travelable area is calculated, the turning radius of the vehicle is further considered, the curvature radius of a first path curve obtained by sequentially connecting the positions of the first reference points in the planning process is not smaller than the minimum turning radius of the vehicle, and the curvature radius of a second path curve obtained by sequentially connecting the positions of the second reference points is not smaller than the minimum turning radius of the vehicle, so that the planned path meets the smoothness, namely, the vehicle is prevented from making large transverse movement within a short distance. The minimum turning radius is a distance from a turning center to a ground contact center of the front and outer turning wheels when the steering wheel is turned to the extreme position. Optionally, the value of the vehicle turning radius is greater than or equal to the minimum turning radius of the vehicle.
And S106, in the travelable area of the automatic driving vehicle, performing dynamic optimization on the transverse offset and the path smoothness of the first reference point and the second reference point on the local reference path at preset positions and the local reference path, and generating the current local planned path of the vehicle.
Specifically, in the travelable area, there are countless travel paths, and it is necessary to introduce an optimization problem when selecting which path is the most suitable, so as to obtain a locally planned path having good smoothness and fitting the local reference path to a large extent. Wherein the lateral offset is a distance of the first reference point/the second reference point in a direction perpendicular to the local reference path.
As shown in fig. 5, in the travelable area of the autonomous vehicle, performing dynamic optimization on the lateral offset and the path smoothness of the first reference point and the second reference point on the local reference path at preset positions relative to the local reference path, and generating a current local planned path of the vehicle, including:
s1061, constructing a path cost function, where the path cost function includes: taking a plurality of preset positions of the first reference point and the second reference point along the local reference path as optimization variables, the smoothness of the path formed by the first reference point and the second reference point and the transverse offset of the local reference path are used as optimization targets;
and S1062, solving the path cost function in the travelable area to generate the current local planned path of the vehicle.
Wherein the generated locally planned path comprises a series of columns spaced at preset steps d, like { (S =0, L = 0), (S = d, L = 0.3), (S =2d, L = 0.5). }, each (S, L) coordinate point representing a lateral position L of the autonomous vehicle at the S position. The optimization objective of the present application is to consider the smoothness of the solved locally planned path, that is, to avoid the situation that the vehicle needs to make a large lateral movement within a short distance, from the position (S =2d, l = 0.5) to the position (S =3d, l = 2.5), and to consider the obtained locally planned path to fit the reference path as much as possible, that is, the vehicle travels along the lane center line as much as possible when it does not collide with the obstacle.
Further, the method further comprises:
and S108, when the automatic driving vehicle runs along the local planned path and moves to the next preset position, re-optimizing the local reference path of the current position to obtain the current local planned path.
In practical applications, after the autonomous vehicle performs steps S102 to S106 at the current preset position (e.g., S = d), when the autonomous vehicle travels to the next preset position (e.g., S =2 d), the steps S102 to S106 are repeatedly performed, so that the local optimal path can be planned in real time.
According to the automatic driving path planning method, the constraint of the left, right, front and rear four-wheel positions of the vehicle is converted into the constraint of a first reference point and a second reference point of the vehicle by combining the road boundary constraint and the obstacle constraint with the vehicle width geometric information, so that the minimum complete boundary constraint of the real contour of the automatic driving vehicle is defined, the envelope curve of the automatic driving vehicle does not need to be calculated in the process, namely, any unnecessary contour expansion assumption is not made, and the method is efficient and accurate; and the local path planning is further solved based on the minimum complete boundary constraint combined optimization method, the scale of the solved problem can be configured, the real-time performance is good, the smoothness and the safety of the obtained local planned path can be ensured, and the collision posterior detection is not needed.
Example 2
As shown in fig. 6, an automatic driving path planning apparatus 600 according to an embodiment of the present invention, which uses a center of a rear axle of a vehicle as a first reference point and uses a center of a front bumper of the vehicle as a second reference point, includes:
a reference path obtaining module 610, configured to obtain a local reference path of a preset length of the autonomous vehicle on the target driving path;
a boundary information obtaining module 620, configured to obtain boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same time, where the boundary constraint information includes an obstacle boundary constraint and a road boundary constraint;
an area calculation module 630, configured to determine a drivable area of the autonomous vehicle within a preset length on a target driving path based on boundary constraint information of the first reference point and the second reference point at each preset position, and considering a turning radius of the vehicle, so that the vehicle does not collide;
and the path planning module 640 is configured to perform dynamic optimization on the lateral offset between the first reference point and the second reference point on the local reference path at a preset position and the local reference path in the travelable area of the autonomous vehicle, so as to generate a current local planned path of the vehicle.
In an optional embodiment, the boundary information obtaining module 620 is further configured to: acquiring boundary constraint information of the positions of the first reference point every other preset step length by taking a preset step length as a sampling period; acquiring the position of the second reference point at the same moment based on the position of the first reference point and by considering the orientation variable of the vehicle; and determining boundary constraint information of the second reference point based on the second reference point position.
In an alternative embodiment, the region calculating module 630 is further configured to: acquiring obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the automatic driving vehicle at each preset position based on boundary constraint information and vehicle width geometric information of the first reference point and the second reference point at each preset position;
in an optional embodiment, the area calculating module 630 specifically includes: the device comprises a position determination module 631, an obstacle avoidance information acquisition module 632, an obstacle avoidance information conversion module 633 and an obstacle avoidance information calculation module 634.
The position determining module 631 is configured to determine the positions of two rear wheels of the autonomous vehicle according to the position of the first reference point and the vehicle width geometric information; and determining the positions of two front wheels of the automatic driving vehicle according to the current position of the second reference point and the vehicle width geometrical information.
The obstacle avoidance information obtaining module 632 is configured to: respectively acquiring obstacle avoidance constraint information of the positions of the two rear wheels based on the boundary constraint information of the first reference point; and respectively acquiring obstacle avoidance constraint information of the positions of the two front wheels based on the boundary constraint information of the second reference point.
The obstacle avoidance information conversion module 633 is configured to: converting obstacle avoidance constraint information of the two front wheels into collision avoidance constraint information of a first reference point based on the vehicle width geometric information; converting the obstacle avoidance constraint information of the two rear wheels into collision avoidance constraint information of a second reference point;
the obstacle avoidance information calculating module 634 is configured to: and integrating to obtain a drivable area of the automatic driving vehicle on the local reference path based on the obstacle avoidance constraint information of the first reference point and the obstacle avoidance constraint information of the second reference point at each preset position.
In an alternative embodiment, the path planning module 640 includes a function building module 641 and a path generating module 642. The function building module 641 is configured to build a path cost function, where the path cost function includes: taking a plurality of preset positions of the first reference point and the second reference point along the local reference path as optimization variables, and taking the smoothness of the path formed by the first reference point and the second reference point and the transverse offset of the local reference path as optimization targets;
the path generation module 642 is configured to: and in the travelable area, solving the path cost function to generate the current local planned path of the vehicle.
Further, the apparatus 600 includes a real-time planning module 650, where the real-time planning module 650 is configured to re-optimize the local reference path of the current position when the autonomous vehicle travels along the local planned path and moves to a next preset position, so as to obtain the current local planned path of the vehicle.
According to the automatic driving path planning device, the constraint of the left, right, front and rear four-wheel positions of the vehicle is converted into the constraint of a first reference point and a second reference point of the vehicle by utilizing the road boundary constraint and the obstacle constraint in combination with the vehicle width geometric information, the definition of the minimum complete boundary constraint of the real outline of the automatic driving vehicle is realized, the envelope curve of the automatic driving vehicle does not need to be calculated in the process, namely, any unnecessary outline expansion assumption is not made, and the automatic driving path planning device is more efficient and accurate; and the local path planning solution is further carried out based on the minimum complete boundary constraint and an optimization method, the scale of the problem solution can be configured, the real-time performance is good, the smoothness and the safety of the obtained local planning path can be ensured, and the collision posterior detection is not needed.
Example 3
The disclosed embodiments provide an autonomous vehicle comprising a processor and a memory, the memory storing computer program instructions executable by the processor, the processor implementing the method steps as described in embodiment 1 when executing the computer program instructions.
Example 4
Embodiments of the present disclosure provide a non-transitory computer readable storage medium storing computer program instructions which, when invoked and executed by a processor, implement the method steps as described in embodiment 1.
As shown in fig. 7, the controller may include a processing device (e.g., central processing unit, graphics processor, etc.) 701 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage device 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data necessary for the operation of the electronic controller 700 are also stored. The processing apparatus 701, the ROM 702, and the RAM 803 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.
Generally, the following devices may be connected to the I/O interface 705: input devices 706 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 707 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; a storage device 708 including, for example, a hard disk; and a communication device 709. The communications device 709 may allow the electronic controller to communicate wirelessly or by wire with other controllers to exchange data. While fig. 7 illustrates an electronic controller having various devices, it is to be understood that not all of the illustrated devices are required to be implemented or provided. More or fewer devices may be alternatively implemented or provided.
In particular, according to an embodiment of the present disclosure, the process described above with reference to the flow diagram may be implemented as a controller software program. For example, embodiments of the present disclosure include a controller software program product comprising a computer program embodied on a readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via the communication means 709, or may be installed from the storage means 708, or may be installed from the ROM 702. The computer program, when executed by the processing device 701, performs the above-described functions defined in the methods of the embodiments of the present disclosure.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solutions of the present disclosure, not to limit them; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present disclosure.
Claims (10)
1. An automatic driving vehicle path planning method is characterized in that the center of a rear axle of a vehicle is taken as a first reference point, the center of a front bumper of the vehicle is taken as a second reference point, and the method comprises the following steps:
acquiring a local reference path with a preset length of an automatic driving vehicle on a target driving path;
acquiring boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same moment, wherein the boundary constraint information comprises barrier boundary constraint and road boundary constraint;
determining a travelable region of the autonomous vehicle on the local reference path based on boundary constraint information of the first reference point and the second reference point at each preset position and considering a turning radius of the vehicle so that the vehicle does not collide;
and in the travelable area of the automatic driving vehicle, performing dynamic optimization on the transverse offset and the path smoothness of the first reference point and the second reference point at the preset positions on the local reference path and the local reference path to generate the current local planning path of the vehicle.
2. The method of claim 1, wherein the obtaining of the local reference path of the autonomous vehicle on the target travel path for a preset length comprises:
and acquiring lane central points of the target driving path and sequentially connecting the lane central points to form a local reference path with a preset length.
3. The method according to claim 1, wherein the obtaining boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same time comprises:
acquiring boundary constraint information of the position of the first reference point at every other preset step length by taking a preset step length as a sampling period;
acquiring the position of the second reference point at the same moment based on the position of the first reference point and by considering the orientation variable of the vehicle;
determining boundary constraint information for the second reference point based on the second reference point location.
4. The method of claim 1, wherein determining the travelable region of the autonomous vehicle on the local reference path based on the boundary constraint information of the first and second reference points at each preset location comprises:
acquiring obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the automatic driving vehicle at each preset position based on boundary constraint information and vehicle width geometric information of the first reference point and the second reference point at each preset position;
converting the obstacle avoidance constraint information of the two front wheels into collision avoidance constraint information of a first reference point; converting the obstacle avoidance constraint information of the two rear wheels into collision avoidance constraint information of a second reference point;
and determining a travelable area of the automatic driving vehicle on the local reference path based on the obstacle avoidance constraint information of the first reference point and the obstacle avoidance constraint information of the second reference point at each preset position.
5. The method of claim 4, wherein the obtaining obstacle avoidance constraint information of two front wheels and obstacle avoidance constraint information of two rear wheels of the autonomous vehicle at each preset position based on the boundary constraint information of the first reference point and the second reference point at each preset position and the vehicle width geometric information comprises:
determining the positions of two rear wheels of the automatic driving vehicle according to the position of the first reference point and the vehicle width geometrical information; determining the positions of two front wheels of the automatic driving vehicle according to the current position of the second reference point and the vehicle width geometric information;
respectively acquiring obstacle avoidance constraint information of the positions of the two rear wheels based on the boundary constraint information of the first reference point; and respectively acquiring obstacle avoidance constraint information of the positions of the two front wheels based on the boundary constraint information of the second reference point.
6. The method of claim 1, wherein performing dynamic optimization of lateral offset and path smoothness of a first reference point and a second reference point from a local reference path at preset locations on the local reference path within a drivable region of the autonomous vehicle to generate a current locally planned path for the vehicle comprises:
constructing a path cost function, the path cost function comprising: taking a plurality of preset positions of the first reference point and the second reference point along the local reference path as optimization variables, and taking the smoothness of the path formed by the first reference point and the second reference point and the transverse offset of the path with the local reference path as optimization targets;
and solving the path cost function in the travelable area to generate the current local planned path of the vehicle.
7. The method according to any one of claims 1-6, further comprising:
and the automatic driving vehicle drives along the local planned path, and when the automatic driving vehicle moves to the next preset position, the local reference path of the current position is optimized again to obtain the current local planned path.
8. An automatic vehicle route planning device, characterized by, with vehicle rear axle center as a first reference point, with vehicle front bumper center as a second reference point, includes:
the reference path acquisition module is used for acquiring a local reference path with a preset length on a target running path of the automatic driving vehicle;
a boundary information obtaining module, configured to obtain boundary constraint information of the first reference point at a preset position on the local reference path and boundary constraint information of the second reference point at the same time, where the boundary constraint information includes an obstacle boundary constraint and a road boundary constraint;
the area calculation module is used for determining a drivable area of the automatic driving vehicle within a preset length on a target driving path based on the boundary constraint information of the first reference point and the second reference point at each preset position and considering the turning radius of the vehicle so as to prevent the vehicle from colliding;
and the path planning module is used for performing dynamic optimization on the transverse offset and the path smoothness of the first reference point and the second reference point at preset positions on the local reference path and the local reference path in the travelable area of the automatic driving vehicle to generate the current local planned path of the vehicle.
9. An autonomous vehicle comprising a processor and a memory, characterized in that the memory stores computer program instructions executable by the processor, which when executed by the processor, carry out the method steps of any of claims 1-7.
10. A non-transitory computer-readable storage medium, having stored thereon computer program instructions, which when invoked and executed by a processor, perform the method steps of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211191993.6A CN115685992B (en) | 2022-09-28 | 2022-09-28 | Automatic driving vehicle path planning method and device, vehicle and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211191993.6A CN115685992B (en) | 2022-09-28 | 2022-09-28 | Automatic driving vehicle path planning method and device, vehicle and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115685992A true CN115685992A (en) | 2023-02-03 |
| CN115685992B CN115685992B (en) | 2024-07-23 |
Family
ID=85065506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211191993.6A Active CN115685992B (en) | 2022-09-28 | 2022-09-28 | Automatic driving vehicle path planning method and device, vehicle and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115685992B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116576875A (en) * | 2023-05-23 | 2023-08-11 | 北京斯年智驾科技有限公司 | Real-time planning method and system for four-wheel steering vehicle outline collision-free local path |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147105A (en) * | 2019-05-27 | 2019-08-20 | 安徽江淮汽车集团股份有限公司 | Controlling of path thereof, equipment, storage medium and the device of automatic driving vehicle |
| CN112379679A (en) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | Unmanned vehicle local path planning method |
| CN112937557A (en) * | 2021-03-09 | 2021-06-11 | 东风汽车集团股份有限公司 | Curvature control-based passenger-riding parking path planning method and system |
| US20210237771A1 (en) * | 2020-06-30 | 2021-08-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for vehicle avoiding obstacle, electronic device, and computer storage medium |
| CN115042812A (en) * | 2022-06-24 | 2022-09-13 | 白犀牛智达(北京)科技有限公司 | Automatic stop parking method, device, medium and electronic equipment |
-
2022
- 2022-09-28 CN CN202211191993.6A patent/CN115685992B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110147105A (en) * | 2019-05-27 | 2019-08-20 | 安徽江淮汽车集团股份有限公司 | Controlling of path thereof, equipment, storage medium and the device of automatic driving vehicle |
| US20210237771A1 (en) * | 2020-06-30 | 2021-08-05 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method for vehicle avoiding obstacle, electronic device, and computer storage medium |
| CN112379679A (en) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | Unmanned vehicle local path planning method |
| CN112937557A (en) * | 2021-03-09 | 2021-06-11 | 东风汽车集团股份有限公司 | Curvature control-based passenger-riding parking path planning method and system |
| CN115042812A (en) * | 2022-06-24 | 2022-09-13 | 白犀牛智达(北京)科技有限公司 | Automatic stop parking method, device, medium and electronic equipment |
Non-Patent Citations (1)
| Title |
|---|
| 任;郑玲;张巍;杨威;熊周兵;: "基于模型预测控制的智能车辆主动避撞控制研究", 汽车工程, no. 04, 25 April 2019 (2019-04-25) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116576875A (en) * | 2023-05-23 | 2023-08-11 | 北京斯年智驾科技有限公司 | Real-time planning method and system for four-wheel steering vehicle outline collision-free local path |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115685992B (en) | 2024-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11390300B2 (en) | Method for using lateral motion to optimize trajectories for autonomous vehicles | |
| CN114270142B (en) | Unstructured vehicle path planner | |
| EP3517893B1 (en) | Path and speed optimization fallback mechanism for autonomous vehicles | |
| US20200302662A1 (en) | System and Methods for Generating High Definition Maps Using Machine-Learned Models to Analyze Topology Data Gathered From Sensors | |
| CN109491376B (en) | Dynamic programming and gradient descent based decision and programming for autonomous vehicles | |
| US10515321B2 (en) | Cost based path planning for autonomous driving vehicles | |
| US10754339B2 (en) | Dynamic programming and quadratic programming based decision and planning for autonomous driving vehicles | |
| US10571922B2 (en) | Context-specific tolerance for motion control in autonomous vehicles | |
| EP3638981A2 (en) | Fusion framework and batch alignment of navigation information for autonomous navigation | |
| JP2021524410A (en) | Determining the drive envelope | |
| US11753006B2 (en) | Representing objects in a surrounding environment of a vehicle using a frenet coordinate system | |
| CN110345957A (en) | Vehicle route identification | |
| US11586209B2 (en) | Differential dynamic programming (DDP) based planning architecture for autonomous driving vehicles | |
| CN112839853A (en) | Responsive vehicle control | |
| US20220017112A1 (en) | Systems and Methods for Generating Vehicle Corridors to Improve Path Planning Efficiency | |
| US20240174239A1 (en) | Route-relative trajectory generation and optimization computations incorporating vehicle sideslip | |
| WO2023147769A1 (en) | Systems, methods, and computer-readable media for spatio-temporal motion planning | |
| CN115685992B (en) | Automatic driving vehicle path planning method and device, vehicle and medium | |
| EP3838697A1 (en) | Speed planning using a speed planning guideline for idle speed of autonomous driving vehicles | |
| CN115246394A (en) | Intelligent vehicle overtaking obstacle avoidance method | |
| CN117916682A (en) | Motion planning using a time-space convex corridor | |
| US20230415739A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects | |
| US20230415781A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects | |
| US20230415736A1 (en) | Systems and methods for controlling longitudinal acceleration based on lateral objects | |
| US20230373523A1 (en) | Systems and methods for biasing a trajectory of an autonomous vehicle while moving in a lane |
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 |