CN115540892A - Obstacle-detouring terminal point selection method and system for fixed line vehicle - Google Patents
Obstacle-detouring terminal point selection method and system for fixed line vehicle Download PDFInfo
- Publication number
- CN115540892A CN115540892A CN202211495730.4A CN202211495730A CN115540892A CN 115540892 A CN115540892 A CN 115540892A CN 202211495730 A CN202211495730 A CN 202211495730A CN 115540892 A CN115540892 A CN 115540892A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- path planning
- end point
- obstacle detouring
- detouring
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3461—Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types, segments such as motorways, toll roads, ferries
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A fixed line vehicle obstacle avoidance terminal selection method and system relate to the field of fixed line obstacle avoidance. Determining a position point at a preset distance in the fixed line as an initial obstacle detouring end point; starting iteration of the obstacle detouring end point from the initial obstacle detouring end point; determining a position point at a search distance along the barrier-detouring terminal point advancing direction in the fixed line as a candidate barrier-detouring terminal point; obtaining an obstacle closest to the candidate obstacle detouring end point, and obtaining the distance between the obstacle and the candidate obstacle detouring end point; if the distance is larger than the set threshold, setting the candidate obstacle detouring end point as a new obstacle detouring end point and continuing to iterate the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, and stopping the iteration of the obstacle detouring end point to complete path planning; and reducing the search distance to update the search distance and performing next path planning according to the updated search distance after completing the path planning each time, and stopping the iteration of the path planning until the stopping condition of the path planning is reached.
Description
Technical Field
The invention relates to the field of fixed line obstacle avoidance, in particular to a fixed line vehicle obstacle avoidance end point selection method and system.
Background
The automatic driving vehicle running on a fixed line is widely applied to various types of park factories and some specific test scenes. One of the essential functions of such vehicles is to bypass obstacles present on the driving route and to return to the fixed route as quickly as possible to complete the intended task. If the obstacle avoidance terminal point is not reasonably selected, problems such as that the vehicle cannot successfully complete obstacle avoidance route planning, the vehicle cannot return to the route to continue driving as soon as possible, and the vehicle cannot be re-obstacle after returning to a fixed route can occur.
The automatic driving vehicle running along the fixed line inevitably encounters an obstacle detouring scene, the vehicle deviates from the fixed line in the obstacle detouring process, and the vehicle can return to the fixed line to run as soon as possible by selecting a proper obstacle detouring terminal point. Meanwhile, the obstacle detouring end point is selected by considering the obstacle distribution condition and the position of the line end point, so that the condition that the obstacle detouring is required for multiple times or the line end point cannot be reached is avoided. Therefore, in the current selection of the obstacle detouring end point, the success rate and the rationality of the selection of the obstacle detouring end point need to be considered, and the situation that the obstacle advances to a line in different forms of obstacles needs to be considered, so that an obstacle detouring end point selection system with a global view is needed to be designed.
Disclosure of Invention
In order to solve the problems, the invention provides a barrier-bypassing end point selection method and system for automatic driving of a fixed line.
According to a first aspect, an embodiment provides a method for obstacle detouring end point selection for fixed line autopilot, comprising:
acquiring a fixed line, a first barrier on the fixed line and a terminal point of the fixed line;
determining a position point at a preset distance along the advancing direction of the first obstacle in the fixed line as an initial obstacle detouring end point;
and iterating the path planning according to the search distance, wherein each path planning comprises the following steps:
starting from the initial obstacle detouring endpoint, performing an iteration of the obstacle detouring endpoint, wherein the iteration of the obstacle detouring endpoint comprises:
obtaining the searching distance of the path planning;
determining a position point at a search distance along the current obstacle detouring end point advancing direction in the fixed line as a candidate obstacle detouring end point;
judging whether the vehicle is in collision when being positioned at the candidate obstacle detouring terminal point;
if the vehicle is determined to be located at the candidate obstacle detouring terminal point and no collision occurs, acquiring an obstacle closest to the candidate obstacle detouring terminal point in the fixed line, and acquiring the distance between the obstacle and the candidate obstacle detouring terminal point;
if the distance is larger than a set threshold value, setting the candidate obstacle detouring end point as a new obstacle detouring end point, continuing iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, stopping the iteration of the obstacle detouring end point, and finishing the path planning;
and when the path planning is finished once, reducing the search distance to update the search distance, and performing the next path planning according to the updated search distance until the stop condition of the path planning is reached, stopping the iteration of the path planning, and enabling the vehicle to run according to the obstacle-detouring terminal point determined by the last path planning.
In an embodiment, the step of reducing the search distance to update the search distance each time the path planning is completed, and performing next path planning according to the updated search distance until a stop condition of the path planning is reached stops the iteration of the path planning includes:
and obtaining the iteration times of the path planning and the iteration time of the path planning, and stopping the iteration of the path planning when the iteration time of the path planning exceeds the set time or the iteration times of the path planning exceeds the set times.
In one embodiment, the method further comprises,
and acquiring updated driving boundary environment and obstacle information each time the candidate obstacle detouring end point is determined.
In one embodiment, the reducing the search distance to update the search distance includes:
half of the search distance is reduced to update the search distance.
According to a second aspect, there is provided in an embodiment a fixed line autopilot barrier terminal selection system comprising:
the path operation unit comprises a barrier-bypassing end point screening module and a path planning module;
the obstacle detouring terminal screening module acquires a fixed line, a first obstacle on the fixed line and a terminal of the fixed line, and determines a position point at a preset distance along the advancing direction of the first obstacle in the fixed line as an initial obstacle detouring terminal; and iterating the path planning by the obstacle-detouring end point screening module according to the searching distance, wherein each path planning comprises the following steps:
starting from the initial obstacle detouring endpoint, performing an iteration of the obstacle detouring endpoint, wherein the iteration of the obstacle detouring endpoint comprises:
obtaining the searching distance of the path planning;
determining a position point at a search distance along the current obstacle detouring end point advancing direction in the fixed line as a candidate obstacle detouring end point;
judging whether the vehicle is in collision when being positioned at the candidate obstacle detouring terminal point;
if the vehicle is determined to be located at the candidate obstacle detouring terminal point and no collision occurs, acquiring an obstacle closest to the candidate obstacle detouring terminal point in the fixed line, and acquiring the distance between the obstacle and the candidate obstacle detouring terminal point;
if the distance is larger than a set threshold value, setting the candidate obstacle detouring end point as a new obstacle detouring end point, continuing iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, stopping the iteration of the obstacle detouring end point, and finishing the path planning;
reducing the search distance to update the search distance each time path planning is completed, and performing next path planning according to the updated search distance until a stop condition of the path planning is reached, and stopping iteration of the path planning; and the path planning module acquires the obstacle detouring end point determined by the last path planning so as to complete the path planning.
In an embodiment, the step of reducing the search distance to update the search distance each time the path planning is completed, and performing next path planning according to the updated search distance until a stop condition of the path planning is reached stops the iteration of the path planning includes:
and the obstacle detouring end point screening module acquires the iteration times of path planning and the iteration time of the path planning, and stops the iteration of the path planning when the iteration time of the path planning exceeds the set time or the iteration times of the path planning exceeds the set times.
In one embodiment, the system further comprises a vehicle control unit, wherein the vehicle control unit acquires a barrier-detouring end point determined by the last path planning sent by the path planning module for path following, and controls the vehicle to complete barrier detouring.
In one embodiment, the system further comprises a global environment and obstacle information sensing unit, configured to acquire the driving boundary environment and the obstacle information, and acquire updated driving boundary environment and obstacle information each time the candidate obstacle detouring endpoint is determined.
In one embodiment, the reducing the search distance to update the search distance includes:
the search distance is reduced by half to update the search distance.
According to a third aspect, an embodiment provides a computer readable storage medium having a program stored thereon, the program being executable by a processor to implement the method as described above.
The obstacle detouring end point selecting method, system and computer readable storage medium for fixed line automatic driving according to the above embodiments. Determining a position point of a preset distance along the advancing direction of a first obstacle in a fixed line as an initial obstacle detouring end point, obtaining a search distance of path planning, determining a position point at the search distance along the advancing direction of the current obstacle detouring end point in the fixed line as a candidate obstacle detouring end point from the initial obstacle detouring end point, determining that a vehicle is located at the candidate obstacle detouring end point and cannot collide, obtaining an obstacle closest to the advancing direction of the candidate obstacle detouring end point in the fixed line, obtaining the distance from the candidate obstacle detouring end point to the obstacle, setting the candidate obstacle detouring end point as a new obstacle detouring end point when the distance is larger than a set threshold, continuing iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, and stopping iteration of the obstacle detouring end point so as to complete the path planning. And when each iteration is completed, reducing the search distance to update the search distance, and performing next path planning according to the updated search distance until a stop condition of the path planning is reached. The method and the device have the advantages that the candidate obstacle-detouring destination is repeatedly searched, the interference of the environment is eliminated to the maximum extent, and the vehicle can return to the fixed driving route as soon as possible according to the path planned by the found destination to complete the established task. Meanwhile, continuous barrier-avoiding process caused by the continuous obstacles is avoided.
Drawings
FIG. 1 is a flow diagram of a method for obstacle avoidance end selection for fixed line autopilot in one embodiment;
FIG. 2 is a flow diagram of an iterative process for each path planning in one embodiment;
FIG. 3 is a flow diagram of a process for multiple path planning loop iterations in one embodiment;
FIG. 4 is a schematic illustration of an example barrier avoidance process;
FIG. 5 is a schematic diagram of an obstacle detour end selection system for fixed line autopilot in one embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous specific details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" as used herein includes both direct and indirect connections (couplings), unless otherwise specified.
The present application focuses on the barrier-detour end-point selection method and does not discuss the path planning method in the case where the start and end points of a fixed route are known. The method and the device can be completely applied under the condition that the vehicle has a global view, the global view means that the vehicle can sense static or moving obstacles appearing on a fixed line, and common sensing means comprise a global camera, an indoor UWB positioning tag and an outdoor RTK positioning device. In addition, communication links between each tag or detection means and the vehicle are needed, and communication is usually performed by using a cloud background or a local area network. Without a global view, the method of the present application can also be implemented using only local perception results around the vehicle itself, but the effect is compromised. Most of the current researches do not discuss the obstacle avoidance terminal selection method in detail, or other planning methods are adopted to avoid the terminal selection process, and the method is difficult to adapt to the requirements of 'fixed line operation' and 'obstacle avoidance returning to the fixed line as soon as possible'.
The method is designed for automatic obstacle detouring of a vehicle, focuses on processing information collected by a camera, judging the traffic width in the obstacle detouring process and judging whether the vehicle has obstacle detouring feasibility or not so as to guarantee the feasibility and comfort in the obstacle detouring process, and does not relate to an obstacle detouring end point selection method. The determination of the obstacle avoidance feasibility is performed by the path planning module in the application, and the determination is not required to be displayed.
Also disclosed are a method, a device, an electronic apparatus and a medium for obstacle avoidance driving, wherein the method emphasizes the following scenes: when the vehicle is too close to the obstacle, the vehicle needs to go back for a certain distance and then go forward to perform the obstacle avoidance process. Since the process is performed in two steps, the planning is also performed in two steps. The method specifically comprises the following steps:
firstly, in the backward movement process, scattering points at a preset distance, then judging point by point, and selecting a reasonable point as a terminal point of backward movement planning. The method is different from the method, the selection of the end point of the method deviates from a fixed driving route, and the distance of the preset point is fixed and cannot be adapted to enough conditions.
And secondly, in the process of barrier avoidance, selecting a planning terminal point as a terminal point of a barrier avoidance area, wherein the barrier avoidance area refers to an area capable of bypassing the barrier. The obstacle-detouring end point of the method is not on a fixed line, and the method is different from the method in the following aspects: when the obstacle detouring end point is not on the fixed line, it is difficult to ensure that the vehicle can quickly return to the fixed line.
The application scenarios of the method are consistent with the discussion method of the application, and the method aims at the process that the vehicle runs on the fixed line, needs to be barrier-detoured, and returns to the fixed line to run. The obstacle detouring end point selecting method in the method is characterized in that a preset distance mode is adopted, and one point which is a fixed distance away from the current vehicle position is selected as an obstacle detouring end point. In the method, the barrier starting point is selected in two ways: (1) Selecting a point on a fixed line with a fixed distance from an obstacle as a starting point; (2) And (3) fine adjustment is performed on the basis of the step (1) according to the motion state of the vehicle, so that the vehicle is prevented from being overturned and the like. The present application differs from this method in that it does not address the situation where there is an obstacle in front of the obstacle detour end point and in the vicinity of the end line.
The above-described method has been disclosed with limitations on the choice of barrier-bypassing end point: firstly, the end point selection is usually carried out by adopting a preset distance or direction mode, the candidate obstacle-detouring end points are fewer, the coverage area is smaller, and the relation of more obstacles is not considered; secondly, a point scattering mode in the range is adopted, more choices are provided, but most of the end points are far away from the driving route and cannot be directly returned to the fixed driving route. The above limitations may eventually lead to planning failures, or to a route being unreasonable and not returning quickly to the vicinity of a fixed driving route, affecting the completion of a particular task.
Aiming at the problems and limitations, a reasonable obstacle detouring terminal point is selected on a fixed moving line by combining global obstacle information and considering the possible positions of obstacles through a general disc and a circular calculation method so as to guide a vehicle and complete an obstacle detouring function.
Referring to fig. 1, the present application provides a method for selecting an obstacle detouring endpoint for automatic fixed-line driving, which includes an iterative process of path planning for each time as shown in fig. 2 and a process of multiple iterations of path planning loops as shown in fig. 3. The following is specifically described.
Step S100: an initial barrier-bypassing endpoint is determined.
Referring to the flowchart of each iteration of path planning shown in fig. 2, in some embodiments, a fixed line, a first obstacle on the fixed line, and an end point of the fixed line are obtained first, and a position point at a preset distance along a forward direction of the first obstacle in the fixed line is determined as an initial obstacle detouring end point. In some embodiments, the direction of travel along the first obstacle is the direction of travel of the fixed line.
In some embodiments, referring to fig. 4, taking fig. 4 as an example, the fixed line is as shown in fig. 4, the vehicle is at the current position a of the vehicle in fig. 4, the first obstacle on the fixed line is b in fig. 4, b1 is the front edge position of the obstacle, and b2 is the rear edge position of the obstacle. The first obstacle advancing direction is the advancing direction of the first obstacle b in fig. 4, and the initial obstacle detouring end point in the direction is determined as g in fig. 4.
In some embodiments, the predetermined distance for determining the initial obstacle detour end is the length b2 to g in fig. 4, and the predetermined distance is influenced by the parameters of the vehicle itself, and if the fixed path has a turning condition and the minimum turning radius is larger, the predetermined distance can be increased appropriately.
Step S200: candidate barrier-bypassing endpoints are determined.
In some embodiments, a search distance of the path plan is obtained, and from an initial obstacle detouring end point, a position point in the fixed line at the search distance along the current obstacle detouring end point advancing direction is determined as a candidate obstacle detouring end point.
In some embodiments, updated driving boundary environment and obstacle information may need to be obtained each time the candidate obstacle detour end point is determined. Because the environment is typically dynamically changing, updating the environment may cause each candidate obstacle crossing point to be based on the most recent ambient conditions.
Taking fig. 4 as an example, the above process moves a search distance from the initial obstacle detouring end point g along the current obstacle detouring end point advancing direction, and obtains a candidate obstacle detouring end point e. In fig. 4, the search distance is a distance g to e.
Step S300: and judging that the candidate obstacle detouring end points do not collide and meet the space reasonable condition.
In some embodiments, whether the vehicle is located at the candidate obstacle detouring end point and collides or not is judged, if it is determined that the vehicle is located at the candidate obstacle detouring end point and does not collide, an obstacle closest to the candidate obstacle detouring end point in the fixed line is obtained, and the distance between the obstacle and the candidate obstacle detouring end point is obtained. And if the distance is larger than the set threshold, setting the candidate obstacle detouring end point as a new obstacle detouring end point.
In some embodiments, the candidate obstacle detouring terminal point is checked first, whether the vehicle collides with the candidate obstacle detouring terminal point is checked first, if so, updated driving boundary environment and obstacle information are obtained again, and a new candidate obstacle detouring terminal point is determined again; if the collision does not occur, further judging whether the candidate obstacle detouring end point meets a space reasonable condition, namely acquiring the distance between the candidate obstacle detouring end point and an obstacle closest to the candidate obstacle detouring end point, judging whether the distance is greater than a threshold value, and if the distance is smaller than the threshold value, acquiring updated driving boundary environment and obstacle information again, and determining a new candidate obstacle detouring end point again; and if the candidate barrier-bypassing end point is larger than the threshold value, determining the candidate barrier-bypassing end point as a new barrier-bypassing end point.
Taking fig. 4 as an example, the above process determines whether the candidate obstacle detouring end point satisfies a space reasonable condition, that is, the distance from the candidate obstacle detouring end point e to the nearest obstacle in front of the candidate obstacle detouring end point e, that is, the distance from e to c1, is checked. c is the obstacle closest to the candidate obstacle detouring end point e, c1 is the front edge position of the obstacle, and c2 is the rear edge position of the obstacle. This distance reflects the amount of space in front of the vehicle, i.e., the amount of space that can be traveled forward after the vehicle has completed obstacle detouring. This distance is dictated by the length of the body and the distance the vehicle is required to travel along the route for the task involved. If the vehicle body is long, the distance is preferably large, otherwise a subsequent obstacle difficult to circumvent may occur; if the task in question requires that the vehicle be on a fixed route for as long as possible, the distance should be as small as possible within reasonable limits, only so that the vehicle can stay on the route for a sufficiently long time.
Step S400: and setting the candidate obstacle detouring end point as a new obstacle detouring end point, and stopping iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, so as to complete the path planning.
In some embodiments, when the candidate barrier-bypassing end point satisfies the no-collision condition and satisfies the space reasonable condition, the candidate barrier-bypassing end point is determined as a new barrier-bypassing end point. After the candidate obstacle detouring end point is set as a new obstacle detouring end point, the next round of search is carried out, namely the new obstacle detouring end point advances for a search distance along the fixed line, and the judgment in the steps S200 and S300 is carried out again to obtain the new candidate obstacle detouring end point. Taking fig. 4 as an example, the candidate barrier bypassing end point determined in step S300 is e, the candidate barrier bypassing end point e is determined as a new barrier bypassing end point, then the search distance is advanced along the fixed line, and step S200 and step S300 are performed to perform re-judgment to obtain a new candidate barrier bypassing end point f. And continuously and circularly iterating until the new barrier-bypassing end point is the end point of the fixed line, namely the end point f of the fixed line in the figure 4 is reached, stopping the iteration of the barrier-bypassing end point, and outputting the new barrier-bypassing end point determined by each iteration so as to complete the path planning. And performing path planning by using the obstacle detouring end point of multiple iterations, judging whether the path planning is successfully completed or not by the path planner, if the path planner gives a result indicating that the current path planning is successful, and if the path planner does not return a result indicating that the current path planning is failed. In some embodiments, different path planners output results in different forms.
Step S500: and when the path planning is finished once, reducing the search distance to update the search distance, and performing the next path planning according to the updated search distance until the stop condition of the path planning is reached, stopping the iteration of the path planning, and driving the vehicle according to the obstacle detouring terminal point determined by the last path planning.
In some embodiments, after completing one path planning, please refer to fig. 3, which is a flowchart of a multiple path planning loop iteration process, obtaining an iteration number of the path planning and an iteration time of the path planning, and stopping the iteration of the path planning when the iteration time of the path planning exceeds a set time or the iteration number of the path planning exceeds the set number. In some embodiments, half of the search distance is reduced to update the search distance. The purpose of this is to make a more intensive search on the subsequent fixed line, ensuring that a reasonable candidate barrier-bypassing endpoint can be found.
In some embodiments, the iteration number of the path planning is comprehensively influenced by the time spent by the planning algorithm, the total acceptable waiting time, the length of the fixed line, the search distance and the like, and can be set according to the actual situation. Preferably, two path plans can be covered within the set iteration number of the obstacle detouring end point.
According to the method from the step S100 to the step S500, repeated search of the candidate obstacle detouring destination can be achieved, the interference of the environment is eliminated to the maximum extent, the found candidate obstacle detouring destination and the route planned by the route enable the vehicle to return to the fixed driving route as soon as possible to complete the set task, and meanwhile, the continuous obstacle detouring process caused by the continuous obstacles is avoided.
Referring to fig. 5, the present application further provides an obstacle detouring end point selecting system 600 for automatic fixed line driving, which includes a global environment and obstacle information sensing unit 610, a vehicle-mounted positioning unit 620, a path calculating unit 630, and a vehicle control unit 640.
The global environment and obstacle information sensing unit 610 is configured to output global environment information and obstacle information, especially environment and obstacle information near a fixed moving route of a vehicle, which are necessary information for obstacle avoidance tasks. The environment information mainly refers to a road boundary range where the vehicle moves, and the obstacle information mainly includes the position and the outer dimension of the obstacle.
The vehicle-mounted positioning unit 620 is configured to output position information of the vehicle in the global environment, where the position information is a starting point of path planning, and after an initial obstacle detouring end point is found by using the starting point of the path planning as a start, a subsequent candidate obstacle detouring end point is selected.
The path calculation unit 630 includes a barrier-detour end point screening module 631 and a path planning module 632. The obstacle detouring end point screening module 631 acquires the fixed line, the first obstacle on the fixed line and the end point of the fixed line, and determines a position point at a preset distance in the fixed line along the advancing direction of the first obstacle as an initial obstacle detouring end point.
The obstacle detouring end point screening module 631 iterates path planning according to the search distance, wherein each path planning includes: starting from an initial barrier-bypassing endpoint, performing an iteration of the barrier-bypassing endpoint, wherein the iteration of the barrier-bypassing endpoint comprises: obtaining the searching distance of the path planning; determining a position point at a search distance along the current obstacle detouring end point advancing direction in the fixed line as a candidate obstacle detouring end point; judging whether the vehicle is in collision when being positioned at the candidate obstacle detouring terminal point; and if the vehicle is determined to be located at the candidate obstacle detouring end point and no collision occurs, acquiring an obstacle which is closest to the candidate obstacle detouring end point in the fixed line, and acquiring the distance between the obstacle and the candidate obstacle detouring end point. And if the distance is greater than the set threshold, setting the candidate obstacle detouring end point as a new obstacle detouring end point, continuing iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, stopping iteration of the obstacle detouring end point, and finishing the path planning.
And reducing the search distance to update the search distance after completing the path planning once, and performing the next path planning according to the updated search distance until reaching the stop condition of the path planning, and stopping the iteration of the path planning. The path planning module 632 obtains the obstacle detouring end point determined by the last path planning to complete the path planning.
In some embodiments, the obstacle detouring end point screening module 631 obtains the iteration number of the path plan and the iteration time of the path plan, and stops the iteration of the path plan when the iteration time of the path plan exceeds a set time or the iteration number of the path plan exceeds the set number.
In some embodiments, the vehicle control unit 640 obtains the obstacle detouring end point determined by the last route planning sent by the route planning module 632 to perform route following, and controls the vehicle to complete obstacle detouring.
In some embodiments, the driving boundary environment and the obstacle information transmitted by the global environment and obstacle information sensing unit 610 are acquired each time the candidate obstacle detouring end point is determined.
In some embodiments, each time the path planning is completed, half of the search distance is reduced to update the search distance, and the next path planning is performed according to the updated search distance until a stop condition of the path planning is reached, and the iteration of the path planning is stopped.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (10)
1. A method for selecting an obstacle detouring end point of automatic fixed line driving is characterized by comprising the following steps:
acquiring a fixed line, a first barrier on the fixed line and a terminal point of the fixed line;
determining a position point at a preset distance along the advancing direction of the first obstacle in the fixed line as an initial obstacle detouring end point;
and iterating the path planning according to the search distance, wherein each path planning comprises the following steps:
starting from the initial obstacle detouring endpoint, performing an iteration of the obstacle detouring endpoint, wherein the iteration of the obstacle detouring endpoint comprises:
obtaining the searching distance of the path planning;
determining a position point at a search distance along the current obstacle detouring end point advancing direction in the fixed line as a candidate obstacle detouring end point;
judging whether the vehicle is in collision when being positioned at the candidate obstacle detouring terminal point;
if the vehicle is determined to be located at the candidate obstacle detouring terminal point and no collision occurs, acquiring an obstacle closest to the candidate obstacle detouring terminal point in the fixed line, and acquiring the distance between the obstacle and the candidate obstacle detouring terminal point;
if the distance is larger than a set threshold value, setting the candidate obstacle detouring end point as a new obstacle detouring end point, continuing to iterate the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, stopping the iteration of the obstacle detouring end point, and finishing the path planning;
and when the path planning is finished once, reducing the search distance to update the search distance, and performing the next path planning according to the updated search distance until the stop condition of the path planning is reached, stopping the iteration of the path planning, and enabling the vehicle to run according to the obstacle-detouring terminal point determined by the last path planning.
2. The method for selecting an obstacle detouring end point of fixed line autopilot as claimed in claim 1, wherein said reducing the search distance to update the search distance each time a path planning is completed, and performing a next path planning according to the updated search distance until a stop condition for path planning is reached, and stopping the iteration of the path planning comprises:
and obtaining the iteration times of the path planning and the iteration time of the path planning, and stopping the iteration of the path planning when the iteration time of the path planning exceeds the set time or the iteration times of the path planning exceeds the set times.
3. The fixed line autopilot barrier-detour endpoint selection method of claim 1 wherein the method further comprises,
and acquiring updated driving boundary environment and obstacle information each time the candidate obstacle detouring end point is determined.
4. The fixed line autopilot obstacle avoidance terminal selection method of claim 1 wherein said reducing the search distance to update the search distance comprises:
the search distance is reduced by half to update the search distance.
5. A barrier-detouring end point selection system for automatic driving on a fixed line is characterized by comprising;
the path operation unit comprises a barrier-bypassing end point screening module and a path planning module;
the obstacle detouring terminal point screening module acquires a fixed line, a first obstacle on the fixed line and a terminal point of the fixed line, and determines a position point at a preset distance along the advancing direction of the first obstacle in the fixed line as an initial obstacle detouring terminal point; and the obstacle-detouring end point screening module performs iteration of path planning according to the search distance, wherein each path planning comprises the following steps:
starting from the initial barrier-bypassing endpoint, performing an iteration of the barrier-bypassing endpoint, the iteration of the barrier-bypassing endpoint comprising:
obtaining the searching distance of the path planning;
determining a position point at a search distance along the current obstacle detouring end point advancing direction in the fixed line as a candidate obstacle detouring end point;
judging whether the vehicle is in collision when being positioned at the candidate obstacle detouring terminal point;
if the vehicle is determined to be located at the candidate obstacle detouring terminal point and no collision occurs, acquiring an obstacle closest to the candidate obstacle detouring terminal point in the fixed line, and acquiring the distance between the obstacle and the candidate obstacle detouring terminal point;
if the distance is larger than a set threshold value, setting the candidate obstacle detouring end point as a new obstacle detouring end point, continuing iteration of the obstacle detouring end point until the new obstacle detouring end point is the end point of the fixed line, stopping the iteration of the obstacle detouring end point, and finishing the path planning;
reducing the search distance to update the search distance every time path planning is completed, and performing next path planning according to the updated search distance until the stopping condition of the path planning is reached, and stopping iteration of the path planning; and the path planning module acquires the obstacle detouring end point determined by the last path planning so as to complete the path planning.
6. The obstacle detouring end point selection system for fixed line autopilot according to claim 5, wherein the step of reducing the search distance to update the search distance each time a path planning is completed, and stopping the iteration of the path planning until a stop condition for the path planning is reached comprises the steps of:
and a barrier-bypassing end point screening module acquires the iteration times of the path planning and the iteration time of the path planning, and stops the iteration of the path planning when the iteration time of the path planning exceeds the set time or the iteration times of the path planning exceeds the set times.
7. The obstacle detour end point selection system for automatic fixed line driving according to claim 5, further comprising a vehicle control unit, wherein the vehicle control unit obtains the obstacle detour end point determined by the last path planning sent by the path planning module for path following and controls the vehicle to complete obstacle detour.
8. The obstacle detour end selection system for fixed-line autonomous driving according to claim 5, further comprising a global environment and obstacle information sensing unit for acquiring driving boundary environment and obstacle information, wherein updated driving boundary environment and obstacle information are acquired each time the candidate obstacle detour end is determined.
9. The fixed line autopilot barrier terminal selection system of claim 5 wherein said reducing the search distance to update the search distance comprises:
half of the search distance is reduced to update the search distance.
10. A computer-readable storage medium, characterized in that the medium has stored thereon a program which is executable by a processor to implement the method according to any one of claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211495730.4A CN115540892B (en) | 2022-11-28 | 2022-11-28 | Obstacle-detouring terminal point selection method and system for fixed line vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211495730.4A CN115540892B (en) | 2022-11-28 | 2022-11-28 | Obstacle-detouring terminal point selection method and system for fixed line vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115540892A true CN115540892A (en) | 2022-12-30 |
| CN115540892B CN115540892B (en) | 2023-03-24 |
Family
ID=84722757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211495730.4A Active CN115540892B (en) | 2022-11-28 | 2022-11-28 | Obstacle-detouring terminal point selection method and system for fixed line vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115540892B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975951A (en) * | 2010-06-09 | 2011-02-16 | 北京理工大学 | Field environment barrier detection method fusing distance and image information |
| CN102902269A (en) * | 2012-09-21 | 2013-01-30 | 北京邮电大学 | Redundant robot dynamic obstacle avoidance method using pre-selected minimum distance index |
| EP3184392A2 (en) * | 2015-12-21 | 2017-06-28 | Valeo Schalter und Sensoren GmbH | Method for avoiding a collision of a vehicle, driver assistance system and motor vehicle |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN109116858A (en) * | 2018-11-07 | 2019-01-01 | 上海木木聚枞机器人科技有限公司 | It is a kind of on specified path around barrier paths planning method and system |
| CN111026114A (en) * | 2019-12-12 | 2020-04-17 | 南京苏美达智能技术有限公司 | Obstacle detouring method and self-walking equipment |
| CN111906779A (en) * | 2020-06-30 | 2020-11-10 | 珠海市一微半导体有限公司 | Obstacle crossing end judgment method, obstacle crossing control method, chip and robot |
| CN112379679A (en) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | Unmanned vehicle local path planning method |
| CN113190010A (en) * | 2021-05-08 | 2021-07-30 | 珠海市一微半导体有限公司 | Edge obstacle-detouring path planning method, chip and robot |
| CN114764249A (en) * | 2022-04-27 | 2022-07-19 | 西安建筑科技大学 | Real-time obstacle avoidance path planning method, system, device and medium |
| CN115183793A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Planning method and system for obstacle expansion, electronic equipment and storage medium |
| CN115179970A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
-
2022
- 2022-11-28 CN CN202211495730.4A patent/CN115540892B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101975951A (en) * | 2010-06-09 | 2011-02-16 | 北京理工大学 | Field environment barrier detection method fusing distance and image information |
| CN102902269A (en) * | 2012-09-21 | 2013-01-30 | 北京邮电大学 | Redundant robot dynamic obstacle avoidance method using pre-selected minimum distance index |
| EP3184392A2 (en) * | 2015-12-21 | 2017-06-28 | Valeo Schalter und Sensoren GmbH | Method for avoiding a collision of a vehicle, driver assistance system and motor vehicle |
| CN107992050A (en) * | 2017-12-20 | 2018-05-04 | 广州汽车集团股份有限公司 | Pilotless automobile local path motion planning method and device |
| CN109116858A (en) * | 2018-11-07 | 2019-01-01 | 上海木木聚枞机器人科技有限公司 | It is a kind of on specified path around barrier paths planning method and system |
| CN111026114A (en) * | 2019-12-12 | 2020-04-17 | 南京苏美达智能技术有限公司 | Obstacle detouring method and self-walking equipment |
| CN111906779A (en) * | 2020-06-30 | 2020-11-10 | 珠海市一微半导体有限公司 | Obstacle crossing end judgment method, obstacle crossing control method, chip and robot |
| CN112379679A (en) * | 2021-01-15 | 2021-02-19 | 北京理工大学 | Unmanned vehicle local path planning method |
| CN113190010A (en) * | 2021-05-08 | 2021-07-30 | 珠海市一微半导体有限公司 | Edge obstacle-detouring path planning method, chip and robot |
| CN114764249A (en) * | 2022-04-27 | 2022-07-19 | 西安建筑科技大学 | Real-time obstacle avoidance path planning method, system, device and medium |
| CN115183793A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Planning method and system for obstacle expansion, electronic equipment and storage medium |
| CN115179970A (en) * | 2022-09-14 | 2022-10-14 | 毫末智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 杜树新等: "机器人避碰撞路径生成中的跨绕问题研究", 《西安交通大学学报》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115540892B (en) | 2023-03-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7295876B2 (en) | Method and system for generating parking routes | |
| US20180148052A1 (en) | Drivable area setting device and drivable area setting method | |
| CN112595337B (en) | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium | |
| US20200307554A1 (en) | Systems and methods for parking a vehicle | |
| CN112394725B (en) | Prediction and reaction field of view based planning for autopilot | |
| CN113009918B (en) | Path planning method, device, system and readable storage medium | |
| WO2004031691A1 (en) | Estimation of vehicle forward path | |
| CN112631306B (en) | Robot moving path planning method and device and robot | |
| CN111413959A (en) | Global path planning and parking method and system from any point to any point | |
| CN115127576B (en) | Path planning method, device, chip, terminal, electronic equipment and storage medium | |
| CN113867347A (en) | Robot path planning method, device, management system and computer storage medium | |
| CN114812566B (en) | Method and device for planning driving path of mine vehicle and computer equipment | |
| KR20200063039A (en) | Apparatus for planning dual path and determining road judgement area for autonomous driving and method using thereof | |
| CN114543815A (en) | Multi-agent navigation control method, equipment and medium based on gene regulation network | |
| CN113548039B (en) | Automatic parking method, automatic parking device, vehicle and storage medium | |
| KR20180040787A (en) | Method and device for autonomous driving based on route adaptation | |
| CN115540892B (en) | Obstacle-detouring terminal point selection method and system for fixed line vehicle | |
| CN113867356A (en) | Robot path planning method and device and robot | |
| CN112445221B (en) | Automatic working system and regression method | |
| US11878712B2 (en) | Trajectory planning with obstacle avoidance for autonomous driving vehicles | |
| CN116476840A (en) | Variable-lane driving method, device, equipment and storage medium | |
| CN115060279B (en) | Path planning method, path planning device, electronic equipment and computer readable medium | |
| CN115014380A (en) | Parking path planning method and device, electronic device and storage medium | |
| JPWO2020074860A5 (en) | ||
| US11724717B2 (en) | Implementation of dynamic cost function of self-driving vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |