CN114184195A - Path searching method and device, unmanned equipment and storage medium - Google Patents
Path searching method and device, unmanned equipment and storage medium Download PDFInfo
- Publication number
- CN114184195A CN114184195A CN202111530202.3A CN202111530202A CN114184195A CN 114184195 A CN114184195 A CN 114184195A CN 202111530202 A CN202111530202 A CN 202111530202A CN 114184195 A CN114184195 A CN 114184195A
- Authority
- CN
- China
- Prior art keywords
- path
- round
- trip
- distance
- candidate
- 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 47
- 230000003247 decreasing effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 7
- 238000007689 inspection Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
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
- G01C21/20—Instruments for performing navigational calculations
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
The embodiment of the application relates to the technical field of automatic driving, and provides a path searching method, a device, unmanned equipment and a storage medium, wherein a candidate path close to the unmanned equipment is determined from a plurality of back-and-forth paths by taking a reference path as a basis, so that the path searching is limited in a smaller range; and then, local search is carried out based on the candidate paths, so that the target path closest to the unmanned equipment can be found, and efficient and accurate search of the target path is realized.
Description
Technical Field
The embodiment of the application relates to the technical field of automatic driving, in particular to a path searching method and device, unmanned equipment and a storage medium.
Background
Before an unmanned device (e.g., an agricultural machine, an unmanned vehicle, etc.) works, a working route including a plurality of back-and-forth paths is planned, and then an automatic driving task is executed by using the working route for navigation. In practice, in order to ensure smooth operation, the unmanned device needs to select a round-trip path closest to the unmanned device as a target path and direct the unmanned device to perform operation. Therefore, how to efficiently and accurately search out a target path is a technical problem to be solved urgently at present.
Disclosure of Invention
An object of the embodiments of the present application is to provide a path searching method, an apparatus, an unmanned device, and a storage medium, so as to efficiently and accurately search out a target path.
In order to achieve the above purpose, the embodiments of the present application employ the following technical solutions:
in a first aspect, an embodiment of the present application provides a path search method, where the method includes:
obtaining a working route, wherein the working route comprises a plurality of round-trip paths which are generated by taking a reference path as a template;
determining a candidate path close to the unmanned equipment from the multiple round-trip paths according to the reference path;
and carrying out local search on the multiple round-trip paths based on the candidate paths to obtain a target path closest to the unmanned equipment.
Further, the determining a candidate path close to the unmanned device from the multiple round-trip paths according to the reference path includes:
obtaining a relative distance between the drone and the reference path, wherein the relative distance characterizes a direction of the drone relative to the reference path and a distance therebetween;
obtaining a round-trip path vector according to the relative distance and the set distance, wherein the round-trip path vector represents the direction of the unmanned equipment relative to the reference path and the number of round-trip paths between the unmanned equipment and the reference path;
and determining the candidate path from the multiple round-trip paths according to the round-trip path vector.
Further, the step of obtaining a round-trip path vector according to the relative distance and the set distance includes:
according to the relative distance and the set distance, using a formula
Calculating the round-trip path vector, wherein Index represents the round-trip path vector, round () represents a function rounding to 0, d0The relative distance is represented, and d represents the set pitch.
Further, the reference path and the round-trip path are both preset with path numbers;
the path number of the reference path and the round-trip path on the first side of the reference path is decreased in sequence from the reference path;
a round trip path on a second side of the reference path and the reference path, the path numbers increasing in order from the reference path; the first side and the second side are opposite.
Further, the step of obtaining a relative distance between the drone and the reference path includes:
calculating a distance between the drone and the reference path;
if the unmanned equipment is located on the first side of the reference path, taking a negative value of the distance as the relative distance;
and if the unmanned equipment is positioned on the second side of the reference path, taking the distance as the relative distance.
Further, the step of determining the candidate path from the multiple round-trip paths according to the round-trip path vector includes:
determining a target path number according to the path number of the reference path and the round-trip path vector;
and taking the round-trip path corresponding to the target path number as the candidate path.
Further, the step of determining a target path number according to the path number of the reference path and the round-trip path vector includes:
if the path number of the reference path is not 0, taking the sum of the path number of the reference path and the round-trip path vector as the target path number;
and if the path number of the reference path is 0, taking the round-trip path vector as the target path number.
Further, the step of performing a local search on the plurality of round-trip paths based on the candidate paths to obtain a target path closest to the unmanned aerial vehicle includes:
determining a reference path closest to the unmanned equipment from the candidate path and a round trip path on a first side of the candidate path;
and determining the target path from the round trip paths of the reference path and a second side of the reference path, wherein the first side and the second side are opposite.
Further, the step of determining a reference path closest to the unmanned aerial vehicle from the candidate path and the round trip path on the first side of the candidate path includes:
obtaining a first distance between the candidate path and the unmanned device;
calculating a first reference distance between the drone and a first roundtrip path, wherein the first roundtrip path is adjacent to and on a first side of the candidate path;
judging whether the first reference distance is smaller than the first distance;
if so, replacing the first round-trip path with the candidate path, and executing the step of obtaining a first distance between the candidate path and the unmanned equipment until the first reference distance is not less than the first distance, and taking the candidate path as the reference path;
if not, the candidate path is taken as the reference path.
Further, the step of determining the target path from the reference path and the round trip path on the second side of the reference path includes:
obtaining a second distance between the reference path and the drone;
calculating a second reference distance between the drone and a second roundtrip path, wherein the second roundtrip path is adjacent to and on a second side of the reference path;
judging whether the second reference distance is smaller than the second distance;
if so, replacing the second round-trip path with the reference path, and executing the step of obtaining a second distance between the reference path and the unmanned equipment until the second reference distance is not less than the second distance, and taking the reference path as the target path;
and if not, taking the reference path as the target path.
In a second aspect, an embodiment of the present application further provides a path searching apparatus, where the apparatus includes:
the system comprises an obtaining module, a processing module and a processing module, wherein the obtaining module is used for obtaining a working route, the working route comprises a plurality of round-trip paths, and the round-trip paths are generated by taking a reference path as a template;
the determining module is used for determining a candidate path close to the unmanned equipment from the multiple round-trip paths according to the reference path;
and the searching module is used for carrying out local search on the multiple round-trip paths based on the candidate paths to obtain a target path closest to the unmanned equipment.
In a third aspect, an embodiment of the present application further provides an unmanned device, where the unmanned device includes: one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the path search method described above.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the above-mentioned path searching method.
Compared with the prior art, the path search method, the path search device, the unmanned equipment and the storage medium provided by the embodiment of the application determine the candidate path close to the unmanned equipment from the multiple round-trip paths by taking the reference path as a basis, so that the path search is limited in a smaller range; and then, local search is carried out based on the candidate paths, so that the target path closest to the unmanned equipment can be found, and efficient and accurate search of the target path is realized.
Drawings
Fig. 1 shows one of exemplary diagrams of paths provided by embodiments of the present application.
Fig. 2 shows a second example of the path provided by the embodiment of the present application.
Fig. 3 shows a flowchart of a path searching method provided in an embodiment of the present application.
Fig. 4 shows a third example of the path provided by the embodiment of the present application.
Fig. 5 shows a fourth example of the path provided by the embodiment of the present application.
Fig. 6 is a flowchart illustrating step S102 in the path searching method illustrated in fig. 5.
Fig. 7 shows five example diagrams of paths provided by the embodiments of the present application.
Fig. 8 is a flowchart illustrating step S103 in the path searching method illustrated in fig. 5.
Fig. 9 is a flowchart illustrating step S1031 of the path searching method illustrated in fig. 8.
Fig. 10 is a flowchart illustrating step S1032 of the path searching method illustrated in fig. 8.
Fig. 11 shows a sixth example of a path diagram provided by an embodiment of the present application.
Fig. 12 is a block diagram illustrating a path search apparatus according to an embodiment of the present application.
Fig. 13 shows a block schematic diagram of an unmanned aerial device provided by an embodiment of the present application.
Icon: 100-path search means; 101-obtaining a module; 102-a determination module; 103-a search module; 10-unmanned equipment; 11-a processor; 12-a memory; 13-bus.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application.
The agricultural unmanned intellectualization is a key for promoting agricultural development, and before operation, unmanned equipment (such as agricultural machinery, unmanned vehicles and the like) firstly needs to plan a plurality of back-and-forth paths, then generates an operation route suitable for the unmanned equipment to work according to the plurality of back-and-forth paths, and then performs an automatic driving task by using the operation route for navigation.
In practical applications, in order to ensure smooth operation of the unmanned aerial vehicle, the unmanned aerial vehicle needs to select a round-trip path closest to the unmanned aerial vehicle as a target path and direct the unmanned aerial vehicle to perform operation.
Currently, the common target path selection method is as follows: and calculating the distance from the unmanned equipment to each round-trip path, and finding out the round-trip path corresponding to the shortest distance from the distance as a target path.
However, taking the unmanned aerial vehicle working in a land parcel as an example, in order to realize the full coverage work of the whole land parcel, when planning the round-trip path, a plurality of round-trip paths covering the whole land parcel are often required to be planned, and most land parcels are irregular in reality. For example, referring to FIG. 1, it is difficult for the plot shown in FIG. 1 to cover the entire plot if only a straight round-trip path is used.
In this case, in addition to the straight reciprocating path, the method shown in fig. 2 may be adopted, and a plurality of curved reciprocating paths may be generated by using the curved edge boundaries of different segments as the reference path and using the reference path as a template, so as to cover the land area that is difficult to be covered by the straight reciprocating path.
It should be noted that, besides the above-mentioned operation scenarios, the curved back-and-forth path may also be used in other operation scenarios, for example, operations around an island, obstacle avoidance operations, etc., and those skilled in the art may flexibly set the path according to practical application scenarios, which is not limited herein.
From the above analysis, the multiple round-trip paths planned for the unmanned equipment may be straight round-trip paths or curved round-trip paths. If the path is a straight-line back-and-forth path, the existing target path selection mode is adopted, and the target path can be searched out more quickly. However, in the case of a curved reciprocating path, it takes a lot of time to select a target path by using the conventional method due to the characteristics of the curve itself, which is disadvantageous to efficient unmanned operation.
Therefore, how to efficiently and accurately search out a target path is a technical problem to be solved urgently at present.
In order to solve the problem, in the embodiment of the application, for a plurality of round-trip paths generated by using a reference path as a template, a candidate path close to the unmanned device is determined from the plurality of round-trip paths according to the reference path, so that path search is limited within a small range, and then local search is performed based on the candidate path, so that a target path closest to the unmanned device can be found, and efficient and accurate search of the target path is realized. As described in detail below.
The unmanned equipment in the embodiment of the application can be agricultural machines, unmanned vehicles and the like, such as agricultural tractors, rice transplanters and the like; and can also be an unmanned ship, a robot and the like, such as an unmanned cleaning ship and the like. The user may select different devices according to the actual application scenario, which is not limited herein.
Referring to fig. 3, fig. 3 is a flowchart illustrating a path searching method according to an embodiment of the present disclosure. The path searching method is applied to the unmanned equipment and can comprise the following steps:
s101, obtaining a working route, wherein the working route comprises a plurality of round-trip paths, and the round-trip paths are generated by taking a reference path as a template.
Before the unmanned equipment executes the automatic driving task, the path searching method provided by the embodiment can be adopted to find a round-trip path closest to the current position of the unmanned equipment from a plurality of pre-planned round-trip paths as a target path, and guide the unmanned equipment to carry out operation.
The round-trip path is generated using the reference path as a template, and is generated by, for example, performing a translation copy or the like on the reference path. For example, referring to fig. 4, the broken line in fig. 4 is a reference path, and the round-trip path can be generated by performing a translation copy of the reference path at a predetermined pitch.
The reference path may be set according to the actual situation of the object to be operated, for example, for a fruit tree in a certain plot, it is necessary to automatically transport picked fruit to a designated place by using unmanned equipment, and then the reference path may be set according to the distribution situation of the fruit tree in the plot. The reference path may also be set according to the actual conditions of the land mass to be worked, for example, in conjunction with fig. 2, curved edge boundaries of different segments may be adopted as the reference path for the land mass edge. The reference path may also be set according to an actual working scene, for example, if there is an obstacle in the land to be worked, the boundary of the obstacle may be used as the reference path, and the like.
It should be noted that the above reference path setting manner is only an example for facilitating understanding of the present embodiment, and in practical application, a person skilled in the art may flexibly set the reference path according to an actual situation, and is not limited herein.
And S102, determining a candidate path close to the unmanned equipment from the multiple round-trip paths according to the reference path.
In this embodiment, a candidate path close to the unmanned device may be determined from the multiple round-trip paths based on the reference path, so that the path search is limited to a small range, and the target path may be found efficiently and accurately in the following.
In some embodiments, since in the path planning stage, when multiple round-trip paths are generated by using the reference path as the template, the distance between each round-trip path and the reference path template is given, the distance between each round-trip path and the reference path in the working route is a fixed value, and the distance can be represented by di. Meanwhile, the distance between the unmanned aerial vehicle and the reference path can be determined according to the current position of the unmanned aerial vehicle, and the distance can be represented by d. Thus, a nearest path d can be found from all di, and the round-trip path corresponding to the found di can be used as a candidate path.
In other embodiments, in the path planning stage, the reference path may be numbered, and each generated round-trip path is also numbered according to the number of the reference path, for example, referring to fig. 5, the number of the reference path is 0, the number of the round-trip path on the left side of the reference path is decreased from 0, and the number of the round-trip path on the right side of the reference path is increased from 0. And, the rough position information of each path, for example, the number of each path, the distance between adjacent paths, etc. may be recorded in the planning stage.
Thus, in the path searching stage, the distance d between the unmanned equipment and the reference path can be calculated firstly; then, calculating the average distance between the adjacent paths according to the distance between the adjacent paths recorded in the planning stage; then, according to the distance d and the average distance, the number of the round-trip paths between the unmanned aerial vehicle and the reference path, that is, how many round-trip paths exist can be calculated, for example, please refer to fig. 5, a black triangle in fig. 5 is the unmanned aerial vehicle, and 4 round-trip paths between the unmanned aerial vehicle and the reference path are obtained through calculation; next, since there are 4 round-trip paths between the unmanned aerial vehicle and the reference path, the 4 th round-trip path from the reference path to the left, i.e., round-trip path-4, may be set as the target path.
S103, local search is carried out on the multiple round-trip paths based on the candidate paths, and a target path closest to the unmanned equipment is obtained.
After the round-trip path close to the unmanned device is determined through step S102, a local search may be performed based on the candidate path to find a target path closest to the unmanned device. For example, the distances between the unmanned device and the candidate route, the round-trip route on the left side of the candidate route, and the round-trip route on the right side of the candidate route may be calculated, respectively, and one having the shortest distance may be found therefrom as the target route. Incorporated into fig. 5, the distances between the drone and round trip path-4, round trip path-5, and round trip path-3, respectively, may be calculated, with round trip path-4 being the target path assuming the shortest distance to round trip path-4.
It should be noted that the number of the round-trip paths on the left and right sides of the candidate path is not limited to one, and those skilled in the art may select an appropriate number of round-trip paths on the left and right sides of the candidate path according to actual situations to search out the target path, which is not limited herein.
As an embodiment, referring to fig. 6 on the basis of fig. 3, step S102 is described in detail below, and step S102 may include the following sub-steps:
and S1021, obtaining a relative distance between the unmanned device and the reference path, wherein the relative distance represents the direction of the unmanned device relative to the reference path and the distance between the unmanned device and the reference path.
The direction of the drone relative to the reference path refers to: and determining which side of the reference path the unmanned equipment is on based on the direction from the starting point to the end point of the reference path. For example, assuming that the direction from the start point to the end point of the reference path in fig. 5 is from bottom to top, it may be determined that the unmanned device is on the left side of the reference path.
The distance between the unmanned device and the reference path may be a common unsigned distance, such as a planar euclidean distance. In general, the paths are each composed of a plurality of discrete points, and therefore, the process of calculating the distance between the unmanned device and the reference path may include: the distance between the current position of the unmanned equipment and each discrete point on the reference path is calculated, then the shortest distance is found and is used as the distance between the unmanned equipment and the reference path.
In some embodiments, the reference path and the round-trip path are both preset with path numbers, and the setting principle of the path numbers may be: a reference path and a round-trip path on a first side of the reference path, wherein path numbers are sequentially decreased from the reference path; a reference path and a round-trip path on a second side of the reference path, wherein path numbers are sequentially increased from the reference path; the first side is opposite the second side. The following examples are presented by way of example of this numbering convention.
The first side and the second side of the reference path are determined by taking the direction from the starting point to the end point of the reference path as a reference. That is, the first side may be a left side or a right side of the reference path, and the second side is the other side opposite to the first side, with reference to a direction from the start point to the end point of the reference path. For example, if the first side is the left side and the second side is the right side, the numbers of the left side paths are sequentially decreased and the numbers of the right side paths are sequentially increased based on the reference path; and if the first side is the right side and the second side is the left side, the serial numbers of the left side paths are sequentially increased and the serial numbers of the right side paths are sequentially decreased on the basis of the reference path.
It should be noted that, in addition to the above-described numbering manners, there may be other numbering manners, for example, the numbering is performed in a manner of sequentially decreasing from left to right or sequentially increasing from left to right with respect to the direction from the starting point to the end point of the reference path, and the numbering is not limited herein.
In some embodiments, the relative distance between the drone and the reference path may be a signed distance, since the numbering setting principle is that the first side decreases in order and the second side increases in order, the relative distance is negative if the drone is on the first side of the reference path and positive if the drone is on the second side of the reference path.
As an embodiment, the process of obtaining the relative distance between the unmanned device and the reference path in step S1021 may include:
calculating the distance between the unmanned equipment and the reference path;
if the unmanned equipment is positioned on the first side of the reference path, taking a negative value of the distance as a relative distance;
and if the unmanned equipment is positioned on the second side of the reference path, taking the distance as the relative distance.
For example, referring to fig. 5, assuming that the distance d between the drone and the reference path is calculated to be 9.5, since the drone is on the left side of the reference path, it is determined that the relative distance between the drone and the reference path is-9.5.
And S1022, obtaining a round-trip path vector according to the relative distance and the set distance, wherein the round-trip path vector represents the direction of the unmanned equipment relative to the reference path and the number of round-trip paths between the unmanned equipment and the reference path.
The number of round-trip paths between the unmanned aerial vehicle and the reference path means the number of round-trip paths between the unmanned aerial vehicle and the reference path. Similar to the relative distance, the round trip path vector is also a signed number and is negative if the drone is on a first side of the reference path and positive if the drone is on a second side of the reference path.
In some embodiments, the process of obtaining the round-trip path vector according to the relative distance and the set distance in step S1022 may include:
according to the relative distance and the set interval, using a formula
Calculating a round-trip path vector, wherein Index represents the round-trip path vector, round () represents a function rounding to 0, d0The relative distance is indicated, and d is the set pitch. E.g. d0When the Index is-9.5, the Index is-3.
S1023, according to the round-trip path vector, a candidate path is determined from the round-trip paths.
After obtaining the round-trip path vector through step S1023, a candidate path can be determined from the plurality of round-trip paths according to the round-trip path vector, and the process may include:
determining a target path number according to the path number of the reference path and the round-trip path vector;
and taking the round-trip path corresponding to the target path number as a candidate path.
In some embodiments, if the path number of the reference path is not 0, the sum of the path number of the reference path and the round-trip path vector may be set as the target path number; if the path number of the reference path is 0, the round trip path vector is set as the target path number.
For example, referring to fig. 7, since the reference route number is 0, the round-trip route vector may be directly set as the target route number, i.e., the target route number is-3, and the round-trip route-3 may be set as the candidate route.
After the candidate route is determined in step S102, since the candidate route is only close to the unmanned device and may not be the target route closest to the unmanned device, a local search needs to be performed based on the candidate route to accurately find the target route closest to the unmanned device.
Therefore, as an embodiment, referring to fig. 8 on the basis of fig. 3, step S103 may include the following sub-steps:
and S1031, determining a reference path closest to the unmanned equipment from the candidate path and the round trip path on the first side of the candidate path.
S1032 determines a target path from the round-trip paths of the reference path and the second side of the reference path, wherein the first side and the second side are opposite.
That is, first, a round-trip path on a first side of a candidate path is checked in sequence from the candidate path to find a reference path closest to the unmanned device; then, the round-trip paths on the second side of the candidate path are checked in sequence from the reference path to find out the target path closest to the unmanned device.
It should be noted that the above process is only an example, and the round trip path on the second side of the candidate path may be checked first, and then the round trip path on the first side of the reference path may be checked, which is not limited herein.
Alternatively, on the basis of fig. 8, please refer to fig. 9, step S1031 may include the following sub-steps:
and S10311, obtaining a first distance between the candidate path and the unmanned device.
S10312, a first reference distance between the unmanned device and a first round-trip path is calculated, wherein the first round-trip path is adjacent to the candidate path and located on a first side of the candidate path.
And S10313, judging whether the first reference distance is smaller than the first distance.
If the first reference distance is smaller than the first distance, performing substep S10314; if the first reference distance is not less than the first distance, sub-step S10315 is performed.
And S10314, replacing the first round-trip path with a candidate path, and returning to execute the substep S10311 until the first reference distance is not less than the first distance, and taking the candidate path as the reference path.
The substep S10311 is executed back until the first reference distance is not less than the first distance. This can be understood as follows: after the substep S10311 is executed, the steps S10312 to S10313 are continuously executed until the first reference distance is not less than the first distance, so as to obtain the reference distance.
And S10315, taking the candidate path as a reference path.
Alternatively, on the basis of fig. 8, please refer to fig. 10, step S1032 may include the following sub-steps:
s10321, a second distance between the reference path and the unmanned device is obtained.
S10322, a second reference distance between the drone and a second roundtrip path is calculated, where the second roundtrip path is adjacent to the reference path and on a second side of the reference path.
S10323, it is determined whether the second reference distance is smaller than the second distance.
If the second reference distance is less than the second distance, performing substep S10324; if the second reference distance is not less than the second distance, sub-step S10325 is performed.
S10324, the second round-trip path is replaced with the reference path, and the substep S10321 is returned to be executed until the second reference distance is not less than the second distance, taking the reference path as the target path.
The substep S10321 is performed back until the second reference distance is not less than the second distance. This can be understood as follows: after the substep S10321 is performed, the steps S10322 to S10323 are continuously performed until the second reference distance is not less than the second distance, and the target distance is obtained.
S10325, the reference path is taken as the target path.
For example, referring to FIG. 11, taking the first side as the left side as an example, first, the inspection is started to the left side of the candidate route, when the round-trip route with the number-4 is inspected, if d-4 < d-3 is found, the inspection is continued to the left, when the round-trip route with the number-5 is inspected, if d-5 > d-4 is found, the inspection is stopped, and the round-trip route with the number-4 is taken as the reference route; then, the inspection is started to the right side of the reference path, and since the right side of the reference path is the round trip path of number-3 and d-4 < d-3 has been determined in the previous step, the inspection is stopped, and the round trip path of number-4 is taken as the target path.
Compared with the prior art, the embodiment of the application has the following beneficial effects:
firstly, a candidate path close to the unmanned equipment is determined from multiple round-trip paths by taking a reference path as a basis, so that the path search is limited in a smaller range, and then the target path closest to the unmanned equipment can be found by carrying out local search based on the candidate path, so that the efficient and accurate search of the target path is realized.
Secondly, the method can be applied to the reciprocating path with any shape, and the target path can be efficiently and accurately searched no matter the reciprocating path is a straight reciprocating path or a curve reciprocating path.
In order to execute the corresponding steps in the above-mentioned embodiment of the path searching method and various possible embodiments, an implementation manner applied to the path searching apparatus is given below.
Referring to fig. 12, fig. 12 is a block diagram illustrating a path search apparatus 100 according to an embodiment of the present disclosure. The path search apparatus 100 is applied to an unmanned device, and includes: an obtaining module 101, a determining module 102 and a searching module 103.
The obtaining module 101 is configured to obtain a work route, where the work route includes multiple round-trip paths, and the round-trip paths are generated by using a reference path as a template.
The determining module 102 is configured to determine, according to the reference path, a candidate path close to the unmanned device from the multiple round-trip paths.
The searching module 103 is configured to perform local search on multiple round-trip paths based on the candidate paths to obtain a target path closest to the unmanned device.
Optionally, the determining module 102 is specifically configured to:
obtaining a relative distance between the unmanned equipment and the reference path, wherein the relative distance represents the direction of the unmanned equipment relative to the reference path and the distance between the unmanned equipment and the reference path;
obtaining a round-trip path vector according to the relative distance and the set distance, wherein the round-trip path vector represents the direction of the unmanned equipment relative to the reference path and the number of the round-trip paths between the unmanned equipment and the reference path;
and determining a candidate path from the multiple round-trip paths according to the round-trip path vector.
Optionally, the determining module 102 performs a manner of obtaining a relative distance between the unmanned device and the reference path, which may include:
calculating the distance between the unmanned equipment and the reference path; if the unmanned equipment is positioned on the first side of the reference path, taking a negative value of the distance as a relative distance; and if the unmanned equipment is positioned on the second side of the reference path, taking the distance as the relative distance.
Optionally, the determining module 102 may execute a manner of obtaining the round-trip path vector according to the relative distance and the set distance, where the manner includes:
according to the relative distance and the set interval, using a formula
Calculating a round-trip path vector, wherein Index represents the round-trip path vector, round () represents a function rounding to 0, d0The relative distance is indicated, and d is the set pitch.
Optionally, the determining module 102 performs a manner of determining a candidate path from multiple round-trip paths according to the round-trip path vector, which may include:
determining a target path number according to the path number of the reference path and the round-trip path vector; and taking the round-trip path corresponding to the target path number as a candidate path.
Optionally, the determining module 102 may determine the target path number according to the path number of the reference path and the round-trip path vector, where the determining module may include:
if the path number of the reference path is not 0, taking the sum of the path number of the reference path and the round-trip path vector as the target path number; if the path number of the reference path is 0, the round trip path vector is set as the target path number.
Optionally, the searching module 103 is specifically configured to: determining a reference path closest to the unmanned equipment from the candidate path and the round-trip path on the first side of the candidate path; a target path is determined from a round trip path between the reference path and a second side of the reference path, wherein the first side and the second side are opposite.
Optionally, the determining, by the searching module 103, a reference path closest to the unmanned device from the candidate path and the round trip path on the first side of the candidate path includes:
obtaining a first distance between the candidate path and the unmanned device; calculating a first reference distance between the unmanned device and a first round-trip path, wherein the first round-trip path is adjacent to the candidate path and is positioned on a first side of the candidate path; judging whether the first reference distance is smaller than the first distance; if so, replacing the first round-trip path with a candidate path, and executing the step of obtaining a first distance between the candidate path and the unmanned equipment until the first reference distance is not less than the first distance, and taking the candidate path as a reference path; and if not, taking the candidate path as a reference path.
Optionally, the searching module 103 determines the target path from the reference path and the round trip path on the second side of the reference path, where the determining includes:
obtaining a second distance between the reference path and the unmanned device; calculating a second reference distance between the drone and a second roundtrip path, wherein the second roundtrip path is adjacent to the reference path and on a second side of the reference path; judging whether the second reference distance is smaller than the second distance; if so, replacing the second round-trip path with a reference path, and executing the step of obtaining a second distance between the reference path and the unmanned equipment until the second reference distance is not less than the second distance, and taking the reference path as a target path; and if not, taking the reference path as the target path.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the path searching apparatus 100 described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
Referring to fig. 13, fig. 13 is a block diagram illustrating an unmanned aerial vehicle 10 according to an embodiment of the present application. The unmanned equipment 10 may be an agricultural machine, an unmanned vehicle, etc., such as an agricultural tractor, a rice transplanter, etc.; and can also be an unmanned ship, a robot and the like, such as an unmanned cleaning ship and the like. The drone 10 includes a processor 11, a memory 12, and a bus 13, and the processor 11 is connected to the memory 12 through the bus 13.
The memory 12 is used for storing a program, such as the path searching apparatus 100 shown in fig. 12, the path searching apparatus 100 includes at least one software functional module which can be stored in the memory 12 in a form of software or firmware (firmware), and the processor 11 executes the program after receiving an execution instruction to implement the path searching method disclosed in the above embodiment.
The Memory 12 may include a Random Access Memory (RAM) and may also include a non-volatile Memory (NVM).
The processor 11 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 11. The processor 11 may be a general-purpose processor, and includes a Central Processing Unit (CPU), a Micro Control Unit (MCU), a Complex Programmable Logic Device (CPLD), a Field Programmable Gate Array (FPGA), and an embedded ARM.
The embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored, and the computer program, when executed by the processor 11, implements the path searching method disclosed in the above embodiment.
To sum up, according to the path search method, the apparatus, the unmanned device and the storage medium provided in the embodiments of the present application, a candidate path close to the unmanned device is determined from multiple round-trip paths based on a reference path, so that the path search is limited to a smaller range; and then, local search is carried out based on the candidate path, so that the target path closest to the unmanned equipment can be found, the efficient and accurate search of the target path is realized, and the method can be suitable for the round-trip path in any shape.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (13)
1. A method for path search, the method comprising:
obtaining a working route, wherein the working route comprises a plurality of round-trip paths which are generated by taking a reference path as a template;
determining a candidate path close to the unmanned equipment from the multiple round-trip paths according to the reference path;
and carrying out local search on the multiple round-trip paths based on the candidate paths to obtain a target path closest to the unmanned equipment.
2. The method of claim 1, wherein determining a candidate path from the plurality of round trip paths that is close to an unmanned device based on the reference path comprises:
obtaining a relative distance between the drone and the reference path, wherein the relative distance characterizes a direction of the drone relative to the reference path and a distance therebetween;
obtaining a round-trip path vector according to the relative distance and the set distance, wherein the round-trip path vector represents the direction of the unmanned equipment relative to the reference path and the number of round-trip paths between the unmanned equipment and the reference path;
and determining the candidate path from the multiple round-trip paths according to the round-trip path vector.
3. The method of claim 2, wherein the step of deriving a round-trip path vector based on the relative distance and a set pitch comprises:
according to the relative distance and the set distance, using a formula
Calculating the round-trip path vector, wherein Index represents the round-trip path vector, round () represents a function rounding to 0, d0The relative distance is represented, and d represents the set pitch.
4. The method according to claim 2, wherein the reference path and the round trip path are each preset with a path number;
the path number of the reference path and the round-trip path on the first side of the reference path is decreased in sequence from the reference path;
a round trip path on a second side of the reference path and the reference path, the path numbers increasing in order from the reference path; the first side and the second side are opposite.
5. The method of claim 4, wherein the step of obtaining the relative distance between the drone and the reference path comprises:
calculating a distance between the drone and the reference path;
if the unmanned equipment is located on the first side of the reference path, taking a negative value of the distance as the relative distance;
and if the unmanned equipment is positioned on the second side of the reference path, taking the distance as the relative distance.
6. The method of claim 4, wherein said step of determining said candidate path from said plurality of round-trip paths based on said round-trip path vector comprises:
determining a target path number according to the path number of the reference path and the round-trip path vector;
and taking the round-trip path corresponding to the target path number as the candidate path.
7. The method of claim 6, wherein the step of determining a target path number based on the path number of the reference path and the round-trip path vector comprises:
if the path number of the reference path is not 0, taking the sum of the path number of the reference path and the round-trip path vector as the target path number;
and if the path number of the reference path is 0, taking the round-trip path vector as the target path number.
8. The method of claim 1, wherein the step of locally searching the plurality of round trip paths based on the candidate paths to obtain a target path closest to the drone comprises:
determining a reference path closest to the unmanned equipment from the candidate path and a round trip path on a first side of the candidate path;
and determining the target path from the round trip paths of the reference path and a second side of the reference path, wherein the first side and the second side are opposite.
9. The method of claim 8, wherein the step of determining a reference path closest to the drone from the candidate path and the round trip path to the first side of the candidate path comprises:
obtaining a first distance between the candidate path and the unmanned device;
calculating a first reference distance between the drone and a first roundtrip path, wherein the first roundtrip path is adjacent to and on a first side of the candidate path;
judging whether the first reference distance is smaller than the first distance;
if so, replacing the first round-trip path with the candidate path, and executing the step of obtaining a first distance between the candidate path and the unmanned equipment until the first reference distance is not less than the first distance, and taking the candidate path as the reference path;
if not, the candidate path is taken as the reference path.
10. The method of claim 8, wherein said step of determining said target path from said reference path and a roundtrip path to a second side of said reference path comprises:
obtaining a second distance between the reference path and the drone;
calculating a second reference distance between the drone and a second roundtrip path, wherein the second roundtrip path is adjacent to and on a second side of the reference path;
judging whether the second reference distance is smaller than the second distance;
if so, replacing the second round-trip path with the reference path, and executing the step of obtaining a second distance between the reference path and the unmanned equipment until the second reference distance is not less than the second distance, and taking the reference path as the target path;
and if not, taking the reference path as the target path.
11. A path search apparatus, characterized in that the apparatus comprises:
the system comprises an obtaining module, a processing module and a processing module, wherein the obtaining module is used for obtaining a working route, the working route comprises a plurality of round-trip paths, and the round-trip paths are generated by taking a reference path as a template;
the determining module is used for determining a candidate path close to the unmanned equipment from the multiple round-trip paths according to the reference path;
and the searching module is used for carrying out local search on the multiple round-trip paths based on the candidate paths to obtain a target path closest to the unmanned equipment.
12. An unmanned device, comprising:
one or more processors;
memory storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the path search method of any of claims 1-10.
13. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out a path search method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111530202.3A CN114184195B (en) | 2021-12-14 | 2021-12-14 | Path search method, path search device, unmanned equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111530202.3A CN114184195B (en) | 2021-12-14 | 2021-12-14 | Path search method, path search device, unmanned equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114184195A true CN114184195A (en) | 2022-03-15 |
| CN114184195B CN114184195B (en) | 2024-04-26 |
Family
ID=80543819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111530202.3A Active CN114184195B (en) | 2021-12-14 | 2021-12-14 | Path search method, path search device, unmanned equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114184195B (en) |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011170843A (en) * | 2010-01-20 | 2011-09-01 | Ihi Aerospace Co Ltd | Route generation device and method, and mobile device with the route generation device |
| CN106774395A (en) * | 2016-12-14 | 2017-05-31 | 东北农业大学 | Agricultural plant protection unmanned plane avoidance sprays paths planning method and unmanned plane |
| CN107289938A (en) * | 2017-05-27 | 2017-10-24 | 中国北方车辆研究所 | A kind of unmanned ground vehicle local paths planning method |
| CN107860387A (en) * | 2017-10-19 | 2018-03-30 | 上海拓攻机器人有限公司 | The unmanned machine operation flight course planning method of plant protection and plant protection unmanned plane |
| JP2019021197A (en) * | 2017-07-20 | 2019-02-07 | 株式会社Ｉｈｉエアロスペース | Route determination device and route determination method |
| CN110967019A (en) * | 2019-11-28 | 2020-04-07 | 深圳优地科技有限公司 | Method for planning local path of robot and robot |
| CN112097781A (en) * | 2019-06-17 | 2020-12-18 | 郑州宇通客车股份有限公司 | Path planning method and device based on multi-stage tentacles |
| CN112504276A (en) * | 2020-11-20 | 2021-03-16 | 广州极飞科技有限公司 | Path planning method and device, unmanned equipment and storage medium |
| CN112525198A (en) * | 2020-11-23 | 2021-03-19 | 广州极飞科技有限公司 | Operation route planning method and related device |
| CN112639849A (en) * | 2020-01-17 | 2021-04-09 | 华为技术有限公司 | Route selection method and route selection device |
| CN112697135A (en) * | 2020-12-31 | 2021-04-23 | 广州极飞科技有限公司 | Path shortening method and device, unmanned equipment and storage medium |
| CN112783208A (en) * | 2020-12-31 | 2021-05-11 | 广州极飞科技股份有限公司 | Unmanned equipment return control method and device and unmanned equipment |
| CN112947485A (en) * | 2021-03-31 | 2021-06-11 | 亿海蓝（北京）数据技术股份公司 | Path planning method and system |
| CN113124870A (en) * | 2020-01-14 | 2021-07-16 | 株式会社久保田 | Travel route management system for work machine |
| CN113156970A (en) * | 2021-05-08 | 2021-07-23 | 珠海市一微半导体有限公司 | Path fusion planning method for passing area, robot and chip |
| CN113310494A (en) * | 2021-06-02 | 2021-08-27 | 广州极飞科技股份有限公司 | Job path generation method, job device, and storage medium |
| CN113671988A (en) * | 2021-08-10 | 2021-11-19 | 广州极飞科技股份有限公司 | Job path setting method, apparatus, system, and storage medium |
| CN113739802A (en) * | 2021-08-30 | 2021-12-03 | 山东省科学院自动化研究所 | Unmanned bulldozer path planning method, system, storage medium and equipment |
-
2021
- 2021-12-14 CN CN202111530202.3A patent/CN114184195B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011170843A (en) * | 2010-01-20 | 2011-09-01 | Ihi Aerospace Co Ltd | Route generation device and method, and mobile device with the route generation device |
| CN106774395A (en) * | 2016-12-14 | 2017-05-31 | 东北农业大学 | Agricultural plant protection unmanned plane avoidance sprays paths planning method and unmanned plane |
| CN107289938A (en) * | 2017-05-27 | 2017-10-24 | 中国北方车辆研究所 | A kind of unmanned ground vehicle local paths planning method |
| JP2019021197A (en) * | 2017-07-20 | 2019-02-07 | 株式会社Ｉｈｉエアロスペース | Route determination device and route determination method |
| CN107860387A (en) * | 2017-10-19 | 2018-03-30 | 上海拓攻机器人有限公司 | The unmanned machine operation flight course planning method of plant protection and plant protection unmanned plane |
| CN112097781A (en) * | 2019-06-17 | 2020-12-18 | 郑州宇通客车股份有限公司 | Path planning method and device based on multi-stage tentacles |
| CN110967019A (en) * | 2019-11-28 | 2020-04-07 | 深圳优地科技有限公司 | Method for planning local path of robot and robot |
| CN113124870A (en) * | 2020-01-14 | 2021-07-16 | 株式会社久保田 | Travel route management system for work machine |
| WO2021145009A1 (en) * | 2020-01-14 | 2021-07-22 | 株式会社クボタ | Traveling path management system for work vehicle |
| CN112639849A (en) * | 2020-01-17 | 2021-04-09 | 华为技术有限公司 | Route selection method and route selection device |
| CN112504276A (en) * | 2020-11-20 | 2021-03-16 | 广州极飞科技有限公司 | Path planning method and device, unmanned equipment and storage medium |
| CN112525198A (en) * | 2020-11-23 | 2021-03-19 | 广州极飞科技有限公司 | Operation route planning method and related device |
| CN112783208A (en) * | 2020-12-31 | 2021-05-11 | 广州极飞科技股份有限公司 | Unmanned equipment return control method and device and unmanned equipment |
| CN112697135A (en) * | 2020-12-31 | 2021-04-23 | 广州极飞科技有限公司 | Path shortening method and device, unmanned equipment and storage medium |
| CN112947485A (en) * | 2021-03-31 | 2021-06-11 | 亿海蓝（北京）数据技术股份公司 | Path planning method and system |
| CN113156970A (en) * | 2021-05-08 | 2021-07-23 | 珠海市一微半导体有限公司 | Path fusion planning method for passing area, robot and chip |
| CN113310494A (en) * | 2021-06-02 | 2021-08-27 | 广州极飞科技股份有限公司 | Job path generation method, job device, and storage medium |
| CN113671988A (en) * | 2021-08-10 | 2021-11-19 | 广州极飞科技股份有限公司 | Job path setting method, apparatus, system, and storage medium |
| CN113739802A (en) * | 2021-08-30 | 2021-12-03 | 山东省科学院自动化研究所 | Unmanned bulldozer path planning method, system, storage medium and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114184195B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112837371B (en) | Object grabbing method and device based on 3D matching and computing equipment | |
| US11776217B2 (en) | Method for planning three-dimensional scanning viewpoint, device for planning three-dimensional scanning viewpoint, and computer readable storage medium | |
| CN111209978B (en) | Three-dimensional visual repositioning method and device, computing equipment and storage medium | |
| EP3709231A1 (en) | Vehicle track planning method, device, computer device and computer-readable storage medium | |
| US11048262B2 (en) | Robot movement control method and apparatus and robot using the same | |
| CN110561423A (en) | pose transformation method, robot and storage medium | |
| EP4057100A1 (en) | Vehicle scheduling method, apparatus and system | |
| CN108732554B (en) | Laser radar calibration method and device | |
| CN109974699B (en) | Robot and map autonomous exploration method and device thereof | |
| KR102207408B1 (en) | Method, apparatus and computer readable medium for image processing | |
| CN111433780A (en) | Lane line detection method, lane line detection apparatus, and computer-readable storage medium | |
| CN113671965B (en) | Path planning method and device | |
| CN112561859B (en) | Monocular vision-based steel belt drilling and anchor net identification method and device for anchoring and protecting | |
| CN111380510A (en) | Repositioning method and device and robot | |
| CN112348817A (en) | Parking space identification method and device, vehicle-mounted terminal and storage medium | |
| CN114427866A (en) | Path planning method, electronic device and storage medium | |
| CN110276801B (en) | Object positioning method and device and storage medium | |
| CN115014328A (en) | Dynamic loading method, device, equipment and medium for grid map | |
| EP3620962A1 (en) | Method, device and terminal for simulating a distribution of obstacles | |
| CN114184195B (en) | Path search method, path search device, unmanned equipment and storage medium | |
| Zoev et al. | Convolutional neural networks of the YOLO class in computer vision systems for mobile robotic complexes | |
| CN109416748B (en) | SVM-based sample data updating method, classification system and storage device | |
| CN111986299A (en) | Point cloud data processing method, device, equipment and storage medium | |
| CN114510053A (en) | Robot planned path checking method and device, storage medium and electronic equipment | |
| CN114460961A (en) | Unmanned equipment operation route determining method, device, equipment and storage medium |
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 |