CN114323019A - Method for planning all-covering path of agricultural machinery in complex environment - Google Patents
Method for planning all-covering path of agricultural machinery in complex environment Download PDFInfo
- Publication number
- CN114323019A CN114323019A CN202111437329.0A CN202111437329A CN114323019A CN 114323019 A CN114323019 A CN 114323019A CN 202111437329 A CN202111437329 A CN 202111437329A CN 114323019 A CN114323019 A CN 114323019A
- Authority
- CN
- China
- Prior art keywords
- area
- path
- algorithm
- coverage
- agricultural machinery
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000010845 search algorithm Methods 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 3
- 239000003016 pheromone Substances 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 241000257303 Hymenoptera Species 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000009191 jumping Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for planning a full-coverage path of agricultural machinery in a complex environment. The invention can solve the problems that the existing full coverage path planning technology can not effectively deal with complex environment, the coverage rate can not meet the requirement and the repetition rate is high. The ant colony path planning algorithm, the tabu search algorithm and the LQR control algorithm in the three-dimensional environment are combined and applied to the full-coverage path planning of agricultural machinery, and firstly, the farmland environment is wholly divided into a plurality of areas; then, carrying out overall path planning by using an ant colony path planning algorithm; then, local path planning is carried out on each area by utilizing a tabu search algorithm; in order to ensure no duplication, a mark is set for each area to distinguish whether the area is covered; and an LQR control algorithm is adopted during the advancing period of the agricultural machine to ensure that the agricultural machine does not yaw. The invention is suitable for various environments and has high coverage rate.
Description
Technical Field
The invention relates to the technical field of intelligent agricultural machinery, in particular to a full-coverage path planning method for the intelligent agricultural machinery.
Background
With the improvement and wide application of technologies of positioning systems and various sensors, autonomous navigation of agricultural machinery and various agricultural intelligent robots become hot spots of research of people. When traditional agricultural machinery works in the field, the position and the speed of the agricultural machinery are usually judged by the sense of a driver, and the current position of the agricultural machinery is difficult to be accurately judged, so that the agricultural production is finished by the autonomous navigation of the agricultural machinery. In agricultural operation, the final goal of farmers is to utilize the land to the maximum extent, thereby bringing the most income, so that the full coverage path planning is one of the important problems in the field of intelligent agricultural machinery. Agricultural full coverage path planning is all the points that pass through the required working space as unrepeated as possible while avoiding obstacles, with grid-based representation being the most widely used in coverage algorithms.
At present, a plurality of algorithms aiming at the full coverage path planning are available, the ant colony optimization algorithm is utilized to solve the path planning problem, a path planning method combining the particle swarm optimization algorithm and the PID control strategy is available, a layered fuzzy control system is also available for determining the motion of a robot, and the robot optimal path planning system with multiple functions comprises map construction, optimal path planning and mobile robot operation. However, the above path planning method still needs to be improved when the intelligent farm machinery serves in a complex environment, and the path coverage repetition rate of the existing method is high.
Disclosure of Invention
In view of the above, the invention provides an intelligent agricultural machinery full-coverage path planning method, which can solve the problems that the existing full-coverage path planning technology cannot effectively cope with complex environments such as hilly and mountainous regions, basins and valleys, the coverage rate cannot meet the requirement, and the repetition rate is high. The invention adopts a heuristic algorithm and a control algorithm to combine to carry out full-coverage path planning on agricultural machinery, and the specific technical scheme is as follows.
1) Firstly, expressing a farmland environment, roughly dividing the farmland into a plurality of adjacent areas by adopting a Boustrophledon decomposition algorithm, assigning K to each area, wherein K is used for expressing whether the area is covered or not, and K is initialized to be uncovered;
2) randomly taking one point in each region as a reference point, traversing the regions through an ant colony path planning algorithm in a three-dimensional environment to obtain a path which can pass through each reference point one time without repetition;
3) each area is divided into sub-areas represented by grids in a thinning mode, agricultural machinery adopts a tabu search algorithm to traverse the sub-areas for local coverage, and paths in each area are planned;
4) the agricultural machinery works along the path planned by the ant colony path planning algorithm, before entering the area after rough division, the value of K in the area is retrieved, if K indicates that the corresponding area is not covered, the agricultural machinery works in the area according to the path planned by the tabu search algorithm; if K indicates that the corresponding area is covered, turning to the next area until all areas reach the full coverage effect.
Furthermore, the agricultural machine is controlled to follow the planned path to drive through an LQR control algorithm in the advancing process of the agricultural machine.
Has the advantages that:
the method combines and applies the ant colony path planning algorithm, the tabu search algorithm and the LQR control algorithm in the three-dimensional environment to the full-coverage path planning of the agricultural machinery, based on the method, the technology can effectively cope with the complex environments such as hilly mountain areas, basins and river valleys compared with other technologies, and the coverage repetition rate is low.
Drawings
FIG. 1 is a main flow chart of the method.
Fig. 2 is an ant colony algorithm path planning diagram.
Fig. 3 is an ant colony routing diagram in a three-dimensional environment.
Fig. 4 is a tabu search routing diagram.
In fig. 2 and 4, black indicates an obstacle.
Detailed Description
The invention provides an intelligent agricultural machinery full coverage path planning method, which is explained in detail by a specific implementation mode and the accompanying drawings in order to clearly explain the technical characteristics of the invention.
The first step is as follows: firstly, expressing a farmland environment, roughly dividing the farmland into a plurality of adjacent areas by adopting a Boustrophledon decomposition algorithm, assigning K to each area, wherein the area is not covered by 0 and is covered by 1, and K is initialized to 0;
and constructing a layered structure based on rough division and fine division, wherein the farmland is divided into two layers, the first layer is the rough division of the working environment, and the second layer is the fine division of all the sub-areas. In roughly dividing the area, not only the position of the obstacle but also the size and turning radius of the agricultural machine are taken into consideration. More precisely, if an area is too small, the agricultural machinery may not pass smoothly, let alone achieve maximum efficiency.
The second step is that: randomly taking one point in each region as a reference point, traversing the regions through an ant colony path planning algorithm in a three-dimensional environment to obtain a path which can pass through each reference point one time without repetition;
the path planning result of the ant colony algorithm is shown in fig. 2 and 3. The algorithm initializes parameters such as population size m, important information degree alpha, importance degree of heuristic function beta, pheromone evaporation factor rho, pheromone release amount Q and the like. Referring to the path planning result diagram of fig. 2, the whole working space is divided into 16 regions, a reference point is randomly selected in each region, ants are randomly allocated to the reference points in the solution space, the distance between two nodes is calculated, the probability distribution of the starting point is calculated according to a probability formula, pheromones are updated, if the termination criterion is not met, the ant record table is cleared, the ant is returned to the point of reference reallocation, and otherwise, the shortest path is output. Thus, during the operation of the agricultural machine, the ant colony algorithm finds a path to enable the agricultural machine to accurately pass through each reference point once. The feasible path is 6 → 10 → 11 → 7 → 8 → 12 → 16 → 15 → 14 → 13 → 9 → 5 → 1 → 2 → 3 → 4. By combining the path planning result diagram in the three-dimensional environment of fig. 3, the invention can more effectively deal with complex environments such as hilly and mountainous regions, basins, valleys and the like.
The third step: each area is divided into sub-areas represented by grids in a thinning mode, agricultural machinery adopts a tabu search algorithm to traverse the sub-areas for local coverage, and paths in each area are planned;
and each area is divided into sub-areas represented by grids in a thinning mode, and the agricultural machinery adopts a tabu search algorithm to traverse the sub-areas to carry out local coverage.
Based on the result of the first-level coarse partitioning, each region is further processed into a mesh. And decomposing the working space into a series of grid units with binary information by adopting a grid method. The mesh may be divided into an empty mesh and a non-empty mesh. The empty mesh contains no obstacles, while the non-empty mesh contains obstacles.
Tabu Search (TS) employed in this step is used to guide local coverage planning. The tabu search algorithm briefly proceeds as follows:
1) generating an initial solution as a current solution, and adding a tabu table;
2) creating a candidate solution set (neighborhood solution set) of a current solution;
3) selecting a solution with the optimal objective function value and not in the tabu table in the candidate solution set as a new current solution;
4) adding a tabu table into the new current solution, and updating the tabu table;
5) and when the iteration termination condition is met, jumping out of an iteration link, and executing and outputting the searched optimal solution.
The tabu table stores the complete path, and the candidate solutions are generated by exchanging the order of two adjacent points in one solution. If all the candidate solutions generated in a certain round of iteration are in the tabu table, the round of iteration directly selects the optimal solution in the tabu table as a new current solution, and the tabu table is not updated. The number of remaining rounds that each solution in the tabu table can save in iteration is recorded by a number, when the number of remaining saved rounds of the solution is 0, the solution is moved out of the tabu table, and the process selects the best local candidate so as to avoid the local optimum. Therefore, path planning by adopting the TS in the sub-area is beneficial to avoiding the local optimization, and a specific planned path diagram is shown in fig. 4.
The fourth step: the ant colony path planning algorithm plans the whole operation path, and the tabu search algorithm plans the operation path in each area. The agricultural machine operates along the planned path through an LQR control algorithm, in order to avoid overlapping of repeated operation in an area, the agricultural machine searches a K value of the area before entering the area after rough division, if K is 0, the agricultural machine operates in the area according to the path planned by a taboo search algorithm, and the operation is finished and the K value is updated; if K is 1, the next area is turned until all the areas reach the full coverage effect. The LQR control algorithm is used for overcoming deviation of the agricultural machinery from a preset path caused by various reasons such as slipping and the like, and further ensuring that the agricultural machinery can accurately follow the planned path to drive.
Therefore, the method can effectively cope with complex environments such as hilly and mountainous regions, basins, valleys and the like compared with other technologies, is low in coverage repetition rate, and can be suitable for planning the optimal full coverage path of the intelligent agricultural machinery.
In summary, the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (2)
1. A method for planning a full-coverage path of agricultural machinery in a complex environment is characterized by comprising the following steps:
1) firstly, expressing a farmland environment, roughly dividing the farmland into a plurality of adjacent areas by adopting a Boustrophledon decomposition algorithm, assigning K to each area, wherein K is used for expressing whether the area is covered or not, and K is initialized to be uncovered;
2) randomly taking one point in each region as a reference point, traversing the regions through an ant colony path planning algorithm in a three-dimensional environment to obtain a path which can pass through each reference point one time without repetition;
3) each area is divided into sub-areas represented by grids in a thinning mode, agricultural machinery adopts a tabu search algorithm to traverse the sub-areas for local coverage, and paths in each area are planned;
4) the agricultural machinery follows the path operation planned by the ant colony path planning algorithm, before entering the area after rough division, the K value of the area is searched, if K indicates that the corresponding area is not covered, the agricultural machinery operates in the area according to the path planned by the tabu search algorithm, and the K value is updated after the operation is finished; if K indicates that the corresponding area is covered, turning to the next area until all areas reach the full coverage effect.
2. The method for planning the full-coverage path of the agricultural machine in the complex environment according to claim 1, further comprising the step of controlling the agricultural machine to follow the planned path through an LQR control algorithm during the traveling process of the agricultural machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111437329.0A CN114323019A (en) | 2021-11-30 | 2021-11-30 | Method for planning all-covering path of agricultural machinery in complex environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111437329.0A CN114323019A (en) | 2021-11-30 | 2021-11-30 | Method for planning all-covering path of agricultural machinery in complex environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114323019A true CN114323019A (en) | 2022-04-12 |
Family
ID=81047431
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111437329.0A Pending CN114323019A (en) | 2021-11-30 | 2021-11-30 | Method for planning all-covering path of agricultural machinery in complex environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114323019A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115421522A (en) * | 2022-06-20 | 2022-12-02 | 南京信息工程大学 | Unmanned aerial vehicle coverage path planning method based on parallel self-adaptive ant colony algorithm |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107843262A (en) * | 2017-10-30 | 2018-03-27 | 洛阳中科龙网创新科技有限公司 | A kind of method of farm machinery all standing trajectory path planning |
WO2018176595A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Unmanned bicycle path planning method based on ant colony algorithm and polar coordinate transformation |
CN112650219A (en) * | 2020-12-05 | 2021-04-13 | 合肥工业大学 | Unmanned mobile platform path planning method based on full coverage algorithm |
CN112965485A (en) * | 2021-02-03 | 2021-06-15 | 武汉科技大学 | Robot full-coverage path planning method based on secondary region division |
-
2021
- 2021-11-30 CN CN202111437329.0A patent/CN114323019A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018176595A1 (en) * | 2017-03-31 | 2018-10-04 | 深圳市靖洲科技有限公司 | Unmanned bicycle path planning method based on ant colony algorithm and polar coordinate transformation |
CN107843262A (en) * | 2017-10-30 | 2018-03-27 | 洛阳中科龙网创新科技有限公司 | A kind of method of farm machinery all standing trajectory path planning |
CN112650219A (en) * | 2020-12-05 | 2021-04-13 | 合肥工业大学 | Unmanned mobile platform path planning method based on full coverage algorithm |
CN112965485A (en) * | 2021-02-03 | 2021-06-15 | 武汉科技大学 | Robot full-coverage path planning method based on secondary region division |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115421522A (en) * | 2022-06-20 | 2022-12-02 | 南京信息工程大学 | Unmanned aerial vehicle coverage path planning method based on parallel self-adaptive ant colony algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Frontier-based multi-robot map exploration using particle swarm optimization | |
CN109254588B (en) | Unmanned aerial vehicle cluster cooperative reconnaissance method based on cross variation pigeon swarm optimization | |
US8396730B2 (en) | System and method for resource allocation and management | |
CN106323293B (en) | Two groups of multidirectional robot path planning methods based on multiple target search | |
Ma et al. | Improved ant colony algorithm for global optimal trajectory planning of UAV under complex environment. | |
CN110308740A (en) | A kind of unmanned aerial vehicle group dynamic task allocation method towards mobile target tracking | |
CN106647754A (en) | Path planning method for orchard tracked robot | |
Ferguson et al. | Anytime, dynamic planning in high-dimensional search spaces | |
CN112229419B (en) | Dynamic path planning navigation method and system | |
CN110989352A (en) | Group robot collaborative search method based on Monte Carlo tree search algorithm | |
CN111024080A (en) | Unmanned aerial vehicle group-to-multi-mobile time-sensitive target reconnaissance path planning method | |
CN106647808B (en) | AUVs searching and trapping task allocation control method based on fuzzy control algorithm | |
CN114323019A (en) | Method for planning all-covering path of agricultural machinery in complex environment | |
CN112025715A (en) | Mobile robot double-layer path planning method with unknown local environment | |
Wang | RETRACTED: Path planning for unmanned wheeled robot based on improved ant colony optimization | |
Qiming et al. | A review of intelligent optimization algorithm applied to unmanned aerial vehicle swarm search task | |
Wang et al. | Full coverage path planning methods of harvesting robot with multi-objective constraints | |
Saffari et al. | Bee colony algorithm for real-time optimal path planning of mobile robots | |
Su et al. | Collaborative motion planning based on the improved ant colony algorithm for multiple autonomous vehicles | |
Zafar et al. | Mine detection and route planning in military warfare using multi agent system | |
Wang et al. | Double heuristic optimization based on hierarchical partitioning for coverage path planning of robot mowers | |
Peng et al. | Cooperative area search for multiple UAVs based on RRT and decentralized receding horizon optimization | |
Chen | Path Planning of Mobile Robot Using Hybrid Algorithm Based on GA-IACO. | |
CN114625137A (en) | AGV-based intelligent parking path planning method and system | |
CN111896001A (en) | Three-dimensional ant colony track optimization method |
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 |