CN107703945A - A kind of intelligent farm machinery paths planning method of multiple targets fusion - Google Patents
A kind of intelligent farm machinery paths planning method of multiple targets fusion Download PDFInfo
- Publication number
- CN107703945A CN107703945A CN201711036801.3A CN201711036801A CN107703945A CN 107703945 A CN107703945 A CN 107703945A CN 201711036801 A CN201711036801 A CN 201711036801A CN 107703945 A CN107703945 A CN 107703945A
- Authority
- CN
- China
- Prior art keywords
- path
- obstacle
- node
- point
- target point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000004927 fusion Effects 0.000 title claims abstract description 13
- 230000004888 barrier function Effects 0.000 claims abstract description 17
- 230000003068 static effect Effects 0.000 claims abstract description 15
- 238000013135 deep learning Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 6
- 238000005457 optimization Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000013459 approach Methods 0.000 claims description 2
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims description 2
- 230000006872 improvement Effects 0.000 claims description 2
- 238000012886 linear function Methods 0.000 claims description 2
- 238000011176 pooling Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 238000004800 variational method Methods 0.000 claims description 2
- 230000015572 biosynthetic process Effects 0.000 abstract 1
- 239000000446 fuel Substances 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Guiding Agricultural Machines (AREA)
Abstract
The intelligent farm machinery paths planning method based on multiple targets fusion of the present invention, it is related to farm machinery automation, is embodied as：A) gis maps, are generated by photo；B) navigation map, is generated, while static-obstacle is positioned, generates grating map；C), starting point, target point are set on the grating map of formation；D) straight line and the path planning in turning section, are carried out according to starting point, target point：E) deep learning system identification barrier, is used in by path planning operation process, and the safe distance of agricultural machinery and barrier is set；If running into dynamic barrier, meet that safe distance then blow a whistle warning；If barrier is not hidden, using static barrier-avoiding method avoiding obstacles, continue after releasing barrier by original route operation.Realize agricultural machinery and make intelligent decision in unknown work environment, ensure that path is shorter and fuel consumption is less and ensures to avoid rapidly when running into barrier while the task that fulfils assignment, greatly improve operating efficiency.
Description
Technical Field
The invention relates to agricultural machinery automation, in particular to a multi-target fusion intelligent agricultural machinery path planning method.
Background
Years of development experience of foreign agricultural machinery industry shows that the adoption of an intelligent and automatic operation mode is a necessary trend of agricultural development and is an effective way for developing high-efficiency and cost-saving agriculture. Developed countries of world agriculture adopt highly automated operation machinery to not only improve work efficiency and reduce operation cost, but also improve the relative advantages of quantity and price of agricultural products in international markets. To be internationally established in the agricultural machinery industry of China, the gap between China and agriculture developed countries in the aspect of agricultural machinery equipment must be reduced, so that the agricultural machinery equipment with high degree of automation and intelligence in foreign countries cannot completely occupy the market of China, and the situation that the agricultural machinery industry of China falls into a predicament is also avoided. In recent years, with the continuous deepening of the reform open policy of China, the scientific and technical aspects of China also get a rapid development, and a foundation is laid for realizing the automation and the intellectualization of agricultural production in China.
The multi-objective optimization problem has been a very important research topic in scientific research and engineering applications. The evolutionary algorithm has the advantage of solving the multi-objective optimization problem, can simultaneously search a plurality of solutions of the optimization problem because of no requirement on the prior knowledge of the optimization problem, has the capacity of processing a large problem space, and can overcome the defects of the traditional multi-objective optimization method.
The Chinese patent CN201310121591.3 (a multi-target path planning method considering target node timeliness) discloses a multi-target path planning device and method considering searching robot target node timeliness, and the route planning considering two optimization targets of route consumption and node timeliness is realized by using a multi-target genetic algorithm through two-stage decoupling including route planning and route generation, so that the searching performance of a mobile robot supervised by an operator is improved, and particularly better searching performance can be obtained when the problem of node timeliness needs to be considered in route searching. The invention provides a thought on solving the multi-objective optimization problem, but when the method is applied to the intelligent agricultural machinery path planning, the method also needs to consider the completion of the operation task, simultaneously ensures that the path is short and the oil consumption is less, and ensures that the method can be quickly avoided when encountering obstacles, and the key point of the method is that.
Disclosure of Invention
In order to achieve the aim and overcome the defects of the prior art, the invention provides an intelligent agricultural machine path planning method based on multi-target fusion, so that an agricultural machine can make an intelligent decision in an unknown working environment, the purposes of ensuring a shorter path and less oil consumption and quickly avoiding obstacles while completing an operation task are achieved, and the working efficiency can be greatly improved.
It is first clear that the optimal path planning here requires four conditions to be met: within the boundary working environment constraint (that is, to achieve full coverage), dynamic obstacle avoidance can be performed, the path is shortest, and the oil consumption is lowest, wherein the full coverage, the path is shortest, and the oil consumption is lowest all can be achieved through optimal path planning, and then the solution idea of the application can be summarized as performing agricultural machinery path planning by a method of finding an optimal path and fusing the dynamic obstacle avoidance.
The intelligent agricultural mechanical path planning method based on multi-target fusion comprises the following steps:
a) Generating a gis map by aerial photo of the unmanned aerial vehicle;
b) Generating a navigation map for agricultural machinery according to the boundary characteristics of the operation block, and positioning static obstacles in the navigation map by combining an accurate positioning technology to generate a grid map;
c) Setting a starting point and a target point on the formed grid map;
d) And planning a path according to the starting point and the target point:
d-1, taking a straight line section from the starting point to the target point 1, and adopting the combination of an A-star algorithm and a Dijkstra algorithm to perform static obstacle avoidance so as to determine an optimal straight line path;
d-2, determining the optimal turning path by adopting an optimal control theory, wherein the turning path is from the target point 1 to the target point 2;
d-3, repeating the step d-1 for a straight line section from the target point 2 to the target point 3, repeating the step d-2 for a turning section from the target point 3 to the target point 4, planning a path in sequence according to the method until a final target point is reached, and finally generating an optimal path electronic map;
e) Adopting a deep learning system to identify the barrier in the process of operating according to the planned path, and setting the safety distance between the agricultural machinery and the barrier;
if a dynamic barrier is met, if the safety distance is met, a whistle is given to warn;
if the obstacle is not avoided, the obstacle is avoided by adopting the static obstacle avoiding method in the step d-1, and the operation is continued according to the original path after the obstacle is removed.
The method firstly plans the path of the farmland environment, wherein the total coverage, the shortest path and the lowest oil consumption are integrated, and the static obstacle avoidance is included, so that the planning is relatively comprehensive, the working efficiency is improved, and the cost is saved. Meanwhile, a deep learning theory is introduced, the deep learning recognition system is adopted to process the image, the surrounding environment of the operation plot is monitored in real time, and the operation plot can be avoided in time if dynamic obstacles are met. By adopting the operation method combining path planning and dynamic obstacle avoidance, the overall control performance of the agricultural machinery is greatly improved when the agricultural machinery operates in the farmland independently, and the operation can be completed efficiently and safely on the whole.
Drawings
FIG. 1 is a schematic diagram of a grid map of an embodiment of the invention:
fig. 2 is a flow chart of the method combining the a-algorithm and the Dijkstra algorithm of the present invention:
FIG. 3 is a schematic view of a motion model of the agricultural machine of the present invention;
FIG. 4 is a diagram of a specific obstacle avoidance method-a shortest tangent method;
FIG. 5 is a schematic diagram of a dynamic obstacle avoidance process based on a deep learning system;
FIG. 6 is a flow chart diagram of the intelligent agricultural machine path planning method based on multi-objective fusion.
Detailed Description
To realize the intellectualization of agricultural machinery, one of the key technologies is path planning and navigation, but at present, the path planning of agricultural machinery in China mainly relates to a single target, for example, a shortest path algorithm is adopted and obstacle avoidance is added while an operation task is completed, so that the problem of oil consumption is ignored under the condition, and the total cost is not ideal. The invention perfectly solves the defects by combining the shortest path planning method of the agricultural machinery, the obstacle avoidance method of the agricultural machinery and the minimum oil consumption movement path planning method of the agricultural machinery, namely, the scheme of finishing the operation task, ensuring that the path is shorter and the oil consumption is less and ensuring that the agricultural machinery can be quickly avoided when encountering the obstacle is considered in the path planning of the intelligent agricultural machinery.
Specifically, the invention is applied to agricultural machinery, and the working place is a farmland. The following detailed description is made in conjunction with the accompanying drawings.
With reference to fig. 6, the intelligent agricultural mechanical path planning method based on multi-objective fusion of the present application includes the following steps:
a) Generating a gis map by aerial photography of the photo by the unmanned aerial vehicle;
b) Generating a navigation map for agricultural machinery to use according to the boundary characteristics of the operation block, positioning static obstacles in the navigation map by combining an accurate positioning technology, and generating a grid map as shown in figure 1;
c) Setting a starting point and a target point on the formed grid map;
d) And planning a path according to the starting point and the target point:
d-1, taking a straight line section from the starting point to the target point 1, and adopting the combination of an A-star algorithm and a Dijkstra algorithm to perform static obstacle avoidance so as to determine an optimal straight line path;
d-2, determining the optimal turning path by adopting an optimal control theory, wherein the turning path is from the target point 1 to the target point 2;
d-3, repeating the step d-1 for a straight line section from the target point 2 to the target point 3, repeating the step d-2 for a turning section from the target point 3 to the target point 4, planning a path in sequence according to the method until a final target point is reached, and finally generating an optimal path electronic map;
e) Adopting a deep learning system to identify the barrier in the process of operating according to the planned path, and setting the safe distance between the agricultural machinery and the barrier;
if a dynamic barrier is met, whistling and warning are carried out if the safety distance is met;
if the obstacle is not avoided, the obstacle is avoided by adopting the static obstacle avoiding method in the step d-1, and the operation is continued according to the original path after the obstacle is removed.
With reference to fig. 2, the method for determining the optimal straight-line path by combining the a-star algorithm and the Dijkstra algorithm in step d-1 includes the following steps:
1) And recording raster map information and recording the accessible or inaccessible state of each area.
2) And initializing the grid map, namely recording all areas as unsearched areas, and setting a starting point and a target point for the current journey of the agricultural machinery.
3) And searching eight nodes around the current node, removing the inaccessible node and the expanded node, then putting the rest nodes into a temporary table, and putting the current node into a closed table.
4) And calculating f values of nodes (evaluation function values from a starting point to a target point) stored in the temporary table, sorting according to the length of the estimated path, selecting the first two nodes with the shortest path (if repeated single selection is available), and inputting the rest nodes into the open table.
5) Detecting whether the node selected in the step 4) contains a target point:
if yes, placing the target points into the closed table, placing the other points into the open table, and continuing to perform the step 6);
if not, the node f is compared with the maximum estimation value K. If the f values of the selected nodes are all larger than K, selecting the nodes as the current nodes and continuing to the step 3); if the f value of the node is smaller than K, the node with the f value smaller than K is taken as the current node to continue the step 3), and the rest nodes are clicked into the open table.
6) And independently extracting the closing form containing the target point and a batch of better nodes, putting the starting point into the shortest node set, and putting the rest points into the node set to be calculated.
7) And selecting the node N with the shortest distance from the node set to be calculated, putting the node N into the shortest node set, and removing the node N from the node set to be calculated.
8) And recalculating the distance from each node of the node set to be calculated to the starting point, wherein N is selected to update the distance of each node.
9) And 7) repeating the steps 7) and 8), when the node set to be detected is empty, selecting a shortest path from the starting point to the end point.
In connection with a and Dijkstra algorithm, reference may be made in detail to "a method for shortest path planning for agricultural machinery based on Dijkstra algorithm" with application number 201710966489.1.
The optimal control theory (optimal control theory) is a main branch of modern control theory, and focuses on researching basic conditions and comprehensive methods for optimizing performance indexes of a control system. The optimal control theory is a discipline that studies and solves the optimal solution sought from all possible control schemes. The application determines the optimal turning path by using an optimal control theory, and the method comprises the following steps:
with reference to fig. 3, the agricultural machine such as a tractor is simulated as a two-wheeled vehicle model, and a vehicle motion equation formula is established:
x and y are coordinates (m) of the central point of the rear wheel of the tractor, theta is the yaw angle (rad) of the tractor, alpha is the steering angle (rad) of the tractor, v is the speed (m/s) of the tractor, and l is the wheelbase (m) of the tractor;
1) The state equation of the coordinates x and y of the rear wheels is
2) Setting an initial time t 0 =0, terminal time t f Let initial time t 0 Then each state quantity is x =0, y =0, z =0; terminal time t f When the state quantity is z = pi, x =0, y = d (width of one operation of the agricultural machine set); the constraint condition is that | u | is less than or equal to alpha, x is more than or equal to 0, and the trolley turns left;
3) Establishing an evaluation function formula according to the constraint conditions
In the formula of gamma 1 ,γ 2 H (x (t)) is a penalty function, wherein
When J is<10 -3 The time is the optimal path; since the state function is a non-linear function, by constantly changing t f And solving by using a quadratic variational method.
The deep learning based automatic obstacle avoidance method for the agricultural machinery mainly comprises the steps of collecting image information, identifying the collected images by a deep learning system, matching the obtained result with the corresponding set output, and still performing appropriate processing by a powerful online learning system if the obtained result is not identified. With reference to fig. 5, the dynamic obstacle avoidance method based on deep learning includes the steps of:
1) The agricultural machine works according to a set path and carries out shooting by using a carried camera;
2) Extracting characteristics layer by layer through a convolution group consisting of a convolution layer and a pooling layer in the convolution neural network, and finally completing classification through a plurality of full connection layers;
3) Comparing the extracted image characteristics with image data in a database, screening out image data which is most matched with the acquired image, and judging the environmental information of the agricultural machinery;
4) If the obstacle is detected, detecting the shortest distance between the obstacle and a sensor arranged on the agricultural machine;
first, the type of the obstacle is judged:
if the static obstacle is detected, combining the A and Dijkstra algorithms after the improvement and optimization to realize the local obstacle avoidance path planning;
if the obstacle is a dynamic obstacle, the obstacle is whistled to remind or is decelerated to parking waiting, and if the obstacle does not react for a certain time, the obstacle is processed according to a static obstacle.
The local obstacle avoidance path planning method comprises the following steps:
(1) When an obstacle is found, a limited search area is divided according to the required precision and the widest width of the agricultural machinery according to a specific distance, and a local grid map is established along the advancing direction of the agricultural machinery in the area;
(2) Determining the size of the obstacle and the position of the obstacle in the local grid map according to the sensing information;
(3) Determining the minimum safe distance to an obstacle according to the information of the width, the speed and the minimum turning radius of the agricultural machine, and determining the maximum obstacle approach point as a starting point A of a local obstacle avoidance path on the motion track of the original agricultural machine; determining a minimum obstacle approaching point on the original movement track of the agricultural machine as a local obstacle avoidance termination point B;
(4) According to the grid division graph, combining A and Dijkstra algorithm, searching a local planning grid, and determining a path from the point A to the point B;
(5) And connecting the points of the shortest distance set to form an optimal path.
(6) And (5) fitting the obtained optimal path by adopting a specific obstacle avoidance method and a shortest tangent method, so as to obtain a more reasonable path.
5) And continuing to operate according to the original path after the barrier is removed.
The intelligent decision making method realizes intelligent decision making of the agricultural machinery in an unknown working environment, and achieves the purposes of ensuring a shorter path and less oil consumption while completing the working task and ensuring that the agricultural machinery can be quickly avoided when encountering obstacles.
Claims (5)
1. An intelligent agricultural mechanical path planning method based on multi-objective fusion is characterized in that: the method comprises the following steps:
a) Generating a gis map by aerial photography of the photo by the unmanned aerial vehicle;
b) Generating a navigation map for agricultural machinery according to the boundary characteristics of the operation block, and positioning static obstacles in the navigation map by combining an accurate positioning technology to generate a grid map;
c) Setting a starting point and a target point on the formed grid map;
d) And planning a path according to the starting point and the target point:
d-1, taking a straight line section from the starting point to the target point 1, and adopting the combination of an A-star algorithm and a Dijkstra algorithm to perform static obstacle avoidance so as to determine an optimal straight line path;
d-2, determining the optimal turning path by adopting an optimal control theory, wherein the turning path is from the target point 1 to the target point 2;
d-3, repeating the step d-1 for a straight road section from the target point 2 to the target point 3, repeating the step d-2 for a turning road section from the target point 3 to the target point 4, sequentially planning a path according to the method until a final target point is reached, and finally generating an optimal path electronic map;
e) Adopting a deep learning system to identify the barrier in the process of operating according to the planned path, and setting the safe distance between the agricultural machinery and the barrier;
if a dynamic barrier is met, whistling and warning are carried out if the safety distance is met;
if the obstacle is not avoided, the obstacle is avoided by adopting the static obstacle avoiding method in the step d-1, and the operation is continued according to the original path after the obstacle is removed.
2. The intelligent agricultural mechanical path planning method based on multi-objective fusion of claim 1, which is characterized in that:
the method for determining the optimal straight line path by combining the A-star algorithm and the Dijkstra algorithm in the step d-1 comprises the following steps:
1) Inputting grid map information, and recording the accessible or inaccessible state of each area;
2) Initializing a grid map, namely recording all areas as unsearched areas, and setting a starting point and a target point for the current journey of the agricultural machinery;
3) Searching eight nodes around the current node, removing the inaccessible node and the expanded node, then putting the rest nodes into a temporary table, and putting the current node into a closed table;
4) Calculating the f value of the node stored in the temporary table, namely the evaluation function value from the departure point to the target point, sorting according to the length of the estimated path, and selecting the first two nodes with the shortest path, wherein if repeated single selection exists; the other points are input into an open table;
5) Detecting whether the node selected in the step 4) contains a target point:
if yes, placing the target points into the closed table, placing the other points into the open table, and continuing to perform the step 6);
if not, comparing the node f value with the maximum estimated value K: if the f values of the selected nodes are all larger than K, selecting the nodes as the current nodes and continuing to the step 3); if the f value of the node is smaller than K, taking the node with the f value smaller than K as the current node to continue the step 3), and inputting the rest nodes into the open table;
6) Extracting the closing form containing the target point and a batch of better nodes, putting the starting point into the shortest node set, and putting the rest points into the node set to be calculated;
7) Selecting a node N with the shortest distance from the node set to be calculated, putting the node N into the shortest node set, and removing the node N from the node set to be calculated;
8) Recalculating the distance from each node of the node set to be calculated to the starting point, wherein N is required to update the distance of each node because N is selected;
9) And 7) repeating the steps 7) and 8), when the node set to be detected is empty, selecting a shortest path from the starting point to the end point.
3. The intelligent agricultural mechanical path planning method based on multi-objective fusion of claim 1, which is characterized in that: in the step d-2, an optimal turning path is determined by using an optimal control theory, and the method comprises the following steps:
simulating agricultural machinery such as a tractor into a two-wheeled vehicle model, and establishing a vehicle motion equation formula:
x and y are coordinates (m) of the central point of the rear wheel of the tractor, theta is the yaw angle (rad) of the tractor, alpha is the steering angle (rad) of the tractor, v is the speed (m/s) of the tractor, and l is the wheelbase (m) of the tractor;
1) The state equation of the coordinates x and y of the rear wheels is
2) Setting an initial time t 0 =0, terminal time t f Let initial time be t 0 Then each state quantity is x =0, y =0, z =0; terminal time t f When the state quantity is z = pi, x =0, y = d (width of one operation of the agricultural machine set); the constraint condition is that | u | is less than or equal to alpha, x is more than or equal to 0, and the trolley turns left;
3) Establishing an evaluation function formula according to the constraint conditions
In the formula of gamma 1 ,γ 2 H (x (t)) is a penalty function, wherein
When J is<10 -3 The time is the optimal path; since the state function is a non-linear function, by constantly changing t f And solving by using a quadratic variational method.
4. The intelligent agricultural mechanical path planning method based on multi-objective fusion of claim 1, which is characterized in that: the dynamic obstacle avoidance method based on deep learning in the step e) comprises the following steps:
1) The agricultural machine works according to a set path and carries out shooting by using a carried camera;
2) Extracting characteristics layer by layer through a convolution group consisting of a convolution layer and a pooling layer in the convolution neural network, and finally completing classification through a plurality of full connection layers;
3) Comparing the extracted image characteristics with image data in a database, screening out image data which is most matched with the acquired image, and judging the environmental information of the agricultural machinery;
4) If the obstacle is detected, detecting the shortest distance between the obstacle and a sensor arranged on the agricultural machine;
judging the type of the obstacle:
if the static obstacle is detected, combining the A and Dijkstra algorithms after the improvement and optimization to realize the local obstacle avoidance path planning;
if the obstacle is a dynamic obstacle, whistling to remind or decelerating to a parking waiting state, and if the obstacle does not react for a certain time, processing according to a static obstacle;
5) And continuing to operate according to the original path after the barrier is removed.
5. The intelligent agricultural mechanical path planning method based on multi-objective fusion as claimed in claim 4, wherein:
the local obstacle avoidance path planning method comprises the following steps:
(1) When an obstacle is found, a limited search area is divided according to the required precision and the widest width of the agricultural machinery according to a specific distance, and a local grid map is established along the advancing direction of the agricultural machinery in the area;
(2) Determining the size of the obstacle and the position of the obstacle in the local grid map according to the sensing information;
(3) Determining the minimum safe distance to an obstacle according to the information of the width, the speed and the minimum turning radius of the agricultural machine, and determining the maximum obstacle approach point as a starting point A of a local obstacle avoidance path on the motion track of the original agricultural machine; determining a minimum obstacle approaching point on the original movement track of the agricultural machinery as a local obstacle avoidance termination point B;
(4) According to the grid division graph, combining A and Dijkstra algorithm, searching a local planning grid, and determining a path from the point A to the point B;
(5) And connecting the points of the shortest distance set to form an optimal path.
(6) And fitting the obtained optimal path by adopting a shortest tangent obstacle avoidance method so as to obtain a more reasonable path.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711036801.3A CN107703945A (en) | 2017-10-30 | 2017-10-30 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711036801.3A CN107703945A (en) | 2017-10-30 | 2017-10-30 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107703945A true CN107703945A (en) | 2018-02-16 |
Family
ID=61177102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711036801.3A Pending CN107703945A (en) | 2017-10-30 | 2017-10-30 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107703945A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109099925A (en) * | 2018-08-31 | 2018-12-28 | 江苏大学 | A kind of unmanned farm machinery navigation path planning and operation quality appraisal procedure and device |
| CN109164808A (en) * | 2018-09-07 | 2019-01-08 | 农业部南京农业机械化研究所 | A kind of intelligent agricultural machinery automatic aligning device |
| CN109471432A (en) * | 2018-11-08 | 2019-03-15 | 南京农业大学 | A kind of independent navigation agricultural vehicle Short Path Avoiding Obstructions planing method |
| CN109557928A (en) * | 2019-01-17 | 2019-04-02 | 湖北亿咖通科技有限公司 | Automatic driving vehicle paths planning method based on map vector and grating map |
| CN109717175A (en) * | 2019-03-06 | 2019-05-07 | 山东交通学院 | Orchard intelligence self-travel type spraying system and its control method |
| CN109885060A (en) * | 2019-01-18 | 2019-06-14 | 丰疆智能科技研究院(常州)有限公司 | Path management system and its management method |
| CN110058563A (en) * | 2019-01-18 | 2019-07-26 | 丰疆智能科技研究院(常州)有限公司 | Operation monitoring system and its monitoring method |
| CN110209156A (en) * | 2019-04-09 | 2019-09-06 | 丰疆智能科技股份有限公司 | The driving path planning system and its method of automatic harvester |
| CN110262518A (en) * | 2019-07-22 | 2019-09-20 | 上海交通大学 | Automobile navigation method, system and medium based on track topological map and avoidance |
| CN110794832A (en) * | 2019-10-21 | 2020-02-14 | 同济大学 | Mobile robot path planning method based on reinforcement learning |
| CN110825091A (en) * | 2019-11-29 | 2020-02-21 | 洛阳中科龙网创新科技有限公司 | Intelligent tractor intelligent routing method and device based on unmanned aerial vehicle |
| CN110908387A (en) * | 2019-12-13 | 2020-03-24 | 齐鲁工业大学 | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment |
| CN111459169A (en) * | 2020-04-27 | 2020-07-28 | 四川智动木牛智能科技有限公司 | Comprehensive pipe gallery inspection method based on wheeled robot |
| CN111462323A (en) * | 2020-05-06 | 2020-07-28 | 中国人民解放军国防科技大学 | Three-dimensional space-oriented dynamic deception path planning method and system |
| CN112015176A (en) * | 2020-08-14 | 2020-12-01 | 合肥工业大学 | Unmanned tractor field operation path planning method and device |
| CN112230649A (en) * | 2019-06-28 | 2021-01-15 | 丰田自动车株式会社 | Machine learning method and mobile robot |
| CN112525195A (en) * | 2020-11-20 | 2021-03-19 | 中国人民解放军国防科技大学 | Multi-target genetic algorithm-based aircraft track rapid planning method |
| CN113406960A (en) * | 2021-07-08 | 2021-09-17 | 浙江大学 | Real-time path planning and control method for ground steering of agricultural unmanned vehicle |
| CN113701780A (en) * | 2021-09-14 | 2021-11-26 | 成都信息工程大学 | Real-time obstacle avoidance planning method based on A-star algorithm |
| CN113821027A (en) * | 2021-08-27 | 2021-12-21 | 中国人民解放军军事科学院战争研究院 | Priority-based incomplete self-body deck coordinated dispatching path planning method |
| CN114326717A (en) * | 2021-12-13 | 2022-04-12 | 中国科学院计算技术研究所 | Intelligent agricultural machinery transition and operation fusion path planning method and system |
| CN116225031A (en) * | 2023-05-09 | 2023-06-06 | 南京泛美利机器人科技有限公司 | Three-body cooperative intelligent obstacle avoidance method and system for man-machine cooperative scene |
| CN116360465A (en) * | 2023-05-31 | 2023-06-30 | 陕西耕辰科技有限公司 | Intelligent agricultural machine grain unloading control method, intelligent agricultural machine grain unloading control system, storage medium and intelligent agricultural machine |
| WO2023123117A1 (en) * | 2021-12-29 | 2023-07-06 | 广东美的白色家电技术创新中心有限公司 | Obstacle avoidance method of mowing robot, and mowing robot |
| CN116400740A (en) * | 2023-06-06 | 2023-07-07 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866181A (en) * | 2009-04-16 | 2010-10-20 | 中国农业大学 | Navigation method and navigation device of agricultural machinery as well as agricultural machinery |
| CN102167038A (en) * | 2010-12-03 | 2011-08-31 | 北京农业信息技术研究中心 | Method and device for generating all-region-covering optimal working path for farmland plot |
| CN102749084A (en) * | 2012-07-10 | 2012-10-24 | 南京邮电大学 | Path selecting method oriented to massive traffic information |
| CN104850011A (en) * | 2015-05-22 | 2015-08-19 | 上海电力学院 | Optimal path planning method for TSP obstacle avoidance in obstacle environment |
| CN105182979A (en) * | 2015-09-23 | 2015-12-23 | 上海物景智能科技有限公司 | Mobile robot obstacle detecting and avoiding method and system |
| CN106292704A (en) * | 2016-09-07 | 2017-01-04 | 四川天辰智创科技有限公司 | The method and device of avoiding barrier |
| CN106681335A (en) * | 2017-01-22 | 2017-05-17 | 无锡卡尔曼导航技术有限公司 | Obstacle-avoiding route planning and control method for unmanned agricultural machine driving |
| CN106909148A (en) * | 2017-03-10 | 2017-06-30 | 南京沃杨机械科技有限公司 | Based on the unmanned air navigation aid of agricultural machinery that farm environment is perceived |
| CN106970615A (en) * | 2017-03-21 | 2017-07-21 | 西北工业大学 | A kind of real-time online paths planning method of deeply study |
-
2017
- 2017-10-30 CN CN201711036801.3A patent/CN107703945A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101866181A (en) * | 2009-04-16 | 2010-10-20 | 中国农业大学 | Navigation method and navigation device of agricultural machinery as well as agricultural machinery |
| CN102167038A (en) * | 2010-12-03 | 2011-08-31 | 北京农业信息技术研究中心 | Method and device for generating all-region-covering optimal working path for farmland plot |
| CN102749084A (en) * | 2012-07-10 | 2012-10-24 | 南京邮电大学 | Path selecting method oriented to massive traffic information |
| CN104850011A (en) * | 2015-05-22 | 2015-08-19 | 上海电力学院 | Optimal path planning method for TSP obstacle avoidance in obstacle environment |
| CN105182979A (en) * | 2015-09-23 | 2015-12-23 | 上海物景智能科技有限公司 | Mobile robot obstacle detecting and avoiding method and system |
| CN106292704A (en) * | 2016-09-07 | 2017-01-04 | 四川天辰智创科技有限公司 | The method and device of avoiding barrier |
| CN106681335A (en) * | 2017-01-22 | 2017-05-17 | 无锡卡尔曼导航技术有限公司 | Obstacle-avoiding route planning and control method for unmanned agricultural machine driving |
| CN106909148A (en) * | 2017-03-10 | 2017-06-30 | 南京沃杨机械科技有限公司 | Based on the unmanned air navigation aid of agricultural machinery that farm environment is perceived |
| CN106970615A (en) * | 2017-03-21 | 2017-07-21 | 西北工业大学 | A kind of real-time online paths planning method of deeply study |
Non-Patent Citations (1)
| Title |
|---|
| 梁栋: "基于深度学习的目标识别研究及其多机器人编队应用", 《万方数据库平台》 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109099925A (en) * | 2018-08-31 | 2018-12-28 | 江苏大学 | A kind of unmanned farm machinery navigation path planning and operation quality appraisal procedure and device |
| CN109099925B (en) * | 2018-08-31 | 2021-07-20 | 江苏大学 | Unmanned agricultural machine navigation path planning and operation quality evaluation method and device |
| CN109164808B (en) * | 2018-09-07 | 2021-04-02 | 农业部南京农业机械化研究所 | Intelligent automatic aligning device for agricultural machinery |
| CN109164808A (en) * | 2018-09-07 | 2019-01-08 | 农业部南京农业机械化研究所 | A kind of intelligent agricultural machinery automatic aligning device |
| CN109471432A (en) * | 2018-11-08 | 2019-03-15 | 南京农业大学 | A kind of independent navigation agricultural vehicle Short Path Avoiding Obstructions planing method |
| CN109471432B (en) * | 2018-11-08 | 2021-09-28 | 南京农业大学 | Shortest obstacle avoidance path planning method for autonomous navigation agricultural vehicle |
| CN109557928A (en) * | 2019-01-17 | 2019-04-02 | 湖北亿咖通科技有限公司 | Automatic driving vehicle paths planning method based on map vector and grating map |
| AU2019422604B2 (en) * | 2019-01-18 | 2023-06-29 | Fj Dynamics Technology Academy (Chang Zhou) Co., Ltd | Route management system and management method thereof |
| EP3913454A4 (en) * | 2019-01-18 | 2022-10-19 | FJ Dynamics Technology Academy (Chang Zhou) Co., Ltd. | Route management system and management method thereof |
| RU2763327C1 (en) * | 2019-01-18 | 2021-12-28 | Фж Дайнемикс Текнолоджи Экедеми (Чан Чжоу) Ко., Лтд | Route control system and method of it control |
| CN110058563B (en) * | 2019-01-18 | 2020-05-05 | 丰疆智能科技研究院(常州)有限公司 | Operation monitoring system and monitoring method thereof |
| WO2020147326A1 (en) * | 2019-01-18 | 2020-07-23 | 丰疆智能科技研究院(常州)有限公司 | Route management system and management method thereof |
| CN109885060A (en) * | 2019-01-18 | 2019-06-14 | 丰疆智能科技研究院(常州)有限公司 | Path management system and its management method |
| CN110058563A (en) * | 2019-01-18 | 2019-07-26 | 丰疆智能科技研究院(常州)有限公司 | Operation monitoring system and its monitoring method |
| CN109717175A (en) * | 2019-03-06 | 2019-05-07 | 山东交通学院 | Orchard intelligence self-travel type spraying system and its control method |
| CN110209156A (en) * | 2019-04-09 | 2019-09-06 | 丰疆智能科技股份有限公司 | The driving path planning system and its method of automatic harvester |
| CN112230649B (en) * | 2019-06-28 | 2024-01-09 | 丰田自动车株式会社 | Machine learning method and mobile robot |
| CN112230649A (en) * | 2019-06-28 | 2021-01-15 | 丰田自动车株式会社 | Machine learning method and mobile robot |
| CN110262518A (en) * | 2019-07-22 | 2019-09-20 | 上海交通大学 | Automobile navigation method, system and medium based on track topological map and avoidance |
| CN110794832A (en) * | 2019-10-21 | 2020-02-14 | 同济大学 | Mobile robot path planning method based on reinforcement learning |
| CN110825091A (en) * | 2019-11-29 | 2020-02-21 | 洛阳中科龙网创新科技有限公司 | Intelligent tractor intelligent routing method and device based on unmanned aerial vehicle |
| CN110908387A (en) * | 2019-12-13 | 2020-03-24 | 齐鲁工业大学 | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment |
| CN111459169A (en) * | 2020-04-27 | 2020-07-28 | 四川智动木牛智能科技有限公司 | Comprehensive pipe gallery inspection method based on wheeled robot |
| CN111459169B (en) * | 2020-04-27 | 2023-11-24 | 四川智动木牛智能科技有限公司 | Comprehensive pipe gallery inspection method based on wheeled robot |
| CN111462323A (en) * | 2020-05-06 | 2020-07-28 | 中国人民解放军国防科技大学 | Three-dimensional space-oriented dynamic deception path planning method and system |
| CN111462323B (en) * | 2020-05-06 | 2023-04-18 | 中国人民解放军国防科技大学 | Three-dimensional space-oriented dynamic deception path planning method and system |
| CN112015176A (en) * | 2020-08-14 | 2020-12-01 | 合肥工业大学 | Unmanned tractor field operation path planning method and device |
| CN112525195A (en) * | 2020-11-20 | 2021-03-19 | 中国人民解放军国防科技大学 | Multi-target genetic algorithm-based aircraft track rapid planning method |
| CN113406960A (en) * | 2021-07-08 | 2021-09-17 | 浙江大学 | Real-time path planning and control method for ground steering of agricultural unmanned vehicle |
| CN113821027A (en) * | 2021-08-27 | 2021-12-21 | 中国人民解放军军事科学院战争研究院 | Priority-based incomplete self-body deck coordinated dispatching path planning method |
| CN113821027B (en) * | 2021-08-27 | 2023-11-28 | 中国人民解放军军事科学院战争研究院 | Incomplete autonomous deck cooperative allocation and transportation path planning method based on priority |
| CN113701780B (en) * | 2021-09-14 | 2023-08-29 | 成都信息工程大学 | Real-time obstacle avoidance planning method based on A star algorithm |
| CN113701780A (en) * | 2021-09-14 | 2021-11-26 | 成都信息工程大学 | Real-time obstacle avoidance planning method based on A-star algorithm |
| CN114326717A (en) * | 2021-12-13 | 2022-04-12 | 中国科学院计算技术研究所 | Intelligent agricultural machinery transition and operation fusion path planning method and system |
| WO2023123117A1 (en) * | 2021-12-29 | 2023-07-06 | 广东美的白色家电技术创新中心有限公司 | Obstacle avoidance method of mowing robot, and mowing robot |
| CN116225031A (en) * | 2023-05-09 | 2023-06-06 | 南京泛美利机器人科技有限公司 | Three-body cooperative intelligent obstacle avoidance method and system for man-machine cooperative scene |
| CN116360465A (en) * | 2023-05-31 | 2023-06-30 | 陕西耕辰科技有限公司 | Intelligent agricultural machine grain unloading control method, intelligent agricultural machine grain unloading control system, storage medium and intelligent agricultural machine |
| CN116360465B (en) * | 2023-05-31 | 2023-09-01 | 陕西耕辰科技有限公司 | Intelligent agricultural machine grain unloading control method, intelligent agricultural machine grain unloading control system, storage medium and intelligent agricultural machine |
| CN116400740A (en) * | 2023-06-06 | 2023-07-07 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
| CN116400740B (en) * | 2023-06-06 | 2023-09-08 | 成都时代星光科技有限公司 | Intelligent unmanned aerial vehicle trend processing method, system and medium in full blind area environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107703945A (en) | A kind of intelligent farm machinery paths planning method of multiple targets fusion | |
| JP6916551B2 (en) | A method and device for planning a short-term route for autonomous driving by information fusion using V2X communication and image processing {METHOD AND DEVICE FOR SHORT-TERM PATH PLANNING OF AUTONOMOUS DRIVING THROUGH INFORMATION FOUSION | |
| CN114384920B (en) | Dynamic obstacle avoidance method based on real-time construction of local grid map | |
| JP2022016419A (en) | Trajectory prediction method and device | |
| CN108519094B (en) | Local path planning method and cloud processing terminal | |
| CN110749333A (en) | Unmanned vehicle motion planning method based on multi-objective optimization | |
| CN109597087A (en) | A kind of 3D object detection method based on point cloud data | |
| CN113705636B (en) | Method and device for predicting track of automatic driving vehicle and electronic equipment | |
| Jaspers et al. | Multi-modal local terrain maps from vision and lidar | |
| CN114005280A (en) | Vehicle track prediction method based on uncertainty estimation | |
| CN110986945B (en) | Local navigation method and system based on semantic altitude map | |
| CN111295666A (en) | Lane line detection method, device, control equipment and storage medium | |
| Grimmett et al. | Integrating metric and semantic maps for vision-only automated parking | |
| CN111098850A (en) | Automatic parking auxiliary system and automatic parking method | |
| Muhammad et al. | Novel algorithm for mobile robot path planning in constrained environment | |
| Büchner et al. | Learning and aggregating lane graphs for urban automated driving | |
| Wang et al. | Research on AGV task path planning based on improved A* algorithm | |
| Masmoudi et al. | Autonomous car-following approach based on real-time video frames processing | |
| Valente et al. | Evidential SLAM fusing 2D laser scanner and stereo camera | |
| CN114120270A (en) | Point cloud target detection method based on attention and sampling learning | |
| CN111310919B (en) | Driving control strategy training method based on scene segmentation and local path planning | |
| CN115451987A (en) | Path planning learning method for automatic driving automobile | |
| Xu et al. | TrafficEKF: A learning based traffic aware extended Kalman filter | |
| Yoo et al. | Gin: Graph-based interaction-aware constraint policy optimization for autonomous driving | |
| CN116203973B (en) | Intelligent control system of track AI inspection robot |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180216 |
|
| RJ01 | Rejection of invention patent application after publication |