CN114415718B - Three-dimensional track planning method based on improved potential field RRT algorithm - Google Patents
Three-dimensional track planning method based on improved potential field RRT algorithm Download PDFInfo
- Publication number
- CN114415718B CN114415718B CN202111584969.4A CN202111584969A CN114415718B CN 114415718 B CN114415718 B CN 114415718B CN 202111584969 A CN202111584969 A CN 202111584969A CN 114415718 B CN114415718 B CN 114415718B
- Authority
- CN
- China
- Prior art keywords
- track
- node
- rand
- potential
- obstacle
- 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.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 42
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000005070 sampling Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000001514 detection method Methods 0.000 claims description 4
- 230000004888 barrier function Effects 0.000 claims 2
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000010845 search algorithm Methods 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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a three-dimensional track planning method based on an improved potential field RRT algorithm, which is characterized in that an artificial potential field value is added into a node expansion process based on the RRT algorithm, a gravitational field is arranged at a target position, the expansion direction of a node is guided, the searching speed of the algorithm is accelerated, a repulsive field is arranged on an obstacle, the track and the obstacle are kept at a safe distance, and an initial track is obtained through continuous expansion of the node. And judging whether redundant nodes exist or not through a sight line algorithm, enabling the flight path to be smoother and safer through deleting the redundant nodes, finally obtaining an improved potential field RRT algorithm, applying the algorithm to a three-dimensional map, and planning a three-dimensional flight path for the unmanned aerial vehicle.
Description
Technical Field
The invention belongs to the field of unmanned aerial vehicles, and particularly relates to a three-dimensional track planning method based on an improved potential field RRT algorithm.
Background
The rapid expansion random tree (RRT) algorithm is a sampling-based search algorithm, wherein the initial position is set as a root node, then sampling is carried out in a map according to a certain rule to obtain leaf nodes, the leaf nodes are continuously sampled to form a random tree, and when the sampling point is close enough to the target position, the search is completed. The RRT algorithm is a completely random algorithm, lacks directionality, and performs poorly in maps with many obstacles. The artificial potential field method adds the virtual potential field concept into the map, sets a repulsive field for the obstacle, keeps a safe distance between the track and the obstacle, sets a gravitational field for the target position, guides the track searching direction, and moves the unmanned aerial vehicle along the resultant force direction until reaching the target point. The artificial potential field method has strong direction and high planning speed, but has the problem of easy sinking into local extremum.
Along with the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicle functions are more comprehensive, the degree of intelligence is higher and higher, and track planning technology is the important component of unmanned aerial vehicle intelligent process. The unmanned aerial vehicle track planning is to plan a series of continuous track nodes for the unmanned aerial vehicle on the premise of meeting the limitations of physical conditions and the like, so that the unmanned aerial vehicle keeps a safe distance from an obstacle and a threat area when flying along the track nodes, has smaller track cost, and finally reaches a target position.
In the three-dimensional map, the data quantity of map nodes is huge, and edge collision is easy to occur, so that a reliable three-dimensional track planning algorithm is designed, and the method has very important practical significance for unmanned aerial vehicle flight safety.
The existing method has the following problems:
1) The RRT algorithm is completely random and non-directional in the search process, and may not search for tracks in a map with more obstacles.
2) The artificial potential field method has strong directivity and high planning speed due to the existence of a gravitational field, but a path may not be found because of the extreme value at the position where the resultant force is zero. Meanwhile, if the obstacle is close to the target position, the repulsive force can cause the unmanned aerial vehicle to be unable to approach the target position, so that the flight path planning fails.
3) The tracks searched by the existing track planning technology are often more tortuous and have more redundant nodes, so that subsequent track smoothing processing is needed.
4) The existing track planning method is difficult to solve and low in efficiency when searching tracks in a three-dimensional map.
Disclosure of Invention
The invention aims to provide a three-dimensional track planning method based on an improved potential field RRT algorithm, which is characterized in that an artificial potential field concept is added into a node expansion process based on the RRT algorithm, an initial track is obtained through node expansion, then redundant nodes are deleted through a line-of-sight algorithm, the track is smoother and safer, the improved potential field RRT algorithm is finally obtained, and the algorithm is applied to a three-dimensional map to plan a three-dimensional track for an unmanned aerial vehicle.
The technical scheme for realizing the invention is as follows: a three-dimensional track planning method based on an improved potential field RRT algorithm is characterized in that in a three-dimensional environment, an unmanned plane is utilized to explore obstacles, a three-dimensional map is constructed, and after the three-dimensional map is built, track searching is carried out in the map, and the method comprises the following steps:
step 1, setting the number of sampling points Samples, a starting position and a target position, setting the starting position as a root node of a tree, and turning to step 2.
Step 2, generating a random point x by sampling random Searching the tree for x random Nearest node x nearest Generating new node x according to step rule rand And (3) switching to step 3.
Step 3, judging x rand Whether in the passable area, then judge x rand If the artificial potential field value is greater than a random value, then x is reserved when both conditions are yes rand And (4) switching to step 4. Otherwise discard x rand And returning to the step 2.
Step 4, connect x rand And x nearest Will x nearest Set to x rand Parent node x of (2) parent Calculate x parent X as parent node rand The track cost of (2) is set as the cost of the original track, and the track cost is from the starting position to x rand Is transferred to step 5.
Step 5, x rand As the center, r c To draw a circle for a radius, nodes are searched on a tree within the circle range, used as potential father nodes, and a potential father node set X is formed potential_parent For updating x rand Judging whether a parent node with the track cost smaller than the original track cost exists or not, and turning to the step 6.
Step 6, from X potential_parent Optionally selecting a potential parent node x potential_parent Will x potential_parent And x child Connected, x child ＝x rand The cost of this track is calculated. Judging whether the cost of the new track is smaller than that of the original track, judging whether the communication detection is passed or not, and deleting the original link when the two judging conditions are yesWiring x potential_parent Let x be rand Adding a new connection line, and proceeding to step 7. Otherwise, x potential_parent Cannot be used as a new parent node, and the process proceeds to step 7.
And 7, judging whether all potential father nodes are searched, if yes, turning to the step 8. Otherwise, return to step 6.
And 8, judging whether the total sampling points are equal to Samples, if so, backtracking from the target position to obtain an initial track node according to the relation of the father node, and turning to the step 9. Otherwise, return to step 2.
And 9, optimizing the initial track nodes by using a line-of-sight algorithm to obtain an optimized track, and finally outputting a final track.
Compared with the prior art, the invention has the remarkable advantages that:
(1) According to the invention, an artificial potential field value is added for the node, a gravitational field value is set to guide the expansion direction of the node, the speed of track planning is accelerated, and a repulsive field value is set to keep a safe distance between the track and an obstacle.
(2) The invention modifies the state information of the search node, applies the algorithm to the three-dimensional map, and can search out the three-dimensional track.
(3) After the initial track is searched, the sight line algorithm is applied to optimize the track, redundant nodes are abandoned, and the safe, smooth and practical track can be finally obtained.
Drawings
Fig. 1 is a flow chart of an improved potential field RRT algorithm of the method of the present invention.
Fig. 2 is a sampling result when the method of the present invention samples 750.
Fig. 3 is a sampling result when the method of the present invention samples 1500.
Fig. 4 is a track obtained by sampling according to the method of the invention.
Fig. 5 is the final track obtained by the method of the present invention through track optimization.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without creative efforts, are within the scope of the present invention based on the embodiments of the present invention.
In addition, the technical solutions of the embodiments of the present invention may be combined with each other, but it is necessary to base that the technical solutions can be implemented by those skilled in the art, and when the technical solutions are contradictory or cannot be implemented, the combination of the technical solutions should be considered to be absent, and not included in the scope of protection claimed in the present invention.
The following describes the specific embodiments, technical difficulties and inventions of the present invention in further detail in connection with the present design examples.
The invention takes RRT algorithm as the basis, adds the artificial potential field method concept into the node expansion process, sets a gravitational field for the target position, guides the expansion direction of the node, accelerates the searching speed of the algorithm, sets a repulsive field for the obstacle, keeps the safe distance between the track and the obstacle, obtains the initial track through node expansion, judges whether redundant nodes exist through the line-of-sight algorithm, smoothes and safer the track through deleting the redundant nodes, and finally obtains the improved potential field RRT algorithm.
As shown in fig. 1, the three-dimensional track planning method based on the improved potential field RRT algorithm of the present invention explores obstacles by using an unmanned aerial vehicle in a three-dimensional environment, constructs a three-dimensional map, and performs track search based on the improved potential field RRT algorithm in the three-dimensional map after the three-dimensional map is constructed, comprising the following steps:
step 1, setting the number of sampling points Samples, a starting position and a target position, and setting the starting position as a root node of a tree, wherein the steps are as follows:
step 1-1, setting the number of sampling points, the starting position and the target position of the track.
And step 1-2, setting the starting position of the track as the root node of the expansion tree.
And (2) switching to step 2.
Step 2, generating a random point x by sampling random Searching the tree for x random Nearest node x nearest Then generating new node x according to the step rule rand The method is characterized by comprising the following steps:
step 2-1, generating a random point x by sampling random 。
Step 2-2, searching the tree for the AND x random Nearest node x nearest 。
Step 2-3, then generating a new node x according to the step rule rand The specific step rule is as follows:
in the formula, |x random -x nearest And I is the modulus of the vector.
And (3) switching to step 3.
Step 3, judging x rand Whether in the passable area, then judging whether the artificial potential field value is larger than a random value, if both judging conditions are yes, retaining x rand And (4) switching to step 4. Otherwise discard x rand And returning to the step 2.
The method comprises the following steps:
step 3-1, judging x rand Whether or not in a passable area, i.e. determine x rand Whether or not in the range of the obstacle.
Because the unmanned aerial vehicle is simplified to be a point during track planning, the unmanned aerial vehicle possibly collides when flying along the planned track, so that the obstacle in the map is expanded, namely the boundary of the obstacle is enlarged, and a safety boundary is additionally arranged outside the physical boundary of the obstacle. When x is rand Within the safety boundary, then in an unvented region. When x is rand Outside the safety boundary, the vehicle is in a passable area.
Step 3-2, judging whether the artificial potential field value is larger than a random value, and calculating x rand Is manually operated by the force field value and the repulsive force field valueThe potential field value calculation formula is as follows:
F a ＝(F r ) α ·(F g ) β
wherein F is r To repulsive force field value, F g For gravitational field value, α, β are the weights of repulsive force field value and gravitational field value, respectively.
When the repulsive field value is set for the node, all the obstacles need to be traversed, and when the distance between the node and the center of the obstacle is smaller than a limiting value, the obstacle can generate repulsive force to the node, and the limiting value is the radius R of the obstacle o And an extension radius R l A kind of electronic device. Set F r An initial value of 1, F is set when a repulsive force is generated on the node by finding an obstacle ri ＝F r The repulsive force field value is calculated, and the repulsive force field value calculation formula is shown as follows:
wherein R is d And when all the obstacles are calculated, the repulsive force field value of the node is obtained for the distance between the node and the center of the obstacle.
When the gravitational field value is set for the node, the initial node and the target node are connected to obtain a straight line. Then calculate the distance D of the node from the straight line l . Set F g The initial value of (1) when D l F when the value is smaller than the preset value g Is unchanged. When D is l When the value is larger than the preset value, F is set gi ＝F g The gravitational field value is calculated, and the gravitational field value calculation formula is as follows:
step 4, connect x rand And x nearest Will x nearest Set to x rand Parent node x of (2) parent Calculate x parent X as parent node rand The track cost of (2) is set as the cost of the original track, and the track cost is from the starting position to x rand Is specified as follows.
Step 4-1, join x rand And x nearest Will x nearest Set to x rand Parent node x of (2) parent 。
Step 4-2, calculating x parent X as parent node rand The track cost of (1) is from the start position to x rand Is a flying distance of (c).
Go to step 5.
Step 5, x rand As the center, r c To draw a circle for a radius, nodes are searched on a tree within the circle range, used as potential father nodes, and a potential father node set X is formed potential_parent For updating x rand Judging whether a parent node with the track cost smaller than the original track cost exists or not, and turning to the step 6.
Step 6, from X potential_parent Optionally selecting a potential parent node x potential_parent Will x potential_parent And x child Connected, x child ＝x rand The cost of this track is calculated. Judging whether the cost of the new track is smaller than that of the original track, judging whether the communication detection is passed or not, deleting the original connecting line when the two judging conditions are yes, and obtaining x potential_parent Let x be rand Adding a new connection line, and proceeding to step 7. Otherwise, x potential_parent Cannot be used as a new parent node, and the process proceeds to step 7.
The method comprises the following steps:
step 6-1, from X potential_parent Selecting a potential parent node x potential_parent First, x is not detected by communication potential_parent And x child (i.e. x rand ) In connection, the cost of this track is calculated.
Step 6-2, judging whether the cost of the new track is smaller than the cost of the original track, then judging whether the communication detection is passed or not, deleting the original connecting line when the two judging conditions are yes, and obtaining x potential_parent Let x be rand Adding a new connection line. Otherwise, x potential_parent And cannot act as a new parent node.
And 7, judging whether all potential father nodes are searched, if yes, turning to the step 8. Otherwise, return to step 6.
And 8, judging whether the total sampling points are equal to Samples, if so, backtracking from the target position to obtain an initial track node according to the relation of the father node, and turning to the step 9. Otherwise, return to step 2.
And 9, optimizing the initial track nodes by using a line-of-sight algorithm to obtain an optimized track, and finally outputting a final track.
And 9-1, taking the initial track node as an input.
And 9-2, circularly judging whether an obstacle exists between the two interval nodes in the initial track nodes by using a line-of-sight algorithm, deleting redundant nodes between the two points if the obstacle exists, and directly connecting the two points, otherwise, keeping unchanged. The specific steps of the line-of-sight algorithm are as follows:
step A: in a three-dimensional map, two points are connected by a straight line.
And (B) step (B): and taking points on the straight line according to the sequence of the intervals of the points, judging whether the taken points are in the range of the obstacle, if all the points are out of the range of the obstacle, the straight line is not intersected with the obstacle and is visible, otherwise, the straight line is intersected with the obstacle and is invisible.
And 9-3, when all the nodes are judged, obtaining an optimized track, and finally outputting a final track.
The invention is illustrated below by way of an example. In the three-dimensional map simulation experiment, sampling points are set to be sampling=1500, the initial position is (0.7 km,0.3km,0.5 km), and the target position is (9 km,8km,3.7 km). The starting position is set as the root node, and sampling is started. When 750 times of sampling are performed, the sampling result is shown in fig. 2, when 1500 times of sampling are performed, the sampling result is shown in fig. 3, and the graph shows that the sampled nodes are concentrated near the connection line of the starting node and the target node, and the farther the nodes are from the line, the fewer the nodes are, so that the action of a gravitational field is reflected. After the sampling is completed, the obtained sampling track is shown in fig. 4, the number of track nodes is 12, and the track cost is 13.86km. The final track obtained through track optimization is shown in fig. 5, the number of track nodes is 4, the track cost is 12.67km, and the effectiveness of the track optimization is proved. At the same time, as can be seen from fig. 5, the track can be kept at a safe distance from the obstacle. Simulation analysis shows that the improved potential field RRT algorithm designed by the invention can effectively solve the unmanned aerial vehicle track planning problem in the three-dimensional map.
Claims (4)
1. The three-dimensional track planning method based on the improved potential field RRT algorithm is characterized in that in a three-dimensional environment, an unmanned aerial vehicle is utilized to explore obstacles, a three-dimensional map is constructed, and after the three-dimensional map is built, track searching is carried out in the map, and the method comprises the following steps:
step 1, setting the number of sampling points Samples, a starting position and a target position, setting the starting position as a root node of a tree, and turning to step 2;
step 2, generating a random point x by sampling random Searching the tree for x random Nearest node x nearest Generating new node x according to step rule rand Turning to step 3;
step 3, judging x rand Whether in the passable area, then judge x rand If the artificial potential field value is greater than a random value, then x is reserved when both conditions are yes rand Turning to step 4; otherwise discard x rand Returning to the step 2; the method comprises the following steps:
step 3-1, judging x rand Whether or not in a passable area, i.e. determine x rand Whether or not within the range of the obstacle: expanding the boundary of the obstacle, adding a safety boundary outside the physical boundary of the obstacle, when x rand When the safety boundary is in the safety boundary, the safety boundary is in an unvented area; when x is rand When the safety boundary is out, the safety boundary is positioned in a passable area;
step 3-2, judging whether the artificial potential field value is larger than a random value, and calculating x rand Is manually operated by the force field value and the repulsive force field valuePotential field value F a The calculation formula is as follows:
F a ＝(F r ) α ·(F g ) β
wherein F is r To repulsive force field value, F g The values of the gravitational field are respectively the weights of the repulsive force field value and the gravitational field value;
when the repulsive field value is set for the node, all the obstacles need to be traversed, and when the distance between the node and the center of the obstacle is smaller than a limiting value, the obstacle can generate repulsive force to the node, and the limiting value is the radius R of the obstacle o And an extension radius R l And (2) a sum of (2); set F r An initial value of 1, F is set when a repulsive force is generated on the node by finding an obstacle ri ＝F r The repulsive force field value is calculated, and the repulsive force field value calculation formula is shown as follows:
wherein R is d When all the barriers are calculated, a repulsive force field value of the node is obtained for the distance between the node and the center of the barrier;
when a gravitational field value is set for a node, connecting a starting node with a target node to obtain a straight line; then calculate the distance D of the node from the straight line l The method comprises the steps of carrying out a first treatment on the surface of the Set F g The initial value of (1) when D l F when the value is smaller than the preset value g Unchanged; when D is l When the value is larger than the preset value, F is set gi ＝F g The gravitational field value is calculated, and the gravitational field value calculation formula is as follows:
step 3-3, when both judging conditions are yes, reserving x rand Turning to step 4; otherwise discard x rand Returning to the step 2;
step 4, connect x rand And x nearest Will x nearest Set to x rand Parent node x of (2) parent Calculate x parent X as parent node rand The track cost of (2) is set as the cost of the original track, and the track cost is from the starting position to x rand Is transferred to step 5;
step 5, x rand As the center, r c To draw a circle for a radius, nodes are searched on a tree within the circle range, used as potential father nodes, and a potential father node set X is formed potential_parent For updating x rand Judging whether a parent node with the track cost smaller than the original track cost exists or not, and switching to the step 6;
step 6, from X potential_parent Optionally selecting a potential parent node x potential_parent Will x potential_parent And x child Connected, x child ＝x rand Calculating the cost of the track; judging whether the cost of the new track is smaller than that of the original track, judging whether the communication detection is passed or not, deleting the original connecting line when the two judging conditions are yes, and obtaining x potential_parent Let x be rand Adding a new connecting wire to the parent node of the node (B), and turning to the step 7; otherwise, x potential_parent Step 7 is carried out without being used as a new father node;
step 7, judging whether all potential father nodes are searched, if yes, turning to step 8; otherwise, returning to the step 6;
step 8, judging whether the total sampling points are equal to Samples, if so, backtracking from the target position to obtain an initial track node according to the father node relation, and turning to step 9; otherwise, returning to the step 2;
and 9, optimizing the initial track nodes by using a line-of-sight algorithm to obtain an optimized track, and finally outputting a final track.
2. The three-dimensional track planning method based on the improved potential field RRT algorithm according to claim 1, wherein the step rule in step 2 is as follows:
in the formula, |x random -x nearest And I is the modulus of the vector.
3. The three-dimensional track planning method based on the improved potential field RRT algorithm according to claim 1, wherein in step 9, the line-of-sight algorithm is used to optimize the initial track nodes to obtain an optimized track, and the final track is finally output, which is specifically as follows:
step 9-1, taking a group of track nodes as input;
9-2, in a group of track nodes, circularly judging whether an obstacle exists between two interval nodes by using a line-of-sight algorithm, if no obstacle exists, deleting redundant nodes between the two points, directly connecting the two points, otherwise, keeping unchanged;
and 9-3, when all the nodes are judged, obtaining an optimized track, and outputting a final track.
4. A three-dimensional track planning method based on an improved potential field RRT algorithm according to claim 3, characterized in that the line-of-sight algorithm comprises the following specific steps:
step A: in the three-dimensional map, connecting two coordinate points to be judged by using straight lines;
and (B) step (B): taking points on the straight line according to a certain interval sequence, judging whether the taken points are in the range of the obstacle, if all the points are out of the range of the obstacle, the straight line is not intersected with the obstacle, and the two points are visible; otherwise, the straight line intersects the obstacle, and the two points are not visible.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111584969.4A CN114415718B (en) | 2021-12-22 | 2021-12-22 | Three-dimensional track planning method based on improved potential field RRT algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111584969.4A CN114415718B (en) | 2021-12-22 | 2021-12-22 | Three-dimensional track planning method based on improved potential field RRT algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114415718A CN114415718A (en) | 2022-04-29 |
| CN114415718B true CN114415718B (en) | 2023-10-13 |
Family
ID=81268333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111584969.4A Active CN114415718B (en) | 2021-12-22 | 2021-12-22 | Three-dimensional track planning method based on improved potential field RRT algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114415718B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106990777A (en) * | 2017-03-10 | 2017-07-28 | 江苏物联网研究发展中心 | Robot local paths planning method |
| CN108983780A (en) * | 2018-07-24 | 2018-12-11 | 武汉理工大学 | One kind is based on improvement RRT*The method for planning path for mobile robot of algorithm |
| CN113534838A (en) * | 2021-07-15 | 2021-10-22 | 西北工业大学 | Improved unmanned aerial vehicle track planning method based on artificial potential field method |
| WO2021242215A1 (en) * | 2020-05-26 | 2021-12-02 | Edda Technology, Inc. | A robot path planning method with static and dynamic collision avoidance in an uncertain environment |
| CN113741423A (en) * | 2021-08-03 | 2021-12-03 | 上海电机学院 | AGV dynamic obstacle avoidance method based on artificial potential field method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11231715B2 (en) * | 2018-05-22 | 2022-01-25 | King Fahd University Of Petroleum And Minerals | Method and system for controlling a vehicle |
-
2021
- 2021-12-22 CN CN202111584969.4A patent/CN114415718B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106990777A (en) * | 2017-03-10 | 2017-07-28 | 江苏物联网研究发展中心 | Robot local paths planning method |
| CN108983780A (en) * | 2018-07-24 | 2018-12-11 | 武汉理工大学 | One kind is based on improvement RRT*The method for planning path for mobile robot of algorithm |
| WO2021242215A1 (en) * | 2020-05-26 | 2021-12-02 | Edda Technology, Inc. | A robot path planning method with static and dynamic collision avoidance in an uncertain environment |
| CN113534838A (en) * | 2021-07-15 | 2021-10-22 | 西北工业大学 | Improved unmanned aerial vehicle track planning method based on artificial potential field method |
| CN113741423A (en) * | 2021-08-03 | 2021-12-03 | 上海电机学院 | AGV dynamic obstacle avoidance method based on artificial potential field method |
Non-Patent Citations (1)
| Title |
|---|
| 动态环境下基于人工势场引导的RRT路径规划算法;司徒华杰;计算机应用研究;第38卷(第3期);714-717 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114415718A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109764886A (en) | A kind of paths planning method | |
| CN113359718B (en) | Method and equipment for fusing global path planning and local path planning of mobile robot | |
| CN111753425B (en) | Simulation method, simulation device, electronic equipment and storage medium | |
| CN108827335B (en) | Shortest path planning method based on one-way search model | |
| CN106444740A (en) | MB-RRT-based unmanned aerial vehicle two-dimensional track planning method | |
| CN108444490B (en) | Robot path planning method based on depth fusion of visible view and A-x algorithm | |
| CN112987799B (en) | Unmanned aerial vehicle path planning method based on improved RRT algorithm | |
| CN111753424B (en) | Simulation method, simulation device, electronic equipment and storage medium | |
| WO2023029188A1 (en) | Path planning method and apparatus, and device and storage medium | |
| CN112286202B (en) | Mobile robot path planning method for non-uniform sampling FMT | |
| CN112650256A (en) | Improved bidirectional RRT robot path planning method | |
| CN114115362B (en) | Unmanned aerial vehicle track planning method based on bidirectional APF-RRT algorithm | |
| CN112344938B (en) | Space environment path generation and planning method based on pointing and potential field parameters | |
| Gu et al. | An improved RRT algorithm based on prior AIS information and DP compression for ship path planning | |
| CN115562272A (en) | Planning method and device for robot traveling path | |
| CN113325389A (en) | Unmanned vehicle laser radar positioning method, system and storage medium | |
| CN115291597A (en) | Path planning method and device based on bidirectional hybrid A-algorithm and terminal | |
| CN114415718B (en) | Three-dimensional track planning method based on improved potential field RRT algorithm | |
| Shang et al. | Research on path planning of autonomous vehicle based on RRT algorithm of Q-learning and obstacle distribution | |
| CN113239138A (en) | Map matching method, map matching device, computer equipment and storage medium | |
| CN116817947B (en) | Random time path planning method based on variable step length mechanism | |
| JP6623130B2 (en) | ROUTE INFORMATION GENERATION DEVICE, ROUTE COUPLING DEVICE, METHOD, AND PROGRAM | |
| US20230099772A1 (en) | Lane search for self-driving vehicles | |
| CN111483465A (en) | MPP expanding method and device, electronic equipment and storage medium | |
| CN114509085B (en) | Quick path searching method combining grid and topological map |
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 |