CN113885567B - Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search - Google Patents
Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search Download PDFInfo
- Publication number
- CN113885567B CN113885567B CN202111235644.5A CN202111235644A CN113885567B CN 113885567 B CN113885567 B CN 113885567B CN 202111235644 A CN202111235644 A CN 202111235644A CN 113885567 B CN113885567 B CN 113885567B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- node
- map
- path
- 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
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 5
- 238000005070 sampling Methods 0.000 claims description 7
- 238000012795 verification Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000009191 jumping Effects 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims 1
- 230000015572 biosynthetic process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012163 sequencing technique 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
- G05D1/104—Simultaneous control of position or course in three dimensions specially adapted for aircraft involving a plurality of aircrafts, e.g. formation flying
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
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 provides a path planning method of multiple unmanned aerial vehicles based on conflict search, which not only ensures that the searched path accords with the flight characteristics of the unmanned aerial vehicle, but also greatly reduces the number of expansion nodes in the path planning process and improves the overall planning efficiency. Comprising the following steps: preprocessing a point cloud map acquired by an unmanned aerial vehicle into a voxel grid map; performing low-level search on the voxel grid map to obtain a path of a single unmanned aerial vehicle; and traversing the constraint tree according to the paths of the single unmanned aerial vehicle to perform conflict detection on the trajectories of all unmanned aerial vehicles, adding constraint on the unmanned aerial vehicle if the conflict exists, performing constrained path planning, and if the conflict does not exist, successfully planning.
Description
Technical Field
The invention belongs to the technical field of robots, and relates to a collaborative path planning method of multiple unmanned aerial vehicles based on conflict searching.
Background
Multi-robot systems have wide application in monitoring, searching and rescuing and warehouse automation applications. Compared with the single robot path planning problem, the multi-robot path planning problem has several characteristics:
1) There are more constraints, such as the need to maintain a certain formation, or the need to satisfy a sequencing constraint of movements, i.e. the completion of a movement of a certain robot as a condition for another robot to start moving;
2) The problem of planning conflict exists in a robot team, namely, two robots can arrive at the same position at the same moment in the process of executing a planning path, and collision is caused.
Multiple robot path planning algorithms can be divided into two broad categories, centralized and distributed. The centralized type is to consider multiple robots as a whole, and integrate all robots into one multi-degree-of-freedom space. Planning and searching. And distributed is a separate path planning for each robot. And then, the path of the single robot is coordinated and modified through a coordination and scheduling method to solve the conflict problem.
The path planning algorithms now directed to multiple drones are mostly distributed. For the formation problem of multiple unmanned aerial vehicles, the formation problem of unmanned aerial vehicles is mainly realized by a distributed path planning algorithm, a complete decentralization method, namely, only planning a 'leading' robot and other robots only 'following a leading' while avoiding barriers. In the centralized planning algorithm, sharon et al in 2015 propose a method for multi-robot cooperation optimal path planning based on conflict, and the problem of path conflict among multiple robots is solved by using a constraint tree.
For the existing multi-unmanned plane path planning algorithm, most of the multi-unmanned plane path planning algorithm is distributed, solutions can be guaranteed, but the solutions are not optimal, and flight safety in a space with complex narrow and high conflict risks cannot be guaranteed. The method for planning the optimal path by the cooperation of multiple robots based on conflict, which is proposed by Sharon and the like, can well solve the problem of track conflict of the multiple robots in path planning, but cannot be completely applied to unmanned aerial vehicles in practical application. The algorithm can only solve the problem of collision of multiple robots on a two-dimensional plane, and the motion environment of the unmanned aerial vehicle is a three-dimensional space. And the actual model of the robot is not considered, so that no collision of the track is difficult to achieve in practical application.
Disclosure of Invention
The invention provides a path planning method of multiple unmanned aerial vehicles based on conflict search, which not only ensures that the searched path accords with the flight characteristics of the unmanned aerial vehicle, but also greatly reduces the number of expansion nodes in the path planning process and improves the overall planning efficiency.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
a multi-unmanned aerial vehicle collaborative path planning method based on conflict search comprises the following steps:
preprocessing a point cloud map acquired by an unmanned aerial vehicle into a voxel grid map;
performing low-level search on the voxel grid map to obtain a path of a single unmanned aerial vehicle;
and traversing the constraint tree according to the paths of the single unmanned aerial vehicle to perform conflict detection on the trajectories of all unmanned aerial vehicles, adding constraint on the unmanned aerial vehicle if the conflict exists, performing constrained path planning, and if the conflict does not exist, successfully planning.
The invention has the beneficial effects that:
according to the invention, the constraint tree is constructed to constrain the collision organism so as to obtain a safe flight sequence, so that the flight safety of the unmanned aerial vehicle group in a complex narrow and high-collision risk space is greatly improved; meanwhile, the hybrid Astar algorithm is combined in the low-level searching process, and through introducing the unmanned aerial vehicle kinematics and dynamics model, the searched path is more in line with the flight characteristics of the unmanned aerial vehicle, the number of expansion nodes in the path planning process is greatly reduced, and the overall planning efficiency is improved.
Drawings
FIG. 1 is a flow chart of a method for path planning for multiple unmanned aerial vehicles based on conflict searching in the present invention;
FIG. 2 is a flowchart of cloud map preprocessing as voxel grid maps in this embodiment;
fig. 3 is a path flow diagram of a single unmanned aerial vehicle obtained by searching a path plan in the present embodiment.
Detailed Description
The invention will now be described in detail by way of example with reference to the accompanying drawings.
As shown in fig. 1, the collaborative path planning method of the multiple unmanned aerial vehicle based on conflict search in this embodiment specifically includes the following steps:
preprocessing a point cloud map acquired by an unmanned aerial vehicle into a voxel grid map; in this embodiment, as shown in fig. 2, specifically:
1.1, inputting environment information of the point cloud map to obtain point cloud data; wherein the obstacle information of the point cloud map is contained in three-dimensional point cloud data, and three-dimensional coordinate values (x, y, z) of the point cloud data under a world coordinate system represent that an obstacle exists at the position;
1.2, calculating three-dimensional grid coordinates of the point cloud data under the voxel grid map according to the point cloud data in the step 1.1; the method comprises the following steps:
firstly, setting a sampling space by taking the size of a physical map as a reference, and carrying out segmentation sampling on the sampling space according to a preset resolution to form a three-dimensional dense voxel grid map, wherein the resolution represents the fineness of the map. The world map used in this example has a size of 50×50×5m and a resolution of 0.1, and the generated grid map contains 125,000 voxels.
Secondly, converting point cloud data of the voxel grid graph from physical coordinate values to grid coordinate values; taking x-axis coordinates as an example:
p index ＝[p real ÷λ]
wherein p is index And p real Grid coordinate values and physical coordinate values for data points, respectively, lambda being a preset resolution, brackets "[]"to round operator, this embodiment employs to round down. In practice, the rounding operation in the conversion process results in two adjacent, closely spaced data points having the same grid coordinate values, but can be adjusted by modifying the resolution.
1.3 setting and storing occupation information of each voxel according to the voxel grid map and grid coordinates of the point cloud data; the method comprises the following steps:
creating an occupancy queue to store occupancy information in said voxel grid map, the queue length of which is equal to the total number of voxel grids, wherein all element values are initialized to 0 to represent non-obstructions; when the obstacle information is stored, cloud point data is converted into grid coordinates from physical coordinates, and then the queue index value is calculated according to the following calculation formula:
x index *Y size *Z size +y index *Z size +z index
wherein x is index 、y index 、z index Representing the grid coordinates of the point, Y size 、Z size Representing the maximum grid number of the map on the Y axis and the Z axis; the queue index value is the unique representation of the three-dimensional data point in the queue, and the element is set to be 1 to represent that the point is an obstacle; when the voxel occupation condition needs to be judged, only the elements at the index of the point queue in the occupation queue need to be queriedAnd if not, the number is 1.
1.4, expanding the map according to the voxel grid map containing the occupation information obtained in the step 1.3; in specific implementation, the purpose of the map expansion is to approximate the physical model of the unmanned aerial vehicle as a particle, so that subsequent path planning work is facilitated, that is, conversion from a Working Space (Working Space) to a configuration Space (Configuration Space) of the unmanned aerial vehicle is completed. In this embodiment, expansion processing is performed on the map obstacle according to the volume parameter of the unmanned aerial vehicle. The method comprises the following steps:
approximating the unmanned plane as a sphere with a radius of n, and expanding each set occupied voxel to a surrounding area by taking the expansion radius n as a limit value in the voxel grid map obtained in the step 1.3 to obtain n 3 And a unit for setting all expanded nodes as barriers in the occupation queue to complete map expansion.
Step two, performing low-level search on the voxel grid map obtained in the step one to obtain a path of a single unmanned aerial vehicle; in the embodiment, a hybrid Astar algorithm is adopted to conduct path planning search to obtain a path of a single unmanned aerial vehicle; as shown in fig. 3, specifically:
2.1 calculating a cost f value of a starting point of the unmanned aerial vehicle through a Heuristic function, and adding the starting point of the unmanned aerial vehicle into an Open list;
2.2, taking the node with the minimum f value in the Openlist as a father node, and putting the father node into a Close list;
2.3 judging whether the current node reaches the vicinity of the end point, if so, jumping out of the cycle, otherwise, continuing the cycle, and entering the next step;
2.4, using a father node to despread the child node under the constraint of power and kinematics, judging whether the child node is in a Close list, if not, judging whether the node is expanded, if so, updating the node if the f value of a new node is smaller than the f value of the new node before, putting the node into an Open list, and if not, directly putting the node into the Open list; returning to the step 2.3 after the child node is expanded;
and thirdly, according to the track of the single unmanned aerial vehicle obtained in the second step, traversing the constraint tree to perform conflict detection on the tracks of all unmanned aerial vehicles, adding constraint on the unmanned aerial vehicle if the conflict exists, performing constrained path planning, and if the conflict does not exist, successfully planning. The method comprises the following steps:
3.1 constructing a constraint tree, wherein each node N of the constraint tree comprises:
a set of constraints (n.constraints), each of which belongs to a single unmanned aerial vehicle, the root node of the constraint tree being a set of empty constraints, child nodes of nodes in the constraint tree inheriting the constraints of parent nodes and adding a new constraint to a unmanned aerial vehicle;
one solution (n.solution): each unmanned aerial vehicle corresponds to one path, the path of the agent is consistent with the constraint of the path, and the path is obtained by carrying out path planning search by adopting a hybrid Astar algorithm;
total cost (n.cost): the total cost of the current solution is called the f-value of node N.
3.2 processing nodes in the constraint tree, wherein the processing process specifically comprises the following steps:
a) Given a constraint list of nodes N in the constraint tree, invoking the search for each drone a using hybrid Astar i Returning a shortest path to satisfy the node N and the agent a i All constraints related;
b) Respectively verifying the validity of the path to other unmanned aerial vehicles, and in the embodiment, verifying by iterating and matching the current positions of all unmanned aerial vehicles in all time steps;
c) If there are no two unmanned aerial vehicles located at the same time, the constraint tree node N is set as a target node, and returns a current solution (N.solution) containing the path; conversely, if two or more drones a are found during the verification process i And a j There is a conflict c= (a) i ，a j V, t), stopping verification, and setting the node as a non-target node;
in the specific implementation, when the number k of unmanned aerial vehicles generating conflict is more than 2 in the verification process, the following method is adopted for processing: generating k sub-nodes, each adding a constraint for k+1 unmanned aerial vehicles, i.e. each sub-node only allows one unmanned aerial vehicle to occupy the collision vertex v at time t.
3.3 re-conducting the low-level hybrid Astar search as conflict drone a i Returning a shortest path to satisfy the node N and the agent a i All constraints related.
In summary, the above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (13)
1. A multi-unmanned aerial vehicle collaborative path planning method based on conflict search is characterized by comprising the following steps:
preprocessing a point cloud map acquired by an unmanned aerial vehicle into a voxel grid map;
performing low-level search on the voxel grid map to obtain a path of a single unmanned aerial vehicle;
according to the paths of the single unmanned aerial vehicle, traversing a constraint tree to perform conflict detection on the tracks of all unmanned aerial vehicles, adding constraint on the unmanned aerial vehicle if the conflict exists, performing constrained path planning, and if the conflict does not exist, successfully planning;
the path of the single unmanned aerial vehicle traverses the constraint tree to perform conflict detection on the tracks of all unmanned aerial vehicles, and specifically comprises the following steps: constructing a constraint tree, processing nodes in the constraint tree, and carrying out low-level hybrid Astar search again to return a shortest path for the conflict unmanned aerial vehicle so as to enable the conflict unmanned aerial vehicle to meet all constraints related to agents in the nodes; each node N of the constraint tree includes:
the processing method specifically comprises the following steps of:
a) Given a constraint list of nodes N in the constraint tree, invoking the search for each drone a using hybrid Astar i Returning a shortest path to satisfy the node N and the agent a i All constraints related;
b) Respectively verifying the validity of the path to other unmanned aerial vehicles;
c) If no two unmanned aerial vehicles are simultaneously located at the same position, the constraint tree node N is set as a target node, and a current solution containing the path is returned; if two or more unmanned aerial vehicles are found to have conflict in the verification process, stopping verification, and setting the node as a non-target node;
a set of constraints (n.constraints), each of which belongs to a single unmanned aerial vehicle, the root node of the constraint tree being a set of empty constraints, child nodes of nodes in the constraint tree inheriting the constraints of parent nodes and adding a new constraint to a unmanned aerial vehicle;
one solution (n.solution): each unmanned aerial vehicle corresponds to one path, the path of the agent is consistent with the constraint of the path, and the path is obtained by carrying out path planning search by adopting a hybrid Astar algorithm;
total cost (n.cost): the total cost of the current solution is called the f-value of node N.
2. The method for collaborative path planning for multiple unmanned aerial vehicles based on conflicting searches of claim 1, wherein the preprocessing is performed on a voxel grid map in the following manner: inputting the environment information of the point cloud map to obtain point cloud data; calculating three-dimensional grid coordinates under a voxel grid map according to the point cloud data; setting and storing occupation information of each voxel according to the voxel grid map and the three-dimensional grid coordinates; and carrying out map expansion according to the voxel grid map occupying the information.
3. A method of collaborative path planning for a multi-unmanned aerial vehicle based on a collision search according to claim 2, wherein the computing of three-dimensional grid coordinates under a voxel grid map is performed by:
firstly, setting a sampling space by taking the size of a physical map as a reference, carrying out segmentation sampling on the sampling space according to a preset resolution to form a three-dimensional dense voxel grid map, and secondly, converting point cloud data of the voxel grid map from physical coordinate values to grid coordinate values.
4. A method for collaborative path planning for multiple unmanned aerial vehicles based on conflicting searches as claimed in claim 3, wherein the resolution characterizes the fineness of the map when the sampling space is divided and sampled according to a preset resolution.
5. The method for collaborative path planning for multiple unmanned aerial vehicles based on conflicting searches of claim 3 or 4, wherein the conversion from physical coordinate values to grid coordinate values is specifically:
p index ＝[p real ÷λ]
wherein p is index And p real Grid coordinate values and physical coordinate values for data points, respectively, lambda being a preset resolution, brackets "[]"is a rounding operator.
6. The method for collaborative path planning for multiple unmanned aerial vehicles based on conflicting searches of claim 3 or 4, wherein the setting and storing occupancy information for each voxel is specifically:
creating an occupancy queue to store occupancy information in said voxel grid map, the queue length of which is equal to the total number of voxel grids, wherein all element values are initialized to 0 to represent non-obstructions; when the obstacle information is stored, cloud point data are converted into grid coordinates from physical coordinates, and then the queue index value of the cloud point data is calculated.
7. The method for collaborative path planning for multiple unmanned aerial vehicles based on collision search according to claim 6, wherein the calculation formula for calculating the queue index value is as follows:
x index *Y size *Z size +y index *Z size +z index
wherein x is index 、y index 、z index Representing the grid coordinates of the point, Y size 、Z size Representing the maximum grid number of the map on the Y axis and the Z axis; the queue index value is the only representation of a three-dimensional data point in the queue where the element is set to 1 to indicate that the point is a barrier.
8. The method for collaborative path planning for multiple unmanned aerial vehicles based on conflicting searches of claim 2, 3 or 4, wherein the expanding of the map according to the voxel grid map of occupancy information employs expanding of map obstacles according to volumetric parameters of the unmanned aerial vehicle.
9. The method for planning a collaborative path for multiple unmanned aerial vehicles based on conflict search according to claim 8, wherein the expanding the map obstacle according to the volume parameter of the unmanned aerial vehicle is specifically: approximating the unmanned plane as a sphere with a radius of n, and expanding each set occupied voxel to a surrounding area by taking the expansion radius n as a limit value in the voxel grid map to obtain n 3 And a unit for setting all expanded nodes as barriers in the occupation queue to complete map expansion.
10. The collaborative path planning method for multiple unmanned aerial vehicles based on conflict searching according to claim 1, 2, 3 or 4, wherein the path planning searching is performed by adopting a hybrid Astar algorithm to obtain the path of a single unmanned aerial vehicle.
11. The collaborative path planning method of multiple unmanned aerial vehicles based on conflict search according to claim 10, wherein the path planning search by adopting the hybrid Astar algorithm is performed to obtain the path of a single unmanned aerial vehicle, and the specific steps are as follows:
2.1 calculating a cost f value of a starting point of the unmanned aerial vehicle through a Heuristic function, and adding the starting point of the unmanned aerial vehicle into an Open list;
2.2, taking the node with the minimum f value in the Openlist as a father node, and putting the father node into a Close list;
2.3 judging whether the current node reaches the vicinity of the end point, if so, jumping out of the cycle, otherwise, continuing the cycle, and entering the next step;
2.4, using a father node to despread the child node under the constraint of power and kinematics, judging whether the child node is in a Close list, if not, judging whether the node is expanded, if so, updating the node if the f value of a new node is smaller than the f value of the new node before, putting the node into an Open list, and if not, directly putting the node into the Open list; and (3) returning to the step (2.3) after the child nodes are expanded.
12. A method of collaborative path planning for multiple drones based on conflicting searches according to claim 11 wherein the paths are validated separately for other drones by iterating through all time steps and matching the current locations of all drones.
13. A method for collaborative path planning for multiple drones based on conflicting searches according to claim 11 or 12, wherein when the number of conflicting drones k >2 is generated during the verification process, the following is adopted: generating k sub-nodes, each adding a constraint for k+1 unmanned aerial vehicles, i.e. each sub-node only allows one unmanned aerial vehicle to occupy the collision vertex v at time t.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111235644.5A CN113885567B (en) | 2021-10-22 | 2021-10-22 | Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111235644.5A CN113885567B (en) | 2021-10-22 | 2021-10-22 | Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113885567A CN113885567A (en) | 2022-01-04 |
| CN113885567B true CN113885567B (en) | 2023-08-04 |
Family
ID=79013433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111235644.5A Active CN113885567B (en) | 2021-10-22 | 2021-10-22 | Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113885567B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115174582B (en) * | 2022-09-06 | 2022-11-18 | 中国中金财富证券有限公司 | Data scheduling method and related device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103557867A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工程大学 | Three-dimensional multi-UAV coordinated path planning method based on sparse A-star search (SAS) |
| CN106067193A (en) * | 2016-06-06 | 2016-11-02 | 中国人民解放军信息工程大学 | A kind of voxelization method of cloud data and voxel block method of cutting out |
| CN109115226A (en) * | 2018-09-01 | 2019-01-01 | 哈尔滨工程大学 | The paths planning method of multirobot conflict avoidance based on jump point search |
| CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
| CN111880559A (en) * | 2020-07-13 | 2020-11-03 | 南京航空航天大学 | Optimization method for joint problem of task allocation and path planning of multiple unmanned aerial vehicles |
| CN112166457A (en) * | 2019-08-29 | 2021-01-01 | 深圳市大疆创新科技有限公司 | Point cloud segmentation method and system and movable platform |
| CN113345018A (en) * | 2021-05-31 | 2021-09-03 | 湖南大学 | Laser monocular vision fusion positioning mapping method in dynamic scene |
-
2021
- 2021-10-22 CN CN202111235644.5A patent/CN113885567B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103557867A (en) * | 2013-10-09 | 2014-02-05 | 哈尔滨工程大学 | Three-dimensional multi-UAV coordinated path planning method based on sparse A-star search (SAS) |
| CN106067193A (en) * | 2016-06-06 | 2016-11-02 | 中国人民解放军信息工程大学 | A kind of voxelization method of cloud data and voxel block method of cutting out |
| CN109115226A (en) * | 2018-09-01 | 2019-01-01 | 哈尔滨工程大学 | The paths planning method of multirobot conflict avoidance based on jump point search |
| CN109634304A (en) * | 2018-12-13 | 2019-04-16 | 中国科学院自动化研究所南京人工智能芯片创新研究院 | Unmanned plane during flying paths planning method, device and storage medium |
| CN112166457A (en) * | 2019-08-29 | 2021-01-01 | 深圳市大疆创新科技有限公司 | Point cloud segmentation method and system and movable platform |
| CN111880559A (en) * | 2020-07-13 | 2020-11-03 | 南京航空航天大学 | Optimization method for joint problem of task allocation and path planning of multiple unmanned aerial vehicles |
| CN113345018A (en) * | 2021-05-31 | 2021-09-03 | 湖南大学 | Laser monocular vision fusion positioning mapping method in dynamic scene |
Non-Patent Citations (1)
| Title |
|---|
| 结合跳点引导的无人机随机搜索避撞决策方法;李安醍 等;《航空学报》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113885567A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Qin et al. | Autonomous exploration and mapping system using heterogeneous UAVs and UGVs in GPS-denied environments | |
| Fu et al. | An improved A* algorithm for the industrial robot path planning with high success rate and short length | |
| CN108958285B (en) | Efficient multi-unmanned aerial vehicle collaborative track planning method based on decomposition idea | |
| Alejo et al. | Collision-free 4D trajectory planning in unmanned aerial vehicles for assembly and structure construction | |
| US20170219353A1 (en) | Method and system for determining a path of an object for moving from a starting state to an end state set avoiding one or more obstacles | |
| CN109657868A (en) | A kind of probabilistic programming recognition methods of task sequential logic constraint | |
| CN111811511A (en) | Unmanned aerial vehicle cluster real-time track generation method based on dimension reduction decoupling mechanism | |
| Zhao et al. | A path planning method based on multi-objective cauchy mutation cat swarm optimization algorithm for navigation system of intelligent patrol car | |
| Respall et al. | Fast sampling-based next-best-view exploration algorithm for a MAV | |
| CN113253744B (en) | Multi-robot collaborative trajectory planning method and device, electronic equipment and storage medium | |
| Vashisth et al. | Existing path planning techniques in unmanned aerial vehicles (UAVs): A systematic review | |
| CN113885567B (en) | Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search | |
| Coenen et al. | Motion planning for mobile robots—A guide | |
| Ju et al. | A hybrid systems-based hierarchical control architecture for heterogeneous field robot teams | |
| Rocha et al. | Plannie: A benchmark framework for autonomous robots path planning algorithms integrated to simulated and real environments | |
| BAYGIN et al. | PSO based path planning approach for multi service robots in dynamic environments | |
| Yang et al. | Learning graph-enhanced commander-executor for multi-agent navigation | |
| CN116858253A (en) | Lightweight predictive navigation method and system suitable for indoor environment | |
| CN115933637A (en) | Path planning method and device for substation equipment inspection robot and storage medium | |
| CN111596668B (en) | Mobile robot anthropomorphic path planning method based on reverse reinforcement learning | |
| Taha et al. | Optimal 3D path planning for the delivery quadcopters operating in a city airspace | |
| Chu et al. | Track planning of multi-rotor unmanned aerial vehicle in the complex environment space | |
| Guo et al. | A Survey of Trajectory Planning Methods for Autonomous Driving—Part I: Unstructured Scenarios | |
| Zhang et al. | FGIP: A Frontier-Guided Informative Planner for UAV Exploration and Reconstruction | |
| Yuan et al. | Development of rule-based agents for autonomous parking systems by association rules mining |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Song Wenjie Inventor after: Zeng Linzhi Inventor after: Feng Siyuan Inventor after: Qian Yizhao Inventor after: Liu Jining Inventor before: Zeng Linzhi Inventor before: Feng Siyuan Inventor before: Song Wenjie Inventor before: Qian Yizhao Inventor before: Liu Jining |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |