CN106933246B - Multi-unmanned aerial vehicle complex task planning method - Google Patents
Multi-unmanned aerial vehicle complex task planning method Download PDFInfo
- Publication number
- CN106933246B CN106933246B CN201710195712.7A CN201710195712A CN106933246B CN 106933246 B CN106933246 B CN 106933246B CN 201710195712 A CN201710195712 A CN 201710195712A CN 106933246 B CN106933246 B CN 106933246B
- Authority
- CN
- China
- Prior art keywords
- behavior
- task
- flight
- library
- decomposition
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000006399 behavior Effects 0.000 claims abstract description 83
- 230000024703 flight behavior Effects 0.000 claims abstract description 41
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 29
- 230000008569 process Effects 0.000 claims abstract description 15
- 230000015572 biosynthetic process Effects 0.000 claims description 17
- 125000004122 cyclic group Chemical group 0.000 claims description 5
- 238000002898 library design Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 2
- 238000005755 formation reaction Methods 0.000 description 14
- 239000000575 pesticide Substances 0.000 description 9
- 238000005507 spraying Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000000875 corresponding effect Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 4
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Images
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
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)
- Traffic Control Systems (AREA)
Abstract
A complex task planning method for multiple unmanned aerial vehicles relates to an unmanned aerial vehicle. The method comprises a flight task decomposition flow, a flight behavior library design flow and an XML file compiling flow; the flight task decomposition flow is to perform behavior tree decomposition on multiple executed tasks and then perform behavior tree decomposition on the obtained single task; the flight behavior library design flow is to design a basic behavior library and a custom behavior library aiming at the flight behavior required in a single task; the XML file compiling flow is compiled by using a custom XML format language aiming at the behavior tree knots obtained by decomposition. The method can help a user to plan the whole task process, carries out task decomposition according to task levels, carries out task execution according to actual conditions, solves the practical problem of complex tasks of multiple unmanned aerial vehicles, and has the advantages of simple and convenient principle, flexible planning, strong practicability, good execution effect and the like.
Description
Technical Field
The invention relates to an unmanned aerial vehicle, in particular to a complex task planning method for multiple unmanned aerial vehicles.
Background
With the popularization of unmanned aerial vehicles and the rapid development of related technologies, a task planning system as the top layer is a prerequisite for ensuring success or failure of task execution of the unmanned aerial vehicles, and is an important means for flexibly configuring and optimizing the resources of the whole unmanned aerial vehicle system. Under the existing task premise, a plan is required to be made, and simultaneously, according to the resource quantity, the task type, the initial state and the constraint condition, a corresponding planning method is adopted to decompose the task into a series of behavior sequences, and then corresponding actions are executed through judging conditions, so that the purpose of completing the task is achieved. A task is generally composed of different behaviors through complex time sequence and causal constraints, and the problems of resource allocation, behavior organization, conflict processing and the like are solved, so that the task planning of the unmanned aerial vehicle becomes a dynamic complex system process.
At present, one part of the existing unmanned aerial vehicle mission planning methods is conventional waypoint-route planning, the other part of the existing unmanned aerial vehicle mission planning methods is an optimization method based on resource allocation and target sequencing, and the existing unmanned aerial vehicle mission planning methods have less mission planning by using behaviors. With the continuous improvement of task complexity, how to use an artificial intelligence method becomes a key for solving the technical bottleneck.
Disclosure of Invention
The invention aims to provide a multi-unmanned aerial vehicle complex task planning method which is used for solving the problem of multi-unmanned aerial vehicle complex tasks and adopts an artificial intelligent method of a behavior tree aiming at the defects of the prior art.
The invention comprises the following steps:
1) decomposing a flight task;
in the step 1), the specific steps of the flight mission decomposition are as follows:
(1) establishing a structural characteristic library of the behavior tree: establishing a corresponding logical relation library according to the structural characteristics of the behavior tree;
(2) and (3) performing multi-task decomposition: converting the multiple tasks into single tasks according to the logical relation of the behavior tree;
(3) and (3) performing single task decomposition: and converting the single task into the flight behavior in the flight behavior library according to the logical relation of the behavior tree.
In step 1), part (1), the structural characteristics library of the behavior tree comprises: root nodes and their characteristics, combination nodes and their characteristics, leaf nodes and their characteristics.
In the step 1) and the part (2), the multitask decomposition method comprises: sequential, parallel, selective, cyclic.
In the step 1) part (3), the single task decomposition method includes: sequential, parallel, selective, cyclic.
2) Designing a flight behavior library;
in step 2), the flight behavior library is designed by the following specific steps:
(1) setting a basic flight behavior library: defining and storing basic flight behaviors required by the unmanned aerial vehicle in the process of executing the task;
(2) setting a custom flight behavior library: defining and storing special flight behaviors required by the unmanned aerial vehicle in the process of executing a special task;
in step 2), part (1), the basic flight behavior library, the defined and stored basic flight behaviors, includes: take-off, cruise, hover, return, humanoid formation, square formation, circular formation.
In the step 2) and the part (2), the defined and stored flight behaviors of the custom flight behavior library comprise special flight behaviors set by a user, and can be supplemented and modified according to task requirements.
3) And compiling the XML file of the behavior tree structure.
In step 3), the specific steps of compiling the behavior tree structure XML file are as follows:
and writing a file by adopting a custom XML format language according to the behavior tree structure obtained by decomposition.
The method comprises a flight task decomposition flow, a flight behavior library design flow and an XML file compiling flow; the flight task decomposition flow is to perform behavior tree decomposition on multiple executed tasks and then perform behavior tree decomposition on the obtained single task; the flight behavior library design flow is to design a basic behavior library and a custom behavior library aiming at the flight behavior required in a single task; the XML file compiling flow is compiled by using a custom XML format language aiming at the behavior tree knots obtained by decomposition.
Compared with the prior art, the invention has the beneficial effects that: the method can help a user to plan the whole task process, decompose the task according to the task level and execute the task according to actual conditions, solves the practical problem of complex tasks of multiple unmanned aerial vehicles, and has the advantages of simple principle, flexible planning, strong practicability, good execution effect and the like.
Drawings
FIG. 1 is a schematic diagram of the construction of the method according to the present invention.
Fig. 2 is a schematic diagram of a root node of a structural feature library of a behavior tree using the method provided by the present invention.
Fig. 3 is a schematic view of sequential combination nodes of a structural property library of a behavior tree using the method provided by the present invention.
Fig. 4 is a schematic diagram of parallel combination nodes of a structural feature library of a behavior tree using the method provided by the present invention.
Fig. 5 is a schematic diagram of selected combination nodes of a structural feature library of a behavior tree using the method provided by the present invention.
FIG. 6 is a schematic diagram of a cyclic combination node of a structural property library of a behavior tree using the method provided by the present invention.
FIG. 7 is a schematic diagram of a state leaf node of the structural property library of the behavior tree using the method provided by the present invention.
FIG. 8 is a schematic diagram of a behavior leaf node of the structural property library of the behavior tree using the method provided by the present invention.
FIG. 9 is an exploded view of a behavior tree for two tasks in a specific application example.
FIG. 10 is an exploded view of a behavior tree for a target tracking task in a specific application example.
Fig. 11 is an exploded view of a behavior tree for a pesticide spraying task in a specific application example.
Detailed Description
The invention is described in detail below with reference to the figures and examples.
As shown in FIG. 1, the invention includes a flight mission decomposition process and a flight behavior library design process. The flight task decomposition process is a first link, a structural characteristic library (root node, combination node and leaf node) of a behavior tree is established for a single task or a plurality of tasks executed by a single unmanned aerial vehicle or a plurality of unmanned aerial vehicles, and the tasks are decomposed and executed according to corresponding logical relations. The design flow of the flight behavior library is a second link, a basic behavior library containing basic flight behaviors is set for the flight behaviors of the unmanned aerial vehicle required by the task, and a custom flight behavior library containing special tasks is set. The XML file compiling process is a third link, and the custom XML format file is compiled by decomposing the multiple tasks to obtain a behavior tree structure.
The flight task decomposition process comprises the following detailed steps:
(1) establishing a structural characteristic library of the behavior tree, as shown in FIGS. 2-8:
root node characteristics: and traversing and executing a plurality of or single combined nodes from top to bottom according to the set frequency, executing until a certain leaf node each time, and returning to a certain state identifier of the root node upwards to share four state identifiers of success, failure, in-service and error. The success represents that the task is successfully executed, the failure represents that the task is failed to be executed, and the error represents that the task is unpredictable during the execution process of the existing task in operation.
Combining node characteristics: the execution mode comprises sequence, parallel, selection and circulation. Sequentially executing: the subtrees are executed sequentially from left to right until one of the subtrees returns a fail, in-flight, error flag, and the remaining subtrees are not executed any more, and if all subtrees return a success flag, the node returns a success flag to the upper level. And (3) executing in parallel: all subtrees are executed simultaneously, and if the number of subtrees returning success (or failure) is greater than a set threshold (different parallel nodes may set different thresholds), the node returns a success (or failure) identifier to the upper layer. Selecting and executing: also known as priority selection execution, executes the subtrees in left-to-right order until one of the subtrees returns a success, in-flight, error flag, and no more other remaining subtrees are executed, if all subtrees return a failure flag, the node returns a failure flag to the upper level. And (3) circularly executing: the node only contains one subtree, executes the subtree set by the lower layer according to the set cycle number, and can be used for changing the execution frequency of the subtree of the lower layer until the successful identifier is returned to the upper layer after the execution is finished, otherwise, the identifier in operation is returned.
Leaf node characteristics: including state leaf nodes, behavior leaf nodes. State leaf node: and judging whether the current state meets the set index or not, and returning a success or failure identifier to the upper layer. Behavior leaf nodes: and selecting and executing the set behavior from the basic or custom behavior library, and returning success, failure, running or error identifiers to the upper layer.
(2) And (3) performing multi-task decomposition: under the condition of multitask, the multitask state is used as a root node, the sequential, parallel and selective or circular combination nodes are selected to be connected with the root node according to the logical relation between each single task and the multitask, and the single task is used as the root node of a lower-layer sub-tree to be connected with the combination nodes.
(3) And (3) performing single task decomposition: under the condition of single task, the single task is used as a root node, the sequential, parallel and selective or circular combination nodes are selected to be connected with the root node according to the logical relation of each state, behavior and the single task, and the state and behavior are used as leaf nodes to be connected with the combination nodes. Under the condition of multitask, a single task is used as a root node of a lower-layer sub-tree of a combined node, the combined node is selected to be in sequence, parallel and selected or circularly connected with the root node of the lower-layer sub-tree according to the logic relation of each state, behavior and the single task, and the state and the behavior are used as leaf nodes to be connected with the combined node.
The design process of the flight behavior library comprises the following detailed steps:
(1) setting a basic behavior library: and defining and storing basic flight behaviors required by the unmanned aerial vehicle in the task execution process, including take-off, cruise, hover, return flight, humanoid formation, square formation and circular formation.
(2) Setting a custom behavior library: and defining and storing special flight behaviors required by the unmanned aerial vehicle in the process of executing special tasks, such as target tracking, pesticide spraying and the like.
The detailed steps of the XML file compiling process are as follows:
and compiling by adopting a self-defined XML format according to the behavior tree structure obtained by task decomposition.
A specific example is adopted for explanation below, and to the multitask application of many unmanned aerial vehicles cooperation to ground, be equipped with 10 unmanned aerial vehicles, divide into 6 and 4 formations, a team of unmanned aerial vehicle carries out the target tracking task to an area, and another team of unmanned aerial vehicle carries out the pesticide and sprays the task to another area. The two teams of unmanned aerial vehicles take off at the same airport at the same time, the two target areas are different, and after the task is finished, the unmanned aerial vehicles respectively return to the airport.
The method comprises the following steps:
as shown in fig. 9, the completion states of two tasks are used as root nodes, parallel combination nodes are selected to be connected with the root nodes due to the fact that the tasks are parallel tasks, two single tasks of target tracking and pesticide spraying are used as lower-layer subtrees to be connected with the parallel combination nodes, and the threshold value of the parallel combination nodes is set to be 2, so that the two formation unmanned aerial vehicles are indicated to successfully complete the tasks and return to the voyage.
Step two:
as shown in fig. 10, 6 drones are used as a target tracking task, the completion state of the task is used as a root node of a lower-layer sub-tree, and each behavior in the task satisfies a selection logic, so that a selection combination node is connected with the root node of the lower-layer sub-tree, and the following sub-trees are sequentially connected from left to right according to a priority order. The first sub-tree is a sequential combination node, whether a takeoff instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a takeoff behavior is executed by a lower-layer behavior leaf node; the second subtree is a sequential combination node, whether a formation instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a circular formation behavior is executed by a lower-layer behavior leaf node; the third sub-tree is a sequential combination node, whether a cruise instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a cruise behavior is executed by a lower-layer behavior leaf node; the fourth sub-tree is a sequential combination node and is set for special early warning, whether the power supply is lower than a designated limit or not is judged by a lower-layer state leaf node and is lower than a failure identifier of a return combination node, and a return behavior is executed by a lower-layer behavior leaf node; the fifth sub-tree is a sequential combination node, whether the fifth sub-tree reaches the designated area is judged by a lower-layer state leaf node, the success identifier of the combination node is returned, the lower-layer circular combination node executes the target tracking behavior of the lower-layer behavior leaf node for 50 times, if the 50 times are not finished, the circular combination node returns the in-operation identifier, and if the 50 times are finished, the circular combination node returns the success identifier; the sixth sub-tree performs a return walk behavior for an individual behavioral leaf node;
as shown in fig. 11, 4 drones are used as pesticide spraying tasks, the completion states of the tasks are used as root nodes of lower subtrees, and all behaviors in the tasks meet selection logic, so that the selection combination nodes are connected with the root nodes of the lower subtrees, and the following subtrees are connected in sequence from left to right according to the priority order. The first sub-tree is a sequential combination node, whether a takeoff instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a takeoff behavior is executed by a lower-layer behavior leaf node; the second subtree is a sequential combination node, whether a formation instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a square formation behavior is executed by a lower-layer behavior leaf node; the third sub-tree is a sequential combination node, whether a cruise instruction is received or not is judged by a lower-layer state leaf node, a success identifier of a returned combination node is received, and a cruise behavior is executed by a lower-layer behavior leaf node; the fourth sub-tree is a sequential combination node and is set for special early warning, whether the power supply is lower than a designated limit or not is judged by a lower-layer state leaf node and is lower than a failure identifier of a return combination node, and a return behavior is executed by a lower-layer behavior leaf node; the fifth sub-tree is a sequential combination node, whether the fifth sub-tree reaches the designated area is judged by a lower-layer state leaf node, the success identifier of the combination node is returned, the pesticide spraying behavior of the lower-layer behavior leaf node is executed for 30 times by the lower-layer cycle combination node, the cycle combination node returns the in-operation identifier when the 30 times are not completed, and the cycle combination node returns the success identifier when the 30 times are completed; the sixth sub-tree performs the return leg behavior for individual behavioral leaf nodes.
Step three: several basic flight behaviors for target tracking and pesticide spraying tasks are defined and stored, namely take-off, cruise, hover, return, round formation and square formation.
Step four: two self-defined special flight behaviors of the target tracking task and the pesticide spraying task are defined and stored, and the target tracking task and the pesticide spraying task are respectively carried out.
Step five: according to the requirement of XML format, writing XML file according to the action tree structure chart, able to define XML format by itself. The custom canonical format may be as follows: a root node (< permission name ═ task name >), a combination node type (selection combination node < selectrree >, sequence combination node < sequence tree >, parallel combination node < parallelTree >, loop combination node < repeat time ═ execution times >), a leaf node type (status leaf node < condition value ═ setting indicator ">, action leaf node < action name ═ flight action name >). And aiming at the designed XML file, under different software platforms, developing a corresponding parser by self.
Claims (7)
1. A multi-unmanned aerial vehicle complex mission planning method is characterized by comprising the following steps:
1) decomposing a flight task;
2) designing a flight behavior library;
3) compiling a behavior tree structure XML file;
the specific steps of the flight task decomposition are as follows:
(1) establishing a structural characteristic library of the behavior tree: establishing a corresponding logical relation library according to the structural characteristics of the behavior tree;
(2) and (3) performing multi-task decomposition: converting the multiple tasks into single tasks according to the logical relation of the behavior tree; specifically, the multitask state is used as a root node, sequential, parallel and selective or circular combination nodes are selected to be connected with the root node according to the logical relation between each single task and the multitask, and the single task is used as the root node of a lower-layer sub-tree to be connected with the combination nodes;
(3) and (3) performing single task decomposition: converting the single task into the flight behavior in the flight behavior library according to the logical relation of the behavior tree; specifically, under the multitask condition, a single task is used as a root node of a lower subtree of a combined node, the combined node is selected to be in sequence, parallel and selective or circularly connected with the root node of the lower subtree according to the logical relation between each state, behavior and the single task, and the state and the behavior are used as leaf nodes to be connected with the combined node;
the flight behavior library is designed by the following specific steps:
(1) setting a basic flight behavior library: defining and storing basic flight behaviors required by the unmanned aerial vehicle in the process of executing the task;
(2) setting a custom flight behavior library: and defining and storing special flight behaviors required by the unmanned aerial vehicle in the process of executing a special task.
2. The method for planning complex mission of multiple drones according to claim 1, wherein in step 1), part (1), the library of structural characteristics of behavior tree comprises: root nodes and their characteristics, combination nodes and their characteristics, leaf nodes and their characteristics.
3. The method for planning complex mission of multiple drones according to claim 1, wherein in step 1), part (2), the multitask decomposition method comprises: sequential, parallel, selective, cyclic.
4. The method for planning complex mission of multiple drones according to claim 1, wherein in step 1), part (3), the single mission decomposition method comprises: sequential, parallel, selective, cyclic.
5. The method according to claim 1, wherein in step 2), part (1), the base flight behavior library, the defined and stored base flight behaviors comprise: take-off, cruise, hover, return, humanoid formation, square formation, circular formation.
6. The method for planning complex mission of multiple drones according to claim 1, wherein in step 2), part (2), the defined and stored flight behavior library contains special flight behavior set by the user himself, which is supplemented and modified according to mission requirement.
7. The method for planning complex tasks of multiple drones according to claim 1, wherein in the steps, the specific steps of writing the behavior tree structure XML file are as follows:
and writing a file by adopting a custom XML format language according to the behavior tree structure obtained by decomposition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710195712.7A CN106933246B (en) | 2017-03-29 | 2017-03-29 | Multi-unmanned aerial vehicle complex task planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710195712.7A CN106933246B (en) | 2017-03-29 | 2017-03-29 | Multi-unmanned aerial vehicle complex task planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106933246A CN106933246A (en) | 2017-07-07 |
| CN106933246B true CN106933246B (en) | 2020-04-14 |
Family
ID=59426144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710195712.7A Expired - Fee Related CN106933246B (en) | 2017-03-29 | 2017-03-29 | Multi-unmanned aerial vehicle complex task planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106933246B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019173981A1 (en) * | 2018-03-14 | 2019-09-19 | 深圳市大疆创新科技有限公司 | Unmanned aerial vehicle control method and device, unmanned aerial vehicle, system, and storage medium |
| US11429101B2 (en) * | 2018-04-19 | 2022-08-30 | Aurora Flight Sciences Corporation | Adaptive autonomy system architecture |
| CN109656267B (en) * | 2018-12-24 | 2022-03-15 | 中国航空工业集团公司西安飞机设计研究所 | Parallel cooperative test method for flight control system |
| CN112394701A (en) * | 2020-12-10 | 2021-02-23 | 之江实验室 | Multi-robot cloud control system based on cloud-edge-end hybrid computing environment |
| CN113534662B (en) * | 2021-06-04 | 2022-12-02 | 中国人民解放军军事科学院国防科技创新研究院 | Behavior tree-based unmanned system cluster control method |
| CN116430754B (en) * | 2023-06-09 | 2023-09-12 | 北京中兵天工防务技术有限公司 | Unmanned aerial vehicle cluster multitask control semi-physical simulation method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004213360A (en) * | 2002-12-27 | 2004-07-29 | Sumitomo Electric Ind Ltd | Data retrieval system and data retrieval apparatus |
| US9280584B2 (en) * | 2013-11-25 | 2016-03-08 | International Business Machines Corporation | Finding optimal query plans |
| US9500488B2 (en) * | 2012-03-14 | 2016-11-22 | Lockheed Martin Corporation | Route re-planning using enemy force lethality projection |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8417689B1 (en) * | 2011-11-21 | 2013-04-09 | Emc Corporation | Programming model for transparent parallelization of combinatorial optimization |
| CN103617497B (en) * | 2013-12-03 | 2016-12-07 | 中国航空无线电电子研究所 | A kind of aircraft task system task synthetic method |
| CN103777640B (en) * | 2014-01-15 | 2016-05-04 | 北京航空航天大学 | A kind of distributed control unmanned aerial vehicle group is concentrated sub-clustering formation method |
| CN104808679B (en) * | 2015-02-27 | 2017-06-23 | 中国民航大学 | General Aviation AIP file intelligent Matching methods based on Flight Trajectory Prediction |
| CN104809935A (en) * | 2015-05-13 | 2015-07-29 | 中国航空工业集团公司沈阳飞机设计研究所 | Simulation training method for special situation fault of unmanned aerial vehicle and system thereof |
| CN105205271B (en) * | 2015-09-29 | 2019-03-12 | 中国运载火箭技术研究院 | A kind of aircraft mission reliability modeling method based on dynamic characteristic |
| CN105892480B (en) * | 2016-03-21 | 2018-12-11 | 南京航空航天大学 | Isomery multiple no-manned plane systematic collaboration, which is examined, beats task self-organizing method |
-
2017
- 2017-03-29 CN CN201710195712.7A patent/CN106933246B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004213360A (en) * | 2002-12-27 | 2004-07-29 | Sumitomo Electric Ind Ltd | Data retrieval system and data retrieval apparatus |
| US9500488B2 (en) * | 2012-03-14 | 2016-11-22 | Lockheed Martin Corporation | Route re-planning using enemy force lethality projection |
| US9280584B2 (en) * | 2013-11-25 | 2016-03-08 | International Business Machines Corporation | Finding optimal query plans |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106933246A (en) | 2017-07-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106933246B (en) | Multi-unmanned aerial vehicle complex task planning method | |
| CN105183445B (en) | A kind of Visual Design System of the game artificial intelligence based on XML | |
| Stumptner | An overview of knowledge‐based configuration | |
| Wainer | CD++: a toolkit to develop DEVS models | |
| Tu et al. | Rollout strategies for sequential fault diagnosis | |
| Syriani et al. | A modular timed graph transformation language for simulation-based design | |
| CN113722912B (en) | Virtual-real fused unmanned cluster collaborative verification system | |
| CN103399787B (en) | A kind of MapReduce operation streaming dispatching method and dispatching patcher calculating platform based on Hadoop cloud | |
| Maia et al. | Dragonfly: a tool for simulating self-adaptive drone behaviours | |
| Kvarnström et al. | Automated planning for collaborative UAV systems | |
| CN113435033B (en) | Multi-resolution-based complex system operation flow simulation method and system | |
| CN103530898A (en) | Animation processing method and system based on 3D real-time rendering | |
| CN110287088B (en) | Automatic testing method based on dynamic UI model | |
| CN110175676B (en) | High-performance rule matching method for memory-limited environment | |
| CN106096159B (en) | A kind of implementation method of distributed system behavior simulation analysis system under cloud platform | |
| Feljan et al. | Task allocation optimization for multicore embedded systems | |
| Gueye et al. | Component-based autonomic managers for coordination control | |
| Molina et al. | Behavior coordination for self-adaptive robots using constraint-based configuration | |
| Marion et al. | Gaspar: Aviation management on an aircraft carrier using virtual reality | |
| Durán et al. | R-MOZART: a reconfiguration tool for WebThings applications | |
| Huang et al. | Autonomous Reconnaissance Action of Swarm Unmanned System Driven by Behavior Tree | |
| Ma et al. | Object-oriented petri nets based formal modeling for high-confidence cyber-physical systems | |
| Mühlbacher et al. | Constraint-based testing of an industrial multi-robot navigation system | |
| Yan et al. | Collaborative Simulation Testing with State Behavior Tree | |
| Fu et al. | A Cooperation Graph Approach for Multiagent Sparse Reward Reinforcement Learning |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200414 Termination date: 20210329 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |