CN111144827B - Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation - Google Patents
Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation Download PDFInfo
- Publication number
- CN111144827B CN111144827B CN202010071333.9A CN202010071333A CN111144827B CN 111144827 B CN111144827 B CN 111144827B CN 202010071333 A CN202010071333 A CN 202010071333A CN 111144827 B CN111144827 B CN 111144827B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- historical
- region
- gain
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0835—Relationships between shipper or supplier and carriers
- G06Q10/08355—Routing methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the technical field of unmanned aerial vehicles, and relates to a dynamic planning method for a cruising path of an unmanned aerial vehicle based on historical gain estimation. The method comprises the following steps: s1) calculating the historical gain of each region; s2) calculating the benefit score of the next hop destination region by combining the distance factor; and S3) designing a dynamic planning method for the unmanned aerial vehicle path. The method comprises the steps of calculating historical gains of all areas according to historical data obtained by the fact that the unmanned aerial vehicle visits all the areas, and calculating benefit scores of all the areas in the next-hop cruise. Compared with the traditional unmanned aerial vehicle ferrying method, the method is more flexible, so that the purpose of dynamically acquiring the next-hop optimal path in the cruising process of the unmanned aerial vehicle and improving the comprehensive performance is achieved.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicles, and relates to a dynamic planning method for a cruising path of an unmanned aerial vehicle based on historical gain estimation.
Background
The unmanned aerial vehicle is a new sensing device, and because the unmanned aerial vehicle has the characteristics of small volume, flexible and free movement in a three-dimensional space, convenient use, suitability for complex environments and strong viability, the unmanned aerial vehicle and related technologies thereof are favored by countries all over the world, are widely concerned about and used in various fields, and are often used in industries such as agriculture, weather, emergency rescue and disaster relief. Particularly, in an emergency environment, due to the reason that the geographic position of the mobile node is not uniformly distributed, the mobile node moves, the node fails and the like, a plurality of disconnected sub-networks in the mobile ad hoc network, namely, a network segmentation phenomenon occurs. The connectivity of the network is very important in disaster area rescue, military communication and other aspects, and concerns the life and property safety of people, so how to connect a plurality of disconnected subnets to ensure the connectivity of the whole network is very important. When a plurality of disconnected subnetworks occur in the mobile ad hoc network, the realization of the mutual communication of nodes in different subnetworks through the unmanned aerial vehicle is one of effective solutions to the problem.
Unmanned aerial vehicle flight involves many technologies, but most importantly, the problem of path planning for unmanned aerial vehicles. The path planning is an important component of an unmanned aerial vehicle control strategy, and the reasonable planning of the cruise path plays an important role in reducing the flight path length and improving the endurance performance. In the existing researches, because many scenes utilizing the unmanned aerial vehicle are driven based on tasks at the present stage, the motion trail of the unmanned aerial vehicle is artificially planned in advance, the unmanned aerial vehicle only needs to move according to the planned trail, the current position state of the unmanned aerial vehicle is only considered in many existing methods, and the characteristic that the unmanned aerial vehicle at the present moment is driven based on the tasks is not fully considered, so that the optimal object for next hop transmission is difficult to find.
Therefore, the designed historical gain estimation-based unmanned aerial vehicle cruising path dynamic planning method suitable for the multiple target nodes has great significance for auxiliary data transmission of the unmanned aerial vehicle.
Disclosure of Invention
In view of this, the present invention provides a method for dynamically planning a cruising path of an unmanned aerial vehicle based on historical gain estimation. The unmanned aerial vehicle can acquire historical data when accessing each area, gains obtained by analyzing the historical data attributes of the unmanned aerial vehicle represent data increment obtained in unit time, such as the weight and number of express delivered by communities and the number of message packages in a network. And the unmanned aerial vehicle obtains the regional benefit by combining the historical gain of the region and the position distance of the unmanned aerial vehicle at the current moment, and reasonably selects the next hop destination region. According to the method, when the unmanned aerial vehicle carries out path planning, the area with the highest area benefit is selected as the next hop, and therefore the optimal path is dynamically obtained in the cruising process of the unmanned aerial vehicle.
In order to achieve the purpose, the invention provides the following technical scheme:
an unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation comprises the following steps:
step 1) calculating the historical gain of each region;
step 2) calculating the benefit score of the next hop destination region by combining the distance factors;
and 3) designing a dynamic planning method for the unmanned aerial vehicle path.
Further, the step 1) specifically comprises the following steps:
and step 11) after the unmanned aerial vehicle interacts with one region, the unmanned aerial vehicle makes a decision on the central node of the next hop region according to the collected historical data. And the unmanned aerial vehicle calculates the historical gain of each region by combining the relative weight distributed by the data attribute according to the historical data obtained by visiting the regions. The historical data and the classification (attribute) thereof can be defined differently for different application scenarios. For example: in the application scene of carrying out article delivery with unmanned aerial vehicle, the number of the goods of delivery can regard as historical data, can classify the goods according to the emergency degree that the goods need deliver. Each class is given a respective weight. Thus, the weighted sum of all the goods and their corresponding weights can be counted and used as the historical gain of the area for a period of time. For another example: in a scene that an unmanned aerial vehicle is used as a ferry node to carry and forward messages between different areas in a delay tolerant network, the number of message packets can be used as historical data, the message packets can be classified according to the importance, the emergency degree, the size and the like of the message packets, and different weights are given to the message packets of each grade. And counting the weighted sum of the message packets of all the grades as the historical gain of the region for a period of time. The historical gain may be calculated by the following formula:
arrival time t of jth cruise r region j The data volume of the ith type data received at the moment is n i Each class of data is weighted by ω i ；
Step 12) calculating the average gain of the previous m cruising times according to the historical gains of all the areas, wherein the average gain can be expressed as:
further the step 2) comprises the following steps:
step 21) calculating benefit scores of all regions of the next-hop cruise by combining the distances from the unmanned aerial vehicle to all the regions at the moment after the unmanned aerial vehicle obtains the historical gains; unmanned plane at t k Selecting the next hop destination area according to the area benefit at the moment, and at t k The requirements of other areas cannot be obtained at any moment, so the average gain estimation t obtained by the previous m times of cruising obtained in the step 1 is adopted k The gain in the region of time r can be expressed as:
wherein t is k-1 D (f, r) is the time of the previous visit to the r area, and the linear distance between the unmanned aerial vehicle and the r area; v is the average cruising speed;
step 22) additionally needs to consider t on drone k The cruise gain for the r region calculated from the region data stored at the time can be expressed as:
step 23) the benefit epsilon (r) of each cruise r region can be calculated by the following formula:
further, the step 3) specifically comprises the following steps:
step 31) in the cruising starting stage of the unmanned aerial vehicle, due to the lack of historical information, the uploading requirement of the central node of each area cannot be obtained, so in the starting stage, the linear distance d between the areas is firstly used ij And calculating a shortest path as a weight, taking the shortest path as a cruise path at the beginning stage of ferry, wherein the average gain of each historical data of each area needs to be calculated and the record needs to be updated during the cruising period of the unmanned aerial vehicle except that the required historical data acquisition of each area is completed.
And 32) when the online decision is started, the ferry node uses the information collected in the starting stage as an initial value, calculates epsilon (r) according to the step 2), selects the area with the maximum epsilon (r) as the next hop destination area of the unmanned aerial vehicle, and repeats the process until the cruise is finished.
The invention has the beneficial effects that: according to the invention, the historical data attribute of the unmanned aerial vehicle is calculated, and the historical gain, distance factors and the like of each region are calculated according to the weight distributed by the data attribute to jointly calculate the benefit score. Compared with the traditional unmanned aerial vehicle cruising method, the method is more flexible, the optimal path can be dynamically acquired in the unmanned aerial vehicle cruising process, and the service efficiency of the unmanned aerial vehicle is improved.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a schematic flow chart of a method for implementation
FIG. 2 shows the whole environment for planning the cruising path of the unmanned aerial vehicle
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The invention provides a method for dynamically planning an unmanned aerial vehicle path based on message priority, which is shown in a schematic flow chart of a method provided for implementation as shown in figure 1. Fig. 2 shows the whole environment of the cruise path planning of the unmanned aerial vehicle. According to the path planning of the historical cruising data of the unmanned aerial vehicle, the unmanned aerial vehicle cruises among a plurality of areas. The method comprises the following steps: step 1) calculating the historical gain of each region; step 2) calculating the benefit score of the next hop destination region by combining the distance factors; and 3) designing a dynamic planning method for the unmanned aerial vehicle path.
Further, the step 1) specifically comprises the following steps:
and step 11) after the unmanned aerial vehicle interacts with one region, the unmanned aerial vehicle makes a decision on the central node of the next hop region according to the collected historical data. And the unmanned aerial vehicle calculates the historical gain of each region by combining the relative weight distributed by the data attribute according to the historical data obtained by visiting the regions. The historical data and the classification (attribute) thereof can be defined differently for different application scenarios. For example: in the application scene of carrying out article delivery with unmanned aerial vehicle, the number of the goods of delivery can regard as historical data, can classify the goods according to the emergency that the goods need deliver. Each class is given a corresponding weight. Thus, the weighted sum of all the goods and their corresponding weights can be counted and used as the historical gain of the area for a period of time. For another example: in a scene that an unmanned aerial vehicle is used as a ferry node to complete carrying and forwarding of messages between different areas in a delay tolerant network, the number of message packets can be used as historical data, the message packets can be classified according to the importance, the emergency degree, the size and the like of the message packets, and different weights are given to the message packets of each grade. And counting the weighted sum of the message packets of all the grades as the historical gain of the region for a period of time. The historical gain can be calculated by the following formula:
arrival time t of jth cruise r region j The data volume of the ith type data received at the moment is n i Each class of data is weighted by ω i ；
Step 12) calculating the average gain of the previous m cruising times according to the historical gains of all the areas, wherein the average gain can be expressed as:
further the step 2) comprises the following steps:
step 21) calculating benefit scores of each region for the next-hop cruise by combining the distances from the unmanned aerial vehicle to the regions at the moment after the unmanned aerial vehicle obtains the historical gains; unmanned plane at t k Selecting the next hop destination area according to the area benefit at the moment, and at t k Time of day cannot be acquiredTo other areas, so the previous m cruise average gain estimate t from step 1 above is used k The gain in the region of time r can be expressed as:
wherein t is k-1 D (f, r) is the time of the previous visit to the r area, and the linear distance between the unmanned aerial vehicle and the r area; v is the average cruising speed;
step 22) additionally needs to consider t on drone k The cruise gain for the r region calculated from the region data stored at the time can be expressed as:
step 23) the benefit epsilon (r) of each cruise r region can be calculated by the following formula:
further, the step 3) specifically comprises the following steps:
step 31) in the cruising starting stage of the unmanned aerial vehicle, due to the lack of historical information, the uploading requirement of the central node of each area cannot be obtained, so in the starting stage, the linear distance between the areas is firstly used
And calculating a shortest path as a weight, taking the shortest path as a cruise path at a cruise starting stage, and calculating an average gain of historical data of each area and updating a record, except for finishing the necessary historical data acquisition of each area during the cruise of the unmanned aerial vehicle.
And 32) when the online decision is started, the ferry node uses the information collected in the starting stage as an initial value, calculates epsilon (r) according to the step 2), selects the area with the maximum epsilon (r) as the next hop destination area of the unmanned aerial vehicle, and repeats the process until the cruise is finished.
Through carrying out above step, can realize at the unmanned aerial vehicle region of jumping of the dynamic selection of in-process that cruises, and then realize that unmanned aerial vehicle cruises the in-process dynamic acquireing optimum route, improve comprehensive properties's purpose.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (1)
1. An unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation is characterized in that: the method comprises the following steps:
s1) calculating historical gains of all regions; the method comprises the following steps:
s11) the unmanned aerial vehicle calculates the historical gain of each region according to the historical data obtained by accessing the region and the relative weight distributed by the data attribute;
the historical gain is calculated with the following formula:
wherein the arrival time t of the jth cruise r region j The data volume of the ith type data received at the moment is n i Each type of data has a weight of ω i ；
S12) calculating the average gain of the previous m cruising times according to the historical gains of all the areas, wherein the average gain can be expressed as:
s2) calculating the benefit score of the next hop destination region by combining the distance factor; the method comprises the following steps:
s21) after obtaining the historical gain, the unmanned aerial vehicle calculates benefit scores of all regions of the next-hop cruise by combining the distance from the unmanned aerial vehicle to each region at the moment, and the method comprises the following steps:
unmanned plane at t k Selecting the next hop destination area according to the area benefit at the moment, and at t k The requirements of other areas cannot be obtained at the moment, and the average gain estimation t obtained by the previous m times of cruising and obtained in the step S12) is adopted k The gain in the region at time r is expressed as:
wherein t is k-1 D (f, r) is the time of the previous visit to the r area, and the linear distance between the unmanned aerial vehicle and the r area; v is the average cruising speed;
step S22) consider t on drone k The cruise gain for the r region calculated from the region data stored at the time is represented by:
step S23) cruising the benefit epsilon (r) of each r area is calculated by the following formula:
s3) designing a dynamic planning method for the unmanned aerial vehicle path; the method comprises the following steps:
step 31) in the cruising starting stage of the unmanned aerial vehicle, due to the lack of historical information, the uploading requirement of the central node of each area cannot be obtained, so in the starting stage, the linear distance between the areas is firstly used
As a weight, a shortest path is calculated, and the shortest path is calculatedThe path is used as a cruising path at the starting stage of ferrying, and the unmanned aerial vehicle needs to calculate the average gain of each historical data of each area and update the record during cruising except for finishing the necessary acquisition of the historical data of each area;
step 32) when the online decision is started, the ferry node uses the information collected in the starting stage as an initial value, selects an area with the largest epsilon (r) as a next hop destination area of the unmanned aerial vehicle according to the epsilon (r) calculated in the step 23, and repeats the steps S1-S3 until the cruise is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010071333.9A CN111144827B (en) | 2020-01-21 | 2020-01-21 | Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010071333.9A CN111144827B (en) | 2020-01-21 | 2020-01-21 | Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111144827A CN111144827A (en) | 2020-05-12 |
| CN111144827B true CN111144827B (en) | 2022-10-18 |
Family
ID=70526862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010071333.9A Active CN111144827B (en) | 2020-01-21 | 2020-01-21 | Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144827B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113873203B (en) * | 2021-09-30 | 2023-09-26 | 杭州华橙软件技术有限公司 | Method, device, computer equipment and storage medium for determining cruising path |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426806A (en) * | 2011-11-07 | 2012-04-25 | 同济大学 | Regional rail network UAV cruise method based on dynamic cell division |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9659503B2 (en) * | 2015-07-14 | 2017-05-23 | International Business Machines Corporation | Ambulatory route management based on a personal drone |
| US11100589B1 (en) * | 2016-09-02 | 2021-08-24 | State Farm Mutual Automobile Insurance Company | Systems and methods for analyzing unmanned aerial missions |
| CN106679666B (en) * | 2016-12-26 | 2019-12-17 | 北京联合大学 | Unmanned aerial vehicle large-range cruise path planning model and method |
| CN106842963B (en) * | 2017-04-14 | 2018-01-30 | 合肥工业大学 | Multiple no-manned plane detection mission is distributed and trajectory planning combined optimization method and device |
| CN108362285B (en) * | 2018-01-30 | 2021-07-09 | 信阳师范学院 | Plant protection unmanned aerial vehicle accurate coverage track planning method and system |
| CN109521794A (en) * | 2018-12-07 | 2019-03-26 | 南京航空航天大学 | A kind of multiple no-manned plane routeing and dynamic obstacle avoidance method |
| CN110470301B (en) * | 2019-08-13 | 2020-12-11 | 上海交通大学 | Unmanned aerial vehicle path planning method under multi-dynamic task target point |
-
2020
- 2020-01-21 CN CN202010071333.9A patent/CN111144827B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426806A (en) * | 2011-11-07 | 2012-04-25 | 同济大学 | Regional rail network UAV cruise method based on dynamic cell division |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111144827A (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hong et al. | Toward swarm coordination: Topology-aware inter-UAV routing optimization | |
| Iranmanesh et al. | Novel DTN mobility-driven routing in autonomous drone logistics networks | |
| CN110543185B (en) | Unmanned aerial vehicle data collection method based on minimum information age | |
| Zhang et al. | A novel multicast routing method with minimum transmission for WSN of cloud computing service | |
| Motlagh et al. | UAV selection for a UAV-based integrative IoT platform | |
| CN104581862A (en) | Measurement and control communication method and system based on low-altitude unmanned aerial vehicle self-network | |
| CN112822745B (en) | Self-adaptive routing method for unmanned aerial vehicle ad hoc network | |
| KR102009080B1 (en) | Path planning decision method for unmanned aerial vehicles | |
| CN110650039A (en) | Multimodal optimization-based network collaborative communication model for unmanned aerial vehicle cluster-assisted vehicle | |
| CN110572797B (en) | Route-finding network topology structure for emergency communication and routing method thereof | |
| CN110191413B (en) | Method and system for broadcasting in mobile ad hoc network based on greedy ant colony algorithm | |
| CN113163466B (en) | Self-adaptive fish school routing packet routing method based on fuzzy decision tree | |
| CN109275154B (en) | Dynamic self-adaptive routing path planning method based on double-layer topological routing algorithm | |
| Yoon et al. | Rendezvous: Opportunistic data delivery to mobile users by UAVs through target trajectory prediction | |
| CN111144827B (en) | Unmanned aerial vehicle cruising path dynamic planning method based on historical gain estimation | |
| Melaouene et al. | An enhanced routing algorithm using ant colony optimization and VANET infrastructure | |
| CN113115399A (en) | Route optimization method for self-organizing network of heterogeneous unmanned aerial vehicle | |
| CN114828146A (en) | Routing method for geographical position of unmanned cluster based on neural network and iterative learning | |
| CN113163332B (en) | Road sign graph coloring unmanned aerial vehicle energy-saving endurance data collection method based on metric learning | |
| Aboueleneen et al. | Deep reinforcement learning for internet of drones networks: issues and research directions | |
| Shu et al. | Mobility prediciton clustering routing in UAVs | |
| CN113727278A (en) | Path planning method, access network equipment and flight control equipment | |
| Singh et al. | Energy-efficient uav trajectory planning in rechargeable iot networks | |
| Karthik et al. | Optimized multiple existence for pedestrian evacuation using geographic map-based path discovery | |
| Aravindhan et al. | Experimental design of VANET routing using enhanced ant colony optimization technique |
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 |