CN114537666B - Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method - Google Patents
Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method Download PDFInfo
- Publication number
- CN114537666B CN114537666B CN202210246232.XA CN202210246232A CN114537666B CN 114537666 B CN114537666 B CN 114537666B CN 202210246232 A CN202210246232 A CN 202210246232A CN 114537666 B CN114537666 B CN 114537666B
- Authority
- CN
- China
- Prior art keywords
- garbage
- aerial vehicle
- unmanned ship
- unmanned
- unmanned aerial
- 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
- 239000010813 municipal solid waste Substances 0.000 title claims abstract description 141
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007667 floating Methods 0.000 title claims abstract description 29
- 238000004891 communication Methods 0.000 claims abstract description 25
- 230000005540 biological transmission Effects 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims description 25
- 230000033001 locomotion Effects 0.000 claims description 20
- 238000004140 cleaning Methods 0.000 claims description 16
- 238000013507 mapping Methods 0.000 claims description 13
- 238000007726 management method Methods 0.000 claims description 10
- 238000001914 filtration Methods 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000013135 deep learning Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims description 3
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 239000003643 water by type Substances 0.000 description 2
- 241000192700 Cyanobacteria Species 0.000 description 1
- 230000002567 autonomic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64C—AEROPLANES; HELICOPTERS
- B64C39/00—Aircraft not otherwise provided for
- B64C39/02—Aircraft not otherwise provided for characterised by special use
- B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B35/32—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for for collecting pollution from open water
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/08—Arrangements of cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63B—SHIPS OR OTHER WATERBORNE VESSELS; EQUIPMENT FOR SHIPPING
- B63B35/00—Vessels or similar floating structures specially adapted for specific purposes and not otherwise provided for
- B63B2035/006—Unmanned surface vessels, e.g. remotely controlled
- B63B2035/008—Unmanned surface vessels, e.g. remotely controlled remotely controlled
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
-
- 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
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02T90/10—Technologies relating to charging of electric vehicles
- Y02T90/14—Plug-in electric vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Public Health (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a water surface floating garbage removing device with cooperation of an unmanned aerial vehicle and an unmanned ship and an operation method, wherein the water surface floating garbage removing device comprises the unmanned aerial vehicle and the unmanned ship; the unmanned aerial vehicle builds a map of a target water area and identifies water surface garbage, the ground workstation transmits garbage coordinate information to each unmanned ship, the unmanned ship plans a global path of a water area in charge of the unmanned ship to reach a garbage point, and the garbage is picked up through a mechanical arm; the device also comprises a control system which is divided into three layers: a management layer, a communication layer and a control execution layer; the management layer is a ground workstation and is used for controlling, visualizing and operating the integral structure of the unmanned aerial vehicle and the integral structure of the unmanned ship; the communication layer mainly transmits the running state of the unmanned aerial vehicle unmanned ship to the ground workstation through WIFI data transmission; the control layer mainly acquires environment data and receives a control instruction of the management layer.
Description
Technical Field
The invention belongs to the field of cleaning of floating garbage in rivers and lakes in cities, and particularly relates to automatic garbage cleaning equipment for cleaning floating garbage on water surfaces by using unmanned aerial vehicles and unmanned ships.
Background
The water areas of urban rivers and lakes are large, and garbage, blue-green algae and the like floating on the water surface have large influence on the ecological environment and are difficult to remove. Therefore, the method becomes a big link of environmental management aiming at the cleaning of the water surface garbage. A large amount of manpower is spent on special cleaning every year, the working efficiency is low, the problems of safety and the like need to be considered in manual operation on the water surface, and the method is not the optimal choice for cleaning river channel garbage. Compare manual work, surface of water unmanned ship can realize all-weather, autonomic operation, can carry out the operation in some artifical danger areas that are difficult to reach simultaneously, can promote clean efficiency effectively. Along with the rapid development of mobile internet and big data, the unmanned aerial vehicle is more and more widely applied in the aspects of aerial surveying and mapping, agricultural plant protection, forest fire control and the like. The unmanned ship on the water surface is deficient due to the advantages of wide visual field, strong maneuverability and the like. The unmanned aerial vehicle and the unmanned ship are combined, so that the search capability of the garbage in a large-scale water area can be greatly improved, and the garbage cleaning efficiency is improved.
Disclosure of Invention
The invention mainly solves the problems of low efficiency, high cost, unsafe and the like of manually cleaning water surface garbage. In order to improve the cleaning capacity of the water surface garbage, the invention provides the water surface floating garbage cleaning equipment with the cooperation of the unmanned aerial vehicle and the unmanned ship and a using method thereof, the invention realizes that a frame is constructed based on an open-source robot operating system ROS, and the main technical scheme is as follows: the unmanned aerial vehicle is used for drawing a target water area and identifying water surface garbage, the ground workstation is used for transmitting garbage coordinate information to each unmanned ship, the unmanned ship carries out global path planning on the water area in charge of the unmanned ship to reach a garbage point, and garbage is picked up through the mechanical arm.
In order to achieve the technical characteristics, the invention aims to realize that: a water surface floating garbage removing device with cooperation of an unmanned aerial vehicle and an unmanned ship comprises the unmanned aerial vehicle and the unmanned ship;
the unmanned aerial vehicle builds a map of a target water area and identifies water surface garbage, the ground workstation transmits garbage coordinate information to each unmanned ship, the unmanned ship plans a global path of a water area in charge of the unmanned ship to reach a garbage point, and the garbage is picked up through a mechanical arm;
the device also comprises a control system, wherein the control system is divided into three layers: a management layer, a communication layer and a control execution layer; the management layer is a ground workstation and is used for controlling, visualizing and operating the integral structure of the unmanned aerial vehicle and the integral structure of the unmanned ship; the communication layer transmits the running state of the unmanned aerial vehicle unmanned ship to the ground workstation mainly through WIFI data transmission; the control layer mainly acquires environment data and receives a control instruction of the management layer.
The unmanned aerial vehicle is provided with an on-board computer, a first depth camera, a first laser radar, a GPS module, PX4 open source flight control, WIFI data transmission and charging and discharging devices;
the onboard computer receives first depth camera and first laser radar information, and a control instruction; the method comprises the steps that a first depth camera obtains information of floating garbage on the water surface, wherein the information comprises garbage category and position information; a first laser radar acquires surrounding environment information and is matched with an SLAM algorithm to carry out positioning and mapping; the GPS module realizes the positioning of the unmanned aerial vehicle; WIFI data transmission is used for communication between unmanned aerial vehicle overall structure and unmanned ship overall structure.
The unmanned ship is provided with a mechanical arm, a garbage storage device, a driving device, a WIFI data transmission module, a high-precision inertial navigation module, a second laser radar, a GPS module, an onboard computer and a second depth camera;
the mechanical arm picks up the garbage; the high-precision inertial navigation module and the GPS module perform position and speed fusion in an extended Kalman filtering loose coupling mode, wherein the high-precision inertial navigation module comprises a speed acceleration, an angular speed and a yaw angle, the position and the speed are obtained by resolving through an inertial system, the GPS module resolves the position and the speed through a navigation system, data fusion is performed through extended Kalman filtering, and finally, the output result is subjected to feedback correction and then the position and the speed are output; the second laser radar acquires surrounding environment information and performs positioning navigation by matching with an SLAM algorithm; the GPS module provides positioning for the unmanned ship; the depth camera identifies spam information, including spam category and location information.
Unmanned aerial vehicle's location is built the picture and is discerned rubbish and include: the unmanned aerial vehicle carries out mapping and positioning through the SLAM technology, a target water area two-dimensional grid map is established through an SLAM framework Cartogrer algorithm based on map optimization, floating garbage in a water area is identified through a deep learning YOLOV3 algorithm in the mapping process, XYZ coordinates are calculated according to point cloud information in an identification frame, the X coordinates are converted into a world coordinate system, and the world coordinate system is sent to the unmanned ship through a workstation.
Converting coordinates of the unmanned aerial vehicle and the unmanned ship, converting the motion of the unmanned aerial vehicle into three-dimensional space rigid motion, converting the coordinates of a first depth camera of the unmanned aerial vehicle into a base mark of the unmanned aerial vehicle, and finally converting the coordinates into a world coordinate system; the motion of the unmanned ship in the plane can be regarded as rigid motion, the rigid motion is converted into a world coordinate system through homogeneous coordinate transformation, and the unmanned ship of the unmanned plane is located in the world coordinate system.
Unmanned aerial vehicle, unmanned ship and workstation's communication, unmanned aerial vehicle, unmanned ship and workstation constitute in this communication system, and the workstation belongs to the main control computer, and unmanned aerial vehicle and unmanned ship are as following the machine, connect through the WIFI LAN between the three, and the main control computer is responsible for controlling unmanned aerial vehicle and unmanned ship, mainly realizes: the unmanned aerial vehicle and the unmanned ship realize the transmission of images and the interaction of environmental information.
The method comprises the steps of positioning the unmanned ship, mainly obtaining the position of the unmanned ship in a map, leading the positioning of the unmanned ship to be deviated due to the influence of wind speed waves when the unmanned ship sails on the water surface, adopting a high-precision inertial navigation module and a GPS module to carry out global positioning, adopting an extended Kalman filtering loose coupling mode to estimate the state errors of the inertial navigation module and the GPS module, correcting each navigation system through feedback through estimation of the state errors, and improving the positioning precision.
Planning the path of the unmanned ship, dividing a two-dimensional grid map and areas by a ground workstation, acquiring a world coordinate system of each unmanned ship, and obtaining a garbage coordinate relation of a water area in which the unmanned ship is responsible through coordinate transformation; the unmanned ship carries out path planning from near to far according to the received garbage coordinate information of the water area in which the unmanned ship is responsible, global path planning is carried out by using an A-star algorithm in navigation, and the optimal route from the unmanned ship to the target position is calculated.
And the garbage picking of the mechanical arm mainly comprises the steps of using a point cloud generated by a second depth camera after reaching the position, carrying out target detection on the floating garbage on the water surface, calculating a point cloud coordinate in the identification frame, converting the acquired garbage coordinate into a mechanical arm coordinate system, and starting motion planning and grabbing by the mechanical arm.
The operation method of the water surface floating garbage removing equipment with the cooperation of the unmanned aerial vehicle and the unmanned ship comprises the following steps:
s1 is the beginning;
s2, enabling the unmanned aerial vehicle unmanned ship to reach a target water area;
s3, the unmanned aerial vehicle unmanned ship stops statically, and wireless communication is established with a ground workstation;
s4, drawing an SLAM of the target water area according to a planned route, and identifying garbage;
s5, returning by the unmanned aerial vehicle;
s6, dividing the target water area by the ground station according to the number of unmanned ships, wherein one ship is responsible for one water area;
s7, converting the coordinates of each ship into a world coordinate system according to the identified garbage coordinates;
s8, performing global path planning for the garbage coordinate traversal of each ship in charge of the water area;
s9, enabling the unmanned ship to arrive at a target point;
s10, if the rubbish is identified, an in-place rotation searching target is not identified;
s11, grabbing by a mechanical arm;
s12, heading to an unscanned area;
s13 is the end;
the specific process of S2 is as follows:
step A1: the unmanned ship unmanned aerial vehicle reaches a target water area;
step A2: checking the surrounding environment of the target water area;
the specific process of S3 is as follows:
step B1: starting an unmanned ship, an unmanned aerial vehicle and a ground workstation;
and step B2: checking the running condition of the equipment;
and step B3: inputting an IP address and establishing communication among the three through WIFI data transmission;
the specific process of S4 is as follows:
step C1: vertically lifting the unmanned aerial vehicle to a proper height;
and step C2: starting SLAM map building, and building a two-dimensional grid map by adopting a Cartogrer algorithm;
and C3: identifying the floating garbage on the water surface through a first depth camera by using a deep learning YOLOV3 algorithm while establishing a map;
the specific process of S5 is as follows:
step D1: the unmanned aerial vehicle carries the collected garbage coordinate information and the two-dimensional map and returns to the ground workstation;
the specific process of S6 is as follows:
step E1: processing a two-dimensional map and garbage coordinate information established by the unmanned aerial vehicle;
step E2: reasonably dividing the responsible water area of each ship according to the map, the number of ships and the water area environment;
the specific process of S7 is as follows:
step F1: converting the garbage coordinate calculated by the unmanned aerial vehicle into a world coordinate system by the ground workstation;
step F2: converting the coordinate system of the unmanned ship into a world coordinate system by the ground workstation;
step F3: transmitting the garbage coordinates under each area to an unmanned ship in charge of the area;
the specific process of S8 is as follows:
step G1: receiving garbage coordinate information under a world coordinate system by the unmanned ship;
step G2: setting a navigation point from near to far according to the garbage coordinate information;
step G3: carrying out global path planning according to the grid map, and finding out an optimal path through an A-star algorithm;
the specific process of S9 is as follows:
step H1: the unmanned ship sequentially goes to the areas where the garbage are located according to the planned route obtained in the S8;
the S10 specific process:
step I1: when the unmanned ship reaches the region where the water surface floating garbage is located, the unmanned ship identifies the garbage by using a YOLOV3 target identification algorithm;
step I2: if the garbage is not identified, the unmanned ship rotates in situ to search for a target;
the specific process of S11 is as follows:
step J1: identifying a target, processing point cloud information in an identification frame, acquiring garbage coordinate information, and calculating coordinates of garbage relative to the mechanical arm through coordinate conversion;
step J2: moveit is adopted to plan a mechanical arm movement route, and a mechanical arm clamping jaw moves to reach a garbage position for grabbing;
the specific process of S12:
step K1: after the work of the area is finished, carrying the unmanned plane with the unmanned ship to work in the next subarea, and repeating the steps S3-S11;
step K2: if the cleaning work of all the areas is completed, S13 is performed, and the work is finished.
The invention has the following beneficial effects:
1. according to the unmanned aerial vehicle and the multi-unmanned ship combined type water surface garbage collection and treatment system, the unmanned aerial vehicle and the multi-unmanned ship are used for cleaning water surface garbage in a cooperative working mode, so that the defect of the view of the unmanned ship can be overcome, and the garbage searching and cleaning efficiency can be effectively improved. The operation of multiple unmanned ships can shorten the working time and reduce the time consumed by cleaning garbage.
2. The invention relates to an unmanned aerial vehicle, which establishes a two-dimensional grid map for a target water area through a laser radar and a depth camera carried by the unmanned aerial vehicle, and the method comprises the following steps: and a software framework based on ROS is used, and a laser SLAM algorithm is adopted, so that the problem of mapping and positioning of the unmanned aerial vehicle is solved. A Cartogrer algorithm is adopted in a mapping algorithm, loop detection is added to the algorithm based on a graph optimization framework to eliminate accumulated errors, and the algorithm can be used for an unmanned aerial vehicle to construct a two-dimensional grid map.
3. The method adopts the YOLOV3 algorithm to identify the garbage, so that the accuracy and the reliability of identification are ensured.
Drawings
The invention is further illustrated by the following figures and examples.
Fig. 1 is an overall structure diagram of the unmanned aerial vehicle of the present invention.
Fig. 2 is an overall configuration diagram of the unmanned ship of the present invention.
Fig. 3 is an overall block diagram of the system of the present invention.
Fig. 4 shows a method for positioning an unmanned ship according to the present invention.
FIG. 5 illustrates an embodiment of the present invention.
In the figure: a GPS module 101, a battery compartment 102, an onboard computer 103, a first depth camera 104, a lidar 105;
a robotic arm 201, a waste storage bin 202, a two-dimensional lidar 203, a second depth camera 204.
Detailed Description
Embodiments of the present invention will be further described with reference to the accompanying drawings.
Example 1:
referring to fig. 1-5, a water surface floating garbage removing device with cooperation of an unmanned aerial vehicle and an unmanned ship comprises the unmanned aerial vehicle and the unmanned ship; the unmanned aerial vehicle builds a map of a target water area and identifies water surface garbage, the ground workstation transmits garbage coordinate information to each unmanned ship, the unmanned ship plans a global path of a water area in charge of the unmanned ship to reach a garbage point, and the garbage is picked up through a mechanical arm; the device also comprises a control system which is divided into three layers: a management layer, a communication layer and a control execution layer; the management layer is a ground workstation and is used for controlling, visualizing and operating the integral structure of the unmanned aerial vehicle and the integral structure of the unmanned ship; the communication layer mainly transmits the running state of the unmanned aerial vehicle unmanned ship to the ground workstation through WIFI data transmission; the control layer mainly acquires environmental data and receives a control instruction of the management layer. Through foretell clear away equipment, its realization frame is based on open source robot operating system ROS and is found the picture and discern surface of water rubbish to the target waters through unmanned aerial vehicle, and ground workstation sends rubbish coordinate information to each unmanned ship, and unmanned ship carries out global path planning to oneself responsible for the waters and reachs the rubbish point, picks up rubbish through the robotic arm.
Further, the unmanned aerial vehicle is provided with an on-board computer 103, a first depth camera 104, a first laser radar 105, a GPS module 101, a PX4 open-source flight control device, a WIFI data transmission device and a charging and discharging device; the on-board computer 103 receives the first depth camera 104 and first lidar 105 information, as well as control instructions; the first depth camera 104 acquires information of floating garbage on the water surface, including garbage category and position information; the first laser radar 105 acquires surrounding environment information and performs positioning and mapping by matching with an SLAM algorithm; the GPS module 101 realizes the positioning of the unmanned aerial vehicle; WIFI data transmission is used for communication between unmanned aerial vehicle overall structure and unmanned ship overall structure.
Further, the unmanned ship is provided with a mechanical arm 201, a garbage storage device, a driving device, a WIFI data transmission module, a high-precision inertial navigation module, a second laser radar 203, a GPS module, an onboard computer and a second depth camera 204; the mechanical arm 201 picks up the garbage; the high-precision inertial navigation module and the GPS module perform position and speed fusion in an extended Kalman filtering loose coupling mode, wherein the high-precision inertial navigation module comprises a speed acceleration, an angular speed and a yaw angle, the position and the speed are obtained by resolving through an inertial system, the GPS module resolves the position and the speed through a navigation system, data fusion is performed through extended Kalman filtering, and finally, the position and the speed are output after the output result is subjected to feedback correction; the second laser radar 203 acquires surrounding environment information and performs positioning navigation by matching with an SLAM algorithm; the GPS module provides positioning for the unmanned ship; the depth camera identifies spam information, including spam category and location information.
Further, unmanned aerial vehicle's location is built the picture and is discerned rubbish and include: the unmanned aerial vehicle carries out mapping positioning through the SLAM technology, a target water area two-dimensional grid map is established through a SLAM framework Cartogrier algorithm based on map optimization, floating garbage in a water area is identified through a deep learning YOLOV3 algorithm in the mapping process, XYZ coordinates are calculated according to point cloud information in an identification frame, the XYZ coordinates are converted into a world coordinate system, and the world coordinate system is sent to the unmanned ship through a workstation. The Cartogrer algorithm is a set of graph optimization-based Laser SLAM algorithm, supports 2D and 3D Laser SLAM simultaneously, can be used in a cross-platform mode, and supports various sensor configurations such as Laser, IMU, radiometer and GPS. The algorithm can realize real-time positioning and mapping. In addition, the algorithm is based on a graph optimization framework, loop detection is added, accumulated errors are eliminated, and the algorithm can be used for the unmanned aerial vehicle to construct a two-dimensional grid map. The accuracy of garbage identification is guaranteed by adopting a YOLOV3 algorithm.
Further, coordinate transformation of the unmanned aerial vehicle and the unmanned ship is carried out, the motion of the unmanned aerial vehicle is three-dimensional space rigid motion, the first depth camera 104 coordinate of the unmanned aerial vehicle is transformed to be under a base mark of the unmanned aerial vehicle, and finally the first depth camera is transformed to be under a world coordinate system; the motion of the unmanned ship in the plane can be regarded as rigid motion, the rigid motion is converted into a world coordinate system through homogeneous coordinate transformation, and the unmanned ship of the unmanned plane is located in the world coordinate system. Through the coordinate transformation, subsequent path planning is facilitated.
Further, unmanned aerial vehicle, unmanned ship and workstation's communication, unmanned aerial vehicle, unmanned ship and workstation constitute in this communication system, and the workstation belongs to the main control computer, and unmanned aerial vehicle and unmanned ship are as following the machine, connect through the WIFI LAN between the three, and the main control computer is responsible for controlling unmanned aerial vehicle and unmanned ship, mainly realizes: the unmanned aerial vehicle and the unmanned ship realize the transmission of images and the interaction of environmental information. By the communication mode, the reliability of communication among the three is ensured.
Furthermore, the unmanned ship is positioned, the position of the unmanned ship in a map is mainly obtained, the unmanned ship is influenced by wind speed waves when sailing on the water surface, so that the unmanned ship is positioned in an offset mode, the high-precision inertial navigation module and the GPS module are combined to perform global positioning, the state errors of the inertial navigation module and the GPS module are estimated in an expanded Kalman filtering loose coupling mode, and the navigation systems are corrected through feedback through estimation of the state errors, so that the positioning precision is improved. Through the positioning mode, the unmanned ship can be accurately positioned in a dynamic environment.
Further, planning a path of the unmanned ship, dividing a two-dimensional grid map and areas by the ground workstation, acquiring a world coordinate system of each unmanned ship, and obtaining a garbage coordinate relation of a water area in which the unmanned ship is responsible through coordinate transformation; the unmanned ship carries out path planning from near to far according to the received garbage coordinate information of the water area in which the unmanned ship is responsible, global path planning is carried out by using an A-star algorithm in navigation, and the optimal route from the unmanned ship to the target position is calculated. The A-algorithm is a most effective direct search method for solving the shortest path in the static road network, and is also an effective algorithm for solving a plurality of search problems. The closer the distance estimation value in the algorithm is to the actual value, the faster the final search speed is. And further, the optimal path planning of the unmanned ship can be rapidly realized.
Further, the garbage picking of the mechanical arm mainly comprises the steps of performing target detection on the floating garbage on the water surface by using point cloud generated by the second depth camera 204 after the garbage reaches the position, calculating cloud coordinates of points in the identification frame, converting the acquired garbage coordinates into a mechanical arm coordinate system, and starting motion planning and grabbing by the mechanical arm. The mechanical arm is planned to move through a Moveit function package based on the ROS frame, and garbage is picked up. The Moveit is the most advanced software aiming at the mobile operation at present. It combines the latest advances in motion planning, manipulation, three-dimensional perception, kinematics, control and navigation.
Example 2:
the operation method of the water surface floating garbage removing equipment with the cooperation of the unmanned aerial vehicle and the unmanned ship comprises the following steps:
s1 is started;
s2, enabling the unmanned aerial vehicle unmanned ship to reach a target water area:
step A1: the unmanned ship unmanned aerial vehicle reaches a target water area;
step A2: checking the surrounding environment of the target water area;
s3, the unmanned aerial vehicle unmanned ship stops still, and wireless communication is established with the ground workstation:
step B1: starting an unmanned ship, an unmanned aerial vehicle and a ground workstation;
and step B2: checking the running condition of the equipment;
and step B3: inputting an IP address and establishing communication among the three through WIFI data transmission;
s4, drawing the SLAM of the target water area according to a planned route, and identifying garbage:
step C1: vertically lifting the unmanned aerial vehicle to a proper height;
and step C2: starting SLAM map building, and building a two-dimensional grid map by adopting a Cartogrph algorithm;
and C3: identifying the floating garbage on the water surface through a first depth camera by using a deep learning YOLOV3 algorithm while establishing a map;
s5, returning by the unmanned aerial vehicle:
step D1: the unmanned aerial vehicle returns to the ground workstation with the acquired garbage coordinate information and the two-dimensional map;
s6, dividing the target water area by the ground station according to the number of unmanned ships, wherein one ship is responsible for one water area:
step E1: processing a two-dimensional map and garbage coordinate information established by the unmanned aerial vehicle;
and E2: reasonably dividing the responsible water area of each ship according to the map, the number of ships and the water area environment;
s7, converting the coordinates of the identified garbage into the world coordinate system:
step F1: converting the garbage coordinate calculated by the unmanned aerial vehicle into a world coordinate system by the ground workstation;
step F2: converting the coordinate system of the unmanned ship into a world coordinate system by the ground workstation;
step F3: transmitting the garbage coordinates under each area to an unmanned ship in charge of the area;
s8, global path planning is carried out for the garbage coordinate traversal of the water area in charge of each ship:
step G1: receiving garbage coordinate information under a world coordinate system by the unmanned ship;
step G2: setting a navigation point from near to far according to the garbage coordinate information;
step G3: carrying out global path planning according to the grid map, and finding out an optimal path through an A-star algorithm;
s9, enabling the unmanned ship to reach a target point:
step H1: the unmanned ship sequentially goes to the areas where the garbage are located according to the planned route obtained in the S8;
s10, if the in-place rotation searching target is not identified by identifying the garbage:
step I1: when the unmanned ship reaches the region where the water surface floating garbage is located, the unmanned ship identifies the garbage by using a YOLOV3 target identification algorithm;
step I2: if the garbage is not identified, the unmanned ship rotates in situ to search for a target;
s11, mechanical arm grabbing:
step J1: identifying a target, processing point cloud information in an identification frame, acquiring garbage coordinate information, and calculating coordinates of garbage relative to the mechanical arm through coordinate conversion;
step J2: moveit is adopted to plan a mechanical arm movement route, and a mechanical arm clamping jaw moves to reach a garbage position for grabbing;
s12 is heading to an unscanned area:
step K1: after the work of the area is finished, carrying the unmanned plane with the unmanned ship to work in the next subarea, and repeating the steps S3-S11;
step K2: if the cleaning work of all the areas is completed, S13 is performed, and the work is finished.
And S13 is finished.
Claims (3)
1. The utility model provides an unmanned aerial vehicle and unmanned ship collaborative surface of water floats rubbish and clears away equipment which characterized in that: the unmanned aerial vehicle comprises an unmanned aerial vehicle and an unmanned ship;
the unmanned aerial vehicle builds a map of a target water area and identifies water surface garbage, the ground workstation transmits garbage coordinate information to each unmanned ship, the unmanned ship carries out global path planning on a water area in charge of the unmanned ship to reach a garbage point, and the garbage is picked up through a mechanical arm;
the device also comprises a control system, wherein the control system is divided into three layers: a management layer, a communication layer and a control execution layer; the management layer is a ground workstation and is used for controlling, visualizing and operating the integral structure of the unmanned aerial vehicle and the integral structure of the unmanned ship; the communication layer mainly transmits the running state of the unmanned aerial vehicle unmanned ship to the ground workstation through WIFI data transmission; the control layer mainly acquires environmental data and receives a control instruction of the management layer;
the unmanned aerial vehicle is provided with an on-board computer (103), a first depth camera (104), a first laser radar (105), a GPS module (101), a PX4 open source flight control device, a WIFI data transmission device and a charging and discharging device;
the on-board computer (103) receiving first depth camera (104) and first lidar (105) information, and control instructions; a first depth camera (104) acquires information of floating garbage on the water surface, wherein the information comprises garbage category and position information; a first laser radar (105) acquires surrounding environment information and performs positioning and mapping by matching with an SLAM algorithm; the GPS module (101) realizes the positioning of the unmanned aerial vehicle; the WIFI data transmission is used for communication between the integral structure of the unmanned aerial vehicle and the integral structure of the unmanned ship;
the unmanned ship is provided with a mechanical arm (201), a garbage storage device, a driving device, a WIFI data transmission, a high-precision inertial navigation module, a second laser radar (203), a GPS module, an onboard computer and a second depth camera (204);
the mechanical arm (201) picks up the garbage; the high-precision inertial navigation module and the GPS module perform position and speed fusion in an extended Kalman filtering loose coupling mode, wherein the high-precision inertial navigation module comprises a speed acceleration, an angular speed and a yaw angle, the position and the speed are obtained by resolving through an inertial system, the GPS module resolves the position and the speed through a navigation system, data fusion is performed through extended Kalman filtering, and finally, the output result is subjected to feedback correction and then the position and the speed are output; the second laser radar (203) acquires surrounding environment information and performs positioning navigation by matching with an SLAM algorithm; the GPS module provides positioning for the unmanned ship; the depth camera identifies spam information, including spam category and location information;
unmanned aerial vehicle's location is built the picture and is discerned including rubbish: the unmanned aerial vehicle carries out mapping positioning through a SLAM technology, a target water area two-dimensional grid map is established by adopting a SLAM framework Cartogrier algorithm based on map optimization, floating garbage in a water area is identified by using a deep learning YOLOV3 algorithm in the mapping process, XYZ coordinates are calculated according to point cloud information in an identification frame, the point cloud information is converted into a world coordinate system, and the world coordinate system is sent to the unmanned ship through a workstation;
converting coordinates of the unmanned aerial vehicle and the unmanned ship, converting the coordinates of a first depth camera (104) of the unmanned aerial vehicle into a base mark of the unmanned aerial vehicle when the unmanned aerial vehicle moves rigidly in a three-dimensional space, and finally converting the coordinates into a world coordinate system; the motion of the unmanned ship in the plane can be regarded as rigid motion, the rigid motion is converted into a world coordinate system through homogeneous coordinate transformation, and the unmanned ship of the unmanned plane is positioned in the world coordinate system;
unmanned aerial vehicle, unmanned ship and workstation's communication, unmanned aerial vehicle, unmanned ship and workstation constitute in this communication system, and the workstation belongs to the main control computer, and unmanned aerial vehicle and unmanned ship are as the machine of following, connect through the WIFI LAN between the three, and the main control computer is responsible for controlling unmanned aerial vehicle and unmanned ship, mainly realizes: the unmanned aerial vehicle and the unmanned ship realize image transmission and interaction of environmental information;
positioning of the unmanned ship, mainly obtaining the position of the unmanned ship in a map, leading the positioning of the unmanned ship to generate deviation due to the influence of wind speed waves when the unmanned ship sails on the water surface, adopting a high-precision inertial navigation module and a GPS module to carry out global positioning, adopting an extended Kalman filtering loose coupling mode to estimate the state errors of the inertial navigation module and the GPS module, correcting each navigation system through feedback through estimation of the state errors, and improving the positioning precision;
planning the path of the unmanned ship, dividing a two-dimensional grid map and areas by a ground workstation, acquiring a world coordinate system of each unmanned ship, and obtaining a garbage coordinate relation of a water area in which the unmanned ship is responsible through coordinate transformation; the unmanned ship carries out path planning from near to far according to the received garbage coordinate information of the water area in which the unmanned ship is responsible, carries out global path planning by using an A-star algorithm in navigation, and calculates the optimal path from the unmanned ship to the target position.
2. The unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment as claimed in claim 1, wherein: the garbage picking of the mechanical arm mainly comprises the steps of using a point cloud generated by a second depth camera (204) after the garbage reaches a position, carrying out target detection on the floating garbage on the water surface, calculating cloud coordinates of points in a recognition frame, converting the acquired garbage coordinates into a mechanical arm coordinate system, and starting motion planning and grabbing by the mechanical arm.
3. The method of operating a surface floating debris removal installation with a drone and an unmanned ship in combination as claimed in any one of claims 1 to 2, comprising the steps of:
s1 is started;
s2, enabling the unmanned aerial vehicle unmanned ship to reach a target water area;
s3, the unmanned aerial vehicle unmanned ship stops statically, and wireless communication is established with a ground workstation;
s4, drawing an SLAM of the target water area according to a planned route, and identifying garbage;
s5, returning by the unmanned aerial vehicle;
s6, dividing the target water area by the ground station according to the number of unmanned ships, wherein one ship is responsible for one water area;
s7, converting the identified garbage coordinates into a world coordinate system;
s8, performing global path planning for the garbage coordinate traversal of each ship in charge of the water area;
s9, enabling the unmanned ship to arrive at a target point;
s10, if the rubbish is identified, an in-place rotation searching target is not identified;
s11, mechanical arm grabbing;
s12, heading to an unscanned area;
s13 is the end;
the specific process of S2 is as follows:
step A1: the unmanned ship unmanned aerial vehicle reaches a target water area;
step A2: checking the surrounding environment of the target water area;
the specific process of S3 is as follows:
step B1: starting an unmanned ship, an unmanned aerial vehicle and a ground workstation;
and step B2: checking the running condition of the equipment;
and step B3: inputting an IP address and establishing communication among the three through WIFI data transmission;
the specific process of S4 is as follows:
step C1: vertically lifting the unmanned aerial vehicle to a proper height;
and step C2: starting SLAM map building, and building a two-dimensional grid map by adopting a Cartogrer algorithm;
and C3: identifying the floating garbage on the water surface through a first depth camera by using a deep learning YOLOV3 algorithm while establishing a map;
the specific process of S5 is as follows:
step D1: the unmanned aerial vehicle returns to the ground workstation with the acquired garbage coordinate information and the two-dimensional map;
the specific process of S6 is as follows:
step E1: processing a two-dimensional map and garbage coordinate information established by the unmanned aerial vehicle;
step E2: reasonably dividing the responsible water area of each ship according to the map, the number of ships and the water area environment;
the specific process of S7 is as follows:
step F1: converting the garbage coordinate calculated by the unmanned aerial vehicle into a world coordinate system by the ground workstation;
step F2: converting the coordinate system of the unmanned ship into a world coordinate system by the ground workstation;
step F3: transmitting the garbage coordinates of each region to an unmanned ship in charge of the region;
the specific process of S8 is as follows:
step G1: receiving garbage coordinate information under a world coordinate system by the unmanned ship;
step G2: setting a navigation point from near to far according to the garbage coordinate information;
step G3: carrying out global path planning according to the grid map, and finding out an optimal path through an A-star algorithm;
the specific process of S9 is as follows:
step H1: the unmanned ship sequentially goes to the areas where the garbage are located according to the planned route obtained in the S8;
the S10 specific process:
step I1: when the unmanned ship reaches the region where the water surface floating garbage is located, the unmanned ship identifies the garbage by using a YOLOV3 mesh identification algorithm;
step I2: if the garbage is not identified, the unmanned ship rotates in situ to search for the target;
the specific process of S11:
step J1: identifying a target, processing point cloud information in an identification frame, acquiring garbage coordinate information, and calculating coordinates of garbage relative to the mechanical arm through coordinate conversion;
step J2: moveit is adopted to plan a mechanical arm movement route, and a mechanical arm clamping jaw moves to reach a garbage position to grab;
the specific process of S12 is as follows:
step K1: after the work of the area is finished, carrying the unmanned ship unmanned aerial vehicle to work in the next sub-area, and repeating the steps S3-S11;
step K2: if the cleaning work of all the areas is completed, S13 is performed, and the work is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210246232.XA CN114537666B (en) | 2022-03-14 | 2022-03-14 | Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210246232.XA CN114537666B (en) | 2022-03-14 | 2022-03-14 | Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114537666A CN114537666A (en) | 2022-05-27 |
| CN114537666B true CN114537666B (en) | 2023-02-21 |
Family
ID=81664044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210246232.XA Active CN114537666B (en) | 2022-03-14 | 2022-03-14 | Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114537666B (en) |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107117268B (en) * | 2017-05-12 | 2019-04-30 | 西南科技大学 | A kind of the ocean rubbish recovering method and system of heterogeneous system |
| CN108287542B (en) * | 2018-01-04 | 2021-01-26 | 浙江大学 | Unmanned aerial vehicle and unmanned ship cooperative control system and method based on cooperative cloud control |
| US20210405654A1 (en) * | 2018-03-22 | 2021-12-30 | Infinium Robotics Pte Ltd | Autonomous taking off, positioning and landing of unmanned aerial vehicles (uav) on a mobile platform |
| CN110096056A (en) * | 2019-04-08 | 2019-08-06 | 三峡大学 | A kind of intelligent vehicle detection system and its control method based on unmanned aerial vehicle platform |
| CN110758658A (en) * | 2019-11-08 | 2020-02-07 | 湘潭大学 | Method for cleaning water surface floating garbage by using unmanned aerial vehicle and unmanned ship in cooperation |
| KR102452044B1 (en) * | 2020-08-28 | 2022-10-07 | 금오공과대학교 산학협력단 | USV-UAV Collaboration for Development of Marine Environment |
| CN112278170B (en) * | 2020-10-06 | 2021-12-07 | 武汉烽火凯卓科技有限公司 | Unmanned aerial vehicle and unmanned ship cooperative water area cleaning method and system |
| CN214150420U (en) * | 2020-12-08 | 2021-09-07 | 南京信息工程大学 | Unmanned aerial vehicle unmanned ship is water installation in coordination |
| CN215622702U (en) * | 2021-08-26 | 2022-01-25 | 浙江安防职业技术学院 | Intelligent cleaning system for water surface garbage |
-
2022
- 2022-03-14 CN CN202210246232.XA patent/CN114537666B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114537666A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Map-based localization method for autonomous vehicles using 3D-LIDAR | |
| Cantelli et al. | UAV/UGV cooperation for surveying operations in humanitarian demining | |
| CN102998679B (en) | GIS (Geographic Information System) data acquisition method applied to unmanned vehicle | |
| CN111982114B (en) | Rescue robot for estimating three-dimensional pose by adopting IMU data fusion | |
| WO2015180021A1 (en) | Pruning robot system | |
| CN108645420B (en) | Method for creating multipath map of automatic driving vehicle based on differential navigation | |
| CN103869824A (en) | Biological antenna model-based multi-robot underwater target searching method and device | |
| CN110749895B (en) | Laser radar point cloud data-based positioning method | |
| EP3799618B1 (en) | Method of navigating a vehicle and system thereof | |
| CN114332360A (en) | Collaborative three-dimensional mapping method and system | |
| EP4042105B1 (en) | Map including data for routing aerial vehicles during gnss failure | |
| CN113050685B (en) | Autonomous inspection method for underground unmanned aerial vehicle of coal mine | |
| CN110926485A (en) | Mobile robot positioning method and system based on linear features | |
| Liu et al. | An enhanced lidar inertial localization and mapping system for unmanned ground vehicles | |
| Kim et al. | Autonomous mobile robot localization and mapping for unknown construction environments | |
| CN107255446B (en) | Dwarfing close-planting fruit tree canopy three-dimensional map construction system and method | |
| CN116540706A (en) | System and method for providing local path planning for ground unmanned aerial vehicle by unmanned aerial vehicle | |
| CN114537666B (en) | Unmanned aerial vehicle and unmanned ship cooperative water surface floating garbage removing equipment and operation method | |
| US20220269281A1 (en) | Method and system for generating a topological graph map | |
| CN115049825B (en) | Water surface cleaning method, device, equipment and computer readable storage medium | |
| CN113741425B (en) | Full-coverage path planning method and navigation system | |
| CN115790571A (en) | Simultaneous positioning and map construction method based on mutual observation of heterogeneous unmanned system | |
| CN112614171B (en) | Air-ground integrated dynamic environment sensing system for engineering machinery cluster operation | |
| CN114353799A (en) | Indoor rapid global positioning method for unmanned platform carrying multi-line laser radar | |
| CN115328122A (en) | Unmanned ship obstacle avoidance method and system based on multi-radar sensing |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221019 Address after: 443300 Shilipu Industrial Park, Lucheng, Yidu City, Yichang City, Hubei Province (West of the city) Applicant after: HUBEI TIANYI MACHINERY Co.,Ltd. Address before: 443002 No. 8, University Road, Xiling District, Yichang, Hubei Applicant before: CHINA THREE GORGES University |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A Water Surface Floating Garbage Removal Equipment and Operation Method for Cooperation between Unmanned Aerial Vehicles and Unmanned Ships Effective date of registration: 20230830 Granted publication date: 20230221 Pledgee: Hubei Yidu Rural Commercial Bank Co.,Ltd. Pledgor: HUBEI TIANYI MACHINERY Co.,Ltd. Registration number: Y2023980054449 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |