CN110661541A - Underwater robot positioning evaluation system based on machine learning - Google Patents
Underwater robot positioning evaluation system based on machine learning Download PDFInfo
- Publication number
- CN110661541A CN110661541A CN201910843177.0A CN201910843177A CN110661541A CN 110661541 A CN110661541 A CN 110661541A CN 201910843177 A CN201910843177 A CN 201910843177A CN 110661541 A CN110661541 A CN 110661541A
- Authority
- CN
- China
- Prior art keywords
- electromagnetic wave
- machine learning
- underwater
- underwater robot
- wireless transceiver
- 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.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63C—LAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
- B63C11/00—Equipment for dwelling or working underwater; Means for searching for underwater objects
- B63C11/52—Tools specially adapted for working underwater, not otherwise provided for
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B1/00—Details of transmission systems, not covered by a single one of groups H04B3/00 - H04B13/00; Details of transmission systems not characterised by the medium used for transmission
- H04B1/38—Transceivers, i.e. devices in which transmitter and receiver form a structural unit and in which at least one part is used for functions of transmitting and receiving
- H04B1/40—Circuits
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Manipulator (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mechanical Engineering (AREA)
- Ocean & Marine Engineering (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
Abstract
The invention belongs to the field of research and development and testing of underwater robots, and provides an underwater robot positioning evaluation system based on machine learning. The underwater electromagnetic wave communication module comprises an electromagnetic wave receiver, an electromagnetic wave emitter, a data transceiving line and a microcontroller, wherein the microcontroller is connected with the wireless transceiver a through the data transceiving line; the overwater wireless communication module consists of a wireless transceiver a and a wireless transceiver b, the background monitoring module consists of a monitor, and the monitor and the wireless transceiver b are directly connected through a wire; the underwater robot position evaluation system evaluates the position of the underwater robot by the robot, when the underwater robot reaches the position close to the target place, the underwater robot can be quickly and efficiently received by the underwater electromagnetic wave communication module, whether the underwater robot reaches the target place is quickly analyzed through a machine learning algorithm, a judge and a judge are not required to watch a screen for a long time, and meanwhile, the underwater robot position evaluation system is not influenced by impurities in the underwater environment.
Description
Technical Field
The invention belongs to the field of research and development and testing of underwater robots, and particularly relates to an underwater robot positioning evaluation system based on machine learning.
Background
The coastline of China is 1.8 kilometers in length and occupies the fourth place in the world; the area of the continental shelf is the fifth of the world, the area of a 200-nautical exclusive economic area is the tenth of the world, marine resources are still in a preliminary development stage, the land resources begin to be in shortage along with the gradual saturation of the development of the land resources, and various coastal countries throw attention to the ocean, so that the research, development and utilization of the ocean, particularly the research, development and test of underwater robots are accelerated. Meanwhile, many colleges and institutions in China organize underwater robot related matches to promote research and development of the underwater robots in China. One classic item in many underwater robot competition items is fixed-point detection, namely, the underwater robot moves to a specified place, and in the process, whether the underwater robot reaches a specified position needs to be judged. The judgment method adopted at present mainly comprises the steps of carrying out naked eye judgment by using an underwater camera, and judging by a judge through a picture transmitted back by the underwater camera when an underwater robot appears in a pre-arranged mark place. The method needs a judge to observe the screen for a long time, and needs a lot of spirits and attention, and is seriously interfered by the underwater environment, once impurities appear in the underwater environment and are close to the underwater camera, the method greatly influences the evaluation work, thereby possibly influencing the fairness of the competition. Therefore, a new evaluation method is needed to make up for the defects of the currently used evaluation.
Disclosure of Invention
To meet the needs in the technical background, the present invention provides a machine learning based underwater robot positioning assessment system.
The technical scheme of the invention is as follows:
an underwater robot positioning evaluation system based on machine learning mainly comprises an underwater electromagnetic wave communication module 1, an overwater wireless communication module 2 and a background monitoring module 3;
the underwater electromagnetic wave communication module 1 mainly comprises an electromagnetic wave receiver 4, an electromagnetic wave emitter 5, a data transceiving line 6 and a microcontroller 10, wherein the microcontroller 10 is connected with a wireless transceiver a7 through the data transceiving line 6, and the microcontroller 10 and the electromagnetic wave receiver 4 are sealed into a whole and are connected through a lead for communication and used for receiving the electromagnetic wave emitted by the electromagnetic wave emitter 5;
the water wireless communication module 2 mainly comprises a wireless transceiver a7 and a wireless transceiver b 8;
the background monitoring module 3 is composed of a monitor 9, and the monitor 9 and the wireless transceiver b8 are directly connected through a wire.
The electromagnetic wave emitter 5 is mounted on the underwater robot in actual work, is driven by the underwater robot, moves along with the underwater robot and emits electromagnetic wave signals continuously.
The wireless transceiver a7 and the wireless transceiver b8 support broadband communication, when the communication is not carried out, the wireless transceiver a7 and the wireless transceiver b8 are in a sleep mode, the wireless transceiver a7 and the wireless transceiver b8 need to be activated before the communication, and the sleep mode is changed into the working mode for the communication.
The electromagnetic wave transmitter 5 supports multi-band communication, the communication distance is controllable, and the maximum underwater environment communication can reach 30 cm.
The microcontroller 10 processes signals of the electromagnetic wave receiver 4 through a programmed machine learning algorithm, the model used by the machine learning algorithm is a double-layer neural network model, the training set used by the machine learning algorithm is electromagnetic wave signals sent by the electromagnetic wave transmitter 5 in an underwater environment and received by the electromagnetic wave receiver 4, the number of the training sets is 10000, and the test accuracy of the machine algorithm model obtained after the training is more than 97%.
The invention has the following beneficial effects: the system is designed in a modularized way, and is convenient to move and assemble; the underwater robot position evaluation system evaluates the position of the underwater robot by the robot, when the underwater robot reaches the position close to a target place, the underwater robot can be quickly and efficiently received by the underwater electromagnetic wave communication module 1, whether the underwater robot reaches the target place is quickly analyzed according to a trained machine learning algorithm model, a judge and judge are not needed to watch a screen for a long time, and meanwhile, the underwater robot position evaluation system is not influenced by impurities of an underwater environment.
Drawings
FIG. 1 is a block diagram of the system;
FIG. 2 is a schematic diagram of the system;
in the figure: 1, an underwater electromagnetic wave communication module; 2, a water wireless communication module; 3 a posterior monitoring module; 4 an electromagnetic wave receiver; 5 an electromagnetic wave emitter; 6, data receiving and transmitting lines; 7, a wireless transceiver a; 8, a wireless transceiver b; 9 monitor, 10 microcontroller
Detailed Description
The following further describes the specific embodiments of the present invention with reference to the technical solutions and the drawings of the specification.
An underwater robot positioning evaluation system based on machine learning mainly comprises an underwater electromagnetic wave communication module 1, an overwater wireless communication module 2 and a background monitoring module 3; the underwater electromagnetic wave communication module 1 mainly comprises an electromagnetic wave receiver 4, an electromagnetic wave emitter 5, a data transceiving line 6 and a microcontroller 10, wherein the microcontroller 10 is connected with a wireless transceiver a7 through the data transceiving line 6; the microcontroller 10 and the electromagnetic wave receiver 4 are sealed into a whole and are connected for communication through a lead; the overwater wireless communication module 2 consists of a wireless transceiver a7 and a wireless transceiver b8, the background monitoring module 3 consists of a monitor 9, and the monitor 9 and the wireless transceiver b8 are directly connected through wires;
in the implementation process, an electromagnetic wave emitter 5 with power adjusted according to requirements to enable the maximum transmission length of the emitted electromagnetic waves to be 30cm is mounted on the underwater robot, the underwater robot supplies power to drive the electromagnetic wave emitter 5, and the underwater robot drives the electromagnetic wave emitter 5 to move together in the underwater movement process; the electromagnetic wave signal transmitted by the electromagnetic wave transmitter 5 consists of communication protocol header information and label information of the mounted underwater robot.
In an actual working environment, since a large amount of ions exist in seawater, the conductivity is strong, the attenuation effect on electromagnetic waves is obvious, the attenuation effects on electromagnetic waves of seawater in different regions are different, and the process of converting electromagnetic waves received by the electromagnetic wave receiver 4 and the microcontroller 10 into digital signals needs to be subjected to noise reduction analysis according to an actual working place. The method comprises the steps of carrying out field test in an actual working environment to collect electromagnetic wave signals which are received by an electromagnetic wave receiver 4 and transmitted by electromagnetic wave transmitters 5 within 30cm and different distances, using the data as a training set to train a machine learning algorithm, wherein the training algorithm uses a double-layer neural network algorithm to extract the characteristics of the electromagnetic wave signals received in the underwater environment, obtaining an electromagnetic wave signal processing algorithm result model in the working environment through 10000 data volume training, programming the algorithm result model into a microcontroller 10, and substituting the received electromagnetic wave signals into the algorithm result model to quickly distinguish whether the electromagnetic wave signals are transmitted by the electromagnetic wave transmitters 5 carried by the underwater robot.
When the distance between the electromagnetic transmitter 5 mounted on the underwater robot and the electromagnetic wave receiver 4 is less than 30cm, the electromagnetic wave transmitted by the electromagnetic wave transmitter 5 is received by the electromagnetic wave receiver 4 to the electromagnetic wave signal transmitted by the electromagnetic wave transmitter 5, the electromagnetic wave receiver 4 analyzes the digital signal through the machine learning algorithm programmed by the microcontroller 10, and when the received electromagnetic wave signal is matched with the characteristics of the machine learning algorithm, the digital signal is transmitted to the wireless transceiver a7 through the data transmitting and receiving wire 6.
The wireless transceiver a7 is activated to switch from the sleep mode to the working mode after receiving the information from the electromagnetic wave receiver 4, and simultaneously transmits information to activate the wireless transceiver b8, the wireless transceiver b8 transmits a response signal to the wireless transceiver a6 after switching from the sleep mode to the working mode, and the wireless transceiver a6 starts to wirelessly transmit information after receiving the response signal from the wireless transceiver b 7.
After receiving the information sent by the wireless transceiver a6, the wireless transceiver b7 sends the information to a monitor directly connected with the underwater robot, and the monitor analyzes the received information and displays the information on a screen to represent that the underwater robot in competition arrives at the target place.
Claims (8)
1. An underwater robot positioning evaluation system based on machine learning is characterized in that the underwater robot positioning evaluation system based on machine learning mainly comprises an underwater electromagnetic wave communication module (1), an above-water wireless communication module (2) and a background monitoring module (3);
the underwater electromagnetic wave communication module (1) mainly comprises an electromagnetic wave receiver (4), an electromagnetic wave emitter (5), a data transmitting and receiving line (6) and a microcontroller (10), wherein the microcontroller (10) is connected with a wireless transceiver a (7) through the data transmitting and receiving line (6), and the microcontroller (10) and the electromagnetic wave receiver (4) are sealed into a whole and are connected for communication through a lead and used for receiving electromagnetic waves emitted by the electromagnetic wave emitter (5);
the overwater wireless communication module (2) mainly comprises a wireless transceiver a (7) and a wireless transceiver b (8);
the background monitoring module (3) is composed of a monitor (9), and the monitor (9) and the wireless transceiver b (8) are directly connected through a wire.
2. The underwater robot positioning evaluation system based on machine learning of claim 1, wherein the electromagnetic wave transmitter (5) is mounted on the underwater robot in actual operation, is driven by the underwater robot, moves along with the underwater robot, and transmits electromagnetic wave signals uninterruptedly.
3. The system according to claim 1 or 2, wherein the wireless transceiver a (7) and the wireless transceiver b (8) support broadband communication, the wireless transceiver a (7) and the wireless transceiver b (8) are in a sleep mode when not communicating, and the wireless transceiver a (7) and the wireless transceiver b (8) need to be activated before communication, and the sleep mode is changed into the working mode for communication.
4. The underwater robot positioning evaluation system based on machine learning of claim 1 or 2, characterized in that the electromagnetic wave transmitter (5) supports multi-band communication, the communication distance is controllable, and the underwater environment communication can reach 30cm at most.
5. The underwater robot positioning evaluation system based on machine learning of claim 3, characterized in that the electromagnetic wave transmitter (5) supports multi-band communication, the communication distance is controllable, and the underwater environment communication can reach up to 30 cm.
6. The underwater robot positioning evaluation system based on machine learning of claim 1, 2 or 5, characterized in that the microcontroller (10) processes signals of the electromagnetic wave receiver (4) through a machine learning algorithm after programming, the model used by the machine learning algorithm is a double-layer neural network model, the training set used by the machine learning algorithm is electromagnetic wave signals received by the electromagnetic wave receiver (4) sent by the electromagnetic wave transmitter (5) in the underwater environment, the number of the training sets is 10000, and the accuracy of the test of the model result of the machine algorithm obtained through the training is more than 97%.
7. The underwater robot positioning evaluation system based on machine learning of claim 3, characterized in that the microcontroller (10) processes signals of the electromagnetic wave receiver (4) through a machine learning algorithm after programming, the model used by the machine learning algorithm is a double-layer neural network model, the training set used by the machine learning algorithm is the electromagnetic wave signals sent by the electromagnetic wave transmitter (5) in the underwater environment and received by the electromagnetic wave receiver (4), the number of the training sets is 10000, and the accuracy of the test of the model result of the machine algorithm obtained through the training is more than 97%.
8. The underwater robot positioning evaluation system based on machine learning of claim 4, characterized in that the microcontroller (10) processes signals of the electromagnetic wave receiver (4) through a machine learning algorithm of programming, the model used by the machine learning algorithm is a double-layer neural network model, the training set used by the machine learning algorithm is the electromagnetic wave signals sent by the electromagnetic wave transmitter (5) in the underwater environment and received by the electromagnetic wave receiver (4), the number of the training sets is 10000, and the accuracy of the test of the model result of the machine algorithm obtained after the training is more than 97%.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910843177.0A CN110661541B (en) | 2019-09-06 | 2019-09-06 | Underwater robot positioning evaluation system based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910843177.0A CN110661541B (en) | 2019-09-06 | 2019-09-06 | Underwater robot positioning evaluation system based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110661541A true CN110661541A (en) | 2020-01-07 |
CN110661541B CN110661541B (en) | 2021-03-26 |
Family
ID=69037994
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910843177.0A Active CN110661541B (en) | 2019-09-06 | 2019-09-06 | Underwater robot positioning evaluation system based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110661541B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1588124A (en) * | 2004-08-20 | 2005-03-02 | 清华大学 | Passive speed measuring and distance measuring method and device using Doppler variation |
CN206601787U (en) * | 2016-12-06 | 2017-10-31 | 北京臻迪科技股份有限公司 | A kind of communication system of unmanned boat under water |
US20180099733A1 (en) * | 2016-10-06 | 2018-04-12 | Fuji Xerox Co., Ltd. | Underwater mobile body and underwater communication system |
CN207882429U (en) * | 2017-11-10 | 2018-09-18 | 交通运输部天津水运工程科学研究所 | A kind of pull-type black box detection system based on round basic matrix |
CN108680170A (en) * | 2018-06-20 | 2018-10-19 | 浙江大学 | AUV based on electromagnetic wave attenuation principle returns depressed place navigation system and method |
-
2019
- 2019-09-06 CN CN201910843177.0A patent/CN110661541B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1588124A (en) * | 2004-08-20 | 2005-03-02 | 清华大学 | Passive speed measuring and distance measuring method and device using Doppler variation |
US20180099733A1 (en) * | 2016-10-06 | 2018-04-12 | Fuji Xerox Co., Ltd. | Underwater mobile body and underwater communication system |
CN206601787U (en) * | 2016-12-06 | 2017-10-31 | 北京臻迪科技股份有限公司 | A kind of communication system of unmanned boat under water |
CN207882429U (en) * | 2017-11-10 | 2018-09-18 | 交通运输部天津水运工程科学研究所 | A kind of pull-type black box detection system based on round basic matrix |
CN108680170A (en) * | 2018-06-20 | 2018-10-19 | 浙江大学 | AUV based on electromagnetic wave attenuation principle returns depressed place navigation system and method |
Non-Patent Citations (1)
Title |
---|
李军远: "基于超低频电磁波的管道机器人示踪定位技术研究", 《中国优秀博硕士学位论文全文数据库(博士)信息科技辑》 * |
Also Published As
Publication number | Publication date |
---|---|
CN110661541B (en) | 2021-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
FR2881837B1 (en) | DEVICE FOR SIGNALING AND LOCATING AN INDIVIDUAL TO THE SEA AND METHOD FOR ITS IMPLEMENTATION | |
WO2003103301A3 (en) | Two-way wide area telemetry system | |
CN104568970B (en) | Underwater weld automatic recognition system | |
CN101831923B (en) | Automatic monitoring technical method for marine structures with underwater wireless transmission system | |
CN108415318A (en) | Water monitoring device based on high in the clouds platform | |
CN107831466A (en) | Underwater wireless acoustic marker and its multi-address instruction code method | |
CN111784948A (en) | Social distance monitoring and tracing device and method thereof | |
CN110661541B (en) | Underwater robot positioning evaluation system based on machine learning | |
CN204359703U (en) | Underwater weld automatic recognition system | |
CN104690455B (en) | A kind of underwater weld automatic identifying method | |
CN112235049A (en) | Communication system and method for diving, shipborne communicator and diving communicator | |
CN105374191A (en) | Modulator-demodulator used for elevator hoistway and short distance wireless communication method | |
CN111998734B (en) | T-shaped shock wave target-reporting model | |
CN110557202A (en) | Underwater communication device based on LED light source | |
CN202771012U (en) | Detector used for logistics management | |
CN110727224A (en) | Multi-mode communication control system of underwater robot | |
CN206183242U (en) | Skin moisture oil content detection device and detecting system based on acoustic wave transmission | |
CN114339649B (en) | WKNN classified NLOS recognition system | |
CN204948366U (en) | Wireless computer network signal detection system | |
CN217501868U (en) | Floating wind power generation system | |
CN206133909U (en) | Ware is forwardded to wireless temperature data | |
CN110167125B (en) | Farmland communication method and device | |
CN205121395U (en) | Fridge wireless monitoring system | |
CN205120993U (en) | Rainfall monitoring station based on 433 wireless transmission | |
Lowes et al. | Low-Power, Low-Cost LoRaWAN Gateway Buoy for use with Wireless Underwater Sensor Networks |
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 |