CN113034718A - Subway pipeline inspection system based on multiple agents - Google Patents
Subway pipeline inspection system based on multiple agents Download PDFInfo
- Publication number
- CN113034718A CN113034718A CN202110223792.9A CN202110223792A CN113034718A CN 113034718 A CN113034718 A CN 113034718A CN 202110223792 A CN202110223792 A CN 202110223792A CN 113034718 A CN113034718 A CN 113034718A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- model
- image information
- historical
- pipeline state
- 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.)
- Pending
Links
- 238000007689 inspection Methods 0.000 title claims description 26
- 238000001514 detection method Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims description 29
- 238000013136 deep learning model Methods 0.000 claims description 16
- 238000005516 engineering process Methods 0.000 claims description 10
- 230000007613 environmental effect Effects 0.000 claims description 5
- 238000013526 transfer learning Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 15
- 230000006399 behavior Effects 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a subway pipeline system of patrolling and examining based on many agents, this system includes: the acquisition unit is used for acquiring pipeline image information by utilizing the detection equipment; the pipeline state prediction unit is used for predicting the pipeline state according to the pipeline image information; and the control unit is used for acquiring the optimal cruising path of the detection device according to the current position coordinate of the detection device and the pipeline state and controlling the detection device to cruise according to the optimal cruising path. The technical scheme that this application provided can reach the subway pipeline of all-round, the high accuracy task of patrolling and examining, has improved efficiency and the reliability that the pipeline patrolled and examined.
Description
Technical Field
The application belongs to the technical field of urban rail transit, and particularly relates to a subway pipeline inspection system based on multiple agents.
Background
The subway pipeline inspection is the most important system for ensuring the safe, reliable and effective operation of urban subways. At present, pipeline inspection mainly depends on manual work to carry out intermittent field inspection and report, and the task is heavy and the efficiency is low. Meanwhile, as subways develop in the depth direction, manual inspection often becomes a difficult and possibly dangerous complex task due to the influence of terrain and environmental factors.
Disclosure of Invention
In order to overcome the problems in the related technology to a certain extent at least, the application provides a subway pipeline inspection system based on multiple intelligent agents, which can achieve the subway pipeline inspection task with omnibearing and high precision and improve the efficiency and reliability of pipeline inspection.
According to a first aspect of an embodiment of the application, a multi-agent based subway pipeline inspection system comprises:
the acquisition unit is used for acquiring pipeline image information by utilizing the detection equipment;
the pipeline state prediction unit is used for predicting the pipeline state according to the pipeline image information;
and the control unit is used for acquiring the optimal cruising path of the detection device according to the current position coordinate of the detection device and the pipeline state and controlling the detection device to cruise according to the optimal cruising path.
Further, the detection device is: unmanned aerial vehicles, unmanned vehicles, or robots.
Furthermore, a sensor is arranged on the detection equipment and used for collecting image information of the pipeline.
Further, the pipeline state prediction unit is specifically configured to:
and predicting the pipeline state by using a pipeline state prediction model according to the pipeline image information.
Further, the system further comprises:
and the model establishing unit is used for establishing the pipeline state prediction model.
Further, the model building unit includes:
the first model establishing module is used for training by taking historical first pipeline image information as an input layer training sample of the deep learning model and taking a historical pipeline state corresponding to the historical first pipeline image information as an output layer training sample of the deep learning model to obtain a preset deep learning model;
and the second model establishing module is used for training by using the transfer learning technology and taking the historical second pipeline image information as an input layer training sample of the preset deep learning model and taking the historical pipeline state corresponding to the historical second pipeline image information as an output layer training sample of the preset deep learning model to obtain the pipeline state prediction model.
Further, the system further comprises:
and the position acquisition unit is used for acquiring the current position coordinates of the detection equipment by utilizing the GPS technology.
Further, the control unit includes:
and the path acquisition module is used for taking the current position coordinates of the detection equipment and the pipeline state as the input of the multi-agent planning model and acquiring the optimal cruising path of the detection equipment.
Further, the control unit further includes:
a model building module for building the multi-agent planning model.
Further, the model building module includes:
the acquisition submodule is used for acquiring environment information;
the establishing submodule is used for establishing a multi-agent model based on a Markov model according to the acquired environmental information;
and the model obtaining submodule is used for taking the current position coordinates of the historical detection equipment and the corresponding pipeline states as input layer training samples of the multi-agent model, taking the historical optimal cruise path as the output layer training samples of the multi-agent model for training, and obtaining the multi-agent planning model.
The technical scheme provided by the embodiment of the application can have the following beneficial effects: this application utilizes detecting equipment to gather pipeline image information through the collection unit, and pipeline state prediction unit basis pipeline image information prediction pipeline state, the control unit basis detecting equipment's current position coordinate with the pipeline state acquires detecting equipment's the optimum route of cruising, and control detecting equipment cruises according to the optimum route of cruising, can reach the subway pipeline of all-round, high accuracy and patrol and examine the task, has improved the efficiency and the reliability that the pipeline was patrolled and examined, simultaneously, has still reduced the manual work and has patrolled and examined the danger that brings.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
FIG. 1 is a schematic diagram illustrating a multi-agent based subway pipe inspection system according to an exemplary embodiment;
FIG. 2 is a schematic diagram illustrating another multi-agent based subway pipe inspection system according to an exemplary embodiment;
fig. 3 is a schematic diagram illustrating an actual application of another multi-agent based subway pipe inspection system according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
Fig. 1 is a schematic diagram illustrating a multi-agent based subway pipe inspection system according to an exemplary embodiment, as shown in fig. 1, the system comprising:
the acquisition unit is used for acquiring pipeline image information by utilizing the detection equipment;
the pipeline state prediction unit is used for predicting the pipeline state according to the pipeline image information;
and the control unit is used for acquiring the optimal cruising path of the detection device according to the current position coordinate of the detection device and the pipeline state and controlling the detection device to cruise according to the optimal cruising path.
According to the subway pipeline inspection system based on the multiple intelligent agents, the acquisition unit is used for acquiring the image information of the pipeline by using the detection equipment, the pipeline state prediction unit is used for predicting the state of the pipeline according to the image information of the pipeline, the control unit is used for acquiring the optimal cruising path of the detection equipment according to the current position coordinate and the state of the pipeline of the detection equipment and controlling the detection equipment to cruise according to the optimal cruising path, the subway pipeline inspection task with omnibearing and high precision can be achieved, the efficiency and the reliability of pipeline inspection are improved, and meanwhile, the danger caused by manual inspection is reduced.
As an improvement of the foregoing embodiment, an embodiment of the present invention provides a schematic structural diagram of another multi-agent based subway pipeline inspection system, as shown in fig. 2, including:
the acquisition unit is used for acquiring pipeline image information by utilizing the detection equipment;
the pipeline state prediction unit is used for predicting the pipeline state according to the pipeline image information;
and the control unit is used for acquiring the optimal cruising path of the detection device according to the current position coordinate of the detection device and the pipeline state and controlling the detection device to cruise according to the optimal cruising path.
Further optionally, the detection device may be, but is not limited to: unmanned aerial vehicles, unmanned vehicles, or robots.
It can be understood that, as shown in fig. 3, a stereoscopic interaction is achieved by the unmanned aerial vehicle, the pipeline robot, the acquisition unit, the pipeline state prediction unit, and the control unit.
Further optionally, a sensor is arranged on the detection device and used for collecting image information of the pipeline.
It should be noted that the type of the sensor provided on the detection device according to the embodiment of the present invention may be, but is not limited to, a sensor of an image capturing and scanning type.
Further optionally, the pipeline state prediction unit is specifically configured to:
and predicting the pipeline state by using a pipeline state prediction model according to the pipeline image information.
Further optionally, the system further comprises:
and the model establishing unit is used for establishing a pipeline state prediction model.
Further optionally, the model building unit includes:
the first model establishing module is used for training by taking historical first pipeline image information as an input layer training sample of the deep learning model and taking a historical pipeline state corresponding to the historical first pipeline image information as an output layer training sample of the deep learning model to obtain a preset deep learning model;
and the second model establishing module is used for training by using the transfer learning technology and taking the historical second pipeline image information as an input layer training sample of the preset deep learning model and taking the historical pipeline state corresponding to the historical second pipeline image information as an output layer training sample of the preset deep learning model to obtain the pipeline state prediction model.
It should be noted that the historical first pipe image information is different from the historical second pipe image information in that the historical first pipe image information is historical acquired pipe image information (for example, pipe image information that has been stored in an image library); and the historical second pipeline image information is collected image information of rare pipeline abnormal states (for example, except the pipeline image information in the image library, the image information of the pipeline abnormal states encountered in the real-time collected pipeline image information, or the historical first pipeline image information rare in the historical first pipeline image information is extracted).
It is understood that the historical first pipe image information and the historical second pipe image information may or may not have repeated pipe image information.
In some alternative embodiments, the system may, but is not limited to, compare data of different environments by similarity between environment states (such as KL distance), and reuse some parameters between models. It can be understood that the reuse of some parameters between models is realized by the method, and the design of the driving transfer learning algorithm is realized, and the algorithm can process the comparison of different pipeline state characteristics.
In some optional embodiments, the training of the pipeline state prediction model may be, but is not limited to, performed on a cloud server, and the prediction of the pipeline state prediction model may be, but is not limited to, performed on a general laptop or a mobile phone, so as to achieve the analysis and judgment anytime and anywhere.
It will be appreciated that since the abnormal states of some pipelines are quite rare, the trained state model by general deep learning is not sufficient to accurately judge these abnormal states. Therefore, a transfer learning technology can be introduced, and the universality of the training model is improved by learning the image information of the states of different types of pipelines (not limited to subway pipelines). It can be understood that in the design of the migration technology, the main difficulty is the extraction and comparison of different pipeline state features, and the embodiment of the invention overcomes the difficulty, thereby transferring the state knowledge with information quantity and improving the judgment precision of the learning model.
In some embodiments, the abnormal condition of the pipeline may be caused by, but is not limited to, weather changes, human damage, and the like. The pipeline state prediction model established by the embodiment of the invention can quickly and accurately analyze the image information, and particularly realize the judgment and prediction of the pipeline state under the condition of noise.
Further optionally, the system further includes:
and the position acquisition unit is used for acquiring the current position coordinates of the detection equipment by utilizing the GPS technology.
It should be noted that the manner of "acquiring the current position coordinates of the detection device by using GPS technology" in the embodiments of the present invention is well known to those skilled in the art, and therefore, the specific implementation manner thereof is not described too much.
Further optionally, the control unit includes:
and the path acquisition module is used for taking the current position coordinates and the pipeline state of the detection equipment as the input of the multi-agent planning model and acquiring the optimal cruising path of the detection equipment.
Further optionally, the control unit further includes:
and the model establishing module is used for establishing a multi-agent planning model.
Further optionally, the model building module includes:
the acquisition submodule is used for acquiring environment information;
the establishing submodule is used for establishing a multi-agent model based on a Markov model according to the acquired environmental information;
and the model obtaining submodule is used for taking the current position coordinates of the historical detection equipment and the corresponding pipeline states as input layer training samples of the multi-agent model, taking the historical optimal cruise path as the output layer training samples of the multi-agent model for training, and obtaining the multi-agent planning model.
It should be noted that the method of "establishing a multi-agent model based on a markov model according to collected environment information" in the embodiments of the present invention is well known to those skilled in the art, and therefore, the specific implementation manner thereof is not described in detail.
In some optional embodiments, firstly, a single intelligent agent planning model is adopted to plan the cruising path of the robot/unmanned aircraft off line; selectively correcting the new cruising position of the robot/unmanned aerial vehicle at the right time and place according to the current position of the robot/unmanned aerial vehicle and the updated environment information;
secondly, on the basis of a single robot/unmanned aircraft cruise behavior model, a multi-agent coordination mechanism is adopted to coordinate the behaviors of a plurality of robots/unmanned aircraft, so that the maximization of a cruise area is realized, and cruise blind spots are eliminated.
It should be noted that, but not limited to, a markov-based multi-agent planning model can be established, and the coordination of the planning implementation behavior of the multi-agent can be obtained by solving the model.
It should be noted that the process of planning the cruising path of the robot/drone offline may be, but is not limited to: establishing a Markov-based planning model for path planning by considering possible states of the environment variables; the updated environmental information may be, but is not limited to, acquired by a GPS sensor; correcting the new cruise position of the robot/drone may be, but is not limited to, by correcting the position based on the cruise position, according to the new GPS information;
further optionally, the system may also make intervention decisions on sensor behaviors according to information determined by the pipeline state; this will be embedded in the behavior coordination mechanism of multiple robotic/unmanned aircraft. The technique employed may be, but is not limited to, finding the optimal coordinated action of multiple sensors by maximizing the coverage of the sensors through a mathematical optimization method.
Specifically, optionally, the decision to intervene in the sensor behavior may be, but is not limited to: if the current sensor position fails to capture the desired image information, the control unit of the system may coordinate the position of each sensor via wireless communication.
Specifically, optionally, finding the optimal coordination action of the multiple sensors may be implemented by, but not limited to, the following mathematical optimization methods: establishing a coverage function of the multiple sensors according to the positions of the sensors; and determining whether the position of the sensor needs to be adjusted according to the range needing to be covered. It can be understood that the detection equipment such as the robot and the unmanned aerial vehicle is cooperatively controlled by analyzing the sensor information on line, so that the pipeline inspection task with omnibearing and high precision is achieved.
It will be appreciated that by optimizing the scan area of the sensor using the maximum coverage function, the cost effectiveness of the sensor is increased.
As a further alternative, the system may also enable comprehensive detection of pipe conditions in a coordinated fashion by taking into account the individual robot/drone capability limitations, such as energy and sensor scan dimensions.
The embodiment of the invention provides another subway pipeline inspection system based on multiple intelligent agents, which is different from a traditional centralized control system, particularly separates a data communication, analysis and prediction platform from a complex system, provides input for the control system, embodies the modularization of system design, simplifies the realization and implementation of the system and improves the reliability of the operation of the whole system;
the subway pipeline inspection system based on the multiple intelligent agents provided by the embodiment of the invention has the advantages that the stereoscopic type and the intelligentization are realized, the modularization of the system design is realized, the realization and the implementation of the system are simplified, and the reliability of the operation of the whole system is improved;
according to the subway pipeline inspection system based on the multiple intelligent agents, the provided pipeline state prediction model is a lightweight deep learning model, the model can run at a portable terminal and occupies the least amount of CPU computing resources, so that a data analysis platform can run at any time and any place;
according to the subway pipeline inspection system based on the multiple intelligent agents, the coordination mechanism of the multiple intelligent agents is achieved, the specific constraints of all the intelligent agents are particularly considered, the specific implementation of a planning model of the multiple intelligent agents is achieved, the maximization of a cruise area is achieved, and cruise blind spots are eliminated. .
It is understood that the same or similar parts in the above embodiments may be mutually referred to, and the same or similar parts in other embodiments may be referred to for the content which is not described in detail in some embodiments.
It should be noted that, in the description of the present application, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present application, the meaning of "a plurality" means at least two unless otherwise specified.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present application includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A multi-agent based subway pipeline inspection system, comprising:
the acquisition unit is used for acquiring pipeline image information by utilizing the detection equipment;
the pipeline state prediction unit is used for predicting the pipeline state according to the pipeline image information;
and the control unit is used for acquiring the optimal cruising path of the detection device according to the current position coordinate of the detection device and the pipeline state and controlling the detection device to cruise according to the optimal cruising path.
2. The system of claim 1, wherein the detection device is: unmanned aerial vehicles, unmanned vehicles, or robots.
3. The system of claim 1, wherein the detection device is provided with a sensor for collecting image information of the pipeline.
4. The system of claim 1, wherein the pipeline state prediction unit is specifically configured to:
and predicting the pipeline state by using a pipeline state prediction model according to the pipeline image information.
5. The system of claim 4, further comprising:
and the model establishing unit is used for establishing the pipeline state prediction model.
6. The system of claim 5, wherein the model building unit comprises:
the first model establishing module is used for training by taking historical first pipeline image information as an input layer training sample of the deep learning model and taking a historical pipeline state corresponding to the historical first pipeline image information as an output layer training sample of the deep learning model to obtain a preset deep learning model;
and the second model establishing module is used for training by using the transfer learning technology and taking the historical second pipeline image information as an input layer training sample of the preset deep learning model and taking the historical pipeline state corresponding to the historical second pipeline image information as an output layer training sample of the preset deep learning model to obtain the pipeline state prediction model.
7. The system of claim 1, further comprising:
and the position acquisition unit is used for acquiring the current position coordinates of the detection equipment by utilizing the GPS technology.
8. The system of claim 1, wherein the control unit comprises:
and the path acquisition module is used for taking the current position coordinates of the detection equipment and the pipeline state as the input of the multi-agent planning model and acquiring the optimal cruising path of the detection equipment.
9. The system of claim 8, wherein the control unit further comprises:
a model building module for building the multi-agent planning model.
10. The system of claim 9, wherein the model building module comprises:
the acquisition submodule is used for acquiring environment information;
the establishing submodule is used for establishing a multi-agent model based on a Markov model according to the acquired environmental information;
and the model obtaining submodule is used for taking the current position coordinates of the historical detection equipment and the corresponding pipeline states as input layer training samples of the multi-agent model, taking the historical optimal cruise path as the output layer training samples of the multi-agent model for training, and obtaining the multi-agent planning model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110223792.9A CN113034718A (en) | 2021-03-01 | 2021-03-01 | Subway pipeline inspection system based on multiple agents |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110223792.9A CN113034718A (en) | 2021-03-01 | 2021-03-01 | Subway pipeline inspection system based on multiple agents |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113034718A true CN113034718A (en) | 2021-06-25 |
Family
ID=76465062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110223792.9A Pending CN113034718A (en) | 2021-03-01 | 2021-03-01 | Subway pipeline inspection system based on multiple agents |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113034718A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117749A (en) * | 2018-07-23 | 2019-01-01 | 福建中海油应急抢维修有限责任公司 | A kind of abnormal object monitoring and managing method and system based on unmanned plane inspection image |
| CN110027701A (en) * | 2019-03-28 | 2019-07-19 | 苏州大学 | Underground pipe gallery cruising inspection system |
| CN110414359A (en) * | 2019-07-01 | 2019-11-05 | 中国石化销售有限公司华南分公司 | The analysis of long distance pipeline unmanned plane inspection data and management method and system |
| CN110737989A (en) * | 2019-10-18 | 2020-01-31 | 中国科学院深圳先进技术研究院 | parallel intelligent emergency cooperation method, system and electronic equipment |
| CN110992349A (en) * | 2019-12-11 | 2020-04-10 | 南京航空航天大学 | Underground pipeline abnormity automatic positioning and identification method based on deep learning |
| CN111300372A (en) * | 2020-04-02 | 2020-06-19 | 同济人工智能研究院(苏州)有限公司 | Air-ground cooperative intelligent inspection robot and inspection method |
| CN112060106A (en) * | 2020-09-11 | 2020-12-11 | 徐州工程学院 | Inspection system of inspection robot for mine and inspection method of inspection robot group |
| CN112099510A (en) * | 2020-09-25 | 2020-12-18 | 东南大学 | Intelligent agent control method based on end edge cloud cooperation |
| CN112286203A (en) * | 2020-11-11 | 2021-01-29 | 大连理工大学 | Multi-agent reinforcement learning path planning method based on ant colony algorithm |
-
2021
- 2021-03-01 CN CN202110223792.9A patent/CN113034718A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109117749A (en) * | 2018-07-23 | 2019-01-01 | 福建中海油应急抢维修有限责任公司 | A kind of abnormal object monitoring and managing method and system based on unmanned plane inspection image |
| CN110027701A (en) * | 2019-03-28 | 2019-07-19 | 苏州大学 | Underground pipe gallery cruising inspection system |
| CN110414359A (en) * | 2019-07-01 | 2019-11-05 | 中国石化销售有限公司华南分公司 | The analysis of long distance pipeline unmanned plane inspection data and management method and system |
| CN110737989A (en) * | 2019-10-18 | 2020-01-31 | 中国科学院深圳先进技术研究院 | parallel intelligent emergency cooperation method, system and electronic equipment |
| CN110992349A (en) * | 2019-12-11 | 2020-04-10 | 南京航空航天大学 | Underground pipeline abnormity automatic positioning and identification method based on deep learning |
| CN111300372A (en) * | 2020-04-02 | 2020-06-19 | 同济人工智能研究院(苏州)有限公司 | Air-ground cooperative intelligent inspection robot and inspection method |
| CN112060106A (en) * | 2020-09-11 | 2020-12-11 | 徐州工程学院 | Inspection system of inspection robot for mine and inspection method of inspection robot group |
| CN112099510A (en) * | 2020-09-25 | 2020-12-18 | 东南大学 | Intelligent agent control method based on end edge cloud cooperation |
| CN112286203A (en) * | 2020-11-11 | 2021-01-29 | 大连理工大学 | Multi-agent reinforcement learning path planning method based on ant colony algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108189043B (en) | Inspection method and inspection robot system applied to high-speed rail machine room | |
| US10732261B1 (en) | Generating data using radar observation model based on machine learning | |
| US20210389766A1 (en) | Methods and Apparatuses for Water Body Pollution Intelligent Investigation Utilizing Unmanned Ships | |
| CN112098326B (en) | Automatic detection method and system for bridge diseases | |
| CN110780305A (en) | Track cone bucket detection and target point tracking method based on multi-line laser radar | |
| LU500120B1 (en) | Multi-arm robot for automatic tunnel maintenance and control method thereof | |
| CN116494201A (en) | Monitoring integrated power machine room inspection robot and unmanned inspection method | |
| CN108549370A (en) | Collecting method and harvester | |
| CN117806355A (en) | Control method and system for electric power line inspection unmanned aerial vehicle | |
| CN115941529A (en) | Cable tunnel detection method and system based on robot | |
| CN114814877A (en) | Tunnel data acquisition method, equipment and medium based on inspection robot | |
| CN112015180B (en) | Intelligent experiment trolley and control system thereof | |
| CN113034718A (en) | Subway pipeline inspection system based on multiple agents | |
| CN113085882A (en) | Fault processing method and device, electronic equipment and storage medium | |
| CN116499429B (en) | Marine environment monitoring method, marine environment monitoring device, computer equipment and storage medium | |
| CN117288094A (en) | Real-time positioning system of heading machine based on laser sensor | |
| Rezaei et al. | A deep learning-based approach for vehicle motion prediction in autonomous driving | |
| CN115877855A (en) | Intelligent power inspection robot adaptive to environmental path planning and inspection method | |
| CN112965529B (en) | Typhoon observation-oriented marine glider control method | |
| Wang et al. | The Application of Computer Vision Target Recognition Technology in Autonomous Driving | |
| CN114200946B (en) | AGV trolley control method for intelligent manufacturing machining production line | |
| CN116652973B (en) | Analog traffic director system with V2X function | |
| CN117784120B (en) | Unmanned aerial vehicle flight state monitoring method and system | |
| US11938939B1 (en) | Determining current state of traffic light(s) for use in controlling an autonomous vehicle | |
| CN117873162A (en) | Unmanned aerial vehicle photovoltaic intelligent inspection device and method, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |