CN116117817A - Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium - Google Patents
Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium Download PDFInfo
- Publication number
- CN116117817A CN116117817A CN202310173814.4A CN202310173814A CN116117817A CN 116117817 A CN116117817 A CN 116117817A CN 202310173814 A CN202310173814 A CN 202310173814A CN 116117817 A CN116117817 A CN 116117817A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- type
- robot
- clearance
- image
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
- B25J9/161—Hardware, e.g. neural networks, fuzzy logic, interfaces, processor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
Landscapes
- Engineering & Computer Science (AREA)
- Robotics (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Manipulator (AREA)
Abstract
The invention discloses a control method and device of an obstacle clearing robot, the robot and a storage medium, wherein the control method comprises the following steps: when the robot moves on the power transmission line, acquiring images of the power transmission line in the moving direction through the camera; inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of the obstacle and the position of the obstacle; when the type of the obstacle is a designated type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle; the robot is controlled to move to the obstacle clearance position and to execute obstacle clearance operation in an obstacle clearance mode, images can be acquired and input into the obstacle detection model to obtain the type and the position of the obstacle, the obstacle is detected timely, the corresponding obstacle clearance mode is determined according to the type and the position of the obstacle, the obstacle on the obstacle clearance position clearance line is cleared, the robot is not required to be controlled manually, and the degree of automation of obstacle clearance of the robot is improved.
Description
Technical Field
The invention relates to the technical field of electric power installation, in particular to a control method and device for an obstacle clearing robot, the robot and a storage medium.
Background
At present, the overhead line often leads to the contact of electrified bare wires and tree barriers due to insufficient safe distance setting, and the condition of line tripping faults occurs, so that public safety is easily damaged.
Therefore, before the insulating sheath is installed, the obstacles on or around the overhead line are required to be removed, however, in the case that the obstacles exist on or around the line, the obstacles are required to be observed on site manually and the robot is controlled to remove the obstacles manually, the robot cannot automatically detect and remove the obstacles in time, and the automation degree of removing the obstacles by the robot is low.
Disclosure of Invention
The invention provides a control method, a control device, a robot and a storage medium for an obstacle clearing operation robot, which are used for solving the problems that the existing robot cannot automatically detect and clear obstacles in time and the automation degree of the robot for clearing the obstacles is low.
In a first aspect, the present invention provides a control method for an obstacle clearing robot, which is applied to control a robot to clear an obstacle on a power transmission line, where the robot is provided with a camera, and includes:
when the robot moves on the power transmission line, acquiring images of the power transmission line in the moving direction through the camera;
inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle;
when the type of the obstacle is a designated type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle;
and controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation in the obstacle clearance mode.
In a second aspect, the present invention provides a control device for an obstacle clearing robot, which is used for controlling the robot to clear an obstacle on a power transmission line, the robot is provided with a camera, and includes:
the image acquisition module is used for acquiring images of the power transmission line in the moving direction through the camera when the robot moves on the power transmission line;
the obstacle detection result acquisition module is used for inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle;
the obstacle clearance position and mode determining module is used for determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle when the type of the obstacle is a specified type;
and the obstacle clearance module is used for controlling the robot to move to the obstacle clearance position and executing obstacle clearance operation in the obstacle clearance mode.
In a third aspect, the present invention provides an obstacle clearing robot comprising:
the camera, the memory and the obstacle clearance mechanism are all connected with the at least one processor, wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the obstacle clearing robot control method according to any one of the first aspects of the invention.
In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions for causing a processor to execute the method for controlling the obstacle clearing robot according to any one of the first aspects of the invention.
The obstacle clearing robot is provided with a camera, when the robot moves on a power transmission line, images are acquired on the power transmission line in the moving direction through the camera, the images are input into a pre-trained obstacle detection model, and an obstacle detection result is obtained, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle; when the type of the obstacle is a specified type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle, controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation by adopting the obstacle clearance mode. The robot of this embodiment can gather the image and input in the barrier detection model to obtain the type and the position of barrier, realized in time detecting the barrier, and according to type and the position of barrier, confirm that corresponding clearance mode clears away the barrier on the line in clearance position, clear away the barrier for other operations of follow-up, need not the manual control robot, improved the degree of automation that the robot cleared the barrier, and guaranteed the security performance of the subsequent operation of robot.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a control method of an obstacle clearing robot according to an embodiment of the present invention;
fig. 2 is a flowchart of a control method of an obstacle clearing robot according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a control device for an obstacle clearing robot according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a robot according to a fourth embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Fig. 1 is a flowchart of a method for controlling an obstacle clearing robot according to an embodiment of the present invention, where the method may be applied to detecting an obstacle on or around a line and clearing the obstacle during installation of an insulating sheath, and the method may be performed by an obstacle clearing robot control device, and the obstacle clearing robot control device may be implemented in hardware and/or software, and the obstacle clearing robot control device may be configured in an electronic device. As shown in fig. 1, the obstacle clearing robot control method includes:
s101, when the robot moves on the power transmission line, acquiring images of the power transmission line in the moving direction through the camera.
The robot of this embodiment is the robot that removes obstacles for the robot is when walking on the power transmission line, clear away the power transmission line, the obstacle in the power transmission line presets the within range, and the obstacle can be trees around the power transmission line, twine debris on the power transmission line, nest of animal on the power transmission line etc..
The robot can be provided with a camera, a positioning sensor and an obstacle removing mechanism, the obstacle removing mechanism can be provided with a plurality of obstacle removing modes so as to remove different types of obstacles, the positioning sensor can be a GPS (global positioning system), beidou and other positioning sensors, and the camera can be a monocular or binocular camera.
Before other operations are carried out, the robot can walk on the line to be operated to remove the obstacle, and when the robot walks on the power transmission line, the image can be acquired towards the walking direction through the camera on the robot.
S102, inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of the obstacle and the position of the obstacle.
In this embodiment, the obstacle detection model may be a model that is trained in advance and is used to identify the type and position of an obstacle in the acquired image, and the obstacle detection model may be various neural networks that may be trained by a supervised, unsupervised or other training method, for example, images in which various types of obstacles exist on or around the transmission line may be acquired and labeled as training images, and the obstacle detection model is trained to enable the obstacle detection model to learn the capability of identifying the type and position of the obstacle, and output the type and position of the obstacle in the image after the acquired image is input into the obstacle detection model, where the type of the outputted obstacle is the type with the largest probability.
S103, when the type of the obstacle is a specified type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle.
The specified type may be a type of obstacle that the robot is capable of removing, at least one of the specified types, and illustratively the specified type may be a plant, an insect nest, plastic refuse, or the like. The robot can store the obstacle clearance modes and the optimal obstacle clearance positions corresponding to different types of obstacles, and when the types of the obstacles are the specified types, the optimal obstacle clearance modes and the optimal obstacle clearance positions can be matched through the types of the obstacles.
When the type of the obstacle is out of the appointed type, the robot is determined to be incapable of removing the obstacle, the acquired image and the position can be sent to a system background, so that the image is displayed at the position corresponding to the obstacle on the electronic map displayed at the system background, and the system background personnel is prompted that the obstacle incapable of being removed exists on the power transmission line.
S104, controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation in an obstacle clearance mode.
After the obstacle clearance position and the obstacle clearance mode of the obstacle are determined, an obstacle clearance instruction can be generated, wherein the obstacle clearance instruction comprises codes corresponding to the obstacle clearance position and the obstacle clearance mode, so that after the robot is controlled to walk to the obstacle clearance position, the obstacle clearance mechanism is controlled to clear the obstacle in the obstacle clearance mode corresponding to the codes.
The obstacle clearing robot is provided with a camera, when the robot moves on a power transmission line, images are acquired on the power transmission line in the moving direction through the camera, the images are input into a pre-trained obstacle detection model, and an obstacle detection result is obtained, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle; when the type of the obstacle is a specified type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle, controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation by adopting the obstacle clearance mode. The robot of this embodiment can gather the image and input in the barrier detection model to obtain the type and the position of barrier, realized in time detecting the barrier, and according to type and the position of barrier, confirm that corresponding clearance mode clears away the barrier on the line in clearance position, clear away the barrier for other operations of follow-up, need not the manual control robot, improved the degree of automation that the robot cleared the barrier, and guaranteed the security performance of the subsequent operation of robot.
Example two
Fig. 2 is a flowchart of a method for controlling an obstacle clearing robot according to a second embodiment of the present invention, where the method for controlling an obstacle clearing robot according to the first embodiment of the present invention is optimized on the basis of the first embodiment, as shown in fig. 2, and includes:
s201, when the robot moves on the power transmission line, acquiring images of the power transmission line in the moving direction through the camera.
Before other operations are carried out, the robot can walk on the line to be operated to remove the obstacle, and when the robot walks on the power transmission line, the image can be acquired towards the walking direction through the camera on the robot.
S202, inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of the obstacle and the position of the obstacle.
The obstacle detection result of the present embodiment may include the existence probability of an obstacle existing in the image, the type probability of the obstacle belonging to various types, and the position of the obstacle.
When the obstacle detection model is trained, a training image can be obtained, the training image is an image after labeling a label on the image acquired by performing obstacle clearing operation on the robot, the label comprises the existence probability of an obstacle, the type probability of the obstacle belonging to a certain type and the labeling position of the obstacle, N training images are randomly extracted and input into the obstacle clearing operation detection model, the prediction existence probability, the prediction type probability and the prediction position of the type of the obstacle in each training image are obtained, the loss rate is calculated according to the prediction existence probability, the prediction type probability and the prediction position of the obstacle, the labeling existence probability, the labeling type probability and the labeling position of the obstacle in the N training images, if yes, the training on the obstacle detection model is stopped, the trained obstacle detection model is obtained, if no, the gradient is reduced according to the loss rate on the parameters of the obstacle detection model, and the step of randomly extracting N training images is returned to be input into the obstacle detection model.
Wherein the loss rate may be calculated from the following loss function:
wherein Result is i L_result is the predicted existence probability of the obstacle in the ith image i Probability of presence of obstacle labeled for ith image, type i L_result is a prediction type probability of a certain type for predicting an obstacle in an ith image i Type probability, pos, for type of obstacle noted for ith image i L_Pos for the position of the obstacle of the ith image in the image i The position of the obstacle in the image is marked for the ith image.
The present embodiment calculates the loss rate by the existence probability of the obstacle, the type probability belonging to each type, and the position of the obstacle in the image, so that the obstacle detection model learns the ability to recognize whether the obstacle exists, recognize the type of the obstacle, and determine the position of the obstacle in the image.
The present embodiment executes S203-S207 when the type of the obstacle is a specified type, and executes S208-S209 when the type of the obstacle is a non-specified type.
S203, when the type of the obstacle is the appointed type, searching an obstacle clearance mode matched with the appointed type in a preset type-obstacle clearance mode comparison table.
The type-obstacle clearance mode comparison table includes comparison relations of different types of obstacles and obstacle clearance modes, in one example, the obstacle clearance modes can include mechanical arm obstacle clearance, laser obstacle clearance, high-pressure air obstacle clearance and the like, for example, the obstacle clearance mode can be laser obstacle clearance, the obstacle clearance mode can be mechanical arm obstacle clearance for insect nest type obstacles, the obstacle clearance mode can be high-pressure air obstacle clearance for bird feces or other obstacles attached to a line, of course, the obstacle clearance mode can be one type or can be a combination of a plurality of obstacle clearance modes, and after the type of the obstacle is determined, the corresponding obstacle clearance mode can be searched in the comparison table through the type.
S204, determining the obstacle clearance position based on the obstacle clearance mode and the position of the obstacle.
After the image position of the obstacle in the image is obtained by the obstacle detection model, the image position may be converted into a position in the world coordinate system as the position of the obstacle in the world coordinate system. In addition, each obstacle clearance mode is provided with an optimal obstacle clearance distance, and then the obstacle clearance position can be determined through the obstacle clearance distance and the position of the obstacle, for example, when the obstacle is a tree, the obstacle clearance mode can be laser obstacle clearance, the optimal obstacle clearance distance can be determined to be 2 meters according to the power of laser, and then the position 2 meters away from the tree can be determined to be the obstacle clearance position.
According to the method, the obstacle clearance mode is determined through table lookup, the obstacle clearance position is determined through the obstacle clearance mode and the position of the obstacle, the scheme is simple, and the optimal obstacle clearance mode and the obstacle clearance position can be determined rapidly.
S205, controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation in an obstacle clearance mode.
After the obstacle clearance position and the obstacle clearance mode of the obstacle are determined, an obstacle clearance instruction can be generated, wherein the obstacle clearance instruction comprises codes corresponding to the obstacle clearance position and the obstacle clearance mode, so that after the robot is controlled to walk to the obstacle clearance position, the obstacle clearance mechanism is controlled to clear the obstacle in the obstacle clearance mode corresponding to the codes.
S206, detecting whether the obstacle is cleared.
In one embodiment, after performing the obstacle clearing operation on the obstacle, an image may be acquired, and the image may be input into the obstacle detection model to detect whether the obstacle still exists, if not, S207 is performed, if yes, it is determined that the obstacle has been cleared, and the robot is controlled to continue to walk to clear other obstacles.
In another embodiment, the robot can be further provided with an infrared sensor so as to acquire infrared data of the position of the obstacle through the infrared sensor, and whether the obstacle is cleared is determined through comparison of the infrared data before and after obstacle clearing. The infrared data are infrared images, when an obstacle is attached to a power transmission line, a first infrared image is acquired before obstacle clearance, a second infrared image is acquired after obstacle clearance, and when the similarity is smaller than a preset threshold value, a large difference exists between the power transmission line before and after obstacle clearance and the obstacle is cleared by calculating the similarity of the first infrared image and the second infrared image.
In another example, an infrared image without an obstacle may be stored in advance as a template image, the infrared image is collected after obstacle clearance, the similarity between the infrared image and the template image is calculated, and when the similarity is greater than a preset threshold value, the obstacle is cleared.
S207, controlling the robot to execute re-obstacle clearance operation at the obstacle clearance position.
When the obstacle is not cleared, the robot is controlled to move to the obstacle clearing position to execute the obstacle clearing operation again.
In another embodiment, the number of times of obstacle clearing operation on the same obstacle can be counted, when the number of times of obstacle clearing operation on the same obstacle is larger than a preset number of times threshold, the obstacle is determined to be difficult to clear, the robot can be controlled to stop the obstacle clearing operation, prompt information is generated, the prompt information and the acquired images of the obstacle are uploaded to a system background, the prompt information and the images are displayed on the system background, and personnel in the system background are prompted to clear the obstacle manually.
In yet another embodiment, the total number of the obstacles detected in the line with the preset length and the number of the obstacles with the non-specified type can be counted, the number of the obstacles with the non-specified type and the total number of the obstacles with the non-specified type are sent to the system background, so that the total number of the obstacles with the non-specified type and the total number of the obstacles with the non-specified type are displayed on the corresponding line on the electronic map displayed on the system background, the system background personnel are prompted that more obstacles which cannot be cleared by the robot exist on the line section, and the system background personnel can conveniently discharge the operation and maintenance personnel to manually clear the line section, so that the safety of subsequent operation is ensured.
And S208, controlling the robot to stop the obstacle clearance operation when the type of the obstacle is a non-designated type.
In one embodiment, when the type of the obstacle is out of the specified type, the robot is determined to be incapable of clearing the obstacle, and the robot can be controlled to stop the obstacle clearing operation so as to avoid potential safety hazards caused by blocking when the robot walks to the obstacle.
S209, sending prompt information to the system background and sending the image to the system background.
When the type of the obstacle is a non-appointed type, after the robot is controlled to stop the obstacle removing operation, the acquired image and the position are sent to a system background so as to display the image at the position corresponding to the obstacle on the electronic map displayed by the system background, so that the system background personnel can be prompted that the obstacle which cannot be removed exists on the power transmission line.
The obstacle clearing robot is provided with a camera, when the robot moves on a power transmission line, images are acquired on the power transmission line in the moving direction through the camera, the images are input into a pre-trained obstacle detection model, and an obstacle detection result is obtained, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle; when the type of the obstacle is the appointed type, searching an obstacle clearance mode matched with the appointed type in a preset type-obstacle clearance mode comparison table, determining an obstacle clearance position based on the obstacle clearance mode and the position of the obstacle, controlling the robot to move to the obstacle clearance position, and executing the obstacle clearance operation by adopting the obstacle clearance mode. The robot of this embodiment can gather the image and input in the barrier detection model to obtain the type and the position of barrier, realized in time detecting the barrier, and according to type and the position of barrier, confirm that corresponding clearance mode clears away the barrier on the line in clearance position, clear away the barrier for other operations of follow-up, need not the manual control robot, improved the degree of automation that the robot cleared the barrier, and guaranteed the security performance of the subsequent operation of robot.
Further, when the type of the obstacle is a non-designated type, the robot is controlled to stop the obstacle removing operation, prompt information is sent to the system background, and an image is sent to the system background, so that accidents caused by the robot in the obstacle removing operation of the non-designated type which cannot be removed are avoided, and system background personnel can be prompted, so that the system background personnel can know the situation of the obstacle.
Example III
Fig. 3 is a schematic structural diagram of a control device for an obstacle clearing robot according to a third embodiment of the present invention. As shown in fig. 3, the obstacle clearing robot control device includes:
the image acquisition module 301 is configured to acquire an image of a power transmission line in a moving direction through the camera when the robot moves on the power transmission line;
an obstacle detection result obtaining module 302, configured to input the image into a pre-trained obstacle detection model, to obtain an obstacle detection result, where the obstacle detection result includes a type of an obstacle and a position of the obstacle;
a clearing position and mode determining module 303, configured to determine a clearing position and a clearing mode according to the type of the obstacle and the position of the obstacle when the type of the obstacle is a specified type;
the clearance module 304 is configured to control the robot to move to the clearance position and perform the clearance operation in the clearance mode.
Optionally, the method further comprises a model training module, wherein the model training module comprises:
the robot obstacle clearance system comprises a training image acquisition unit, a robot clearance operation acquisition unit and an obstacle clearance operation acquisition unit, wherein the training image acquisition unit is used for acquiring a training image, wherein the training image is an image after labeling a label on an image acquired by performing the obstacle clearance operation on a robot, and the label comprises the existence probability of an obstacle, the type probability of the obstacle belonging to a certain type and the labeling position of the obstacle;
the training image input unit is used for randomly extracting N training images to be input into the obstacle clearance operation detection model to obtain the predicted existence probability, the type prediction type probability and the predicted position of the obstacle in each training image;
the loss rate calculation unit is used for calculating the loss rate according to the predicted existence probability, the predicted type probability and the predicted position of the obstacle in the N training images, the existence probability of the mark, the type probability of the mark and the mark position;
the loss rate judging unit is used for judging whether the loss rate is smaller than a preset loss rate threshold value or not;
the training stopping unit is used for stopping training the obstacle detection model to obtain a trained obstacle detection model;
and the parameter adjusting unit is used for carrying out gradient descent on the parameters of the obstacle detection model according to the loss rate and returning the parameters to the training image input unit.
Optionally, the loss rate calculation unit includes:
a loss rate calculation subunit for calculating a loss rate according to the following loss function:
wherein Result is i L_result is the predicted existence probability of the obstacle in the ith image i Probability of presence of obstacle labeled for ith image, type i L_result is a prediction type probability of a certain type for predicting an obstacle in an ith image i Type probability, pos, for type of obstacle noted for ith image i L_Pos for the position of the obstacle of the ith image in the image i The position of the obstacle in the image is marked for the ith image.
Optionally, the obstacle clearance position and mode determining module 303 includes:
the obstacle clearance mode searching unit is used for searching an obstacle clearance mode matched with the appointed type in a preset type-obstacle clearance mode comparison table;
and the obstacle clearance position determining unit is used for determining an obstacle clearance position based on the obstacle clearance mode and the position of the obstacle.
Optionally, the robot communicates with a system background, further comprising:
and the type and image uploading module is used for uploading the type of the obstacle and the image to a system background.
Optionally, the robot communicates with a system background, further comprising:
the obstacle clearance stopping module is used for controlling the robot to stop obstacle clearance operation when the type of the obstacle is a non-appointed type;
and the prompt information sending module is used for sending the prompt information to the system background and sending the image to the system background.
Optionally, the method further comprises:
an obstacle detection module for detecting whether the obstacle has been cleared;
and the obstacle re-clearing module is used for controlling the robot to execute obstacle re-clearing operation at the obstacle-clearing position.
The obstacle clearing robot control device provided by the embodiment of the invention can execute the obstacle clearing robot control method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 4 shows a schematic structural diagram of a robot 40 that may be used to implement an embodiment of the invention. As shown in fig. 4, the robot 40 includes a camera 46, an obstacle clearing mechanism 47, at least one processor 41, and a memory, and the camera 46, the obstacle clearing mechanism 47, and the memory are all connected to the at least one processor, wherein the memory includes, for example, a Read Only Memory (ROM) 42, a Random Access Memory (RAM) 43, etc., and the memory stores a computer program executable by the at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 42 or the computer program loaded from the storage unit 48 into the Random Access Memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the robot 40 may also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44, and an input/output (I/O) interface 45 is also connected to the bus 44.
A camera 46, an obstacle clearing mechanism 47, a storage unit 48, a communication unit 49 in the robot 40 are connected to the I/O interface 45, the storage unit 48, such as a magnetic disk, an optical disk, or the like; a communication unit 49, such as a network card, modem, wireless communication transceiver, etc. The communication unit 49 allows the robot 40 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processor 41 may be various general and/or special purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 41 performs the respective methods and processes described above, such as the obstacle clearing robot control method.
In some embodiments, the obstacle clearing robot control method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program may be loaded and/or installed onto the robot 40 via the ROM 42 and/or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the obstacle clearing robot control method described above may be performed. Alternatively, in other embodiments, processor 41 may be configured to perform the obstacle clearing work robot control method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The utility model provides a clear barrier operation robot control method which characterized in that is applied to control robot and clears away the obstacle on the power transmission line, the robot is provided with the camera, includes:
when the robot moves on the power transmission line, acquiring images of the power transmission line in the moving direction through the camera;
inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle;
when the type of the obstacle is a designated type, determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle;
and controlling the robot to move to the obstacle clearance position and executing the obstacle clearance operation in the obstacle clearance mode.
2. The obstacle clearing robot control method as claimed in claim 1, wherein the obstacle detection model is trained by:
acquiring a training image, wherein the training image is an image obtained by labeling a label on an image acquired by performing obstacle clearing operation on a robot, and the label comprises the existence probability of an obstacle, the type probability of the obstacle belonging to a certain type and the labeling position of the obstacle;
randomly extracting N training images, inputting the N training images into an obstacle clearing operation detection model, and obtaining the predicted existence probability, the predicted type probability and the predicted position of the type of the obstacle in each training image;
calculating loss rate according to the predicted existence probability, the predicted type probability and the predicted position of the obstacle, the existence probability of the label, the type probability of the label and the label position in the N training images;
judging whether the loss rate is smaller than a preset loss rate threshold value or not;
if yes, stopping training the obstacle detection model to obtain a trained obstacle detection model;
if not, carrying out gradient descent on the parameters of the obstacle detection model according to the loss rate, and returning to the step of randomly extracting N training images and inputting the N training images into the obstacle detection model.
3. The obstacle clearing robot control method according to claim 2, wherein the calculating the loss rate from the predicted existence probabilities, predicted type probabilities, and predicted positions of the obstacle, and the existence probabilities of the markers, the type probabilities of the markers, and the marker positions in the N training images includes:
the loss rate is calculated from the following loss function:
wherein Result is i L_result is the predicted existence probability of the obstacle in the ith image i The probability of the presence of an obstacle labeled for the ith image,Type i l_result is a prediction type probability of a certain type for predicting an obstacle in an ith image i Type probability, pos, for type of obstacle noted for ith image i L_Pos for the position of the obstacle of the ith image in the image i The position of the obstacle in the image is marked for the ith image.
4. A control method of an obstacle clearing robot as claimed in any one of claims 1 to 3, wherein said determining the obstacle clearing position and the obstacle clearing mode based on the type of the obstacle and the position of the obstacle when the type of the obstacle is a specified type comprises:
searching an obstacle clearance mode matched with the appointed type in a preset type-obstacle clearance mode comparison table;
and determining the obstacle clearance position based on the obstacle clearance mode and the position of the obstacle.
5. A method of controlling an obstacle clearing robot as claimed in any one of claims 1 to 3, wherein the robot communicates with the system background and, when the type of obstacle is a specified type, further comprises, before determining the obstacle clearing position and the obstacle clearing mode based on the type of obstacle and the position of the obstacle:
uploading the type of the obstacle and the image to a system background.
6. A method of controlling an obstacle clearing robot as claimed in any one of claims 1 to 3, wherein the robot communicates with the system background and, after inputting the image into a pre-trained obstacle detection model, further comprises:
when the type of the obstacle is a non-designated type, controlling the robot to stop the obstacle clearance operation;
and sending prompt information to the system background and sending the image to the system background.
7. A method of controlling an obstacle clearing robot as claimed in any one of claims 1 to 3, wherein the robot, after controlling the robot to move to the obstacle clearing position and to perform an obstacle clearing operation in the obstacle clearing manner, further comprises:
detecting whether the obstacle has been cleared;
if not, controlling the robot to execute re-obstacle clearing operation at the obstacle clearing position.
8. The utility model provides a clear barrier operation robot control method which characterized in that is applied to control robot and clears away the obstacle on the power transmission line, the robot is provided with the camera, includes:
the image acquisition module is used for acquiring images of the power transmission line in the moving direction through the camera when the robot moves on the power transmission line;
the obstacle detection result acquisition module is used for inputting the image into a pre-trained obstacle detection model to obtain an obstacle detection result, wherein the obstacle detection result comprises the type of an obstacle and the position of the obstacle;
the obstacle clearance position and mode determining module is used for determining an obstacle clearance position and an obstacle clearance mode according to the type of the obstacle and the position of the obstacle when the type of the obstacle is a specified type;
and the obstacle clearance module is used for controlling the robot to move to the obstacle clearance position and executing obstacle clearance operation in the obstacle clearance mode.
9. An obstacle clearing robot, comprising:
the camera, the memory and the obstacle clearance mechanism are all connected with the at least one processor, wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the obstacle clearing robot control method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores computer instructions for causing a processor to execute the obstacle clearing robot control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310173814.4A CN116117817A (en) | 2023-02-28 | 2023-02-28 | Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310173814.4A CN116117817A (en) | 2023-02-28 | 2023-02-28 | Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116117817A true CN116117817A (en) | 2023-05-16 |
Family
ID=86310102
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310173814.4A Pending CN116117817A (en) | 2023-02-28 | 2023-02-28 | Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116117817A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116721093A (en) * | 2023-08-03 | 2023-09-08 | 克伦斯(天津)轨道交通技术有限公司 | Subway rail obstacle detection method and system based on neural network |
-
2023
- 2023-02-28 CN CN202310173814.4A patent/CN116117817A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116721093A (en) * | 2023-08-03 | 2023-09-08 | 克伦斯(天津)轨道交通技术有限公司 | Subway rail obstacle detection method and system based on neural network |
| CN116721093B (en) * | 2023-08-03 | 2023-10-31 | 克伦斯(天津)轨道交通技术有限公司 | Subway rail obstacle detection method and system based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106341661B (en) | Patrol robot | |
| CN116117817A (en) | Obstacle clearing robot control method, obstacle clearing robot control device, robot and storage medium | |
| KR102043142B1 (en) | Method and apparatus for learning artificial neural network for driving control of automated guided vehicle | |
| CN116108397B (en) | Electric power field operation violation identification method integrating multi-mode data analysis | |
| CN107786848A (en) | The method, apparatus of moving object detection and action recognition, terminal and storage medium | |
| CN115294185B (en) | Pig weight estimation method and related equipment | |
| CN114419537A (en) | Power transmission line warning method and device based on deep learning | |
| CN114665608A (en) | Intelligent sensing inspection system and method for transformer substation | |
| CN116740833A (en) | Line inspection and card punching method based on unmanned aerial vehicle | |
| CN115272656A (en) | Environment detection alarm method and device, computer equipment and storage medium | |
| CN110197130B (en) | Abnormal gait detection equipment and system for live pigs | |
| KR102045161B1 (en) | Search system | |
| CN114359137A (en) | Satellite-ground integrated transmission line external damage monitoring method and device | |
| CN111959526B (en) | Unmanned vehicle-based control method and device, unmanned vehicle and electronic equipment | |
| CN114661057B (en) | Intelligent bionic biped inspection robot | |
| CN114049563B (en) | Live working environment evaluation method, working environment evaluation system and electronic equipment | |
| CN116700228A (en) | Robot path planning method, electronic device and readable storage medium | |
| CN111954188A (en) | Robot control method, device, terminal and medium | |
| EP3696406A1 (en) | A method for computer-implemented analysis of a wind farm comprising a number of wind turbines | |
| CN116913028A (en) | Power grid early warning method, device, equipment and medium | |
| CN114445395B (en) | Distribution line tree obstacle intelligent positioning method and device based on Internet and big data | |
| EP4350639A1 (en) | Safety rule violation detection in a construction or constructed site | |
| CN117456206A (en) | Overhead line external-breakage early warning method, system and equipment | |
| CN117671892A (en) | Construction site warning method, device, equipment and medium | |
| CN117170358A (en) | Path planning method, system, terminal and storage medium for test production line robot |
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 |