Dual-end voice interactive control method and system for electric tunnel track robot

Abstract

The present invention provides a dual-end voice interactive control system and method for an electric tunnel robot, comprising a robot body, a controller and a communication module, wherein the controller is connected to the communication module, wherein the communication module adopts a dual-channel setting, one channel is connected to an on-site voice acquisition module, and the other channel is connected to a remote voice communication module; the controller is used to receive a voice signal from an on-site or remote control platform through the communication module, and convert the voice signal into a corresponding robot control signal based on a voice recognition model, so as to control the robot to perform a corresponding task.

Description

Technical Field

[0001] The present invention belongs to the technical field related to robot dispatching control, and in particular relates to a two-end voice interaction control method and system for a power tunnel track robot. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The power tunnel is like the main artery of a city, continuously delivering electricity to thousands of households. The safety of the power tunnel is the prerequisite for the normal operation of the entire city.

[0004] In recent years, with the continuous improvement of informatization, robots have been used more and more widely in power tunnels. The control methods of traditional operation robots are mostly limited to terminal devices such as desktop computers and laptops, which maintenance personnel cannot carry with them when going down the tunnel. At the same time, maintenance personnel sometimes rely on video images of different positions collected by track robots and other functional operations during the maintenance process. However, track robots are usually suspended at high altitudes, and there is a certain inconvenience in manually operating the robots. Maintenance personnel in the tunnel can only request external personnel to assist in control, and the real-time and accuracy of external personnel's assisted control cannot effectively meet the needs of maintenance personnel, resulting in a poor user experience. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a two-end voice interactive control method and system for an electric tunnel track robot. The scheme controls the electric tunnel robot through voice, and adopts a dual-channel setting for its communication module, one channel is connected to the on-site voice acquisition module, and the other channel is connected to the remote voice communication module; and based on the voice recognition model, the voice signal is converted into a corresponding robot control signal to control the robot to perform the corresponding task, which can realize on-site human-machine voice dialogue and can also interact with the back-end user at the same time, meet the special needs in the power industry, and improve the user experience.

[0006] According to a first aspect of an embodiment of the present invention, there is provided a dual-end voice interactive control system for a power tunnel robot, comprising a robot body, a controller and a communication module, wherein the controller is connected to the communication module, wherein the communication module adopts a dual-channel setting, one channel is connected to an on-site voice acquisition module, and the other channel is connected to a remote voice communication module;

[0007] The controller is used to receive voice signals from an on-site or remote control platform through the communication module, and convert the voice signals into corresponding robot control signals based on a voice recognition model to control the robot to perform corresponding working tasks.

[0008] Furthermore, the speech recognition model adopts a dynamic time warping algorithm to extract keywords in the speech based on the trained speech recognition model, determines the control instructions corresponding to the current keywords based on a preset mapping relationship table between keywords and control instructions, and implements the robot's job scheduling based on the control instructions.

[0009] Furthermore, when the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to a preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot.

[0010] Furthermore, the preset priority adopts the remote voice signal control to be greater than the on-site voice signal control; or

[0011] The far-end voice signal control is smaller than the on-site voice signal control.

[0012] Furthermore, the voice collection module adopts a microphone array composed of a plurality of microphones, and the voice collection module is installed at the bottom of the robot body.

[0013] Furthermore, the tunnel robot is controlled based on the on-site user's voice, follows the user to conduct collaborative inspections, and records the inspection results based on the user's voice and uploads them to the remote control platform.

[0014] Furthermore, the remote voice communication module adopts a wireless communication module or a wired communication module.

[0015] According to a second aspect of an embodiment of the present invention, a two-terminal voice interactive control method for a power tunnel track robot is provided, which utilizes the above-mentioned two-terminal voice interactive control system for a power tunnel robot, and the method includes:

[0016] receiving a voice signal;

[0017] Converting the speech signal into a corresponding robot control signal based on a speech recognition model to control the robot to perform a corresponding task;

[0018] Among them, when the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to the preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot.

[0019] According to a third aspect of an embodiment of the present invention, there is provided an electronic device comprising a memory, a processor and a computer program stored and running on the memory, wherein when the processor executes the program, the two-end voice interactive control method for a power tunnel rail robot is implemented.

[0020] According to a fourth aspect of an embodiment of the present invention, a non-transitory computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the two-terminal voice interactive control method for a power tunnel rail robot is implemented.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] (1) The present invention provides a dual-end voice interactive control method and system for a power tunnel rail robot. The scheme controls the power tunnel robot through voice, and adopts a dual-channel setting for its communication module, one channel is connected to the on-site voice acquisition module, and the other channel is connected to the remote voice communication module; and based on the voice recognition model, the voice signal is converted into a corresponding robot control signal to control the robot to perform the corresponding task; it effectively solves the problem that maintenance personnel are inconvenient to carry the robot control equipment into the tunnel and cannot effectively control the robot, that is, it can realize on-site human-machine voice dialogue and can also interact with the back-end users at the same time, meet the special needs of the power industry, and improve the user experience effect.

[0023] (2) In the power tunnel, there are a large number of transmission lines and various components in operation, which will generate strong noise interference. Ordinary voice acquisition modules cannot clearly collect the voice signals of users on site, resulting in inaccurate voice signal recognition. The solution of the present invention fully considers the actual problems in tunnel inspection. By adopting a microphone array setting, the noise signal is effectively shielded, and the receiving range of the voice signal can be effectively expanded to ensure the accuracy of voice signal acquisition.

[0024] (3) Considering that power tunnel robots are usually suspended, the audio signals of on-site users can be collected more effectively by setting the voice collection device at the bottom of the robot body.

[0025] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0027] Figure 1 It is a schematic diagram of the structure of a two-terminal voice interactive control system for a power tunnel track robot described in an embodiment of the present invention;

[0028] Figure 2 It is a schematic diagram of an application scenario of a two-end voice interactive control for a power tunnel track robot described in an embodiment of the present invention;

[0029] Figure 3 Schematic diagram of the robot voice keyword command described in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0031] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0032] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0033] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0034] Embodiment 1:

[0035] The purpose of this embodiment is to provide a two-terminal voice interaction control system for a power tunnel robot.

[0036] A dual-end voice interactive control system for an electric power tunnel robot, comprising a robot body, a controller and a communication module, wherein the controller is connected to the communication module, wherein the communication module adopts a dual-channel setting, one channel is connected to an on-site voice acquisition module, and the other channel is connected to a remote voice communication module;

[0037] The controller is used to receive voice signals from an on-site or remote control platform through the communication module, and convert the voice signals into corresponding robot control signals based on a voice recognition model to control the robot to perform corresponding working tasks.

[0038] Furthermore, the speech recognition model adopts a dynamic time warping algorithm to extract keywords in the speech based on the trained speech recognition model, determines the control instructions corresponding to the current keywords based on a preset mapping relationship table between keywords and control instructions, and implements the robot's job scheduling based on the control instructions.

[0039] The dynamic time warping algorithm (DTW: Dynamic Time Warping) is specifically:

[0040] Step 1: Calculate the distance matrix between each point of the two sequences;

[0041] Step 2: Find a path from the upper left corner to the lower right corner of the matrix so that the elements on the path and the path length of the minimum matrix from the upper left corner to the lower right corner have the following properties:

[0042] Current path length = path length of the previous step + size of the current element;

[0043] For an element (i, j) on the path, its previous element can only be one of the following three:

[0044] a) The adjacent element on the left (i, j-1);

[0045] b) The adjacent element above (i-1, j);

[0046] c) The adjacent element to the upper left (i-1, j-1);

[0047] Assume the matrix is ​​M, and the shortest path length from the upper left corner of the matrix (1,1) to any point (i,j) is Lmin(i,j). Then the recursive algorithm can be used to calculate the shortest path length:

[0048] Starting conditions:

[0049] L min (1, 1) = M (1, 1)

[0050] Recursion rules:

[0051] L min (i, j) = min{L min (i, j-1), L min (i-1, j), L min (i-1, j-1)}+M(i, j)

[0052] The reason why the recursive rule is written like this is because the shortest path of the current element must be the length of the shortest path from the previous element plus the value of the current element. There are three possibilities for the previous element, and we can choose the one with the shortest path among the three possibilities.

[0053] Furthermore, when the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to a preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot.

[0054] Furthermore, the preset priority adopts the remote voice signal control to be greater than the on-site voice signal control; or

[0055] The far-end voice signal control is smaller than the on-site voice signal control.

[0056] Furthermore, the voice collection module adopts a microphone array composed of a plurality of microphones, and the voice collection module is installed at the bottom of the robot body.

[0057] Furthermore, the tunnel robot is controlled based on the on-site user's voice, follows the user to conduct collaborative inspections, and records the inspection results based on the user's voice and uploads them to the remote control platform.

[0058] Furthermore, the remote voice communication module adopts a wireless communication module or a wired communication module.

[0059] Specifically, for ease of understanding, the solution of the present invention is described in detail below with reference to the accompanying drawings:

[0060] A dual-end voice interactive control system for an electric power tunnel robot, comprising a robot body, a controller and a communication module, wherein the controller is connected to the communication module, wherein the communication module adopts a dual-channel setting, one channel is connected to an on-site voice acquisition module, and the other channel is connected to a remote voice communication module;

[0061] The controller is used to receive voice signals from an on-site or remote control platform through the communication module, and convert the voice signals into corresponding robot control signals based on a voice recognition model to control the robot to perform corresponding working tasks.

[0062] Among them, Figure 1 As shown, the system can be divided into: a picking module, a playing module, a recognition module, and a business module; the direction of the arrow represents the data processing flow, where the voice information is first received by the picking module and then transferred to the recognition module. After recognition and analysis, the corresponding business processing flow is scheduled and the execution result is played to the user in the form of voice.

[0063] Among them, the picking template is used to collect and receive voice elements. Specifically, the picking module includes a voice collection module for collecting user's on-site voice signals. The voice collection module adopts a microphone array composed of several microphones and is installed at the bottom of the robot body.

[0064] The advantages of the above settings include the following two aspects:

[0065] On the one hand, there are a large number of transmission lines and various components in operation in the power tunnel, which will generate strong noise interference. Ordinary voice acquisition modules cannot clearly collect the voice signals of users on site, resulting in inaccurate voice signal recognition. The solution of the present invention fully considers the actual problems in tunnel inspection. By adopting a microphone array setting, the noise signal is effectively shielded, and the receiving range of the voice signal can be effectively expanded to ensure the accuracy of voice signal acquisition.

[0066] On the other hand, considering that power tunnel robots are usually suspended, the audio signals of on-site users can be collected more effectively by setting the voice collection device at the bottom of the robot body.

[0067] The playback module is used to play sounds to achieve a voice dialogue effect. It is used to give a voice reply to the completion status of user instructions. The playback module is connected to the main controller. When the main controller detects that the current job is completed, it controls the playback module to perform voice broadcasting.

[0068] The recognition module is used to recognize key words from speech elements. Specifically, the recognition module extracts key words from speech based on a built-in speech recognition model and a trained speech recognition model, and determines the control instruction corresponding to the current keyword based on a preset mapping relationship table between key words and control instructions.

[0069] The business module dispatches robots to complete business tasks through control instructions determined by keywords.

[0070] The communication module of the system adopts a dual-end voice processing method, one channel receives the voice commands of the on-site user and the other channel receives the voice commands of the back-end user.

[0071] like Figure 2 As shown in the figure, the actual application scenario of intelligent voice is demonstrated. Usually, the intelligent voice module is installed inside the robot. The microphone of the robot is the pickup module, and the speaker is the playback module. The robot is suspended on the track above the tunnel and can move freely forward and backward. The user can communicate with the robot through the voice function. The back-end platform is deployed in the work area environment far away from the tunnel. The microphone connected to the computer is the pickup module, and the speaker is the playback module. In this way, voice can also be used to communicate with the robot and dispatch the robot to work.

[0072] like Figure 3As shown in the figure, combined with the robot's business-specific, keyword instructions are divided into three types, namely wake-up instructions, inquiry instructions, and control instructions. The wake-up instruction can wake up the dormant voice function, and after waking up, you can communicate with the robot. After a certain period of no voice communication, the robot automatically enters the dormant mode; the inquiry instruction mainly asks the robot about the operating status, monitoring data, inspection results, etc.; the control instruction can control the robot's forward and backward movement, scheduling charging, immediate inspection, and other operations. The wake-up instruction and inquiry instruction do not involve the control of the robot, and can process business requests from the back-end and users in the tunnel at the same time. The control instruction only allows one user to control. When a control conflict occurs, it is necessary to wait for the previous user to complete the action instruction before intervening.

[0073] Furthermore, the solution of the present invention does not require carrying hardware equipment for controlling the robot, and the robot can be operated by voice commands. The following effect can be achieved through voice, and the robot can determine the location of the personnel through voice. If necessary, it can follow the staff to inspect the cable line and record the inspection results by voice.

[0074] Furthermore, when the robot detects an abnormal situation, the solution of the present invention can broadcast it in the tunnel by voice, and the staff can understand the specific content of the situation through voice dialogue.

[0075] Furthermore, on the platform side, voice commands are monitored in real time, and device information can be directly queried through voice interaction commands, with questions asked by voice and responses given by voice; or interface data can be displayed according to the commands, with questions asked by voice and responses given by the interface.

[0076] Furthermore, the solution of the present invention uses a question-and-answer method to achieve a dialogue effect, and the type of answering voice can be changed through configuration, such as: female voice, male voice, robot voice, etc.

[0077] Furthermore, the background of the solution of the present invention adopts a high-speed voice processing module, including modules such as command recognition, command analysis, and command processing, which has a fast response speed and low latency, and can reach the speed of communicating with everyone.

[0078] Embodiment 2:

[0079] The purpose of this embodiment is to provide a two-terminal voice interactive control method for an electric tunnel track robot.

[0080] A two-end voice interaction control method for a power tunnel track robot, which utilizes the two-end voice interaction control system for a power tunnel robot described in the first embodiment, and the method comprises:

[0081] receiving a voice signal;

[0082] Converting the speech signal into a corresponding robot control signal based on a speech recognition model to control the robot to perform a corresponding task;

[0083] Among them, when the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to the preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot.

[0084] In further embodiments, there is also provided:

[0085] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 1 is performed. For the sake of brevity, no further description is given here.

[0086] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0087] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0088] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method described in embodiment 1 is completed.

[0089] The method in the first embodiment can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0090] Those skilled in the art will appreciate that the units, i.e., algorithm steps, of the various examples described in the present embodiment can be implemented in electronic hardware or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0091] The two-terminal voice interaction control system and method for a power tunnel robot provided in the above-mentioned embodiment can be realized and has broad application prospects.

[0092] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A two-terminal voice interactive control system for a power tunnel robot, characterized in that: It includes a robot body, a controller and a communication module, wherein the controller is connected to the communication module, wherein the communication module adopts a dual-channel setting, one channel is connected to the on-site voice collection module, and the other channel is connected to the remote voice communication module; The controller is used to receive voice signals from the on-site or remote control platform through the communication module, and convert the voice signals into corresponding robot control signals based on the voice recognition model to control the robot to perform corresponding operation tasks; The speech recognition model adopts a dynamic time warping algorithm, extracts keywords from the speech based on the trained speech recognition model, determines the control instruction corresponding to the current keyword based on a preset mapping relationship table between keywords and control instructions, and implements the robot's job scheduling based on the control instruction; When the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to the preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot; The voice collection module adopts a microphone array composed of a plurality of microphones, and the voice collection module is installed at the bottom of the robot body.

2. A two-terminal voice interactive control system for a power tunnel robot as claimed in claim 1, characterized in that: The preset priority adopts the remote voice signal control to be greater than the on-site voice signal control; or The far-end voice signal control is smaller than the on-site voice signal control.

3. A two-terminal voice interactive control system for a power tunnel robot as claimed in claim 1, characterized in that: The tunnel robot is controlled by the on-site user voice, follows the user to conduct collaborative inspections, and records the inspection results based on the user's voice and uploads them to the remote control platform.

4. A two-terminal voice interactive control system for a power tunnel robot as claimed in claim 1, characterized in that: The remote voice communication module adopts a wireless communication module or a wired communication module.

5. A two-terminal voice interactive control method for a power tunnel track robot, characterized in that: It utilizes a two-end voice interactive control system for a power tunnel robot as described in any one of claims 1 to 4, and the method comprises: receiving a voice signal; Converting the speech signal into a corresponding robot control signal based on a speech recognition model to control the robot to perform a corresponding task; Among them, when the controller receives two voice signals at the same time, it selects the voice signal of one channel for processing according to the preset priority, determines the control instruction corresponding to the voice signal of the current channel, and realizes the operation scheduling of the robot.

6. An electronic device comprising a memory, a processor and a computer program stored and running on the memory, characterized in that: When the processor executes the program, the two-terminal voice interactive control method for a power tunnel track robot as described in claim 5 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a two-terminal voice interactive control method for a power tunnel track robot as described in claim 5 is implemented.

Images