Voice control method and system of foot robot, electronic equipment and storage medium
By deploying a voice control system in the foot-type robot body, the problem of insufficient flexibility and responsiveness of manual control and touch screen interaction methods is solved, and the rapid recognition and real-time response of voice control are achieved, which is suitable for remote control and multi-task environments. Reduces data acquisition and training requirements, improves operation ease and control efficiency.
Patent Information
- Application Number
- CN202410692168.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-30
- Publication Date
- 2024-11-08
AI Technical Summary
The manual control and touch screen interaction methods of existing foot robots are not flexible and fast response, and it is difficult to adapt to sudden environment changes and remote operation scenarios. The voice control method depends on the network environment and has a low computing rate, requiring a large amount of data training.
Design a voice control method and system, by deploying a voice control system in the foot-type robot body, collecting voice signals based on preset time periods, generating voice control information, and generating action control instructions according to preset rules, controlling joint motors, and realizing Voice control. The system includes a voice acquisition module, a voice processing module and a motion control module, which can collect and process voice signals in standby and voice control states, independent of the external network environment.
It realizes the rapid recognition and real-time response of user voice commands, is flexible and convenient, and is suitable for remote control and multi-task environments, reducing data acquisition and training needs, improving operation simplicity and control efficiency.
Smart Images

Figure CN118918880A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of legged robots, and in particular to a voice control method and system, electronic equipment and storage medium for a legged robot. Background Art
[0002] A legged robot is a mobile robot with multiple legs that can move and perform tasks on various terrains. The design of a legged robot allows it to move freely on complex terrains, just like humans or animals.
[0003] At present, the control and interaction of legged robots are generally achieved through manual control or touch screen interactive control. However, the inventors of this application found that the manual control method has the problems of multiple control modes, complex interactions and low operational convenience. And although the touch screen interactive control method can provide users with convenient operations based on the user interaction interface, it also has the problem of difficulty in achieving rapid response to sudden environmental changes and not being well applicable to remote operation scenarios, and cannot meet the operator's friendly interactive experience.
[0004] Voice control can replace manual control or touch screen interactive control to control and interact with legged robots. Voice control can convert cumbersome and complex remote control or touch operation instructions into easy-to-understand voice instructions, which can improve the intelligent operability of legged robots. Summary of the invention
[0005] According to one aspect of the present application, the present application provides a voice control method for a legged robot, the method comprising: a voice control system collecting voice signals from a user based on a preset time period; generating voice control information according to the voice signal; determining whether the voice control information includes first preset information; in the case where it is determined that the voice control information includes the first preset information, adjusting the state of the voice control system to a voice control state; in the voice control state, generating action control instructions according to the first preset information; according to the action control instructions, controlling the joint motors of the legged robot to output corresponding joint torques so that the legged robot performs corresponding actions; wherein the voice control system is configured in the body of the legged robot.
[0006] According to some embodiments of the present application, the voice control method further includes: determining whether the voice control information includes second preset information; and if it is determined that the voice control information includes the second preset information, adjusting the state of the voice control system to a standby state.
[0007] According to some embodiments of the present application, the voice control system collects voice signals from the user based on a preset time period, including: judging the state of the voice control system; when the state is a standby state, the voice control system collects voice signals from the user within a first preset time period; when the state is a voice control state, the voice control system collects voice signals from the user within a second preset time period.
[0008] According to some embodiments of the present application, the voice control system collects voice signals from the user based on a preset time period, including: collecting original voice signals from the user based on a preset time period; and determining original voice signal segments in the original voice signal whose energy is greater than a preset energy threshold as voice signals.
[0009] According to some embodiments of the present application, generating voice control information based on a voice signal includes: generating voice coding information based on a voice signal; generating text word count information and audio vector information based on the voice coding information; generating text information based on the voice coding information and the audio vector information; generating voice control information based on the text information and the text word count information.
[0010] According to some embodiments of the present application, in a voice control state, generating an action control instruction based on first preset information includes: decomposing the first preset information based on preset rules to obtain decomposition information; matching and mapping the decomposition information with preset rule base information to obtain an action control instruction including multiple control instruction vectors.
[0011] According to another aspect of the present application, the present application provides a voice control system for a legged robot. The voice control system includes a voice acquisition module, a voice processing module, and a motion control module. The voice acquisition module is used to acquire voice signals from the user based on a preset time period; the voice processing module is used to generate voice control information according to the voice signal, and to determine whether the voice control information includes first preset information; the voice processing module adjusts the state of the voice control system to a voice control state when it is determined that the voice control information includes the first preset information; the motion control module is used to generate action control instructions according to the first preset information in the voice control state, and according to the action control instructions, control the joint motor of the legged robot to output the corresponding joint torque, so that the legged robot performs the corresponding action.
[0012] According to some embodiments of the present application, the voice processing module is also used to determine whether the voice control information includes second preset information; when the voice processing module determines that the voice control information includes the second preset information, the voice control system is adjusted to a standby state.
[0013] According to another aspect of the present application, an electronic device is provided, which includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors can implement the voice control method described above.
[0014] According to another aspect of the present application, a non-volatile computer-readable storage medium is provided, wherein a computer program is stored on the storage medium, and the computer program can implement the voice control method described above.
[0015] The voice control method provided by the present application can realize voice control of the legged robot independently by deploying the voice control system on the legged robot body, without being affected by the external network environment. The voice control method provided by the present application can realize rapid recognition of user voice commands according to the state of the voice control system, and has the characteristics of flexibility, convenient interaction and rapid real-time response.
[0016] The voice control method provided in the present application does not require data collection and training and can be quickly deployed; and when the voice control system is in a voice control state, multiple action instructions can be executed continuously by waking up with a wake-up action word once. It has the characteristics of simple control, convenient operation, and can meet remote control scenarios and is suitable for multi-tasking environments. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0018] Figure 1 A flow chart showing a voice control method according to an embodiment of the present application;
[0019] Figure 2 Another flow chart showing the voice control method according to an embodiment of the present application;
[0020] Figure 3 Another flow chart showing the voice control method according to an embodiment of the present application;
[0021] Figure 4 A schematic diagram showing speech processing according to an embodiment of the present application;
[0022] Figure 5 Another flow chart showing the voice control method according to an embodiment of the present application;
[0023] Figure 6Another schematic diagram showing speech processing according to an embodiment of the present application;
[0024] Figure 7 Another flow chart showing the voice control method according to an embodiment of the present application;
[0025] Figure 8 Another schematic diagram showing speech processing according to an embodiment of the present application;
[0026] Fig. 9 Another schematic diagram showing speech processing according to an embodiment of the present application;
[0027] Fig.10 Another flow chart showing the voice control method according to an embodiment of the present application;
[0028] Fig.11 A schematic diagram showing the structure of a voice control system according to an embodiment of the present application is shown.
[0029] Description of reference numerals:
[0030] Voice control system 1; voice collection module 10; voice processing module 20; motion control module 30. DETAILED DESCRIPTION
[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this application will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.
[0032] The described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of these specific details, or other modes, components, materials, devices, etc. may be adopted. In these cases, known structures, methods, devices, implementations, materials or operations will not be shown or described in detail.
[0033] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.
[0034] The terms "first", "second" and the like in the specification and claims of this application and the above drawings are used to distinguish different objects rather than to describe a specific order.
[0035] The following is a clear and complete description of the technical solution of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.
[0036] The inventor believes that the current control and interaction of legged robots based on manual control or touch screen interactive control still has at least the following problems:
[0037] 1. Lack of flexibility and fast real-time response
[0038] In some scenarios of sudden environmental changes, such as the need to respond to emergencies or quickly adjust the movements or behaviors of the legged robot, remote control operations or touch screen interactive operations may not be able to respond quickly and in real time due to response delays, which will affect the execution efficiency and safety of the legged robot.
[0039] 2. Limitations on interaction with users
[0040] In some specific situations, such as when the operator is currently handling other operation tasks, if the operator is required to operate the remote control or interact with the user interface at the same time, it will cause inconvenience to the user operation. Complex manual control devices or complex interactive interfaces will also increase the complexity of user interaction, thereby limiting user interaction.
[0041] 3. Insufficient operation convenience, difficult to cope with remote control scenarios
[0042] In some scenarios that require remote control, such as disaster rescue or complex terrain exploration where human resources cannot reach the scene directly, control methods based on remote control operation or touch screen interactive operation cannot implement remote control of legged robots.
[0043] 4. Unable to adapt to the challenges of multi-tasking environment
[0044] In multi-tasking scenarios or scenarios with changing environments, legged robots may need to quickly switch between different operation modes or execution strategies, but control methods based on remote control operations or touch screen interactive operations cannot provide sufficient response capabilities.
[0045] The inventors found that the above technical problems can be overcome by controlling the legged robot through voice control. However, the voice control method in the prior art configures the voice control model on the cloud server, which makes the voice control algorithm dependent on the network environment, and has the problems of limited application scenarios and relatively low computing speed. In addition, the current voice control method also has the problem of requiring a large amount of data for training and complex computing.
[0046] According to one aspect of the present application, the present application provides a voice control method for a legged robot, which can be executed by a voice control system.
[0047] Figure 1 A flow chart showing a voice control method according to an embodiment of the present application; Figure 2 Another flow chart showing the voice control method according to an embodiment of the present application; Figure 3 Another flow chart showing the voice control method according to an embodiment of the present application; Figure 4 A schematic diagram showing speech processing according to an embodiment of the present application is shown.
[0048] like Figure 1 As shown, the voice control method includes steps S100-S600.
[0049] According to an example embodiment, in step S100, the voice control system collects a voice signal from a user based on a preset time period.
[0050] For example, the preset time period may be customized according to user needs. The voice control system collects voice signals outside the legged robot through a microphone array arranged in the voice control system within each preset time period.
[0051] Alternatively, if Figure 2 As shown, step S100 may include steps S110 - S112 .
[0052] In step S110 , the voice control system determines the state of the voice control system.
[0053] For example, the state of the voice control system includes but is not limited to a standby state and a voice control state. The standby state may be that the voice control system is in an idle state (non-operating state); the voice control state may be that the voice control system is in a controlling state (operated state).
[0054] In step S110, if the voice control system determines that the state of the voice control system is the standby state, the process proceeds to step S111; otherwise, the process proceeds to step S112.
[0055] In step S111, when the voice control system is in a standby state, the voice control system collects a voice signal from the user within a first preset time period.
[0056] In step S112, when the state of the voice control system is the voice control state, the voice control system collects a voice signal from the user within a second preset time period.
[0057] For example, the first preset time period and the second preset time period may be set according to a user's own settings. Exemplarily, the first preset time period may be 15 seconds, and the second preset time period may be 8 seconds. It is understood that the first preset time period is significantly greater than the second preset time period.
[0058] The corresponding preset time period is determined according to the running state of the voice control system. When the voice control system is in a standby state (for example, in an idle state), by appropriately setting the first preset time period, unnecessary resource operations can be reduced. And when the voice control system is in a voice control state, by appropriately setting the second preset time period, the voice signal from the user can be obtained in a short time and the user command can be quickly responded to.
[0059] Alternatively, if Figure 3 As shown, step S100 may further include steps S120 - S121 .
[0060] In step S120, the voice control system collects an original voice signal from the user based on a preset time period.
[0061] In step S121, the voice control system determines the original voice signal segment whose energy in the original voice signal is greater than a preset energy threshold as a voice signal.
[0062] According to an exemplary embodiment, the voice control system determines the valid voice signal segment by endpoint detection based on a preset energy threshold. Figure 4 As shown, when the energy of the speech signal is greater than the preset energy threshold, the current position is determined to be the starting point of the valid speech signal segment; when the energy of the speech signal is less than the preset energy threshold, the current position is determined to be the end point of the valid speech signal segment. The generation of a valid speech signal is determined based on the valid speech signal segment. The preset energy threshold can be customized according to user needs.
[0063] The original speech signal collected by the microphone array is a whole speech signal and contains a lot of environmental noise. The speech control system cannot directly recognize the speech information contained in the original speech signal. By performing endpoint detection on the original speech signal through the above energy threshold method, the noise signal can be filtered out to achieve fast and accurate collection of effective speech signals.
[0064] In step S200, the voice control system generates voice control information according to the voice signal.
[0065] For example, the voice control system converts the voice signal into corresponding voice control information. For example, the voice control information may be operation instruction information from the user to the legged robot.
[0066] Figure 5 Another flow chart showing the voice control method according to an embodiment of the present application; Figure 6 Another schematic diagram showing the speech processing according to the embodiment of the present application.
[0067] Alternatively, if Figure 5 As shown, step S200 may also include steps S210-S240.
[0068] In step S210, the voice control system generates voice coding information according to the voice signal.
[0069] In step S220, the voice control system generates text word count information and audio vector information according to the voice coding information.
[0070] In step S230, the voice control system generates text information according to the voice coding information and the audio vector information.
[0071] In step S240, the voice control system generates voice control information according to the text information and the text word count information.
[0072] For example, Figure 6 As shown, when the voice control system performs voice recognition processing, the collected voice signal is mapped into voice coding information with a hidden representation through a preset encoder, and the voice coding information is mapped into corresponding text word count information and audio vector information through a preset predictor.
[0073] The voice control system also inputs the voice coding information and the audio vector information into a preset decoder to obtain text information. Finally, the voice control system combines the text word count information with the text information to achieve alignment processing of the voice information and the text information, thereby obtaining voice control information including text instructions.
[0074] Through the above non-autoregressive end-to-end model, parallel decoding can be achieved without recursively waiting for the decoding result, thereby improving the efficiency of speech recognition.
[0075] In step S300, the voice control system determines whether the voice control information includes first preset information.
[0076] In step S400, when the voice control system determines that the voice control information includes the first preset information, the voice control system adjusts the state of the voice control system to the voice control state.
[0077] In step S500, the voice control system generates an action control instruction according to first preset information in a voice control state.
[0078] For example, the first preset information may be customized according to user needs. The first preset information may be a keyword (action wake-up word) for the user to instruct the legged robot to perform a corresponding movement. For example, the keyword may be an imperative term such as "go forward", "go backward", "brake", "turn left", etc.
[0079] When the voice control system determines that the voice control information contains an action wake-up word, it enters the voice control state and generates a corresponding action control instruction according to the action wake-up word.
[0080] Figure 7 Another flow chart showing the voice control method according to an embodiment of the present application; Figure 8 Another schematic diagram showing the speech processing according to the embodiment of the present application.
[0081] Alternatively, if Figure 7 As shown, step S500 may further include steps S510-S520.
[0082] In step S510, the voice control system decomposes the first preset information based on a preset rule to obtain decomposed information.
[0083] In step S520, the voice control system matches and maps the decomposed information with the preset rule base information to obtain an action control instruction including a plurality of control instruction vectors.
[0084] For example, the voice control system decomposes the pinyin letters of the action wake-up word based on the preset word segmenter according to the preset rules, and maps the decomposed information with the preset instructions in the preset rule library to obtain the matched control instruction vector. The preset rule library can be customized according to user needs.
[0085] For example, Figure 8As shown, the voice control system obtains the "forward" instruction that matches the preset rule library according to the action wake-up word "walk forward", and obtains the control instruction vector of the "forward" instruction, such as Vx=1, Vy=0, W=0, H=0.5, Vx, Vy, W and H are the control instruction vectors. Vx represents the linear velocity of the legged robot in the x direction, Vy represents the linear velocity of the legged robot in the y direction, W represents the yaw angular velocity of the legged robot, and H represents the base height.
[0086] By using the above-mentioned rule-based natural language processing method for decomposing the action wake-up words into pinyin letters according to a preset word segmenter, the problem of language recognition errors caused by homophones in Chinese texts can be avoided, thereby improving the accuracy of language recognition processing.
[0087] In step S600, the voice control system controls the joint motors of the legged robot to output corresponding joint torques according to the action control instructions, so that the legged robot performs corresponding actions.
[0088] For example, the voice control system generates corresponding action control instructions based on the action wake-up word, and sends the action control instructions to the controller of the legged robot, so that the legged robot controller controls the joint motors of the legged robot to output corresponding joint torques (such as the torques of the 12 joint motors of the legged robot) according to the action control instructions, thereby realizing motion control of the legged robot based on voice control.
[0089] Fig. 9 Another schematic diagram showing speech processing according to an embodiment of the present application; Fig.10 Another flow chart of the voice control method according to an embodiment of the present application is shown.
[0090] For example, Fig. 9 As shown, after receiving the motion control instruction, the legged robot matches the current motion information, joint state information and base state information of the legged robot, determines and outputs the desired position of the joints of the legged robot according to the pre-trained multi-layer perceptron, and outputs the corresponding joint torque according to the PD controller (Proportional Derivative Control) to realize the operational control of the legged robot.
[0091] According to an example embodiment, the voice control system is configured in the body of the legged robot.
[0092] For example, the voice control system can be deployed to a local hardware device, and by configuring the local hardware device in the body of the legged robot, the legged robot can be made into an independent voice-controlled entity without being disturbed by the external environment.
[0093] Alternatively, if Fig.10As shown, the voice control method may further include steps S700-S800.
[0094] In step S700, the voice control system determines whether the voice control information includes second preset information.
[0095] In step S800, when it is determined that the voice control information includes the second preset information, the state of the voice control system is adjusted to a standby state.
[0096] The second preset information may be customized according to user needs. The second preset information may be a sleep keyword that instructs the voice control system to stop voice control. For example, the sleep keyword may be words such as "lie down" or "rest".
[0097] If the voice control system detects a sleep keyword during the voice control phase, the voice control of the legged robot is terminated and the voice control system is switched to a standby state.
[0098] Through the above embodiments, the voice control method provided by the present application can independently realize the voice control of the legged robot by deploying the voice control system on the legged robot body without being affected by the external network environment. The voice control method provided by the present application can realize the rapid recognition of the user's voice command according to the state of the voice control system, and has the characteristics of flexibility, convenient interaction and rapid real-time response.
[0099] The voice control method provided in the present application does not require data collection and training and can be quickly deployed; and when the voice control system is in a voice control state, multiple action instructions can be executed continuously by waking up with a wake-up action word once. It has the characteristics of simple control, convenient operation, and can meet remote control scenarios and is suitable for multi-tasking environments.
[0100] The voice control system designed by the voice control method provided in this application occupies relatively small storage space, and the complexity of the voice processing algorithm and the voice interaction algorithm is relatively low, and has the characteristics of low computing requirements. In addition, the control frequency of the voice control system can reach more than 100Hz, which can meet the high-frequency control requirements of the legged robot, and is suitable for offline environments such as the wild and disaster areas, and has good environmental adaptability.
[0101] According to another aspect of the present application, the present application provides a voice control system for a legged robot. Fig.11 A schematic diagram showing the structure of the voice control system of an embodiment of the present application is shown in FIG. Fig.11 As shown, the voice control system 1 includes a voice collection module 10 , a voice processing module 20 and a motion control module 30 .
[0102] According to an exemplary embodiment, the voice collection module 10 is used to collect a voice signal from a user based on a preset time period.
[0103] The voice processing module 20 is used to generate voice control information according to the voice signal and determine whether the voice control information includes the first preset information. When the voice processing module 20 determines that the voice control information includes the first preset information, it adjusts the state of the voice control system to the voice control state.
[0104] The motion control module 30 is used to generate motion control instructions according to the first preset information in the voice control state, and control the joint motors of the legged robot to output corresponding joint torques according to the motion control instructions, so that the legged robot performs corresponding actions.
[0105] Optionally, the voice processing module 20 is further configured to determine whether the voice control information includes the second preset information. When the voice processing module determines that the voice control information includes the second preset information, the voice control system is adjusted to a standby state.
[0106] The voice control system provided in the present application is used to execute the voice control method as described above. The voice control method has been described in detail above and will not be repeated here.
[0107] According to another aspect of the present invention, an electronic device is provided, which includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors can implement the voice control method described above.
[0108] According to another aspect of the present invention, a non-volatile computer-readable storage medium is provided, wherein a computer program is stored on the storage medium, and the computer program can implement the voice control method described above.
[0109] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application is described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions of the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.
Claims
1. A voice control method for a legged robot, characterized in that: include: The voice control system collects voice signals from the user based on a preset time period; generating voice control information according to the voice signal; Determining whether the voice control information includes first preset information; In the case where it is determined that the voice control information includes the first preset information, adjusting the state of the voice control system to a voice control state; In the voice control state, generating an action control instruction according to the first preset information; According to the action control instruction, control the joint motors of the legged robot to output corresponding joint torques, so that the legged robot performs corresponding actions; Wherein, the voice control system is configured in the body of the legged robot.
2. The voice control method according to claim 1, characterized in that: The voice control method further includes: Determining whether the voice control information includes second preset information; When it is determined that the voice control information includes the second preset information, the state of the voice control system is adjusted to a standby state.
3. The voice control method according to claim 1, characterized in that: The voice control system collects voice signals from the user based on a preset time period, including: Determining a state of the voice control system; When the state is the standby state, the voice control system collects a voice signal from the user within a first preset time period; When the state is the voice control state, the voice control system collects a voice signal from the user within a second preset time period.
4. The voice control method according to claim 1, characterized in that: The voice control system collects voice signals from the user based on a preset time period, including: Collecting an original voice signal from a user based on the preset time period; An original speech signal segment whose energy in the original speech signal is greater than a preset energy threshold is determined as the speech signal.
5. The voice control method according to claim 1, characterized in that: Generating voice control information according to the voice signal comprises: Generating speech coding information according to the speech signal; Generate text word count information and audio vector information according to the speech coding information; Generate text information according to the speech coding information and the audio vector information; The voice control information is generated according to the text information and the text word count information.
6. The voice control method according to claim 1, characterized in that: In the voice control state, generating an action control instruction according to the first preset information includes: Decomposing the first preset information based on a preset rule to obtain decomposed information; The decomposition information is matched and mapped with the preset rule base information to obtain an action control instruction including a plurality of control instruction vectors.
7. A voice control system for a legged robot, characterized in that: The voice control system is configured in the body of the legged robot, and the voice control system includes: A voice collection module, used to collect voice signals from users based on a preset time period; a voice processing module, configured to generate voice control information according to the voice signal, and to determine whether the voice control information includes first preset information; if the voice processing module determines that the voice control information includes the first preset information, the voice control system is adjusted to a voice control state; The motion control module is used to generate action control instructions according to the first preset information in the voice control state, and control the joint motors of the footed robot to output corresponding joint torques according to the action control instructions, so that the footed robot performs corresponding actions.
8. The voice control system according to claim 7, characterized in that: The voice processing module is also used to determine whether the voice control information includes second preset information; When the voice processing module determines that the voice control information includes the second preset information, the voice control system is adjusted to a standby state.
9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the voice control method as described in any one of claims 1-6.
10. A non-volatile computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program implements the voice control method as described in any one of claims 1-6.
Citation Information
Cited By
Robot control method and device, computer equipment, readable storage medium and program product
CN120002666A
