Intelligent robot and control system thereof
By combining target task instructions and robot vision data, an execution strategy is generated and the operation status is adjusted in real time. This solves the problems of low task execution efficiency and insufficient safety of existing robot systems in unsupervised environments, and achieves efficient and safe task execution.
Patent Information
- Application Number
- CN202410993274.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
Existing robotic systems have limited capabilities in handling complex tasks in unsupervised environments, particularly in understanding and executing natural language instructions. Their visual perception capabilities are separated from the task execution process, leading to fragmented information processing and insufficient security.
By acquiring target task instructions and robot vision data, and combining large language models and computer vision technology, execution strategies are generated, and the operational and environmental states are adjusted in real time to ensure the safety and accuracy of task execution.
It achieves the safety and accuracy of target tasks in an unsupervised environment, enhances the autonomy and intelligence of the robot system, and ensures the efficiency and safety of task execution.
Smart Images

Figure CN118927242A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent robot control, and in particular to an intelligent robot control system and an intelligent robot. Background Art
[0002] In the current industry trend, robotic systems that integrate artificial intelligence, natural language processing and computer vision are becoming a hot topic in research and development. The autonomy, flexibility and intelligence of such systems are constantly improving. However, the problem with related technologies is that existing robotic systems have limited processing capabilities for complex tasks, especially in understanding and executing natural language instructions. In addition, the robot's visual perception ability is often separated from the task execution process, resulting in fragmented information processing processes and low efficiency. In addition, security is also a shortcoming of the current system, which is particularly important in unsupervised operating environments. Summary of the invention
[0003] The present invention aims to solve one of the technical problems in the related art at least to a certain extent. To this end, the first object of the present invention is to provide a control method for an intelligent robot, which can ensure the safety and accuracy of target task execution in an unsupervised environment.
[0004] A second object of the present invention is to provide a computer-readable storage medium.
[0005] The third objective of the present invention is to provide a control device for an intelligent robot.
[0006] The fourth objective of the present invention is to provide an intelligent robot.
[0007] To achieve the above-mentioned objectives, the control method of an intelligent robot proposed in an embodiment of the first aspect of the present invention includes: obtaining target task instructions and robot vision data; controlling the intelligent robot to perform the target task according to the target task instructions and the robot vision data; and in the process of controlling the intelligent robot to perform the target task, adjusting the operating state and / or environmental state of the intelligent robot according to the robot vision data.
[0008] According to the control method of the intelligent robot of the embodiment of the present invention, the target task instruction and the robot vision data are obtained, and then, according to the target task instruction and the robot vision data, the intelligent robot is controlled to perform the target task, and, in the process of controlling the intelligent robot to perform the target task, the operation state and / or environmental state of the intelligent robot are adjusted according to the robot vision data. Thus, by combining the target task instruction with the visual perception ability of the intelligent robot, accurate target task execution is achieved, and at the same time, in the process of controlling the intelligent robot to perform the target task, the operation state and / or environmental state of the intelligent robot are adjusted in real time using the robot vision data, thereby ensuring the safety and accuracy of the target task execution in an unsupervised environment.
[0009] In addition, the control system of the intelligent robot according to the above embodiment of the present invention may also have the following additional technical features:
[0010] According to one embodiment of the present invention, obtaining the target task instructions includes: obtaining user voice instructions and preprocessing the user voice instructions; using a large language model to perform feature extraction on the preprocessed user voice instructions to obtain semantic information corresponding to the user voice instructions; and generating the target task instructions based on the semantic information corresponding to the user voice instructions.
[0011] According to one embodiment of the present invention, controlling the intelligent robot to perform the target task includes: generating operating environment information of the intelligent robot based on the robot vision data; and controlling the intelligent robot to execute the target task instructions based on the operating environment information.
[0012] According to one embodiment of the present invention, in the process of controlling the intelligent robot to perform a target task, the method further includes: when the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, adjusting the operating state and / or environmental state of the intelligent robot.
[0013] According to one embodiment of the present invention, the adjustment includes: controlling the intelligent robot to execute a fallback instruction or a stop instruction.
[0014] According to an embodiment of the present invention, the method further includes: obtaining an execution result of the target task; and adjusting the target task instruction according to the execution result.
[0015] According to an embodiment of the present invention, the method further includes: obtaining a user correction instruction; and adjusting the target task instruction according to the user correction instruction.
[0016] To achieve the above-mentioned purpose, the second aspect of the present invention proposes a computer-readable storage medium, on which a control program of an intelligent robot is stored. When the control program of the intelligent robot is executed by a processor, the control method of the intelligent robot of the above-mentioned embodiment of the present invention is implemented.
[0017] According to the computer-readable storage medium of the embodiment of the present invention, by executing the control program of the intelligent robot stored thereon, it is possible to ensure the safety and accuracy of the execution of the target task in an unsupervised environment.
[0018] To achieve the above-mentioned purpose, the control device of the intelligent robot proposed in the third aspect of the embodiment of the present invention includes: an acquisition module, used to acquire target task instructions and robot vision data; a control module, used to control the intelligent robot to perform the target task according to the target task instructions and the robot vision data; an adjustment module, used to adjust the operating state and / or environmental state of the intelligent robot according to the robot vision data during the process of the intelligent robot performing the target task.
[0019] According to the control device of the intelligent robot of the embodiment of the present invention, the target task instruction and the robot vision data are acquired by the acquisition module, and then, the intelligent robot is controlled to perform the target task according to the target task instruction and the robot vision data by the control module, and the operation state and / or environmental state of the intelligent robot are adjusted according to the robot vision data in the process of controlling the intelligent robot to perform the target task by the adjustment module. Thus, accurate target task execution is achieved by combining the target task instruction with the visual perception ability of the intelligent robot, and at the same time, in the process of controlling the intelligent robot to perform the target task, the operation state and / or environmental state of the intelligent robot are adjusted in real time using the robot vision data, thereby ensuring the safety and accuracy of the target task execution in an unsupervised environment.
[0020] To achieve the above-mentioned purpose, the intelligent robot proposed in the fourth aspect of the present invention includes the control device of the intelligent robot of the above-mentioned embodiment of the present invention.
[0021] The intelligent robot according to the embodiment of the present invention can ensure the safety and accuracy of the execution of the target task in an unsupervised environment by adopting the control device of the intelligent robot.
[0022] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention;
[0024] Figure 2 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention;
[0025] Figure 3 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention;
[0026] Figure 4 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention;
[0027] Figure 5 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention;
[0028] Figure 6 is a schematic diagram of the principle of a control method for an intelligent robot according to an embodiment of the present invention;
[0029] Figure 7 is a block diagram of a control system of an intelligent robot according to an embodiment of the present invention;
[0030] Figure 8 is a block diagram of an intelligent robot according to an embodiment of the present invention. DETAILED DESCRIPTION
[0031] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0032] The following describes a control method for an intelligent robot, a computer-readable storage medium, a control device for an intelligent robot, and an intelligent robot according to embodiments of the present invention with reference to the accompanying drawings.
[0033] Figure 1 4 is a flow chart of a control method for an intelligent robot according to an embodiment of the present invention.
[0034] Specifically, in some embodiments of the present invention, Figure 1 As shown, the control method of the intelligent robot includes:
[0035] S101, obtaining target task instructions and robot vision data.
[0036] It can be understood that in this embodiment of the present invention, the intelligent robot can receive user voice commands through a microphone, and then the voice recognition unit of the intelligent robot can be responsible for parsing and understanding the user voice commands, and converting the user voice commands into target task commands that the intelligent robot can understand. In addition, the intelligent robot can also obtain robot visual data through the visual perception unit of the intelligent robot.
[0037] Optionally, the robot vision data may include object recognition data, environmental analysis data, and spatial positioning data.
[0038] Specifically, in the above-mentioned embodiments of the present invention, computer vision technology (for example, convolutional neural network CNN, etc.) can be used to analyze the images collected by the visual perception unit to obtain object recognition data (this data is used to enable the intelligent robot to recognize and understand the objects in the image), environmental analysis data (this data is used to enable the intelligent robot to recognize and understand the environment in the image) and spatial positioning data (this data is used to enable the intelligent robot to recognize and understand the relative positions of various objects in the image).
[0039] S102, controlling the intelligent robot to execute the target task according to the target task instruction and the robot vision data.
[0040] It can be understood that in this embodiment of the present invention, by combining the robot vision data and the target task instructions, an execution strategy corresponding to the target task instructions can be generated, such as the travel path planning of the intelligent robot and the robotic arm operation of the intelligent robot, thereby controlling the intelligent robot to perform the corresponding target task through precise robot visual perception, thereby ensuring the accuracy of the target task execution in an unsupervised environment.
[0041] Optionally, in the above-mentioned embodiments of the present invention, the intelligent robot can be controlled to perform corresponding target tasks by combining robot vision data with data from other sensors (for example, touch, sound, etc.), thereby further improving the accuracy of the execution of the target tasks.
[0042] S103, in the process of controlling the intelligent robot to perform the target task, adjusting the operating state and / or environmental state of the intelligent robot according to the robot vision data.
[0043] It can be understood that in this embodiment of the present invention, in the process of controlling the intelligent robot to perform the target task, the operating state and / or environmental state of the intelligent robot can also be adjusted in real time according to the robot vision data, so that the operating state and / or environmental state of the intelligent robot are consistent with the operating state and / or environmental state corresponding to the target task instruction, thereby ensuring the accuracy of the target task execution in an unsupervised environment.
[0044] Further, in some embodiments of the present invention, Figure 2 As shown, the target task instruction includes:
[0045] S201, obtaining user voice commands and preprocessing the user voice commands.
[0046] It is understandable that, in this embodiment of the present invention, the speech recognition unit may perform pre-processing such as noise reduction, noise elimination, and enhancement on the collected user voice commands to improve the accuracy of speech recognition.
[0047] S202: Using a large language model to perform feature extraction on the preprocessed user voice command to obtain semantic information corresponding to the user voice command.
[0048] It can be understood that in this embodiment of the present invention, the speech recognition unit has a built-in large language model, wherein the large language model adopts advanced natural speech processing algorithms (for example, deep learning, contextual understanding, etc.), and the speech recognition unit can also use the large language model to perform feature extraction on the preprocessed user voice instructions to accurately obtain the semantic information corresponding to the user voice instructions.
[0049] S203: Generate a target task instruction according to the semantic information corresponding to the user's voice instruction.
[0050] It can be understood that in this embodiment of the present invention, the semantic information corresponding to the user's voice command can be converted into a target task instruction, wherein the target task instruction can include the visual task of the intelligent robot and the action plan of the intelligent robot.
[0051] Further, in some embodiments of the present invention, Figure 3 As shown, controlling the intelligent robot to perform the target task includes:
[0052] S301, generating operating environment information of the intelligent robot according to robot vision data.
[0053] It can be understood that in this embodiment of the present invention, when the intelligent robot receives the target task instruction, it can generate the operating environment information of the intelligent robot based on the visual data, wherein the operating environment information may include: the current position of the intelligent robot, the current position of the robotic arm of the intelligent robot, the relative distance between the intelligent robot and various objects in the task execution environment, etc.
[0054] S302, controlling the intelligent robot to execute target task instructions according to the operating environment information.
[0055] It can be understood that in this embodiment of the present invention, the intelligent robot is controlled to execute the target task instructions by combining the operating environment information, thereby combining the target task execution process of the intelligent robot with the visual perception ability of the intelligent robot to achieve accurate target task execution.
[0056] Furthermore, in some embodiments of the present invention, in the process of controlling the intelligent robot to perform a target task, the method also includes: when the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, adjusting the operating state and / or environmental state of the intelligent robot.
[0057] It can be understood that in this embodiment of the present invention, in the process of controlling the intelligent robot to perform the target task, it can be determined in real time whether the operating environment information is consistent with the operating environment information corresponding to the target task instruction. When the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, for example, when the target task instruction is to control the intelligent robot to go to the kitchen to move the pots on the stove to the sink, and based on the operating environment information, it is monitored that the intelligent robot is moving to the master bedroom or the guest room, or, based on the operating environment information, it is monitored that the intelligent robot moves the bowls on the stove, or, based on the operating environment information, it is monitored that the intelligent robot moves the pots on the stove to the disinfection cabinet, etc. At this time, it can be considered that the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, and the intelligent robot has not correctly executed the target task instruction. It is necessary to adjust the operating state and / or environmental state of the intelligent robot, thereby ensuring the safety and accuracy of the execution of the target task in an unsupervised environment.
[0058] Furthermore, in some embodiments of the present invention, the adjustment includes: controlling the intelligent robot to execute a backoff instruction or a stop instruction.
[0059] It can be understood that in this embodiment of the present invention, when the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, the intelligent robot can be controlled to execute a fallback instruction or a stop instruction, so that the intelligent robot performs a fallback operation or a static operation, thereby preventing the intelligent robot from erroneously executing the target task instruction. Thus, in an unsupervised environment, the intelligent robot can respond to potential faults and risks in a timely manner to ensure the safety of the target task execution.
[0060] Further, in some embodiments of the present invention, Figure 4 As shown, the method also includes:
[0061] S401, obtaining the execution result of the target task.
[0062] It can be understood that in this embodiment of the present invention, after executing the target task instructions, the intelligent robot can also upload the execution results of the target task to the cloud for storage as learning data, wherein the execution results of the target task may include the execution strategy of the target task instructions, the execution time of the target task instructions and the number of adjustments of the target task instructions.
[0063] S402: Adjust the target task instruction according to the execution result.
[0064] It can be understood that in this embodiment of the present invention, the optimization points of the execution results of each target task can be analyzed by using machine learning algorithms (for example, reinforcement learning, pattern recognition, etc.), for example, adjustment of the execution strategy (including but not limited to the movement speed of the robotic arm, the movement angle of the robotic arm, the movement accuracy of the robotic arm, the movement speed of the intelligent robot, etc.), adjustment of the execution time (for example, selecting the target task execution instruction with the shortest execution time), and adjustment of the number of executions (for example, selecting the target task execution instruction with the least number of adjustments).
[0065] Specifically, in the above-mentioned embodiments of the present invention, the intelligent robot can utilize historical execution data and operating environment information to dynamically adjust target task instructions, so that the intelligent robot can adopt a better execution strategy for the same target task instructions to achieve more efficient task execution, thereby improving the efficiency and adaptability of the intelligent robot's long-term operation.
[0066] Further, in some embodiments of the present invention, Figure 5 As shown, the method also includes:
[0067] S501, obtaining a user correction instruction.
[0068] It can be understood that, in this embodiment of the present invention, the speech recognition unit can also receive a user correction instruction initiated by the user during the process of controlling the intelligent robot to perform the target task.
[0069] S502: Adjust the target task instruction according to the user correction instruction.
[0070] It can be understood that, in this embodiment of the present invention, after receiving the user correction instruction, the intelligent robot can also be directly controlled to perform corresponding operations according to the user correction instruction.
[0071] Combine the following Figure 6 A specific embodiment of the present invention is described below.
[0072] Specifically, in some embodiments of the present invention, Figure 6As shown, the intelligent robot may include a speech recognition unit, a task execution unit, a safety supervision unit and a self-learning unit, wherein the speech recognition unit is responsible for parsing and understanding the user's voice instructions, and adopts natural speech processing technology, for example, a deep learning model GPT (Generative Pre-Trained Transformer, a deep learning model based on the Internet, trained with available data, and generated by text, or BERT (Bidirectional Encoder Representations from Transformers, language representation model) to understand the semantic information of the user's voice instructions and convert them into target task instructions that the intelligent robot can understand. Then, the task execution unit performs the specific task corresponding to the target task instruction according to the target task instruction received from the speech recognition unit in combination with the robot's visual data. At the same time, the safety supervision unit is responsible for monitoring the operating state and / or environmental state of the intelligent robot, and adjusting the target task instruction when the operating state and / or environmental state is abnormal, and the self-learning unit adjusts the target task instruction according to the task execution result and monitoring information.
[0073] For example, in a specific embodiment of the present invention, the intelligent robot may be a household service robot. The user may issue instructions to the intelligent robot through a voice interface, such as "clean the living room" or "prepare coffee for me". The voice recognition unit parses the instructions and converts them into target task instructions that can be executed by the intelligent robot. Furthermore, the self-learning unit may adjust the target task instructions according to the task execution results and user feedback, such as the cleaning effect or the satisfaction with the coffee (for example, the frequency of cleaning or the concentration of coffee may be adjusted to meet the user's preferences). At the same time, the operation of the intelligent robot may be monitored in real time through the safety supervision unit to detect potential safety risks (such as collision risks or erroneous operations) and take timely measures when an abnormality occurs (such as pausing the operation or notifying the user that the intelligent robot has an error).
[0074] Optionally, in the above-mentioned embodiments of the present invention, the user can also input text instructions through the mobile application, the voice recognition unit can parse the text instructions to perform corresponding tasks, the self-learning unit can also adjust the target task instructions based on long-term performance data, and the safety supervision unit can also perform real-time monitoring of the intelligent robot through external devices (for example, by linking with the camera in the smart home system).
[0075] In addition, in another specific embodiment of the present invention, the intelligent robot can also be a household service robot. The user can issue instructions to the intelligent robot through a voice interface, such as "replace parts on the assembly line". The voice recognition unit parses the instructions and converts them into target task instructions that can be executed by the intelligent robot. Then, the self-learning unit can adjust the target task instructions according to the task execution results and user feedback, such as the efficiency and quality of each task execution (for example, automatically adjust operating parameters, such as the speed or accuracy of the robotic arm). At the same time, the operation of the intelligent robot is monitored in real time through the safety supervision unit to detect potential safety risks (for example, ensure that safety standards are complied with, such as avoiding collisions with personnel or other machines), and take timely measures (such as shutting down or sending alarms) when abnormalities occur.
[0076] Optionally, in the above-mentioned embodiment of the present invention, the instruction may also be preset by the automation system or generated by a scheduled task, and the safety monitoring of the safety supervision unit may be integrated into the central monitoring system of the factory.
[0077] In summary, according to the control method of the intelligent robot of the embodiment of the present invention, the target task instruction and the robot vision data are obtained, and then, according to the target task instruction and the robot vision data, the intelligent robot is controlled to perform the target task, and, in the process of controlling the intelligent robot to perform the target task, the operating state and / or environmental state of the intelligent robot are adjusted according to the robot vision data. Thus, by combining the target task instruction with the visual perception ability of the intelligent robot, accurate target task execution is achieved. At the same time, in the process of controlling the intelligent robot to perform the target task, the operating state and / or environmental state of the intelligent robot are adjusted in real time using the robot vision data, thereby ensuring the safety and accuracy of the target task execution in an unsupervised environment.
[0078] Based on the control method of the intelligent robot of the aforementioned embodiment of the present invention, the embodiment of the present invention further proposes a computer-readable storage medium, on which a control program of the intelligent robot is stored. When the control program of the intelligent robot is executed by a processor, the control method of the intelligent robot of the aforementioned embodiment of the present invention is implemented.
[0079] It should be understood that the specific implementation of the computer-readable storage medium of the embodiment of the present invention can refer to the specific implementation of the control method of the intelligent robot of the aforementioned embodiment of the present invention, and will not be repeated here to reduce redundancy.
[0080] In summary, according to the computer-readable storage medium of the embodiment of the present invention, by executing the control program of the intelligent robot stored thereon, it is possible to ensure the safety and accuracy of the execution of the target task in an unsupervised environment.
[0081] Figure 74 is a block diagram of a control device for an intelligent robot according to an embodiment of the present invention.
[0082] Specifically, in some embodiments of the present invention, Figure 7 As shown, the control device 100 of the intelligent robot includes: an acquisition module 10 , a control module 20 and an adjustment module 30 .
[0083] Among them, the acquisition module 10 is used to acquire target task instructions and robot vision data; the control module 20 is used to control the intelligent robot to perform the target task according to the target task instructions and robot vision data; the adjustment module 30 is used to adjust the operating state and / or environmental state of the intelligent robot according to the robot vision data during the process of the intelligent robot performing the target task.
[0084] Furthermore, in some embodiments of the present invention, the acquisition module 10 is also used to acquire user voice instructions and preprocess the user voice instructions; use a large language model to perform feature extraction on the preprocessed user voice instructions to acquire semantic information corresponding to the user voice instructions; and generate target task instructions based on the semantic information corresponding to the user voice instructions.
[0085] Furthermore, in some embodiments of the present invention, the control module 20 is also used to generate operating environment information of the intelligent robot based on the robot vision data; and control the intelligent robot to execute target task instructions based on the operating environment information.
[0086] Furthermore, in some embodiments of the present invention, in the process of controlling the intelligent robot to perform a target task, the adjustment module 30 is also used to adjust the operating state and / or environmental state of the intelligent robot when the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction.
[0087] Furthermore, in some embodiments of the present invention, the adjustment includes: controlling the intelligent robot to execute a backoff instruction or a stop instruction.
[0088] Furthermore, in some embodiments of the present invention, the adjustment module 30 is also used to obtain the execution result of the target task; and adjust the target task instruction according to the execution result.
[0089] Furthermore, in some embodiments of the present invention, the adjustment module 30 is further used to obtain a user correction instruction; and adjust the target task instruction according to the user correction instruction.
[0090] It should be understood that the specific implementation of the control device of the intelligent robot in the embodiment of the present invention corresponds one-to-one to the control method of the intelligent robot in the aforementioned embodiment of the present invention, and will not be repeated here to reduce redundancy.
[0091] In summary, according to the control device of the intelligent robot of the embodiment of the present invention, the target task instruction and the robot vision data are acquired by the acquisition module, and then, the intelligent robot is controlled to perform the target task according to the target task instruction and the robot vision data by the control module, and the operation state and / or environmental state of the intelligent robot are adjusted according to the robot vision data in the process of controlling the intelligent robot to perform the target task by the adjustment module. Thus, accurate target task execution is achieved by combining the target task instruction with the visual perception ability of the intelligent robot, and at the same time, in the process of controlling the intelligent robot to perform the target task, the operation state and / or environmental state of the intelligent robot are adjusted in real time using the robot vision data, thereby ensuring the safety and accuracy of the target task execution in an unsupervised environment.
[0092] Figure 8 is a block diagram of an intelligent robot according to an embodiment of the present invention.
[0093] Specifically, in some embodiments of the present invention, Figure 8 As shown, the intelligent robot 1000 includes the intelligent robot control device 100 of the above-mentioned embodiment of the present invention.
[0094] It should be understood that the specific implementation of the intelligent robot of the embodiment of the present invention can refer to the specific implementation of the control method of the intelligent robot of the aforementioned embodiment of the present invention. In addition, other structures and functions of the intelligent robot of the embodiment of the present invention are known to technicians in this field and will not be described here to reduce redundancy.
[0095] In summary, the intelligent robot according to the embodiment of the present invention, by adopting the control device of the aforementioned intelligent robot, can ensure the safety and accuracy of the execution of the target task in an unsupervised environment.
[0096] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0097] In the description of the present invention, it is to be understood that the terms “center”, “longitudinal”, “lateral”, “length”, “width”, “thickness”, “up”, “down”, “front”, “back”, “left”, “right”, “vertical”, “horizontal”, “top”, “bottom”, “inside”, “outside”, “clockwise”, “counterclockwise”, “axial”, “radial”, “circumferential”, etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.
[0098] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0099] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0100] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.
[0101] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.
Claims
1. A control method for an intelligent robot, characterized in that: The method comprises: Obtain target task instructions and robot vision data; Controlling the intelligent robot to perform the target task according to the target task instruction and the robot vision data; In the process of controlling the intelligent robot to perform the target task, the operating state and / or environmental state of the intelligent robot is adjusted according to the robot vision data.
2. The control method of the intelligent robot according to claim 1, characterized in that: The target task acquisition instruction includes: Acquire user voice commands and pre-process the user voice commands; Using a large language model to perform feature extraction on the preprocessed user voice command to obtain semantic information corresponding to the user voice command; The target task instruction is generated according to the semantic information corresponding to the user voice instruction.
3. The control method of the intelligent robot according to claim 1, characterized in that: The controlling the intelligent robot to perform the target task includes: generating operating environment information of the intelligent robot according to the robot vision data; According to the operating environment information, the intelligent robot is controlled to execute the target task instructions.
4. The control method of the intelligent robot according to claim 3, characterized in that: In the process of controlling the intelligent robot to perform the target task, the method further includes: When the operating environment information is inconsistent with the operating environment information corresponding to the target task instruction, the operating state and / or environmental state of the intelligent robot is adjusted.
5. The control method of the intelligent robot according to any one of claims 1 or 4, characterized in that: The adjustments include: Control the intelligent robot to execute a fallback instruction or a stop instruction.
6. The control method of the intelligent robot according to claim 1, characterized in that: The method further comprises: Obtaining the execution result of the target task; The target task instruction is adjusted according to the execution result.
7. The control method of the intelligent robot according to claim 1, characterized in that: The method further comprises: Get user correction instructions; The target task instruction is adjusted according to the user correction instruction.
8. A computer-readable storage medium, characterized in that: A control program of an intelligent robot is stored thereon, and when the control program of the intelligent robot is executed by a processor, a control method of an intelligent robot according to any one of claims 1-7 is implemented.
9. A control device for an intelligent robot, characterized in that: The device comprises: An acquisition module, used to obtain target task instructions and robot vision data; A control module, used to control the intelligent robot to perform the target task according to the target task instruction and the robot vision data; The adjustment module is used to adjust the operating state and / or environmental state of the intelligent robot according to the robot vision data during the process of controlling the intelligent robot to perform the target task.
10. An intelligent robot, characterized in that: The intelligent robot comprises the control device of the intelligent robot as claimed in claim 9.
Citation Information
Patent Citations
Voice control method and voice control system for air-conditioner
CN104240702A
Robot and control method, system and device thereof
CN108227691A
Highway service area cleaning robot voice interaction device
CN111531565A
Robot control method and device, robot and storage medium
CN114454176A
Industrial robot co-fusion cooperation method in dynamic non-structural environment
CN117301099A
