Robot and control method therefor

Abstract

Disclosed is a robot. One or more processors, when instructions are individually or collectively executed, cause the robot to: monitor at least one function of the robot related to a preset task; when an error related to the at least one function is identified, identify the type of the error; identify, on the basis of the type of the error, the degree of feasibility of the preset task after the error occurs; and change the at least one function on the basis of the degree of feasibility of the preset task.

Description

Robot and method for controlling the same

[0001] The present disclosure relates to a robot and a control method thereof, and more particularly, to a robot providing a safety function and a control method thereof.

[0002] As research into robots incorporating AI technology continues, technology for robots requiring higher levels of safety features is advancing.

[0003] Traditionally, robots were equipped with safety features that immediately halted their functions to prevent accidents caused by malfunctions. However, these safety features have limitations in terms of task efficiency and productivity, raising concerns about the safety of robots.

[0004] A robot according to one or more embodiments of the present disclosure comprises one or more processors including a memory for storing instructions and processing circuitry, wherein the one or more processors are configured to, when the instructions are individually or collectively executed, cause the robot to monitor at least one function of the robot related to a preset task, identify a type of the error related to the at least one function, identify a degree of performance of the preset task after the error occurs based on the type of the error, and change the at least one function based on the degree of performance of the preset task.

[0005] According to one or more embodiments, the memory further stores score information corresponding to a type of error associated with each of a plurality of tasks including the preset task, and the instructions, when individually or collectively executed by the one or more processors, cause the robot to identify a score corresponding to a degree of performance of the preset task based on the score information and to change the at least one function based on the score.

[0006] According to one or more embodiments, the robot further comprises at least one sensor, and the instructions, when individually or collectively executed by the one or more processors, cause the robot to obtain situational information about the working environment of the robot based on sensed data obtained from the at least one sensor, and to change the at least one function based on the degree of performance of the preset task and the situational information.

[0007] According to one or more embodiments, the memory further stores first score information corresponding to a type of error associated with each of a plurality of tasks including the preset task and second score information according to situations of a plurality of task environments, and the instructions, when individually or collectively executed by the one or more processors, cause the robot to identify a first score corresponding to a degree of performance of the preset task based on the first score information and the second score information, to identify a second score corresponding to the situation information based on the first score information and the second score information, and to change the at least one function based on the first score and the second score.

[0008] According to one or more embodiments, the instructions, when individually or collectively executed by the one or more processors, cause the robot to identify one of a plurality of control levels corresponding to the at least one function based on the first score and the second score, and to change the at least one function based on the identified control level.

[0009] According to one or more embodiments, the plurality of control levels include at least one of maintaining functionality, maintaining functionality with limitations, stopping functionality after current task completion, and stopping functionality immediately.

[0010] According to one or more embodiments, the instructions, when individually or collectively executed by the one or more processors, cause the robot to provide a warning notification corresponding to the identified control level.

[0011] According to one or more embodiments, the instructions, when individually or collectively executed by the one or more processors, cause the robot to identify a weight to be applied to each of the first score and the second score based on a number of types of the situation information, and to change the at least one function based on the first score and the second score to which the identified weight is applied.

[0012] According to one or more embodiments, the instructions, when individually or collectively executed by the one or more processors, cause the robot to identify second sensing data to replace first sensing data of the at least one sensor in which the error occurred based on the type of the error, and to identify the degree to which the preset task can be performed by replacing the first sensing data with the second sensing data.

[0013] According to one or more embodiments, the robot further comprises at least one sensor, and the instructions, when individually or collectively executed by the one or more processors, cause the robot to input the type information of the error and the sensing data obtained from the at least one sensor into an artificial intelligence model to identify one of a plurality of control levels corresponding to the at least one function, and change the at least one function based on the identified control level.

[0014] A method for controlling a robot according to one or more embodiments of the present disclosure comprises: an operation of monitoring at least one function of the robot related to a preset task; an operation of identifying a type of an error related to the at least one function when an error is identified; an operation of identifying a degree of performance of the preset task after the error occurs based on the type of the error; and an operation of changing the at least one function based on the degree of performance of the preset task.

[0015] A non-transitory computer-readable storage medium storing computer instructions that, when executed by a processor of a robot according to one or more embodiments of the present disclosure, cause the robot to perform an operation, the operation includes: monitoring at least one function of the robot related to a preset task; identifying a type of an error related to the at least one function when an error is identified; identifying a degree of performance of the preset task after the error occurs based on the type of the error; and changing the at least one function based on the degree of performance of the preset task.

[0016] The above and other aspects, features and advantages of specific embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings.

[0017] FIG. 1 is a drawing for explaining the operation of a robot according to one or more embodiments.

[0018] FIG. 2 is a block diagram illustrating a configuration of a robot according to one or more embodiments.

[0019] FIG. 3 is a block diagram illustrating a detailed configuration of a robot according to one or more embodiments.

[0020] FIG. 4 is a diagram illustrating a process for identifying score information corresponding to a type of error for each preset task of a robot according to one or more embodiments.

[0021] FIG. 5 is a diagram for explaining a process of identifying a score corresponding to the degree of performance of a preset task of a robot according to one or more embodiments.

[0022] FIG. 6 is a diagram illustrating a score identification process corresponding to situational information about a working environment of a robot according to one or more embodiments.

[0023] FIG. 7 is a diagram illustrating a process for identifying multiple control levels corresponding to at least one function of a robot according to one or more embodiments.

[0024] FIG. 8 is a diagram illustrating a process for identifying first and second scores based on weights of a robot according to one or more embodiments.

[0025] FIG. 9 is a diagram illustrating a process for identifying the degree of performance of a preset task based on alternative data of a robot according to one or more embodiments.

[0026] FIG. 10 is a diagram illustrating at least one function control process based on an artificial intelligence model of a robot according to one or more embodiments.

[0027] FIG. 11 is a drawing for explaining at least one function control process of a robot according to one or more embodiments.

[0028] Figure 12 is a flowchart illustrating the overall operation process of a robot according to one or more embodiments.

[0029] FIG. 13 is a flowchart illustrating the operation of a robot according to one or more embodiments.

[0030] The terms used in the various embodiments of this disclosure have been selected from widely used, current terms, taking into account the functions of this disclosure. However, these terms may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc. Furthermore, in certain cases, terms may be arbitrarily selected by the applicant, and in such cases, their meanings will be described in detail in the description of the relevant disclosure. Therefore, the terms used in this disclosure should be defined based on the meaning of the terms and the overall content of this disclosure, rather than simply their names.

[0031] In this disclosure, expressions such as “has,” “can have,” “includes,” or “may include” indicate the presence of a corresponding feature (e.g., a component such as a number, function, operation, or part), and do not exclude the presence of additional features.

[0032] The expression "at least one of A and / or B" should be understood to mean either "A" or "B" or "A and B".

[0033] The expressions “first,” “second,” “first,” or “second,” etc., used in this disclosure can describe various components, regardless of order and / or importance, and are only used to distinguish one component from another, but do not limit the components.

[0034] When it is said that a component (e.g., a first component) is “(operatively or communicatively) coupled with / to” or “connected to” another component (e.g., a second component), it should be understood that the component may be directly coupled to the other component, or may be connected through another component (e.g., a third component).

[0035] Singular expressions include plural expressions unless the context clearly dictates otherwise. In this disclosure, terms such as "comprise" or "consist of" are intended to indicate the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but should be understood not to preclude the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0036] In the present disclosure, a "module" or "part" performs at least one function or operation and may be implemented as hardware or software, or as a combination of hardware and software. Furthermore, multiple "modules" or multiple "parts" may be integrated into at least one module and implemented as at least one processor (not shown), excluding any "modules" or "parts" that need to be implemented as specific hardware.

[0037] In this disclosure, the term user may refer to a person using an electronic device or a device used by the person.

[0038] An embodiment of the present disclosure will be described in more detail with reference to the attached drawings below.

[0039] FIG. 1 is a drawing for explaining the operation of a robot according to one or more embodiments.

[0040] A robot (100) may be a device capable of driving without direct human control. The robot (100) may also be referred to by various other terms, such as an autonomous driving device, an autonomous mobile robot (AMR), an automated guided vehicle (AGV), an unmanned ground vehicle (UGV), etc., but in the present disclosure, it will be collectively referred to as a robot (100).

[0041] The robot (100) can be implemented as various types of robots that move through space and perform necessary tasks, such as a cleaning robot, a serving robot, a mobile projector, an industrial robot, a guide robot, a delivery robot, etc., depending on the method of use or purpose.

[0042] The robot (100) may include at least one of various sensors, such as a lidar sensor, an infrared sensor, an image sensor, an ultrasonic sensor, and a depth camera. The robot (100) may implement at least one function for performing a preset task through the above-described sensors.

[0043] Predefined tasks may include various types of tasks, such as cleaning, serving, industrial, educational and research, and medical tasks. For example, the robot (100) may be designed or manufactured to perform the predefined tasks. For example, the robot (100) may have at least one function that can be implemented differently depending on the predefined task.

[0044] According to one embodiment, the robot (100) can identify whether an error has occurred (or whether a malfunction has occurred) in at least one function. The robot (100) can identify whether an error has occurred in at least one function through data analysis based on sensed data, a self-diagnosis algorithm, log monitoring, external system warning notifications, etc. For example, if the robot (100) does not identify a sensed value corresponding to a specific direction and angle through a sensor, it can be identified that an error has occurred in the sensing function. For example, if the input driving speed and the driving speed identified from the encoder are different, it can be identified that an error has occurred in the driving function.

[0045] According to one embodiment, if the robot (100) is identified as having an error in at least one function, it may control at least one function based on the degree of performance of the preset task. For example, the robot (100) may degrade at least one function based on the degree of performance of the preset task. Degradation control may be to degrade the function in which the error occurred in order to prevent the performance of the task from being degraded as much as possible even if an error occurs in a specific function.

[0046] For example, if a robot (100) can perform a preset task through functions other than the function in which an error occurred, even if an error occurs in at least one function, the robot can control at least one function in stages.

[0047] For example, the robot (100) can control at least one function in stages if it is possible to perform a preset task through the function in which the error occurred, even if an error occurs in at least one function.

[0048] For example, if the robot (100) is unable to perform a preset task due to an error occurring in at least one function, it may immediately stop all or at least one function.

[0049] An error in a function may include a situation in which a problem occurs in the system, software, or hardware configuration of the robot (100) and thus the robot cannot perform the function normally or / and efficiently. For example, if an error occurs in the driving motor of the robot (100), the robot (100) may not be able to perform the driving function, or may not be able to perform the driving function efficiently, depending on the degree of the error. For example, an error in at least one function of the robot (100) may include not only a case in which the robot cannot perform a preset task due to this, but also a case in which the robot can perform the preset task but consumes more time or power compared to when the error does not occur.

[0050] According to one embodiment, the robot (100) can identify an error type for at least one function among a plurality of error types and identify the degree of performance of a preset task based on the error type.

[0051] Referring to FIG. 1, the robot (100) can identify an error that has occurred in at least one of a plurality of functions for performing a preset task. The robot (100) can identify the degree to which the robot (100) can perform the preset task based on the error that has occurred. If an error (11) has occurred in at least one function to the extent that the robot (100) cannot perform the task, the robot (100) can immediately stop all functions (12). On the other hand, if the robot (100) can perform the preset task even if an error (13) has occurred in at least one function, the robot (100) can control at least one function (14).

[0052] For example, in a robot (100) traveling at 1.2 m / s, if an error (11) occurs in at least one function, such as a sensing function or an object detection function, to the extent that the robot cannot perform a preset task, the robot (100) can immediately stop all functions or at least one function. For example, even if an error (13) occurs in at least one function of a robot (100) traveling at 1.2 m / s, if the preset task can be performed through functions other than the function in which the error (13) occurred, the robot (100) can control at least one function (14), such as reducing the driving speed (driving speed 0.5 m / s) depending on the degree to which the preset task can be performed.

[0053] Hereinafter, with reference to the drawings, various embodiments in which a robot (100) identifies the degree to which a preset task can be performed according to the type of error and controls at least one function will be described.

[0054] FIG. 2 is a block diagram illustrating a configuration of a robot according to one or more embodiments.

[0055] According to FIG. 2, the robot (100) includes a memory (110) and one or more processors (120). However, the present invention is not limited thereto, and the robot (100) may be implemented in a form in which some components are excluded, or may be implemented in a form in which other components are further included.

[0056] The memory (110) can store at least one command, data, program, etc. required for the operation of the robot (100). For example, the memory (110) can store score information corresponding to the type of error for each task.

[0057] The memory (110) may be implemented in the form of memory embedded in the robot (100) or in the form of memory detachable from the robot (100) depending on the purpose of data storage. For example, data for driving the robot (100) may be stored in a memory embedded in the robot (100), and data for expanding the functions of the robot (100) may be stored in a memory detachable from the robot (100).

[0058] In the case of memory embedded in the robot (100), it may be implemented as at least one of volatile memory (e.g., dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM)), non-volatile memory (e.g., one time programmable ROM (OTPROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (e.g., NAND flash or NOR flash), hard drive, or solid state drive (SSD)).

[0059] The memory (110) may be implemented as a single memory that stores data generated from various operations according to the present disclosure, but is not limited thereto, and the memory (110) may be implemented to include multiple memories that each store different types of data or each store data generated at different stages.

[0060] One or more processors (120) control the overall operation of the robot (100). Specifically, one or more processors (120) are connected to each component of the robot (100) and can control the overall operation of the robot (100). For example, one or more processors (120) are electrically connected to the memory (110) and can control the overall operation of the robot (100). One or more processors (120) may include a processing circuit and may be composed of one or more processors.

[0061] One or more processors (120) can perform operations of the robot (100) according to various embodiments by executing one or more commands stored in the memory (110).

[0062] The one or more processors (120) may include one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), an Accelerated Processing Unit (APU), a Many Integrated Core (MIC), a Digital Signal Processor (DSP), a Neural Processing Unit (NPU), a hardware accelerator, or a machine learning accelerator. The one or more processors (120) may control one or any combination of other components of the robot, and may perform operations related to communication or data processing. The one or more processors (120) may execute one or more programs or instructions stored in a memory. For example, the one or more processors may perform a method according to one or more embodiments of the present disclosure by executing one or more instructions stored in a memory.

[0063] When a method according to one or more embodiments of the present disclosure includes multiple operations, the multiple operations may be performed by one processor or by multiple processors. For example, when a first operation, a second operation, and a third operation are performed by a method according to one or more embodiments, the first operation, the second operation, and the third operation may all be performed by the first processor, or the first operation and the second operation may be performed by the first processor (e.g., a general-purpose processor) and the third operation may be performed by the second processor (e.g., an artificial intelligence-specific processor).

[0064] One or more processors (120) may be implemented as a single core processor including one core, or may be implemented as one or more multicore processors including multiple cores (e.g., homogeneous multicores or heterogeneous multicores). When one or more processors (120) are implemented as a multicore processor, each of the multiple cores included in the multicore processor may include an internal processor memory, such as a cache memory or an on-chip memory, and a common cache shared by the multiple cores may be included in the multicore processor. In addition, each of the multiple cores (or some of the multiple cores) included in the multicore processor may independently read and execute a program instruction for implementing a method according to one or more embodiments of the present disclosure, or all (or some) of the multiple cores may be linked to read and execute a program instruction for implementing a method according to one or more embodiments of the present disclosure.

[0065] When a method according to one or more embodiments of the present disclosure includes a plurality of operations, the plurality of operations may be performed by one core among the plurality of cores included in a multi-core processor, or may be performed by the plurality of cores. For example, when a first operation, a second operation, and a third operation are performed by a method according to one or more embodiments, the first operation, the second operation, and the third operation may all be performed by a first core included in the multi-core processor, or the first operation and the second operation may be performed by a first core included in the multi-core processor, and the third operation may be performed by a second core included in the multi-core processor.

[0066] In the embodiments of the present disclosure, a processor may mean a system on a chip (SoC) in which one or more processors and other electronic components are integrated, a single-core processor, a multi-core processor, or a core included in a single-core processor or a multi-core processor, wherein the core may be implemented as a CPU, a GPU, an APU, a MIC, a DSP, an NPU, a hardware accelerator, or a machine learning accelerator, but the embodiments of the present disclosure are not limited thereto. Hereinafter, for the convenience of explanation, one or more processors (120) will be referred to as a processor (120).

[0067] According to one embodiment, the processor (120) may monitor in real time at least one function of the robot (100) for performing a preset task. Monitoring may be a process of continuously tracking and evaluating whether the function of the robot (100) is operating as defined (or intended). According to one example, the processor (120) may perform function monitoring through log data monitoring, metric data monitoring, sensing data monitoring, notification information monitoring, automated test monitoring, etc.

[0068] For example, the processor (120) can monitor in real time whether the sensing value from at least one sensor is sensed as intended. For example, the processor (120) can monitor in real time whether the sensing value is output as intended through an internal algorithm and / or whether the output sensing value has no errors.

[0069] At least one function may include multiple functions, depending on the type, such as a movement function, a sensing function, a map generation function, a task function, and a learning function. For example, a serving robot may include multiple functions, such as a movement function for serving, a loading function for serving loaded items, and a spatial map generation function for generating a driving map.

[0070] According to one embodiment, when the processor (120) identifies that an error has occurred in at least one function, it can identify the type of error.

[0071] For example, functional errors can be classified into multiple error types. For example, errors can be classified into input error types, process error types, and output error types. For example, input error types can be further classified into sensor error types, timing error types, and self-test error types. For example, process error types can be further classified into algorithm error types, memory error types, and so on. For example, output error types can be further classified into actuator error types, feedback error types, and so on.

[0072] For example, multiple error types may be predefined and distinguished by function, and the processor (120) may identify one of the error types mapped to the corresponding function when an error occurs in the function. However, the present invention is not limited thereto, and multiple error types may be predefined regardless of the function, and the processor (120) may identify one of the multiple error types when an error occurs in the function. For the convenience of explanation, the latter case will be assumed below.

[0073] According to one embodiment, the processor (120) may identify the degree to which a preset task can be performed due to an error based on the type of error. The degree to which a preset task can be performed may be numerical data used to determine the extent to which the type of identified error affects the performance of the task.

[0074] According to one embodiment, the processor (120) may control at least one function based on the degree of performance of a preset task. The processor (120) may deteriorate and control at least one function based on at least one of a plurality of control levels based on the degree of performance of the preset task.

[0075] FIG. 3 is a block diagram illustrating a detailed configuration of a robot according to one or more embodiments.

[0076] According to FIG. 3, the robot (100) includes a memory (110), one or more processors (120), at least one sensor (130), a driving unit (140), a communication circuit (150), a display (160), an input / output interface (170), and a speaker (180). Among the configurations illustrated in FIG. 3, a detailed description of configurations that overlap with those illustrated in FIG. 2 will be omitted.

[0077] At least one sensor (130) is a sensor for detecting the surrounding environment and obtaining situational information about the working environment. Specifically, it may include at least one or more of a LiDAR sensor, a vision sensor, an image sensor, an infrared sensor, an ultrasonic sensor, a gyro sensor, an acceleration sensor, and a proximity sensor. In addition, at least one sensor (130) may include at least one or more of a 2D camera, a TOF (Time of Flight) camera, a depth camera, a multi-lens array camera, a stereo vision system, a fused lidar camera, and a 3D camera.

[0078] The driving unit (140) is a component for moving the main body of the robot (100). The driving unit (140) may include components such as a plurality of wheels, a driving motor for rotating each of the plurality of wheels, a gear, and a shaft. The plurality of wheels are provided on the lower or side of the main body of the robot (100) and support the main body of the robot (100) from the floor. When the driving motor operates and the driving force is transmitted to the plurality of wheels so that each wheel rotates, the robot (100) can move by the frictional force between the floor and the wheels. In addition, the driving unit (140) may vary the rotational speed of at least one wheel among the plurality of wheels or adjust the alignment direction of the wheels differently when changing direction. Depending on the type of the robot (100), the weight of the loaded item, and the usage environment of the robot (100), an infinite track or the like may be used instead of the wheels.

[0079] The communication circuit (150) may include wired or wireless input / output interfaces (or input / output terminals) according to various standards. The communication circuit (150) may be configured to communicate with various types of external devices according to various types of communication methods. The communication circuit (150) may include a wireless communication module or a wired communication module. Here, each communication module may be implemented in the form of at least one hardware chip.

[0080] The communication circuit (150) may include various interfaces such as HDMI (High Definition Multimedia Interface), MHL (Mobile High-Definition Link), USB (Universal Serial Bus), DP (Display Port), Thunderbolt, VGA (Video Graphics Array) port, RGB port, D-SUB (D-subminiature), DVI (Digital Visual Interface), Bluetooth, Zigbee, wired / wireless LAN (Local Area Network), WAN (Wide Area Network), Ethernet, IEEE 1394, AES / EBU (Audio Engineering Society / European Broadcasting Union), optical, coaxial, etc.

[0081] The display (160) is configured to display a photographed image acquired through at least one sensor (130) or to display at least one function according to a preset task. The display (160) may be implemented as a display module including a self-luminous element or a display module including a non-luminous element and a backlight. In addition, the display (160) may be implemented as an LFD display according to the above-described content. For example, the display may be implemented as various types of displays such as an LCD (Liquid Crystal Display), an OLED (Organic Light Emitting Diodes) display, an LED (Light Emitting Diodes), a micro LED, a Mini LED, a PDP (Plasma Display Panel), a QD (Quantum dot) display, a QLED (Quantum dot light-emitting diodes), etc. The display (160) may also include a driving circuit, a backlight unit, etc., which may be implemented in a form such as an a-si TFT, an LTPS (low temperature poly silicon) TFT, an OTFT (organic TFT), etc.

[0082] The input / output interface (170) may be any one of HDMI (High Definition Multimedia Interface), MHL (Mobile High-Definition Link), USB (Universal Serial Bus), DP (Display Port), Thunderbolt, VGA (Video Graphics Array) port, RGB port, D-SUB (D-subminiature), and DVI (Digital Visual Interface). The input / output interface (170) may input / output at least one of audio and video signals. Depending on the implementation example, the input / output interface (170) may include a port that inputs / outputs only audio signals and a port that inputs / outputs only video signals as separate ports, or may be implemented as a single port that inputs / outputs both audio signals and video signals.

[0083] The robot (100) can transmit at least one of audio and video signals to an external device (e.g., another electronic device or another robot) through an input / output interface (170). Specifically, an output port included in the input / output interface (170) can be connected to an external device, and the robot (100) can transmit at least one of audio and video signals to the external device through the output port.

[0084] The speaker (180) can convert and amplify a digital audio signal processed by the processor (120) into an analog audio signal and output the converted signal. For example, the speaker (180) can include at least one speaker unit, a D / A converter, an audio amplifier, etc., which can output at least one channel. For example, the speaker (180) can output various notifications, messages, information, etc. related to feedback from the processor (120).

[0085] FIG. 4 is a diagram illustrating a process for identifying score information corresponding to a type of error for each preset task of a robot according to one or more embodiments.

[0086] According to one embodiment, the robot (100) can identify information corresponding to a preset task of the robot (100) stored in the memory (110). The robot (100) can identify a task to be performed by the robot (100) during the manufacturing stage or according to a user's settings.

[0087] According to one embodiment, the robot (100) can store score information corresponding to the type of error for each preset task in the memory (110) and identify the same. The score information may include a score value that quantifies the degree to which each type of error affects the preset task. The score information corresponding to the type of error may be a preset value, may be set during the manufacturing process, or may be set directly by the user.

[0088] For example, for a robot performing a cleaning task, the lidar sensor error type may have the highest score value because it detects surrounding obstacles through the lidar sensor. Conversely, an error type indicating the degree of task performance may have the lowest score value because the degree of impact on the preset task (e.g., cleaning) is minor.

[0089] The score information corresponding to the type of error for each task may be score information in the form of a lookup table. The lookup table may include multiple error types for at least one function for each preset task and score information corresponding to the type of error for each task.

[0090] According to one embodiment, the robot (100) may have different score information corresponding to the same error type for each preset task. For example, a robot performing task A and a robot performing task B may have the same first error type identified according to the same function. However, even for the same error type, the degree to which it affects the degree of task performance may differ depending on the preset task (e.g., task A or task B). In this case, a score value corresponding to the identified first error type of a robot performing task A may be different from a score value corresponding to the first error type of a robot performing task B.

[0091] Referring to FIG. 4, a serving robot (410) performing a serving task (or task A) can identify a driving error type (or error type A) (411), a B error type (412), and a C error type (413) according to at least one function. An industrial robot (420) performing a lifting task (or task B) can identify an error type A (421), an error type D (422), and an error type E (423) according to at least one function.

[0092] For example, a robot (410) performing task A performs a serving task by controlling the driving speed, and therefore, the score information corresponding to the identified A error type (411) may include a score value of 8 points (414). On the other hand, a robot (420) performing task B mainly performs a task of loading and lifting objects, and therefore, the score information corresponding to the identified A error type may include a score value of 3 points (424).

[0093] Even for the same error type, the score information corresponding to the error type may be different depending on the preset task.

[0094] FIG. 5 is a diagram for explaining a process of identifying a score corresponding to the degree of performance of a preset task of a robot according to one or more embodiments.

[0095] According to one embodiment, the robot (100) may identify a first score corresponding to the degree of performance of a preset task based on score information corresponding to the identified error type. For example, the first score may be the same value as the score value included in the score information corresponding to the error type. For example, the first score may be a maximum of 10 points. However, the maximum score of the score corresponding to the degree of performance of the preset task is not limited thereto, and may be set differently depending on the manufacturing stage of the robot (100) or user settings.

[0096] Referring to FIG. 4, in the case of a serving robot (410) performing task A, the first score according to error type A may be 8 points. For example, in the case of an industrial robot (420) performing task B, the first score according to error type A may be 3 points.

[0097] Referring to FIG. 5, the robot (100) can monitor a first function (520) and a second function (530) for performing a preset first task (510). If an error is identified in the first function (520), the robot (100) can identify an A error type (521), a B error type (522), and a C error type (523) based on the error that has occurred. Similarly, the robot (100) can identify a D error type (531) and an E error type (532) based on an error that has occurred in the second function (530).

[0098] The robot (100) can identify a score value corresponding to each error type based on a lookup table including score information corresponding to the task-specific error type described in FIG. 4. For example, if the error that occurred is an A error type, the first score of the robot (100) can be 10 points. For example, if the error that occurred is a C error type, the first score of the robot (100) can be 6 points.

[0099] According to one embodiment, the robot (100) can deteriorate and control at least one function based on the first score. The robot (100) can control the function in which an error has occurred in a stepwise manner. For example, if a sensing data processing error type is identified in the surrounding obstacle detection function, the detection range of the surrounding obstacles can be adjusted. The robot (100) can control other functions in which no error has occurred in a stepwise manner. For example, if a lidar sensor error type is identified in the surrounding obstacle detection function, the driving function can be controlled to reduce the driving speed.

[0100] FIG. 6 is a diagram illustrating a score identification process corresponding to situational information about a working environment of a robot according to one or more embodiments.

[0101] According to one embodiment, the robot (100) can obtain situational information about the working environment of the robot (100) based on sensing data obtained from at least one sensor.

[0102] For example, if an error occurs in at least one function of a robot (100) and at least one function is controlled, the degree (or level) of control of at least one function may vary depending on situational information about the working environment of the robot (100). For example, if an error occurs in at least one function of a cleaning robot and at least one function is controlled, if there are many dynamic obstacles around the robot, at least one function may be stopped immediately rather than being controlled step by step. For example, in the case of a serving robot, if the load loaded on the serving robot body exceeds a preset range, at least one function may be stopped immediately rather than being controlled step by step. In this way, in the process of controlling at least one function of the robot (100), not only the degree to which the preset task can be performed, but also situational information about the working environment of the robot (100) may be considered.

[0103] The situation information about the work environment may include additional situation information about the work environment of the robot (100) for performing a preset task.

[0104] For example, situational information about the work environment may include information (or Type A) regarding the presence of dynamic obstacles around the robot (100). Dynamic obstacles may include dynamic objects such as people, other robots, etc. The robot (100) may identify dynamic obstacles around the robot (100) based on sensing data sensed from at least one sensor.

[0105] For example, situational information about the work environment may include information (or Type B) about the level of load loaded on the robot (100) body. The robot (100) may identify whether there is a load and the level of load through at least one sensor.

[0106] For example, situational information about the work environment may include information (or C type) about the margin distance to objects around the robot (100). The robot (100) may identify distance information to surrounding objects through a lidar sensor or a depth camera.

[0107] For example, situational information about the working environment may include information (or D type) about the running surface of the robot (100). The robot (100) may identify the degree of friction of the running surface through at least one sensor.

[0108] Contextual information about the work environment is not limited to the aforementioned embodiments and may include additional types. The types included in the contextual information about the work environment may be set during the manufacturing process or directly by the user. However, for convenience of explanation, the present disclosure assumes that the contextual information about the work environment includes four types.

[0109] According to one embodiment, the robot (100) can identify a second score corresponding to situational information about the working environment of the robot (100) based on types A to D. The second score may be a score that adds up all scores for each type included in the situational information.

[0110] For example, each type included in the situation information can be worth a minimum of 1 point and a maximum of 3 points, but this is not limited to this. For example, a large number of surrounding dynamic obstacles could be worth 3 points, while a small number could be worth 1 point. For example, a large number of loaded objects could be worth 3 points, while a small number could be worth 1 point.

[0111] For example, since there are a total of 4 types included in the situation information, the second score can be a minimum of 3 points and a maximum of 12 points.

[0112] Referring to FIG. 6, the robot (100) can identify a second score (640) corresponding to situation information (610) about the working environment of the robot (100) based on sensing data (620) sensed from at least one sensor. The situation information about the working environment can include types A to D (630).

[0113] For example, if the number of dynamic obstacles in the vicinity is small, the friction of the running surface is high, the margin distance is close to the average, and there are many loaded objects, the robot (100) can identify a score of 1 point corresponding to type A, a score of 3 points corresponding to type B, a score of 2 points corresponding to type C, and a score of 1 point corresponding to type D through at least one sensor.

[0114] For example, the robot (100) can identify a second score (640) of 7 points total, which is the sum of the scores corresponding to type A and the scores corresponding to type D.

[0115] According to one embodiment, the robot (100) can degrade and control at least one function based on the degree of performance of a preset task and situational information about the work environment. Specifically, the robot (100) can control at least one function based on a first score and a second score.

[0116] FIG. 7 is a diagram illustrating a process for identifying multiple control levels corresponding to at least one function of a robot according to one or more embodiments.

[0117] According to one embodiment, the robot (100) can identify one of a plurality of control levels corresponding to at least one function based on the first score and the second score. The robot (100) can identify a third score that is the sum of the first score and the second score. As an example, referring to FIGS. 5 and 6 , the third score can be up to 22 points.

[0118] The plurality of control levels may include at least one of: maintaining function (or level 1), maintaining limited function (or level 2), stopping function after current task completion (or level 3), and stopping function immediately (or level 4) to stepwise control at least one function of the robot (100). The robot (100) may identify one of the plurality of control levels based on the third score.

[0119] For example, Level 1 may be 0 to 5 points, Level 2 may be 6 to 10 points, Level 3 may be 11 to 15 points, and Level 4 may be 16 to 22 points. However, the score range for each level is not limited to this and may be set to a different range.

[0120] Referring to FIG. 7, the robot (100) can identify one of multiple control levels (740) based on a third score (730) that is the sum of the first score (710) and the second score (720). For example, if the first score (710) is 7 points and the second score (720) is 5 points, the robot (100) can identify a third level (750) based on a third score (730) of 12 points. In this case, the robot (100) can control at least one function to a function stop after completing the current task.

[0121] According to one embodiment, the robot (100) may provide warning notifications corresponding to the identified control level. For example, the robot (100) may provide different warning sounds set for each control level through the speaker (180). For example, the robot (100) may provide warning lights of different patterns or brightness set for each control level through at least one sensor.

[0122] FIG. 8 is a diagram illustrating a process for identifying first and second scores based on weights of a robot according to one or more embodiments.

[0123] According to one embodiment, the robot (100) can identify weights to be applied to each of the first score and the second score based on the number of types of situation information.

[0124] For example, the robot (100) may control at least one function in stages based on a total score (or a third score) that is the sum of the first score and the second score. However, the first score may be identified based on score information corresponding to the type of error stored in the memory (110), while the second score may be identified as a score that is the sum of scores corresponding to each type of situation information. In the above-described embodiment, the number of types of situation information is assumed to be four, but if the number of types of situation information is more than four, the third score may exceed the maximum score of 22 points.

[0125] For example, if the number of types of situation information regarding the working environment of the robot (100) exceeds 4 and the second score is identified as high, the robot (100) may immediately stop at least one function even though the first score corresponding to the degree of performance of the preset task is a low score of less than 5. To solve this problem, the robot (100) may apply different weights to the first score and / or the second score based on the number of types of situation information.

[0126] According to one embodiment, the robot (100) can deteriorate at least one function based on a first score and a second score to which the identified weights are applied.

[0127] Referring to FIG. 8, the robot (100) can identify a weight to be applied to the second score based on the number of types of situation information set. If the number of types of situation information is 4, the maximum score of the second score is 12 points, and therefore, weights for each type of situation information can be identified based on 12 points.

[0128] For example, if the number of types of situation information is 5 (810), and the maximum score for each type is 3 points, the maximum score of the second score is 15 points, so the weight to be applied to the second score can be identified as 0.8 based on 12 points. For example, if the number of types of situation information is 6 (820), and the maximum score for each type is 3 points, the maximum score of the second score is 18 points, so the weight to be applied to the second score can be identified as 0.66 based on 12 points.

[0129] For example, the weight (830) to be applied for each type of situation information can be identified and stored in memory (110).

[0130] Although Figure 8 illustrates the process of identifying the third score by only identifying the weights to be applied to the second score, different weights can be applied to the first and second scores depending on the number of types of contextual information. Furthermore, the maximum score for each type included in the contextual information can be adjusted.

[0131] FIG. 9 is a diagram illustrating a process for identifying the degree of performance of a preset task based on alternative data of a robot according to one or more embodiments.

[0132] According to one embodiment, the robot (100) can identify second sensing data to replace the first sensing data of the sensor in which the error occurred based on the type of error. The first sensing data and the second sensing data may be data sensed through different sensors. For example, the first sensing data may be data sensed through a lidar sensor, while the second sensing data may be data sensed through a depth camera.

[0133] For example, if an error type corresponding to a first sensor among the surrounding obstacle detection functions is identified, the robot (100) may not be able to perform a preset task as intended due to the error type. In this case, the robot (100) may be able to identify a first score with a high score based on the error type.

[0134] However, even if an error occurs in the first sensor, if the first sensing data of the first sensor can be replaced with the second sensing data of the second sensor, the robot (100) can perform the preset task as intended. In this case, the robot (100) can identify a first score with a low score based on the corresponding error type.

[0135] According to one embodiment, the robot (100) can identify the degree to which a preset task can be performed by replacing the first sensing data with the second sensing data.

[0136] Referring to FIG. 9, the robot (100) can implement a first function (910) based on the first sensing data (920) of the first sensor. If an error occurs in the first sensor, the robot (100) can identify an A error type (930) based on the first sensing data (920) of the first sensor. The robot (100) can identify a first score (e.g., 9 points) (930) based on the A error type (930).

[0137] However, if the first function (910) can be implemented based on the second sensing data (950) of the second sensor, the robot (100) can identify the first score (e.g., 2 points) (970) by replacing the first sensing data (920) with the second sensing data (950) (960).

[0138] FIG. 10 is a diagram illustrating at least one function control process based on an artificial intelligence model of a robot according to one or more embodiments.

[0139] According to one embodiment, the robot (100) can input error type information and sensing data obtained from at least one sensor into an artificial intelligence model to identify one of a plurality of control levels corresponding to at least one function.

[0140] Error type information may include functional information corresponding to the error type, the error type, sensed data values, self-diagnosis result information, etc. Error type information may be information for identifying a preset task and error type.

[0141] An artificial intelligence model may refer to a model that inputs specific input values ​​into a specific function based on learned data and outputs an output value. Here, the artificial intelligence model may be a model trained to identify the degree of performance of a preset task and situational information about the task environment based on error type information and sensing data. The artificial intelligence model may be referred to by various names, such as a neural network model, deep learning model, neural network model, or generative artificial intelligence model, but in this disclosure, it will be collectively referred to as an artificial intelligence model.

[0142] Here, the learning of an artificial intelligence model may mean that a basic artificial intelligence model (e.g., an artificial intelligence model including any random parameters) is trained using a learning algorithm using a plurality of training data, thereby creating a predefined set of operation rules or an artificial intelligence model set to perform a desired characteristic (or purpose). This learning may be performed through a separate server and / or system, but is not limited thereto, and may also be performed in a cooking device. Examples of learning algorithms include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

[0143] Here, the artificial intelligence model can be implemented as, for example, a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Restricted Boltzmann Machine (RBM), a Deep Belief Network (DBN), a Bidirectional Recurrent Deep Neural Network (BRDNN), or a Deep Q-Network, but is not limited thereto.

[0144] According to one embodiment, the robot (100) can degrade and control at least one function based on the identified control level. A detailed description of the method for controlling at least one function is omitted, as it has been described in the above-described embodiment.

[0145] Referring to FIG. 10, the robot (100) can input error type information (1010) and sensing data (1020) into an artificial intelligence model (1030) to identify one of a plurality of control levels (1040) corresponding to at least one function. When a control level (e.g., a first level to a fourth level) is identified through the artificial intelligence model (1030), the robot (100) can deteriorate and control at least one function based on the identified control level.

[0146] FIG. 11 is a drawing for explaining at least one function control process of a robot according to one or more embodiments.

[0147] Referring to FIG. 11, the robot (100) may be a robot (1110) that moves at 1.2 m / s with an obstacle detection range of 10 m. For example, the robot (100) may identify at least one of a rider error (1120), an encoder error (1130), a software error (1140), and a motor error (1150) in at least one function. The robot (100) may identify the type of error based on each identified error. The robot (100) may identify the degree of performance of a preset task and situational information about the work environment in real time (1160) based on the type of error. The robot (100) may control (1170) the function for each identified error in a stepwise manner.

[0148] For example, if a lidar error (1120) is identified, the robot (100) may perform operations such as reducing the obstacle detection area, slowing down the driving speed, and issuing a warning notification to reduce the amount of computation. For example, if an encoder error (1130) is identified, the robot (100) may further perform operations to replace sensing data through the lidar sensor. For example, if a motor error (1140) is identified, the robot (100) may perform operations to reduce the motor control cycle.

[0149] Figure 12 is a flowchart illustrating the overall operation process of a robot according to one or more embodiments.

[0150] Referring to FIG. 12, in operation 1210, the robot (100) can identify an error that has occurred in at least one function.

[0151] In operation 1211, if the robot (100) identifies that an error has occurred in at least one function, it can identify the type of error.

[0152] In operation 1212, the robot (100) can identify the degree to which a preset task can be performed due to an error based on the type of error.

[0153] In operation 1213, the robot (100) can obtain situational information about the working environment of the robot (100) based on sensing data obtained from at least one sensor.

[0154] In operation 1214, the robot (100) can identify a first score corresponding to the degree of performance of a preset task.

[0155] In action 1215, the robot (100) can identify a second score corresponding to the situation information.

[0156] In action 1216, the robot (100) can identify a third score based on the first score and the second score.

[0157] In operation 1217, the robot (100) can control the function step by step based on the third score.

[0158] At action 1218, the robot (100) can immediately stop the function based on the third score.

[0159] FIG. 13 is a flowchart illustrating the operation of a robot according to one or more embodiments.

[0160] Referring to FIG. 13, in operation 1310, the robot (100) can monitor at least one function of the robot (100) to perform a preset task.

[0161] In operation 1320, if the robot (100) identifies that an error has occurred in at least one function, it can identify the type of error.

[0162] In operation 1330, the robot (100) can identify the degree to which a preset task can be performed due to an error based on the type of error.

[0163] In operation 1340, the robot (100) can deteriorate and control at least one function based on the degree of performance of a preset task.

[0164] Since the method of identifying the type of error, identifying the degree of performance of a preset task, and controlling at least one function has been specifically described in the various embodiments described above, a redundant description will be omitted.

[0165] The control method described in Fig. 13 can be performed by a robot (100) having the configuration of Fig. 2 described above, but is not necessarily limited thereto, and can also be performed by a robot having various configurations.

[0166] The various embodiments described above may be implemented as a single embodiment, or at least one of the embodiments may be combined in whole or in part to be implemented together in one device.

[0167] According to the various embodiments described above, when an error occurs in at least one function, the robot can increase the productivity of the robot by controlling at least one function in a stepwise manner rather than immediately stopping it.

[0168] Meanwhile, the various embodiments described above may be applied to a product as an embodiment alone, but at least some of the contents may be implemented in combination with other embodiments of the present disclosure.

[0169] The various embodiments described above can be implemented as software including instructions stored in a machine-readable storage medium that can be read by a machine (e.g., a computer). The machine is a device that can call instructions stored in the storage medium and operate according to the called instructions, and may include an electronic device (e.g., a robot (100)) according to the disclosed embodiments. When an instruction is executed by a processor, the processor can perform a function corresponding to the instruction directly or by using other components under the control of the processor. The instruction may include code generated or executed by a compiler or interpreter. The machine-readable storage medium can be provided in the form of a non-transitory computer-readable storage medium. Here, 'non-transitory' means that the storage medium does not contain a signal and is tangible, but does not distinguish between data being stored semi-permanently or temporarily in the storage medium.

[0170] Additionally, according to one embodiment of the present disclosure, the method according to the various embodiments described above may be provided as included in a computer program product.

[0171] Specifically, a non-transitory readable storage medium or a computer program product storing computer instructions may be provided that perform an action of monitoring at least one function of a robot for performing a preset task, an action of identifying a type of error when an error is identified in at least one function, an action of identifying a degree of performance of the preset task due to the error based on the type of error, and an action of controlling at least one function based on the degree of performance of the preset task.

[0172] The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or online through an application store (e.g., Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created in a storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0173] In addition, computer instructions or programs for performing the control methods of the robot according to the various embodiments described above may be stored in a non-transitory computer-readable medium. The computer instructions stored in such a non-transitory computer-readable medium, when executed by a processor of a specific device, cause the specific device to perform processing operations in the device according to the various embodiments described above. A non-transitory computer-readable medium refers to a medium that stores data semi-permanently and can be read by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specific examples of non-transitory computer-readable media may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, or ROM.

[0174] Although the preferred embodiments of the present disclosure have been illustrated and described above, the present disclosure is not limited to the specific embodiments described above, and various modifications may be made by a person skilled in the art to which the present disclosure pertains without departing from the gist of the present disclosure as claimed in the claims, and such modifications should not be understood individually from the technical idea or prospect of the present disclosure.

Claims

1. In robots, memory that stores instructions; and one or more processors including processing circuitry; The one or more processors, when the instructions are individually or collectively executed, cause the robot to: Monitor at least one function of the robot related to a preset task, If an error related to at least one of the above functions is identified, the type of the error is identified, Based on the type of the above error, identify the degree to which the above preset task can be performed after the above error occurs, A robot that changes at least one function based on the degree of performance of the above-described task.

2. In paragraph 1, The above memory is, Further storing score information corresponding to the type of error associated with each of a plurality of tasks including the above-described preset task, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Based on the above score information, identify a score corresponding to the degree of performance of the preset task, A robot that changes at least one function based on the score.

3. In paragraph 1, further comprising at least one sensor; The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Obtain situational information about the working environment of the robot based on sensing data obtained from at least one sensor, A robot that changes at least one function based on the degree of performance of the above-described task and the above-described situation information.

4. In paragraph 3, The above memory is, Further storing first score information corresponding to the type of error associated with each of a plurality of tasks including the above-described preset task and second score information according to the situation of the plurality of task environments, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Identifying a first score corresponding to the degree of performance of the preset task based on the first score information and the second score information, Identifying a second score corresponding to the situation information based on the first score information and the second score information, A robot that changes at least one function based on the first score and the second score.

5. In paragraph 4, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Identifying one of a plurality of control levels corresponding to the at least one function based on the first score and the second score, A robot that changes at least one function based on the identified control level.

6. In paragraph 5, The above multiple control levels are: A robot comprising at least one of: maintaining function, maintaining limited function, stopping function after completion of current task, and stopping function immediately.

7. In paragraph 5, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: A robot that provides warning notifications corresponding to the above identified control levels.

8. In paragraph 5, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Identifying a weight to be applied to each of the first score and the second score based on the number of types of the above situation information, A robot that changes at least one function based on the first score and the second score to which the identified weights are applied.

9. In paragraph 5, The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Identifying second sensing data to replace the first sensing data of the sensor in which the error occurred among the at least one sensor based on the type of the error; A robot that identifies the degree to which the preset task can be performed by replacing the first sensing data with the second sensing data.

10. In paragraph 1, further comprising at least one sensor; The above instructions, when individually or collectively executed by the one or more processors, cause the robot to: Inputting the type information of the above error and the sensing data obtained from the at least one sensor into an artificial intelligence model to identify one of a plurality of control levels corresponding to the at least one function, A robot that changes at least one function based on the identified control level.

11. In the method of controlling a robot, An action of monitoring at least one function of said robot related to a preset task; An action of identifying a type of error when an error related to at least one function is identified; An operation for identifying the degree to which the preset task can be performed after the error occurs based on the type of the error; and A control method comprising: an operation for changing at least one function based on the degree of performance of the above-described preset task; 12. In paragraph 11, An action that changes at least one of the above functions, An operation of identifying a score corresponding to the degree of performance of the preset task based on score information corresponding to the type of error associated with each of a plurality of tasks including the preset task; and A control method further comprising: an operation for changing the at least one function based on the score.

13. In paragraph 11, An action that changes at least one of the above functions, An operation of obtaining situational information about the working environment of the robot based on sensing data; and A control method further comprising an operation for changing the at least one function based on the performability of the above-described task and the situation information.

14. In paragraph 13, An action that changes at least one of the above functions, An operation of identifying a first score corresponding to the degree of performance of the preset task based on score information corresponding to the type of error associated with each of a plurality of tasks including the preset task; An operation of identifying a second score corresponding to the situation information based on the situation score information of multiple work environments; and A control method further comprising: an operation for changing the at least one function based on the first score and the second score.

15. A non-transitory computer-readable storage medium storing computer instructions that, when executed by a processor of the robot, cause the robot to perform an action, wherein the action is: An action of monitoring at least one function of said robot related to a preset task; An action of identifying a type of error when an error related to at least one function is identified; An operation for identifying the degree to which the preset task can be performed after the error occurs based on the type of the error; and A non-transitory computer-readable storage medium, comprising: an operation for changing at least one function based on the degree of performance of the above-described preset task;

Images