10, ambient environment information about the AI device 10, and user information by using various sensors.

Examples of the sensors included in the sensor 14 may include a proximity sensor, an illuminance sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, an optical sensor, a microphone, a lidar, and a radar.

The output interface 15 may generate an output related to a visual sense, an auditory sense, or a haptic sense.

At this time, the output interface 15 may include a display unit for outputting time information, a speaker for outputting auditory information, and a haptic module for outputting haptic information.

The memory 17 may store data that supports various functions of the AI device 10. For example, the memory 17 may store input data acquired by the input interface 12, learning data, a learning model, a learning history, and the like.

The processor 18 may determine at least one executable operation of the AI device 10 based on information determined or generated by using a data analysis algorithm or a machine learning algorithm. The processor 18 may control the components of the AI device 10 to execute the determined operation.

To this end, the processor 18 may request, search, receive, or utilize data of the learning processor 13 or the memory 17. The processor 18 may control the components of the AI device 10 to execute the predicted operation or the operation determined to be desirable among the at least one executable operation.

When the connection of an external device is required to perform the determined operation, the processor 18 may generate a control signal for controlling the external device and may transmit the generated control signal to the external device.

The processor 18 may acquire intention information for the user input and may determine the user's requirements based on the acquired intention information.

The processor 18 may acquire the intention information corresponding to the user input by using at least one of a speech to text (STT) engine for converting speech input into a text string or a natural language processing (NLP) engine for acquiring intention information of a natural language.

At least one of the STT engine or the NLP engine may be configured as an artificial neural network, at least part of which is learned according to the machine learning algorithm. At least one of the STT engine or the NLP engine may be learned by the learning processor 13, may be learned by the learning processor 24 of the AI server 20, or may be learned by their distributed processing.

The processor 18 may collect history information including the operation contents of the AI apparatus 100 or the user's feedback on the operation and may store the collected history information in the memory 17 or the learning processor 13 or transmit the collected history information to the external device such as the AI server 20. The collected history information may be used to update the learning model.

The processor 18 may control at least part of the components of AI device 10 so as to drive an application program stored in memory 17. Furthermore, the processor 18 may operate two or more of the components included in the AI device 10 in combination so as to drive the application program.

FIG. 2 illustrates an AI server 20 connected to a robot according to an embodiment of the present disclosure.

Referring to FIG. 2, the AI server 20 may refer to a device that learns an artificial neural network by using a machine learning algorithm or uses a learned artificial neural network. The AI server 20 may include a plurality of servers to perform distributed processing, or may be defined as a 5G network. At this time, the AI server 20 may be included as a partial configuration of the AI device 10, and may perform at least part of the AI processing together.

The AI server 20 may include a communicator 21, a memory 23, a learning processor 24, a processor 26, and the like.

The communicator 21 can transmit and receive data to and from an external device such as the AI device 10.

The memory 23 may include a model storage unit 23a. The model storage unit 23a may store a learning or learned model (or an artificial neural network 26b) through the learning processor 24.

The learning processor 24 may learn the artificial neural network 26b by using the learning data. The learning model may be used in a state of being mounted on the AI server 20 of the artificial neural network, or may be used in a state of being mounted on an external device such as the AI device 10.

The learning model may be implemented in hardware, software, or a combination of hardware and software. If all or part of the learning models are implemented in software, one or more instructions that constitute the learning model may be stored in memory 23.

The processor 26 may infer the result value for new input data by using the learning model and may generate a response or a control command based on the inferred result value.

FIG. 3 illustrates an AI system 1 according to an embodiment of the present disclosure.

Referring to FIG. 3, in the AI system 1, at least one of an AI server 20, a robot 10a, a self-driving vehicle 10b, an XR device 10c, a smartphone 10d, or a home appliance 10e is connected to a cloud network 2. The robot 10a, the self-driving vehicle 10b, the XR device 10c, the smartphone 10d, or the home appliance 10e, to which the AI technology is applied, may be referred to as AI devices 10a to 10e.

The cloud network 2 may refer to a network that forms part of a cloud computing infrastructure or exists in a cloud computing infrastructure. The cloud network 2 may be configured by using a 3G network, a 4G or LTE network, or a 5G network.

That is, the devices 10a to 10e and 20 configuring the AI system 1 may be connected to each other through the cloud network 2. In particular, each of the devices 10a to 10e and 20 may communicate with each other through a base station, but may directly communicate with each other without using a base station.

The AI server 20 may include a server that performs AI processing and a server that performs operations on big data.

The AI server 20 may be connected to at least one of the AI devices constituting the AI system 1, that is, the robot 10a, the self-driving vehicle 10b, the XR device 10c, the smartphone 10d, or the home appliance 10e through the cloud network 2, and may assist at least part of AI processing of the connected AI devices 10a to 10e.

At this time, the AI server 20 may learn the artificial neural network according to the machine learning algorithm instead of the AI devices 10a to 10e, and may directly store the learning model or transmit the learning model to the AI devices 10a to 10e.

At this time, the AI server 20 may receive input data from the AI devices 10a to 10e, may infer the result value for the received input data by using the learning model, may generate a response or a control command based on the inferred result value, and may transmit the response or the control command to the AI devices 10a to 10e.

Alternatively, the AI devices 10a to 10e may infer the result value for the input data by directly using the learning model, and may generate the response or the control command based on the inference result.

Hereinafter, various embodiments of the AI devices 10a to 10e to which the above-described technology is applied will be described. The AI devices 10a to 10e illustrated in FIG. 3 may be regarded as a specific embodiment of the AI device 10 illustrated in FIG. 1.

<AI+Robot>

The robot 10a, to which the AI technology is applied, may be implemented as a guide robot, a carrying robot, a cleaning robot, a wearable robot, an entertainment robot, a pet robot, an unmanned flying robot, or the like.

The robot 10a may include a robot control module for controlling the operation, and the robot control module may refer to a software module or a chip implementing the software module by hardware.

The robot 10a may acquire state information about the robot 10a by using sensor information acquired from various kinds of sensors, may detect (recognize) surrounding environment and objects, may generate map data, may determine the route and the travel plan, may determine the response to user interaction, or may determine the operation.

The robot 10a may use the sensor information acquired from at least one sensor among the lidar, the radar, and the camera so as to determine the travel route and the travel plan.

The robot 10a may perform the above-described operations by using the learning model composed of at least one artificial neural network. For example, the robot 10a may recognize the surrounding environment and the objects by using the learning model, and may determine the operation by using the recognized surrounding information or object information. The learning model may be learned directly from the robot 10a or may be learned from an external device such as the AI server 20.

At this time, the robot 10a may perform the operation by generating the result by directly using the learning model, but the sensor information may be transmitted to the external device such as the AI server 20 and the generated result may be received to perform the operation.

The robot 10a may use at least one of the map data, the object information detected from the sensor information, or the object information acquired from the external apparatus to determine the travel route and the travel plan, and may control the driving unit such that the robot 10a travels along the determined travel route and travel plan.

The map data may include object identification information about various objects arranged in the space in which the robot 10a moves. For example, the map data may include object identification information about fixed objects such as walls and doors and movable objects such as pollen and desks. The object identification information may include a name, a type, a distance, and a position.

In addition, the robot 10a may perform the operation or travel by controlling the driving unit based on the control/interaction of the user. At this time, the robot 10a may acquire the intention information of the interaction due to the user's operation or speech utterance, and may determine the response based on the acquired intention information, and may perform the operation.

<AI+Robot+Self-Driving>

The robot 10a, to which the AI technology and the self-driving technology are applied, may be implemented as a guide robot, a carrying robot, a cleaning robot, a wearable robot, an entertainment robot, a pet robot, an unmanned flying robot, or the like.

The robot 10a, to which the AI technology and the self-driving technology are applied, may refer to the robot itself having the self-driving function or the robot 10a interacting with the self-driving vehicle 10b.

The robot 10a having the self-driving function may collectively refer to a device that moves for itself along the given movement line without the user's control or moves for itself by determining the movement line by itself.

The robot 10a and the self-driving vehicle 10b having the self-driving function may use a common sensing method so as to determine at least one of the travel route or the travel plan. For example, the robot 10a and the self-driving vehicle 10b having the self-driving function may determine at least one of the travel route or the travel plan by using the information sensed through the lidar, the radar, and the camera.

The robot 10a that interacts with the self-driving vehicle 10b exists separately from the self-driving vehicle 10b and may perform operations interworking with the self-driving function of the self-driving vehicle 10b or interworking with the user who rides on the self-driving vehicle 10b.

At this time, the robot 10a interacting with the self-driving vehicle 10b may control or assist the self-driving function of the self-driving vehicle 10b by acquiring sensor information on behalf of the self-driving vehicle 10b and providing the sensor information to the self-driving vehicle 10b, or by acquiring sensor information, generating environment information or object information, and providing the information to the self-driving vehicle 10b.

Alternatively, the robot 10a interacting with the self-driving vehicle 10b may monitor the user boarding the self-driving vehicle 10b, or may control the function of the self-driving vehicle 10b through the interaction with the user. For example, when it is determined that the driver is in a drowsy state, the robot 10a may activate the self-driving function of the self-driving vehicle 10b or assist the control of the driving unit of the self-driving vehicle 10b. The function of the self-driving vehicle 10b controlled by the robot 10a may include not only the self-driving function but also the function provided by the navigation system or the audio system provided in the self-driving vehicle 10b.

Alternatively, the robot 10a that interacts with the self-driving vehicle 10b may provide information or assist the function to the self-driving vehicle 10b outside the self-driving vehicle 10b. For example, the robot 10a may provide traffic information including signal information and the like, such as a smart signal, to the self-driving vehicle 10b, and automatically connect an electric charger to a charging port by interacting with the self-driving vehicle 10b like an automatic electric charger of an electric vehicle.

FIG. 4 is an exploded perspective view of a robot according to an embodiment of the present disclosure.

A robot 10a according to the present embodiment may include a main body 200, a neck body 300, and a head 400.

The main body 200 may include a driving wheel 202 for driving the robot 10a. The driving wheel 202 may protrude downward from the main body 200.

In addition, casters 203 may be provided in the main body 200. The caster 203 may protrude downward from the main body 200 and assist the robot 10a in traveling.

The number and location of the driving wheel 202 and the casters 203 may vary as needed.

The main body 200 may be accommodated in housings 211 and 212. That is, the housings 211 and 212 may be skins surrounding the main body 200. The housings 211 and 212 may form the outer appearance of the robot 10a.

The housings 211 and 212 may include a front housing 211 and a rear housing 212. Therefore, fastening and separating work of the housings 211 and 212 may be facilitated.

The front housing 211 may be curved convexly forward, and the rear housing 212 may be curved convexly backward. The rear end of the front housing 211 and the front end of the rear housing 212 may come into contact with each other. Outer surfaces of the front housing 211 and the rear housing 212 may be continuously connected.

A lidar 204 may be provided in the main body 200. A recessed portion 211a in which the lidar 204 is disposed may be formed in the front housing 211. The recessed portion 211a may be recessed rearward from the front surface of the front housing 211. The recessed portion 211a may be opened forward and may be elongated in the left-and-right direction. The lidar 204 may detect an obstacle or a person located in front of the robot 10a through the recessed portion 211a.

In addition, a plurality of ultrasonic sensors (not shown) may be provided in the main body 200. The plurality of ultrasonic sensors may be spaced apart from each other in the circumferential direction of the main body 200. In more detail, a plurality of openings in which the ultrasonic sensors are disposed may be formed in outer circumferences of the housings 211 and 212. The ultrasonic sensors may detect an object around the robot 10a through the openings.

The main body 200 may be provided with a terminal 206 for charging the robot 10a. A through-hole through which the terminal 206 passes may be formed in the housing 210, more specifically, the front housing 211. The terminal 206 may protrude forward from the housing 210 through the through-hole.

The robot 10a may dock the terminal 206 to a charger (not shown), and the charger may charge a battery 270 built in the robot 10a through the terminal 206. The charger may be installed on an indoor wall or structure in which the robot 10a travels.

On the other hand, the neck body 300 may be elongated upward from the front portion of the main body 200. The neck body 300 may be formed vertically.

The head 400 may be provided at the upper end of the neck body 300. The head 400 may include a display 410. A preset image or video may be output on the display 410. In addition, the display 410 may include a touch panel.

FIG. 5 is a side view of the main body of the robot according to an embodiment of the present disclosure, FIG. 6 is a front view of the main body of the robot according to an embodiment of the present disclosure, and FIG. 7 is a bottom view of the main body of the robot according to an embodiment of the present disclosure.

The body 200 may include a base 230, a plurality of lower pillars 231 extending upward from the base 230, and an upper module 240 supported by the plurality of lower pillars 231.

The base 230 may be a horizontal plate. The driving wheel 202 and the casters 203 may be connected to the base 230.

The plurality of lower pillars 231 may extend vertically between the base 230 and the upper module 240. The plurality of lower pillars 231 may support the upper module 240 from the lower side. The plurality of lower pillars 231 may be spaced apart from each other, and the load of the upper module 240 may be uniformly distributed to the plurality of lower pillars 231.

The lower end of the lower pillar 231 may be fastened to the base 230, and the upper end of the lower pillar 231 may be fastened to the upper module 240, more specifically, a first plate 241 to be described below.

That is, the main body 200 may have a substantially flat plate structure. This has an effect of securing a wide inner space and reducing vibration.

The upper module 240 may be spaced upward from the base 230 and supported by the plurality of lower pillars 231. The neck body 300 may be connected to the upper module 240.

In more detail, the upper module 240 may include a plurality of plates 241 and 242 spaced apart from each other in a vertical direction, and a plurality of upper pillars 243 disposed between the plurality of plates 241 and 242. The plurality of plates 241 and 242 may be respectively disposed horizontally, and the plurality of upper pillars 243 may extend vertically.

The number of plates 241 and 242 and the vertical distance between the plurality of plates 241 and 353 may vary as needed. That is, the height and number of floors of the upper module 240 may vary according to the functions or roles required of the robot 10.

Hereinafter, a case where the plurality of plates 241 and 242 are a pair will be described as an example.

The pair of plates 241 and 242 may include a first plate 241 spaced upward apart from the base 230, and a second plate 241 spaced upward from the first plate 241. In this case, the plurality of upper pillars 243 may be located between the first plate 241 and the second plate 242 and may support the second plate 242 from the lower side. The lower end of the upper pillar 243 may be fastened to the first plate 241, and the upper end of the upper pillar 243 may be fastened to the second plate 242.

On the other hand, the main body 200 may further include at least one substrate 270 and a battery 280.

At least one substrate 270 may include a plurality of processors for operating the robot 10a. For example, a plurality of substrates 270 may be provided. The plurality of substrates 270 may include a main control board for controlling overall operations of the robot 10a and a power board electrically connected to the battery 280.

The battery 280 may supply power required for operations of the robot 10a. The battery 280 may be electrically connected to the terminal 206, and the battery 280 may be charged through the terminal 206.

The battery 280 may be located below the substrate 270. That is, since the relatively heavy battery 280 is located below the main body 200, the center of gravity of the main body 200 may be lowered and the robot may travel stably.

In more detail, the battery 280 may be located between the base 230 and the upper module 240. The base 230 may support the battery 280. In addition, the battery 280 may be located eccentrically to the rear. Therefore, the load of the battery 280 and the load of the neck body 300 and the head (see 400 of FIG. 4) may be balanced.

At least one substrate 270 may be disposed inside the upper module 240. For example, at least one substrate 270 may be located between the first plate 241 and the second plate 242.

On the other hand, the lidar 204 and the terminal 206 may be fastened to the base 230.

The lidar 204 and the terminal 206 may be mounted on the front portion of the base 230. In more detail, a lidar mounter 204a, to which the lidar 204 is mounted, and a charger 206a, from which the terminal 206 protrudes, may be fastened to the front portion of the base 230.

The lidar mounter 204a may be fastened to the upper surface of the base 230, and the lidar 204 may be spaced upward apart from the base 230 by the lidar mounter 204a. In addition, the lidar 204 may be located below the upper module 240.

The charger 206a may be located below the lidar mounter 204a. The terminal 206 may protrude forward from the charger 206a.

On the other hand, the main body 200 may further include a suspension 500 to which the driving wheel 202 is connected. The suspension 500 may be provided on at least one of the plurality of lower pillars 231. For example, the driving wheels 202 may be provided with a pair located on both sides of the base 230, and the suspension 500 may be provided with a pair to which a pair of driving wheels 202 are connected.

The suspension 202 may minimize vibration or shock transmitted to the main body 200 through the driving wheel 202. In more detail, the driving wheel 202 may move upward and downward due to the suspension 500. Therefore, even when the ground is uneven and bumpy, the driving wheel 202 may move upward and downward while maintaining contact with the ground. Therefore, the robot may travel stably with less shaking. A detailed configuration of the suspension 500 will be described below in detail.

A pair of cutouts 232 may be formed in the base 230 so as to prevent the driving wheel 202 and the suspension 500 from interfering with the base. The pair of cutouts 232 may be formed on both sides of the base 230.

The cutouts 232 may include a first cutout 233 where the driving wheel 202 is located and a second cutout 234 located inside the first cutout 233.

The second cutout 234 may prevent interference between the suspension 500 and the base 230 when the driving wheel 202 moves upward and downward. That is, the suspension 500 may protrude downward from the base 230 through the second cutout 234.

FIG. 8 is a view for describing the positions of the plurality of lower pillars and the plurality of upper pillars according to an embodiment of the present disclosure.

The body 200 may have a bilaterally symmetrical shape.

In more detail, with respect to an imaginary reference plane X1 crossing the center of the robot 10a back and forth, the base 230 and the plurality of plates 241 and 242 may have a symmetrical shape, and the plurality of lower pillars 231 and the plurality of upper pillars 234 may be symmetrically disposed. Accordingly, the center C of gravity of the robot 10a may be located on the reference plane X1.

The plurality of lower pillars 231 may be disposed closer to the edge of the base 230 than to the center of the base 230. Accordingly, a wide space is secured between the base 230 and the upper module 240, and a sufficiently large battery 280 may be disposed in the space. In addition, the load of the upper module 240 may be more efficiently distributed to the plurality of lower pillars 231.

For example, the plurality of lower pillars 231 may include a pair of first lower pillars 231a, a pair of second lower pillars 231b, a third lower pillar 231c, and a pair of fourth lower pillars 231d.

The pair of first lower pillars 231a may be located on both sides of the front of the base 230, and the pair of second lower pillars 231b may be located on both sides of the rear of the base 230. The pair of first lower pillars 231a and the pair of second lower pillars 231b may be located symmetrically with respect to the reference plane X1, and thus, he load of the upper module 240 may be widely distributed and stably supported.

The third lower pillar 231c may be located on the reference plane X1. The third lower pillar 231c may be located in the front center of the base 230. The third lower pillar 231c may intensively support the loads of the neck body 300 and the head 400.

The pair of fourth lower pillars 231d may be located at both sides of the center of the base 230 and may be located symmetrically with respect to the reference plane X1. The pair of fourth lower pillars 231d may not only support the load of the upper module 240, but also act as a suspension mounter where the suspension 500 is installed. This will be described in detail below.

The plurality of upper pillars 243 may be disposed closer to the edge of the first plate 241 than to the center of the first plate 241. Therefore, a wide space may be secured between the first plate 241 and the second plate 242. In addition, the load of the second plate 242 or an object placed on the second plate 242 may be more efficiently distributed to the plurality of upper pillars 243.

For example, the plurality of upper pillars 243 may include a pair of first upper pillars 243a, a pair of second upper pillars 243b, and a third upper pillar 243c.

The pair of first upper pillars 243a may be located on both sides of the front of the first plate 241, and the pair of second upper pillars 243b may be located on both sides of the rear of the first plate 241. The pair of first upper pillars 243a and the pair of second upper pillars 243b may be located symmetrically with respect to the reference plane X1, and the load of the first plate 242 and the object placed on the first plate 242 may be widely distributed and stably supported.

The third upper pillar 231c may be located on the reference plane X1. The third upper pillar 231c may be located at the front center of the first plate 241. The third upper pillar 243c may intensively support the loads of the neck body 300 and the head 400.

The plurality of lower pillars 231 and the plurality of upper pillars 243 may each include at least one pair of pillars arranged symmetrically with each other with respect to a vertical axis passing through the center C of gravity of the robot 10a or a point C1 adjacent to the center C of gravity. That is, the diagonal intersection between the plurality of lower pillars 231 and the diagonal intersection between the plurality of upper pillars 243 may not deviate greatly from the center C of gravity of the robot 10a.

For example, a diagonal line connecting the first lower pillar 231a located on one side of the reference plane X1 and the second lower pillar 231b located on the other side of the reference plane X1 may pass through the point C1 adjacent to the center C of gravity. In this case, a diagonal line connecting the first lower pillar 231a located on the other side of the reference plane X1 and the second lower pillar 231b located on one side of the reference plane X1 may pass through the point C1.

In addition, a diagonal line connecting the first upper pillar 243a located on one side of the reference plane X1 and the second upper pillar 243b located on the other side of the reference plane X1 may pass through the center C of gravity. In this case, a diagonal line connecting the first upper pillar 243a located on the other side of the reference plane X1 and the second upper pillar 243b located on one side of the reference plane X1 may pass through the center C of gravity.

Accordingly, rotational moment generated by vibration transmitted through the driving wheel 202 may be minimized, and the robot 10a may travel more stably.

On the other hand, the upper end of the lower pillar 231 may be adjacent to the lower end of the upper pillar 243. Therefore, the load may be easily transmitted to the upper pillar 243 and the lower pillar 231.

In more detail, the upper end of the first lower pillar 231a and the lower end of the first upper pillar 243a may be adjacent to each other. The upper end of the second lower pillar 231b and the lower end of the second upper pillar 243b may be adjacent to each other. The upper end of the third lower pillar 231c and the lower end of the third upper pillar 243c may be adjacent to each other.

FIG. 9 is a view illustrating the suspension according to an embodiment of the present disclosure, and FIG. 10 is a view of the suspension when viewed from the inside of the main body, according to an embodiment of the present disclosure.

The suspension 500 may be connected to at least one of the plurality of lower pillars 231. The suspension 500 may be provided with a pair to which the pair of driving wheels 200 are connected.

In more detail, the suspensions 500 may each include a slider 510, a spring 520, a suspension arm 530, and a connector 540.

The slider 510 may move upward and downward while sliding along the lower pillar 231, more specifically, the fourth lower pillar 231d. The slider 510 may be disposed to surround the outer circumference of the lower pillar 231.

The spring 520 may be disposed on the outer circumference of the lower pillar 231, more specifically, the fourth lower pillar 231d, and may press the slider 510 downward. The spring 520 may surround the outer circumference of the fourth lower pillar 231d, may be located above the slider 510, and may be vertically tensioned.

In more detail, a spring connector 521 to which the spring 520 is connected may be provided at the upper end of the fourth lower pillar 231d. The spring connector 521 may come into contact with the lower surface of the upper module 240, more specifically, the first plate 241. The upper end of the spring 520 may be connected to the spring connector 521, and the lower end of the spring 520 may be connected to the slider 510. The spring 520 may be compressed or tensioned between the spring connector 521 and the slider 510. The spring 520 may act as a damper that cancels vibration transmitted from the driving wheel 202.

The suspension arm 530 may be connected to the slider 510 and the driving wheel 202. The slider 510 may be located on one side of the suspension arm 530, and the driving wheel 202 may be located on the other side of the suspension arm 530.

In addition, the suspension arm 530 may move the slider 510 and the driving wheel 202 upward and downward while rotating with respect to the connector 540.

In more detail, an elongated hole (see 535 of FIG. 14) may be formed in the suspension arm 530 in one direction (e.g., in the front-and-rear direction), and a protruding pin 511 inserted into the elongated hole 535 may be formed in the slider 510.

As the slider 510 moves upward and downward, the protruding pin 511 may move between both ends of the elongated hole 535. Accordingly, the rotational motion of the suspension arm 530 may be converted into the vertical motion of the slider 510.

In addition, a through hole (see 536 of FIG. 14) through which a rotational shaft 206 of the driving wheel 202 passes may be formed in the suspension arm 530. Accordingly, the driving wheel