Inter-floor movement method using elevator in multi-story building

Abstract

According to one embodiment of the present disclosure, disclosed is an autonomous driving robot having an inter-floor movement function using an elevator in a multi-story building.

Description

Method of moving between floors using an elevator in a multi-story building

[0001] The present invention relates to a method for moving between floors via an elevator in a multi-story building, and more specifically, to a technology for an autonomous delivery robot to move between floors efficiently via an elevator in a multi-story building.

[0002] Recently, the use of autonomous robots has been increasing in various service sectors, including logistics, delivery, guidance, and security. These autonomous robots are designed to move stably and perform tasks even in complex indoor environments. In particular, moving between floors is essential for robots to perform missions in multi-story buildings, and it is common practice to use elevators for this purpose.

[0003] The elevator is a key facility responsible for vertical movement within a building and is generally controlled by a hoisting machine located in the elevator machine room on the top floor. The hoisting machine raises and lowers the elevator car using wire ropes, and the operation of the elevator is controlled by a control panel inside the machine room. The control panel receives floor call signals, determines the elevator's travel path, and performs the function of stopping the elevator at the precise location on each floor.

[0004] The elevator control panel is a critical facility within a building and operates as a closed system to prevent accidents caused by unauthorized external access or manipulation. Consequently, it is practically difficult for autonomous robots to communicate directly with the elevator control system to use the elevator.

[0005] Korean Patent No. 10-2484732 discloses a control system and control method for inter-floor movement of an autonomous driving robot.

[0006] Due to the closed system of elevator control panels, a method is required for autonomous robots to move between floors in multi-story buildings by calling and boarding an elevator without communicating with the control panel.

[0007] The present disclosure aims to propose a method for moving between floors by efficiently and reliably calling an elevator without communication with an elevator control panel, without modifying the existing elevator system.

[0008] Meanwhile, the technical problem that the present disclosure aims to solve is not limited to the technical problem mentioned above, and various technical problems may be included within the scope obvious to a person skilled in the art from the contents described below.

[0009] An autonomous driving robot equipped with an elevator calling function within a multi-story building according to an embodiment of the present disclosure for realizing the aforementioned objectives is disclosed. The robot comprises: a communication unit that communicates with a button operation module mounted on each elevator of the multi-story building, an elevator internal sensor module, and an elevator call module installed at the elevator boarding area of ​​each floor of the multi-story building; a robot sensor module that detects the position and surrounding environment of the robot; at least one processor; and a memory. The at least one processor may be configured such that, as a path from the robot's current position to a destination is set, the robot calls the elevator to a robot material floor corresponding to the current position via a button operation module included in the elevator and moves to the boarding area of ​​the robot material floor; when the opening of the elevator door is detected via the robot sensor module, the robot determines whether to board the elevator; if boarding is determined, executes a boarding process for the elevator; after boarding, controls the elevator to move to a destination floor corresponding to the destination via a button operation module of the elevator; and upon arrival at the destination floor, executes a disembarking process.

[0010] According to one embodiment, the processor may be configured to determine whether the elevator is moving toward the destination floor based on floor button activation information obtained through the button operation module of the elevator, determine whether the internal congestion level of the elevator is below a threshold, and if the elevator is moving toward the destination floor and the congestion level is below the threshold, decide to board the elevator.

[0011] According to one embodiment, the processor may be configured to calculate the congestion level based on visual information and weight information obtained based on the robot sensor module or the elevator interior sensor module.

[0012] According to one embodiment, the processor may be configured to maintain the elevator in an open state through the button operation module, move into the elevator to board, and close the elevator door through the button operation module when boarding is completed.

[0013] According to one embodiment, the processor may be configured to determine whether a button corresponding to the destination floor of the elevator is activated through the button operation module, and if the button corresponding to the destination floor is not activated, to activate it.

[0014] According to one embodiment, the processor may be configured to determine whether it has arrived at the destination floor through the button operation module, the robot sensor module, or the elevator interior sensor module, and if it has arrived at the destination floor, to maintain the elevator in an open state through the button operation module, to exit the elevator, and to perform the operation of closing the elevator door through the button operation module when the exit is completed.

[0015] According to one embodiment, the processor may be configured to respond based on a Large Language Model (LLM) that has been pre-trained in preparation for an abnormal state when the waiting time of the robot exceeds a threshold, when an impact detected through the robot sensor module exceeds a threshold, or when the estimated time of arrival at the destination is delayed by more than a threshold.

[0016] According to one embodiment, the processor may be further configured to output a visual, auditory, or physical signal that can notify the surroundings that the robot is boarding or alighting during the execution of the boarding process or the alighting process.

[0017]

[0018] According to one embodiment of the present disclosure for realizing the aforementioned objectives, a method for calling an elevator in a multi-story building performed by an autonomous driving robot is disclosed. The method may include: an operation to call the elevator to a robot material floor corresponding to the current location and move to a boarding area on the robot material floor through a button operation module included in the elevator, as a path from the robot's current location to a destination is set; an operation to determine whether to board the elevator when the opening of the elevator is detected through a robot sensor module that detects the robot's location and surrounding environment; an operation to execute a boarding process for the elevator when boarding is determined; an operation to control the elevator to move to a destination floor corresponding to the destination through a button operation module of the elevator after boarding; and an operation to execute a disembarking process when arriving at the destination floor.

[0019] According to one embodiment, the operation of determining whether to board the elevator may include: determining whether the elevator is moving toward the destination floor based on floor button activation information obtained through the button operation module of the elevator; determining whether the internal congestion level of the elevator is below a threshold; and determining to board the elevator if the elevator is moving toward the destination floor and the congestion level is below the threshold.

[0020] According to one embodiment, the operation of determining whether the congestion level is below a threshold may include the operation of calculating the congestion level based on visual information and weight information obtained based on the robot sensor module or the elevator interior sensor module.

[0021] According to one embodiment, the operation of executing the boarding process may include: maintaining the elevator in an open state through the button operation module; moving into the elevator and boarding; and closing the elevator door through the button operation module when boarding is completed.

[0022] According to one embodiment, the operation of controlling the elevator to move to a destination floor corresponding to the destination may include: the operation of determining whether a button corresponding to the destination floor of the elevator is activated through the button operation module; and the operation of activating the button corresponding to the destination floor if it is not activated.

[0023] According to one embodiment, the operation of executing a disembarking process upon arrival at the destination floor may include: determining whether the destination floor has been reached through the button operation module, the robot sensor module, or the elevator interior sensor module; maintaining the elevator in an open state through the button operation module when the destination floor has been reached; disembarking from the elevator; and closing the elevator door through the button operation module when disembarking is completed.

[0024] According to one embodiment, the operation of executing the boarding process or the disembarking process may include a corresponding operation based on a Large Language Model (LLM) that has been pre-trained in preparation for an abnormal state when the waiting time of the robot exceeds a threshold, when an impact detected through the robot sensor module exceeds a threshold, or when the estimated time of arrival at the destination is delayed by more than a threshold.

[0025] According to one embodiment, the operation of executing the boarding process or the disembarking process may further include an operation of outputting a visual, auditory, or physical signal that can notify the surroundings that the robot is boarding or disembarking during the execution of the boarding process or the disembarking process.

[0026]

[0027] According to one embodiment of the present disclosure for realizing the aforementioned objectives, an elevator calling system for an autonomous driving robot in a multi-story building is disclosed. The system comprises: a button operation module included in each elevator of the multi-story building and collecting activation information of each elevator's internal button; an elevator internal sensor module mounted in each elevator of the multi-story building; and an elevator calling module collecting activation information of an elevator call button installed at the elevator boarding area of ​​each floor of the multi-story building. The robot may be configured to include an autonomous driving robot having a function to move between floors within a multi-story building via an elevator, which communicates with the button operation module, the elevator interior sensor module, and the elevator call module, and the robot may be configured to call the elevator to the robot material floor corresponding to the current location through the button operation module as a path from the robot's current location to the destination is set, and when the opening of the elevator door is detected through the robot sensor module that detects the robot's location and surrounding environment, determine whether to board the elevator, execute a boarding process to the elevator if boarding is determined, control the elevator to move to the destination floor corresponding to the destination through the button operation module after boarding, and execute a disembarking process when arriving at the destination floor.

[0028] According to the present disclosure, by proposing a system that calls an elevator and performs inter-floor movement without communication with an elevator control panel within a multi-story building, the usability of autonomous robots in multi-story buildings can be enhanced and the scope of robot services can be expanded.

[0029] According to the present disclosure, the autonomous driving robot can efficiently perform delivery by independently deciding whether to board an elevator and performing inter-floor movement.

[0030] Meanwhile, the effects of the present disclosure are not limited to those mentioned above, and various effects may be included within the scope obvious to a person skilled in the art from the contents described below.

[0031] FIG. 1 is a block diagram of an autonomous driving robot that performs delivery within a multi-story building according to one embodiment of the present disclosure.

[0032] FIG. 2 is a block diagram of a plurality of modules for an autonomous driving robot (100) according to one embodiment of the present disclosure to efficiently perform inter-floor movement via an elevator within a multi-story building.

[0033] Figure 3 is a drawing illustrating an elevator system in a typical multi-story building.

[0034] FIG. 4 is a drawing for explaining an elevator call system of an autonomous driving robot according to one embodiment of the present disclosure.

[0035] FIG. 5 is a flowchart illustrating a method of moving between floors via an elevator in a multi-story building by an autonomous driving robot according to one embodiment of the present disclosure.

[0036] FIG. 6 is a flowchart illustrating a method for determining whether an autonomous driving robot rides an elevator according to one embodiment of the present disclosure.

[0037] FIG. 7 is a flowchart illustrating the operation in an exceptional situation of the boarding and disembarking process of an autonomous driving robot according to one embodiment of the present disclosure.

[0038]

[0039] Various embodiments are now described with reference to the drawings. In this specification, various descriptions are provided to provide an understanding of the present disclosure. However, it is evident that these embodiments can be practiced without such specific descriptions.

[0040] As used herein, terms such as “component,” “module,” “system,” etc. refer to computer-related entities, hardware, firmware, software, combinations of software and hardware, or executions of software. For example, a component may be, but is not limited to, a procedure executed on a processor, a processor, an object, an execution thread, a program, and / or a computer. For example, both an application executed on a computing device and the computing device itself may be a component. One or more components may reside within a processor and / or an execution thread. A component may be localized within a single computer. A component may be distributed among two or more computers. Additionally, these components may be executed from various computer-readable media having various data structures stored therein. Components may communicate through local and / or remote processes, for example, according to signals having one or more data packets (e.g., data from a component interacting with another component in a local system or distributed system, and / or data transmitted through signals to other systems and networks such as the Internet).

[0041] Furthermore, the term "or" is intended to mean an implicit "or" rather than an exclusive "or." That is, unless otherwise specified or evident from the context, "X uses A or B" is intended to mean one of the natural implicit substitutions. In other words, if X uses A; if X uses B; or if X uses both A and B, "X uses A or B" may apply to any of these cases. Additionally, the term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the enumerated related items.

[0042] Additionally, the terms “comprising” and / or “comprising” should be understood to mean that such features and / or components are present. However, the terms “comprising” and / or “comprising” should be understood not to exclude the presence or addition of one or more other features, components and / or groups thereof. Furthermore, unless otherwise specified or clearly evident from the context to indicate a singular form, the singular in this specification and claims should generally be interpreted to mean “one or more.”

[0043] And, the term "at least one of A or B" should be interpreted to mean "a case including only A," "a case including only B," or "a combination of A and B."

[0044] Those skilled in the art should recognize that the various exemplary logical blocks, configurations, modules, circuits, means, logics, and algorithmic steps described in connection with the embodiments disclosed herein may be implemented in electronic hardware, computer software, or a combination of both. To clearly exemplify the interchangeability of hardware and software, various exemplary components, blocks, configurations, means, logics, modules, circuits, and steps have been generally described above in terms of their functionality. Whether such functionality is implemented in hardware or software depends on the specific application and design constraints imposed on the overall system. Skilled technicians may implement the described functionality in various ways for each specific application. However, such decisions regarding implementation should not be construed as going beyond the scope of this disclosure.

[0045] The description of the presented embodiments is provided to enable those skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the present disclosure. Thus, the present invention is not limited to the embodiments presented herein. The present invention should be interpreted in the broadest possible scope consistent with the principles and novel features presented herein.

[0046] In the present disclosure, network functions, artificial neural networks, and neural networks may be used interchangeably.

[0047]

[0048] FIG. 1 is a block diagram of an autonomous driving robot (100) that performs inter-floor movement via an elevator in a multi-story building according to one embodiment of the present disclosure.

[0049] The configuration of the autonomous driving robot (100) equipped with a function for moving between floors within a multi-story building via an elevator as illustrated in FIG. 1 is merely a simplified example, and depending on the embodiment, the autonomous driving robot (100) may be a computing device of various forms. In one embodiment of the present disclosure, the robot (100) may include other configurations for performing the computing environment of the robot (100), and only some of the disclosed configurations may constitute the robot (100).

[0050] The robot (100) may include a processor (110), memory (130), and a communication unit (150).

[0051] The processor (110) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a robot (100) equipped with an elevator calling function in a multi-story building. The processor (110) may read a computer program stored in memory (130) and perform data processing for machine learning according to one embodiment of the present disclosure.

[0052] According to one embodiment of the present disclosure, the processor (110) can perform operations for learning a neural network. The processor (110) can perform operations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (110) can process the learning of the network function. For example, the CPU and GPGPU can together process the learning of the network function and data classification using the network function. In addition, in one embodiment of the present disclosure, processors of a plurality of computing devices can be used together to process the learning of the network function and data classification using the network function. In addition, the computer program executed in the target plastic classification device according to one embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

[0053] According to one embodiment of the present disclosure, the memory (130) can store any form of information generated or determined by the processor (110) and any form of information received by the communication unit (150).

[0054] According to one embodiment of the present disclosure, the memory (130) may include at least one type of storage medium among a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (e.g., SD or XD memory), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, a magnetic disk, and an optical disk. The target plastic sorting device (100) may operate in conjunction with web storage that performs the storage function of the memory (130) on the internet. The description of the memory described above is merely an example and the present disclosure is not limited thereto.

[0055] A communication unit (150) according to one embodiment of the present disclosure can use various wired communication systems such as a public switched telephone network (PSTN), xDSL (x Digital Subscriber Line), RADSL (Rate Adaptive DSL), MDSL (Multi Rate DSL), VDSL (Very High Speed ​​DSL), UADSL (Universal Asymmetric DSL), HDSL (High Bit Rate DSL), and a local area network (LAN).

[0056] In addition, the communication unit (150) presented in this specification may use various wireless communication systems such as CDMA (Code Division Multi Access), TDMA (Time Division Multi Access), FDMA (Frequency Division Multi Access), OFDMA (Orthogonal Frequency Division Multi Access), SC-FDMA (Single Carrier-FDMA), and other systems.

[0057] In the present disclosure, the communication unit (150) can be configured regardless of the mode of communication, such as wired and wireless, and can be configured as various communication networks such as a Local Area Network (LAN), a Personal Area Network (PAN), and a Wide Area Network (WAN). In addition, the network may be a known World Wide Web (WWW), and may utilize wireless transmission technology used for short-range communication, such as Infrared Data Association (IrDA) or Bluetooth.

[0058] The technologies described in this specification can be used not only in the networks mentioned above but also in other networks.

[0059]

[0060] FIG. 2 is a block diagram of a plurality of modules for an autonomous driving robot (100) according to one embodiment of the present disclosure to efficiently perform inter-floor movement via an elevator within a multi-story building.

[0061] According to one embodiment, the autonomous driving robot (100) may be composed of a movement path determining module (210) that determines a movement path to perform a mission (e.g., delivery) within a multi-story building, a robot sensor module (220) that detects the robot's location and surrounding environment, a boarding decision module (230) that determines whether to board an elevator that has been opened upon arrival at a boarding area, a boarding / alighting process control module (240) that controls the process of boarding the elevator and alighting from the elevator, and an exception handling module (250) that performs exception handling during the boarding / alighting process.

[0062] However, for the sake of convenience of explanation, the various modules within the autonomous driving robot (100) may be configured as separate devices from the autonomous driving robot (100) according to the embodiment. In particular, the autonomous driving robot (100) may have limitations on the size of the on-device model that can be mounted within the device, and to overcome this, the autonomous driving robot (100) may be configured to receive only the execution results of the various modules through an external server.

[0063] For example, in FIG. 2, the boarding decision module (230) and the exception handling module (250) are shown as internal modules of the autonomous driving robot (100), but are not limited thereto. The boarding decision and exception handling may be performed on an external server separate from the autonomous driving robot (100), and the autonomous driving robot (100) may receive results through communication with the external server via the communication unit (150).

[0064] In addition, the multiple modules for the autonomous driving robot (100) to call an elevator in the multi-story building described herein are not limited to the modules shown in FIG. 2. For example, as described above with reference to FIG. 1, the autonomous driving robot (100) may also include a control module that performs the function of a processor (110) for control, a communication module that performs the function of a communication unit (150), and a UI module for displaying that the boarding or alighting process is in progress during the movement process for performing a mission. The autonomous driving robot (100) may output a visual, auditory, or physical signal through the UI module to notify the surroundings that it is currently boarding or alighting.

[0065] According to one embodiment, the movement path determination module (210) can determine the movement path required for the robot (100) to perform a mission. For example, when the robot (100) performs a delivery mission, the movement path determination module (210) can set the robot material layer as the starting layer, the delivery destination layer as the destination layer, and set the movement path from the robot's current position to the elevator boarding area of ​​the starting layer, the movement path from the elevator boarding area of ​​the destination layer to the delivery destination of the destination layer, etc. In setting the movement path by the movement path determination module (210), the A* algorithm (A star algorithm), Dijkstra algorithm, RRT (Rapidly-exploring Random Tree) algorithm, reinforcement learning-based Q Learning or Deep Q-Network (DQN)-based algorithm, etc., may be utilized, and techniques such as SLAM (Simultaneous Localization and Mapping) may be utilized.

[0066] According to one embodiment, as the robot movement path determination module (210) determines the path, the autonomous driving robot (100) can call an elevator and move to the departure floor boarding area at the same time through the button operation module (410) described later with reference to FIG. 4.

[0067] According to one embodiment, the robot sensor module (220) can detect the location of the robot and the surrounding environment. The robot sensor module (220) utilizes various sensors to collect information about the robot's current location and surrounding environment, and based on this, supports the robot in moving safely and efficiently and performing tasks.

[0068] The robot sensor module (220) utilizes various technologies to accurately determine the robot's current position. For example, the robot sensor module (220) can generate a three-dimensional map of the surrounding environment by using a LiDAR (Light Detection and Ranging) sensor to emit laser pulses and measure the time it takes for them to reflect back. Through this, the robot can accurately determine its position and avoid obstacles. A GPS (Global Positioning System) can be used to determine the robot's absolute position by receiving satellite signals. As another example, since receiving GPS signals may be difficult in an indoor environment, an inertial sensor such as an IMU (Inertial Measurement Unit) can be used in conjunction to correct the robot's position. The IMU measures acceleration and rotational speed to calculate the robot's relative position change and combines this with GPS information to estimate the accurate position. As yet another example, the robot sensor module (220) can precisely measure the robot's position by utilizing UWB (Ultra-Wideband) communication technology. UWB is a technology that measures distance with high accuracy using a wide frequency band, enabling stable location measurement even in indoor environments.

[0069] In addition, the robot sensor module (220) may use various sensors to perceive the surrounding environment and detect obstacles. For example, the robot sensor module (220) may acquire image information through a camera to secure the robot's field of view and recognize people, objects, doors, etc. through computer vision technology.

[0070] As another example, the robot sensor module (220) can detect obstacles at a close distance by emitting ultrasonic waves through an ultrasonic sensor and measuring the time it takes for the reflected waves to return. This complements the blind spots of the LiDAR sensor and is effective in preventing the robot from colliding with nearby obstacles. As yet another example, the presence or absence of obstacles can be detected by emitting infrared rays through an infrared sensor and measuring the amount of reflected light. This allows for the detection of obstacles even in dark environments, contributing to the safe movement of the autonomous robot (100).

[0071] For the interaction between the autonomous driving robot (100) and the elevator, which will be described below, the robot sensor module (220) may utilize the aforementioned technologies or sensors. For example, the opening and closing of the elevator door may be detected by an infrared sensor or a laser sensor of the robot sensor module (220). Alternatively, a camera or a pressure sensor may be utilized to measure the level of congestion inside the elevator. The camera analyzes the video inside the elevator to determine the number of people, and the pressure sensor measures the pressure applied to the floor to estimate the level of congestion.

[0072] The robot sensor module (220) integrates various sensor information to enable the robot to accurately perceive the surrounding environment and move safely. The sensor information is fused through an algorithm such as a Kalman filter to remove noise and increase accuracy. Additionally, the sensor module (220) utilizes machine learning technology to analyze and learn sensor data to improve the robot's recognition capabilities. For example, using deep learning-based object recognition technology, it can accurately recognize and classify people, objects, doors, etc.

[0073] According to one embodiment, when the opening of the elevator door that has arrived at the boarding area is detected through the robot sensor module (220), the boarding decision module (230) can determine whether to board the elevator. The boarding decision module (230) determines whether the robot will board the elevator by comprehensively analyzing the elevator status information obtained through the robot sensor module (220) and the elevator interior sensor module. The elevator interior sensor module is included inside the elevator car and can obtain the elevator's air pressure information, temperature information, interior image information, etc., and the current floor information of the elevator can be obtained based on the air pressure information obtained by the elevator interior sensor module. For example, the air pressure is different for each floor of a multi-story building, and this information exists in the form of a predetermined table. The current floor information determined according to the floor-by-floor air pressure table and the air pressure information obtained by the elevator interior sensor module can be transmitted to the autonomous driving robot (100) through the communication unit (150).

[0074] According to one embodiment, the boarding decision module (230) can determine whether to board by considering the direction of travel of the elevator. This is because it is efficient to board only when the elevator is traveling in the same direction as the robot's destination floor. The direction of travel of the elevator can be determined through an elevator sensor module installed inside the elevator. For example, floor activation information of the elevator can be recognized using a camera installed inside the elevator, or floor activation information can be obtained through a button operation module described later with reference to FIG. 4, and thereby it can be determined whether the elevator is ascending or descending. Alternatively, it can be determined whether the elevator is ascending or descending through a change in air pressure of the elevator obtained through an air pressure sensor installed inside the elevator.

[0075] According to one embodiment, the boarding decision module (230) can determine whether to board by considering the congestion level of the elevator. If the inside of the elevator is excessively crowded, there may be insufficient space for the robot (100) to board or it may obstruct the movement of people. The congestion level of the elevator can be measured through an elevator interior sensor module installed inside the elevator. For example, the congestion level can be estimated by determining the number of people using a camera installed inside the elevator or by measuring the current weight of the elevator using a weight sensor. If the congestion level exceeds a preset threshold, the boarding decision module (230) determines that the robot does not board the elevator.

[0076] According to another embodiment, the boarding decision module (230) may decide whether to board by considering the condition of the robot. If the battery level of the autonomous robot (100) is low or the weight of the delivery items carried by the robot (100) is excessively heavy, the robot may board the elevator even if the level of congestion is high in order to minimize the time waiting for the elevator. Additionally, if the robot (100) is performing an urgent delivery mission, it may board the elevator even if the level of congestion is high in order to reduce the time waiting for the elevator.

[0077] The boarding decision module (230) can decide whether to board by comprehensively considering various factors in addition to the factors described above. For example, it can learn the decision of whether to board in various situations by utilizing machine learning technology and make an optimal judgment.

[0078] According to one embodiment, the boarding decision module (230) can determine whether to board based on the following <Equation 1>.

[0079] <Mathematical Formula 1>

[0080]

[0081] Here is boarding status (1: boarded, 0: not boarded), is the robot's destination layer, is the robot's current layer, is the elevator's direction of movement (1: up, -1: down), is the internal congestion level of the elevator, is the threshold value for the level of congestion inside the elevator.

[0082] In <Mathematical Formula 1>, It is a condition that determines whether the robot's direction of movement matches the elevator's direction of movement. The elevator's direction of movement As described above, it can be determined based on information obtained by the elevator internal sensor module or button operation module. This formula calculates the difference between the robot's destination floor and the current floor; if this value is positive, the robot must move upwards, and if it is negative, the robot must move downwards. That is The condition that... can only be satisfied when the elevator is moving in the same direction as the robot's movement. Elevator internal congestion It can be calculated based on visual information or weight information obtained from a robot sensor module (220) or an elevator interior sensor module. For example, the elevator interior sensor module may include a camera, and the elevator interior congestion level may be calculated based on the number of objects (or people) inside the elevator, the ratio of the object occupancy area, etc. As another example, if the weight of the elevator exceeds a threshold, the congestion level may be calculated as high.

[0083] According to one embodiment, the boarding and disembarking process control module (240) can control the boarding process when the autonomous driving robot (100) decides to board the elevator, control the elevator to move to the destination floor when boarding is completed, and control the disembarking process when the elevator arrives at the destination floor.

[0084] The boarding process may include actions such as keeping the elevator door open, moving into the elevator to complete boarding, and closing the elevator door through a button operation module. When the autonomous robot (100) boards the elevator, the elevator can be controlled to move to the destination floor through a button operation module. Specifically, the boarding / alighting process control module (240) can check whether the button corresponding to the destination floor of the elevator is activated through the button operation module, and if the button corresponding to the destination floor is not activated, it can be controlled to activate it.

[0085] The boarding / alighting process control module (240) can proceed with the alighting process when the elevator arrives at the destination floor. According to one embodiment, the boarding / alighting process control module (240) can check whether the destination floor that was activated by the button operation module is deactivated, or determine whether the elevator has arrived at the destination floor based on a change in air pressure information by the elevator internal sensor module. When it arrives at the destination floor, the boarding / alighting process control module (240) can keep the elevator in an open state through the button operation module, alight from the elevator, and close the elevator door through the button operation module.

[0086] According to one embodiment, the exception handling module (250) can control the operation of the robot (100) in exceptional situations, rather than in a normal inter-floor movement process. For example, the exception handling module (250) can determine whether the robot (100) is currently in an abnormal state and, if it is in an abnormal state, respond based on a Large Language Model (LLM) that has been pre-trained in preparation for the abnormal state. According to one embodiment, the exception handling module (250) can determine that the robot is in an abnormal state if the robot's waiting time exceeds a threshold, if an impact detected through the robot sensor module exceeds a threshold, or if the estimated time of arrival at the destination is delayed by more than a threshold.

[0087] Below, based on the details described above, we will examine the operation flow of the present invention with reference to FIGS. 3 to 7.

[0088]

[0089] FIG. 3 is a drawing for explaining an elevator system (300) in a typical multi-story building.

[0090] Referring to FIG. 3, the elevator system (300) generally consists of an elevator car (320), a hoist (312), a control panel (315), and an elevator boarding area (370). The elevator car (320) is a space for transporting passengers or cargo, and is equipped with a button control unit (330) so that passengers can select a destination floor or call the elevator. The button control unit (330) consists of a floor selection button, a control panel, a door opening / closing button, a manual operation door panel, etc., and may include a light source, a floor selection button, a printed circuit board, etc. inside. The light source provides button lighting, and passengers can select a desired floor through the floor selection button. The printed circuit board serves to transmit signals between the floor selection button and the control panel (315).

[0091] The hoisting machine (312) provides the power to raise and lower the elevator car (320). The hoisting machine consists of an electric motor, a reduction gear, a brake, a rope, etc. The electric motor generates rotational force using electric power, and the reduction gear controls the speed of the elevator car (320) by adjusting this rotational speed. The brake serves to stop the elevator car (320) or to make an emergency stop in case of an emergency, and the rope connects the hoisting machine (312) and the elevator car (320) to move the car up and down.

[0092] The control panel (315) acts as the brain that controls the entire elevator system (300). The control panel (315) receives an elevator call signal, determines the movement path of the elevator car (320), stops the elevator car (320) at the boarding area (370) on each floor, monitors the operating status of the elevator, and activates safety devices in the event of an abnormality. Generally, the control panel is installed together with the hoisting machine (312) in the elevator machine room (310) located on the top floor or in the basement of the building.

[0093] The space where passengers board and alight from the elevator on each floor is the elevator boarding area (370). A call button section (380) is installed in the elevator boarding area (370), and is composed of an upward call button and a downward call button, allowing the elevator to be called in the desired direction.

[0094] Recently, the use of autonomous robots has been increasing in various service fields such as logistics, delivery, guidance, and security. Since movement between floors is essential for robots to perform tasks in multi-story buildings, it is common to use elevators for this purpose. However, when an autonomous robot (100) attempts to use an elevator, direct communication with the elevator machine room (310), particularly the control panel (315), is restricted for security and safety reasons. This is because the elevator control system is operated as a closed system to prevent accidents that may occur due to unauthorized access or manipulation from the outside.

[0095] Therefore, in order for the autonomous robot to freely perform tasks within a multi-story building, a new method is required to call and board an elevator without communication with the control panel (315).

[0096]

[0097] FIG. 4 is a drawing for explaining an elevator call system (400) of an autonomous driving robot according to one embodiment of the present disclosure.

[0098] With reference to FIG. 3, the aforementioned general elevator system (300) is operated by a person directly pressing a button, but the autonomous robot must use the elevator on its own without human intervention. To resolve this difference, a new system (400) is proposed that can call the elevator without communicating directly with the elevator control panel.

[0099] Referring to FIG. 4, the core of the elevator call system (400) of the autonomous robot (100) is an elevator call module (420) and a button operation module (410) through which the autonomous robot (100) communicates. The elevator call module (420) may be installed behind or around a call button section (480) installed in an elevator boarding area (470), and the autonomous robot (100) communicates with the elevator call module (420) through a communication section (150) to call an elevator. The robot transmits a signal to the elevator call module (420) using various wireless communication technologies such as WiFi, Bluetooth, Zigbee, 4G (LTE), and 5G, and this signal is then transmitted to the call button section (480) to call an elevator. During this process, the robot (100) can specify the direction of movement of the elevator (up or down) and determine whether to board the elevator by receiving information such as whether the elevator has arrived and the button operation status in real time from the call button section (480). In the present invention, the elevator call system (400) can call an elevator using either or both of the button operation module (410) or the elevator call module (420), and is not limited to either one.

[0100] An elevator call module (420) may be present at every elevator boarding station.

[0101] For example, if there are multiple boarding areas on a single floor, there may be separate elevator call modules for each boarding area, even if they are on the same floor. The elevator call module may be mounted on the back of the elevator call button section (480) of the boarding area, but is not limited thereto, and depending on the embodiment, there may be only one elevator call module per floor.

[0102] The button operation module (410) may be installed on the rear or around the button operation unit (430) inside the elevator car (320), and the autonomous robot (100) communicates with the button operation module (410) through the communication unit (150) to enable the robot to select a destination floor once it has finished boarding the elevator. Similar to the elevator call module (420), various wireless communication technologies may be used, and the button operation module (410) operates by transmitting a signal sent by the robot to the button operation unit (430) to press the destination floor button. Additionally, the button operation module (410) may receive information inside the elevator car, such as the floor the elevator is currently located on and the direction of movement, and transmit this information to the robot.

[0103] A button operation module (410) may exist for each elevator car (e.g., the elevator car (320) described above with reference to FIG. 3). For example, if there are multiple elevator cars in a multi-story building, a button operation module may exist for each of the multiple cars. The button operation module may be mounted on the rear of the elevator button operation unit (430) inside each elevator car, but is not limited thereto and may be mounted on the top or bottom of the elevator car surface depending on the embodiment.

[0104] For example, the button operation module (410) may include a plurality of button operation communication modules (N-floor button operation communication modules) corresponding to each floor selection button on the rear of the elevator button operation unit (430). The signal receiving unit can receive a signal input to the elevator button operation unit (430) by receiving a signal from each floor selection button. Accordingly, the button operation module (410) can obtain command information through the elevator button operation unit.

[0105] This can be applied likewise to elevator call modules.

[0106] In addition, it is also possible to transmit an appropriate call command to the elevator button control unit (430) or call button unit (480) inside the car using a signal button control communication module included in the button control module (410) or elevator call module (420).

[0107] The autonomous driving robot (100) will be able to control the elevator without the intervention of the elevator machine room (310) by transmitting and receiving call or control commands for the elevator car through the processor of the button operation module (410) or the elevator call module (420).

[0108] The autonomous driving robot (100) can efficiently call an elevator using these two modules (410, 420). When calling an elevator, the direction of movement of the elevator is determined based on the current location and destination floor information, and the elevator can be called through the elevator call module (420). After boarding the elevator, the robot can press the destination floor button through the button operation module (410) and plan its own movement path while continuously checking the operation status of the elevator.

[0109] According to the proposed elevator call system (400) of the autonomous robot (100), security and safety issues can be resolved because the robot does not need to communicate directly with the elevator control panel (e.g., the control panel (315) described above with reference to FIG. 3). In addition, it is designed to be compatible with various types of elevator systems, allowing the robot to use the elevator in various environments. Furthermore, the elevator can be used efficiently by minimizing waiting time by identifying the elevator's status information in real time and deciding whether to board by considering the internal congestion of the elevator. That is, the proposed elevator call control system (400) of the autonomous robot enables the autonomous robot to use the elevator without changing the existing elevator system and supports the robot in using the elevator safely and efficiently. This can greatly contribute to increasing the usability of the autonomous robot in multi-story buildings and expanding the scope of robot services.

[0110]

[0111] FIG. 5 is a flowchart illustrating a method of moving between floors via an elevator in a multi-story building by an autonomous driving robot according to one embodiment of the present disclosure.

[0112] The method of moving between floors via an elevator in a multi-story building illustrated in FIGS. 5 to 7 can be performed by an autonomous driving robot (100) equipped with the function of moving between floors via an elevator in a multi-story building as described above. Therefore, even if the details are omitted below, the details described above regarding the autonomous driving robot (100) can be applied equally to the description of the elevator calling method described below.

[0113] Referring to FIG. 5, the method of moving between floors via an elevator may include, as the path from the current position of the robot (100) to the destination is determined, an operation (510) of calling the elevator to the robot material floor corresponding to the current position of the robot (100) through a button operation module included in the elevator and moving to the boarding area of ​​the robot material floor, an operation (520) of determining whether to board, an operation (530) of executing a boarding process if it is decided to board, an operation (540) of controlling the elevator to move to the destination floor corresponding to the destination after boarding, and an operation (550) of executing a disembarking process when arriving at the destination floor.

[0114] Step 510 is a step of calling an elevator and moving to the boarding area at the same time. According to one embodiment, Step 510 may be performed by the movement path determination module (210) described above with reference to FIG. 2. The detailed description described above with reference to FIG. 2 may be omitted for brevity.

[0115] Step 520 is a step for determining whether to board. According to one embodiment, Step 520 may be performed by the robot sensor module (220) and the boarding determination module (230) described above with reference to FIG. 2. The specific description described above with reference to FIG. 2 may be omitted for brevity. According to one embodiment, the autonomous driving robot (100) can detect whether the elevator has arrived and the door is open through the robot sensor module (220). When the door is open, the boarding determination module (230) can determine whether to board. The specific operation for determining whether to board will be described in detail later with reference to FIG. 6.

[0116] Steps 530 to 550 are steps of moving to the destination floor via elevator after boarding and proceeding with disembarking. According to one embodiment, steps 530 to 550 may be performed by the boarding / disembarking process control module (240) described above with reference to FIG. 2 and the button operation module (410) described above with reference to FIG. 4.

[0117] According to one embodiment, if it is decided to board at step 520, the elevator can be kept open via the button operation module (410) at step 530, and the elevator can be moved inside via the boarding / alighting process control module (240) to board, and when boarding is complete, the elevator door can be closed via the button operation module (410).

[0118] According to one embodiment, in step 540, the boarding / alighting process control module (240) can control the floor button activation information through the button operation module (410) to control the elevator to move to the destination floor.

[0119] According to one embodiment, in step 550, the boarding / alighting process control module (240) can execute the alighting process when it arrives at the destination floor. As described above with reference to FIG. 2, the autonomous driving robot (100) can determine whether the elevator has arrived at the destination floor based on atmospheric pressure information obtained through the elevator internal sensor module. Alternatively, it can determine whether the elevator has arrived at the destination floor based on floor information displayed inside the elevator through the robot sensor module (220).

[0120] In the description above, steps 510 and 550 may be further subdivided into additional steps or combined into fewer steps, depending on the embodiment of the present invention. Additionally, some steps may be omitted as necessary, and the order between steps may be changed.

[0121]

[0122] FIG. 6 is a flowchart illustrating a method for determining whether an autonomous driving robot rides an elevator according to one embodiment of the present disclosure.

[0123] Referring to FIG. 6, the method for determining whether to board an elevator may include an operation (610) of determining whether the elevator is moving toward a destination floor based on floor button activation information obtained through an elevator button operation module (410), an operation (640) of determining whether the internal congestion level of the elevator is below a threshold, and an operation (670) of deciding to board if the elevator is moving toward a destination floor and the congestion level is below the threshold.

[0124] According to one embodiment, in step 610, it can be determined whether the elevator is moving toward the destination floor based on the elevator floor button activation information obtained through the button operation module (410) described above with reference to FIG. 4. As described in <Equation 1> described above with reference to FIG. 2, the boarding determination module (230) can determine whether the elevator is moving toward the destination floor using the robot's destination floor information, the robot's current floor information, and the elevator's movement direction information.

[0125] According to one embodiment, in step 640, it can be determined whether the level of congestion inside the elevator is below a threshold based on visual information and weight information obtained through the elevator internal sensor module or the robot sensor module (220). Specifically, in step 640, it can be determined whether there is space for the autonomous robot (100) to board inside the elevator based on visual information, and whether the elevator can support the total weight of the robot (the sum of the robot's weight and the weight of the items the robot carries) based on elevator weight information detected by the elevator internal sensor module.

[0126] According to one embodiment, in step 670, the elevator is moving toward the destination floor, and a decision can be made whether to board by determining whether the internal congestion level of the elevator is below a threshold. If the elevator is moving toward the destination floor and the congestion level is below the threshold, a decision is made to board, and the boarding process can proceed in step 530. If either of the two conditions is not met, the user may wait until both conditions are met. If multiple elevators can arrive at the boarding area, the direction of movement and congestion level can be calculated for the other elevators.

[0127] In the description above, steps 610, 640, and 670 may be further subdivided into additional steps or combined into fewer steps, depending on an embodiment of the present invention. Additionally, some steps may be omitted as necessary, and the order of the steps may be changed.

[0128]

[0129] FIG. 7 is a flowchart illustrating the operation in an exceptional situation of the boarding and disembarking process of an autonomous driving robot according to one embodiment of the present disclosure.

[0130] Referring to FIG. 7, the operation in an exception situation of the robot boarding / alighting process may include an operation (710) of determining whether the robot waiting time exceeds a threshold, whether an impact detected through the robot sensor module exceeds a threshold, or whether the estimated time of arrival at the destination is delayed by more than a threshold, and a corresponding operation (740) based on a large-scale language model pre-trained in preparation for an abnormal state when any of the aforementioned conditions apply. According to one embodiment, steps 710 and 740 may be performed by the exception handling module (250) described above with reference to FIG. 2. The specific description described above with reference to FIG. 2 may be omitted for brevity.

[0131] Referring to Fig. 7, an exception situation regarding the boarding process situation of step 530 is described as an example, but the same can be applied to an exception situation regarding the disembarking process situation of step 550.

[0132] When boarding is determined in step 520, in step 710, the exception handling module (250) can determine whether the robot (100) is currently in an abnormal state. According to one embodiment, the exception handling module (250) can determine that the robot is in an abnormal state if the robot's waiting time exceeds a threshold, if an impact detected through the robot sensor module exceeds a threshold, or if the estimated time of arrival at the destination is delayed by more than a threshold. For example, the estimated time of arrival may be delayed by more than a threshold if the elevator door does not close, if people obstruct the robot, or if internal elevator communication is not smooth.

[0133] According to one embodiment, the exception handling module (250) can respond based on a large language model that has been pre-trained in preparation for an abnormal state, rather than the existing process in step 740. The large language model (LLM) that has been pre-trained in preparation for an abnormal state supports the autonomous driving robot in effectively responding when it encounters an abnormal state. The LLM is an artificial intelligence model that has the ability to understand and generate human language by learning a vast amount of text data.

[0134] LLM can be a model that learns information about various abnormal conditions that may occur during the boarding and alighting process of an autonomous robot. For example, it may be a model that learns text data regarding various situations, such as when the waiting time exceeds a threshold while waiting for an elevator, when the robot detects a sudden impact inside the elevator, or when the estimated arrival time at the destination is delayed due to an elevator malfunction or congestion. Additionally, LLM can be a model that also learns information on appropriate response methods for each abnormal condition. For example, it may have learned response methods such as outputting a voice message like "The elevator is taking too long" when the waiting time exceeds a threshold, outputting a voice message like "There was a thud. Are you okay?" when a sudden impact is detected, or outputting a voice message like "The estimated arrival time is delayed. Please wait a moment" when the estimated arrival time is delayed.

[0135] The LLM can determine the current situation by analyzing information collected from the sensor module of the autonomous driving robot and information received from the elevator control system, and determine an appropriate response method based on this. For example, if the elevator waiting time exceeds a threshold and information on the elevator's operating status is received from the button operation module (410), the LLM determines that the elevator waiting time delay is abnormal and can select and execute one of the learned response methods. The LLM can select the optimal response method by comprehensively considering the robot's status, the elevator's status, the surrounding environment, etc.

[0136] LLM can provide various functions to enable autonomous robots to flexibly respond to abnormal conditions. For example, LLM can respond to people's voice commands or questions based on natural language understanding capabilities. For instance, if a person asks a robot, "Why is it taking so long?", LLM can use elevator operation information to respond, "We apologize, the elevator is delayed." As another example, LLM can communicate with people in various languages ​​through multilingual support features. This can contribute to increasing the robot's utility in multilingual environments. As yet another example, LLM can generate and output context-appropriate voice messages based on text generation capabilities. For instance, when a robot detects a sudden impact in an elevator, it can output a voice message such as, "There was a loud thud just now; are you okay?" to inform people nearby of the situation and reassure them.

[0137] In the description above, steps 710 and 740 may be further subdivided into additional steps or combined into fewer steps, depending on the embodiment of the present invention. Additionally, some steps may be omitted as necessary, and the order between steps may be changed.

[0138]

[0139] According to one embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

[0140] A data structure can refer to the organization, management, and storage of data that enables efficient access and modification of data. A data structure can refer to the organization of data for solving specific problems (e.g., data retrieval, data storage, data modification in the shortest possible time). A data structure may also be defined by physical or logical relationships between data elements designed to support specific data processing functions. Logical relationships between data elements may include connections between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements physically stored on a computer-readable storage medium (e.g., a permanent storage device). Specifically, a data structure may include sets of data, relationships between data, and functions or instructions applicable to the data. Through an effectively designed data structure, the target plastic sorter can perform operations while minimizing the use of its resources. Specifically, the target plastic sorter can improve the efficiency of operations, reading, insertion, deletion, comparison, exchange, and retrieval through an effectively designed data structure.

[0141] Data structures can be classified into linear and non-linear data structures based on their form. A linear data structure is one where only one piece of data is connected to the next. Linear data structures can include lists, stacks, queues, and deques. A list can refer to a set of data that maintains an internal order. Lists can include linked lists. A linked list is a data structure where data is connected in a line, with each piece of data possessing a pointer. In a linked list, the pointer can contain information regarding the connection to the next or previous data. Depending on its form, a linked list can be represented as a singly linked list, a doubly linked list, or a circular linked list. A stack is a data arrangement structure that allows for restricted access to data. A stack can be a linear data structure where data can be processed (e.g., insertion or deletion) only at one end. Data stored in a stack can be a Last-In, First-Out (LIFO) data structure, meaning that the later an item is entered, the sooner it is retrieved. A queue is a data sequence structure that allows for limited access to data; unlike a stack, it can be a FIFO (First in First Out) data structure where data stored later is retrieved later. A deque is a data structure that can process data at both ends.

[0142] Non-linear data structures can be structures where multiple data are connected after a single piece of data. Non-linear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge may include a line connecting two different vertices. Graph data structures may include tree data structures. A tree data structure may be a data structure where there is only one path connecting two different vertices among the multiple vertices included in the tree. In other words, it may be a data structure that does not form a loop in a graph data structure.

[0143] Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Hereinafter, the term neural network will be used consistently. A data structure may include a neural network. Furthermore, a data structure including a neural network may be stored on a computer-readable medium. A data structure including a neural network may also include data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, loss functions for learning the neural network, etc. A data structure including a neural network may include any of the components disclosed above. That is, a data structure including a neural network may be configured to include all or any combination thereof, such as data preprocessed for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data obtained from the neural network, activation functions associated with each node or layer of the neural network, and loss functions for learning the neural network. In addition to the configurations described above, a data structure including a neural network may include any other information that determines the characteristics of the neural network. Furthermore, the data structure may include any form of data used or generated during the computational process of the neural network, and is not limited to the foregoing. A computer-readable medium may include a computer-readable recording medium and / or a computer-readable transmission medium. A neural network may be composed of a set of interconnected computational units that may generally be referred to as nodes. These nodes may also be referred to as neurons. A neural network is composed of at least one node.

[0144] A data structure may include data input to a neural network. A data structure including data input to a neural network may be stored on a computer-readable medium. Data input to a neural network may include training data input during the neural network learning process and / or input data input to a neural network after training is complete. Data input to a neural network may include pre-processed data and / or data subject to pre-processing. Pre-processing may include a data processing process for inputting data into a neural network. Accordingly, a data structure may include data subject to pre-processing and data generated by pre-processing. The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0145] The data structure may include weights of the neural network. (In this specification, weights and parameters may be used interchangeably.) The data structure including the weights of the neural network may be stored on a computer-readable medium. The neural network may include multiple weights. The weights may be variable and may be varied by a user or an algorithm to enable the neural network to perform a desired function. For example, if one or more input nodes are interconnected to a single output node by respective links, the output node may determine the data value output from the output node based on values ​​input to the input nodes connected to the output node and weights set on the links corresponding to each input node. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0146] As an example rather than a limitation, weights may include weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Weights that vary during the neural network learning process may include weights at the start of the learning cycle and / or weights that vary during the learning cycle. Weights for which neural network learning is completed may include weights for which the learning cycle is completed. Accordingly, a data structure containing the weights of a neural network may include a data structure containing weights that vary during the neural network learning process and / or weights for which neural network learning is completed. Therefore, the weights and / or combinations of each weight described above are included in the data structure containing the weights of a neural network. The aforementioned data structure is merely an example and the present disclosure is not limited thereto.

[0147] Data structures containing the weights of a neural network may be stored on a computer-readable storage medium (e.g., memory, hard disk) after undergoing a serialization process. Serialization may be a process of converting a data structure into a form that can be stored on the same or different computing devices and later reconstructed for use. A computing device may serialize the data structure to transmit and receive data over a network. A serialized data structure containing the weights of a neural network may be reconstructed on the same or different computing devices through deserialization. Data structures containing the weights of a neural network are not limited to serialization. Furthermore, data structures containing the weights of a neural network may include data structures designed to increase computational efficiency while minimizing the use of computing device resources (e.g., B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree in non-linear data structures). The foregoing is merely an example and the present disclosure is not limited thereto.

[0148] The data structure may include hyperparameters of the neural network. The data structure including the neural network hyperparameters may be stored on a computer-readable medium. The hyperparameters may be variables that are varied by the user. The hyperparameters may include, for example, a learning rate, a cost function, the number of learning cycle iterations, weight initialization (e.g., setting the range of weight values ​​subject to weight initialization), and the number of hidden units (e.g., the number of hidden layers, the number of nodes in the hidden layers). The aforementioned data structure is merely an example, and the present disclosure is not limited thereto.

[0149]

[0150] The present invention described above can be implemented as computer-readable code on a medium on which a program is recorded. A machine-readable recording medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of machine-readable media include HDD (Hard Disk Drive), SSD (Solid State Disk), SSD (Silicon Disk Drive), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

[0151] In one embodiment, the recording medium may be a memory. In one embodiment, the recording medium may be implemented in a distributed form in a networked computer system, etc. Software may be stored and executed in a distributed manner in a computer system, etc. The recording medium may be a non-transitory recording medium. A non-transitory recording medium may refer to a tangible medium that exists regardless of whether data is stored semi-permanently or temporarily.

[0152]

[0153] This invention is a technology developed through the Seoul Metropolitan Government Seoul Economic Promotion Agency (2024 Robot Technology Commercialization Support Project) (SP240008) (Development of an Always-on & All-in-one Robot Platform to Maximize Service Experience and Establishment of a Smart Robot Zone in an Electronics Shopping Mall to Provide Life Convenience Services).

Claims

1. In an autonomous robot equipped with a function for moving between floors within a multi-story building via an elevator, A communication unit that communicates with either a button operation module or an elevator internal sensor module installed in each of the elevators of the above-mentioned multi-story building; A robot sensor module for detecting the position and surrounding environment of the above-mentioned robot; At least one processor; and Memory; Includes, The above-mentioned at least one processor is, As the path from the current location of the robot to the destination is set, the elevator is called to the robot material floor corresponding to the current location through a button operation module included in the elevator, and moves to the boarding area of ​​the robot material floor, and When the opening of the elevator door is detected through the robot sensor module, a decision is made regarding whether to board the elevator, and When boarding is determined, the boarding process to the above elevator is executed, and After boarding, the elevator is controlled to move to the destination floor corresponding to the destination through the button operation module of the elevator, and Upon arrival at the aforementioned destination floor, execute the disembarkation process. configured to do so, Autonomous driving robot.

2. In Paragraph 1, The above-mentioned at least one processor is, Based on floor button activation information obtained through the button operation module of the above elevator, it is determined whether the elevator is moving in the direction of the destination floor, and Determining whether the internal congestion level of the above elevator is below a threshold, and Configured to decide to board the elevator when the elevator is moving toward the destination floor and the congestion level is below the threshold. Autonomous driving robot.

3. In Paragraph 2, The above-mentioned at least one processor is, Configured to calculate the congestion level based on visual information and weight information obtained based on the robot sensor module or the elevator interior sensor module, Autonomous driving robot.

4. In Paragraph 1, The above-mentioned at least one processor is, The above button operation module maintains the elevator in an open state, and Move inside the aforementioned elevator and board, and Configured to perform the operation of closing the elevator door through the button operation module when boarding is completed, Autonomous driving robot.

5. In Paragraph 1, The above-mentioned at least one processor is, Determining whether the button corresponding to the destination floor of the elevator is activated through the button operation module, and If the button corresponding to the above destination floor is not activated, it is configured to be activated. Autonomous driving robot.

6. In Paragraph 1, The above-mentioned at least one processor is, Determining whether the destination floor has been reached through the button operation module, the robot sensor module, or the elevator interior sensor module, and When arriving at the above destination floor, the elevator is kept open through the above button operation module, and Get off the above elevator, and Configured to perform the operation of closing the elevator door via the button operation module when disembarking is completed, Autonomous driving robot.

7. In Paragraph 1, The above-mentioned at least one processor is, If the waiting time of the above robot exceeds a threshold, if the impact detected through the robot sensor module exceeds a threshold, or if the estimated time of arrival at the destination is delayed by more than a threshold, Configured to respond based on a pre-trained Large Language Model (LLM) to prepare for abnormal conditions, Autonomous driving robot.

8. In Paragraph 1, The above-mentioned at least one processor is, Output a visual, auditory, or physical signal that can notify the surroundings that the robot is boarding or alighting during the execution of the above boarding process or the above alighting process. further configured to do, Autonomous driving robot.

9. A method of moving between floors within a multi-story building via an elevator, performed by an autonomous robot, As a path from the current location of the robot to the destination is set, an operation to call the elevator to the robot material floor corresponding to the current location through a button operation module included in the elevator and move to the boarding area of ​​the robot material floor; An operation to determine whether to board the elevator when the opening of the elevator door is detected through a robot sensor module that detects the position and surrounding environment of the robot; An action to execute the boarding process to the above elevator when boarding is determined; An operation to control the elevator to move to a destination floor corresponding to the destination through a button operation module of the elevator after boarding; and Action to execute the disembarkation process upon arrival at the aforementioned destination floor including, Method of moving between floors.

10. In Paragraph 9, The operation of determining whether to ride, as described above, is An operation to determine whether the elevator is moving in the direction of the destination floor based on floor button activation information obtained through the button operation module of the elevator; An operation to determine whether the internal congestion level of the above elevator is below a threshold; and An action of deciding to board the elevator when the elevator is moving toward the destination floor and the congestion level is below the threshold. including, Method of moving between floors.

11. In Paragraph 10, The operation of determining whether the above congestion level is below a threshold is, Operation of calculating the congestion level based on visual information and weight information obtained based on the robot sensor module or the elevator interior sensor module. including, Method of moving between floors.

12. In Paragraph 9, The operation of executing the above-mentioned boarding process is, Operation of maintaining the elevator in an open state through the above button operation module; The action of moving into the elevator and boarding; and The operation of closing the elevator door via the button operation module when boarding is complete. including, Method of moving between floors.

13. In Paragraph 9, The operation of controlling the above elevator to move to the destination floor corresponding to the above destination is, An operation to determine whether a button corresponding to the destination floor of the elevator is activated through the button operation module; and If the button corresponding to the above destination floor is not activated, the action of activating it; including Method of moving between floors.

14. In Paragraph 9, The action of executing the disembarkation process upon arrival at the aforementioned destination floor is, An operation to determine whether the destination floor has been reached through the button operation module, the robot sensor module, or the elevator interior sensor module; When arriving at the above destination floor, the operation of maintaining the elevator in an open state through the above button operation module; The action of disembarking from the above elevator; and The operation of closing the elevator door via the button operation module when disembarking is complete. including, Method of moving between floors.

15. In Paragraph 9, The action of executing the above boarding process or the above disembarking process is, If the waiting time of the above robot exceeds a threshold, if the impact detected through the robot sensor module exceeds a threshold, or if the estimated time of arrival at the destination is delayed by more than a threshold, Response actions based on a pre-trained Large Language Model (LLM) in preparation for abnormal states; including, Method of moving between floors.

16. In Paragraph 9, The action of executing the above boarding process or the above disembarking process is, Operation of outputting a visual, auditory, or physical signal that can notify the surroundings that the robot is boarding or alighting during the execution of the above boarding process or the above alighting process. including more, Method of moving between floors.

17. In a system for inter-floor movement of an autonomous robot in a multi-story building via an elevator, A button operation module included in each of the elevators of the multi-story building and collecting activation information for each of the internal buttons of the elevator; and An elevator internal sensor module installed in each elevator of the above-mentioned multi-story building; An autonomous driving robot that communicates with the above-mentioned button operation module and the above-mentioned elevator interior sensor module and is equipped with a function for moving between floors within a multi-story building via an elevator. Includes, The robot is configured such that, as a path from the robot's current location to a destination is set, it calls the elevator to the robot material floor corresponding to the current location via the button operation module, determines whether to board the elevator when the opening of the elevator door is detected via the robot sensor module that detects the robot's location and surrounding environment, executes a boarding process for the elevator if boarding is determined, controls the elevator to move to the destination floor corresponding to the destination via the button operation module after boarding, and executes a disembarking process upon arrival at the destination floor. Inter-floor movement system of autonomous robots in a multi-story building via an elevator.

Images