Method for disassembling battery components by using robot, computing device in which same method is implemented, and system including computing device

Abstract

According to an embodiment of the present disclosure, provided is an operating method of a robot system for controlling an operation of at least one robot device implemented to perform at least one task on the basis of a control signal, and the operating method comprises the steps, performed by at least one processor included in the robot system, of: receiving a control signal for instructing disassembly of a first component of a battery; obtaining sensing data associated with the battery from at least one sensor; controlling a first end effector that has reached a first position to perform a first task of disassembling a first fastening member from the battery; setting a second target position on the basis of the sensing data and determining a second trajectory for a second end effector to reach a second position corresponding to the second target position; and controlling the second end effector that has reached the second position to perform a second task of separating the first component.

Description

A method for disassembling battery components using a robot, a computing device implementing such a method, and a system including the computing device

[0001] The present disclosure relates to a battery handling system. More specifically, it relates to a system for transporting, storing, preprocessing, and dismantling batteries.

[0002] Recently, global concern for the environment has surged, leading to the widespread adoption of electric vehicles. Consequently, demand for batteries used in electric vehicles has skyrocketed. Meanwhile, car batteries require replacement every three to four years on average, leading to an exponential increase in the amount of discarded batteries.

[0003] Accordingly, demand is growing for dismantling technology that safely collects and dismantles used batteries from electric vehicles. Furthermore, to safely dismantle batteries, it is crucial to accurately diagnose their condition and discharge any remaining current within them.

[0004] Currently, the disassembly of various battery components is performed manually. This is because battery disassembly requires a significant level of expertise and precision.

[0005] The present disclosure provides a battery processing system.

[0006] The present disclosure can provide a battery storage method according to battery information.

[0007] The present disclosure may provide a method and system for automatically processing a battery using a robotic device.

[0008] The present disclosure can provide a method for determining a battery processing process based on battery information.

[0009] The present disclosure can provide a learning method of an artificial intelligence engine for controlling a robot device and a robot control method using the learned artificial intelligence engine.

[0010] Meanwhile, the problems to be solved in the present disclosure are not limited to the problems described above, and problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the invention included in the present disclosure belongs from this specification and the attached drawings.

[0011] According to one embodiment of the present disclosure, there is provided an operating method of a robot system that controls the operation of at least one robot device, the operating method including: controlling the robot device to grip at least one connector included in the at least one processing device using an end effector by at least one processor included in the robot system that communicates with at least one processing device; acquiring sensing data related to the battery from at least one sensor; setting a position corresponding to at least one port connected to the battery as a target position based on the sensing data; determining a first trajectory for the end effector to reach a first position corresponding to the target position; and determining a second trajectory for connecting the at least one connector gripped by the end effector that has reached the first position to the at least one port.

[0012] In addition, according to one embodiment of the present disclosure, there is provided an operating method of a robot system for controlling the operation of at least one robot device implemented to perform at least one task based on a control signal, the method comprising: receiving, by at least one processor included in the robot system, a control signal instructing to disassemble a first component of a battery; acquiring sensing data related to the battery from at least one sensor; identifying a position of a first fastening member for fixing the first component based on the sensing data and setting the position as a first target position; determining a first trajectory for a first end effector to reach a first position corresponding to the first target position; controlling the first end effector, which has reached the first position, to perform a first task of disassembling the first fastening member from the battery; setting a second target position based on the sensing data and determining a second trajectory for a second end effector to reach a second position corresponding to the second target position; controlling the second end effector, which has reached the second position, to perform a second task of detaching the first component. A method of operation including a controlling action may be provided.

[0013] In addition, according to one embodiment of the present disclosure, a robot system may be provided, comprising at least one power unit, a first robot device, a second robot device, a first end effector, at least one sensor, an artificial intelligence model, and at least one processor, wherein the at least one processor is configured to input input data acquired based on sensing data acquired from the at least one sensor into the artificial intelligence model, acquire at least one control value for the at least one power unit based on output data acquired from at least one output layer of the artificial intelligence model, and determine a first trajectory for moving the first end effector connected to the first robot device to a target position based on the at least one control value, wherein the first trajectory is determined by acquiring at least one dynamic parameter corresponding to each of a plurality of points for moving to the target position based on the at least one control value, and the target position and the at least one dynamic parameter are determined in consideration of control of the second robot device.

[0014] In addition, according to one embodiment of the present disclosure, there is provided an operating method of a robot system for controlling the operation of at least one robot device implemented to perform at least one task based on a control signal, the method comprising: receiving, by at least one processor included in the robot system, a control signal instructing disassembling a first component of a battery; acquiring sensing data related to the battery from at least one sensor; identifying a predetermined point on the battery based on the sensing data; estimating a pose of the battery based on a positional relationship between the identified predetermined point and the at least one robot device; adjusting a position of at least one robot device or the battery so that the positional relationship between the predetermined point and the at least one robot device satisfies a predetermined criterion; identifying a position of at least one of a plurality of fastening members for fixing the first component based on the sensing data; An operation of determining a disassembly order for the plurality of fastening members, identifying a position of a first fastening member among the plurality of fastening members, and setting the position as a first target position, wherein if the first target position is not located within a work area of ​​the at least one robot device, the position of the battery is adjusted so that the first target position is located within the work area; An operation of determining a first trajectory for a first end effector to reach a first position corresponding to the first target position; An operation of controlling the first end effector, having reached the first position, to perform a first task of disassembling the first fastening member from the battery; An operation of setting a second target position based on the sensing data, and determining a second trajectory for a second end effector to reach a second position corresponding to the second target position;An operating method may be provided, including: an operation of controlling the second end effector, which has reached the second position, to perform a second task of separating the first part;

[0015] The solutions to the problems of the present invention are not limited to the solutions described above, and solutions not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the attached drawings.

[0016] According to the present disclosure, a battery processing system can be provided that provides an appropriate storage method based on battery information.

[0017] According to the present disclosure, a method for efficiently processing a battery using a robotic device can be provided.

[0018] The effects of the present invention are not limited to the effects described above, and effects not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the attached drawings.

[0019] FIG. 1 is a drawing illustrating an implementation example of a battery processing automation system (1) according to various embodiments.

[0020] FIG. 2 is a diagram illustrating systems for implementing a battery processing automation system (1) according to various embodiments.

[0021] FIG. 3 is a drawing for explaining a detailed configuration of an automation system based on a robot system according to various embodiments.

[0022] FIG. 4 is a diagram illustrating a configuration of a battery transport and storage system according to various embodiments.

[0023] FIG. 5 is a diagram illustrating a configuration of a battery preprocessing system according to various embodiments.

[0024] FIG. 6 is a diagram illustrating one embodiment of a method of operating a robot system for controlling the operation of a robot device according to various embodiments.

[0025] FIG. 7 is a diagram illustrating a method for a processor to control a robotic device based on an artificial intelligence engine according to various embodiments.

[0026] FIGS. 8 to 10 are diagrams illustrating a method for a battery handling system to control a robotic device to connect and disconnect a battery with a battery diagnostic device, according to various embodiments.

[0027] FIG. 11 is a diagram illustrating a method for storing batteries according to battery diagnostic grades by a battery handling system according to various embodiments.

[0028] FIG. 12 is a diagram illustrating a method for a battery handling system to control a robotic device to connect a battery discharge device and a battery, according to various embodiments.

[0029] FIG. 13 is a diagram illustrating a configuration of a battery disassembly system according to various embodiments.

[0030] FIGS. 14 and 15 are diagrams illustrating an operation method of a robot system for disassembling a battery pack according to various embodiments.

[0031] FIG. 16 is a drawing illustrating an operation method of a robot system for dismantling an upper cover of a battery pack according to various embodiments.

[0032] FIG. 17 is a diagram illustrating an operation method of a robot system for disassembling a module of a battery pack according to various embodiments.

[0033] FIG. 18 is a diagram illustrating an operation method of a robot system for disassembling cells of a battery pack according to various embodiments.

[0034] FIG. 19 is a diagram illustrating a method for storing components dismantled from a battery pack by a battery handling system according to various embodiments.

[0035] FIG. 20 is a flowchart illustrating a method for a battery processing system to dismantle a plurality of fastening members according to various embodiments.

[0036] FIG. 21 is a diagram illustrating a method for a battery handling system to disassemble a plurality of fastening members according to various embodiments.

[0037] FIG. 22 is a flowchart illustrating a method for a robotic system to perform a task using a robotic device according to various embodiments.

[0038] FIG. 23 is a diagram illustrating a method for a robot system to estimate and correct the attitude of a battery based on sensing data, according to various embodiments.

[0039] FIG. 24 is a diagram illustrating a method for a battery processing system to control a plurality of robotic devices using an artificial intelligence engine, according to various embodiments.

[0040] FIG. 25 is a flowchart illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0041] FIG. 26 is a flowchart illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0042] FIG. 27 is a diagram illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0043] FIG. 28 is a drawing illustrating an example of a working chamber implemented in a battery processing system according to various embodiments.

[0044] FIG. 29 is a drawing illustrating the internal configuration of a working chamber implemented in a battery processing system according to various embodiments.

[0045] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the embodiments, descriptions of technical details that are well-known in the technical field to which the present disclosure pertains and are not directly related to the present disclosure will be omitted. This is to avoid obscuring the gist of the present disclosure by omitting unnecessary explanations and to convey the gist more clearly.

[0046] Since the embodiments described in this specification are intended to clearly explain the idea of ​​the present invention to a person having ordinary skill in the art to which the present invention pertains, the present invention is not limited to the embodiments described in this specification, and the scope of the present invention should be interpreted to include modified or altered examples that do not depart from the idea of ​​the present invention.

[0047] The terms used in this specification have been selected from widely used terms, taking into account the functions of the present invention. However, these terms may vary depending on the intentions of those skilled in the art, precedents, or the emergence of new technologies. However, if a specific term is defined and used with an arbitrary meaning, the meaning of that term will be described separately. Therefore, the terms used in this specification should be interpreted based on the actual meaning of the term and the overall content of this specification, rather than simply the name of the term.

[0048] The drawings attached to this specification are intended to facilitate explanation of the present invention, and the shapes depicted in the drawings may be exaggerated as necessary to help understanding of the present invention, and therefore the present invention is not limited by the drawings.

[0049] If a detailed description of the composition or function of a known disclosure related to the present invention in this specification is deemed to obscure the gist of the present invention, a detailed description thereof will be omitted as necessary. Furthermore, the numbers (e.g., "first," "second," etc.) used throughout the description of this specification are merely identifiers used to distinguish one component from another.

[0050] In addition, the suffixes "part" and "part" for components used in the following description are given or used interchangeably only for the convenience of writing the specification, and do not have distinct meanings or roles in themselves.

[0051] That is, the embodiments of the present disclosure are provided to make the present disclosure complete and to inform those skilled in the art of the scope of the present disclosure, and the invention of the present disclosure is defined solely by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

[0052] Terms such as “first” and / or “second” may be used to describe various components, but the components should not be limited by the terms. The terms are only for the purpose of distinguishing one component from another, for example, a first component may be referred to as a second component, and similarly, a second component may also be referred to as a first component, without departing from the scope of the present disclosure.

[0053] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0054] Each block of the flowchart drawings and combinations of flowchart drawings in the drawings can be performed by computer program instructions. These computer program instructions can be installed in a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, so that the instructions executed by the processor of the computer or other programmable data processing equipment create a means for performing the functions described in the flowchart block(s). These computer program instructions can also be stored in a computer-available or computer-readable memory that can direct a computer or other programmable data processing equipment to implement the functions in a specific manner, so that the instructions stored in the computer-available or computer-readable memory can also produce an article of manufacture that includes an instruction means for performing the functions described in the flowchart block(s). Since the computer program instructions may be installed on a computer or other programmable data processing device, a series of operational steps may be performed on the computer or other programmable data processing device to create a computer-executable process, so that the instructions that cause the computer or other programmable data processing device to perform the steps for performing the functions described in the flowchart block(s) may also be able to provide steps for performing the functions described in the flowchart block(s).

[0055] Additionally, each block may represent a module, segment, or portion of code that contains one or more executable instructions for performing a specific logical function(s). It should also be noted that in some alternative implementation examples, the functions described in the blocks may occur out of order. For example, two blocks depicted in succession may actually be executed substantially concurrently, or the blocks may sometimes be executed in reverse order, depending on their respective functions.

[0056] The term 'unit' as used in this disclosure means a software or hardware component such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC). The 'unit' performs specific roles, but is not limited to software or hardware. The 'unit' may be configured to reside on an addressable storage medium and may be configured to play one or more processors. Accordingly, according to some embodiments, the 'unit' includes components such as software components, object-oriented software components, class components, and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The functionality provided within the components and 'units' may be combined into a smaller number of components and 'units' or further separated into additional components and 'units'. Additionally, the components and '~parts' may be implemented to activate one or more CPUs within a device or secure multimedia card. Furthermore, according to various embodiments of the present disclosure, the '~part' may include one or more processors.

[0057] The operating principles of the present disclosure are described in detail below with reference to the attached drawings. In the following description of the present disclosure, detailed descriptions of related known functions or configurations will be omitted if they are deemed to unnecessarily obscure the gist of the present disclosure. Furthermore, the terms described below are defined based on the functions of the present disclosure and may vary depending on the intent or custom of the user or operator. Therefore, their definitions should be based on the overall content of this specification.

[0058]

[0059] FIG. 1 is a drawing illustrating an example of an implementation of an automated battery processing system (1) according to various embodiments. FIG. 1 (a) is a drawing illustrating an example of an implementation of an automated battery processing system (1) in a top view. FIG. 1 (b) is a drawing illustrating an example of an implementation of an automated battery processing system (1) in a panoramic view.

[0060] FIG. 2 is a diagram illustrating systems for implementing a battery processing automation system (1) according to various embodiments.

[0061] Referring to FIGS. 1 and 2, the battery processing automation system (1) may include multiple automated systems for (physically or chemically) processing a battery. In this case, the battery is composed of one or more modules. One module is composed of multiple cells. A waste battery pack may include, but is not limited to, a top cover, bolts (fastening members), modules, cells, and cooling plates. In the present disclosure, the battery may be expressed as a battery pack, an ESS (Energy Storage System), or a waste battery.

[0062] Specifically, referring to FIG. 1, the battery processing automation system (1) may include a plurality of automated facilities for battery processing. Specifically, the system (1) may include, but is not limited to, a battery transport facility (11), a battery storage facility (12), a battery preprocessing facility (13), a battery dismantling facility (14), and a battery unloading facility (15).

[0063] At this time, multiple facilities may be implemented to perform an automated battery processing process based on multiple automated systems. Specifically, the multiple facilities may be implemented to operate based on the processing results (e.g., calculations, judgments, commands, etc.) of at least one computing device (or electronic device) equipped with an automated system.

[0064] For example, referring to FIG. 2, a computing device (200) including at least one processor may be implemented to control a plurality of automated systems. At this time, the battery handling automated system (1) may include, but is not limited to, a battery transport system (21) for automatically transporting a battery, a battery storage system (22) for automatically storing a battery, a battery preprocessing system (23) for automatically preprocessing a battery (e.g., diagnosing, charging, discharging, removing coolant, etc.), and a battery disassembly system (24) for automatically disassembling (or disassembling) a battery.

[0065] Specifically, the computing device (200) can control the battery transport system (21) to move the battery to a designated location. Furthermore, the computing device (200) can control the battery storage system (22) to store or transport the battery to or from a designated area. Furthermore, the computing device (200) can control the battery preprocessing system (23) to preprocess the battery in a predetermined manner. Furthermore, the computing device (200) can control the battery disassembly system (24) to disassemble at least one component of the battery.

[0066] Additionally, the computing device (200) may be configured to post-process dismantled batteries in conjunction with a recycling / reuse company system (25). For example, the computing device (200) may be configured to transport dismantled batteries to a waste battery recycling company for use in (waste) battery recycling. Furthermore, for example, the computing device (200) may be configured to transport dismantled batteries to a waste battery reuse company for use in (waste) battery reuse.

[0067] An example of a battery processing process based on a battery processing automation system (1) is as follows.

[0068] For example, referring to (b) of FIG. 1, a transport facility (11) having a battery transport system implemented can transport a battery pack received in a space having a battery handling automation system (1) implemented to a storage facility (12) having a battery storage system implemented. At this time, batteries transferred from an external company can be unloaded and transported using an unloading facility (15) and a transport facility (11). In addition, the storage facility (12) can store the battery pack in a storage slot determined according to a predetermined standard. In addition, at least one of the battery packs stored in the transport facility (11) and the storage facility (12) can be taken out and transported to a preprocessing facility (13) having a battery preprocessing system implemented. The preprocessing facility (13) can preprocess the battery pack using at least one preprocessing device (e.g., a diagnostic device, a charger, a discharger, etc.). In addition, the transport facility (11, e.g., a mobile robot) can transport the preprocessed battery pack to a dismantling facility (14) having a battery dismantling system implemented. The dismantling facility (14) can dismantle a battery pack using at least one dismantling means (e.g., a collaborative robot, etc.). The dismantled battery can be stored using a storage system or transferred to an external company.

[0069] The automated systems constituting the battery processing automation system (1) can be implemented based on a robot system and a computing device for controlling the robot system.

[0070] FIG. 3 is a drawing for explaining a detailed configuration of an automation system based on a robot system according to various embodiments.

[0071] Referring to FIG. 3, the battery processing automation system may include a robot system (320) including a plurality of robot devices and at least one computing device (300) for controlling the robot system (320). In this case, the computing device (300) may include a server device, but is not limited thereto.

[0072] The computing device (300) may include, but is not limited to, a processor (301), a memory (302), and a communication circuit (303), and may further include configurations of a computing device that are apparent to those skilled in the art.

[0073] The processor (301) may include at least one processor, at least some of which are implemented to provide different functions. For example, the processor (301) may execute software (e.g., a program) to control at least one other component (e.g., a hardware or software component) of a computing device connected to the processor (301) and perform various data processing or calculations. In one embodiment, as at least a part of the data processing or calculation, the processor (301) may store instructions or data received from other components in the memory (302) (e.g., a volatile memory), process the instructions or data stored in the volatile memory, and store the resulting data in the non-volatile memory. In one embodiment, the processor (301) may include a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together therewith. For example, if a computing device includes a main processor and a coprocessor, the coprocessor may be configured to use less power than the main processor or to be specialized for a given function. The coprocessor may be implemented separately from the main processor, or as a part thereof. The coprocessor may control at least a portion of functions or states associated with at least one component (e.g., the communication circuit (303)) of the computing device, for example, on behalf of the main processor while the main processor is in an inactive (e.g., sleep) state, or together with the main processor while the main processor is in an active (e.g., application execution) state. In one embodiment, the coprocessor (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., the communication circuit (303)).In one embodiment, the auxiliary processor (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. Such learning may be performed, for example, on the computing device itself where the artificial intelligence model is executed, or may be performed through a separate server. The learning algorithm may include, but is not limited to, supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, or reverse reinforcement learning, for example. The artificial intelligence model may include multiple artificial neural network layers. The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), deep Q-networks, a transformer, or a combination of two or more of the above, but is not limited to the examples described above. In addition to the hardware structure, the artificial intelligence model may additionally or alternatively include a software structure. Meanwhile, the operation of the computing device described below may be understood as the operation of the processor (301).

[0074] The memory (302) can store various data output by at least one component of the computing device (e.g., processor (301). The data can include, for example, input data or output data for software (e.g., program) and instructions related thereto. The memory (302) can include volatile memory or non-volatile memory. The memory (302) can be implemented to store an operating system, middleware or application, and / or the artificial intelligence model described above.

[0075] The communication circuit (303) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the computing device and an external electronic device (e.g., a measuring device or a user device), and the performance of communication through the established communication channel. The communication circuit (303) may operate independently from the processor (301) (e.g., a program processor) and may include one or more communication processors (e.g., communication chips) that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication circuit (303) may include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) communication module, or a power line communication module). Any of these communication modules may communicate with an external computing device (e.g., a mobile device, a wearable device, or a server device) via a first network (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a local area network or a wide area network)). These various types of communication modules may be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module may identify or authenticate the computing device within a communication network, such as the first network or the second network, by using subscriber information stored in the subscriber identification module (e.g., an international mobile subscriber identity (IMSI)).The wireless communication module can support 5G networks and next-generation communication technologies beyond 4G networks, such as new radio access technology (NR). NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimizing terminal power and connecting multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency communications (URLLC (ultra-reliable and low-latency communications)). The wireless communication module can support high-frequency bands (e.g., mmWave bands) to achieve high data rates, for example. The wireless communication module may support various technologies to secure performance in high frequency bands, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antennas, analog beam-forming, or large scale antennas. According to one embodiment, the wireless communication module may support peak data rates (e.g., 20 Gbps or more) for eMBB implementation, loss coverage (e.g., 164 dB or less) for mMTC implementation, or U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC implementation.

[0076] The robotic system (320) may include a plurality of robotic devices (310a, 310b, 310c, 310d).

[0077] At this time, the plurality of robot devices (310a, 310b, 310c, 310d) may include various types of robots. For example, the plurality of robot devices (310a, 310b, 310c, 310d) may include, but are not limited to, collaborative robots, industrial robots, mobile robots with autonomous driving functions, automatic transport robots, or autonomous forklifts.

[0078] For example, the first robot device (310a) may include, but is not limited to, at least one robot arm (311), at least one driving device (312) for providing power to the robot arm, at least one sensor (313), at least one processor (314), and a memory (315). At this time, at least one processor (314) may be a sub-processor for communicating with the main processor and controlling the configurations of the robot device, but is not limited thereto.

[0079] A robotic device may be a device including one or more actuators and one or more parts. Here, the actuator may refer to various devices that convert electrical energy into kinetic energy based on a control signal. For example, the actuator may be any one of a direct current (DC) servo motor, an alternating current (AC) servo motor, a stepping motor, a linear motor, a hydraulic cylinder, a hydraulic motor, a pneumatic cylinder, and a pneumatic motor. However, this is merely an example, and the spirit of the present invention is not limited thereto.

[0080] The robot system (320) may further include at least one end effector for performing a specific task. In this case, the at least one end effector may be connected to the end of a robot device (or a robot arm included in the robot device) and implemented to perform a specific task.

[0081] For example, end effectors may include, but are not limited to, grippers used to pick up or move objects (e.g., mechanical grippers that pick up objects using fixed fingers and vacuum (or pneumatic) grippers that pick up objects using vacuum), Welding Torches designed to enable robots to perform welding tasks, Paint Spray Guns that enable robots to automatically perform painting or coating tasks, Cameras and Sensors used for quality inspection, precision measurement, or visual monitoring of the work environment, Tool Holders that mount drills, screwdrivers, or other tools to enable robots to perform various assembly tasks, Electrical and Electronic Component Manipulators used to handle or assemble precise electronic components, or scrapers used to remove materials adhered to a surface.

[0082] Additionally, the battery processing automation system may further include at least one sensor (330), an operator terminal (340), or at least one processing device (350) capable of communicating with the computing device (300).

[0083] At this time, at least one sensor (330) may include, but is not limited to, a camera, a radar sensor, an ultrasonic sensor, a depth measurement sensor (e.g., lidar, TOF camera, etc.), a motion detection sensor, a temperature detection sensor, or a thermal imaging camera for obtaining visual information about the work space.

[0084] The worker terminal (340) may be an electronic device capable of communication connection to the computing device (300). For example, the worker terminal (340) may be a mobile device such as a smartphone or tablet PC, or a display device connected to the automation system, but is not limited thereto. In this case, the computing device (300) may control the automation system based on commands received from the worker terminal (340).

[0085] At least one processing device (350) may include a device for physically or chemically processing the battery. For example, the at least one processing device (350) may include, but is not limited to, a diagnostic device for diagnosing the performance of the battery, a charger for charging the battery, or a discharger for discharging the battery.

[0086] The battery processing automation system may further include at least one light for controlling brightness inside the work cell, a foreign matter suction device for sucking foreign matters such as dust inside the work space, and an air circulation device for controlling temperature and humidity inside the work space.

[0087] The processor (301) can train the robot system (320) based on at least one predetermined robot artificial intelligence learning method.

[0088] For example, the processor (301) can train robot artificial intelligence based on imitation learning. Imitation learning is a method in which a robot learns by observing and imitating the behavior of humans or other robots (e.g., human demonstrations). Through imitation learning, the processor (301) can train the robot to quickly acquire the skills necessary to perform complex tasks.

[0089] As another example, the processor (301) can train the robot's artificial intelligence based on reinforcement learning. Reinforcement learning is a method that allows the robot to learn through trial and error. The robot selects actions in a given environment and learns based on the rewards it receives from those actions. Through reinforcement learning, the processor (301) can train the robot to identify the optimal sequence of actions to achieve a specific goal.

[0090] As another example, the processor (301) can train the robot's artificial intelligence based on the inverse reinforcement learning method. In this case, inverse reinforcement learning is a learning method that infers a reward function from observed behavior. In other words, rather than learning what actions the robot should take to achieve a certain goal, it is a method of training the robot to understand what goals the observed behaviors are intended to achieve. Through inverse reinforcement learning, the processor (301) can train the robot to observe human behavior, understand its purpose, and achieve similar goals in similar situations.

[0091] Below, we describe in detail a robotic system-based automation system for providing battery processing automation.

[0092] Battery Transport and Storage System

[0093] FIG. 4 is a diagram illustrating a configuration of a battery transport and storage system according to various embodiments.

[0094] Referring to FIG. 4, the battery transport and storage system may include at least one transport device (410), storage (420) including a plurality of slots, and a computing device (400) including memory and at least one processor.

[0095] At least one transport device (410) may include a first transport device (410a, e.g., an unmanned forklift) for loading or unloading batteries into or from storage (420) and a second transport device (410b, e.g., a mobile robot or conveyor) for transporting the batteries to a work space. At least one transport device (410) may be equipped with an autonomous driving function, and may be implemented to transport the batteries without manual human operation.

[0096] The storage (420) may include a plurality of slots for storing batteries. The storage (420) may further include at least one sensing device for monitoring the batteries stored in the slots. Specifically, the storage (420) may include at least one temperature sensor for detecting a fire risk in the batteries.

[0097] Additionally, the storage (420) may further include a transport module (not shown) for moving the battery within the storage (420). The transport module may be configured to move the battery between slots within the storage. For example, the transport module may include, but is not limited to, at least one rail and a transport module for moving the battery along the rail.

[0098] The battery (10) may be loaded onto a pallet (not shown) and transported or stored. At least one transport device (410) may transport the battery loaded onto the pallet, and the storage device (420) may be implemented to accommodate the battery loaded onto the pallet in at least one slot.

[0099] At least one processor included in the computing device (400) may be configured to perform an operation of transporting and storing the battery in storage based on a control signal instructing storage of the battery. Furthermore, at least one processor may be configured to perform an operation of transporting and removing the battery from storage based on a control signal instructing removal of the battery.

[0100] The memory included in the computing device (400) may store identification information including a plurality of identifiers corresponding to each of a plurality of slots of the storage. Specifically, the computing device (400) may store an identifier corresponding to a slot that reflects whether a battery is received and / or information about the received battery.

[0101] At least one processor may set conditions for batteries to be accommodated in multiple slots included in the storage (420). In this case, the at least one processor may control at least one transport device (410) and the storage (420) to store or remove the batteries according to the set conditions. In this case, the identification information stored in the memory may include condition information indicating the conditions of the batteries to be stored in the target slots.

[0102] For example, at least one processor may set battery storage conditions based on whether multiple processing steps have been performed on the battery. Specifically, at least one processor may determine which slot to accept the battery by identifying the battery based on whether a diagnostic / discharging process or a disassembly process is in progress.

[0103] Additionally, for example, at least one processor may set battery storage conditions based on processing priorities for batteries to be accommodated in multiple slots within the storage. Specifically, at least one processor may set processing priorities based on factors such as battery stability or degree of damage. In other words, the battery storage system may be configured to quickly remove and process batteries with low stability and high degree of damage.

[0104] Additionally, for example, the battery storage system can be implemented to store batteries by manufacturer. The battery storage system can be implemented to store batteries by type (e.g., for recycling or reuse). The battery storage system can determine the slot in which to store batteries based on user input.

[0105] Additionally, for example, a battery storage system can be implemented to store batteries by classifying them according to their diagnostic grade.

[0106] The storage (420) may include a plurality of zones divided according to predetermined battery storage conditions. In this case, each zone may include at least one slot.

[0107] For example, the first zone (421) of the storage may be configured to accommodate a battery that satisfies a first condition (e.g., performing a diagnosis and discharge process). In this case, at least one processor may be configured to accommodate a battery that satisfies the first condition in a slot closest to the plurality of slots included in the first zone (421), but this is not limited thereto.

[0108] [Battery Preprocessing System]

[0109] FIG. 5 is a diagram illustrating a configuration of a battery preprocessing system according to various embodiments.

[0110] Referring to FIG. 5, the battery preprocessing system may include at least one device (1210), at least one robot (1220), and a computing device (1200) including a memory and at least one processor.

[0111] At least one device (1210) may include at least one of a charging device for charging a battery, a discharging device for discharging a battery, or a diagnostic device for diagnosing a battery.

[0112] The computing device (1200) can preprocess the battery using at least one device (1210).

[0113] More specifically, the computing device (1200) can diagnose a battery using a battery diagnostic device.

[0114] The computing device (1200) can obtain state of charge (SOC) information by measuring the remaining charge in the battery using a battery diagnostic device.

[0115] Additionally, the computing device (1200) can obtain state of health (SOH) information indicating the lifespan and health indicators of the battery by using a battery diagnostic device.

[0116] Additionally, the computing device (1200) can use a battery diagnostic device to measure the voltage and current of the battery to diagnose whether the battery is operating within normal parameters.

[0117] Additionally, the computing device (1200) can diagnose the degree of aging of the battery by measuring the internal resistance using a battery diagnostic device. Here, the internal resistance of the battery increases as the battery ages.

[0118] Additionally, the computing device (1200) can measure temperature data of the battery using a battery diagnostic device. In this case, past temperature data can be utilized to diagnose the past status of the battery's performance and lifespan.

[0119] Additionally, the computing device (1200) can determine the remaining life of the battery by obtaining the charge and discharge cycles of the battery using a battery diagnostic device.

[0120] Additionally, the computing device (1200) can utilize a battery diagnostic device to provide information on the internal chemical and electrical processes of the battery by applying electrochemical impedance spectroscopy (EIS). Through this, the computing device (1200) can identify performance degradation patterns or defects in the battery.

[0121] Additionally, the computing device (1200) can obtain information on the actual capacity of the battery by fully charging and discharging the battery using a battery charging device and a discharge device. At this time, the computing device (1200) can check for any performance degradation by comparing the measured actual capacity with the rated capacity of the battery.

[0122] Additionally, the computing device (1200) can measure the balance status of the cells constituting the battery pack using a battery diagnostic device. Specifically, the computing device (1200) can determine whether the voltages of individual cells are balanced.

[0123] Additionally, the computing device (1200) can charge a battery module (e.g., a battery that supplies power to an electric vehicle) using a battery charging device.

[0124] The computing device (1200) can connect or disconnect at least one device (1210) to or from the battery (10) using at least one robot (1220). Specifically, the at least one robot (1220) can operate to connect or disconnect at least one connection (e.g., a connector, etc.) included in the at least one device (1210) to or from the battery (10) by applying a physical force to the at least one connection.

[0125] Details on how to interface the battery and processing unit using a robotic device are described below.

[0126]

[0127] FIG. 6 is a diagram illustrating one embodiment of a method of operating a robot system for controlling the operation of a robot device according to various embodiments.

[0128] Referring to FIG. 6, the robotic system can connect at least one connector included in at least one processing device to a battery by controlling the operation of the robotic device based on a control algorithm performed by at least one processor.

[0129] Specifically, at least one processor included in the robot system can obtain sensing data related to the battery from at least one sensor (S1301).

[0130] Sequentially or independently of step S1301, at least one robotic device may perform an operation of gripping at least one connector included in at least one processing device using an end effector (S1311).

[0131] Additionally, at least one processor may set a location corresponding to at least one port connected to the battery as a target location based on sensing data (S1302). Specifically, at least one processor may extract feature values ​​of the sensing data and determine the target location by specifying at least a portion of an area having feature values ​​corresponding to a predetermined condition. In this case, at least one processor may utilize at least one artificial intelligence model (e.g., CNN, etc.) for processing the sensing data, but is not limited thereto.

[0132] At least one processor can set a target location based on predetermined conditions. Specifically, at least one processor can set a target location based on whether communication is possible through at least one port. At least one processor can identify multiple ports based on sensing data and determine at least one port among the identified multiple ports that is determined to be capable of communication with the processing device. In this case, at least one processor can set a location corresponding to the determined at least one port as the target location.

[0133] Additionally, at least one processor can control an alarm to be activated if a communication connection through at least one port identified based on sensing data is not possible.

[0134] Additionally, optionally, at least one processor may obtain battery information and determine operating parameters associated with the operation of at least one processing device based on the battery information. For example, the at least one processor may set at least one operating parameter (e.g., voltage or current, etc.) for diagnosis by the battery diagnosis device based on the battery status information, but is not limited thereto. Additionally, for example, the at least one processor may set at least one operating parameter (e.g., charging time, charging speed, etc.) for charging by the battery charging device based on the battery charge status information, but is not limited thereto.

[0135] At least one processor can control the motion of the robotic device by generating a trajectory for controlling the robotic device.

[0136] Specifically, at least one processor can generate a trajectory by determining dynamic parameters (e.g., velocity, acceleration, force, torque, etc.) at a plurality of points until at least a portion of the robotic device (e.g., a plurality of joints included in the robotic device) reaches a particular destination.

[0137] FIG. 7 is a diagram illustrating a method for a processor to control a robotic device based on an artificial intelligence engine according to various embodiments.

[0138] At least one processor can control a robotic device by training an artificial intelligence engine (or model) to perform a specific task. The specific method for training the robotic device has been previously described, so a detailed description thereof will be omitted.

[0139] Referring to FIG. 7, at least one processor may generate a trajectory of a robotic device based on sensed data using an artificial intelligence engine. Specifically, at least one processor may obtain input data based on the sensed data and input the input data into the artificial intelligence engine. In this case, at least one processor may obtain output data from at least one layer included in an artificial intelligence model. Specifically, at least one processor may obtain dynamic parameters (e.g., speed, acceleration, force, torque, etc.) corresponding to a plurality of points toward which at least one robotic device is directed toward a target location. In other words, a trajectory may be composed of a set of dynamic parameters, and the set of dynamic parameters may be determined differently depending on the operational purpose of the robotic device.

[0140] At least one processor can generate a trajectory for at least one robotic device to operate based on the dynamic parameters.

[0141] Additionally, at least one processor can input the generated trajectory to a motion controller of at least one robotic device, and the motion controller can drive the robotic device based on the trajectory.

[0142] Additionally, and not limited thereto, at least one processor may utilize an artificial intelligence model to obtain dynamic parameters for the end effector to perform a specific action (e.g., a screw action, a picking action, etc.).

[0143] According to an embodiment, the task to be achieved can be performed with a minimum computational cost by learning and utilizing an artificial intelligence engine to control the trajectory or movement of an end effector of at least one robotic device by at least one processor.

[0144] Referring again to FIG. 6, at least one processor may determine a first trajectory for the end effector to reach a first position corresponding to the target position (S1303). In addition, in this case, at least one robotic device may perform an operation of moving the end effector to the first position based on the first trajectory (S1312).

[0145] Specifically, at least one processor can determine a first trajectory based on a physical relationship between at least one robotic device (or an end effector included in the robotic device) and a target position based on sensing data.

[0146] At least one processor can determine at least one of a position coordinate of a target position, a direction from at least one robot device (or an end effector included in the robot device), and a distance from the robot device (or an end effector included in the robot device) based on the sensing data. In this case, the at least one processor can determine a first trajectory based on at least one of the position coordinate of the target position, the direction from at least one robot device (or an end effector included in the robot device), and the distance from the robot device (or an end effector included in the robot device).

[0147] At this time, the first position may be a position spaced apart from the target position by a predetermined distance. At least one processor may be trained to position the end effector at the first position spaced apart from the target position by a predetermined distance. For example, at least one processor may measure the distance between the end effector and the target position using at least one sensor for distance measurement, and determine the first position based on the measured distance.

[0148] Additionally, at least one processor may determine a second trajectory for connecting at least one connector gripped by the end effector to at least one port (S1304). In this case, at least one robotic device may perform an operation for connecting at least one connector to at least one port based on the second trajectory (S1313).

[0149] Specifically, at least one processor may train an artificial intelligence model to cause at least a portion of at least one connector (e.g., a protrusion for connection) to be inserted into at least a portion of at least one port (e.g., a receptacle for connection). The at least one processor may control at least one robotic device to apply a force to connect at least one connector to at least one port using the trained artificial intelligence model.

[0150] At least one processor may determine that the connection operation is complete if at least one connector does not move. At least one processor may determine that the connection between the connector and the port is complete if at least one connector is no longer inserted into the port despite applying force to the at least one connector according to the second trajectory. Furthermore, at least one processor may determine that the connection operation is complete if at least one connector does not move for a predetermined period of time.

[0151] Additionally, when processing by the processing device is completed, at least one processor may control the disconnection of the processing device and the battery. Specifically, at least one processor may control at least one robotic device by determining at least one trajectory for performing an operation of gripping at least one connector using an end effector and disconnecting at least one connector connected to at least one port.

[0152] A battery management system (BMS) may be an electronic system connected to a battery to monitor the battery, and the BMS may be built into the battery or a separate device connected to the battery.

[0153] The battery management system can obtain monitoring information about the battery from the battery management system through a communication connection. In other words, the battery can be diagnosed by obtaining monitoring information about the battery stored in the battery management system through a communication connection with the battery management system.

[0154] Accordingly, if a communication connection with the battery management system is possible, the battery processing system can obtain diagnostic information about the battery by performing a battery diagnostic process.

[0155] However, depending on the battery, some batteries may not include a battery management system, or communication with the battery management system may not be possible (e.g., if not authorized by the manufacturer, if the port is damaged, etc.).

[0156] In this case, the battery handling system needs to individually connect diagnostic devices to multiple ports for diagnosing various battery parameters (e.g., SOC, SOH, etc.) to diagnose the battery. However, these ports are located internally within the battery and cannot be accessed without removing the battery cover.

[0157] Accordingly, if communication with the battery management system is not possible, the battery handling system needs to perform a battery diagnosis process by removing the battery cover and connecting to at least one port.

[0158] The battery processing system can select the battery processing process currently required by determining whether communication connection with the battery management system is possible, thereby increasing the efficiency of the battery processing automation process.

[0159] FIGS. 8 to 10 are diagrams illustrating a method for a battery handling system to control a robotic device to connect and disconnect a battery with a battery diagnostic device, according to various embodiments.

[0160] Referring to FIGS. 8 to 10, at least one processor included in the battery processing system can obtain battery information (S1701).

[0161] Sequentially or independently of step S1701, at least one robotic device may perform an operation of gripping at least one connector included in the diagnostic device using an end effector (S1711).

[0162] At least one processor can determine diagnostic parameters for diagnosing a battery based on battery information (S1702). In this case, the diagnostic device can set a diagnostic mode based on the determined diagnostic parameters (S1721).

[0163] Specifically, at least one processor can determine diagnostic parameters suitable for diagnosing a battery based on battery information. For example, at least one processor can determine voltage or current suitable for battery diagnosis, and set diagnostic parameters of a diagnostic device based on these parameters.

[0164] Additionally, the processor included in the diagnostic device can set a diagnostic mode based on diagnostic parameters. For example, the diagnostic device can set a diagnostic mode by selecting at least one of the diagnostic modes (e.g., basic diagnosis, detailed diagnosis, precision diagnosis, etc.) according to the level of diagnosis. Furthermore, for example, the diagnostic device can set a diagnostic mode by selecting at least one of the diagnostic modes (e.g., initial inspection, late inspection, etc.) according to the diagnostic stage.

[0165] At least one processor may set a location corresponding to at least one port connected to the battery as a first target location based on sensing data (S1703). At this time, at least one port may be disposed on at least a portion of the battery. The at least one port may be disposed so as to be exposed on the outer surface of the battery. The at least one port may be disposed on at least a portion of the inside of the battery pack. When the top cover of the battery is removed, the at least one port may be implemented so as to be exposed. In addition, at least one port may be electrically connected to a battery management system (BMS) of the battery. The at least one port may be electrically connected to a configuration capable of diagnosing at least one state of the battery (e.g., state of charge, state of health, state of voltage, state of current, etc.).

[0166] At least one processor can determine a first trajectory for the end effector to move to a first position corresponding to a first target position to connect at least one connector to at least one port (S1704).

[0167] In this case, at least one robotic device can perform an operation of moving an end effector based on a first trajectory to connect at least one connector to at least one port (S1712).

[0168] Additionally, at least one processor can confirm that the diagnostic device and the battery are normally connected (S1705).

[0169] Specifically, at least one processor can determine the physical connection status between the diagnostic device and the battery. For example, the at least one processor can determine whether the physical connection status between a connector included in the diagnostic device and a port included in the battery is normal. As a specific example, the at least one processor can control at least one robotic device that grasps the connector to apply a predetermined force to the connector in a direction that separates it from the port. In this case, if the connector does not separate from the port, the battery and the diagnostic device can be determined to be normally connected.

[0170] Additionally, at least one processor can determine whether the diagnostic device and battery are configured for diagnosis. For example, at least one processor can compare the battery profile and diagnostic parameters of the diagnostic device, and if a predetermined criterion is met, the test can be set to proceed.

[0171] At least one processor can determine a second trajectory for moving the end effector to a predetermined second position (S1706).

[0172] In this case, at least one robotic device can perform an operation in which the end effector places at least one connector based on the second trajectory and moves to a predetermined position (S1713).

[0173] In parallel, the diagnostic device can perform a battery diagnosis based on the determined diagnostic mode (S1722). The processor included in the diagnostic device can examine various battery conditions and, based on the examination results, calculate the battery's SOC, SOH, SOP, or SOB, and determine the diagnostic level.

[0174] Additionally, the diagnostic device can obtain monitoring information by diagnosing the battery (S1723). At this time, the monitoring information may be information obtained by the diagnostic device monitoring the battery's status. Specifically, a processor included in the diagnostic device can check the battery's safety status or the presence of an abnormality in the diagnostic device. Specifically, the diagnostic device can monitor the battery's safety status and the status of the diagnostic device while the diagnosis / inspection is being performed, and transmit the monitoring information to a battery processing system. For example, the monitoring information may include, but is not limited to, the battery's charging status, the battery's voltage status, or the battery's safety status.

[0175] At least one processor can identify whether an event has occurred based on monitoring information (S1707). The event may include at least one event that can occur during battery diagnosis. For example, the event may include an event based on a diagnostic step, an event based on a diagnostic function, an event based on a test mode, or an emergency stop event.

[0176] Additionally, at least one processor can control the system based on the generated event (S1708). Specifically, at least one processor can control the system by determining feedback based on the type of generated event.

[0177] For example, if a battery instability is detected during the initial inspection, at least one processor can control at least one robotic device to send an alarm and perform an action to disconnect the diagnostic device from the battery.

[0178] Additionally, for example, if a fire risk is detected, at least one processor may control at least one robotic device to transmit an alarm and perform emergency measures. Specifically, at least one processor may control at least one robotic device to perform an action of dropping a battery into a tank.

[0179] After diagnosing the battery according to step S1723, the diagnostic device may complete the diagnostic operation (S1724). In this case, the diagnostic device may calculate multiple indicators related to the battery's condition (e.g., SOC, SOH, etc.) and calculate a diagnostic grade based on the multiple indicators.

[0180] Additionally, at least one processor may determine a third trajectory for causing the end effector to move to a third position corresponding to at least a portion of at least one connector and to grip at least one connector (S1709). Additionally, at least one robotic device may perform an operation of moving the end effector to the third position and gripping at least one connector based on the third trajectory (S1714).

[0181] Additionally, at least one processor may determine a fourth trajectory for detaching at least one connector gripped by the end effector from the battery (S1710). In this case, at least one robotic device may perform an operation for detaching at least one connector from the battery based on the fourth trajectory (S1715).

[0182] In one embodiment, at least one processor may control storage of batteries on which a diagnostic process has been performed in a battery storage system. In this case, at least one processor may classify and store batteries based on their diagnostic ratings.

[0183] FIG. 11 is a diagram illustrating a method for storing batteries according to battery diagnostic grades by a battery handling system according to various embodiments.

[0184] Referring to FIG. 11, at least one processor included in the battery processing system can determine a battery diagnosis grade and complete the battery diagnosis (S2001).

[0185] Additionally, at least one processor may use a transfer device to transfer the battery to the battery storage (S2003). The battery storage may include a plurality of slots for accommodating and storing the battery.

[0186] Additionally, battery storage may be implemented to store batteries based on their diagnostic ratings. For example, battery storage may include multiple zones divided by battery diagnostic ratings, and specific zones may be configured to store batteries assigned a specific diagnostic rating.

[0187] At least one processor may determine a target slot for storing the battery based on the determined diagnostic rating (S2005). Specifically, the at least one processor may determine the target slot by selecting at least one slot corresponding to the diagnostic rating of the battery. At this time, the target slot may be assigned identification information corresponding to the diagnostic rating of the battery. Furthermore, the at least one processor may determine the target slot by determining a storage area on the battery storage corresponding to the diagnostic rating of the battery.

[0188] At least one processor may determine a target slot using at least one sensor (e.g., a vision sensor). Specifically, the at least one processor may determine the target slot by identifying at least one slot corresponding to the diagnostic grade of the battery to be stored based on sensing data.

[0189] Additionally, at least one processor may determine a target slot based on a communication connection with the battery storage system. Specifically, the at least one processor may transmit the diagnostic rating of the battery to be stored to the battery storage system, the battery storage system may determine a target slot corresponding to the rating, and transmit location information of the determined target slot to the transfer device.

[0190] At least one processor controls the transport device and battery storage to store the battery in the determined target slot (S2007). The specific method for storing the battery in the target slot has been described above, so it will be omitted.

[0191] FIG. 12 is a diagram illustrating a method for a battery handling system to control a robotic device to connect a battery discharge device and a battery, according to various embodiments.

[0192] Referring to FIG. 12, at least one processor can set a location corresponding to at least one port connected to a battery as a first target location based on sensing data (S2101).

[0193] Sequentially or independently of step S2101, at least one robotic device may perform an action of gripping at least one connector included in the discharger using an end effector (S2111).

[0194] Additionally, at least one processor may determine a first trajectory for the end effector to move to a first position corresponding to a first target position and connect at least one connector to at least one port (S2102). At this time, at least one port may be arranged on at least a portion of the battery. The at least one port may be arranged to be exposed on an outer surface of the battery. The at least one port may be arranged on at least a portion of the interior of the battery pack. When the upper cover of the battery is removed, the at least one port may be implemented to be exposed. Additionally, the at least one port may be electrically connected to at least one cell of the battery.

[0195] In this case, at least one robotic device can perform an operation of moving an end effector based on a first trajectory to connect at least one connector to at least one port (S2112).

[0196] Additionally, at least one processor can verify that the discharger and the battery are normally connected (S2103).

[0197] The discharger can perform battery discharge (S2121).

[0198] Additionally, at least one processor may control a monitoring operation during discharge and a connector separation operation after discharge (S2104). For example, at least one processor may monitor the battery discharge rate, discharge amount, or remaining discharge time, and, when discharge is complete, may use at least one robotic device to separate at least one connector from the battery.

[0199] [Battery Disassembly System]

[0200] FIG. 13 is a diagram illustrating a configuration of a battery disassembly system according to various embodiments.

[0201] Referring to FIG. 13, the battery disassembly system may include a computing device (2300), at least one transport device (2310) for loading and moving a battery (10), a battery disassembly area (2320) where a work space for disassembling a battery is provided, and at least one robotic device (2330).

[0202] The computing device (2300) can control the transport device (2310) or the robotic device (2330) to transport the battery (10) and perform an operation of dismantling at least one component of the battery (10). The computing device (2300) can include, for example, a main server (processor) and at least one sub-processor for controlling a battery dismantling system, but is not limited thereto.

[0203] The battery disassembly area (2320) may include at least one work chamber (2325). In this case, at least one work chamber (2325) may be a modular space for performing battery disassembly work. Details regarding the work chamber (2325) are described below (Figs. 28 and 29).

[0204] The computing device (2300) can move the battery (10) using a transport device (2310).

[0205] At this time, the transport device (2310) may be a drivable device that has a space for loading batteries. For example, the transport device (2310) may include a mobile robot such as that illustrated in FIG. 13, and may also include a conveyor (not illustrated) for transporting the batteries.

[0206] Additionally, the computing device (2300) can cause the transport device (2310) to enter the battery disassembly area (2320) and position the transport device (2310) within the work area of ​​the robotic device (2330) so that the robotic device (2330) can perform the battery (10) disassembly operation.

[0207] For example, the computing device (2300) can position the mobile robot loading the battery (10) within the working area of ​​the robotic device (2330) by causing the mobile robot to enter the battery disassembly area (2320). In this case, the computing device (2300) can control the robotic device (2330) to disassemble the battery (10) loaded on the mobile robot.

[0208] Additionally, for example, the computing device (2300) may control a conveyor belt that loads batteries (10) to cause the batteries to enter a battery disassembly area (2320). In this case, the batteries (10) may be transported along the conveyor belt to be positioned within a working area of ​​the robotic device (2330), and the robotic device (2300) may be controlled to disassemble the transported batteries (10).

[0209] FIGS. 14 and 15 are diagrams illustrating an operation method of a robot system for disassembling a battery pack according to various embodiments.

[0210] Referring to FIG. 14, at least one processor included in the robot system may receive a control signal instructing disassembly of a first component of the battery (S2410). At this time, the control signal may be input to the robot system by a user input, or may be input from another system (e.g., a battery storage system, a battery preprocessing system, etc.). In addition, the first component may include, but is not limited to, an upper cover, a lower cover, a module, or a cell of the battery pack, and may be at least one component connected to the housing of the battery pack via a fastening member.

[0211] At least one processor may acquire sensing data related to a battery from at least one sensor (S2402). At this time, the at least one sensor may include, but is not limited to, a vision sensor, a camera sensor, an image sensor, a lidar sensor, or a radar sensor. The at least one sensor may be arranged on at least a portion of at least one robot device or on at least a portion of a work chamber (see drawing reference numeral 2325 of FIG. 13).

[0212] At least one processor can identify the location of a first fastening member for securing a first component based on sensing data and set it as a first target location (S2403). At this time, the first fastening member may include, but is not limited to, a bolt or a weld for securing the component. Specifically, at least one processor can determine the first target location by identifying the location coordinates, direction, distance, etc. of the first fastening member.

[0213] At this time, at least one processor can identify the positions of the plurality of fastening members based on the sensing data. At least one processor can select a first fastening member to perform a disassembly operation among the plurality of fastening members based on a predetermined criterion. Specifically, at least one processor can predetermine a disassembly order for the plurality of fastening members. In addition, at least one processor can select a fastening member that is close to at least one robotic device among the plurality of fastening members. In addition, at least one processor can select at least two fastening members among the plurality of fastening members that do not interfere with each other among the plurality of robotic devices.

[0214] At least one processor can determine a first trajectory for the first end effector to reach a first position corresponding to the first target position (S2404). At this time, at least one robotic device can perform an operation of moving the first end effector to the first position based on the first trajectory (S2411). Specifically, at least one processor can generate the first trajectory by inputting sensing data into an artificial intelligence model and obtaining a dynamic parameter set for reaching the first position from at least one layer included in the artificial intelligence model.

[0215] The first end effector may be a means for dismantling the first fastening member. For example, the first end effector may be, but is not limited to, a driver-shaped end effector (e.g., a Phillips screwdriver, a flat-head screwdriver, a circular screwdriver, etc.) for dismantling a bolt.

[0216] At least one processor may control the first end effector to perform a first task of disengaging the first fastening member from the battery based on a first condition (S2405). At this time, at least one robotic device may perform the first task of disengaging the first fastening member from the battery by the first end effector (S2412).

[0217] The first condition may be set based on whether at least one robotic device is ready to perform a task to disengage a fastening member. At least one processor may determine a relationship (e.g., distance, direction, etc.) between the first end effector and the first fastening member, and if the relationship meets a predetermined criterion, the processor may determine that the robot is ready to perform the task.

[0218] The first task may include a plurality of unit actions for disengaging the first fastening member. Specifically, the first task may include, but is not limited to, an action of approaching the first end effector to the first fastening member, an action of contacting the first end effector with the first fastening member, an action of driving the first end effector to disengage the first fastening member, and an action of separating the first fastening member.

[0219] For example, at least one processor can detect contact between the first end effector and the first fastening member, and control the first end effector to rotate (e.g., to unscrew) to disengage the first fastening member.

[0220] At least one processor can perform a plurality of first tasks simultaneously or sequentially using a plurality of robotic devices.

[0221] A specific method for controlling multiple robotic devices to perform a task is described below (Figs. 24 to 27).

[0222] At least one processor may determine whether the first task has been completed. Specifically, the at least one processor may determine, based on sensing data, whether all fasteners connecting the first component to the battery housing have been disengaged.

[0223] At least one processor may perform an operation for disassembling the first component when disassembly of all fasteners has been completed.

[0224] At least one processor can identify the removal of the fastening member and transmit a control signal for replacing the end effector. At this time, the at least one processor can control at least one robotic device to mount a second end effector for detaching the cover. In this case, the at least one processor can control at least one robotic device to release the first end effector and mount the second end effector, or, instead of the first robotic device mounted with the first end effector, the second robotic device mounted with the second end effector can be set as the working robot.

[0225] Referring to FIG. 15, at least one processor may set a second target position based on sensing data and determine a second trajectory for the second end effector to reach a second position corresponding to the second target position (S2406). At this time, at least one robot device may perform an operation of moving the second end effector to the second position based on the second trajectory (S2413). Specifically, at least one processor may generate the second trajectory by inputting sensing data into an artificial intelligence model and obtaining a dynamic parameter set for reaching the second position from at least one layer included in the artificial intelligence model.

[0226] At least one processor may determine the number of robotic devices to be used based on the specifications (e.g., volume, weight, etc.) of the first component. Specifically, the at least one processor may control disassembling the first component using one robotic device, or may control disassembling the first component using multiple robotic devices.

[0227] Alternatively, at least one processor may disassemble the first component using an industrial robot. Specifically, at least one processor may disassemble the first component using an industrial robot equipped with multiple pneumatic grippers, but is not limited thereto.

[0228] The second target position for disassembling the first component can be set to a position suitable for performing the operation of separating the first component. The battery disassembly system can pre-store positions suitable for disassembling the component according to the shape of the battery, and set the second target position based on the pre-stored positions.

[0229] The second end effector may be a means for separating the first component from the battery. For example, the second end effector may be, but is not limited to, a pincer-type gripper or a pneumatic gripper for grasping and exposing the component.

[0230] At least one processor may control the second end effector to perform a second task of separating the first part based on the second condition (S2407). At this time, at least one robotic device may perform the second task of separating the first part by the second end effector (S2414).

[0231] The second condition may be set based on whether at least one robotic device is ready to perform a task to separate the first component. At least one processor may determine a relationship (e.g., distance, direction, etc.) between the second end effector and the first component, and if the relationship meets a predetermined criterion, the robot may determine that the robot is ready to perform the task.

[0232] Additionally, the second condition may be set based on whether removal of at least one fastening member has been completed.

[0233] The second task may include a plurality of unit actions for separating the first component. Specifically, the second task may include, but is not limited to, an action of approaching the second end effector to the first component, an action of driving the second end effector to grasp the first component, and an action of separating the first component.

[0234] For example, at least one processor may cause a second end effector to approach a space between the first component and the battery housing, and may drive the second end effector to perform an action of grabbing the first component. Additionally, at least one processor may cause the robotic device to move, thereby performing an action of separating the first component.

[0235] Additionally, at least one processor may perform a second task using multiple robotic devices. In this case, at least one processor may set multiple target locations and position multiple robotic devices at each of the multiple target locations. Furthermore, multiple robotic devices may be driven simultaneously to perform an operation of separating the first component.

[0236] Additionally, at least one processor may control at least one robotic device to perform at least one insulation task at a predetermined location of the battery pack. Specifically, at least one processor may control at least one robotic device equipped with a third end effector to move to a predetermined location and perform at least one insulation task.

[0237] For example, at least one processor can move a third end effector provided with an insulating material to a predetermined position and perform an insulating action by applying the insulating material to a target location.

[0238] FIG. 16 is a drawing illustrating an operation method of a robot system for dismantling an upper cover of a battery pack according to various embodiments.

[0239] Referring to FIG. 16, at least one processor included in the robot system can receive a control signal instructing to disassemble the cover of the battery (S2601).

[0240] The robotic system can be implemented to dismantle the cover using multiple collaborative robots or to dismantle the cover using an industrial robot equipped with multiple pneumatic grippers.

[0241] At least one processor can obtain sensing data related to a battery from at least one sensor (S2602).

[0242] At least one processor can identify the position of at least one fastening member for securing the cover based on the sensing data (S2603).

[0243] At least one processor may control to disengage at least one fastening member by considering the position of at least one identified fastening member (S2604). At this time, at least one robotic device may perform at least one task of disengaging at least one fastening member from the battery using the first end effector (S2611).

[0244] At least one processor can identify removal of at least one fastening member based on sensing data (S2605).

[0245] Additionally, optionally, at least one processor may perform an operation of disassembling a guide plate positioned between a plurality of fastening members and a battery. Specifically, at least one processor may control at least one robotic device to disassemble the guide plate.

[0246] At least one processor may control the separation of the cover from the housing based on the identification action (S2606). At this time, at least one robotic device may perform at least one task of separating the cover from the battery housing using a second end effector (S2612).

[0247] FIG. 17 is a diagram illustrating an operation method of a robot system for disassembling a module of a battery pack according to various embodiments.

[0248] Referring to FIG. 17, at least one processor included in the robot system can receive a control signal instructing disassembly of at least one module of the battery (S2701).

[0249] The robotic system can determine the disassembly order for disassembling multiple modules included in a battery pack. Specifically, the robotic system can disassemble multiple modules in a predetermined order using multiple robotic devices. The robotic system can determine the disassembly order in advance by considering the electrical connections between the multiple modules.

[0250] At least one processor can obtain sensing data related to a battery from at least one sensor (S2702). At least one processor can identify the location of at least one fastening member for securing at least one module based on the sensing data (S2703).

[0251] At least one processor may control disassembly of at least one fastening member by considering the position of at least one identified fastening member (S2704). At this time, at least one robotic device may perform at least one task of disassembling at least one fastening member from the battery using a first end effector (S2711).

[0252] At least one processor can identify removal of at least one fastening member based on sensing data (S2705).

[0253] Additionally, optionally, at least one processor may perform an operation of disassembling a guide plate positioned between a plurality of fastening members and a battery. Specifically, at least one processor may control at least one robotic device to disassemble the guide plate.

[0254] At least one processor may control to separate at least one module from the housing based on an identification operation (S2706). At this time, at least one robotic device may perform at least one task of separating at least one module from the battery housing using a second end effector (S2712).

[0255] Additionally, at least one processor can control at least one module to be flipped (S2707). At this time, at least one robotic device or separate mechanism can perform at least one task for flipping at least one module (S2713). That is, at least one processor can perform an operation of flipping at least one module using at least one robotic device or separate mechanism.

[0256] At least one processor may perform an operation of dismantling a cooling plate attached to the bottom of at least one module. The operation of dismantling the cooling plate by at least one processor using at least one robotic device may be applied as described in FIGS. 14 and 15.

[0257] FIG. 18 is a diagram illustrating an operation method of a robot system for disassembling cells of a battery pack according to various embodiments.

[0258] Referring to FIG. 18, at least one processor included in the robot system can receive a control signal instructing to disassemble at least one cell of the battery (S2801).

[0259] The robotic system can determine the disassembly order for disassembling multiple cells included in a battery pack. Specifically, the robotic system can disassemble multiple cells in a predetermined order using multiple robotic devices. The robotic system can determine the disassembly order in advance by considering the electrical connections between the multiple cells.

[0260] At least one processor can obtain sensing data related to a battery from at least one sensor (S2802). At least one processor can identify the location of at least one fastening member for securing at least one cell based on the sensing data (S2803).

[0261] At least one processor may control to disengage at least one fastening member by considering the position of at least one identified fastening member (S2804). At this time, at least one robotic device may perform at least one task of disengaging at least one fastening member from the battery using the first end effector (S2811).

[0262] At least one processor can identify removal of at least one fastening member based on sensing data (S2805).

[0263] Additionally, optionally, at least one processor may perform an operation of disassembling a guide plate positioned between a plurality of fastening members and a battery. Specifically, at least one processor may control at least one robotic device to disassemble the guide plate.

[0264] At least one processor may control to separate at least one cell from the module housing based on an identification operation (S2806). At this time, at least one robotic device may perform at least one task of separating at least one cell from the module housing using a second end effector (S2812).

[0265] FIG. 19 is a diagram illustrating a method for storing components dismantled from a battery pack by a battery handling system according to various embodiments.

[0266] Referring to FIG. 19, at least one processor included in the battery handling system can load at least one component (e.g., a module, a cell, a fastening member, a battery housing, etc.) dismantled from a battery onto a transport device (S2901). At this time, the transport device may include, but is not limited to, a mobile robot or a conveyor belt. Furthermore, the transport device may be a different device (e.g., a separate mobile robot) from the transport device on which the battery dismantling operation is performed, or may be the same device (e.g., a connected conveyor belt).

[0267] At least one processor controls a transport device to transport at least one component to storage (S2902). The storage may include multiple slots for accommodating and storing battery components. The storage may be configured as a device identical to the battery storage device of FIG. 4, but may also be configured as an independent device.

[0268] Storage may be implemented to store components according to the type of battery component. For example, storage may include multiple zones divided by type of battery component, and specific zones may be configured to store specific components.

[0269] At least one processor may determine a target slot on the storage for storing at least one component, based on the component type (S2903). Specifically, the at least one processor may determine the target slot by selecting at least one slot corresponding to the component type. At this time, the target slot may be assigned identification information corresponding to the type of battery component. Furthermore, the at least one processor may determine the target slot by determining a storage area on the storage corresponding to the component type.

[0270] At least one processor may determine a target slot using at least one sensor (e.g., a vision sensor). Specifically, at least one processor may determine a target slot by identifying at least one slot corresponding to the type of component to be stored based on sensing data.

[0271] Additionally, at least one processor may determine a target slot based on a communication connection with the battery storage system. Specifically, the at least one processor may transmit the type of component to be stored to the battery storage system, the battery storage system may determine a target slot corresponding to the component, and transmit location information of the determined target slot to the transport device.

[0272] At least one processor controls the transport device and storage to store at least one component in a determined target slot (S2904). The specific method for storing the component in the target slot can be applied directly to the method for storing batteries.

[0273] FIG. 20 is a flowchart illustrating a method for a battery processing system to dismantle a plurality of fastening members according to various embodiments.

[0274] FIG. 21 is a diagram illustrating a method for a battery handling system to disassemble a plurality of fastening members according to various embodiments.

[0275] Referring to FIG. 20, at least one processor included in the battery processing system may receive a control signal instructing disassembly of a first component of the battery (S3001). At least one processor may obtain sensing data related to the battery from at least one sensor (S3002).

[0276] At least one processor can identify a position of a first fastening member for fixing a first part based on sensing data and set it as a first target position (S3003).

[0277] At least one processor can perform a task of moving at least one robotic device to a first position corresponding to a first target position and dismantling a first fastening member using the at least one robotic device (S3004).

[0278] At least one processor can identify a position of a second fastening member for fixing the first part based on sensing data and set it as a second target position (S3005).

[0279] At least one processor can adjust the position of the transport device or the at least one robotic device such that the second target position is located within the working area of ​​the at least one robotic device (S3006).

[0280] For example, at least one processor may move the second target location within the work area by adjusting the position of the mobile robot. Specifically, at least one processor may move the second target location within the work area by rotating the mobile robot carrying the battery.

[0281] Additionally, for example, at least one processor may move the second target location into the work area by adjusting the position of the conveyor belt. Specifically, at least one processor may move the second target location into the work area by rotating at least a portion of the conveyor belt (e.g., a rotating conveyor) carrying the batteries.

[0282] Additionally, for example, at least one processor may move the second target location within the work area by adjusting the position of at least one robotic device. Specifically, at least one processor may move the work area itself by moving at least one robotic device, thereby positioning the second target location within the work area.

[0283] At least one processor can perform a task of moving at least one robotic device to a second position corresponding to a second target position and dismantling the second fastening member using the at least one robotic device (S3007).

[0284] For example, referring to (a) of FIG. 21, at least one processor can control the first fastening member (3101a) and the second fastening member (3101b) of the battery (10) to be disassembled using the first robot device (3100a) and the second robot device (3100b).

[0285] In addition, referring to (a), (b) and (c) of FIG. 21, when the first fastening member (3101a) and the second fastening member (3101b) are disassembled, the transport device (3150) can be controlled so that the third fastening member (3101c) and the fourth fastening member (3101d) are positioned within the working areas of the first robot device (3100a) and the second robot device (3100b).

[0286] For example, by moving the position of the mobile robot loaded with the battery (10), the transport device (3150) can be controlled so that the third fastening member (3101c) and the fourth fastening member (3101d) are positioned within the working areas of the first robot device (3100a) and the second robot device (3100b). Specifically, at least one processor can adjust the position of the battery by rotating the mobile robot.

[0287] Additionally, for example, by driving a conveyor belt loaded with batteries (10), the transport device (3150) can be controlled so that the third fastening member (3101c) and the fourth fastening member (3101d) are positioned within the working areas of the first robot device (3100a) and the second robot device (3100b). Specifically, at least one processor can adjust the position of the battery by driving the rotating conveyor to rotate.

[0288] Additionally, for example, by moving the positions of the first robot device (3100a) and the second robot device (3100b), the transport device (3150) can be controlled so that the third fastening member (3101c) and the fourth fastening member (3101d) are positioned within the working areas of the first robot device (3100a) and the second robot device (3100b).

[0289] Also, referring to (c) and (d) of FIG. 21, when all fastening members are dismantled, at least one processor can dismantle the upper cover (3110) of the battery using the first robot device (3100a) and the second robot device (3100b).

[0290] FIG. 22 is a flowchart illustrating a method for a robotic system to perform a task using a robotic device according to various embodiments.

[0291] Referring to Figure 22, at least one processor included in the robot system can learn an artificial intelligence model to perform a task for disassembling the first fastening member (S3601). At this time, the artificial intelligence model can mimic human movements, but can be learned based on the purpose of the action. The learning method for the robot artificial intelligence model has been described above, so it will be omitted here.

[0292] Additionally, at least one processor may obtain at least one control value for controlling the operation of the robotic device from at least one layer of the learned model (S3602). Additionally, at least one processor may control the robotic device to perform a plurality of unit actions based on the at least one control value (S3603). Additionally, at least one processor may perform a task by performing a plurality of unit actions using at least one robotic device (S3604).

[0293] Additionally, in order for the robot system to disassemble the battery, it is necessary to accurately determine the pose of the battery before performing the disassembly operation according to FIGS. 14 to 35.

[0294] The robotic system can estimate the battery's posture by processing sensing data acquired using at least one sensor. Furthermore, at least one processor can calibrate the battery to a posture suitable for disassembling based on the estimated posture.

[0295] FIG. 23 is a diagram illustrating a method for a robot system to estimate and correct the attitude of a battery based on sensing data, according to various embodiments.

[0296] Referring to FIG. 23, at least one processor included in the robot system can obtain sensing data from at least one sensor (S3701).

[0297] Additionally, at least one processor can identify a reference position on the battery based on sensing data (S3702). Additionally, at least one processor can estimate the pose of the battery based on the positional relationship between the identified reference position and at least one robotic device (S3703). Additionally, at least one processor can adjust the position of at least one robotic device or transport device so that the positional relationship satisfies a predetermined standard (S3704).

[0298] Specifically, at least one processor can estimate the attitude of the battery by identifying a reference position on the battery, thereby performing calibration. The at least one processor can adjust the position of the battery or the position of at least one robotic device so that the reference position on the battery and the at least one robotic device have a predetermined positional relationship (e.g., distance, direction, etc.).

[0299] For example, at least one processor may correct the posture by adjusting the position of the battery by controlling a transport device (e.g., a mobile robot, a conveyor). Furthermore, for example, at least one processor may correct the posture by adjusting the position of at least one robotic device.

[0300] [Battery Pack Variety]

[0301] The detailed configuration of battery packs varies by manufacturer. The type, number, placement, and size of each component vary.

[0302] For example, battery packs from certain manufacturers are constructed from modules, while those from other manufacturers are constructed from cells. Furthermore, the shapes of modules and cells often vary from battery to battery.

[0303] That is, the battery processing process needs to be carried out differently depending on the battery profile (e.g., battery manufacturer, model, type, specifications, etc.).

[0304] Additionally, it is necessary to train a robot artificial intelligence engine based on various batteries to implement a robust system for battery disassembly in various environments.

[0305] [Multi-robot control algorithm]

[0306] According to one embodiment, a battery processing system utilizes multiple robotic devices to perform battery processing tasks. Furthermore, the battery processing system trains and utilizes an artificial intelligence engine to simultaneously control the multiple robotic devices. The artificial intelligence engine is trained to control the multiple robotic devices without interference.

[0307] To this end, the battery processing system can train an artificial intelligence engine to allow multiple robotic devices to perform tasks while taking into account the movements of other robotic devices.

[0308] FIG. 24 is a diagram illustrating a method for a battery processing system to control a plurality of robotic devices using an artificial intelligence engine, according to various embodiments.

[0309] Referring to FIG. 24, a battery processing system (4400) may include a processor and an artificial intelligence engine. The battery processing system (4400) may receive task execution commands and, in response to the received commands, determine trajectories for controlling multiple robots using the processor and the artificial intelligence engine. Since the specific method by which the artificial intelligence engine generates robot trajectories has been described above, a detailed description thereof will be omitted.

[0310] Additionally, the processor can control multiple robotic devices based on the determined trajectory. For example, the processor can control a first robotic device by transmitting a first trajectory to the first robotic device. Furthermore, the processor can control a second robotic device by transmitting a second trajectory to the second robotic device.

[0311] FIG. 25 is a flowchart illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0312] Referring to FIG. 25, at least one processor may acquire input data based on sensing data acquired from at least one sensor and input the data into an artificial intelligence model (S4501). In this case, at least one processor may acquire output data from at least one layer included in the artificial intelligence model.

[0313] At least one processor can obtain at least one control value for at least one power device of the first robot device based on the output data (S4502).

[0314] Specifically, at least one processor can drive a power device (e.g., a motor, etc.) included in a driving unit (e.g., a joint, etc.) for driving the first robotic device by transmitting at least one control value to the power device.

[0315] At least one processor may determine a first trajectory for moving a first end effector connected to the first robotic device to a target position based on at least one control value, taking into account the control of the second robotic device (S4503). At this time, at least one processor may determine the control status of the second robotic device by sensing the movement of the second robotic device or receiving the trajectory of the second robotic device.

[0316] At least one processor may determine a trajectory of the first robotic device based on a location of the second robotic device. At this time, the at least one processor may determine the location of the second robotic device based on sensing data associated with the battery. For example, the at least one processor may determine a trajectory of the first robotic device based on a location of the second robotic device such that the location of the second robotic device does not correspond to a location on the path of the first robotic device. The at least one processor may determine a trajectory of the first robotic device such that the trajectory of the first robotic device does not overlap with the location of the second robotic device.

[0317] Additionally, at least one processor may determine a trajectory of the first robot device by considering a trajectory of the second robot device. At this time, the at least one processor may determine the trajectory of the second robot device by receiving the trajectory of the second robot device. For example, the at least one processor may predict a position of the second robot device over time by considering the trajectory of the second robot device, and may determine the trajectory of the first robot device such that the predicted position of the second robot device does not correspond to the path of the first robot device. The at least one processor may determine the trajectory of the first robot device such that the trajectory of the first robot device does not overlap with the trajectory of the second robot device.

[0318] In addition, at least one processor may determine a trajectory of the first robot device by considering a path of the second robot device. At this time, the at least one processor may determine the path of the second robot device by predicting the path of the second robot device based on sensing data. Specifically, the at least one processor may determine the path of the second robot device by predicting a path that the second robot device will move forward based on a path that the second robot device has passed based on the sensing data. For example, the at least one processor may predict a position of the second robot device over time by considering the path of the second robot device, and may determine the trajectory of the first robot device such that the predicted position of the second robot device does not correspond to the path of the first robot device. The at least one processor may determine the trajectory of the first robot device such that the trajectory of the first robot device does not overlap with the predicted path of the second robot device.

[0319] FIG. 26 is a flowchart illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0320] Referring to FIG. 26, at least one processor may acquire sensing data from at least one sensor (S4602). At least one processor may acquire a first dynamic parameter set for controlling a first robotic device (S4602). In this case, the first dynamic parameter set may be a set of dynamic parameters (e.g., force, torque, acceleration, velocity, etc.) at a plurality of points forming a trajectory of the first robotic device.

[0321] Additionally, at least one processor can obtain a second dynamic parameter set for controlling a second robotic device based on the sensing data and the first dynamic parameter set (S4603).

[0322] At least one processor may generate a trajectory of a second robot device by considering the control of the first robot device when the first robot device is identified based on the sensing data. This is because, when the first robot device is identified based on the sensing data, interference of the first robot device may occur in the trajectory of the second robot device. That is, the at least one processor may identify the first robot device based on the sensing data, confirm a first dynamic parameter set corresponding to the trajectory of the first robot device, and obtain a second dynamic parameter set corresponding to the trajectory of the second robot device based on the first dynamic parameter set.

[0323] At least one processor may generate a trajectory of a second robotic device without considering the control of the first robotic device if the first robotic device is not identified based on the sensing data. This is because, if the first robotic device is not identified based on the sensing data, interference from the first robotic device does not occur in the trajectory of the second robotic device.

[0324] FIG. 27 is a diagram illustrating an example of a battery processing system controlling a plurality of robotic devices using an artificial intelligence engine according to various embodiments.

[0325] Referring to FIG. 27, at least one sensor included in the battery processing system can obtain sensing data and transmit it to at least one processor (e.g., a first processor, a second processor, a third processor).

[0326] At this time, at least one processor may operate to control a plurality of robotic devices based on the sensing data.

[0327] For example, the first processor can determine a first target position to which the first robotic device is to move based on sensing data and transmit the same to the first robotic device.

[0328] Additionally, the second processor may generate a first trajectory for moving the first robotic device to a first target location. In this case, the first trajectory may include a first dynamic parameter, which is a set of dynamic parameters at a plurality of points included in the trajectory.

[0329] At this time, the second processor can determine the first dynamic parameter set by considering the control status of the other robotic device.

[0330] For example, the third processor may determine a second set of dynamic parameters that constitute a trajectory of the second robotic device and transmit the same to the second processor.

[0331] The second processor can determine the first dynamic parameter set based on the first target location and the received second dynamic parameter set.

[0332] A battery processing system according to one embodiment can control a plurality of robots without interference using an artificial intelligence model, thereby improving the efficiency of robot control.

[0333] [Example of a working chamber]

[0334] The battery processing system can transport batteries into a work chamber (see reference numeral 2325 in FIG. 13) and perform a battery processing process (e.g., a dismantling process) using at least one robotic device. In this case, the work chamber can be a modular space for performing battery processing (e.g., a dismantling) tasks.

[0335] FIG. 28 is a drawing illustrating an example of a working chamber implemented in a battery processing system according to various embodiments.

[0336] Referring to FIG. 28, the battery processing system may include at least one working chamber (4810, 4820). The working chamber may have a space within it for performing battery processing operations. The working chamber may have a rectangular parallelepiped shape, but is not limited thereto. The working chamber may further include a control module (4830) for controlling the process performed within it and a display module (4840) for monitoring the process performed within it. The working chamber may further include at least one passage (4850) for spatially connecting the exterior and the interior.

[0337] The battery processing system may include a plurality of working chambers. For example, the battery processing system may include, but is not limited to, a first working chamber (4810) and a second working chamber (4820) that are connected to each other. In this case, the first working chamber (4810) and the second working chamber (4820) may be spatially connected. For example, the first working chamber (4810) and the second working chamber (4820) may be spatially connected through a passage formed between the first working chamber (4810) and the second working chamber (4820).

[0338] At this time, a transport device for transporting the battery between the plurality of work chambers may include a mobile robot that moves between the work chambers or a conveyor formed across the plurality of work chambers. For example, a mobile robot loaded with batteries may move between the first work chamber (4810) and the second work chamber (4820) by moving through the passage.

[0339] Multiple work chambers may be configured to perform different tasks. In this case, a battery that has undergone a first process (e.g., disassembling a battery cover) in a first work chamber (4810) may be transferred (using a transport device) to a second work chamber (4820), where a second process (e.g., disassembling a battery module) may be performed.

[0340] Additionally, and not limited thereto, multiple work chambers may be implemented to perform the same task.

[0341]

[0342] FIG. 29 is a drawing illustrating the internal configuration of a working chamber implemented in a battery processing system according to various embodiments.

[0343] Referring to FIG. 29, the work chamber may include at least one robotic device (4910). In this case, the at least one robotic device (4910) may be attached to the ceiling of the work chamber. Alternatively, the at least one robotic device (4910) may be attached to a mounting member that is fixedly mounted to the work chamber.

[0344] Additionally, the work chamber may be provided with at least one work space (4920) for performing battery processing operations. In this case, the work space (4920) may be located within the work area of ​​at least one robotic device (4910). The battery processing system may control a battery transport device so that a battery that has entered the work chamber is positioned in the work space (4920).

[0345] At least one robotic device (4910) may be controlled to perform a process for dismantling at least one component of a battery located on a workspace (4920). In this case, the at least one robotic device (4910) may include, but is not limited to, at least one collaborative robot or industrial robot.

[0346] For example, at least one robotic device (4910) may be controlled to perform a process of dismantling the upper cover of a battery. The battery with the cover removed may be moved to another chamber via a transport device to perform the next process. Furthermore, without limitation, at least one robotic device (4910) may be controlled to perform a process of dismantling at least one module of the battery with the cover removed. Furthermore, at least one robotic device (4910) may be controlled to perform a process of dismantling at least one cell of the battery with the module removed. In this case, at least one robotic device (4910) may be controlled to replace an end effector suitable for dismantling a module or cell. Furthermore, the dismantled component may be loaded onto a transport device, and the transport device may transport the dismantled component by moving it out of the work chamber.

[0347] Since the detailed description of the method for disassembling battery components (e.g., covers, modules, cells, etc.) using at least one of the above-described robotic devices has been described above, it will be omitted.

[0348]

[0349] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0350] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above teachings. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0351] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. An operating method of a robot system for controlling the operation of at least one robot device implemented to perform at least one task based on a control signal, By at least one processor included in the above robot system, An action of receiving a control signal directing disassembly of a first component of a battery; An operation of acquiring sensing data related to the battery from at least one sensor; An operation of identifying a predetermined point on the battery based on sensing data; An operation of estimating a pose of a battery based on a positional relationship between the identified predetermined point and the at least one robotic device; An action of adjusting the position of at least one robotic device or battery so that the positional relationship between the predetermined point and the at least one robotic device satisfies a predetermined criterion; An operation of identifying a position of at least one of a plurality of fastening members for fixing the first component based on sensing data; An operation of determining a disassembly order for the plurality of fastening members, identifying a position of a first fastening member among the plurality of fastening members, and setting the position of the battery as a first target position - if the first target position is not located within a working area of ​​the at least one robot device, adjusting the position of the battery so that the first target position is located within the working area; An operation of determining a first trajectory for a first end effector to reach a first position corresponding to the first target position; An operation of controlling the first end effector, which has reached the first position, to perform a first task of disengaging the first fastening member from the battery; An operation of setting a second target position based on the sensing data and determining a second trajectory for the second end effector to reach a second position corresponding to the second target position; An operating method comprising: an operation of controlling the second end effector, which has reached the second position, to perform a second task of separating the first part.

2. In paragraph 1, An operating method characterized in that the first target position is determined by identifying at least one of the position coordinates of the first fastening member, the direction, and the distance to the first fastening member based on the sensing data.

3. In paragraph 1, By at least one processor, An operation of identifying the positions of a plurality of fastening members based on the above sensing data; and An operating method further comprising: an operation of selecting the first fastening member among the plurality of fastening members based on a predetermined criterion.

4. In paragraph 1, An operating method characterized in that the first trajectory is generated by inputting the sensing data into an artificial intelligence model and obtaining a set of dynamic parameters for reaching the first position from at least one layer included in the artificial intelligence model.

5. In paragraph 1, The operation for controlling the performance of the above first task is: An operating method further comprising: an operation of determining whether to perform the first task based on a first condition; wherein the first condition is set based on a distance or direction between the first end effector and the first fastening member.

6. In paragraph 1, An operating method characterized in that the first task includes at least one unit action for disassembling the first fastening member, and the at least one unit action includes an action of rotating the first end effector to disassemble the first fastening member.

7. In paragraph 1, By at least one processor, An operating method further comprising: an operation of identifying whether all fastening members for securing the first component from the battery have been dismantled based on sensing data; 8. In paragraph 7, By at least one processor, An operating method further comprising: controlling at least one robotic device to release the first end effector and mount the second end effector.

9. In paragraph 1, The above first component is an operating method including a cover.

10. In paragraph 1, The above first component is an operating method including a battery module.

11. A robotic system that controls the operation of at least one robotic device implemented to perform at least one task based on a control signal, memory; and At least one processor electronically connected to said memory; At least one processor, Receive a control signal instructing dismantling of the first component of the battery; Obtain sensing data related to the battery from at least one sensor, Based on the sensing data, the position of the first fastening member for fixing the first part is identified and set as the first target position, The first end effector determines a first trajectory for reaching a first position corresponding to the first target position, Controlling the first end effector that has reached the first position to perform a first task of disengaging the first fastening member from the battery; Setting a second target position based on the above sensing data, and determining a second trajectory for the second end effector to reach a second position corresponding to the second target position, A robot system configured to control the second end effector, which has reached the second position, to perform a second task of separating the first part.

12. In paragraph 11, A robot system characterized in that the first target position is determined by identifying at least one of the position coordinates of the first fastening member, the direction, and the distance to the first fastening member based on the sensing data.

13. In paragraph 11, At least one processor, Identify the positions of multiple fastening members based on the above sensing data, A robot system further configured to select the first fastening member among the plurality of fastening members based on a predetermined criterion.

14. In paragraph 11, A robot system characterized in that the first trajectory is generated by inputting the sensing data into an artificial intelligence model and obtaining a set of dynamic parameters for reaching the first position from at least one layer included in the artificial intelligence model.

15. A computer program implemented by any one of the methods of paragraphs 1 to 10 and stored in a computer-readable storage medium.

Images