Device and method for determining image analysis policy

Abstract

This server device may comprise: a transceiver for transmitting / receiving data to / from at least one robot device; and a controller for controlling the transceiver and selecting an image analysis policy for control of the robot device, wherein the controller collects at least one of state information of a wireless network connected to the robot device, meta information of the robot device, and task characteristic information of the robot device, and determines the image analysis policy on the basis of the collected information.

Description

Device and method for image analysis policy decision making

[0001] The present invention relates to a device and method for image analysis policy decision making.

[0002] Wireless communication systems utilize various Radio Access Technologies (RATs), including LTE, LTE-A, and WiFi, and 5G is included. 5G encompasses three key requirements: (1) Enhanced Mobile Broadband (eMBB), (2) Massive Machine Type Communication (mMTC), and (3) Ultra-reliable and Low Latency Communications (URLLC). Some use cases may require optimization across multiple areas, while others may focus on just one Key Performance Indicator (KPI). 5G supports these diverse use cases in a flexible and reliable manner.

[0003] eMBB extends far beyond basic mobile internet access, encompassing rich interactive tasks, cloud computing, and augmented reality media and entertainment applications. Data is a key driver of 5G, and dedicated voice services may not be the first to emerge in the 5G era. In 5G, voice is expected to be handled as an application, simply using the data connection provided by the communication system. The primary drivers of increased traffic volume are the increasing size of content and the growing number of applications requiring high data rates. Streaming services (audio and video), interactive video, and mobile internet connectivity will become more prevalent as more devices connect to the internet. Many of these applications require always-on connectivity to push real-time information and notifications to users. Cloud storage and applications are rapidly growing on mobile communication platforms, applicable to both work and entertainment. Cloud storage is a particular use case driving the growth of uplink data rates. 5G is also used for remote work in the cloud, requiring significantly lower end-to-end latency to maintain a superior user experience when tactile interfaces are used. Entertainment, for example, cloud gaming and video streaming are other key factors driving the demand for mobile broadband. Entertainment is essential on smartphones and tablets, regardless of location, including in highly mobile environments such as trains, cars, and airplanes. Another use case is augmented reality and information retrieval for entertainment, where augmented reality requires extremely low latency and instantaneous data volumes.

[0004] Additionally, one of the most anticipated 5G use cases concerns mMTC, the ability to seamlessly connect embedded sensors across all sectors. The number of potential IoT devices is projected to reach 20.4 billion by 2020. Industrial IoT is one area where 5G will play a key role, enabling smart cities, asset tracking, smart utilities, agriculture, and security infrastructure.

[0005] URLLC encompasses new services that will transform industries through ultra-reliable, low-latency links, such as remote control of critical infrastructure and self-driving vehicles. Reliability and latency are essential for smart grid control, industrial automation, robotics, and drone control and coordination.

[0006] Next, we will look at several use cases in more detail.

[0007] 5G can complement fiber-to-the-home (FTTH) and cable-based broadband (or DOCSIS) by delivering streams rated at hundreds of megabits per second to gigabits per second. These high speeds are required to deliver TV at resolutions beyond 4K (6K, 8K, and beyond), as well as virtual and augmented reality. Virtual reality (VR) and augmented reality (AR) applications include near-immersive sports events. Certain applications may require specialized network configurations. For example, for VR games, game companies may need to integrate their core servers with the network operator's edge network servers to minimize latency.

[0008] Automotive is expected to be a significant new driver for 5G, with numerous use cases for in-vehicle mobile communications. Passenger entertainment, for example, demands simultaneous high-capacity and high-mobility mobile broadband. This is because future users will expect high-quality connectivity regardless of their location or speed. Another automotive application is an augmented reality dashboard, which overlays information on what the driver sees through the windshield, identifying objects in the dark and informing the driver about their distance and movement. In the future, wireless modules will enable communication between vehicles, the exchange of information between vehicles and supporting infrastructure, and between vehicles and other connected devices (e.g., devices accompanying pedestrians). Safety systems can guide drivers on alternative courses of action to ensure safer driving, reducing the risk of accidents. The next step will be remotely controlled or self-driving vehicles, which will require highly reliable and fast communication between different self-driving vehicles and between vehicles and infrastructure. In the future, self-driving cars will perform all driving tasks, leaving drivers to focus solely on traffic anomalies that the vehicles themselves cannot detect. The technological requirements for self-driving cars will require ultra-low latency and ultra-high-speed reliability, increasing traffic safety to levels unattainable by humans.

[0009] Smart cities and smart homes, often referred to as "smart societies," will be embedded with dense wireless sensor networks. A distributed network of intelligent sensors will identify conditions for cost- and energy-efficient maintenance of cities or homes. A similar setup can be implemented for each home. Temperature sensors, window and heating controllers, burglar alarms, and appliances will all be connected wirelessly. Many of these sensors typically have low data rates, low power, and low cost. However, for example, real-time HD video may be required for certain types of devices for surveillance purposes.

[0010] The consumption and distribution of energy, including heat and gas, are becoming increasingly decentralized, requiring automated control of distributed sensor networks. Smart grids interconnect these sensors using digital information and communication technologies to collect and act on information. This information can include the behavior of suppliers and consumers, enabling smart grids to improve efficiency, reliability, economic efficiency, sustainable production, and automated distribution of fuels like electricity. Smart grids can also be viewed as another low-latency sensor network.

[0011] The health sector has numerous applications that can benefit from mobile communications. Telecommunications systems can support telemedicine, which provides clinical care in remote locations. This can help reduce distance barriers and improve access to health services that are otherwise unavailable in remote rural areas. It can also be used to save lives in critical care and emergency situations. Mobile-based wireless sensor networks can provide remote monitoring and sensors for parameters such as heart rate and blood pressure.

[0012] Wireless and mobile communications are becoming increasingly important in industrial applications. Wiring is expensive to install and maintain. Therefore, the potential to replace cables with reconfigurable wireless links presents an attractive opportunity for many industries. However, achieving this requires wireless connections to operate with similar latency, reliability, and capacity to cables, while simplifying their management. Low latency and extremely low error rates are new requirements for 5G connectivity.

[0013] Logistics and freight tracking are important use cases for mobile communications, enabling the tracking of inventory and packages anywhere using location-based information systems. Logistics and freight tracking typically require low data rates but wide coverage and reliable location information.

[0014] Wireless communication systems are multiple access systems that support communication with multiple users by sharing available system resources (e.g., bandwidth, transmission power, etc.). Examples of multiple access systems include code division multiple access (CDMA), frequency division multiple access (FDMA), time division multiple access (TDMA), orthogonal frequency division multiple access (OFDMA), single carrier frequency division multiple access (SC-FDMA), and multi-carrier frequency division multiple access (MC-FDMA).

[0015] Sidelink (SL) refers to a communication method that establishes a direct link between user equipment (UE), allowing voice or data to be exchanged directly between terminals without going through a base station (BS). SL is being considered as a solution to address the burden on base stations due to rapidly increasing data traffic.

[0016] V2X (vehicle-to-everything) refers to a communication technology that exchanges information with other vehicles, pedestrians, and infrastructure-based objects through wired / wireless communication. V2X can be divided into four types: V2V (vehicle-to-vehicle), V2I (vehicle-to-infrastructure), V2N (vehicle-to-network), and V2P (vehicle-to-pedestrian). V2X communication can be provided through the PC5 interface and / or Uu interface.

[0017] Meanwhile, as more and more communication devices demand greater communication capacity, the need for improved mobile broadband communication compared to existing Radio Access Technology (RAT) is emerging. Accordingly, communication systems that consider reliability and latency-sensitive services or terminals are being discussed. Next-generation wireless access technologies that take into account improved mobile broadband communication, massive Machine Type Communication (MTC), and Ultra-Reliable and Low Latency Communication (URLLC) can be referred to as new RAT (new radio access technology) or NR (new radio).

[0018] Meanwhile, ensuring high-level robot control / operation in diverse environments requires robot motion teaching (programming) for each environment, which can be time-consuming depending on the teaching scope. Currently, motion-based robotic arms have standardized their installation workspaces to reduce teaching time for each environment and utilize sensors specific to each arm part to enable response to hazardous situations. However, this approach has limitations, such as limited installation space and increased robotic arm costs due to the use of multiple sensors.

[0019] Recently, with the advancement of AI technology, image analysis and object recognition rates have improved dramatically, and methods for using these as the main sensors of robots to perform robot control / operations are being proposed, and AI-based vision recognition is also being utilized / verified as a main sensor in the robot industry.

[0020] The present invention proposes a method or device for performing robot control by selecting local control or central control or combining the two depending on the state of a wireless network.

[0021] The problems to be solved by the present invention are not limited to the problems to be solved above, and other problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0022] A server device is proposed, comprising: a transceiver for transmitting and receiving data with at least one robot device; and a controller for controlling the transceiver and selecting an image analysis policy for controlling the robot device, wherein the controller can: collect at least one of status information of a wireless network connected to the robot device, meta information of the robot device, and task characteristic information of the robot device, and determine an image analysis policy based on the collected information.

[0023] A method for determining an image analysis policy is proposed, the method being performed by a server device including a transceiver for transmitting and receiving data with at least one robot device; and a controller for controlling the transceiver and selecting an image analysis policy for controlling the robot device, the method including a step of collecting at least one of status information of a wireless network connected to the robot device, meta information of the robot device, and task characteristic information of the robot device; and a step of determining an image analysis policy based on the collected information.

[0024] A robot device is proposed, wherein the robot device includes a transceiver for transmitting and receiving data with a server device; and a controller for controlling the transceiver, wherein the controller: receives an image analysis policy from the server device or receives a control command for the robot according to the image analysis policy, and performs analysis or processing on an image captured around the robot device according to the image analysis policy, wherein the image analysis policy can be determined based on at least one of status information of a wireless network connected to the robot device, meta information of the robot, and task characteristic information of the robot.

[0025] A method for receiving an image analysis policy is proposed, the method being performed by a robot device including a transceiver for transmitting and receiving data with a server device; and a controller for controlling the transceiver, the method comprising: receiving an image analysis policy from the server device or receiving a control command for the robot device according to a result of image analysis or processing based on the image analysis policy; and performing analysis or processing on an image captured around the robot device according to the image analysis policy, wherein the image analysis policy can be determined based on at least one of status information of a wireless network connected to the robot device, meta information of the robot, and task characteristic information of the robot.

[0026] A non-volatile computer-readable medium storing a computer program configured to perform the method for image analysis policy decision making described above is proposed.

[0027] The above problem solving methods are only some of the embodiments of the present invention, and various embodiments reflecting the technical features of the present invention can be derived and understood by a person having ordinary knowledge in the relevant technical field based on the detailed description of the present invention described below.

[0028] The present invention has the following effects.

[0029] The present invention can control a robot in the field through local control, central control, or a combination of the two depending on the wireless network status.

[0030] In addition, the present invention can perform robot control that maintains ultra-low latency by determining a control method according to a wireless network status.

[0031] The effects according to the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art to which the present invention pertains from the detailed description of the invention below.

[0032] The accompanying drawings, which are included as part of the detailed description to aid in understanding the present invention, provide embodiments of the present invention and, together with the detailed description, explain the technical idea of ​​the present invention.

[0033] Figure 1 shows the Non-Roaming 5G System Architecture disclosed in 3GPP TS 23.501.

[0034] Figure 2 illustrates NRF, NRF registration procedures, etc.

[0035] Figure 3 shows the overall 5G NR architecture.

[0036] Figure 4 is a block diagram illustrating an image analysis policy decision process according to the present invention.

[0037] Figure 5 illustrates a wireless network environment for robot control according to the present invention.

[0038] Figure 6 illustrates a block diagram of a server device (100) and a robot device (200) of the present invention.

[0039] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the attached drawings. Regardless of the drawing numbers, identical or similar components will be given the same reference numbers, and redundant descriptions thereof will be omitted. The suffixes "module" and "part" used for components in the following description are assigned or used interchangeably only for the convenience of writing the specification, and do not in themselves have distinct meanings or roles. In addition, when describing the embodiments disclosed in this specification, if it is determined that a specific description of a related known technology may obscure the gist of the embodiments disclosed in this specification, a detailed description thereof will be omitted. In addition, the attached drawings are only intended to facilitate easy understanding of the embodiments disclosed in this specification, and the technical ideas disclosed in this specification are not limited by the attached drawings, and should be understood to include all modifications, equivalents, and substitutes included in the spirit and technical scope of the present invention.

[0040] Terms that include ordinal numbers, such as first, second, etc., may be used to describe various components, but the components are not limited by these terms. These terms are used solely to distinguish one component from another.

[0041] 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 intervening. Conversely, when a component is referred to as being "directly connected" or "connected" to another component, it should be understood that there are no other components intervening.

[0042] Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0043] In this application, terms such as “include” or “have” are intended to specify the presence of a feature, number, step, operation, component, part or combination thereof described in the specification, but should be understood not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts or combinations thereof.

[0044] In various embodiments of the present disclosure, “ / ” and “,” should be interpreted as indicating “and / or.” For example, “A / B” can mean “A and / or B.” Furthermore, “A, B” can mean “A and / or B.” Furthermore, “A / B / C” can mean “at least one of A, B, and / or C.” Furthermore, “A, B, C” can mean “at least one of A, B, and / or C.”

[0045] In various embodiments of the present disclosure, "or" should be interpreted as meaning "and / or." For example, "A or B" can include "only A," "only B," and / or "both A and B." In other words, "or" should be interpreted as meaning "additionally or alternatively."

[0046] The following technologies can be used in various wireless communication systems, such as CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), and SC-FDMA (single carrier frequency division multiple access). CDMA can be implemented with wireless technologies such as UTRA (universal terrestrial radio access) or CDMA2000. TDMA can be implemented with wireless technologies such as GSM (global system for mobile communications) / GPRS (general packet radio service) / EDGE (enhanced data rates for GSM evolution). OFDMA can be implemented with wireless technologies such as IEEE (Institute of Electrical and Electronics Engineers) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802-20, and E-UTRA (evolved UTRA). IEEE 802.16m is an evolution of IEEE 802.16e, providing backward compatibility with systems based on IEEE 802.16e. UTRA is part of UMTS (universal mobile telecommunications system). 3GPP (3rd generation partnership project) LTE (long term evolution) is a part of E-UMTS (evolved UMTS) that uses E-UTRA (evolved-UMTS terrestrial radio access), employing OFDMA in the downlink and SC-FDMA in the uplink.LTE-A (advanced) is an evolution of 3GPP LTE.

[0047] 5G NR, the successor to LTE-A, is a new clean-slate mobile communications system featuring high performance, low latency, and high availability. 5G NR can utilize all available spectrum resources, from low-frequency bands below 1 GHz, mid-frequency bands between 1 GHz and 10 GHz, and high-frequency (millimeter wave) bands above 24 GHz.

[0048] For clarity of explanation, the description will focus on LTE-A or 5G NR, but the technical ideas according to one embodiment of the present disclosure are not limited thereto.

[0049] Figure 1 illustrates the Non-Roaming 5G System Architecture disclosed in 3GPP TS 23.501. As illustrated, the 5G Core Network includes various Network Functions (NFs), such as the Access and Mobility Management Function (AMF), the User Plane Function (UPF), and the Session Management Function (SMF). Network functions can be implemented as network elements on dedicated hardware, software instances running on dedicated hardware, or virtualized functions instantiated on a suitable platform. For example, they can run on cloud infrastructure.

[0050] Table 1 below discloses the NFs of the 5G Core Network and their functions.

[0051] NFfunctionAMF (Access and Mobility Management Function) RAN CP interface (N2) termination NAS (N1) termination, NAS encryption and integrity protection. Registration management. Connection management. Accessibility management. Mobility management. Lawful interception (for AMF events and interfaces to LI systems). Provides SM message transfer between UE and SMF. Transparent proxy for SM message routing. Access authentication and access authorization. Provides SMS message transfer between UE and SMSF. SEAF (Security Anchor Function). Interacts with AUSF and UE, receives intermediate key generated as a result of UE authentication process. In case of USIM based authentication, AMF retrieves security material from AUSF. Functions for non-3GPP access network. User Plane Function (UPF) Anchor point for Intra- / Inter-RAT mobility (if applicable). External PDU session point of interconnection to data network. Packet routing and forwarding. Packet inspection. User plane part of policy rule enforcement (e.g. gating, redirection, traffic shaping). Lawful blocking (UP collection). Traffic usage reporting. QoS processing for user plane (e.g. UL / DL rate enforcement, reflected QoS marking in DL). Uplink traffic validation (QoS flow mapping in SDF). Transport level packet marking in uplink and downlink. Downlink packet buffering and downlink data notification triggering. Sends and forwards one or more "end markers" to the source NG-RAN node. Session Management Function (SMF) Session Management Functions UE IP address allocation and management; Selection and control of UP functions; Traffic shaping in UPF. Configure and enforce routing policies to route traffic to appropriate destinations and control some of the QoS for downlink data notifications.PCF (Policy Control Function) Policy Control Function Supports a unified policy framework for managing network behavior. Provides and enforces policy rules to control plane functions. Accesses subscription information related to policy decisions in the Unified Data Repository (UDR). Unified Data Management (UDM) Unified Data Management Generates 3GPP AKA authentication credentials. Processes user identification. Grants access rights based on subscription data (e.g., roaming restrictions). Manages UE's Serving NF registration. Supports service / session continuity. For example, maintains SMF / DNN allocation for ongoing sessions. Supports MT-SMS forwarding. Lawful Interception Function Subscription Management. SMS Management. AUSF (Authentication Server Function) Supports the Authentication Server Function (AUSF) specified by SA WG3. AF (Application Function) Application influence on traffic routing. Access to network exposure functions. Interacts with the policy framework for policy control.

[0052] Additionally, there are various reference points such as N2, N3, and N4, which signify interfaces between different functions or nodes in the network architecture.

[0053]

[0054] Figure 2(a) illustrates the Network Repository Function (NRF). The NRF serves as a central registration center (registration center) for all core network components. As illustrated in Figure 2, the NRF is connected to all 5G Core components in the HPLMN and to other NRFs in the VPLMN via the N27 interface. The NRF performs registration functions for the AMF, AUSF, UDM, UDR, PCF, SMF, NSSF, and BSF, respectively.

[0055] Figure 2(b) illustrates the process by which NFs (NF service consumers) other than NRF register with the NRF. For detailed procedures, refer to 3GPP TS 29.510.

[0056]

[0057] Figure 3 shows the overall 5G NR architecture.

[0058] The gNB node provides NR User Plane and Control Plane protocol terminations to the user equipment (UE) side and is connected to the 5GC (5G core network) through the NG interface.

[0059] The ng-eNB node provides E-UTRA User Plane and Control Plane protocol terminations to the terminal side and is connected to the 5GC via the NG interface.

[0060] As shown, the terminal is connected to the air base station (gNB, or ng-eNB) via the air interface.

[0061]

[0062] Figure 4 is a block diagram illustrating an image analysis policy decision process according to the present invention.

[0063] The present invention proposes a method for a robot to stream workspace information to a remote server in a wireless communication network environment capable of building a multi-access edge computing (MEC) platform based on mobile communication technologies such as 5G and private 5G by utilizing AI (artificial intelligence)-based vision recognition, and for the server to analyze / recognize the information and control / operate a robot arm.

[0064] Image analysis based on the MEC platform can collect status information such as overall network load and data transmission / reception speed through the MEC platform, and can utilize this to select an image analysis policy (S11) and an image analysis model algorithm (S12). As a result, the MEC server (100) or robot controller (130) can perform robot arm control / operation based on the image analysis results. The image analysis policy selection (S11) and the image analysis model algorithm selection (S12) can be performed by the MEC server (100), but are not limited thereto.

[0065] Image analysis policy selection (S11) determines a real-time situational awareness image analysis strategy policy. The MEC server (100) determines a real-time situational awareness image analysis strategy policy based on the overall network load, data transmission / reception speed, and robot meta-information (robot local performance, model, version, etc.) through the MEC platform. The image analysis strategy policy according to the present invention is broadly divided into three types based on the resource target used, and a detailed operation policy / algorithm is set for each policy to determine the image analysis strategy policy for the target robot.

[0066] a) Server: Performs image analysis and object recognition using the resources of the MEC server.

[0067] b) Robot & Server: Image analysis and object recognition are performed by utilizing robot and MEC server resources in parallel, based on the overall network and MEC server resources, robot analysis performance, etc. Split computing-based image analysis algorithms optimized for resource-constrained, edge computing environments can be used.

[0068] c) Robot: Image analysis and object recognition are performed on the robot based on the resources of the entire network and MEC server, robot analysis performance, etc. Image analysis based on limited resources and early exit algorithms can be used.

[0069] Image Analysis Model Algorithm Selection (S12) selects an algorithm for image analysis and object recognition of the streamed workspace (i.e., the space where the robot is deployed). Accordingly, the robot or MEC server uses the selected image analysis and object recognition algorithm to analyze or recognize captured images of the robot's surroundings.

[0070]

[0071] Figure 5 illustrates a wireless network environment for robot control according to the present invention.

[0072] The robot (200) can communicate with the image analysis service of the MEC platform or a device (100) therefor based on the 3GPP N1, N2, N3, and N6 network interfaces via a 5G core network, such as a private 5G network. If the image analysis service is implemented as a device, the device (100) may be an MEC server (100). Specific details for each network interface are as follows.

[0073] - N1: Network interface for transmitting Robot (200, UE) information to AMF

[0074] - N2: Control Plane (control flow) interface for network traffic control flow between gNB (base station) and 5G Core network.

[0075] - N3: User Plane (data) interface for user data transmission between gNB (base station) and 5G Core network.

[0076] - N6: Interface between UPF and DN (Data Network)

[0077] The MEC server (100) may include an image analysis policy decision device (110), an image analyzer (120), and a robot controller (130).

[0078] The image analysis policy decision unit (110) performs image analysis policy selection (S11) described with reference to FIG. 4. The image analysis policy decision unit (110) is connected to the MEC platform via an interface for network information collection, and can collect network information from the MEC platform. The network information may include the load, speed, etc. of the entire network. In addition, the image analysis policy decision unit (110) can collect meta information of the robot (200), such as information related to the performance of the robot, the model name, the software or hardware version, etc. The meta information of the robot includes data that can determine the identification and performance of the robot. This may be composed of different types of data depending on the robot manufacturer or robot type (MCU usage, Desktop Raspberry PI Robot ARM, etc.).

[0079] Network information and robot metadata are used to select image analysis policies. For a detailed explanation of image analysis policy decisions, please refer to the explanation previously provided with reference to Figure 4.

[0080] The image analyzer (120) acquires an image of the workspace where the robot (200) performs its work through the robot (200) or an image sensor related to the robot, and performs analysis, processing, etc. on the acquired image. However, the image analyzer (120) does not perform image analysis or processing if the MEC server (100) is determined not to participate in image analysis according to the image analysis policy of the image analysis policy decision device (110).

[0081] The robot controller (130) can generate commands for robot control based on the results of image analysis or processing, and transmit them to the robot (200) via the 5G core network.

[0082] Meanwhile, although a single robot (200) is depicted in FIG. 5, multiple robots (200) may be controlled by the MEC server (100) according to the present invention via the MEC platform. When multiple robots (200) are subject to control, the image analysis policy decision unit (110) may determine an image analysis policy for each robot.

[0083] In addition, when multiple robots (200) are subject to control, network information, robot meta information, as well as data or task characteristics of each robot are used to select image analysis policy decisions.

[0084] If a robot's tasks must be performed sequentially and require sequential data handling, the task is inevitably sensitive to delay or latency. Therefore, it may be preferable to perform image analysis or processing on the server side, which typically boasts superior image analysis or processing performance. However, this consideration is only a partial example, and image analysis policy decisions can be made based on various information described above (such as network conditions, robot metadata, and the characteristics of the robot's task).

[0085]

[0086] Figure 6 illustrates a block diagram of a server device (100) and a robot device (200) according to the present invention.

[0087] The server device (100) includes a transceiver (1001) for transmitting and receiving data with the robot device (200) and a controller (1002) for controlling the transceiver. In addition, the server device (100) may include a memory (1003) for generating and storing information, such as meta information and task characteristics of the robot device (200), related to the present invention.

[0088] Additionally, the memory (1003) can store information about the image analysis policy.

[0089] The controller (1002) can collect at least one of status information of a wireless network connected to the robot device (200), meta information of the robot device (200), and task characteristic information of the robot device (200). In addition, the controller (1002) can determine an image analysis policy based on at least one of the collected status information, meta information, or task characteristic information. The status information of the wireless network can include the load or data transmission / reception speed of the wireless network.

[0090] Here, the image analysis policy may include any one of a first policy in which analysis or processing of images captured around the robot device (200) is performed solely by the robot device (200), a second policy in which analysis or processing is performed solely by the server device (100), or a third policy in which analysis or processing is performed through collaboration between the robot device (200) and the server device (100). In this case, the image analysis algorithm used according to the first policy may be different from the image analysis algorithm used according to the third policy.

[0091] The controller (1002) can transmit the determined image analysis policy to the robot device (200).

[0092] Meanwhile, in order for the controller (1002) to perform analysis or processing on images captured around the robot device (200), acquisition of a target image is required. The controller (1002) can receive images captured around the robot device (200) in real time by streaming via the wireless network. The images captured around the robot device (200) can be acquired by an image sensor installed in the robot device (200) or an image sensor connected to the robot device (200).

[0093]

[0094] The robot device (200) may include a transceiver (2001) for transmitting and receiving data with the server device (100); and a controller (2002) for controlling the transceiver (2001). In addition, the robot device (200) may include a memory (2003) for generating and storing information, such as meta information and task characteristics of the robot device (200), related to the present invention.

[0095] The controller (2002) can receive an image analysis policy from the server device (100) or receive a control command for the robot device (200) according to the received image analysis policy.

[0096] The controller (2002) can perform analysis or processing on images captured around the robot device (200) according to the received image analysis policy.

[0097] Meanwhile, although the server device (100) or the robot device (200) is not described with reference to FIG. 6, it can perform the operations or functions described with reference to FIGS. 4 and 5 described above.

[0098] Additionally, the server device (100) of the present invention is configured with a plurality of server devices and can perform the operations of the server device according to the present invention. This can be introduced for the purpose of distributing the processing load of the server devices.

[0099]

[0100] In addition, as another aspect of the present invention, the operation of the proposal or invention described above may be implemented, performed or executed by a “computer” (a comprehensive concept including a system on chip (SoC) or a (micro) processor, etc.), or may be provided as a code or a computer-readable storage medium storing or including the code or a computer program product, and the scope of the present invention may be extended to the code or the computer-readable storage medium storing or including the code or the computer program product.

[0101]

[0102] The detailed description of the preferred embodiments of the present invention disclosed above has been provided to enable those skilled in the art to implement and practice the present invention. While the above description has been made with reference to preferred embodiments of the present invention, those skilled in the art will appreciate that various modifications and variations of the present invention, as defined by the following claims, are possible. Accordingly, the present invention is not intended to be limited to the embodiments disclosed herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. As a server device, A transceiver for transmitting and receiving data with at least one robotic device; and A controller for controlling the transceiver and selecting an image analysis policy for controlling the robotic device, The above controller: Collect at least one of status information of a wireless network connected to the robot device, meta information of the robot device, and task characteristic information of the robot device, A server device that determines an image analysis policy based on the information collected above.

2. In paragraph 1, the image analysis policy is: Analysis or processing of images captured around the robot device, including one of a first policy performed solely by the robot device, a second policy performed solely by the server device, or a third policy performed in collaboration between the robot device and the server device. Server device.

3. In the second paragraph, the image analysis algorithm used according to the first policy is different from the image analysis algorithm used according to the third policy. Server device.

4. In the second paragraph, the status information of the wireless network includes the load or data transmission / reception speed of the wireless network. Server device.

5. In the second paragraph, the controller: Transmitting the image analysis policy determined above to the robot device, Server device.

6. In paragraph 1, the controller: Receive real-time streaming of images taken of the surroundings of the above robotic device, Server device.

7. A method for determining an image analysis policy, the method being performed by a server device including a transceiver for transmitting and receiving data with at least one robot device; and a controller for controlling the transceiver and selecting an image analysis policy for controlling the robot device. A step of collecting at least one of status information of a wireless network connected to the robot device, meta information of the robot device, and task characteristic information of the robot device; and A method comprising a step of determining an image analysis policy based on the collected information.

8. In paragraph 7, the image analysis policy is: Analysis or processing of images captured around the robot device, including one of a first policy performed solely by the robot, a second policy performed solely by the server device, or a third policy performed in collaboration between the robot device and the server device. method.

9. In paragraph 8, the image analysis algorithm used according to the first policy is different from the image analysis algorithm used according to the third policy. method.

10. In paragraph 8, the status information of the wireless network includes the load or data transmission / reception speed of the wireless network. method.

11. In paragraph 8, comprising a step of transmitting the determined image analysis policy to the robot device; method.

12. In paragraph 8, A step of receiving streaming images captured from the surroundings of the robotic device in real time, method.

13. As a robotic device, A transceiver for transmitting and receiving data with a server device; and including a controller for controlling the above transceiver, The above controller: Receive an image analysis policy from the server device, or receive a control command for the robot device according to the image analysis policy, Perform analysis or processing on images captured around the robot device according to the above image analysis policy, A robot device, wherein the image analysis policy is determined based on at least one of status information of a wireless network connected to the robot device, meta information of the robot, and task characteristic information of the robot.

14. A method for receiving an image analysis policy, wherein the method is performed by a robot device including a transceiver for transmitting and receiving data with a server device; and a controller for controlling the transceiver. A step of receiving an image analysis policy from the server device or receiving a control command for the robot device according to an image analysis or processing result based on the image analysis policy; and A step of performing analysis or processing on an image captured around the robot device according to the image analysis policy, A method wherein the image analysis policy is determined based on at least one of status information of a wireless network connected to the robot device, meta information of the robot, and task characteristic information of the robot.

15. A non-volatile computer-readable medium storing a computer program configured to perform a method according to any one of claims 7 to 12.

Images