JP2005111603A - Robot and robot management device - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve a problem that various knowledge information utilized by an autonomous robot for control is not appropriately managed. <P>SOLUTION: A knowledge management device 100 manages knowledge information of each robot 200 and analyzes or recognizes information on the external environment supplied from each robot 200 through a radio network 12, utilizing knowledge information under management to generate control information of the robot 200. Each robot 200 can utilize knowledge information by accessing the knowledge management device 100 with an authentication ID supplied from the knowledge management device 100. An individual knowledge database 102 holds individual knowledge information of each robot 200 corresponding to the knowledge ID. A shared knowledge database 104 holds the knowledge information shared and utilized by each robot 200. A management table 106 holds information for specifying the knowledge information to be utilized by each robot 200. The knowledge information collected by the autonomous robot can thereby be safely managed. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a robot, and more particularly to an apparatus and system for managing knowledge information of a robot and generating control information for the robot using the knowledge information.

In 1921, Czechoslovak writer Karel Chapek presented the drama “Rossum's Universal Robot” and “automatic machinery” began to be called “robot”. Almost a century has passed since then, and various types of robots such as pet robots and industrial robots have been developed and used. In general, robots can be classified into, for example, industrial robots and service robots, and the former is active in place of manpower in many factories. Since the latter service robot is directly related to human life such as a care robot, a welfare robot, and a cleaning robot, it requires a higher level of technology than an industrial robot. For this reason, service robots are not as widespread as industrial robots. In recent years, various technologies related to the manufacture of robots have been developed, and in particular, information processing technologies have been remarkably developed. With this technological development, bipedal walking robots, pet robots, etc. have appeared one after another. As such a robot, there is one that learns based on user evaluation (Patent Document 1).
JP-A-11-175132

  In general, an autonomous robot holds information collected by itself or information registered in advance as knowledge information, makes a judgment according to the situation using the knowledge information, and acts autonomously. As computers have developed rapidly, robots are expected to develop and spread rapidly. For example, when a robot that supports household chores in households spreads to each household and performs various tasks on behalf of the household, the robot knows private information such as credit card numbers and passwords. It is expected to be stored internally as information. For this reason, such a robot may be stolen and knowledge information stored inside may be taken out.

  The present invention has been made in view of these points, and an object thereof is to provide a technique for improving the safety of robot knowledge information and a technique for efficiently handling a plurality of robots.

  One embodiment of the present invention is an apparatus that manages a plurality of robots. This device communicates with multiple robots via a network and assigns knowledge sets to multiple robots, and the knowledge information collected by multiple robots corresponds to the knowledge sets assigned to each robot. By receiving environmental information related to the surrounding environment of the robot from one of a plurality of robots and a management unit that manages the environmental information, and using the knowledge set assigned to the robot, performing predetermined processing on the environmental information An intelligent unit that generates control information necessary for controlling the robot, and a providing unit that provides the control information to the robot via a network. Thereby, since the knowledge information of a robot can be managed with the apparatus on a network, the safety | security with respect to knowledge information improves.

  The apparatus further includes a reception unit that receives state information indicating an operation state from the first robot. When the operation state of the first robot is a predetermined state, the management unit sends the information to the first robot. The assigned knowledge set may be reassigned to the second robot. As a result, the robot can be easily replaced. The “predetermined state” is, for example, a state where it is necessary to replenish energy necessary for failure or operation, and it is preferable that the “predetermined state” can be arbitrarily set according to the type and configuration of the robot.

  The knowledge set includes individual knowledge information that can be used only by the robot to which the knowledge set is assigned, and shared knowledge information that can be shared and used by a plurality of robots. Information and shared knowledge information may be classified and managed.

  The intelligence unit may generate control information by performing a predetermined process using the knowledge set in order from the environment information to which high priority is added.

  Another aspect of the present invention is a robot that acts autonomously. The robot includes an environment detection unit that outputs environment information indicating a state of the external environment of the robot, a control unit that generates first control information according to the environment information using the first knowledge set, and a second A communication unit that transmits environmental information via a network and receives the second control information from the external device, and the first control information or the second control And an operation unit that executes a predetermined operation based on the information. Thereby, since the robot does not need to incorporate the second knowledge set, the structure can be made compact.

  It should be noted that any combination of the above-described constituent elements and a conversion of the expression of the present invention between a method, an apparatus, a system, a recording medium, a computer program, etc. are also effective as an aspect of the present invention.

  According to the present invention, since the knowledge information of the robot can be stored in the management device on the network, it is possible to provide a device that manages the knowledge information safely and efficiently. In addition, since the robot can be easily exchanged by changing the correspondence between the robot and the knowledge information, an apparatus that controls a plurality of robots in a coordinated manner can be provided.

<First Embodiment>
FIG. 1 is a configuration diagram of a robot management system 10 according to the embodiment. The first robot 200a, the second robot 200b, the third robot 200c, and the fourth robot 200d (hereinafter simply referred to as “robot 200”) are connected to the knowledge management apparatus 100 via the wireless network 12 to perform communication. The robot 200 is a robot that can act autonomously, for example, based on various information related to the external environment (hereinafter simply referred to as “external environment information”) such as surrounding images, sounds, and vibrations. And an application operation is performed based on an instruction from the knowledge management apparatus 100. The “basic motion” is a basic motion such as posture maintenance and avoidance behavior. “Applied operation” is an operation that identifies a person or an object based on, for example, a video acquired as one of external environment information, and performs a conversation or operation accordingly, and requires a lot of knowledge for recognition processing. It is an operation to do.

  Although details will be described later, the robot 200 according to the present embodiment does not hold knowledge for applied operations inside, outputs external environment information to the knowledge management device 100, and is supplied from the knowledge management device 100 accordingly. Application operation is performed based on the control information. That is, the knowledge management apparatus 100 performs intelligent processing such as recognition processing, learning, and knowledge accumulation that the robot 200 should originally perform. In this way, by separating the intelligent processing from the robot 200 and mounting it on the knowledge management device 100, it is possible to prevent the robot 200 from being lost due to theft, destruction, or failure. Further, as the robot 200 becomes familiar with us, for example, personal information of users, confidential information in companies, and the like are accumulated as knowledge. In order to extract such important information, a crime such as stealing the robot 200 is also expected. Even in such a case, storing knowledge of the robot 200 in the knowledge management apparatus 100 can prevent leakage of important information.

  Further, it is not necessary to provide the robot 200 with a complicated configuration for intelligent processing, and for example, it is not necessary to mount a knowledge database having a huge size. For this reason, since the configuration of the robot 200 can be simplified, the size can be reduced, and the cost can be reduced. Even if the program that realizes intelligent processing is modified or improved so that more advanced intelligent processing can be implemented by incorporating a new theory, it is only necessary to newly write the program in the knowledge management device 100, so that maintainability is improved. high.

  Each robot 200 acquires the authentication ID 202 from the knowledge management device 100 when performing autonomous behavior in the robot management system 10. The knowledge management device 100 uses the individual knowledge information and shared knowledge information (hereinafter simply referred to as “knowledge set”) associated with the authentication ID 202 of the robot 200 to perform intelligent processing and obtain control information for applied operations. Generated for each robot 200. That is, since the knowledge management apparatus 100 performs intelligent processing using the knowledge set uniquely accumulated by each robot 200, each robot 200 can operate independently and can store knowledge accumulated in the past even in the same external environment. Different operations are possible depending on the content. Specifically, for example, the first robot 200a acting together with the user A can reflect the knowledge such as the user A's preference accumulated by acting with the user A in the intelligence process, so that the first robot 200a according to the user A's personality and preference Operation becomes possible. Further, the second robot 200b acting together with the user B can operate according to the personality and preference of the user B.

  The knowledge management device 100 does not manage such a knowledge set in association with each robot 200 in a fixed manner, but manages it in association with a knowledge ID for identifying the knowledge set. When using the knowledge set, the knowledge management apparatus 100 associates the authentication ID assigned to each robot 200 in operation with the knowledge ID. Thereby, the knowledge management apparatus 100 can perform intelligent processing on each robot 200 based on the knowledge set specified by the knowledge ID, and can generate control information. In general, in order for the robot 200 to operate, energy such as a battery or fuel is required, and for example, it cannot be operated during charging. In addition, the robot 200 cannot operate when it is broken, repaired, or inspected. In this state, according to the present embodiment, the knowledge set of the robot 200 can be easily changed. For example, instead of the robot 200 being charged, other robots 200 can perform the same operation.

  The individual knowledge database 102 holds knowledge that each robot 200 should use individually, such as user personal information. The shared knowledge database 104 holds knowledge that can be shared and used, such as patterns for pattern matching and data for speech recognition. Knowledge stored in the individual knowledge database 102 and the shared knowledge database 104 for each knowledge ID is referred to as a knowledge set. The management table 106 has a robot ID column 110, an authentication ID column 112, a knowledge ID column 114, and a status column 116. The robot ID column 110 holds information for identifying each robot 200 such as a name, an IP address, and a MAC (Media Access Control address) address of a network connection unit mounted on the robot 200. In this figure, the robot ID column 110 holds the name of each robot 200. The authentication ID column 112 holds an authentication ID. The knowledge ID column 114 holds a knowledge ID. The status column 116 holds the status of each robot 200. As the state of the robot 200, operation, failure, charging, standby, etc. are prepared in advance, and the knowledge management apparatus 100 accepts such state information from each robot 200 and updates the state column 116 each time.

  From the management table 106 in this figure, the authentication ID “AAA” is assigned to the first robot 200a, the use of the knowledge set with the knowledge ID “100” is set, and the state is “in operation”. I understand that. For example, when external environment information is received from the first robot 200a via the wireless network 12, the knowledge management device 100 refers to the management table 106 to identify a knowledge ID and associates the knowledge ID with the knowledge set. Perform intelligent processing using, and generate control information. Then, the knowledge management device 100 supplies the generated control information to the first robot 200a. Thereby, the first robot 200a performs an applied operation based on the control information. No authentication ID is assigned to the third robot 200c that is being charged or the fourth robot 200d that is being charged and is waiting.

  When a failure occurs in the second robot 200b, the second robot 200b notifies the knowledge management device 100 that a failure has occurred. In response to the notification, the knowledge management apparatus 100 refers to the management table 106 and extracts the waiting robot 200. In this figure, the knowledge management device 100 extracts the fourth robot 200d. Then, the knowledge management apparatus 100 instructs the second robot 200b to return to the base 20, for example, and deletes the authentication ID “CCC”. Further, the knowledge management apparatus 100 assigns the authentication ID “CCC” to the fourth robot 200d and instructs the start of the operation. Thereby, the fourth robot 200d can perform an intelligence process using the same knowledge set “101” as the second robot 200b.

  In this way, the robot 200 can be replaced quickly, and troubles in business operations can be minimized when a plurality of robots 200 are used to provide work and services. By making the outer shape of each robot 200 the same, even when the robot 200 is replaced with another robot 200 due to charging or failure, the user can contact without being aware that the robot 200 has been replaced. In addition, when there are a plurality of types of robots 200, the management table 106 further holds information for specifying the type of each robot 200, and the knowledge management device 100 extracts the same type when extracting the robot 200 for replacement. The robot 200 may be extracted. Of course, the knowledge management apparatus 100 may not extract the same type of robot 200.

  FIG. 2 is an internal configuration diagram of the knowledge management apparatus 100 of FIG. In terms of hardware components, each component of the knowledge management device 100 is a CPU, a memory of any computer, a program that realizes the components of the figure loaded in the memory, and a storage unit such as a hard disk that stores the program. However, it will be understood by those skilled in the art that there are various modifications in the implementation method and apparatus. Each figure to be described below shows functional unit blocks, not hardware unit configurations.

  The communication unit 130 communicates with each robot 200 via the wireless network 12. The communication unit 130 receives external environment information and state information in association with the robot ID or the authentication ID from the robot 200 and supplies the received information to the determination unit 120. In the present embodiment, the communication unit 130 receives external environment information and state information in association with the robot ID. The determination unit 120 determines whether the information supplied from the communication unit 130 is external environment information or state information. In the case of state information, the determination unit 120 supplies the state information to the robot state reception unit 126. In the case of external environment information, the determination unit 120 supplies the external environment information to the intelligence unit 122.

  The robot state reception unit 126 supplies the state information to the management unit 128 in association with the robot ID. The management unit 128 updates the management table 106 based on the received state information. When the received state information indicates a state that needs to be replaced with another robot 200 such as “failing” or “charging”, for example, the management unit 128 refers to the management table 106 and reads “ ”Is extracted. Then, the management unit 128 notifies the related robot 200 via the communication unit 130 that the authentication ID is removed from the robot 200 to be exchanged and the authentication ID is assigned to the extracted robot 200. Thereby, the management unit 128 can automatically perform the replacement process of the robot 200 based on the state information supplied from each robot 200.

  In another example, the operation of each robot 200 is scheduled, and the management unit 128 may perform the replacement process of each robot 200 based on the schedule. The timing at which each robot 200 is replaced in the management unit 128 and the procedure for extracting the robot 200 for replacement may be arbitrary depending on the service realized by the robot management system 10 in FIG. The management unit 128 may manage the knowledge set associated with the knowledge ID based on the management table 106 and appropriately determine the robot 200 that uses the knowledge set.

  The intelligence unit 122 specifies the knowledge ID by referring to the management table 106 using the authentication ID as a key. And the intelligence part 122 performs the intelligence process based on external environment information using the specified knowledge set. For example, when the external environment information is a video and a person included in the video is specified, matching is performed with a person image held in the shared knowledge database 104 to specify the person. In addition, if the image cannot be matched with the person image held in the shared knowledge database 104, the intelligence unit 122 generates control information for asking a name of the person, and transmits the control information to the robot 200 via the communication unit 130. The robot 200 that has received this control information asks the person a question, and supplies the name to the knowledge management apparatus 100 as external environment information. Then, the intelligence unit 122 supplies the acquired name and the person image to the storage processing unit 124 as knowledge information to be newly registered.

  The storage processing unit 124 registers the knowledge information supplied from the intelligence unit 122 in the individual knowledge database 102 or the shared knowledge database 104. The storage processing unit 124 determines the type of knowledge information, and registers it in the individual knowledge database 102 in association with the knowledge ID, for example, in the case of personal information such as the telephone number or address of the user who has contacted the robot 200. If the knowledge information is other than personal information, the storage processing unit 124 registers the knowledge information in the shared knowledge database 104. For example, the storage processing unit 124 may hold a table in which the type of knowledge information is associated with the registration destination, and register knowledge information in the individual knowledge database 102 or the shared knowledge database 104 based on the table.

  Thereby, in the case of individual information to be stored in the individual knowledge database 102, the intelligence unit 122 can accumulate learning for each knowledge set. In the case of shared information to be stored in the shared knowledge database 104, the intelligence unit 122 can accumulate learning based on external environment information collected by all the robots 200 under the management of the knowledge management apparatus 100.

  The intelligence unit 122 can simultaneously perform intelligence processing for a plurality of robots 200 based on each knowledge set. However, since the number of intelligent processes that can be executed simultaneously by the intelligent unit 122 is limited, the intelligent processes are sequentially performed for the unprocessable parts. Depending on the contents of the intelligent processing, there are some that need to be processed quickly. Therefore, a priority order may be set for each intelligent processing content, and the intelligence unit 122 may perform the intelligent processing from the intelligent processing content with a high priority. Specifically, the robot 200 transmits external environment information to the knowledge management apparatus 100 in association with priorities. And the intelligence part 122 performs an intelligence process sequentially from the external environment information with the high priority. Thereby, when the robot 200 encounters the fire scene, the intelligence unit 122 can preferentially process the external environment information.

  FIG. 3 is an internal configuration diagram of the robot 200 of FIG. The environment information detection unit 212 inputs, for example, analog information such as video, audio, smell, vibration, and digital information such as a computer, a mobile phone, infrared communication, and radio waves as external environment information. The environment information detection unit 212 includes sensors for vision, hearing, smell, taste, and touch, and supplies information detected by the sensors to the control unit 214 as external environment information.

  The control unit 214 includes a basic operation control unit 216 and an application operation control unit 218. The basic operation control unit 216 controls the operation unit 224 to perform the basic operation based on the basic knowledge held in the basic knowledge database 222. The basic knowledge may be knowledge for performing posture maintenance, avoidance action against an obstacle, and emergency action, for example. In short, the basic knowledge is knowledge necessary for realizing an action to be naturally performed in an environment in which the robot 200 acts. The applied operation control unit 218 controls the operation unit 224 based on the control information supplied from the knowledge management device 100. In addition, the control unit 214 supplies external environment information to the knowledge management apparatus 100 via the communication unit 220. The communication unit 220 transmits the external environment information to the robot ID column 110 in association with the authentication ID held in the authentication ID storage unit 228.

  The robot ID storage unit 210 holds a robot ID for identifying the knowledge management apparatus 100. The robot ID may be registered in the knowledge management apparatus 100 in advance. The communication unit 220 communicates with the knowledge management device 100 using the robot ID held in the robot ID storage unit 210. For example, the robot ID may be an IP address in TCP / IP, and is used to identify the robot 200 in communication with the knowledge management apparatus 100.

  When the authentication ID is received from the knowledge management apparatus 100, the communication unit 220 writes the authentication ID in the authentication ID storage unit 228 and instructs the control unit 214 to start autonomous behavior. Thereby, the basic operation control unit 216 starts the basic operation based on the external environment information. In addition, the control unit 214 transmits the external environment information to the knowledge management apparatus 100 in association with the authentication ID held in the authentication ID storage unit 228.

  The operation unit 224 may be configured such that the robot outputs to the external environment, such as a moving mechanism, an arm mechanism, a hand mechanism, a speaker, a monitor display, and data transmission of the robot 200, for example. The state detection unit 226 detects the state of the robot 200 such as various mechanisms in the operation unit 224 and transmits the detection result to the knowledge management apparatus 100 via the communication unit 220.

<Second Embodiment>
FIG. 4 is a configuration diagram of a robot management system 50 according to the second embodiment. The robot management system 50 is a system that is connected to a plurality of robot management systems and allows knowledge information to be shared by these robot management systems.

  The first robot management system 52 a, the second robot management system 52 b, and the third robot management system 52 c (hereinafter simply referred to as “local management system 52”) are communicably connected to the main knowledge management device 350 via the network 14. Has been. Each local management system 52 includes a plurality of robots 200 and a local knowledge management device 300, and the robot 200 and the local knowledge management device 300 are communicably connected via the wireless network 12. The internal configuration of each robot 200 is the same as the internal configuration of the robot 200 described with reference to FIG.

  FIG. 5 is an internal configuration diagram of the local knowledge management device 300 of FIG. Configurations denoted by the same reference numerals as those already described in the figure are substantially the same in function and operation as those already described. The following description will focus on points that differ from the functions in the configuration already described. The intelligence unit 310 determines whether the external environment information supplied from the determination unit 120 can be intelligently processed using the knowledge sets held in the individual knowledge database 102 and the shared knowledge database 104. When it is determined that the intelligence process cannot be performed, the intelligence unit 310 instructs the knowledge acquisition unit 302 to acquire knowledge. The knowledge acquisition unit 302 requests knowledge information from the main knowledge management device 350 and acquires necessary knowledge information. Then, the intelligence unit 310 further performs intelligence processing based on the acquired knowledge information.

  When the intelligence unit 310 newly learns knowledge information, the intelligence unit 310 supplies the learning data to the learning data transmission unit 304. The learning data transmission unit 304 transmits the learning data to the main knowledge management device 350. Thereby, knowledge information newly learned by the local knowledge management device 300 can be stored in the main knowledge management device 350. Thereby, the knowledge information accumulated every day in the local management system 52 connected to the network 14 of FIG. 4 can be shared.

  FIG. 6 is an internal configuration diagram of the main knowledge management apparatus 350 of FIG. The shared knowledge database 354 holds shared knowledge information. The communication unit 130 receives external environment information from the local knowledge management device 300 and supplies it to the intelligence unit 352. The intelligence unit 352 performs intelligence processing based on the knowledge information held in the shared knowledge database 354 and generates control information. Then, the communication unit 130 transmits the control information generated by the intelligence unit 352 to the local knowledge management device 300. As a result, even if the intelligence processing cannot be performed by the knowledge set that the local knowledge management apparatus 300 has uniquely, the intelligence processing can be performed based on the shared knowledge database 354 that holds an enormous amount of knowledge. As described above, the hierarchical knowledge structure enables efficient knowledge information management.

  The learning data reception unit 356 receives the knowledge information newly accumulated from the local knowledge management device 300 as learning data and supplies it to the storage processing unit 358. The storage processing unit 358 newly stores knowledge information in the shared knowledge database 354 based on the learning data. Thereby, knowledge information is sequentially accumulated and updated in the shared knowledge database 354.

  FIG. 7 is a diagram illustrating an example of a processing sequence among the robot 200, the local knowledge management device 300, and the main knowledge management device 350 in FIG. The robot 200 inputs data from various sensors in order to input external environment information or state information (S10). Then, the input data from the sensor is converted into a format that can be used for intelligent processing (S12). The control unit 214 in FIG. 3 determines whether or not to perform a basic operation based on the external environment information (S14). When the basic operation is performed (Y in S14), the basic operation is instructed to the operation unit 224 in FIG. 3 (S16), and the operation unit 224 in FIG. 3 operates accordingly (S18). If it is determined in step 14 that the basic operation is not performed (N in S14), the control unit 214 transmits external environment information or state information to the local knowledge management device 300 (S15). That is, the external environment information and the state information are transmitted from the robot 200 to the local knowledge management device 300.

  The local knowledge management device 300 receives external environment information or status information. And the determination part 120 of FIG. 5 determines whether the intelligence process was requested according to external environment information (S20). When the intelligent processing is requested (Y of S20), the intelligent unit 310 of FIG. 5 determines whether the intelligent processing is possible with the knowledge set held in the individual knowledge database 102 and the shared knowledge database 104 of FIG. 5 (S24). ). If intelligent processing is possible with the local knowledge set (Y in S24), the intelligent unit 310 determines an optimal behavioral solution (S25), and transmits corresponding control information to the robot 200 via the communication unit 130 in FIG. (S26). Here, the “behavior solution” is associated with control information for each robot, and the intelligence unit 310 outputs control information corresponding to the action solution to the learning data transmission unit 304 in accordance with the robot to be controlled.

  If new knowledge information is generated in step 26, it is registered, that is, learned as knowledge information (S28), and the learning data is transmitted to the main knowledge management device 350 (S30). The learning data receiving unit 356 in FIG. 6 receives the learning data, and the storage processing unit 358 in FIG. 6 registers the learning data as knowledge information in the shared knowledge database 354, that is, learns (S44). Further, as necessary, the storage processing unit 358 arranges the knowledge by discarding the knowledge information held in the shared knowledge database 354 (S46).

  Further, the local knowledge management device 300 organizes the knowledge information learned in the individual knowledge database 102 or the shared knowledge database 104 (S32). If it is determined in step 24 that the intelligence processing cannot be performed with the knowledge sets held in the individual knowledge database 102 and the shared knowledge database 104 in FIG. 5 (N in S24), the local knowledge management apparatus 300 uses the external environment information as the main information. It transmits to the knowledge management apparatus 350 (S40).

  The intelligence unit 352 of FIG. 6 refers to the shared knowledge database 354 of FIG. 6 in order to intelligently process the external environment information (S41), and finds a behavior solution candidate (S42). Then, the shared knowledge database 354 transmits the behavior solution to the local knowledge management device 300 via the communication unit 130 of FIG. 6 (S43). If it is not an intelligent process in step 20 (N in S20), the determination unit 120 in FIG. 5 outputs the state information to the robot state reception unit 126 in FIG. 5, and the management unit 128 in FIG. The process is executed (S22) and, for example, an authentication ID or the like is transmitted to the corresponding robot 200.

  The present invention has been described based on the embodiments. This embodiment is an exemplification, and it will be understood by those skilled in the art that various modifications can be made to combinations of the respective constituent elements and processing processes, and such modifications are also within the scope of the present invention. is there.

1 is a configuration diagram of a robot management system according to a first embodiment. FIG. It is an internal block diagram of the knowledge management apparatus of FIG. It is an internal block diagram of the robot of FIG. It is a block diagram of the robot management system which concerns on 2nd Embodiment. It is an internal block diagram of the local knowledge management apparatus of FIG. It is an internal block diagram of the main knowledge management apparatus of FIG. It is a figure which shows an example of the sequence of the process between the robot in FIG. 4, a local knowledge management apparatus, and the main knowledge management apparatus.

Explanation of symbols

  10 robot management system, 12 wireless network, 14 network, 20 base, 50 robot management system, 52 local management system, 100 knowledge management device, 102 individual knowledge database, 104 shared knowledge database, 106 management table, 120 judgment unit, 122 intelligence Unit, 124 storage processing unit, 126 robot state reception unit, 128 management unit, 130 communication unit, 200 robot, 202 authentication ID, 210 robot ID storage unit, 212 environmental information detection unit, 214 control unit, 216 basic operation control unit, 218 Application operation control unit, 220 communication unit, 222 basic knowledge database, 224 operation unit, 226 status detection unit, 228 authentication ID storage unit, 300 local knowledge management device, 302 knowledge acquisition unit, 304 learning data transmission , 310 intelligence unit, 350 main knowledge management apparatus, 352 intelligence unit, 354 shared knowledge database, 356 learning data receiving unit, 358 storage unit.

Claims (3)

A communication unit for communicating with a plurality of robots via a network;
A management unit that assigns knowledge sets to the plurality of robots, and manages the knowledge information collected by the plurality of robots in association with the knowledge sets assigned to the robots;
The environment information related to the surrounding environment of the robot is received from any of the plurality of robots, and the robot is controlled by performing a predetermined process on the environment information using a knowledge set assigned to the robot. An intelligence unit that generates the necessary control information;
A providing unit for providing the control information to the robot via the network;
A robot management apparatus comprising: A reception unit that receives state information indicating an operation state from the first robot;
When the operation state of the first robot is a predetermined state, the management unit reassigns the knowledge set assigned to the first robot to the second robot. Item 2. The robot management device according to Item 1. A robot that acts autonomously,
An environment detection unit that outputs environmental information indicating the state of the external environment of the robot;
A control unit that generates first control information according to the environment information using a first knowledge set;
A communication unit that transmits the environment information to the external device that generates the second control information using the second knowledge set, and receives the second control information from the external device;
An operation unit that performs a predetermined operation based on the first control information or the second control information;
A robot characterized by comprising:

Images