JP2007226634A - Person status recognition device, method, program, robot and life support system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To recognize a status of a person regardless of an instruction from the person. <P>SOLUTION: This person status recognition device has: a physical sensor 51 comprising a plurality of sensors monitoring the person; a logical sensor 52 specifying contents of a plurality of elements for recognizing the status of the person on the basis of information from the physical sensor 51; and a recognition part 53 recognizing the status of the person on the basis of a combination of contents of the respective elements. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a technique for recognizing a person's situation and a life support system that supports a user's life using the recognition result.

2. Description of the Related Art Conventionally, robots that assist, support, and care for users' lives in ordinary households, pet robots, and the like have been developed.
For example, Japanese Patent Laying-Open No. 2005-103678 (Patent Document 1) has a home mode and an answering mode, and during execution of the home mode, monitoring corresponding to a dynamic environment in which the user is at home. A robot that performs an operation and performs a monitoring operation corresponding to a static environment where the user is not at home when the answering machine mode is executed is disclosed. In Patent Literature 1, the robot includes a voice processing unit that recognizes the user's voice, and the operation mode is switched according to the voice of the user who has been voice-recognized.

Japanese Patent No. 3558222 (Patent Document 2) has a parameter indicating the recognition result of an external environment such as vision and hearing, and an internal state such as instinct and emotion, and executes an action according to the parameter value. A robot is disclosed.
Japanese Patent Laying-Open No. 2002-2331979 (Patent Document 3) discloses a pet robot that can provide various services to the user by switching the operation mode to be executed according to the number of applause by the user. ing.

JP 2005-103678 A Japanese Patent No. 3558222 Japanese Patent Laid-Open No. 2002-2331979

By the way, in recent years, in the field of robot development, one of the major goals has been to realize a living space in which humans and robots can naturally communicate with each other and where humans and robots can coexist comfortably. For this purpose, it is required that the robot spontaneously recognizes what kind of situation the person is in without any instruction from the person and takes a response according to the recognition result.
However, with conventional robots, it is difficult to recognize the situation in which the user is placed without a specific instruction from the user, such as “applauding” or “calling”. There was a problem that I could not.

  The present invention has been made to solve the above problem, and includes a person situation recognition apparatus, a method, a program, and a person situation recognition apparatus capable of recognizing the situation of a person regardless of whether there is an instruction from the person. It is an object of the present invention to provide a robot capable of taking action according to a recognized situation and a life support system.

In order to solve the above problems, the present invention employs the following means.
The present invention provides a person situation comprising monitoring means for monitoring a person and a person situation recognition means for recognizing the situation of the person based on information from the monitoring means without obtaining a predetermined instruction from the person. A recognition device is provided.

  According to such a configuration, for example, information about a person acquired by a monitoring unit such as a video camera or a microphone is transferred to the person situation recognition unit. The person situation recognition means recognizes the person situation based on the information from the monitoring means without obtaining a predetermined instruction from the person. This makes it possible to recognize the situation of the person regardless of whether there is a specific instruction such as “applause” or “call” from the person.

  In the above-described person situation recognition apparatus, the person situation recognition means includes an element content identification means for identifying the contents of a plurality of elements for recognizing a person situation based on information from the monitoring means, and each of the elements Recognizing means for recognizing the situation of the person based on the combination of the contents.

According to such a configuration, for example, information about a person acquired by a monitoring unit such as a video camera or a microphone is transferred to an element content specifying unit in the person situation recognition unit. In the element content specifying means, the contents for a plurality of elements are specified based on the information from the monitoring means. For example, a plurality of elements effective for recognizing a person's situation are detected from image information or the like in which a person's appearance is simply captured, and the contents of each element are specified. For example, contents such as “kitchen” and “standing” are specified for each element such as “location” and “person's posture”.
When the content of each element is specified in this way, the situation of the person is recognized by the recognition means based on the combination of the content of each element. For example, the situation of a person “meal” is recognized from a combination of the contents of each element “element: place” — “content: dining”, “element: posture of person” — “content: sitting”. In this way, the information from the monitoring means is classified into each element effective for recognizing the person's situation, and the person's situation is recognized based on the contents of each element. It becomes possible to recognize the situation of a person.

  The present invention includes a monitoring means for monitoring a person, an element content specifying means for specifying the contents of a plurality of elements for recognizing the situation of the person based on information from the monitoring means, There is provided a person situation recognition device comprising recognition means for recognizing the person situation based on a combination.

  According to such a configuration, for example, information about a person acquired by a monitoring unit such as a video camera or a microphone is transferred to the element content specifying unit. In the element content specifying means, the contents for a plurality of elements are specified based on the information from the monitoring means. For example, contents such as “kitchen” and “standing” are specified for each element such as “location” and “person's posture”. When the content of each element is specified in this way, the situation of the person is recognized by the recognition means based on the combination of the content of each element. For example, the situation of the person “meal” is recognized from the combination of the contents of the elements “element: place” — “content: dining”, “element: posture of person” — “content: sitting”. This makes it possible to recognize the situation of the person regardless of whether there is a specific instruction such as “applause” or “call” from the person.

  The above-described person situation recognition apparatus has information storage means in which a person situation is associated with the contents of each element, and the recognition means includes the contents of each element specified by the element contents specification means. It is good also as recognizing the said person's condition by acquiring from the said information storage means the condition of the person who corresponds to the combination.

  According to such a configuration, it is possible to efficiently recognize a person's situation and to improve recognition accuracy. In addition, the recognition accuracy can be further improved by providing a function for updating the information storage means by learning.

  In the above-described person situation recognition apparatus, the recognition unit may recognize the person situation with reference to the past situation history of the person.

  According to such a configuration, since the current situation of the person is recognized with reference to the past situation history of the person, it is possible to further improve the accuracy of the situation recognition of the person.

  The present invention provides an element content specifying process for specifying the contents of a plurality of elements for recognizing a person's situation based on information from a monitoring means for monitoring the person, and a combination of the contents of the elements. There is provided a person situation recognition method comprising a recognition process for recognizing a person situation.

  The present invention is based on element content specifying processing for specifying the contents of a plurality of elements for recognizing a person's situation based on information from monitoring means for monitoring a person, and on the basis of a combination of the contents of each of the elements Provided is a person situation recognition program for causing a computer to execute a recognition process for recognizing a person situation.

The present invention provides a robot that responds to the situation of a person recognized by the person situation recognition apparatus described above.
The present invention provides a life support system including the above-described person situation recognition device and the above-described robot.

According to the person situation recognition apparatus, person situation recognition method, and person situation recognition program of the present invention, there is an effect that the situation of the user can be recognized regardless of whether there is an instruction from the user.
According to the robot and the life support system of the present invention, it is possible to take an action suitable for the user's situation.

  Hereinafter, an embodiment of a life support system according to the present invention will be described with reference to the drawings.

[First Embodiment]
The life support system according to the first embodiment of the present invention will be described below. The life support system according to the present embodiment is intended for a relatively small living space such as a residence, and includes the robot 1 and the person situation recognition device 50 as main components. Moreover, in this embodiment, since living spaces, such as a house, are used as a place of life support, the person (user) who receives the service by the robot 1 is limited to a specific person.

FIG. 2 is a front view of a robot according to an embodiment of the present invention, and FIG. 3 is a left side view of the robot shown in FIG.
2 and 3, the main body of the robot 1 includes a head 2, a chest 3 that supports the head 2 from below, a right arm 4a provided on the right side of the chest 3, and a chest 3 Left arm portion 4 b provided on the left side of the chest, a waist portion 5 connected below the chest portion 3, a skirt portion 6 connected below the waist portion 5, and a leg portion 7 connected below the skirt portion 6. And are provided.

One omnidirectional camera 11 is provided near the top of the head 2. A plurality of infrared LEDs 12 are arranged on the ring at predetermined intervals along the outer periphery of the omnidirectional camera 11.
In the vicinity of the center of the front surface of the head 2, as shown in FIG. 2, the front camera 13 for imaging the front is one on the right side when viewed from the front, and the microphone 14 is one on the left side when viewed from the front. Is provided.

  One monitor 15 is provided near the center of the front surface of the chest 3. One ultrasonic distance sensor 16 for detecting a person is provided above the monitor 15. One power switch 17 is provided below the monitor 15. Above the ultrasonic distance sensor 16, two speakers 18 are provided one on each side. Further, as shown in FIG. 3, the back of the chest 3 is provided with a school bag portion 33 that can store luggage. The school bag 33 is provided with an opening / closing door 33a that can be rotated around a hinge provided at the top. As shown in FIG. 2, one shoulder switch 19 that functions as a man-machine interface is provided on each of the left and right shoulders of the chest 3. For the shoulder switch 19, for example, a touch sensor is employed.

  A multi-joint structure is adopted for the right arm portion 4a and the left arm portion 4b. In the right arm portion 4a and the left arm portion 4b, side switches 20 are provided in the vicinity of the connection portion with the chest portion 3 to detect the pinching of a body or an object and stop the movement of the arm. As shown in FIG. 2, a handshake switch 21 that functions as a man-machine interface is built in the palm of the right arm 4a. For the side switch 20 and the handshake switch 21, for example, a pressure sensor is employed.

  In the vicinity of the center of the front surface of the waist 5, one ultrasonic distance sensor 22 for detecting a person is provided on each side. Below these ultrasonic distance sensors 22, a sensor region 24 in which a plurality of infrared sensors 23 are arranged is provided. These infrared sensors 23 are for detecting an obstacle or the like in the lower front of the robot body 1. As shown in FIGS. 2 and 3, a total of four microphones 25 for detecting the direction of the sound source are provided below the waist 5 on the front and back sides, one on each side. As shown in FIG. 3, one handle portion 26 used for lifting the main body is provided on each of the left and right sides of the waist portion 5. The handle 26 is a recess so that the operator's hand can be inserted.

  Below the front surface of the skirt portion 6, a total of three infrared sensors 27 for detecting a step are provided in the center and on the left and right. As shown in FIG. 3, a charging connector 28 is provided on the back surface of the skirt portion 6.

  As shown in FIG. 2, one infrared sensor 29 for detecting a lateral distance is provided on the front surface of the leg portion 7 on the left and right sides. These infrared sensors 29 are mainly used for level difference detection. As shown in FIG. 3, a hook 30 for fixing the position of the robot body 1 to the charging station is provided on the back surface of the leg portion 7. The leg portion 7 is a carriage provided with traveling wheels 31 and four ball casters 32.

Such a robot 1 has a configuration capable of autonomously moving in a work space by supplying power from a battery built in the robot body, and coexists with a human being as a work space indoors. For example, it is used to provide various services for assisting / supporting / care for the life of a user such as the owner or operator of the robot 1 in a general home.
Therefore, in addition to the conversation function for realizing the conversation with the user, the robot 1 has a function of watching the user's action, assisting the user's action, and acting with the user. Such a function is realized by, for example, a control device including a microcomputer built in the main body of the robot 1. The above-described various cameras and various sensors are connected to the control device, and by acquiring image information from the cameras and sensor detection information from the sensors and executing various programs based on these information, Implement various functions. The shape of the robot 1 is not limited to the shape shown in FIG. 2 and FIG. 3, and various shapes such as those imitating animals for pets can be adopted.

  As shown in FIG. 1, the person situation recognition device 50 includes various physical sensors 51 as monitoring means for monitoring a person and the situation of the person based on information from the physical sensor without obtaining a predetermined instruction from the person. And a person status recognition unit 60 for recognizing. The person situation recognizing unit 60, based on information from the physical sensor 51, a logic sensor (element content identifying means) 52 for identifying the contents of a plurality of elements for recognizing the person situation, An information storage unit (information storage unit) 53 associated with the contents of the elements, and a recognition unit (recognition unit) 54 that recognizes the situation of the person based on the combination of the contents of the elements are provided.

  The physical sensor 51 is, for example, a video camera that captures the state of a person from various angles. In this embodiment, the physical sensor 51 is installed on the ceiling or wall of a residence and captures the state of the person from above or from the side. 55 or a camera provided on the robot 1 that captures the facial expression or posture of a person. Specifically, the front camera 13, the ultrasonic distance sensor 16, the ultrasonic distance sensor 22, and the like provided in the robot 1 function as the physical sensor 51. Moreover, the robot 1 has a clock function, and outputs time information to a logic sensor 52 described later together with various information acquired by these sensors. The physical sensor 51 and the logical sensor 52 are connected via a wireless or wired communication line.

  The logical sensor 52 has a function of receiving information on a person detected by the physical sensor 51. The logic sensor 52 includes a microcomputer, for example, and specifies the contents of a plurality of elements for recognizing a person's situation based on information received from the physical sensor 51. The element here means that each element is performed for a short time or instantaneously and does not have a clear purpose in itself.

  Examples of the element include “location”, “movement situation”, “posture”, “hand state”, “face state”, and the like, as shown in FIGS. Further, as shown in FIG. 4, the contents corresponding to “place” include “bedroom”, “living room”, “kitchen”, “telephone area”, “toilet”, etc., and corresponds to “movement situation”. The contents include “still”, “walking”, “start walking”, “stop”, “walk fast”, “slow walk”, “one direction”, “return”, etc. Corresponding contents are “Stand”, “Sitting on a chair”, “Sitting on the floor”, “Sleeping on the back”, “Standing up”, “Sitting on the floor”, “Sitting on a chair”, “Lie down” Etc. The contents corresponding to the “hand state” include the position of the hand and the movement of the hand. Specifically, the position of the hand is “down”, “side of the ear”, “above the head”, “ “Still” and “motion”, “up / down motion”, “left / right motion” and the like can be cited as motions. The contents corresponding to the “face state” include the position of the face and the action of the face. Specifically, the positions of the face include “front”, “down diagonally”, “up diagonally”, “upper”. ”,“ Below ”,“ horizontal ”, and the like, and the face motions include“ still ”,“ with motion ”, and the like. In addition, about these contents, it is an example and is not restricted to these.

The logic sensor 52 can specify the content of “location” by the following method.
For example, since the installation position of the camera 55 provided on the ceiling or the wall is known, the position of the person is specified by specifying the camera 55 that is the transmission source of the image in which the person is captured. It is possible. In addition, when the robot 1 has a function of detecting its own position, a direction to a person in the vicinity, and a function of detecting a distance, the position information of the robot from the robot 1 and the distance and direction to the person are set. By receiving the information, the position of the person can be specified from the information.

  The logic sensor 52 can specify the content of “movement situation” by the following method. For example, it is determined whether a person is moving or stationary by taking a difference between image frames taken by a camera. Further, by continuously tracking the position of the person with the camera 55, the moving speed and the moving route are tracked. Note that the above-described method is also an example for specifying the movement status, and is not limited to this method.

  The logic sensor 52 can specify the contents of “posture”, “hand state”, and “face state” by the following method. For example, the posture of the person, the state of the hand, and the state of the face are specified by performing image processing on an image acquired by the front camera 13 included in the robot 1. For example, with respect to “posture”, whether the person is standing or sitting can be determined based on the height of the person detected by the front camera 13. Sleeping on the back is performed by recognizing the whole body and the upper body based on image information from the camera 55 installed on the ceiling. Further, regarding “standing up”, “sitting on the floor”, and “sitting on a chair”, each motion can be recognized by using an acceleration sensor together.

  For the hand state and the face state, the hand position is extracted by performing skin color detection from the image information, and the hand position is specified in the positional relationship with the head. As for the face state, facial features such as eyes and nose are extracted by image processing, and the face direction and the like are specified based on these eye and nose states.

  In the case where the robot 1 has a function for specifying the posture of the person, the hand state, and the face state, by receiving the posture information, the hand state information, and the face state information from the robot 1, It is good also as specifying the posture of a person. For hand movement detection and the like, the technique disclosed in Japanese Patent Application Laid-Open No. 2005-215927 can be employed.

  The information storage unit 53 stores the situation of the person and the contents of each element in association with each other. For example, as shown in FIG. 5, “Dining” for “Place”, “Still” for “Movement Status”, “Sitting in a Chair” for “Position”, “State of Hand” On the other hand, the combination of “up and down movement” and “face state” “obliquely and with movement” is associated with the personal situation “meal”. In this way, combinations of the contents of each element are associated with each situation such as “cooking”, “calling”, “reading”, “sleeping”, etc. .

  The recognition unit 54 recognizes the situation of the person by acquiring the situation of the person that matches the combination of the contents of each element specified by the logic sensor 52 from the information storage unit 53, and sends the recognition result via the communication line. Output to the robot 1. The robot 1 has, for example, a database in which each operation program is associated with the person's situation, reads the operation program corresponding to the person's situation with reference to this database, and executes the operation program. Thus, it is possible to realize a response suitable for the situation of the person.

Next, the operation of the life support system having the above-described configuration will be described.
Here, as an example, a case where a person is eating will be described.
First, image information acquired from a physical sensor 51 including a plurality of cameras 55 provided in the house, the front camera 13 of the robot 1, the ultrasonic distance sensor 16, the ultrasonic distance sensor 22, and the like are communication lines. Is input to the logic sensor 52 through the image processing, the logic sensor 52 performs image processing on these pieces of image information, so that “location”, “movement situation”, “posture”, “hand state”, “face condition” The contents of each element composed of “state” and the like are specified. As a result, the logic sensor 52 uses “dining” as the content of “location”, “still” as the content of “moving state”, and “sitting in a chair” as the content of “posture”. "Up and down movement" is specified as "face state", and "downwardly in front and with movement" is specified as "face state". This identification result is output to the recognition unit 54.

  The recognition unit 54 acquires from the information storage unit 53 the situation of the person that matches the combination of the contents of each element described above. As a result, the status of the person “meal” is acquired. When recognizing that the person's situation is “meal”, the recognizing unit 54 transmits the recognition result to the robot 1 via the communication line. As a result, an operation program corresponding to “meal” is executed by the control device of the robot 1, so that a response suitable for the situation of the person is performed.

  As described above, according to the life support system according to the present embodiment, the content of each element for recognizing the situation of the person is specified based on the person image acquired by the physical sensor 51, and this Since the person situation is recognized based on the combination of element contents, the person situation can be recognized very easily. In addition, when the robot 1 performs a response according to the recognition result, it is possible to act independently regardless of whether there is an instruction from the user.

  In the above-described embodiment, the time concept is not considered when recognizing the person's situation, but the person's situation may be recognized including the time concept. In addition, when the temporal concept is included, the situation of the person can be recognized more easily, so that the specification regarding other elements may be omitted. For example, when a person is in a situation of “stopping around the telephone for about 2 minutes”, it can be determined that the telephone is “on the phone”. On the other hand, when determining “on the phone”, “hand state” and “face condition” are not effective determination materials. In such a case, three elements are identified: a “place” element “periphery of the telephone”, a “movement situation” element “stop”, and a “time” element “2 minutes or longer”. By doing so, it is possible to fully recognize the situation of “on the phone”.

In addition, people usually eat “sitting in a chair” in “dining” during the “morning”, “noon”, and “evening” time periods, so “location”, “posture”, and “time period” The person state “meal” may be recognized based on three effective elements.
In this way, it is easier to identify a person by specifying only the elements that are effective for recognizing the person's situation instead of specifying all of the five elements shown in FIGS. It becomes possible to recognize the situation.

  Further, the information storage unit 54 may be configured to be updateable at any time. For example, a place where a person stays continuously for a long time, a place visited many times a day, a place visited at a certain time, a place visited at a substantially constant interval, etc. It is possible to further improve the accuracy of the person's state recognition by registering whether or not.

  For example, when the robot 1 detects that a person has stayed at a certain place for a long time, the robot 1 is programmed to ask the person “What are you doing?” The information storage unit 54 may be updated by associating the answer from the person corresponding to the question with the contents of each element at this time and storing the information in the information storage unit 54.

  Specifically, when a person stays in the living room for a long time, the robot 1 asks the person “What are you doing?”. If there is an answer “watching TV” in response to this question, the answer “watching TV” and the contents of each element currently specified by the logic sensor 52, for example, “location” "Living" as "Contents", "Standing" as "Moving situation", "Sleeping on sofa" as "Position", "Still" as "Hand state", "Slanting and moving as" Face state " A combination of the contents of “Yes” may be stored in the information storage unit 54 in association with each other.

  Further, when information is stored in the information storage unit 54, the robot 1 may confirm to the person whether the situation of the person and the contents of each element are appropriate. In this way, it is possible to store more accurate information in the information storage unit 54 by checking. For example, in order to determine the situation of “watching TV”, “hand state” is not included in the effective elements, so when a person gives an instruction “delete hand state”, “ A person situation of “watching television” is recognized from a combination of contents of elements other than “hand state”.

  Furthermore, the information stored in the information storage unit 54 described above may be customized for each person. Thus, by being customized, it is possible to carry out situation recognition according to the behavioral characteristics of the person, and it is possible to further improve the accuracy of situation recognition. In this case, for example, the person may be identified by collating the face by image processing, or the person carries the IC tag 56 on which the person identification information is recorded. It is also possible to easily identify a person by reading 56 information.

  Furthermore, the person situation recognition device may recognize the current situation based on the past history (situation) of the person. Thus, by recognizing the current situation based on the past history, it becomes possible to recognize the situation of the person with higher accuracy.

[Second Embodiment]
Next, a life support system according to a second embodiment of the present invention will be described with reference to the drawings. The life support system according to the present embodiment is not intended for a relatively narrow indoor living space such as a residence, as in the first embodiment described above, and a relatively large number of unspecified persons come and go. A wide range, for example, theme parks, shopping streets, museums, and the like are the target areas for living support. For this reason, the number of robots 1 provided in the life support system according to the present embodiment and the number of physical sensors 51 are also set according to the action range.

Furthermore, in this embodiment, the information stored in the information storage unit 53 is different from that in the first embodiment described above. In other words, in the first embodiment described above, the life support was performed in a form in close contact with the life of a person in a narrow living space, but in this embodiment, an unspecified number of people existing within a relatively wide range. Recognize the status of a person who needs assistance from the robot 1 or the like, for example, “I am lost,” “I am trying to enter a restricted area”, “I am calling a robot” .
Hereinafter, in the life support system according to the present embodiment, the same components as those in the first embodiment described above are denoted by the same reference numerals, description thereof will be omitted, and different components will be described.

FIG. 6 shows the contents of the information storage unit 53 according to the present embodiment. In the present embodiment, the elements handled by the logic sensor 52 are “place”, “movement state”, “posture”, “hand state”, and “face state” as described above. Examples of the situation of the person include “get lost”, “call a robot”, and “entry into a restricted area”.
As shown in FIG. 6, there are a plurality of combinations of the contents of the elements corresponding to the person action “get lost”.
For example, as the “movement situation”, the content for one element “going back and forth in the same place” is associated with the person situation “getting lost”. In addition, the combination of the contents of the three elements, “Place in front”, “Moving situation” as “Still”, and “Face state” as “Front and up”, and “Lost” It is attached.

Regarding the situation of “calling a robot”, the contents of three elements are “stationary” as “movement situation”, “moving left and right over the head” as “hand state”, and “robot direction” as “face state”. The combination is associated with the situation of “calling a robot”.
In addition, regarding the situation of “entry into the restricted area”, there are a plurality of combinations of element contents as follows.
One is a combination of the contents of two elements, “location of prohibited area” as “location” and “stationary” as “movement situation”, and is associated with the situation of “entry into the prohibited area”. One is “place of prohibited area” as “place”, “still” as “movement situation”, “still in front of face” as “hand state”, and “front” as “face state”. A combination of element contents is associated with a situation of “entry into a restricted area”.

  For each person shown in the image information or the like sent from the physical sensor 51, the logical sensor 52 has each element “location”, “movement state”, “posture”, “hand state”, “face state”. And the contents of these elements are output to the recognition unit 54 in association with the identification information of the person. As for the person identification information, when each person carries an IC tag 56 storing the identification information, the person may be identified by reading the identification information from the IC tag 56, or When such identification information is not assigned, the logical sensor 52 automatically assigns individual identification information for each person to identify each person.

  When the content corresponding to each element of each person is specified by the logic sensor 52, the recognition unit 54 acquires a situation that matches the combination of these contents from the information storage unit 53. At this time, this time recognition is not performed for a person who does not have a corresponding situation. As a result, for a person whose information storage unit 53 has a situation that matches the combination of the contents of each element, the identification information of the person and the situation of the person are associated and output to the robot 1. At this time, since the person status recognition apparatus recognizes the position of each robot 1, it transmits a recognition result or the like to the robot 1 that is closest to the target person.

The robot 1 that has received the recognition result and the person identification information from the person situation recognition device 50 finds out a desired person from among an unspecified number of persons based on the person identification information, and the recognition result for this person is obtained. Take appropriate action.
For example, if the recognition result is “get lost”, the robot 1 asks “Where do you want to go?”, Etc., and guides the route to the current location or destination according to the answer to this question. Provide service.
If the recognition result is “call a robot”, the robot 1 asks “How did you do it?” And the like, and the person's request is obtained by executing a dialogue or an action according to an answer to this question. Take action that suits your needs.
Furthermore, when the recognition result is “entry into the restricted area”, the robot 1 takes an action that prevents entry, such as “do not enter there”. , Ensure the safety of the person.

  As described above, the life support system according to the present embodiment can recognize a person's behavior even in a relatively wide area such as a theme park or an arcade street, and can provide a response suitable for the person's behavior. It is possible to take.

In the first embodiment and the second embodiment described above, the person situation recognition device is installed separately from the robot 1. However, the present invention is not limited to this configuration example. It is good also as a structure by which the apparatus 50 is mounted.
Further, in the first embodiment and the second embodiment described above, processing by hardware is assumed as the person situation recognition device, but it is not necessary to be limited to such a configuration. For example, a configuration in which software is separately processed based on detection signals from the respective physical sensors is also possible. In this case, the person situation recognition apparatus includes a main storage device such as a CPU and a RAM, and a computer-readable recording medium on which a program for realizing all or part of the above processing is recorded. Then, the CPU reads out the program recorded in the storage medium and executes information processing / calculation processing, thereby realizing processing similar to that of the above-described person situation recognition device.
Here, the computer-readable recording medium means a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Alternatively, the computer program may be distributed to the computer via a communication line, and the computer that has received the distribution may execute the program.

  Note that, as described above, instead of processing by software, the person situation recognition device is configured by two hardware units, that is, the logic sensor 52 and the recognition unit 54, so that, for example, specification processing of content corresponding to each element Can be executed in parallel, and even if one of the logic sensors becomes useless, it can be backed up by the remaining logic sensors.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes design changes and the like within a scope not departing from the gist of the present invention.

It is the block diagram which showed typically the schematic structure of the life assistance system which concerns on the 1st Embodiment of this invention. It is the figure which showed an example of the front view of the robot shown in FIG. FIG. 3 is a left side view of the robot shown in FIG. It is the figure which showed an example of the kind of element classified by the logic sensor which concerns on the 1st Embodiment of this invention, and the content in each element. It is the figure which showed an example of the information accumulate | stored in the information storage part which concerns on the 1st Embodiment of this invention. It is the figure which showed an example of the information accumulate | stored in the information storage part which concerns on the 2nd Embodiment of this invention.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Robot 50 Person situation recognition apparatus 51 Physical sensor 52 Logic sensor 53 Information storage part 54 Recognition part 60 Person situation recognition part

Claims (9)

A monitoring means for monitoring a person;
A person situation recognition device comprising: person situation recognition means for recognizing the person situation based on information from the monitoring means without obtaining a predetermined instruction from the person. The person situation recognition means
Element content specifying means for specifying the contents of a plurality of elements for recognizing a person's situation based on information from the monitoring means;
Recognizing means for recognizing the situation of the person based on a combination of the contents of each of the elements. A monitoring means for monitoring a person;
Element content specifying means for specifying the contents of a plurality of elements for recognizing a person's situation based on information from the monitoring means;
Recognizing means for recognizing the situation of the person based on a combination of the contents of the elements. Comprising information storage means in which the situation of the person and the content of each element are associated with each other;
The said recognition means recognizes the said person's condition by acquiring the condition of the person who corresponds to the combination of the content of each said element specified by the said element content specification means from the said information storage means. Item 4. The person situation recognition device according to Item 3.   The person recognition apparatus according to claim 2, wherein the recognition unit recognizes the situation of the person with reference to a past situation history of the person. An element content identification process for identifying the contents of a plurality of elements for recognizing a person's situation based on information from a monitoring means for monitoring the person;
A recognition process for recognizing the situation of the person based on a combination of the contents of the elements. Element content identification processing for identifying the contents of a plurality of elements for recognizing a person's situation based on information from a monitoring means for monitoring a person;
A person situation recognition program for causing a computer to execute a recognition process for recognizing the situation of the person based on a combination of contents of the elements.   The robot which respond | corresponds according to the condition of the person recognized by the person condition recognition apparatus in any one of Claims 1-3. The person situation recognition device according to any one of claims 1 to 5,
A life support system comprising the robot according to claim 8.

Images