JP5366048B2 - Information provision system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an information providing system which predicts behavior of a person to provide information. <P>SOLUTION: The information providing system 100 includes a central control device 10, an LRF (Laser Range Finder) 12 and a robot 14. A topic which is recommendation information on stores in a shopping mall, and a moving trajectory (P_Tx) which represents a comprehensive behavior to the stores, are stored in the memory (18) of the central control device 10. The moving trajectory (P) of a person in the shopping mall are detected by the LRF 12, and the most similar moving trajectory (P_Tx) is identified. Then, the central control device 10 reads content of speech of topics corresponding to the identified moving trajectory (P_Tx), and adds it to the robot 14 together with the position of the person. The robot 14 speaks the content of speech of the topic added, to provide the recommendation information to the person. The comprehensive behavior of the person is predicted from the detected moving trajectory, and the recommendation information is given to the person on the basis of the comprehensive behavior thus predicted. <P>COPYRIGHT: (C)2011,JPO&amp;INPIT

Description

  The present invention relates to an information providing system, and more particularly to an information providing system that provides recommended information to a human who moves arbitrarily, for example.

  In the car navigation system disclosed in Patent Document 1, the destination setting time, the arrival time, and the arrival location specifying information are associated with each other and stored as a driving history by performing a driving guidance process. Then, by analyzing the driving history, services such as recommendations (recommendation of information) are provided to the driver.

  The autonomous mobile robot disclosed in Patent Document 2 includes a pair of left and right CCD cameras for observing as a stereo image, and predicts the course of the specific person by sequentially capturing the accompanying specific person. . Then, when there is an unspecified person in the course of the specific person, the autonomous mobile robot outputs a walk guidance voice to evacuate the specific person.

  In addition, the environmental information structuring system disclosed in Non-Patent Document 1 includes a robot that can approach a human by autonomous behavior and start a service, and an LRF (laser) provided within the robot's activity range. A human movement trajectory is measured using a range finder, and the human global behavior is predicted from the movement trajectory.

JP 2006-250879 A [G01C 21/00, G08G 1/0969] JP 2007-229816 [B25J 13/08, B25J 5/00]

Takayuki Kanda, Dylan F. Glas, Masahiro Shiomi, Hiroshi Ishiguro and Norihiro Hagita, Who will be the customer ?: A social robot that anticipates people's behavior from their trajectories, Tenth International Conference on Ubiquitous Computing (UbiComp 2008), pp.380- 389, 2008

  The car navigation system disclosed in Patent Literature 1 cannot provide a recommendation service without a driving history. Further, the autonomous mobile robot disclosed in Patent Document 2 can only predict a course within a few seconds for a specific person, and is not suitable for a system that provides a service using the predicted result. As in Non-Patent Document 1, global behavior can be predicted from a human movement trajectory, but a technology that combines such prediction technology with an information providing service such as a recommendation has not been realized so far.

  Therefore, a main object of the present invention is to provide a novel information providing system.

  Another object of the present invention is an information providing system capable of providing information by predicting human behavior.

  The present invention employs the following configuration in order to solve the above problems. The reference numerals in parentheses, supplementary explanations, and the like indicate the corresponding relationship with the embodiments described in order to help understanding of the present invention, and do not limit the present invention.

1st invention is the information provision system which provides the recommendation information according to the said person's action to the human who moves arbitrarily, Comprising: It sets beforehand corresponding to each of a plurality of recommendation information and a plurality of recommendation information storage means for memorize a plurality of first moving path, detection means for detecting a change in position of the person is moving the second movement trajectory, upon detection of a second movement trajectory by the detection means, moves the second The degree of similarity between the trajectory and all the first movement trajectories stored in the storage means is calculated, the specifying means for specifying the first movement trajectory having the highest similarity with the second movement trajectory, and the specifying means It is an information provision system provided with the information provision means which provides the recommendation information corresponding to a 1st movement locus | trajectory to a human.

  In the first invention, the information providing system (100) provides, for example, a situation such as a station around the shopping mall as recommendation information to a person in the shopping mall. The storage means (18) is a memory composed of, for example, a RAM or an HDD, and stores the recommendation information and the first movement locus representing the global action in association with each other. For example, the recommendation information representing the situation of the station is associated with the first movement locus representing the global action toward the station.

  An LRF (12) is installed in the shopping mall, and the LRF detects the position of a moving person. And a detection means (12, 16, S1) detects the change of a person's position as a 2nd movement locus | trajectory. Further, the first movement locus and the second movement locus are converted into a state sequence (S), and the similarity (R) is calculated by DP matching. Then, the information providing means (10, 14, 16, S33, 80, S95) indicates the status of the station to the person from whom the second movement locus is detected if the calculated similarity is equal to or greater than a predetermined value. Provide recommendation information.

  According to the first aspect of the present invention, it is possible to predict a global action performed by a person by detecting the movement trajectory of the person, and therefore it is possible to provide recommendation information corresponding to the global action.

A second invention is according to the first invention, when the recommendation information is determined to have been accepted by the human by the determination means, and determination means for determining whether recommendation information is received in humans, by the detection means Update means for adding the detected second movement locus to the storage means as a first movement locus corresponding to the recommendation information is further provided.

  In the second invention, the judging means (10, 14, 16, S35, 80, S97) judges whether the recommended information is accepted from the voice of the person who provided the recommended information, facial expressions, or the like. Then, the updating means (16, S37) calculates a new movement locus from the second movement locus of the person who has received the recommendation information and the first movement locus already stored in the storage means. Update the movement trajectory.

  According to 2nd invention, the precision which estimates global action can be improved by updating the 1st movement locus | trajectory corresponding to the recommendation information provided.

The third invention is dependent on the first invention or the second invention, and the information providing means corresponds to the robot set at a place where a human arbitrarily moves and the first movement locus specified by the specifying means. The operation information providing means for reading the recommended information from the storage means and assigning the recommended information as an operation command to the robot installed at a place where the human arbitrarily moves, and the robot is based on the operation command given by the operation command giving means. Provide recommended information to humans.

The fourth invention is dependent on the third invention, and the motion command giving means gives the robot a current position corresponding to the second movement locus together with the motion command, and is given by the motion command giving means. Based on the current position of the person, the robot approaching the person provides recommendation information.

A fifth invention is according to the third invention or the fourth invention, the robot comprises a communication robot performing the communication behavior including at least one of body motion and sound to a human, the operation instruction communication robot Contains the utterance content that utters.

In the fifth invention, the communication robot (14) can approach a human by autonomous behavior, and the human is provided with recommendation information as part of the communication behavior with the communication robot.

According to the fifth aspect , recommendation information can be provided using a communication robot.

  According to the present invention, since the global action performed by the person can be predicted by detecting the movement trajectory of the person, recommendation information corresponding to the predicted global action can be provided to the person.

  The above object, other objects, features, and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

FIG. 1 is an illustrative view showing an outline of an information providing system of the present invention. FIG. 2 is a block diagram showing an electrical configuration of the central controller shown in FIG. FIG. 3 is an illustrative view showing one example of a topics list and a movement trajectory list stored in the memory shown in FIG. FIG. 4 is an illustrative view showing the appearance of the robot shown in FIG. 1 from the front. FIG. 5 is a block diagram showing an electrical configuration of the robot shown in FIG. FIG. 6 is an illustrative view showing a measurement region of the LRF shown in FIGS. 1 and 2. FIG. 7 is an illustrative view showing one example of a human movement locus detected using the LRF shown in FIGS. 1 and 2. FIG. 8 is an illustrative view showing a map of a certain place where the LRF and the robot shown in FIG. 1 are installed. FIG. 9 is an illustrative view showing one example of a movement trajectory recorded in the topics list shown in FIG. FIG. 10 is an illustrative view showing the relationship between the movement trajectory converted by the CPU of the central control unit shown in FIG. 2 and the converted state sequence. FIG. 11 is an illustrative view showing one example of DP matching processing executed by the CPU of the central controller shown in FIG. FIG. 12 is an illustrative view showing one example of a movement trajectory of a human being detected by the LRF shown in FIGS. 1 and 2. FIG. 13 is an illustrative view showing one example of a memory map of a memory of the central control unit shown in FIG. FIG. 14 is a flowchart showing the position recording process of the CPU of the central controller shown in FIG. FIG. 15 is a flowchart showing the information providing process of the CPU of the central controller shown in FIG. FIG. 16 is a flowchart showing the similar movement locus specifying process of the CPU of the central controller shown in FIG. FIG. 17 is a flowchart showing the overall processing of the CPU of the robot shown in FIG.

  Referring to FIG. 1, an information providing system 100 according to this embodiment includes a central control device 10 having several LRFs including LRFs 12a and 12b and an autonomous mobile robot (hereinafter simply referred to as “robot”) 14. . LRF12, 12b is installed in the place where a human can move arbitrarily, and central controller 10 detects the movement locus (second movement locus) of human A who moves arbitrarily by LRF12a, 12b. For example, the place where the person A acts arbitrarily is a company floor, a museum, a shopping mall, an attraction venue, or the like, and the LRFs 12a and 12b are installed in various places (environments).

  In addition, the central control device 10 gives an operation command to the robot 14 via the network 400 so as to provide recommendation information to the person A. Then, the robot 14 provides recommendation information to the person A according to the given operation command. That is, the information providing system 100 provides recommendation information to the detected person A.

  Although only one person is shown here for simplicity, the central controller 10 can simultaneously detect the positions of two or more persons. Furthermore, although only one robot 14 is shown, the central controller 10 can simultaneously manage two or more robots 14. The robot 14 is also an interaction-oriented robot (communication robot) and communicates with a communication target (communication target) such as the human A including at least one of body movement such as gesture gesture and voice. Has the ability to perform actions.

  FIG. 2 is a block diagram showing an electrical configuration of the central controller 10. Referring to FIG. 2, central control device 10 includes LRFs 12a-12f and CPU 16. This CPU 16 is also called a microcomputer or a processor, and is connected to LRF 12c, LRF 12d, LRF 12e, and LRF 12f in addition to the aforementioned LRF 12a and LRF 12b. Further, the CPU 16 is also connected to the memory 18 and the communication LAN board 20. In addition, when it is not necessary to distinguish LRF12a-12f, it is collectively called "LRF12."

  The LRF 12 measures the distance for the object from the time it takes to irradiate the laser and reflect it back to the object (including humans). For example, a laser beam emitted from a transmitter (not shown) is reflected by a rotating mirror (not shown), and the front is scanned in a fan shape by a certain angle (for example, 0.5 degrees). Here, as the LRF 12, a laser range finder (model LMS200) manufactured by SICK can be used. When this laser range finder is used, a distance of 8 m can be measured with an error of about ± 15 mm.

  Although not shown, the memory 18 as storage means includes a ROM, an HDD, and a RAM, and a control program for controlling the operation of the central controller 10 is stored in advance in the ROM and the HDD. For example, a program necessary for human detection by the LRF 12 is recorded. The RAM is used as a work memory or a buffer memory.

  The CPU 16 is connected to the communication LAN board 20. The communication LAN board 20 is configured by, for example, a DSP, and sends transmission data given from the CPU 16 to the wireless communication device 22. The wireless communication device 22 sends the transmission data to the robot 14 via the network 400. For example, the transmission data may be recommendation information or an operation command signal (command) to be given to the robot 14. Further, the communication LAN board 20 receives data via the wireless communication device 22 and gives the received data to the CPU 16.

  Further, the memory 18 stores a topics list in which a plurality of topics as recommendation information are recorded, and a movement locus list for determining a movement locus (first movement locus) related to each topic.

  Referring to FIG. 3A, the topics list includes a “topics” column, a “movement locus” column, and an “utterance content” column. In the “Topics” column, IDs for identifying a plurality of topics are recorded. Here, topics T1 to T6 are recorded. In the column “movement locus”, movement locus P_T1 to movement locus P_T6 related to each topic are recorded corresponding to the column “topics”.

  In the “Speech content” column, the utterance content to be uttered by the robot 14 according to each topic is recorded corresponding to the “Topics” column, and each utterance content is a recommendation provided to a human. It represents information specifically. For example, corresponding to each of topics T1, topics T2, topics T3, topics T4, topics T5, and topics T6, “the train departure time is 12:00”, “the recommended menu is curry”, “ “There will be a parade from 15:00”, “There are vending machines in the rest area”, “There is a rest area over there” and “There is a guide map” are recorded respectively. This utterance content is updated as time passes.

  Referring to FIG. 3B, for example, the movement trajectory list of movement trajectory P_T1 records movement trajectory P1_T1, movement trajectory P2_T1, and the like. Then, a trajectory (line) that approximates all the movement trajectories (movement trajectory P1_T1 and movement trajectory P2 etc._T1) recorded in the list is calculated, and the approximate trajectory becomes the movement trajectory P_T1. Further, when new movement locus data is added to the movement locus list, the central control apparatus 10 updates the movement locus P_T1. Although not shown, a movement trajectory list corresponding to each of the movement trajectories P_T2 to P_T6 is also stored in the memory 18.

  Hereinafter, a variable x in which an arbitrary natural number is set may be used to represent an arbitrary topic Tx and a movement trajectory P_Tx.

  Although detailed description will be given later, the central control device 10 uses the topics list and the movement trajectory list stored in the memory 18 to determine recommendation information to be provided to the human.

  FIG. 4 is a front view showing the appearance of the robot 14 of this embodiment. Referring to FIG. 4, the robot 14 includes a carriage 30, and two wheels 32 and one slave wheel 34 that move the robot 14 autonomously are provided on the lower surface of the carriage 30. The two wheels 32 are independently driven by a wheel motor 36 (see FIG. 5), and the carriage 30, that is, the robot 14 can be moved in any direction of front, rear, left and right. The slave wheel 34 is an auxiliary wheel that assists the wheel 32. Therefore, the robot 14 can move in the arranged space by autonomous control.

  A cylindrical sensor attachment panel 38 is provided on the carriage 30, and a large number of infrared distance sensors 40 are attached to the sensor attachment panel 38. These infrared distance sensors 40 measure the distance from the sensor mounting panel 38, that is, the object (human being, obstacle, etc.) around the robot 14.

  In this embodiment, an infrared distance sensor is used as the distance sensor, but a small LRF, an ultrasonic distance sensor, a millimeter wave radar, or the like can be used instead of the infrared distance sensor.

  A body 42 is provided on the sensor mounting panel 38 so as to stand upright. In addition, the above-described infrared distance sensor 40 is further provided at the front upper center of the body 42 (a position corresponding to a human chest), and measures the distance mainly to the human in front of the robot 14. Further, the body 42 is provided with a support column 44 extending from substantially the center of the upper end of the side surface, and an omnidirectional camera 46 is provided on the support column 44. The omnidirectional camera 46 photographs the surroundings of the robot 14 and is distinguished from an eye camera 70 described later. As this omnidirectional camera 46, for example, a camera using a solid-state imaging device such as a CCD or a CMOS can be adopted. In addition, the installation positions of the infrared distance sensor 40 and the omnidirectional camera 46 are not limited to the portions, and can be changed as appropriate.

  An upper arm 50R and an upper arm 50L are provided at upper end portions on both sides of the torso 42 (position corresponding to a human shoulder) by a shoulder joint 48R and a shoulder joint 48L, respectively. Although illustration is omitted, each of the shoulder joint 48R and the shoulder joint 48L has three orthogonal degrees of freedom. That is, the shoulder joint 48R can control the angle of the upper arm 50R around each of three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 48R is an axis parallel to the longitudinal direction (or axis) of the upper arm 50R, and the other two axes (pitch axis and roll axis) are orthogonal to the axes from different directions. It is an axis to do. Similarly, the shoulder joint 48L can control the angle of the upper arm 50L around each of three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 48L is an axis parallel to the longitudinal direction (or axis) of the upper arm 50L, and the other two axes (pitch axis and roll axis) are orthogonal to the axes from different directions. It is an axis to do.

  In addition, an elbow joint 52R and an elbow joint 52L are provided at the respective distal ends of the upper arm 50R and the upper arm 50L. Although illustration is omitted, each of the elbow joint 52R and the elbow joint 52L has one degree of freedom, and the angle of the forearm 54R and the forearm 54L can be controlled around the axis (pitch axis).

  A sphere 56R and a sphere 56L corresponding to a human hand are fixedly provided at the tips of the forearm 54R and the forearm 54L, respectively. However, when a finger or palm function is required, a “hand” in the shape of a human hand can be used. Although not shown, the front surface of the carriage 30, the portion corresponding to the shoulder including the shoulder joint 48R and the shoulder joint 48L, the upper arm 50R, the upper arm 50L, the forearm 54R, the forearm 54L, the sphere 56R, and the sphere 56L, A contact sensor 58 (shown generically in FIG. 5) is provided. A contact sensor 58 on the front surface of the carriage 30 detects contact of a person or another obstacle with the carriage 30. Therefore, when the robot 14 is in contact with an obstacle during its movement, the robot 14 can detect it and immediately stop driving the wheels 32 to suddenly stop the movement of the robot 14. Further, the other contact sensors 58 detect whether or not the respective parts are touched. In addition, the installation position of the contact sensor 58 is not limited to the said site | part, and may be provided in an appropriate position (position corresponding to a person's chest, abdomen, side, back, and waist).

  A neck joint 60 is provided at the upper center of the body 42 (a position corresponding to a person's neck), and a head 62 is further provided thereon. Although illustration is omitted, the neck joint 60 has a degree of freedom of three axes, and the angle can be controlled around each of the three axes. A certain axis (yaw axis) is an axis directed directly above (vertically upward) of the robot 14, and the other two axes (pitch axis and roll axis) are axes orthogonal to each other in different directions.

  The head 62 is provided with a speaker 64 at a position corresponding to a human mouth. The speaker 64 is used for the robot 14 to communicate with a person around it by voice or sound. A microphone 66R and a microphone 66L are provided at a position corresponding to a human ear. Hereinafter, the right microphone 66R and the left microphone 66L may be collectively referred to as a microphone 66. The microphone 66 captures ambient sounds, in particular, the voices of humans who are subjects of communication. Furthermore, an eyeball part 68R and an eyeball part 68L are provided at positions corresponding to human eyes. The eyeball portion 68R and the eyeball portion 68L include an eye camera 70R and an eye camera 70L, respectively. Hereinafter, the right eyeball portion 68R and the left eyeball portion 68L may be collectively referred to as the eyeball portion 68. Further, the right eye camera 70R and the left eye camera 70L may be collectively referred to as an eye camera 70.

  The eye camera 70 captures a human face approaching the robot 14, other parts or objects, and captures a corresponding video signal. The eye camera 70 can be the same camera as the omnidirectional camera 46 described above. For example, the eye camera 70 is fixed in the eyeball unit 68, and the eyeball unit 68 is attached to a predetermined position in the head 62 via an eyeball support unit (not shown). Although illustration is omitted, the eyeball support portion has two degrees of freedom, and the angle can be controlled around each of these axes. For example, one of the two axes is an axis (yaw axis) in a direction toward the top of the head 62, and the other is orthogonal to the one axis and goes straight in a direction in which the front side (face) of the head 62 faces. It is an axis (pitch axis) in the direction to be performed. By rotating the eyeball support portion around each of these two axes, the tip (front) side of the eyeball portion 68 or the eye camera 70 is displaced, and the camera axis, that is, the line-of-sight direction is moved. Note that the installation positions of the speaker 64, the microphone 66, and the eye camera 70 described above are not limited to those portions, and may be provided at appropriate positions.

  As described above, the robot 14 of this embodiment has independent two-axis driving of the wheels 32, three degrees of freedom of the shoulder joint 48 (6 degrees of freedom on the left and right), one degree of freedom of the elbow joint 52 (2 degrees of freedom on the left and right), It has a total of 17 degrees of freedom, 3 degrees of freedom for the neck joint 60 and 2 degrees of freedom for the eyeball support (4 degrees of freedom on the left and right).

  FIG. 5 is a block diagram showing an electrical configuration of the robot 14. Referring to FIG. 5, robot 14 includes a CPU 80. The CPU 80 is also called a microcomputer or a processor, and is connected to the memory 84, the motor control board 86, the sensor input / output board 88 and the audio input / output board 90 via the bus 82.

  The memory 84 includes a ROM and a RAM (not shown). The ROM stores in advance a control program for controlling the operation of the robot 14. For example, a detection program for detecting the output (sensor information) of each sensor, a communication program for transmitting / receiving necessary data and commands to / from an external computer (central control device 10), and the like are recorded. The RAM is used as a work memory or a buffer memory.

  The motor control board 86 is constituted by, for example, a DSP, and controls driving of each axis motor such as each arm, neck joint, and eyeball unit. That is, the motor control board 86 receives control data from the CPU 80 and controls two motors (collectively indicated as “right eyeball motor 92” in FIG. 5) that control the angles of the two axes of the right eyeball portion 68R. Control the rotation angle. Similarly, the motor control board 86 receives two control data from the CPU 80 and controls two angles of the two axes of the left eyeball portion 68L (in FIG. 5, collectively shown as “left eyeball motor 94”). Control the rotation angle.

  The motor control board 86 receives control data from the CPU 80, and includes a total of four motors including three motors for controlling the angles of the three orthogonal axes of the shoulder joint 48R and one motor for controlling the angle of the elbow joint 52R. The rotation angle of two motors (collectively indicated as “right arm motor 96” in FIG. 5) is controlled. Similarly, the motor control board 86 receives control data from the CPU 80, and includes a total of three motors for controlling the angles of the three orthogonal axes of the shoulder joint 48L and one motor for controlling the angle of the elbow joint 52L. The rotation angles of four motors (collectively indicated as “left arm motor 98” in FIG. 5) are controlled.

  Further, the motor control board 86 receives the control data from the CPU 80, and controls three motors for controlling the angles of the three orthogonal axes of the neck joint 60 (in FIG. 5, collectively indicated as “head motor 110”). Control the rotation angle. The motor control board 86 receives the control data from the CPU 80 and controls the rotation angles of two motors that drive the wheels 32 (collectively indicated as “wheel motors 36” in FIG. 5). In this embodiment, a motor other than the wheel motor 36 uses a stepping motor (that is, a pulse motor) in order to simplify the control. However, a DC motor may be used similarly to the wheel motor 36. In addition, the actuator that drives the body part of the robot 14 is not limited to a motor that uses current as a power source, and may be changed as appropriate. For example, in another embodiment, an air actuator or the like may be applied.

  Similar to the motor control board 86, the sensor input / output board 88 is configured by a DSP and takes in signals from each sensor and gives them to the CPU 80. That is, data relating to the reflection time from each of the infrared distance sensors 40 is input to the CPU 80 through the sensor input / output board 88. The video signal from the omnidirectional camera 46 is input to the CPU 80 after being subjected to predetermined processing by the sensor input / output board 88 as necessary. Similarly, the video signal from the eye camera 70 is also input to the CPU 80. Further, signals from the plurality of contact sensors 58 described above (collectively referred to as “contact sensors 58” in FIG. 5) are provided to the CPU 80 via the sensor input / output board 88. Similarly, the voice input / output board 90 is also configured by a DSP, and voice or voice in accordance with voice synthesis data provided from the CPU 80 is output from the speaker 64. In addition, voice input from the microphone 66 is given to the CPU 80 via the voice input / output board 90.

  The CPU 80 is connected to the communication LAN board 112 via the bus 82. The communication LAN board 112 is configured by, for example, a DSP, and sends transmission data given from the CPU 80 to the wireless communication device 114. The wireless communication device 114 sends the transmission data to an external computer (central control device 10) via the network 400. Send. The communication LAN board 112 receives data via the wireless communication device 114 and gives the received data to the CPU 80. For example, the transmission data may be surrounding video data captured by the omnidirectional camera 46 and the eye camera 70 or data indicating a human reaction to the provided recommendation information.

  Next, the LRF 12 will be described in detail. Referring to FIG. 6, the measurement range of LRF 12 is indicated by a semicircular shape (fan shape) having a radius r (r≈8 m). That is, the LRF 12 can measure the direction of 90 degrees left and right within a predetermined distance (r) when the front direction is the center.

  The laser used is a class 1 laser in Japanese Industrial Standard JIS C 6802 “Safety Standard for Laser Products”, which is a safe level that does not affect human eyes. In this embodiment, the sampling rate of the LRF 12 is 37 Hz. This is because the position of a person who moves by walking or the like is continuously detected.

  Further, as described above, the LRF 12 is arranged in various places. Specifically, each of the LRFs 12a and 12b is arranged so that the detection regions overlap with each other, and although not illustrated, the LRFs 12a and 12b are fixed to a height of about 90 cm from the floor surface. This height is for enabling detection of the body and arms (both arms) of the subject, and is calculated from, for example, the average height of Japanese adults. Therefore, the height at which the LRF 12 is fixed may be appropriately changed according to the location (region or country) where the central controller 10 is provided and the age or age of the subject (for example, children, adults). In this embodiment, six LRFs 12 are set, but any number of LRFs 12 may be installed as long as the number is two or more.

  In the central controller 10 having such a configuration, the CPU 16 estimates a change in the current position of the human using a particle filter based on the output (distance data) from the LRF 12. The estimated change in the current position is recorded as a movement locus.

  For example, referring to FIG. 7, LRFs 12a and 12b are installed facing each other, and a range where the measurement ranges of LRFs 12a and 12b overlap is indicated by hatching. A hatched range is a detection area E, and the current position of the person is continuously detected in the detection area E. And the change of the present position detected continuously is shown as a movement locus. For example, it is shown as a movement locus Pa and a movement locus Pb. In the detection area E, XY coordinates are set, and the human position can be indicated by coordinates (X, Y).

  8A is an illustrative view showing a map showing a place where the LRF 12 is installed, and FIG. 8B is an illustrative view showing a divided map in which the detection area E is divided. With reference to FIG. 8 (A), a place corresponding to the map is a shopping mall. In addition, a store which is a restaurant is shown on the lower left side of the map, and a guide map for guiding the inside of the shopping mall is shown near the upper right center of the map. Although not shown, a rest space is provided at the lower right of the map. Furthermore, there is a station on the left side not shown in the map, and an attraction venue on the right side not shown.

  Referring to FIG. 8B, the detection area E is divided into 50 grids based on the k-means method. As a division procedure, the detection area E is formed into a 25 cm square spatial grid, and the spatial grid is further clustered at “k = 50”.

  Hereinafter, in this embodiment, an arbitrary spatial grid is a spatial grid i. Further, each of the divided clustered grids is a grid A, and an arbitrary grid A is a grid Am.

  The number of grids is not 50, but may be 50 or less or a value greater than 50. Further, the method of dividing the detection region E is not the k-means method, and may be manually divided by an administrator of the system.

  Further, in this embodiment, by accumulating the movement trajectory P of the human being in the shopping mall, the human local action (local action) and the global action (global action) are analyzed, and six kinds of actions are analyzed. The global behavior was extracted. Each of the six types of topics T1-T6 and the six movement trajectories P_T1 to P_T6 is set based on the extracted six types of global actions.

  Note that the k-means method was used when extracting the global behavior, and the result was “k = 6”. Moreover, when analyzing local action, SVM (Support Vector Machine) which discriminate | determines four types of local action was utilized.

  FIGS. 9A to 9F are illustrative views showing an example of each of the movement trajectories P_T1 to P_T6. With reference to FIG. 9A, the movement trajectory P_T1 shows an example of a global action of “passing from right to left”. Further, since there is a station on the left side of the map, it is highly likely that a person who has detected a movement locus P similar to the movement locus P_T1 is heading to the station. With reference to FIG. 9B, the movement trajectory P_T2 shows an example of the global action of “coming from the right and heading in front of the store”. In addition, a person who has detected a movement locus P similar to the movement locus P_T2 is likely to enter the store. With reference to FIG. 9C, an example of a global action of “passing from left to right” is shown. Further, since there is an attraction venue on the right side of the map, it is highly possible that a person who has detected a movement trajectory P similar to the movement trajectory P_T3 is heading to the attraction venue.

  With reference to FIG. 9D, the movement trajectory P_T4 shows an example of the global action “resting”. Further, since the movement trajectory P_T4 hardly changes at the break space, it is highly possible that a person who has detected the movement trajectory P similar to the movement trajectory P_T4 is taking a break using the break space. Referring to FIG. 9E, the movement locus P_T5 shows an example of a global action “walking around a rest space”. In addition, it is highly possible that a person who has detected a movement locus P similar to the movement locus P_T5 is waiting for a break space to be used. With reference to FIG. 9F, the movement trajectory P_T6 shows an example of the global action of “walking”. A person who has detected a movement trajectory P similar to the movement trajectory P_T6 is likely to be lost in the shopping mall or fail to determine a destination.

  Here, the central control device 10 according to the present embodiment uses each grid Am included in the divided map to move similar to the movement trajectory P corresponding to a certain person from the movement trajectories P_T1 to P_T6. The trajectory P_Tx is specified, and recommendation information (topics Tx) to be provided to a certain person is selected.

  Specifically, the central control apparatus 10 converts each of the detected movement trajectory P and the movement trajectories P_T1 to P_T6 corresponding to each topic into a state string S and a state string S_T1 to a state string S_T6, respectively. . Then, the central controller 10 calculates the similarity R between the state sequence S and the state sequence S_T1 to the state sequence S_T6 by DP matching, and the movement locus P is detected based on the calculated similarity R. The recommended information (topics T) to be provided to the selected person is selected.

  First, the procedure for converting the movement locus P into the state sequence S will be described in detail. For example, n is a certain human being detected, p (X, Y) is a certain point constituting the movement locus P, st is a certain state constituting the state sequence S, and a movement locus corresponding to a certain human n is represented. When Sn is a state sequence in which Pn and movement trajectory Pn are converted, the movement trajectory Pn corresponding to a certain person n is converted by the equation shown in Equation 1. In the equation (1), “m = 50”.

  Note that each of the movement trajectories P_T1 to P_T6 recorded in the topics list is also converted into each of the state sequence S_T1 to the state sequence S_T6 by the equation shown in Equation 1.

  For example, referring to FIG. 10, when a certain person n arbitrarily walks on grid A1, grid A2, and grid A3, the change of point p that constitutes movement trajectory Pn changes from grid A1 → grid A2 → grid A1 → If the grid A2 → the grid A2 → the grid A3, the state string Sn is expressed by the equation (2).

[Equation 2]
Sn = {A1, A2, A1, A2, A2, A3}
Next, a procedure for calculating the similarity R by DP matching will be described. Referring to FIG. 11, each of movement trajectory P1 and movement trajectory P2 is converted into each of state column S1 and state column S2. Further, since the number of states st included in the state sequence S1 is 10, and the number of states st included in the state sequence S2 is 12, the lengths of the two state sequences S are different. Therefore, in the DP matching process, in order to align the lengths of the two state sequences S, the two state sequences S are subjected to insertion and deletion processing to have the same length, and then the distance between the two state sequences is set. That is, the similarity R is calculated.

  It should be noted that the operation cost of DP matching deletion and insertion was set to be a distance of 1 m per operation. In addition, the similarity R increases as the distance between the two state sequences S decreases, and the similarity R decreases as the distance between the two state sequences S increases.

  As described above, when the similarity R is calculated after the movement trajectory P is converted into the state sequence S, the processing of the central control device 10 is accelerated. For example, the processing time when the similarity is calculated from each point p of the movement trajectory P becomes a value that is 10 times or more the processing time for calculating the similarity R by converting the state sequence S.

  In this embodiment, when the similarity R is calculated by DP matching, the movement trajectory P is measured for about 20 seconds. The numerical value of “20 seconds” was obtained from a preliminary experiment, and the accuracy rate of prediction was 80% or more.

  Referring to FIG. 12, for example, when movement locus P3 is detected within 20 seconds within detection region E, central controller 10 calculates similarity R with movement locus P_T1 to movement locus P_T6, The most similar movement trajectory P_Tx is specified. Then, the central control device 10 gives the robot 14 the utterance content of the topics Tx corresponding to the identified movement trajectory P_Tx and the human position corresponding to the movement trajectory P3. Then, the robot 14 approaches the person corresponding to the movement trajectory P3 based on the utterance content of the topic Tx given and the position of the person, and provides recommendation information as part of the communication action.

  For example, if the movement locus P_T1 is the most similar to the movement locus P3, robot 14, in close proximity to the person corresponding to the movement locus P3, after talking with the "Hello", departure time of "the train is 12 o'clock "Speaks."

  Further, when the person who talked to the mobile phone gives a positive response such as “thank you” or “I understand”, the robot 14 notifies the central controller 10 that the provided recommendation information has been accepted. Then, the central control apparatus 10 updates (recalculates) the movement locus P_T1 by adding the movement locus P3 of the person who has received the recommendation information to the movement locus list of the movement locus P_T1.

  On the other hand, if the person who talked to the robot responds negatively such as “I don't need it”, the robot 14 notifies the central controller 10 that the provided recommendation information has not been accepted. In this case, the central control device 10 randomly selects another topic and gives the utterance content of the randomly selected topic Tx to the robot 14. The robot 14 provides recommendation information once again in response to the utterance content of the newly added topics Tx.

  If the second recommendation information is accepted, the central controller 10 adds the movement locus P3 to the movement locus list, but if not accepted, gives the robot 14 an operation command to end the communication action.

  As described above, the information providing system 100 can predict the global human behavior by specifying the movement trajectory P_Tx similar to the human movement trajectory P. And recommendation information can be provided by the robot 14 based on the predicted global behavior.

  FIG. 13 is an illustrative view showing one example of a memory map 300 of the memory 18 in the central controller 10 shown in FIG. As shown in FIG. 13, the memory 18 includes a program storage area 302 and a data storage area 304. In the program storage area 302, a position recording program 312 and an information providing program 314 are stored. However, the information providing program 314 includes a similar movement locus specifying program 314a as a subroutine.

  The position recording program 312 is a program for sequentially recording the position of a person in a shopping mall, for example. The information providing program 314 is a program for selecting a person who provides recommendation information and giving an operation command to the robot 14. The similar movement locus specifying program 314a is a program for specifying a movement locus P_Tx similar to the detected movement locus P.

  Although illustration is omitted, the program for operating the central control device 10 includes a program for performing data communication via the network 400.

  The data storage area 304 is provided with a movement trajectory buffer 330 and a specific buffer 332, and stores topic data 334, movement trajectory data 336, and map data 338. The data storage area 304 is provided with a success flag 340.

  The movement locus buffer 330 is a buffer for temporarily storing a human position recorded by the position recording program 312. The identification buffer 332 is a buffer for temporarily storing the movement locus P_Tx identified by the processing of the similar movement locus identification program 314a. The topic data 334 is data of the topics list shown in FIG. 3A, and the utterance content is read out corresponding to the specified movement trajectory P_Tx.

  The movement trajectory data 336 is data including a movement trajectory list shown in FIG. 3B, for example, and is composed of movement trajectory lists corresponding to the movement trajectories P_T1 to P_T6. The map data 338 includes the shopping mall map and the divided map data shown in FIGS. 8A and 8B, and the divided map data is used when the movement locus P is converted into the state sequence S. It is done.

  The success flag 340 is a flag for determining whether or not the recommendation information has been accepted. For example, the success flag 340 is composed of a 1-bit register. When the success flag 340 is turned on (established), a data value “1” is set in the register. On the other hand, when the success flag 340 is turned off (not established), a data value “0” is set in the register. The success flag 340 is turned on when notified by the robot 14 that the recommendation information has been accepted, and turned off when notified by the robot 14 that the recommendation information has not been accepted.

  Although illustration is omitted, the data storage area 304 is provided with a buffer for temporarily storing the results of various calculations and other counters and flags necessary for the operation of the central controller 10. .

  Specifically, the CPU 16 of the central control apparatus 10 executes a plurality of processes in parallel including the processes shown in FIGS.

  As illustrated in FIG. 14, when the CPU 16 of the central control device 10 executes the position recording process, in step S <b> 1, the position of each person is detected. That is, the position of each person in the detection area E is detected by the LRF 12. Subsequently, in step S3, the position of each person is stored in the movement locus buffer 330 as a movement locus Pn, and the process returns to step S1. For example, the human locus is the movement locus P3 (see FIG. 11), and the movement locus buffer 330 stores the movement locus P3. In addition, CPU16 which performs step S1 functions as a detection means.

  FIG. 15 is a flowchart of the information providing process. As shown in FIG. 15, the CPU 16 of the central control device 10 determines whether or not it is an end operation in step S <b> 21. For example, it is determined whether or not an operation for ending the information providing process has been performed on an input device (not shown). If “YES” in the step S21, that is, if an end operation is performed, the information providing process is ended. On the other hand, if “NO” in the step S21, that is, if the end operation is not performed, a person who can provide information is selected in a step S23. That is, a person for whom recommendation information is not provided is selected. For example, a person whose movement locus P does not intersect the movement path of the robot 14 at the same time is extracted, and a person who is not more than a certain distance and closest to the robot 14 is selected from the extracted persons.

  Subsequently, in step S25, it is determined whether or not the selection has been made. That is, it is determined whether or not a person who can provide recommendation information has been selected in the process of step S23. If “NO” in the step S25, that is, if not selected, the process returns to the step S21. On the other hand, if “YES” in the step S25, the variable C is initialized in a step S27. That is, the value of the variable C that counts the number of times the recommended information is provided to the selected person is set to 1.

  Subsequently, in step S29, a similar movement locus specifying process is executed. Since the process of step S29 will be described later, detailed description thereof is omitted here. In addition, CPU16 which performs the process of step S29 functions as a specific means. Subsequently, in step S31, topics Tx corresponding to the specified movement locus P_Tx are selected. For example, if the movement trajectory P_T1 is specified, the topic T1 is selected, and the utterance content “Train departure time is 12:00” corresponding to the topic T1 is read.

  If the movement locus P_T2 is specified, the topic T2 is selected, and the utterance content “Recommended menu is curry” is read out. If the movement locus P_T3 is specified, the topic T3 is selected, and the utterance content “There is a parade from 15:00” is read out. If the movement locus P_T4 is specified, the topic T4 is selected, and the utterance content “There is a vending machine in the rest area” is read out. Further, if the movement locus P_T5 is specified, the topic T5 is selected, and the utterance content “There is a resting place over there” is read out. Then, if the movement trajectory P_T6 is specified, the topic T6 is selected, and the utterance content “A guide map is over there” is read out.

  In step S33, the robot approaches the selected person and gives an operation command for providing recommendation information to the robot. That is, an operation command is given to the robot 14 so as to execute a communication action for speaking the utterance content of the selected topics Tx to the selected person. For example, the robot 14 is given an operation command for a communication action that approaches the person corresponding to the movement locus P3 and utters “the train departure time is 12:00”.

  Subsequently, in step S35, it is determined whether or not it has been accepted. That is, it is determined whether or not the recommendation information provided by the robot 14 has been accepted. Specifically, the determination is made based on the success flag 340 that is switched on / off based on the data notified from the robot 14. If “NO” in the step S35, that is, if the recommendation information is not accepted, the process proceeds to a step S39. On the other hand, if “YES” in the step S35, that is, if the recommendation information is accepted, the human movement trajectory P selected in the step S37 is stored in the movement trajectory list, and the process returns to the step S21. That is, the position of the selected person is further detected for 20 seconds, and the movement locus P is recorded in the movement locus list corresponding to the movement locus P_Tx. Further, when a new movement track P is recorded, the movement track P_Tx is recalculated.

  For example, the CPU 16 further detects a human locus corresponding to the movement locus P3 to detect a movement locus P3 '. Then, the CPU 16 records (adds) the movement locus P3 'in the movement locus list corresponding to the movement locus P_T1, and further recalculates (updates) the movement locus P_T1. In addition, CPU16 which performs the process of step S37 functions as an update means.

  In step S39, it is determined whether or not the value of the variable C is smaller than 2. That is, it is determined whether or not the number of times that the robot 14 has provided the recommendation information exceeds two. If “NO” in the step S39, that is, if the robot 14 provides the recommendation information twice, the robot 14 is notified of the end of the information provision in a step S41. That is, the provision of the recommendation information to the selected person is terminated.

  On the other hand, if “YES” in the step S39, that is, if the robot 14 does not provide the recommendation information twice, the variable C is incremented in a step S43. That is, the number of times the recommended information is provided by the robot 14 is counted. Subsequently, in step S45, topics are selected at random, and the process returns to step S33. That is, in step S45, the ID of an arbitrary topic is selected from the topics list, and the utterance content corresponding to the selected topic ID is read. Note that a function that returns a pseudo-random number in the range of 1 to 6 is used for the process of randomly selecting a topic ID. Furthermore, when the ID of a topic that has already been selected is selected, a process of reselecting the topic ID may be performed. Note that the value used for the determination in step S39 may be set to 3 or more.

  FIG. 16 is a flowchart of the similar movement locus specifying process in step S29 shown in FIG. As shown in FIG. 16, the CPU 16 of the central control device 10 initializes the variable x and the variable Max in step S61. That is, 1 is set to the variable x and 0 is set to the variable Max. Each variable Max is a variable in which the maximum value of the calculated similarity R is set. Subsequently, in step S63, the selected human movement trajectory P is converted into a state sequence S. For example, the movement trajectory P3 is converted into the state sequence S3 based on the equation shown in Equation 1.

  Subsequently, in step S65, it is determined whether or not the variable x is 6 or less. That is, it is determined whether all the similarities between the movement locus P and the movement locus P_T1 to the movement locus P_T6 have been calculated. If “YES” in the step S65, that is, if all the similarities are calculated, the similar movement locus specifying process is ended, and the process returns to the information providing process which is the main routine.

  On the other hand, if “NO” in the step S65, that is, if all the degrees of similarity are not calculated, the moving trajectory P_Tx is converted into the state string S_Tx in a step S67. For example, if the variable x is 1, the movement trajectory P_T1 is converted into the state sequence S_T1. Subsequently, in step S69, the similarity R between the state sequence S and the state sequence S_Tx is calculated. For example, the distance between the state sequence S and the state sequence S_T1 is calculated by the DP matching process, and the calculated distance is set as the similarity R.

  Subsequently, in step S71, it is determined whether or not the similarity R is greater than the variable Max. That is, it is determined whether or not the calculated similarity R is greater than the variable Max for which the maximum similarity is set. If “NO” in the step S71, that is, if the calculated similarity R is not greater than the variable Max, the process proceeds to a step S77. On the other hand, if “YES” in the step S71, that is, if the calculated similarity R is larger than the variable Max, the contents of the specific buffer 332 are updated to the movement locus P_Tx in a step S73. For example, coordinate data representing the movement locus P_T1 is stored in the specific buffer 332. The specific buffer 332 stores new data after resetting (erasing) stored data. Subsequently, in step S75, the calculated similarity R is set in the variable Max. That is, the maximum value of similarity is updated. Subsequently, in step S77, the variable x is incremented, and the process returns to step S65. That is, the variable x is incremented in order to calculate the degree of similarity with the next movement locus P_Tx.

  In the first loop in steps S65 to S77, since the variable Max is set to 0, steps S73 and S75 are always executed. That is, by setting the initial value of the variable Max to 0, recommendation information is always provided.

  FIG. 17 is a flowchart of overall processing executed by the CPU 80 of the robot 14. As shown in FIG. 17, the CPU 80 of the robot 14 determines whether or not the end operation is performed in step S91. For example, it is determined whether or not a stop switch set for the robot 14 has been operated. If the robot 14 is remotely operated, it is determined whether or not a command to end the process has been transmitted. If “YES” in the step S91, that is, if it is an end operation, the entire process is ended. On the other hand, if “NO” in the step S91, that is, if it is not an end operation, it is determined whether or not an operation command is given in a step S93. That is, it is determined whether or not an operation command providing recommendation information is received. If “NO” in the step S93, that is, if an operation command is not received, the process returns to the step S91.

  On the other hand, if “YES” in the step S93, that is, if an operation command is received, the recommendation information is uttered to the person selected in the step S95 according to the received operation command. In other words, close to the human beings on the basis of the coordinates that is included in the operating instructions, to start the communication behavior and speech as "Hello". Furthermore, based on the utterance content included in the operation command, for example, by saying “Train departure time is 12:00”, recommendation information is provided to a person who is a conversation partner. For example, a person who is predicted to have a global action of “passing from left to right” is presumed to be heading to the station, so the departure time of the train is provided as recommendation information.

  In addition, it is presumed that people who are predicted to be coming from the right and heading in front of the store are heading for the store, so the recommended product (menu) for that store is provided as recommendation information. The In addition, since it is estimated that a person who is predicted to have a global action of “passing from the left to the right” is heading to the attraction venue, the event at the attraction venue is provided as recommendation information.

  In addition, rest space equipment (vending machine) is provided as recommendation information to a person who is predicted to have a global action of “resting”. In addition, since it is estimated that a person who is predicted to be “walking around the rest space” is going to take a rest, the location of another rest space is provided as recommendation information. In addition, people who are predicted to be “walking” are presumed to be lost in the shopping mall or to decide where to go, so the location with a guide map in the shopping mall is provided as recommended information. Is done.

  Subsequently, in step S97, it is determined whether or not the utterance content is accepted. That is, it is determined whether or not the recommended information spoken is accepted. Specifically, the microphone 66 recognizes the voice uttered by the conversation partner and determines whether the utterance content has been accepted. The robot 14 may recognize the face pattern by photographing the face of the conversation partner with the eye camera 70 and determine whether the utterance content has been accepted. If “YES” in the step S97, that is, if the recommendation information is accepted, in a step S99, the acceptance is accepted to the central control apparatus 10, and the process returns to the step S91. That is, the central control device 10 is notified that the recommendation information provided to the conversation partner has been accepted.

  On the other hand, if “NO” in the step S97, that is, if the recommendation information is not accepted, the central controller 10 is notified that the acceptance is not accepted in a step S101. That is, the central control device 10 is notified that the recommendation information provided to the conversation partner has not been accepted. Subsequently, in step S103, it is determined whether or not the end of information provision has been notified. That is, it is determined whether or not the central control device 10 has notified the end of provision of recommendation information. If “YES” in the step S103, that is, if an end notification is given, the process returns to the step S91. On the other hand, if “NO” in the step S103, that is, if an end notification is not received, the process returns to the step S95.

  If the process of step S99 is completed or if “YES” is determined in step S103, the robot 14 utters “see you” and ends the communication action. If “NO” is determined in the step S103, the robot 14 utters “Tell me other recommendations” and continues the communication action.

  Also, the recommendation information uttered by the robot 14 may be uttered in a question form so that the person who is the conversation partner can easily respond. For example, “Train departure time is 12:00” is spoken, “If you head to the station, the train departure time is 12:00, are you okay?”.

  Further, the CPU 16 of the central control apparatus 10 that executes the process of step S33 and the CPU 80 of the robot 14 that executes the process of step S95 function as information providing means. Further, the CPU 16 of the central controller 10 that executes the process of step S35 and the CPU 80 of the robot 14 that executes the process of step S97 function as a determination unit.

  According to this embodiment, the information providing system 100 includes a central control device 10, an LRF 12 installed in a shopping mall, and a robot 14. The memory 18 included in the central control device 10 includes topics T1-T6 which are recommended information related to stores in the shopping mall, surrounding stations and attractions, and a movement trajectory P_T1 representing global behavior toward the stores, stations and attractions. A topics list in which the movement trajectory P_T6 is recorded is stored.

  In addition, the person who is in the shopping mall detects the movement locus P by the LRF 12, and calculates the similarity R with the movement locus P_T1 to the movement locus P_T6 recorded in the topics list. Then, the central controller 10 reads the utterance content of the topic Tx corresponding to the movement trajectory P_Tx for which the highest similarity R is calculated which is greater than the maximum similarity Max. The robot 14 provides recommendation information by speaking based on the utterance content of the read topics Tx while performing communication behavior with humans.

  Thus, by detecting the movement trajectory P of a person, it is possible to predict a global action performed by the person, and therefore it is possible to provide recommendation information according to the global action.

  Further, the central control apparatus 10 updates the movement trajectory P_Tx corresponding to the recommendation information based on the movement trajectory P of the person who has received the recommendation information. Thus, by updating the movement trajectory P_Tx corresponding to the recommendation information, the accuracy of predicting the global behavior is improved.

  Also, since a plurality of recommended information to be provided is prepared, the information providing system 100 can provide recommended information suitable for each of a plurality of persons even if different movement trajectories P are detected from the plurality of persons.

  And recommendation information is provided by the robot 14 which can perform a communication action.

  In the present embodiment, the movement trajectory P_T corresponding to one topic T is not limited to one, and a plurality of movement trajectories P_T may correspond. Further, the movement trajectory P_Tx corresponding to the topic Tx may be calculated by clustering each movement trajectory recorded in the movement trajectory list by the k-means method.

  In the present embodiment, the recommendation information is provided by the robot 14. However, the recommendation information may be provided by transmitting the recommendation information to a portable terminal such as a mobile phone possessed by a human. In this case, the mobile terminal provides recommendation information not by voice but by a character string or an image. In addition, a portable terminal held by a human may be identified by using radio field intensity in wireless communication with the portable terminal, or if it is a portable terminal having an acceleration sensor, it is identified by using acceleration data. Also good.

  Further, the recommended information to be provided may be increased by extracting more global actions.

  Further, although the LRF 12 is used to detect the human position, the human position may be detected using an ultrasonic distance sensor, a millimeter wave radar, or the like instead of the LRF 12.

10 ... Central controller 12a-12f ... LRF
14 ... Robot 16 ... CPU
18 ... Memory 80 ... CPU
400 ... Network

Claims (5)

An information providing system for providing recommended information according to the human behavior to an arbitrarily moving human,
A plurality of the recommendation information, the plurality of the plurality of first moving path and the memorize storing means which is set in advance corresponding to each of the recommendation information,
Detecting means for detecting a change in position of the person is moving the second moving track,
When the second movement locus is detected by the detecting means, the similarity between the second movement locus and all the first movement locus stored in the storage means is calculated, and the similarity with the second movement locus is the highest. Specifying means for specifying a large first movement locus; and
An information providing system comprising information providing means for providing recommendation information corresponding to the first movement locus specified by the specifying means to the person. Determination means for the recommendation are decision received in said human, and when it is determined that the recommendation information is received in the human by the determining means, the second movement trajectory detected by the detecting means The information providing system according to claim 1, further comprising update means for adding to the storage means as a first movement locus corresponding to the recommendation information . The information providing means includes
A robot set in a place where the human moves arbitrarily, and
Including operation command giving means for reading recommended information corresponding to the first movement trajectory specified by the specifying means from the storage means and giving it as an operation command to a robot installed at a place where the human moves arbitrarily;
The information providing system according to claim 1, wherein the robot provides the recommendation information to the human based on the operation command given by the motion command giving unit. The movement command giving means gives the robot the current position of the human corresponding to the second movement locus together with the movement command.
The information providing system according to claim 3, wherein the robot approaching the person provides the recommendation information based on the current position of the person given by the operation command giving unit. The robot includes a communication robot that performs a communication action including at least one of body motion and voice on the human ,
The information providing system according to claim 3 or 4 , wherein the operation command includes an utterance content uttered by the communication robot .

Images