JP2011223223A - Recording controller apparatus and recording control program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a recording control apparatus and program capable of recording only a detection signal from a necessary sensor if needed.SOLUTION: A recording control apparatus 102 includes a CPU 102a that, when starting recording control processing, determines whether a recording start trigger is generated on the basis of a detection signal from an environment sensor 106. The generated recording start trigger causes the CPU 102a to start recording to a sensor information database 104, a detection signal from the environment sensor 106 in which its detection range includes at least one of a robot 12 and a human. On the basis of the detection signal from the environment sensor 106, the CPU 102a determines whether a recording terminating trigger is generated. When the recording terminating trigger is generated, the CPU 102a terminates the recording of the detection signal from the environment sensor 106 started when the recording start trigger corresponding to the recording terminating trigger is generated.

Description

  The present invention relates to a recording control apparatus and a recording control program, and more particularly to a recording control apparatus and a recording control program for recording, for example, robots and human actions and dialogues in a certain environment.

  An example of this type of recording control apparatus is disclosed in Patent Document 1. In the surveillance video recording apparatus disclosed in Patent Document 1, n (n = integer) samplings are extracted from a scanning line of surveillance camera video, and the image information is stored for each frame. The stored image information is compared for each frame, and a change in the captured video pattern is detected. Only when a change in the video pattern is detected, the recording device is operated, and the video signal of the surveillance camera is stored on a recording tape or the like.

JP 7-193781 [H04N 5/915, H04N 7/18]

  However, in the surveillance video recording apparatus of Patent Document 1, since the operation of the recording apparatus is controlled only by the change of the video pattern, it is necessary when necessary in an environment where not only an image sensor but also various types of sensors are arranged. It was not possible to selectively record only the detection signal of a simple sensor.

  Therefore, a main object of the present invention is to provide a novel recording control apparatus and recording control program.

  Another object of the present invention is to provide a recording control device and a recording control program capable of recording a detection signal of only a necessary sensor when necessary.

  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 correspondence relationships with embodiments described later to help understanding of the present invention, and do not limit the present invention in any way.

  A first invention is a recording control device that controls recording of detection signals from a plurality of sensors arranged in an environment where a robot and a human are present, and the detection is performed based on detection signals from the plurality of sensors. When it is determined by the recording start determining means that determines whether or not to start signal recording, and when the recording start determining means determines that recording of the detection signal is to be started, for each of the plurality of sensors, the robot and human A position determination unit that determines whether or not at least one of the above is included, and when the position determination unit determines that at least one of a robot and a human is included in the detection range, the detection signal of the sensor having the detection range is recorded. It is a recording control apparatus provided with the recording start means to start.

  In the first invention, the recording control device (102) receives detection signals from a plurality of sensors (106) arranged in an environment (200) where a robot (12) and a human (A, B, C) exist. Control recording. The recording start determining means (102a, S13) determines whether or not to start recording of the detection signals based on the detection signals from the plurality of sensors. The position determining means (102a, S29), when it is determined by the recording start determining means that recording of the detection signal is started (“YES” in S13), the robot and Determine whether at least one of humans is included. The recording start means (102a, S35) records the detection signal of the sensor having the detection range when the position determination means determines that at least one of the robot and the human is included in the detection range ("YES" in S29). To start.

  According to the first invention, when the recording start of the detection signal of the sensor is determined, the detection signal of the sensor is recorded when a person or a robot exists within the detection range of the sensor. Only the detection signals of the necessary sensors can be recorded. As a result, it is possible to prevent wasteful use of the storage capacity of the memory.

  A second invention is dependent on the first invention, and the robot includes a part of a plurality of sensors.

  In the second invention, since the robot includes a part of a plurality of sensors, the robot also functions as a sensor for identifying a human or detecting a human voice or action, for example.

  According to the second invention, the robot can be used as a sensor disposed in the environment.

  A third invention is dependent on the first or second invention, and the robot is a communication robot that executes a communication action using at least one of a body motion and a voice.

  In a third aspect of the invention, the robot is a communication robot that executes a communication action using at least one of body movement and voice. For example, a communication robot performs communication behavior with a communication target such as a human and provides services such as reception and guidance in a certain environment.

  According to the third aspect of the present invention, it is possible to record the communication robot and human communication behavior in an environment where the communication robot exists.

  A fourth invention is dependent on the first to third inventions, and the recording start determining means determines that recording of the detection signal is started when the detection signals from the plurality of sensors satisfy the first predetermined condition. To do.

  In the fourth invention, the recording start determining means starts recording the detection signal when the detection signals from the plurality of sensors satisfy the first predetermined condition, for example, when a trigger for starting the recording of the detection signal occurs. To do.

  According to the fourth invention, since the recording of the detection signal is started when the detection signals from the plurality of sensors satisfy the first predetermined condition, it is possible to record only the necessary detection signals of the sensor when necessary. it can.

  A fifth invention is dependent on any one of the first to fourth inventions, and based on detection signals from a plurality of sensors, recording end determination means for determining whether or not to end recording of the detection signals, and When it is determined by the recording end determination means to end the recording of the detection signal, the recording end means further includes a recording end means for ending the recording of the detection signal.

  In the fifth invention, the recording end determination means (102a, S15) determines whether or not to end the recording of the detection signal based on the detection signals from the plurality of sensors. The recording end means (102a, S21) ends the recording of the detection signal when it is determined by the recording end determination means to end the recording of the detection signal (“YES” in S15).

  According to the fifth aspect, recording of the detection signal of the sensor is terminated as necessary, so that it is possible to avoid excessively recording the detection signal in advance. Therefore, it is possible to prevent wasteful use of the storage capacity of the memory.

  The sixth invention is dependent on the fifth invention, and the recording end judging means judges that the recording of the detection signal is finished when the detection signals from the plurality of sensors satisfy the second predetermined condition.

  In the sixth invention, the recording end judging means records the detection signal when the detection signals from the plurality of sensors satisfy the second predetermined condition, for example, when a flag for ending the recording of the detection signal is generated. Determine to end.

  According to the sixth aspect, similarly to the fifth aspect, it is possible to avoid recording the detection signal excessively in advance.

  A seventh invention is dependent on the sixth invention, has a plurality of first predetermined conditions, has a second predetermined condition corresponding to each of the plurality of first predetermined conditions, and the recording end means detects When it is determined that the signal recording is to be ended, the recording is ended only for the detection signal that has been recorded when the first predetermined condition corresponding to the second predetermined condition based on the determination is satisfied.

  In the seventh invention, for example, a plurality of first predetermined conditions are provided, and a second predetermined condition corresponding to each of the plurality of first predetermined conditions is provided. When it is determined that the recording of the detection signal is to be ended, the recording end unit only detects the detection signal that has started recording when the first predetermined condition corresponding to the second predetermined condition based on the determination is satisfied (S17, S19, S21) Recording is terminated.

  According to the seventh aspect of the invention, since the recording of only the detection signal that should end the recording is ended, the detection signal that is set to start the overlapping recording is detected by the generation of the flag that ends one recording. , Recording never ends.

  An eighth invention is a recording control program for controlling recording of detection signals from a plurality of sensors arranged in an environment in which a robot and a human are present, the computer controlling the detection signals from the plurality of sensors. When the recording start determination step for determining whether or not to start recording of the detection signal and the recording start determination step determine that recording of the detection signal is to be started, each of the plurality of sensors is set in its own detection range. A position determination step for determining whether or not at least one of a robot and a human is included, and a detection signal of a sensor having the detection range when the position determination step determines that at least one of a robot and a human is included in the detection range A recording control program for executing a recording start step for starting recording on a storage medium That.

  In the eighth invention, as in the first invention, only the detection signals of the necessary sensors can be recorded when necessary.

  According to the present invention, when the start of recording of the detection signal of the sensor is determined, the detection signal of the sensor is recorded when a person or a robot exists within the detection range of the sensor. Only the detection signal of the sensor can be recorded. As a result, it is possible to prevent wasteful use of the storage capacity of the memory.

  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 a configuration of a network robot system according to an embodiment of the present invention. FIG. 2 is a front view of the appearance of the robot shown in FIG. 1 as viewed from the front. FIG. 3 is a block diagram showing an electrical configuration of the robot shown in FIG. FIG. 4 is an illustrative view showing an example of an environment in which the network robot system shown in FIG. 1 is applied and sensor information is acquired. FIG. 5 is an illustrative view showing one example of a trigger information table. FIG. 6 is an illustrative view for explaining detection ranges of the floor sensor, the microphone, and the camera shown in FIG. FIG. 7 is an illustrative view for explaining a coordinate system of a two-dimensional map when the environment is viewed from directly above, and an illustrative view for explaining a detection range of the tag reader shown in FIG. FIG. 8 is an illustrative view showing one example of a RAM memory map of the recording control apparatus shown in FIG. FIG. 9 is an illustrative view showing a subject information table according to the subject information data of FIG. 8 and a sensor information table according to the sensor information data of FIG. FIG. 10 is an illustrative view showing a recording information table according to the recording information data of FIG. FIG. 11 is a flowchart showing a part of the recording control processing of the computer (CPU) of the recording control apparatus shown in FIG. FIG. 12 is another part of the recording control process of the CPU of the recording control apparatus shown in FIG. 1, and is a flowchart subsequent to FIG. 13 is another part of the recording control process of the CPU of the recording control apparatus shown in FIG. 1, and is a flowchart subsequent to FIG.

  Referring to FIG. 1, a network robot system (hereinafter simply referred to as “system”) 10 of this embodiment includes a plurality of communication robots (hereinafter simply referred to as “robots”) 12. Each robot 12 is communicably connected to the recording control apparatus 102 via the network 100. In addition, a sensor information database (sensor information DB) 104 and an environmental sensor 106 are connected to the recording control apparatus 102.

  The robot 12 is an interaction-oriented robot, and has a function of executing communication actions including at least one of body movements such as gestures and voices with communication targets (communication targets) such as human beings. I have. The robot 12 provides various services such as reception and route guidance, and is arranged in various places or situations (environments) such as a certain company or event venue (shopping mall, exhibition hall), for example. Further, the robot 12 can self-propell in the environment. In this embodiment, a tag (wireless tag) 12a is attached to each robot 12 in order to detect each robot 12 in an identifiable manner.

  In the drawing, the tag 12 a is shown as being attached to the outside of the robot 12, but the tag 12 a may be provided inside the robot 12.

  The hardware configuration of the robot 12 will be described with reference to FIG. FIG. 2 is a front view showing the appearance of the robot 12 of this embodiment. The robot 12 includes a carriage 18, and two wheels 20 and one slave wheel 22 for autonomously moving the robot 12 are provided on the lower surface of the carriage 18. The two wheels 20 are independently driven by a wheel motor 24 (see FIG. 3), and the carriage 18, that is, the robot 12 can be moved in any direction of front, rear, left and right. The slave wheel 22 is an auxiliary wheel that assists the wheel 20. Therefore, the robot 12 can move in the arranged environment (space) by autonomous control.

  A cylindrical sensor mounting panel 26 is provided on the carriage 18, and a number of distance sensors 28 (including an infrared distance sensor 28a and a laser distance sensor 28b: see FIG. 3) are mounted on the sensor mounting panel 26. It is done. These distance sensors 28 measure the distance to the sensor mounting panel 26, that is, the object (such as a human being or an obstacle) around the robot 12.

  The body 30 is provided on the sensor mounting panel 26 so as to stand upright. Further, the above-described distance sensor 28 is further provided in the upper front upper portion of the body 30 (a position corresponding to a human chest), and measures the distance mainly to a human in front of the robot 12. Further, the body 30 is provided with a support column 32 extending from substantially the center of the upper end of the side surface, and an omnidirectional camera 34 is provided on the support column 32. The omnidirectional camera 34 captures the surroundings of the robot 12 and is distinguished from an eye camera 58 described later. As this omnidirectional camera 34, 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 28 and the omnidirectional camera 34 are not limited to the portions, and can be changed as appropriate.

  An upper arm 38R and an upper arm 38L are provided at upper end portions on both sides of the body 30 (a position corresponding to a human shoulder) by a shoulder joint 36R and a shoulder joint 36L, respectively. Although illustration is omitted, each of the shoulder joint 36R and the shoulder joint 36L has three orthogonal degrees of freedom. That is, the shoulder joint 36R can control the angle of the upper arm 38R around each of the three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 36R is an axis parallel to the longitudinal direction (or axis) of the upper arm 38R, and the other two axes (pitch axis and roll axis) are orthogonal to the axis from different directions. It is an axis to do. Similarly, the shoulder joint 36L can control the angle of the upper arm 38L around each of three orthogonal axes. A certain axis (yaw axis) of the shoulder joint 36L is an axis parallel to the longitudinal direction (or axis) of the upper arm 38L, and the other two axes (pitch axis and roll axis) are orthogonal to the axis from different directions. It is an axis to do.

  In addition, an elbow joint 40R and an elbow joint 40L are provided at the tips of the upper arm 38R and the upper arm 38L, respectively. Although illustration is omitted, each of the elbow joint 40R and the elbow joint 40L has one degree of freedom, and the angles of the forearm 42R and the forearm 42L can be controlled around this axis (pitch axis).

  A sphere 44R and a sphere 44L corresponding to a human hand are fixedly provided at the tips of the forearm 42R and the forearm 42L, 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 18, the portion corresponding to the shoulder including the shoulder joint 36R and the shoulder joint 36L, the upper arm 38R, the upper arm 38L, the forearm 42R, the forearm 42L, the sphere 44R and the sphere 44L are respectively A contact sensor (shown generically in FIG. 3) 46 is provided. The contact sensor 46 on the front surface of the carriage 18 detects contact of a person or an obstacle with the carriage 18. Therefore, the robot 12 can detect that there is a contact with a human being or an obstacle during its movement, and can immediately stop the driving of the wheel 20 and suddenly stop the movement of the robot 12. Further, the other contact sensors 46 detect whether or not the respective parts are touched. In addition, the installation position of the contact sensor 46 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 48 is provided at the upper center of the body 30 (a position corresponding to a person's neck), and a head 50 is further provided thereon. Although illustration is omitted, the neck joint 48 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 12, and the other two axes (pitch axis and roll axis) are axes orthogonal to each other in different directions.

  The head 50 is provided with a speaker 52 at a position corresponding to a human mouth. The speaker 52 is used for the robot 12 to communicate with humans around it by voice or sound. A microphone 54R and a microphone 54L are provided at a position corresponding to a human ear. Hereinafter, the right microphone 54R and the left microphone 54L may be collectively referred to as a microphone 54. The microphone 54 captures ambient sounds, particularly a human voice that is an object for performing communication. Furthermore, an eyeball portion 56R and an eyeball portion 56L are provided at positions corresponding to human eyes. The eyeball portion 56R and the eyeball portion 56L include an eye camera 58R and an eye camera 58L, respectively. Hereinafter, the right eyeball portion 56R and the left eyeball portion 56L may be collectively referred to as the eyeball portion 56. Further, the right eye camera 58R and the left eye camera 58L may be collectively referred to as an eye camera 58.

  The eye camera 58 captures a human face approaching the robot 12, other parts or objects, and captures a corresponding video signal. The eye camera 58 can be the same camera as the omnidirectional camera 34 described above. For example, the eye camera 58 is fixed in the eyeball unit 56, and the eyeball unit 56 is attached to a predetermined position in the head 50 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 50, and the other is orthogonal to the one axis and goes straight in a direction in which the front side (face) of the head 50 faces. It is an axis (pitch axis) in the direction to be performed. By rotating the eyeball support portion around each of the two axes, the tip (front) side of the eyeball portion 56 or the eye camera 58 is displaced, and the camera axis, that is, the line-of-sight direction is moved. It should be noted that the installation positions of the above-described speaker 52, microphone 54, and eye camera 58 are not limited to the portions, and may be provided at appropriate positions.

  As described above, the robot 12 of this embodiment includes independent two-axis driving of the wheels 20, three degrees of freedom of the shoulder joint 36 (6 degrees of freedom on the left and right), and one degree of freedom of the elbow joint 40 (two 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 48 and 2 degrees of freedom for the eyeball support (4 degrees of freedom on the left and right).

  FIG. 3 is a block diagram showing the electrical configuration of the robot 12. With reference to FIG. 3, the robot 12 includes a CPU 60. The CPU 60 is also called a microcomputer or a processor, and is connected to the memory 64, the motor control board 66, the sensor input / output board 68, and the audio input / output board 70 via the bus 62.

  The memory 64 includes a ROM, an HDD, and a RAM (not shown). In the ROM and the HDD, a control program for controlling the operation of the robot 12 is stored in advance. For example, a program for executing a communication action, a detection program for detecting the output (detection signal) of each sensor, and necessary data and commands (messages) with an external computer (such as the recording control device 102) A communication program for transmitting and receiving is recorded. The RAM is used as a work memory or buffer memory for the CPU 60.

  The motor control board 66 is composed of, for example, a DSP, and controls driving of motors of axes such as arms, neck joints, and eyeballs. That is, the motor control board 66 receives control data from the CPU 60, and controls two motors (collectively indicated as “right eyeball motor 72” in FIG. 3) that control the angles of the two axes of the right eyeball portion 56R. Control the rotation angle. Similarly, the motor control board 66 receives control data from the CPU 60, and shows two motors for controlling the respective angles of the two axes of the left eyeball portion 56L (in FIG. 3, collectively referred to as “left eyeball motor 74”). ) To control the rotation angle.

  The motor control board 66 receives control data from the CPU 60, and includes three motors for controlling the angles of the three orthogonal axes of the right shoulder joint 36R and one motor for controlling the angle of the right elbow joint 40R. The rotation angles of a total of four motors (collectively indicated as “right arm motor 76” in FIG. 3) are controlled. Similarly, the motor control board 66 receives control data from the CPU 60, three motors for controlling the angles of the three orthogonal axes of the left shoulder joint 36L, and one motor for controlling the angle of the left elbow joint 40L. The rotation angles of a total of four motors (collectively indicated as “left arm motor 78” in FIG. 3) are controlled.

  Further, the motor control board 66 receives control data from the CPU 60, and controls three motors that control the angles of the three orthogonal axes of the neck joint 48 (in FIG. 3, collectively indicated as "head motor 80"). Control the rotation angle. The motor control board 66 receives control data from the CPU 60 and controls the rotation angles of the two motors that drive the wheels 20 (collectively indicated as “wheel motors 24” in FIG. 3). In this embodiment, a motor other than the wheel motor 24 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 24. The actuator that drives the body part of the robot 12 is not limited to a motor that uses a current as a power source, and may be changed as appropriate. For example, in another embodiment, an air actuator may be applied.

  Similarly, the sensor input / output board 68 is also constituted by a DSP, and takes in signals from each sensor and gives them to the CPU 60. That is, data relating to the reflection time from each of the distance sensors 28 is input to the CPU 60 through the sensor input / output board 68. The video signal from the omnidirectional camera 34 is input to the CPU 60 after being subjected to predetermined processing by the sensor input / output board 68 as necessary. Similarly, the video signal from the eye camera 58 is also input to the CPU 60. Further, signals from the plurality of contact sensors described above (collectively indicated as “contact sensors 46” in FIG. 3) are provided to the CPU 60 via the sensor input / output board 68.

  Similarly, the voice input / output board 70 is also configured by a DSP, and voice or voice according to voice synthesis data provided from the CPU 60 is output from the speaker 52. Also, voice input from the microphone 54 is given to the CPU 60 via the voice input / output board 70.

  The CPU 60 is connected to the communication LAN board 82 via the bus 62. The communication LAN board 82 is configured by a DSP and provides transmission data given from the CPU 60 to the wireless communication device 84, and sends the transmission data from the wireless communication device 84 to an external computer (such as the recording control device 102) via the network 100. Send. The communication LAN board 82 receives data via the wireless communication device 84 and gives the received data to the CPU 60. That is, the robot 12 can perform wireless communication with the recording control device 102 by the communication LAN board 82 and the wireless communication device 84.

  Further, the wireless tag reader 86 is connected to the CPU 60 via the bus 62. The wireless tag reader 86 receives a radio wave superimposed with identification information transmitted from the wireless tag (RFID tag) via an antenna (not shown). The wireless tag reader 86 amplifies the received radio wave signal, separates the identification signal from the radio wave signal, demodulates (decodes) the identification information, and supplies the identification information to the CPU 60. The wireless tag is attached to a person in a company or an event venue, and the wireless tag reader 86 detects a wireless tag (12a, 250 in this embodiment) within a communicable range. Note that the wireless tag may be an active type or a passive type that is driven in accordance with radio waves transmitted from the wireless tag reader 86.

  FIG. 4 shows an example when the system 10 shown in FIG. 1 is applied to an environment 200. However, for simplicity, the network 100, the recording control apparatus 102, and the sensor information DB 104 are omitted in FIG. In this embodiment, as shown in FIG. 4, the environment 200 includes an environment sensor 106 as a floor sensor 106 a, a plurality of tag readers 106 b, a plurality of image sensors (cameras) 106 c, and a plurality of sound sensors (microphones) 106 d. Is placed. However, the tag reader 106b (same as “86” described above) functions as a part of an identification sensor for individually identifying the robot 12 or a person.

  In addition, the environment 200 may include a robot 12 or a human. In the embodiment shown in FIG. 4, the case where there is one robot 12 is shown, but there may be two or more robots 12. Further, the robot 12 may not exist. Furthermore, although the example shown in FIG. 4 shows a case where three persons A, B, and C exist in the environment 200, the number of persons need not be limited. Also, humans may not exist. As shown in FIG. 4, a tag (wireless tag) 250 is attached to a person (A, B, C) in order to identify each person individually.

  Although detailed description is omitted, as described above, the robot 12 includes the omnidirectional camera 34, the microphone 54, the eye camera 58, and the wireless tag reader (tag reader) 86, which also functions as the environment sensor 106. Therefore, the detection signals from the omnidirectional camera 34, the microphone 54, the eye camera 58, and the tag reader 86 or the analysis results based on the detection signals are transmitted (notified) to the recording control device 102 at all times or at regular intervals. Further, as described above, since the robot 12 can run on its own, the position of the detection range of each of the sensors (34, 54, 58, 86) is changed according to the movement (displacement) of the robot 12.

  In such an environment 200, the system 10 records (history), for example, human communication behavior in the environment where the robot 12 exists, communication behavior between the robot 12 and a human, and communication behavior between humans. For example, by analyzing such a record, the analysis result can be used for developing an application for executing a service provided by the robot 12, or the analysis result can be used for an event venue where the robot 12 is arranged. Get design (installation) tips.

  For example, in a surveillance video recording apparatus using a conventional surveillance camera, a change in the video signal for each frame is detected, and the video signal is recorded on a recording medium such as a magnetic tape only when the change occurs. is there. As a result, the recording medium is efficiently used.

  However, since such a monitoring video recording apparatus performs recording control based only on a change in the video signal, it cannot be applied to the system 10 having various types of environmental sensors 106. For example, when the robot 12 and a person (A, B, C) are talking, there is a possibility that such a conversation may not be recorded because the video signal hardly changes. . Further, when the detection signals of all the environmental sensors 106 are recorded due to the change of the video signal, even the detection signals of the environmental sensors 106 that do not detect any communication behavior of the robot 12 or human (A, B, C) are recorded. Will end up. This wastes the storage area of the recording medium (in this embodiment, the sensor information DB 104).

  Therefore, in this embodiment, when there is a trigger for starting recording (hereinafter referred to as “recording start trigger”), the detection signal (position) of the sensor including the robot 12 and the human (A, B, C) in the detection range. Only information, video signals, tag information, audio signals, tactile (contact) signals, etc.) are recorded in the recording medium, that is, the sensor information DB 104. However, actually, in addition to the detection signal, the sensor information DB 104 includes the identification information (sensor ID) of the sensor that detected the detection signal and the human (A, B, C) or robot detected by the sensor. Twelve pieces of identification information (tag ID) are recorded. When there is a trigger for ending recording (hereinafter referred to as “recording end trigger”) corresponding to the recording start trigger, the sensor information DB 104 of the detection signal of the sensor that started recording in response to the recording start trigger is sent to the sensor information DB 104. End recording.

  However, the detection signals from all the environmental sensors 106 installed in the environment 200 are output to the recording control device 102 together with the sensor ID of each environmental sensor 106 at all times or at regular intervals (for example, 2 to 3 seconds). Thus, detection signals for a predetermined time (for example, 60 seconds) are temporarily stored (buffered) in the RAM 102b and recorded in the sensor information DB 104 as necessary.

  In this embodiment, the recording start trigger and the recording end trigger are determined in advance and are managed in a trigger information table as shown in FIG. As will be described later in detail, the presence / absence of a recording start trigger or a recording end trigger is executed according to a detection signal from the environment sensor 106 or a notification (message) from the robot 12.

  As shown in FIG. 5, the trigger information table describes a recording start trigger and a corresponding recording end trigger. A set of a recording start trigger and a recording end trigger is distinguished by identification information (trigger ID). In this embodiment, the trigger ID is expressed by using Roman letters (Tr) and numerals, but the trigger ID need not be limited to this, and the trigger ID may be expressed by only Roman letters or numerals, It may be represented by information that cannot be deciphered.

  As shown in FIG. 5, when the trigger ID is Tr1, the recording start trigger is “approaching the robot”, and the corresponding recording end trigger is “away from the robot”. The tag reader 86 of the robot 12 detects identification information from the tag 250 attached to a person (A, B, C), and notifies the recording control apparatus 102 of the distance calculated based on the radio wave intensity at that time. The recording control apparatus 102 detects “approaching the robot” when the distance notified from the robot 12 is equal to or less than a certain value (1 m in this embodiment). Similarly, when the distance calculated based on the radio wave intensity at the time of detecting the identification information from the tag 250 notified from the robot 12 exceeds a certain value (1 m), the recording control device 102 reads “From the robot. Detected “away”.

  When the trigger ID is Tr2, the recording start trigger is a predetermined action of a person (A, B, C) such as “walking” or “standing”, and the corresponding recording end trigger is “exit from environment” or “ For example, the above-mentioned predetermined operation ends, such as “no sound for a certain period of time”. The recording control device 102 detects the identification information from the tag 250 attached to the person (A, B, C) by the tag reader 86 or the tag reader 106b of the robot 12, and also uses the detection signal from the floor sensor 106a to detect the person ( The position of A, B, C) is detected. Therefore, it is possible to know the movement amount and movement trajectory of a person (A, B, C) in a certain time. Thereby, “walking” is detected. However, the recording control apparatus 102 has no change in the movement amount or movement locus of the person (A, B, C), and the sound signal is detected by the microphone 106d in the vicinity of the person (A, B, C). If there is, “talking” is detected.

  Although not shown, when a laser distance meter is arranged as the environmental sensor 106, a human (A) can be obtained by adopting the method described in Japanese Patent Application No. 2009-76450 filed earlier by the present applicant. , B, C) can be determined to be walking or stationary.

  Further, the recording control device 102 detects that “exit from the environment” when the identification information from the tag 250 attached to the person (A, B, C) is not detected by the tag readers 86 and 106b. In addition, when the state in which the audio signal from the microphone 106d is equal to or lower than a certain level (level determined to be silent) continues for a certain time (for example, 30 seconds) or more, “no sound for a certain time” is detected.

  When the trigger ID is Tr3, the recording start trigger is “congestion above a certain level”, and the corresponding recording end trigger is “congestion below a certain level”. Based on the detection signal (coordinate data) from the floor sensor 106a, the recording control apparatus 102 detects a plurality of items not registered in the map in advance, and occupies a certain ratio or more in a certain region (within range). In this case, “congestion above a certain level” is detected. However, the map is a sketch when the environment 200 is viewed from above, and is shown in a two-dimensional plane. Although omitted in FIG. 4, the items registered in advance in the map are, for example, pillars, shelves, desks, chairs, foliage plants, etc., fixedly arranged items and similar items (mostly moved) This is the case. Further, the recording control apparatus 102 detects “congestion less than a certain amount” when the ratio is less than the above certain ratio.

  When the trigger ID is Tr4, the recording start trigger is “a certain number or more”, and the corresponding recording end trigger is “less than a certain number”. The recording control apparatus 102 detects “a certain number of persons” when the types of identification information of the tags 250 detected by the tag readers 86 and 106 b are a certain number or more. The recording control apparatus 102 detects “less than a certain number of people” when the type of identification information of the tag 250 detected by the tag readers 86 and 106b is less than a certain number.

  When the trigger ID is Tr5, the recording start trigger is “action in a group”, and the corresponding recording end trigger is “group leaves the environment” or “cancellation of group”. As described above, the recording control apparatus 102 detects that the person (A, B, C) is walking or stopped based on the detection signal from the floor sensor 106a, and further detects the floor sensor 106a. Based on the detection signal from, when multiple people are walking in the same direction or staying in a certain place as a unit, they can walk in groups or line up in groups, etc. Is detected. In addition, the recording control apparatus 102 is configured so that when the number of coordinate data detected by the floor sensor 106a is greatly reduced and the number of identification information detected by the tag readers 86 and 106b is greatly reduced, a person (A, B, C) determines that the user has left the environment, and detects that the group has left the environment. Further, the recording control apparatus 102 detects “group release” when the distance between the coordinates indicated by the plurality of coordinate data detected by the floor sensor 106a is a certain distance (for example, 3 m) or more. However, the condition that the distance between coordinates is more than a certain distance does not have to be the distance between all coordinates, and a certain number (for example, half) or a certain ratio (for example, 50%) between coordinates. The distance only needs to satisfy the condition.

  When the trigger ID is Tr6, the recording start trigger is “sound from a specific direction”, and the corresponding recording start trigger is also “sound from a specific direction”. The recording start device 102 detects a direction in which sound is input by using the microphone 106d having directivity, and detects “sound from a specific direction” when the detected direction is a specific direction. However, a direction in which sound is generated may be detected by arranging a microphone array in the environment 106. However, the “specific direction” for the recording start trigger and the “specific direction” for the recording end trigger may be the same direction or different directions. These are set as appropriate by the developer or user of the system 10.

  When the trigger ID is Tr7, the recording start trigger is “talked from the robot”, and the corresponding recording end trigger is “separated from the robot”. When the robot 12 speaks to a person (A, B, C) existing in the vicinity, the recording control apparatus 102 is notified of this. Upon receiving this notification, the recording control apparatus 102 detects “talked from the robot”. However, the robot 12 knows that a person (A, B, C) exists in the vicinity based on the image taken by the omnidirectional camera 34 and / or the eye camera 58 and the identification information detected by the tag reader 86. . The same applies hereinafter. In addition, as described above, when the distance calculated based on the radio wave intensity at the time of detecting the identification information from the tag 250 notified from the robot 12 exceeds a certain value (1 m). , Detecting “away from robot”. The same applies hereinafter.

  When the trigger ID is Tr8, the recording start trigger is “beginning to touch the robot”, and the corresponding recording end trigger is “away from the robot”. When the robot 12 is touched by a person (A, B, C) existing in the vicinity thereof, the recording control apparatus 102 is notified of this. Upon receiving this notification, the recording control apparatus 102 detects “beginning to touch the robot”. However, the robot 12 detects that a person (A, B, C) is touching based on the detection signal of the contact sensor 46.

  When the trigger ID is Tr9, the recording start trigger is “start of shaking hands”, and the corresponding recording end trigger is “end of shaking hands” or “away from the robot”. When the robot 12 starts a communication action regarding “handshake”, the robot 12 notifies the recording control apparatus 102 of that. Upon receiving this notification, the recording control apparatus 102 detects “start of shaking hands”. In addition, when the robot 12 finishes the communication action regarding “handshake”, the robot 12 notifies the recording control apparatus 102 of that. Upon receiving this notification, the recording control apparatus 102 detects “end of handshake”.

  When the trigger ID is Tr10, the recording start trigger is “start of hug” and the corresponding recording end trigger is “end of hug” or “away from robot”. The robot 12 notifies the recording control apparatus 102 of the start of the communication behavior regarding “cuddle”. Upon receiving this notification, the recording control apparatus 102 detects “the start of hug”. In addition, when the robot 12 finishes the communication behavior regarding “cuddling”, the robot 12 notifies the recording control apparatus 102 of the fact. Upon receiving this notification, the recording control apparatus 102 detects “end of hug”.

  When the trigger ID is Tr11, the recording start trigger is “start of shaking hands”, and the corresponding recording end trigger is “end of shaking hands” or “exit from the environment”. When the robot 12 starts a communication action about “waving hand (bye-bye)”, the robot 12 notifies the recording control apparatus 102 of the communication action. Upon receiving this notification, the recording control apparatus 102 detects “start of shaking hands”. Further, when the robot 12 finishes the communication action for “waving hand”, the robot 12 notifies the recording control apparatus 102 of this. Upon receiving this notification, the recording control apparatus 102 detects “end of waving”.

  When the trigger ID is Tr12, the recording start trigger is “look into the robot's face”, and the corresponding recording end trigger is “away from the robot”. When the robot 12 analyzes the image captured by the eye camera 56 and detects, for example, a flesh-colored lump that approximates an egg shape (ellipse), the human (A, B, C) face is placed in front of its own face. Detect the presence. At this time, the robot 12 notifies the recording control apparatus 102 of that. Upon receiving this notification, the recording control apparatus 102 detects “looking into the robot's face”. However, a face image of a specific person (A, B, C) is stored, and the shape and position of a specific part (eye, eyebrows) are detected from the image captured by the eye camera 56, and based on the detected shape and position, You may make it detect that the face of a human (A, B, C) exists in front of the own face. However, image data is transmitted from the robot 12 to the recording control device 102, and the recording control device 102 may detect whether the human (A, B, C) face is in front of the face of the robot 12. Good.

  When the trigger ID is Tr13, the recording start trigger is “Human has spoken to the robot”, and the corresponding recording end trigger is “Separated from the robot”. When the robot 12 detects the identification information of the tag 250 by the tag reader 86 and detects an audio signal of a certain level (a level considered to be spoken to humans) through the microphone 54, the recording control device 102 detects that. Notify Upon receiving this notification, the recording control apparatus 102 detects that “a human has spoken to the robot”. However, the “level that seems to be spoken to humans” can be obtained empirically by testing or the like.

  When the trigger ID is Tr14, the recording start trigger is “the behavior of the group with respect to the robot”, and the corresponding recording end trigger is “the end of the behavior of the group” or “away from the robot”. For example, the behavior of a group is an orderly and cluttered human (A, B, C) behavior. The presence / absence (start / end) of the behavior of the group is determined by executing the group state estimation process described in Japanese Patent Application Laid-Open No. 2008-225852 filed earlier by the applicant of the present application and published. Since the collective state estimation process itself is not the essential content of the present invention, the description thereof will be omitted.

  Note that the recording start trigger and the recording end trigger shown in FIG. 5 are examples, and need not be limited to these. It may be changed as appropriate according to the environment 200 to which the robot 12 is applied.

  As can be seen from FIG. 5, there may be a plurality of recording end triggers corresponding to the recording start trigger.

  According to the trigger information table described above, the recording control apparatus 102 starts or ends recording of the detection signal of the environment sensor 106. However, as described above, the detection signal is recorded only for the environment sensor 106 in which the detection range includes the robot 12 and the person (A, B, C).

  Specific examples of the detection range of each environmental sensor 106 are shown in FIGS. 6 (A), (B), and (C). However, FIGS. 6A, 6 </ b> B, and 6 </ b> C illustrate a case where the environment 200 is viewed from above. As shown in FIG. 6A, the detection range of the floor sensor 106a coincides with the entire or substantially entire floor surface or ground (two-dimensional plane) of the environment 200. Therefore, the recording control apparatus 102 can detect the positions of the robot 12 and the humans (A, B, C) existing in the environment 200 based on the output (detection signal) of the floor sensor 106a. Although details of the map are not shown here, map data 404d (see FIG. 8) corresponding to the map is stored in the RAM 102b of the recording control apparatus 102. In addition, as shown in FIG. 7A, an XY coordinate system is set corresponding to a two-dimensional plane map. For example, in this XY coordinate system, the lower left vertex on the horizontal plane of the environment 200 is the origin O (0, 0), the horizontal direction is the X axis, and the vertical direction is the Y axis. Further, the right direction from the origin O is the plus direction of the X axis, and the upward direction from the origin O is the plus direction of the Y axis. However, in this embodiment, the coordinates of the lower right point P1 of the environment 200 are (x1, y1), the coordinates of the upper left point P2 of the environment 200 are (x2, y2), and the upper right point P3 of the environment 200 is The coordinates are (x3, y3). Accordingly, the detection range of the floor sensor 106a is the coordinates (0, 0) of the origin O, the coordinates (x1, y1) of the point P1, the coordinates (x2, y2) of the point P2, and the coordinates (x3, y3) of the point P3. Can be prescribed. The same applies hereinafter.

  FIG. 6B shows the detection ranges of the first to seventh tag readers 106b. As shown in FIG. 7B, the detection range of one tag reader 106b is defined by a circle having a radius r with the arrangement position as the center. The arrangement positions of the first to seventh tag readers 106b are determined in advance and are also shown on the map although illustration is omitted. However, in this embodiment, since the robot 12 and humans (A, B, C) in the environment 200 are detected, as shown in FIG. 6B, the range that protrudes from the environment 200 in the detection range of the tag reader 106b. Is not shown. The same applies hereinafter.

  In addition, although illustration is abbreviate | omitted, the detection range of the tag reader 86 of the robot 12 is prescribed | regulated similarly. However, the tag reader 86 is different from the other tag reader 106b in that its detection range is moved according to the position of the robot 12.

  Although not shown, the detection range of the sound sensor, that is, the microphone 106d is also defined by a circle with a certain radius around the arrangement position, like the detection range of the tag reader 106b. However, in the microphone 106d having directivity, the detection range is defined by a sector shape in which a curved surface faces in that direction so as to detect sound from a certain direction.

  Further, FIG. 6C shows respective detection ranges of the first camera 106c and the second camera 106c in the environment 200. When the environment 200 is bisected at the center in the X-axis direction, as can be seen from FIG. 6C, the detection range of the first camera 106c is the left half of the environment 200, and the detection range of the second camera 106c. Is the right half of the environment 200. However, in FIG. 6C, in order to show the detection ranges of the first camera 106c and the second camera 106c in an easy-to-understand manner, the detection ranges are shown to be slightly small. The entire two-dimensional plane can be detected (captured). Therefore, for example, the detection range of the first camera 106c is defined by the origin O, coordinates (x1 / 2, y1), coordinates (x2, y2), and coordinates (x3 / 2, y3). The detection range of the second camera 106c is defined by coordinates (x1 / 2, y1), coordinates (x1, y1), coordinates (x3 / 2, y3), and coordinates (x3, y3).

  In FIG. 6A, the floor sensor 106a is spread over the entire floor surface of the environment 200. However, unnecessary portions in the environment 200, that is, robots 12 and humans (A, B, C) move. The floor sensor 106a may not be provided in a place or area where it is difficult to stop or stop.

  In addition, the arrangement positions and detection ranges of the tag reader 106b and the camera 106c shown in FIGS. 4, 6B, and 6C are merely examples, and the robot 12 and humans (A, B, As long as C) can be detected, different arrangement positions and detection ranges may be adopted. For example, if the tag reader 106b with a wide detection range is used, the number can be reduced. Conversely, if the tag reader 106b with a narrow detection range is used, the number needs to be increased, but the detection accuracy is considered to increase. . Further, the detection ranges of the two cameras 106c may be set slightly larger so that the central portions overlap.

  FIG. 8 is an illustrative view showing one example of a memory map 400 of the RAM 102b shown in FIG. As shown in FIG. 8, the RAM 102 b includes a program storage area 402 and a data storage area 404. The program recording area 402 stores a program (recording control program) for recording the detection signal from the environment sensor 106 in the sensor information DB 104. The recording control program includes a main processing program 402a, a communication program 402b, a sensor information recording program 402c, and the like.

  The main processing program 402a is a program for processing the main routine of recording control of this embodiment. The communication program 402b is a program for executing communication with another computer or the like. In this embodiment, the communication program 402b mainly executes communication with the computer (CPU 60) of the robot 12. The sensor information recording program 402c is a program for recording a detection signal from the environmental sensor 106 in the sensor information DB 104 as necessary. Specifically, the sensor information recording program 402c determines whether or not a recording start trigger has occurred, and when the recording start trigger has occurred, the detection range includes the robot 12 and a person (A, B, C). The detection signal of the environmental sensor 106 is recorded in the sensor information DB 104. Further, the sensor information recording program 402c determines whether or not a recording end trigger has occurred, and when a recording end trigger has occurred, recording of the detection signal that has started recording when the corresponding recording start trigger has occurred. Exit.

  Although illustration is omitted, the program storage area also stores a program for temporarily storing a detection signal from the environment sensor 106.

  In the data storage area 404, a data buffer 404a is provided. The data storage area 404 stores subject information data 404b, sensor information data 404c, map data 404d, sensor detection range data 404e, trigger information data 404f, and recording information data 404g.

  The data buffer 404a is provided for temporarily storing a detection signal from the environment sensor 106. In this embodiment, a detection signal for a fixed time (60 seconds) is temporarily stored, and the detection signal after a fixed time is deleted.

  The subject information data 404b is data about a table (subject information table) for managing tag IDs for one or more robots 12 and one or more humans existing in or entering the environment 200. is there. As shown in FIG. 9A, in the subject information table according to the subject information data 404b, the name of the subject (human, robot) is described corresponding to the tag ID.

  In FIG. 9A, for the sake of simplicity, the tag ID is represented using two Roman characters. The tag ID may be represented by numerals, may be represented using both Roman letters and numerals, or may be represented by information that cannot be deciphered by humans.

  In FIG. 9A, for the sake of simplicity, the names of subjects are abstractly shown as humans A, B, C,..., Robots R1,.

  Returning to FIG. 8, the sensor information data 404 c is obtained by detecting identification information (sensor ID) about the environmental sensor 106 arranged in the environment 200 and the environmental sensor 106 provided in the robot 12 and each detection signal of the environmental sensor 106. It is a table (sensor information table) for managing information (recording start number) whether or not to record in the information DB 104. In this embodiment, the name of the environmental sensor 106 and the recording start number are described corresponding to the sensor ID.

  In FIG. 9B, for the sake of simplicity, the sensor ID is represented by one or two digits. However, the sensor ID may be represented by a romaji or both a numeral and a romaji. It may be represented by information that cannot be deciphered.

  Further, as shown in FIG. 9B, the environmental sensor 106 having the same name is given an identifiable word such as first, second,.

  The recording start number is information for determining whether or not to record the detection signal of the corresponding environmental sensor 106 in the sensor information DB 104. Specifically, if the recording start number is a positive number, the detection signal of the corresponding environment sensor 106 is recorded in the sensor information DB 104, and if the recording start number is 0, the detection signal of the corresponding environment sensor 106 is Not recorded in the information DB 104. However, when a predetermined recording start trigger is generated, the start of recording of the detection signal of the environmental sensor 106 including at least one of the robot 12 and the human (A, B, C) in the detection range is instructed. 1 is added. On the other hand, when a predetermined recording end trigger is generated, 1 is subtracted from the recording start number for the environmental sensor 106 instructed to start recording when the corresponding predetermined recording start trigger is generated.

  The number of recording starts is managed in this way, for example, when a detection signal from the same environmental sensor 106 is recorded due to the occurrence of a recording start trigger with a different trigger ID, corresponding to any one recording start trigger. This is to prevent the recording of the detection signal of the environmental sensor 106 from being terminated due to the occurrence of the recording end trigger.

  Returning to FIG. 8, the map data 404 d is data regarding the map of the environment 200. This map of the environment 200 is used to specify the positions of the robot 12 and humans (A, B, C) and to determine the arrangement positions (position coordinates) of the environmental sensors 106. The sensor detection range data 404e is data for defining a detection range for each environmental sensor 106.

  The trigger information data 404f is data on the trigger information table shown in FIG. As described above, in the trigger information table, the recording start trigger and the recording end trigger are described corresponding to the trigger ID.

  The record information data 404g is data on a table (record information table) for managing the environmental sensor 106 that is recording the detection signal. As shown in FIG. 10, in the recording information table according to the recording information data 404g, information (sensor ID) about the environmental sensor 106 in which the detection signal is recorded in the sensor information DB 104, and the trigger ID of the recording start trigger. The tag IDs of the robot 12 and the human (A, B, C) that are detection targets of the environmental sensor 106 indicated by the sensor ID are described. In this recording information table, when a recording start trigger occurs, the trigger ID, the sensor ID being recorded, and the target tag ID are written (added), and when a recording end trigger occurs, the corresponding recording start trigger Trigger ID, sensor ID being recorded, and target tag ID are deleted from the record information table.

  The recording information data 404g is stored in this way in order to monitor the above-described recording start number and correctly record the detection signal of the environmental sensor 106 in the sensor information DB 104. In addition, even if the same type of recording start trigger occurs in another place in the environment 200, they can be identified.

  Although not shown, other data is stored in the data storage area 404, and flags and counters (timers) necessary for the recording control process are provided.

  FIGS. 11 to 13 are flowcharts showing a specific recording control process of the CPU 102a shown in FIG. As shown in FIG. 11, when the recording control process is started, the CPU 102a determines whether or not a person (A, B, C) or the robot 12 exists in the environment 200 in step S1. Specifically, the CPU 102a refers to the data buffer 404a and determines whether a tag ID is stored.

  If “NO” in the step S1, that is, if there are no humans (A, B, C) and the robot 12 in the environment 200, the recording control process is ended as it is. Although a detailed description is omitted, when the recording control process is ended, the recording control process is started again after a predetermined time (for example, 30 seconds) elapses. same as below. On the other hand, if “YES” in the step S 1, that is, if a person (A, B, C) or the robot 12 exists in the environment 200, the person (A, B, C) existing in the environment 200 and An ID (processing ID) used for the recording control process is assigned to the robot 12. For example, the processing ID is 1, 2,..., M (m is an integer). This processing ID is used to determine whether the coordinates (current position) of the human (A, B, C) and the robot 12 are included in the detection range of the environmental sensor 106. It is used to determine whether or not it is individual.

  In the next step S5, it is determined whether or not there is an end instruction. That is, the CPU 102a determines whether or not an end instruction has been input by the operator of the recording control apparatus 102. If “YES” in the step S5, that is, if there is an instruction to end, the recording control process is ended as it is. On the other hand, if “NO” in the step S5, that is, if there is no instruction to end, it is determined whether or not the number of persons (A, B, C) or the robot 12 has increased in a step S7. That is, the CPU 102a refers to the data buffer 404a to determine whether the tag ID type has increased.

  If “NO” in the step S7, that is, if the number of humans (A, B, C) or the robot 12 is not increased, the process proceeds to a step S11 shown in FIG. On the other hand, if “YES” in the step S7, that is, if the number of humans (A, B, C) or the robot 12 increases, the processing ID is assigned to the increased humans (A, B, C) or the robot 12 in a step S9. Is assigned, the process proceeds to step S11.

  In step S11 shown in FIG. 12, an initial value is set to the variable i. Here, as described above, the variable i is a variable for sequentially executing the determination process for the person (A, B, C) and the robot 12 to which the process ID is attached. Subsequently, in step S13, it is determined whether there is a recording start trigger. Although illustration is omitted, the process of determining whether or not a recording start trigger (the same as a recording end trigger described later) has occurred is executed by another task.

If “NO” in the step S13, that is, if there is no recording start trigger, it is determined whether or not there is a recording end trigger in a step S15. If “NO” in the step S15, that is, if there is no recording end trigger, the process returns to the step S5 shown in FIG. On the other hand, if “YES” in the step S15, that is, if there is a recording end trigger, the recording start number _Sj of the sensor ID corresponding to the recording end trigger is decremented by 1 in a step S17. That is, referring to the recording information table shown in FIG. 10, in step S15, one or more recordings that are described in correspondence with the trigger ID of the recording start trigger for the recording end trigger determined to be present are performed. The sensor ID is acquired, and 1 is subtracted from the recording start number described corresponding to each of the acquired one or more sensor IDs.

In the next step S19, the trigger ID of the recording start trigger, the sensor ID being recorded, and the detected tag ID corresponding to the recording end trigger are deleted from the recording information table. At this time, when there are a plurality of recording start triggers corresponding to the recording end trigger, they are distinguished by the detected tag ID. Subsequently, in step S21, the recording of the detection signal of the sensor j having the recording start number S _j = 0 is terminated by the processing in step S17, and in step S23, it is determined whether there is recording information. That is, the CPU 102a determines whether or not recording information (trigger ID, sensor ID, tag ID) is described in the recording information table. If “YES” in the step S23, that is, if there is recording information, the process returns to the step S5. On the other hand, if “NO” in the step S23, that is, if there is no recording information, the recording control process is ended as it is.

  If “YES” in the step S13, that is, if there is a recording start trigger, it is determined whether or not the variable i exceeds the maximum value (the maximum number of m) in a step S25. In other words, the CPU 102a has performed a process of determining whether or not the coordinates (current position) are included in the detection range of the environment sensor 106 for all humans (A, B, C) and the robot 12 existing in the environment 200. It is determined whether or not.

  If “YES” in the step S25, that is, if the variable i exceeds the maximum value, the process returns to the step S5. On the other hand, if “NO” in the step S25, that is, if the variable i is equal to or less than the maximum value, the variable j is initialized (j = 1) in a step S27. However, the variable j is a variable for identifying the environmental sensor 106 individually.

  As shown in FIG. 13, in the next step S29, it is determined whether or not the coordinate of the variable i is within the detection range of the sensor j. Here, the CPU 102a refers to the sensor detection range data 404e, obtains a detection range for the sensor j, and coordinates of the human 12 (A, B, C) or robot 12 identified by the variable i in this detection range. It is determined whether or not (current position) is included.

  Although detailed description is omitted, the coordinates (current position) of the person (A, B, C) or the robot 12 are the installation positions (current position) of the tag readers 86 and 106b detecting their tag IDs. It is determined based on the detection signal (coordinate data) from the floor sensor 106a.

If “NO” in the step S29, that is, if the coordinates of the variable i are outside the detection range of the sensor j, the process proceeds to a step S37 as it is. On the other hand, if "YES" in the step S29, that is, if the coordinates of the variable i is within the detection range of the sensor j at step S31, and adds 1 to the recording start number S _j of the sensor j, step In S33, it is determined whether or not the recording start number _Sj is 1. Here, the CPU 102a determines whether or not recording of the detection signal of the sensor j has already started. However, the recording start number S _j of each sensor j, when the recording control process is started, (set to 0) to be reset.

If “NO” in the step S33, that is, if the recording start number _Sj is 2 or more, the process proceeds to a step S37 as it is. On the other hand, if “YES” in the step S33, that is, if the recording start number _Sj is 1, recording of the detection signal of the sensor j is started in a step S35. That is, the CPU 102a starts recording the detection signal of the sensor j in the sensor information DB 104. However, at this time, in addition to the detection signal of the sensor j, the CPU 102a also records the sensor ID of the sensor j and the tag ID of the human (A, B, C) or the robot 12 detected by the sensor j.

  Next, in step S37, the trigger ID of the recording start trigger, the sensor ID during recording, and the detected tag ID are registered in the recording information table. Here, in step S13, the trigger ID of the recording start trigger determined to be present is described, the sensor ID of the sensor j determined to include the tag ID in the detection range is described, and the tag ID is It is described. That is, the CPU 102a updates the recording information data 404g. Subsequently, in step S39, the variable j is incremented by 1 (j = j + 1). In step S41, it is determined whether or not the variable j exceeds the maximum value. In other words, the CPU 102a determines whether or not the determination process for determining whether or not the coordinates of the variable i are included in the detection range is performed for all the sensors j.

  If “NO” in the step S41, that is, if the variable j is equal to or less than the maximum value, the process returns to the step S29. On the other hand, if “YES” in the step S41, that is, if the variable j exceeds the maximum value, the variable i is incremented by 1 (i = i + 1) in a step S43, and the process returns to the step S25 shown in FIG. .

  According to this embodiment, when a recording start trigger occurs, if a human or a robot exists within the detection range of the sensor, the detection signal of the sensor is recorded. Only the signal can be recorded. As a result, it is possible to prevent wasteful use of the storage capacity of the memory.

  In this embodiment, the recording of the detection signal of the sensor is started in response to the occurrence of the recording start trigger, and the recording of the detection signal of the sensor is ended in response to the occurrence of the recording end trigger. Since the detection signal is always stored (temporarily stored) in the memory of the recording control device, the sensor detection signal from a predetermined time (for example, 10 seconds) before the recording start trigger is recorded, or the recording end trigger is fixed. You may make it record the detection signal of a sensor until time (for example, 10 second), or perform both of them. In such a case, it is possible to analyze the communication behavior of the human and / or the robot before the recording start trigger is generated or after the recording end trigger is generated based on the recorded detection signal of the sensor.

  Also, (1) a detection signal is recorded from a recording start trigger to a recording end trigger, (2) a sensor detection signal is recorded from a certain time before the recording start trigger, and (3) a certain time of the recording end trigger. It is also possible to record the detection signals of the sensors until later, or (4) execute both (2) and (3) above. In such a case, one of (1) to (4) is set in advance corresponding to the recording start trigger (trigger ID), and the detection signal is recorded by a method determined according to the recording start trigger. do it.

DESCRIPTION OF SYMBOLS 10 ... Network robot system 12 ... Communication robot 24, 72, 74, 76, 78, 80 ... Motor 28 ... Infrared distance sensor 34 ... Omnidirectional camera 52 ... Speaker 54 ... Microphone 58 ... Eye camera 60 ... CPU
64 ... Memory 66 ... Motor control board 68 ... Sensor input / output board 70 ... Voice input / output board 82 ... Communication LAN board 84 ... Wireless communication device 86 ... Wireless tag reader 100 ... Network 102 ... Recording control device 102a ... CPU
104 ... Sensor information DB
106… Environmental sensor

Claims (8)

A recording control device that controls recording of detection signals from a plurality of sensors arranged in an environment where a robot and a human exist,
Recording start determining means for determining whether to start recording of the detection signals based on detection signals from the plurality of sensors;
When it is determined by the recording start determining means that recording of the detection signal is started, it is determined for each of the plurality of sensors whether at least one of the robot and the human is included in its own detection range. A position determination unit; and a recording start unit that starts recording of a detection signal of the sensor having the detection range when the position determination unit determines that at least one of the robot and the human is included in the detection range. A recording control apparatus.   The recording control apparatus according to claim 1, wherein the robot includes a part of the plurality of sensors.   The recording control apparatus according to claim 1, wherein the robot is a communication robot that executes a communication action using at least one of body motion and voice.   4. The recording control according to claim 1, wherein the recording start determination unit determines that recording of the detection signal is started when detection signals from the plurality of sensors satisfy a first predetermined condition. 5. apparatus. Based on the detection signals from the plurality of sensors, a recording end determination unit that determines whether or not to end recording of the detection signal, and the recording end determination unit determines to end recording of the detection signal. The recording control device according to claim 1, further comprising recording end means for ending recording of the detection signal.   The recording control apparatus according to claim 5, wherein the recording end determination unit determines to end recording of the detection signal when detection signals from the plurality of sensors satisfy a second predetermined condition. A plurality of first predetermined conditions, a second predetermined condition corresponding to each of the plurality of first predetermined conditions,
When it is determined that recording of the detection signal is to be ended, the recording end unit is configured to detect the detection signal that has started recording when a first predetermined condition corresponding to the second predetermined condition based on the determination is satisfied. The recording control apparatus according to claim 6, wherein only the recording is terminated. A recording control program for controlling recording of detection signals from a plurality of sensors arranged in an environment where a robot and a human exist.
On the computer,
A recording start determination step for determining whether to start recording of the detection signals based on detection signals from the plurality of sensors;
When it is determined in the recording start determination step that recording of the detection signal is started, it is determined whether each of the plurality of sensors includes at least one of the robot and the human in its own detection range. When the position determination step and the position determination step determine that at least one of the robot and the human is included in the detection range, recording of the detection signal of the sensor having the detection range to the storage medium is started. A recording control program for executing a recording start step.

Images