JP2012110996A - Movement control system of robot, movement control program of the robot, and movement control method of the robot - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide the movement control system of a robot, the movement control program of the robot, and the movement control method of the robot by which the manager of a system can make a robot 14 to which a role is set operate in the same way as a human having the same role.SOLUTION: The movement control system 100 includes a central control unit 10 having a role database (20) and the robot 14 to which a role is set. The role database (20) is configured of representative moving action data of the human having the role. For example, when a role of a "guard easy to talk to" is set to the robot 14, the representative moving action data of the "guard easy to talk to" is selected from the role database (20). In the central control unit 10, actions of the robot 14 with the role set thereto at a plurality of future positions and actions at the respective future positions are predicted on the basis of the representative moving action data, and the occurrence provability of each of the plurality of the predicted actions is calculated. The moving action is instructed to the robot 14 on the basis of the calculated occurrence provability.

Description

  The present invention relates to a robot movement control system, a robot movement control program, and a robot movement control method, and more particularly to, for example, a robot movement control system, a robot movement control program, and a robot movement control that determine a robot movement action. Regarding the method.

The environmental information structuring system disclosed in Non-Patent Document 1 understands the meaning and behavior of the environment from the behavior of people accumulated in large quantities, and predicts the global behavior of people. Then, using the predicted result, the robot can provide a service to a person who performs a specific global action.
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

  However, there has been no system that determines the movement behavior of a robot using the behavior of people accumulated in large quantities.

  Therefore, a main object of the present invention is to provide a novel robot movement control system, a robot movement control program, and a robot movement control method.

  Another object of the present invention is to provide a robot movement control system, a robot movement control program, and a robot movement control method capable of determining the movement behavior of a robot with a role set.

  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.

  A first invention is a robot movement control system including a database composed of a plurality of human movement behavior data having a role and a robot to which a role is set, based on the role set in the robot Selection means for selecting movement behavior data from the database, first prediction means for predicting a plurality of movement behaviors of the robot from the movement behavior data selected by the selection means, and each of the plurality of movement behaviors predicted by the first prediction means A robot movement control system comprising: calculation means for calculating an occurrence probability; and instruction means for instructing the robot to move based on a plurality of occurrence probabilities calculated by the calculation means.

  In the first invention, the movement control system (100: reference numerals exemplifying corresponding parts in the embodiment, hereinafter the same) includes a database (20) and a robot (14) composed of a plurality of movement behavior data. Including. Also, the movement behavior data includes the movement trajectory and behavior of a human having a role, and the role that the human has is set for the robot. For example, if the role of “easy to talk” is set for the robot, the selection means (16, S47) selects the movement behavior data of “easy to talk” from the database. The first predicting means (16, S49) predicts a plurality of movement behaviors of the robot having the role set based on the selected movement behavior data. The calculating means (16, S57, S59) calculates the occurrence probability of each of the predicted plurality of moving actions. Then, the instruction means (16, S61, S63), for example, instructs the robot to move behavior with the highest occurrence probability.

  According to the first invention, the movement behavior of the robot can be determined based on the movement behavior data of the human having the same role as the robot. Therefore, a robot with a set role can be operated in the same way as a human having the same role.

  A second invention is according to the first invention, further comprising movement trajectory acquisition means for acquiring a movement trajectory of the robot, wherein the selection means is a movement trajectory acquired by the movement trajectory acquisition means, a role set in the robot And based on the movement locus | trajectory contained in each movement action data, movement action data are selected from a database.

  In the second invention, the movement trajectory acquisition means (16, S45) acquires, for example, the current position of the robot continuously acquired by the LRF (12) as the movement trajectory of the robot. Then, the movement behavior data is selected from the database based on the movement locus role of the robot and the movement locus included in each movement behavior data.

  According to the second invention, it is possible to determine the movement behavior of the robot in consideration of the current position of the robot and the movement so far.

  A third invention is dependent on the first invention or the second invention, and the movement behavior predicted by the first prediction means includes a future position of the robot, and when a human is present around the robot, Second prediction means for predicting the future position is further provided, and the calculation means calculates the occurrence probability of a plurality of movement actions based on the future position of the robot excluding the human future position predicted by the second prediction means. .

  In the third invention, the first prediction means also predicts the future position of the robot as the movement behavior of the robot. The second predicting means (16, S55) predicts the future position of the human when, for example, the robot and the human are in the same region (E). Further, the second predicting means predicts the future position of the person based on the movement behavior data accumulated regardless of the role. Then, the calculation means calculates the occurrence probability of a plurality of movement actions based on the predicted future robot position from which the predicted future human position is removed.

  According to the third invention, since the robot cannot move to the position where the person is present, the movement behavior of the robot can be prevented from being predicted at the future position of the person.

  A fourth invention is a robot movement control system including a central control device (10), a database (20) composed of a plurality of human movement behavior data having roles, and a robot (14) in which roles are set. (100), the processor (16) of the central control unit selects the moving action data from the database based on the role set in the robot (S47), from the moving action data selected by the selecting means Prediction means (S49) for predicting a plurality of movement behaviors of the robot, calculation means (S57, S59) for calculating the respective occurrence probabilities of the plurality of movement behaviors predicted by the prediction means, and a plurality of calculations calculated by the calculation means Based on the probability of occurrence, let the robot function as instruction means (S61, S63) for instructing the movement action. It is a dynamic control program.

  In the fourth invention, similarly to the first invention, the movement behavior of the robot can be determined based on the movement behavior data of the human having the same role as the robot. Therefore, a robot with a set role can be operated in the same way as a human having the same role.

  The fifth invention provides a robot movement of a robot movement control system (100) including a database (20) composed of a plurality of human movement behavior data having roles and a robot (14) to which roles are set. According to the control method, the movement behavior data is selected from the database based on the role set in the robot (S47), and the plurality of movement behaviors of the robot are predicted from the selected movement behavior data (S49). The robot movement control method calculates the occurrence probability of each of the plurality of movement actions (S57, S59), and instructs the robot on the movement action based on the calculated occurrence probabilities (S61, S63). .

  In the fifth invention as well, similar to the first invention, the movement behavior of the robot can be determined based on the movement behavior data of the human having the same role as the robot. Therefore, a robot with a set role can be operated in the same way as a human having the same role.

  According to this invention, the movement behavior of the robot is determined based on the movement behavior data of the human having the same role as the robot. Therefore, the system administrator can operate a robot with a role set in the same way as a human having the same role.

  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 a robot movement control system according to an embodiment of the present invention. FIG. 2 is an illustrative view showing the appearance of the robot shown in FIG. 1 from the front. FIG. 3 is a block diagram showing an electrical configuration of the robot shown in FIG. FIG. 4 is a block diagram showing an electrical configuration of the central controller shown in FIG. FIG. 5 is an illustrative view showing a measurement region of the LRF shown in FIGS. 1 and 4. FIG. 6 is an illustrative view showing one example of a movement locus detected using the LRF shown in FIGS. 1 and 4. FIG. 7 is an illustrative view showing one example of a table included in the role database shown in FIG. FIG. 8 is an illustrative view showing one example of movement behavior data detected by the central control measure shown in FIG. FIG. 9 is an illustrative view showing one example of representative movement behavior data included in the role database shown in FIG. FIG. 10 is an illustrative view showing one example of a state in which the robot shown in FIG. 1 is moving. FIG. 11 is an illustrative view showing one example of a state in which the movement of the robot shown in FIG. 1 is controlled. FIG. 12 is an illustrative view showing another example of a state in which the movement of the robot shown in FIG. 1 is controlled. FIG. 13 is an illustrative view showing one example of a memory map of the memory shown in FIG. FIG. 14 is a flowchart showing the role database construction process of the CPU shown in FIG. FIG. 15 is a flowchart showing the role setting process of the CPU shown in FIG. FIG. 16 is a flowchart showing a part of the movement control process of the CPU shown in FIG. FIG. 17 is a part of the movement control process of the CPU shown in FIG. 4 and is a flowchart subsequent to FIG.

  Referring to FIG. 1, a robot movement control system 100 according to this embodiment includes a central control device 10 and autonomous mobile robots (hereinafter simply referred to as “robots”) 14 having several LRFs including LRFs 12a and 12b. Is provided. LRF12a, 12b is installed in the place (environment) where a human can move arbitrarily. A place where a human can act 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.

  The central controller 10 detects the movement trajectory of a human who moves arbitrarily by using the LRFs 12a and 12b. In addition, the central control device 10 accumulates in the database movement behavior data including movement trajectories acquired by the LRFs 12a and 12b and the movement modes (behaviors) indicated by the movement trajectories. Furthermore, the central control apparatus 10 sets a role for the robot 14 via the network 200 and gives the robot 14 an operation command for a movement action according to the role. In addition, a movement aspect, ie, action, can be calculated | required based on the moving speed in the space grid mentioned later.

  The role of the robot 14 is set by a system administrator, and the robot 14 operates based on an operation command given by the central controller 10. The robot 14 is also an interaction-oriented robot (communication robot), and communication behavior including at least one of body movements such as gestures and voices with a communication target (communication target) such as a human being. It has a function to execute.

  In FIG. 1, only one person is shown for simplicity, but the central control device 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.

  FIG. 2 is a front view showing the appearance of the robot 14 of this embodiment. Referring to FIG. 2, the robot 14 includes a carriage 30, and two wheels 32 and one slave wheel 34 for moving 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. 3), and the carriage 30, that is, the robot 14, can be moved in any direction, 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. 3) 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, the robot 14 can detect that there is a contact with an obstacle during its movement, and can immediately stop the driving of the wheel 32 and 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. 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. 3 is a block diagram showing an electrical configuration of the robot 14. With reference to FIG. 3, the 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). In the ROM, a control program for controlling the operation of the robot 14 is stored in advance. 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 buffer memory for the CPU 80.

  The motor control board 86 is composed of, for example, a DSP, and controls driving of each axis motor such as each arm, neck joint, and eyeball. 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. 3) 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. 3, collectively referred to 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. 3) 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. 3) are controlled.

  Further, the motor control board 86 receives 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. 3, collectively indicated as “head motor 110”). Control the rotation angle. The motor control board 86 receives control data from the CPU 80 and controls the rotation angles of the two motors (collectively indicated as “wheel motor 36” in FIG. 3) that drive the wheels 32. 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 composed of 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 indicated as “contact sensors 58” in FIG. 3) are provided to the CPU 80 via the sensor input / output board 88. Similarly, the voice input / output board 90 is also constituted by a DSP, and a voice or voice according to voice synthesis data given from the CPU 80 is outputted 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 composed of, 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 200. 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.

  FIG. 4 is a block diagram showing an electrical configuration of the central controller 10. Referring to FIG. 4, central controller 10 includes LRFs 12a-12f, CPU 16, and the like. The CPU 16 is also called a microcomputer or a processor. In addition to LRF 12a and LRF 12b described above, LRF 12c, LRF 12d, LRF 12e, and LRF 12f are also connected to CPU 16. Further, a memory 18, a role database 20, a prediction database 22, and a communication LAN board 24 are also connected to the CPU 16.

  In addition, when it is not necessary to distinguish LRF12a-12f, it is collectively called "LRF12."

  The LRF 12 measures the distance to the object from the time it takes to irradiate the laser, reflect off the object (including a human being), and return. 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 includes a ROM, an HDD, and a RAM, and a control program for controlling the operation of the central control device 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 buffer memory for the CPU 16.

  The role database 20 is a database composed of movement behavior data of a plurality of persons having roles. The prediction database 22 is a database in which mobile behavior data is accumulated for a certain period (for example, one week) regardless of the role of a person. In this embodiment, the movement of the robot 14 is controlled using the role database 20, and the future position of a person existing in the space is predicted using the prediction database 22.

  The communication LAN board 24 is configured by a DSP, for example, and provides transmission data given from the CPU 16 to the wireless communication device 26, and the wireless communication device 24 transmits the transmission data to the robot 14 via the network 200. For example, the transmission data may be an operation command signal (command) instructing the robot 14. The communication LAN board 24 receives data via the wireless communication device 26 and provides the received data to the CPU 16.

  Next, the LRF 12 will be described in detail. Referring to FIG. 5, 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, each of the LRFs 12 is arranged so that the detection regions overlap with each other, and although not shown, is 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. 6, 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 becomes the movement locus t. In the detection area E, XY coordinates are set, and the human position can be indicated by coordinates (X, Y).

  The role database 20 will be described in detail. The role database 20 includes a role table shown in FIG. 7A and a representative movement behavior data table shown in FIG.

  Referring to FIG. 7A, the role table is composed of columns of role ID, representative moving action ID, and average moving speed. The representative movement action ID column includes a plurality of columns corresponding to n (n is a natural number) representative movement action IDs.

  In the role ID column, “a”-“e” are recorded as IDs for identifying roles. For example, the role ID “a” represents “an easy-to-talk guard”. In the row where “a” is recorded in the role ID column, the representative movement action IDs “Ta1”, “Ta2”, “Tan”, and the like are recorded in each column of the representative movement action ID, and the average movement In the speed column, “700 mm / sec” is recorded. Therefore, the “security guard who is easy to talk” moves at a speed of about 700 mm / sec, and the movement trajectory indicated by the representative movement action ID “Ta1”, “Ta2” or “Tan” (see FIGS. 9A and 9B). You can see that it is moving like drawing.

  The role ID “b” represents “a guard who is difficult to talk to”. In the row where “b” is recorded in the role ID column, the representative movement behavior IDs “Tb1”, “Tb2”, “Tbn”, and the like are recorded in each column of the representative movement behavior ID, and the average movement In the speed column, “1200 mm / sec” is recorded. Therefore, the “security guard who is difficult to talk” moves at a speed of about 1200 mm / sec at the speed of the movement trajectory indicated by the representative movement action ID “Tb1”, “Tb2” or “Tbn” (see FIGS. 9C and 9D). You can see that it is moving like drawing.

  Further, the role ID “c” represents “cleaner”, the role ID “d” represents “monitorer who does not move so much”, and the role ID “d” represents “acceptor”. In addition, the column of the representative movement action ID in the row in which these role IDs are recorded has substantially the same configuration as the row in which the role ID “a” or the role ID “b” is recorded, and thus detailed description thereof is omitted. To do. In the average moving speed column, “600 mm / sec” is recorded corresponding to the role ID “c”, “100 mm / sec” is recorded corresponding to the role ID “d”, and the role ID “e” is recorded. Corresponding to “0 mm / sec” is recorded.

  Also, referring to FIG. 7B, the representative movement behavior data table includes a column of representative movement behavior IDs and a column of movement behavior data. In the column of the representative movement action ID, the same ID as the representative movement action ID recorded in the role table is recorded. In addition, in the column of movement action data, movement action data represented by coordinates (X, Y) constituting the movement locus and actions (A) performed at the coordinates are recorded.

  For example, “(Xa1, Ya1, Aa1), (Xa2, Ya2, Aa2),...” Is recorded in the movement behavior data column corresponding to the representative movement behavior ID “Ta1”. Corresponding to the representative movement action ID “Tb1”, “(Xb1, Yb1, Ab1), (Xb2, Yb2, Ab2),...” Is recorded in the movement action data column. Corresponding movement action data is also recorded in each of the representative movement action IDs “Tc1”, “Td1”, and “Te1”.

  In this way, the movement database corresponding to the role is recorded in the role database 20. When representative movement action data is read, the movement action data corresponding to the role set in the robot 14 is read after the role table is referred to.

  These five roles are determined on the assumption of people who are active on street corners, but in other embodiments, other roles may be added depending on the location and circumstances. For example, in another embodiment, the role of “a guard that does not move very much” may be added, which will remain stationary in one place for a few minutes and then turn or move slightly.

  Next, the movement trajectory and behavior included in the movement behavior data will be described. Referring to FIG. 8, when detection area E is formed into a spatial grid in a 25 cm square, and a person moves in detection area E, human movement trajectory Ht is obtained. Further, the moving speed is calculated for each grid, and the action (A) is obtained for each grid.

  For example, if the moving speed in a certain grid is equal to or lower than a first threshold (for example, 10 mm / sec), the action in the grid is “stopped”. Further, if the moving speed is greater than the first threshold and less than or equal to the second threshold (800 mm / sec), the action in the grid is “slowly going straight”. Furthermore, if the moving speed is greater than the second threshold, the moving speed in the grid is “straight forward and go straight”. In FIG. 8, the grid for which the action is determined to be “stop” is colored yellow (polka dot pattern in the drawing), and the grid for which the action is determined to be “slowly straight” is colored blue (horizontal stripe pattern in the drawing). The grid for which the action is determined to be “walk fast and go straight” is colored red (vertical stripe pattern in the drawing). In addition, the movement action in a present Example means the movement accompanying an above-described action.

  Based on these facts, the representative movement behavior data for “easy to speak security guards” and “hard to talk security guards” will be described. First, the movement action data of the representative movement action ID “Ta1” in FIG. 9A represents that “a security guard who is easy to talk” is “slowly going straight” so as to walk around the center. Further, the movement action data of the representative movement action ID “Ta2” in FIG. 9B represents that “a security guard who is easy to talk” is “slowly going straight” so as to draw a circle near the center of the space. From these representative movement behavior data, it can be seen that “the security guard who is easy to talk” slowly moves around the center as if it had no purpose.

  On the other hand, the movement data of the representative movement action ID “Tb1” in FIG. 9 (C) travels around the space along the edge of the space while the “security guard who is difficult to talk to” “walks straight ahead”. Represents that Further, the movement action data of the representative movement action ID “Tb2” in FIG. 9D indicates that the “security guard who is difficult to talk” is “straightly walking straight” on the right and upper fences of the space. From these representative movement behavior data, it can be seen that the “security guard who is difficult to talk to” moves quickly as if having a purpose.

  In this embodiment, when a role is set for the robot 14, representative movement behavior data is selected based on the role of the robot 14, and the movement behavior of the robot 14 is controlled based on the selected representative movement behavior data. Is done.

  First, in order to use the DP matching to select the representative movement action data, the movement trajectory of the robot 14 is converted into a state sequence. Further, in the role table, a plurality of representative movement behavior data is read based on the row of the representative movement behavior ID indicating the role set in the robot 14, and the movement included in each of the plurality of representative movement behavior data. The trajectory is converted to a state sequence. Further, the similarity between the state sequence of the robot 14 and each state sequence of each representative movement action data is calculated by DP matching. Then, representative movement action data is selected from the role database 20 based on the calculated similarity. In addition, since the method of comparing a movement locus | trajectory using DP matching is disclosed by the nonpatent literature 1, detailed description is abbreviate | omitted.

  Thus, since the representative movement behavior data can be selected using the movement locus of the robot 14, the movement behavior of the robot 14 can be determined in consideration of the current position of the robot 14 and the movement so far. .

  When representative movement behavior data is selected, behaviors at a plurality of future positions and a plurality of future positions are predicted at the current position of the robot 14. Furthermore, the probability of occurrence of each predicted action is calculated, and the 14 movement actions of the robot are determined based on the calculated occurrence probabilities. Then, the central control device 10 gives an operation command corresponding to the moving action determined in this way to the robot 14.

  For example, in the state shown in FIG. 10, the robot 10 moves while drawing a movement trajectory from left to right, and a “guard who is difficult to talk to” is set for the robot 14. In this case, based on the role of the robot 14 and the movement trajectory, the row of the representative movement action ID “b” is referred to, and the movement action data (see FIG. 9C) of the representative movement action ID “Tb1” is selected. The

  Then, referring to FIG. 11A, as the future position and action of the robot 14, the robot 14 “runs straight forward” on the right grid, “stops” on the same grid, and “walks fast” on the left grid. "Straight" is predicted. Furthermore, the occurrence probability is calculated for each predicted action, and the movement destination of the robot 14 is determined to be a grid where the action having the highest occurrence probability is obtained. Here, since the probability of occurrence of “straight forward by fast walking” is the highest in the right grid, the robot 14 moves straight to the right grid as shown in FIG. 11B.

  Further, with reference to FIGS. 11C and 11D, the future position and action of the robot 14 are predicted and continue to move to the right in the grid that has moved. That is, the robot 14 moves in the same manner as the movement locus included in the movement action data of the representative movement action ID “Tb1”.

  For example, a “security guard who is easy to talk to” has a lot of behavior that hangs around the center of the detection area E. Therefore, when the role of “an easy-to-talk guard” is set for the robot 14, the probability of the wandering moving action increases near the center of the detection area E. On the other hand, at the edge of the detection region E, the probability of occurrence of a moving action that moves near the center is high. In another embodiment, if the role of the “guard who does not move so much” is set in the robot 14, the probability of occurrence of a stationary moving action increases for a few minutes, and the occurrence of a moving action related to movement occurs after a few minutes. Probability increases.

  As described above, by accumulating the movement behavior data of the person having the role, the administrator can operate the robot 14 in the same space where the data is accumulated, as in the case of the person having the role.

  11A to 11D, the density of the grid pattern (color) varies depending on the occurrence probability. For example, in the case of a vertical stripe pattern (red) or a horizontal stripe pattern (blue), the stripe density (color density) increases as the generation probability increases. In the case of a polka dot pattern (yellow), the density of the polka dots (color density) increases as the probability of occurrence increases. The color density described above may be expressed in the same way in other drawings.

  Here, the case where the human H exists around the robot 14 will be described. First, referring to FIG. 12A to FIG. 12C, the robot 14 to which the “easy to talk” guard is set is the same as the movement trajectory included in the movement action data of the representative movement action ID “Ta1”. To move. When the person H is detected in the detection area E at the time shown in FIG. 12D, the future position and action of the person H are higher than the future position and action of the robot 14 at the next time. Predicted first. 12E and 12F, the future position and action of the robot 14 are predicted in a grid excluding the future position of the human H (range surrounded by a dotted line). That is, since the robot 14 cannot move to the position where the person advances, the future position and behavior of the robot 14 can be prevented from being predicted at the future position of the person.

  In another embodiment, a plurality of people may be detected in the detection area E at the same time. In this case, a future position is predicted for each of a plurality of humans.

  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. The program storage area 302 stores a role database construction program 310, a role setting program 312, a movement control program 314, and the like as programs for operating the central controller 10.

  The role database construction program 310 is a program for adding new movement behavior data to the role database 20. The role setting program 312 is a program for setting a role for the robot 14. The movement control program 314 is a program for controlling the movement behavior of the robot 14 with the role set.

  Although not shown, the program for operating the central control device 10 includes a program for establishing wireless communication with the robot 14.

  The data storage area 304 is provided with a movement trajectory buffer 330, a movement action prediction buffer 332, a representative movement action buffer 334, and an occurrence probability buffer 336. In the data storage area 304, map data 338 and role data 340 are stored.

  The movement locus buffer 330 temporarily stores the movement locus of the human and the robot 14 detected by the LRF 12. The movement behavior prediction buffer 332 temporarily stores a plurality of predicted future positions and behaviors of the robot 14 and humans. For example, the movement behavior prediction buffer 332 stores coordinates indicating a plurality of future positions and representative movement behavior IDs indicating behaviors associated with the coordinates. The representative movement action buffer 334 temporarily stores representative movement action data selected from the role database 20. In the occurrence probability buffer 336, the occurrence probability of the predicted action stored in the movement action prediction buffer 332 is temporarily stored.

  The map data 338 is image data of a map indicating the detection area E, and is a map in which the space is divided into grids as shown in FIG. 8, for example. The role data 340 is data indicating a role set for the robot 14.

  Although not shown, 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. It is done.

  Hereinafter, a program executed by the CPU 16 of the central controller 10 will be described. The flowchart of FIG. 14 shows processing by the role database construction program 310, the flowchart of FIG. 15 shows processing by the role setting program 312, and the flowcharts of FIGS. 16 and 17 show processing by the movement control program 314.

  FIG. 14 is a flowchart of the role database construction process. For example, when the administrator performs an operation of newly adding human movement behavior data with a role, the CPU 16 of the central control device 10 determines whether or not a start operation has been performed in step S1. That is, it is determined whether or not an operation for starting accumulation of human movement trajectory and behavior has been performed. If “NO” in the step S1, that is, if an operation to start is not performed, the process in the step S1 is repeatedly executed. If “YES” in the step S1, that is, if an operation to start is performed, the movement locus and the action are accumulated in a step S3. That is, the movement locus detected by the LRF 12 and the action indicated by the movement locus are stored in the movement locus buffer 330.

  Subsequently, in step S5, it is determined whether or not a predetermined time (for example, 60 seconds) has elapsed. That is, it is determined whether or not the movement trajectory and behavior sufficient to predict the movement behavior are accumulated. If “NO” in the step S5, that is, if the predetermined time has not elapsed, the process returns to the step S3. On the other hand, if “YES” in the step S5, that is, if a predetermined time elapses, it is determined whether or not a labeling operation is performed in a step S7. For example, it is determined whether or not an operation of attaching a label such as “an easy-to-talk guard” to the accumulated movement trajectory and action is performed. If “NO” in the step S7, that is, if a labeling operation is not performed, the process in the step S7 is repeatedly executed.

  If “YES” in the step S7, that is, if a labeling operation is performed, a representative movement action ID is added to the movement trajectory and action accumulated in the step S9 and added to the role database. For example, when an operation for labeling “easy to talk” is performed, a representative movement behavior ID of “easy to speak” is added to the accumulated movement trajectory and action and added to the representative movement behavior data table. To do. In addition, CPU16 which performs the process of step S9 functions as an addition means.

  Subsequently, in step S11, it is determined whether or not an end operation has been performed. That is, it is determined whether or not an operation for ending the role database construction process has been performed. If “NO” in the step S11, that is, if the end operation is not performed, the process returns to the step S1. On the other hand, if “YES” in the step S11, that is, if an end operation is performed, the role database construction process is ended.

  FIG. 15 is a flowchart of role setting processing. For example, when the administrator performs a process for setting a role in the robot 14, the CPU 16 determines whether or not a role has been selected in step S21. For example, it is determined whether or not one role has been selected from among “security guards that are easy to talk to”, “security guards that are difficult to talk to”, “cleaners”, “supervisors that do not move much”, and “receptionists”. If “NO” in the step S21, that is, if a role is not selected, the process of the step S21 is repeatedly executed. If “YES” in the step S21, that is, if a role is selected, the role selected in the robot 14 is set in a step S23, and the role setting process is ended.

  For example, if “easy to talk” is selected, in step S <b> 23, “easy to talk” is set for the robot 14. Further, the set role is stored in the memory 18 as role data 340. In addition, CPU16 which performs the process of step S23 functions as a role means.

  16 and 17 are flowcharts of the movement control process. For example, when the central controller 10 is turned on, the CPU 16 acquires the role set in the robot 14 in step S41. That is, the role set for the robot 14 is acquired from the role data 340. Subsequently, in step S43, it is determined whether or not the end operation is performed. That is, it is determined whether or not an operation for ending the movement control process has been performed. If “NO” in the step S43, if the end operation is not performed, the current position and movement locus of the robot are acquired in a step S45. That is, the movement locus stored in the movement locus buffer 330 is read, and the last position of the movement locus is acquired as the current position. In addition, CPU16 which performs the process of step S45 functions as a movement locus | trajectory acquisition means.

  In step S47, representative movement action data is selected based on the role of the robot 14, the current position, and the movement locus. First, the CPU 16 reads each representative movement action ID from the role ID line indicating the role of the robot 14. Next, the CPU 16 converts the movement trajectory included in the movement behavior data indicated by each representative movement behavior ID and the movement trajectory of the robot 14 into a state sequence, and calculates the similarity by DP matching. Then, the representative movement behavior data having the highest similarity is selected from the representative movement behavior data table of the role database 20. The selected representative movement behavior data is stored in the representative movement behavior buffer 334. The CPU 16 that executes the process of step S47 functions as a selection unit.

  Subsequently, the future position and behavior of the robot 14 are predicted in step S49. That is, based on the selected representative movement action data, a plurality of future positions and actions at the next time are predicted. In addition, CPU16 which performs the process of step S49 functions as a 1st prediction means.

  Subsequently, in step S51, it is determined whether or not a human is present around. That is, it is determined whether or not a person is detected in the detection area E. If “YES” in the step S51, that is, if a human is present in the detection area E, a moving locus of the human is acquired in a step S53. That is, a human movement trajectory is acquired from the movement trajectory buffer 330. Subsequently, in step S55, the future position of the person is predicted based on the movement locus of the person. That is, a movement trajectory similar to a human movement trajectory is selected from the prediction database 22 in the same manner as when predicting the future position of the robot 14. Based on the selected movement locus, the future position of the human at the next time is predicted. In addition, CPU16 which performs the process of step S55 functions as a 2nd prediction means.

  Subsequently, in step S57, the occurrence probability of the predicted action is calculated excluding the human future position. For example, as shown in FIG. 12E, the probability of occurrence of the action of the robot 14 is calculated at each future position of the robot 14 except for the future position of the human. The calculated occurrence probability is stored in the occurrence probability buffer 336 in association with the coordinates indicating the future position.

  If no person is present in the vicinity, “NO” is determined in step S51, and the occurrence probability of the behavior predicted in step S59 is calculated. For example, as shown in FIG. 11A, the occurrence probability of the action at the future position of the robot 14 is calculated.

  In addition, CPU16 which performs the process of step S57 or step S59 functions as a calculation means.

  Subsequently, in step S61, the next moving action is determined based on the calculated occurrence probability. For example, when the occurrence probability is calculated as shown in FIG. 11A, since the action occurrence probability in the right grid of the robot 14 is the highest, the moving action “walk straight to the right grid” is performed. It is determined by the process of S61. Subsequently, in step S63, the robot 14 is instructed to move, and the process returns to step S43. That is, the movement command of the movement action determined in step S61 is given to the robot 14.

  If “YES” in the step S43, that is, if an end operation is performed, the movement control process is ended.

  From the above, the movement control system 100 includes the central controller 10 including the role database 20 and the robot 14 in which the roles are set. The role database 20 is composed of representative mobile behavior data of a person who has a role. For example, when the role of “easy to talk” is set for the robot 14, representative movement behavior data of “easy to talk” is selected from the role database 20. Further, the central controller 10 predicts a plurality of future positions of the robot 14 to which the role is set and actions at each future position based on the representative movement action data, and calculates the occurrence probability of each of the predicted plurality of actions. Is done. Then, the robot 14 is instructed to move based on the calculated occurrence probability.

  Therefore, the movement behavior of the robot 14 is determined based on the movement behavior data of the human having the same role as the robot 14. Therefore, the system administrator can operate a robot with a role set in the same way as a human having the same role.

  If the robot 14 is not moving and there is no movement locus, representative movement action data including coordinates close to the current position of the robot 14 is selected without using DP matching. In another embodiment, the representative movement behavior may be selected using a method different from DP matching.

  In the present embodiment, the action having the highest occurrence probability is selected, but in other embodiments, the action may be selected at random from the top three actions having an occurrence probability exceeding 80%.

  In another embodiment, an action such as “change the direction of the body after stopping” or “reverse” may be detected from the movement trajectory.

  Further, although the LRF 12 is used to detect the human position, the human position may be detected using an ultrasonic distance sensor or a millimeter wave radar instead of the LRF 12. Furthermore, the position and movement trajectory of a person may be detected using the radio wave intensity of a mobile communication terminal that the person has.

  Further, in this embodiment, the representative movement behavior configuring the role database is added by the operation of the administrator, but in other embodiments, movement behavior data may be automatically added. For example, when the movement speed, the action range, and the shape of the movement locus of a person satisfy predetermined conditions, the person's movement action data is added to the role database 20. In this case, the movement trajectory of a person who has a role may be detected using the radio wave intensity of the mobile communication terminal, and other human movement trajectories may be detected by the LRF 12.

  In another embodiment, a plurality of role databases 20 may be prepared and used depending on the season, event, time zone, and the like.

  Further, if it is “functionally the same place”, the robot movement control system 100 may be operated using the role database 20 in a place different from the place where the role database is configured. The “functionally the same place” means a place where the area of the space, the shape of the space, the purpose of use, and the equipment installed inside and outside are the same. For example, two corridors having substantially the same width and length and no equipment installed inside and outside can be said to be “functionally the same place”.

  Further, the role database construction program 310, the role setting program 312 and the movement control program 314 are stored in the HDD of the data distribution server and distributed to the central control device in the system having the same configuration as that of the present embodiment via the network. May be. Further, the storage medium may be sold or distributed in a state where these programs are stored in a storage medium such as an optical disk such as a CD, a DVD, or a BD (Blu-ray Disc), a USB memory, and a memory card. Then, when the role database construction program 310, the role setting program 312 and the movement control program 314 downloaded through the server and storage medium described above are installed in the central control device in the system having the same configuration as the present embodiment, The same effect as in this embodiment can be obtained.

  The specific numerical values such as degrees of freedom, distance, fixed period, radius, angle, frequency, average moving speed, first threshold value, second threshold value, and predetermined time given in this specification are merely examples. Therefore, it can be appropriately changed according to necessity such as product specifications.

10 ... Central controller 12a-12f ... LRF
14 ... Robot 16 ... CPU
18 ... Memory 20 ... Role database 100 ... Mobility control system 200 ... Network

Claims (5)

A robot movement control system including a database composed of movement data of a plurality of humans having roles and a robot to which roles are set,
Selection means for selecting movement behavior data from the database based on a role set in the robot;
First prediction means for predicting a plurality of movement actions of the robot from the movement action data selected by the selection means;
Calculation means for calculating the occurrence probability of each of the plurality of movement actions predicted by the first prediction means, and instruction means for instructing the robot of the movement action based on the plurality of occurrence probabilities calculated by the calculation means A robot movement control system comprising: It further comprises movement trajectory acquisition means for acquiring the movement trajectory of the robot,
The selection means selects movement behavior data from the database based on a movement locus acquired by the movement locus acquisition means, a role set for the robot, and a movement locus included in each movement behavior data. The moving action determination system according to 1. The movement behavior predicted by the first prediction means includes the future position of the robot,
A second predicting means for predicting the future position of the human when a human is present around the robot;
3. The movement behavior according to claim 1, wherein the calculation unit calculates a probability of occurrence of a plurality of movement behaviors based on a future position of the robot excluding a human future position predicted by the second prediction unit. Decision system. A robot movement control system including a central control device, a database composed of movement behavior data of a plurality of persons having roles, and a robot in which roles are set,
A processor of the central control unit;
Selection means for selecting movement behavior data from the database based on a role set in the robot;
Prediction means for predicting a plurality of movement behaviors of the robot from the movement behavior data selected by the selection means;
Function as calculation means for calculating the occurrence probability of each of the plurality of movement actions predicted by the prediction means, and instruction means for instructing the robot on the movement action based on the plurality of occurrence probabilities calculated by the calculation means A robot movement control program. A robot movement control method of a robot movement control system, including a database composed of a plurality of human movement behavior data having a role and a robot to which a role is set,
Select mobile behavior data from the database based on the role set for the robot,
Predicting a plurality of moving behaviors of the robot from the selected moving heartbeat data;
A robot movement control method for calculating an occurrence probability of each of a plurality of predicted movement behaviors, and instructing the robot of the movement behavior based on the calculated occurrence probabilities.

Images