JP2523151B2 - Robot control system - Google Patents

Description

DETAILED DESCRIPTION [Overview] In a robot control method for controlling a robot that freely behaves in a two-dimensional space based on sensed external information, a new situation such as the appearance of obstacles The purpose is to realize a “soft” robot control technique that allows the robot to take a plausible action even when an appearance or a change in the environment occurs, and weights the robot control means that generates the control signal. The weight of this hierarchical network is set by learning control so that some preferred control contents selected in advance are realized while configuring the hierarchical network
In accordance with the hierarchical network having the weight set in this way, a control signal is generated according to the external information detected by the light detection sensor, the sound detection sensor, and the obstacle sensor to freely control the robot in the two-dimensional space. It is configured to control various behaviors.

[Industrial applications]

The present invention relates to a control method for a robot that acts based on a plurality of sensor information.

In recent years, with the progress of artificial intelligence (AI), factory automation (FA), and office automation (OA), there is an increasing demand for an intelligent "soft" system that is easy for humans to use and can coexist with humans. In order to meet this expectation, systems to which expert systems and the like have been applied and robots with pattern recognition functions are beginning to be provided, but they are still far from being "soft" systems. From now on, it is desired to develop a “soft” robot control method that adaptively controls the behavior of the robot according to changes in usage and environment.

[Conventional technology]

The conventional robot control method is realized by a sequential processing computer (Neumann type computer).
Therefore, in the control method of a robot that behaves based on multiple sensor information, when a human considers in advance which sensor will bring what kind of information, when the input pattern from which sensor comes in, This has been realized by a configuration in which what output pattern is generated and what action should be taken is strictly described in the form of a program.

[Problems to be solved by the invention]

Therefore, the robot is only acting on the basis of this program, and naturally cannot cope with situations not described in the program. If it breaks, there is a problem that it is not possible to take appropriate actions. In particular, if the robot has many sensors, it is extremely difficult to create a program itself.
Or, there was a problem that it became impossible.

The present invention has been made in view of such circumstances,
It is an object of the present invention to provide a robot control system that forms a "soft" system that enables a robot to take appropriate actions in a two-dimensional space under any conditions.

[Means for solving problems]

 FIG. 1 is an explanatory view of the principle of the present invention.

In the figure, reference numeral 1 denotes a sensor means, which is a pair of two photodetection sensors for taking in optical information of the outside world surrounding the robot and two pair of sound detecting sensors for taking in sound information of the outside world. And a plurality of sensors including at least one or more contact sensors for taking in obstacle information of the outside world, 2 is an action pattern generating means for a robot that freely behaves in a two-dimensional space Of the action pattern signal for defining the action pattern of the robot by this action pattern signal, 3 is robot control means, which is composed of a hierarchical network having weights, and the detection pattern of the sensor means 1 is set in accordance with this hierarchical network. Action pattern generating means 2 for generating a corresponding control signal
4 is an operation mode signal, 4 is for setting the operation mode of the robot control means 3 to either the learning mode or the processing mode, and 5 is a basic control operation storage means, which is selected in advance. Robot control means 3 for one or more specific detection patterns of the sensor means 1
For storing the control signal information to be generated.

[Work]

According to the present invention, the robot control means 3 sets the weight of the hierarchical network by performing learning control so that the stored information stored in the basic control operation storage means 5 can be realized in the learning mode in the learning mode. At this time, a control signal according to the detection pattern of the sensor means 1 is generated according to the hierarchical network having the weight set in this way, and the behavior of the robot is controlled via the behavior pattern generating means 2. .

As described above, according to the present invention, it is not necessary for a human to perform strict programming in advance in consideration of all the input patterns and the corresponding action patterns, and the human has a basic input / output pattern pair. It is sufficient to give the same number to the robot control means 3 through the basic control operation storage means 5. Further, the robot control means 3 is composed of a network, and if the number of units in the input layer and the intermediate layer is large, the information per unit in the input layer will be dispersed in the units in the intermediate layer. Even if some error is mixed in the input layer, the error can be absorbed without affecting the output layer. Therefore, even if an unknown sensor input pattern other than the input pattern used for learning and training occurs,
It is possible to generate an output pattern associated with the input pattern used for learning and training, which is close to the input pattern, and to take a plausible free action even if there are obstacles in the two-dimensional space. For the same reason, it is possible to deal with sensor characteristic changes and failures.

〔Example〕

 Hereinafter, the present invention will be described in detail according to examples.

FIG. 2 is a detailed configuration diagram of the robot control means 3 described in FIG. As shown in this figure, the robot control means 3 of the present invention is configured by a hierarchical network including a kind of node called a unit and an internal connection having a weight. This configuration is basically a processing method called a back-propagation method (DERumelhart, GEHinton, and RJWilli) that has been proposed as a data processing method that gives an adaptive function to a computer.
ams, “Learning Internal Representations by Error P
ropagation, "PARALLEL DISTRIBUTED PROCESSING, Vol.1,
pp.318-364, The MIT Press, 1986).

Next, an outline of this back propagation method will be described.

In the back propagation method, a hierarchical network is composed of a kind of node called a unit and an internal connection with weight. FIG. 3 shows the internal structure of the unit and is called a basic unit 30. This basic unit 30
Is a multi-input, single-output system. In this unit,
It has an accumulator 31 that multiplies each input by a weight of each internal connection and sums the results of all multiplications, and a threshold processor 32 that performs threshold processing and outputs one output. . That is, the data processing in the basic unit 30 in the back propagation method consists of product-sum calculation of input and weight and threshold processing. Here, in the back propagation method, the sigmoid function represented by Expression (2) is used as a function of the threshold.

The calculation performed by the basic unit is shown below by mathematical expressions.

y _pi = 1 / (1 + exp (-x _pi + θ _i )) Equation (2) where h: h layer unit number i: i layer unit number p: input pattern number θ _i : i layer i unit Threshold value W _ih : h-weight of internal coupling between i layers x _pi : sum of products from each unit of layer i to i-th unit of layer y _ph : p output of layer y for pattern input y _pi : p In the i-layer output back-propagation method for the pattern input, the basic unit 30 based on this product sum and threshold processing has a hierarchical network structure having error feedback as shown in FIG. Using an algorithm that adaptively and automatically adjusts by feedback, the network learns a desired data processing method (association between an input pattern and an output pattern) to execute adaptive data processing.

Here, from the equations (1) and (2), in the back propagation method, the adjustment of the weight and the threshold needs to be executed at the same time, but the setting of the weight and the threshold is a difficult task that interferes with each other. Become. In the conventional back-propagation method, a threshold is given to each unit. However, when the number of units is large, it is a complicated and troublesome task to give a threshold to each unit. It was a coveted one. Therefore, in the robot control means 3 of the present invention, as shown in FIG. 2, in addition to the input unit 3-h for the number of input signals, "1" is always input in the input layer, the threshold input unit for threshold adjustment. 3'-h is provided.

As described above, the reason why the threshold value input unit 3'-h is provided so that the threshold value of each unit 3-i in the intermediate layer can be set by the same process as setting the weight W _ih for the intermediate layer is as follows. You can think of it as such. That is, in each unit 3-i of the intermediate layer, 1 unit in the input layer
Since the value y _ph from the three extra units 3′-h is always “1”, the value x _pi is ∴x ′ _pi = x _pi + W _ih ′ (where h ′ is the threshold input unit number of the input layer). From this result, when substituting θ _i = −W _ih ′ into equation (2), y _pi = 1 / (1 + exp (−x _pi −W _ih ′)), which is the threshold θ _i shown in equation (2). Is substantially −
Corresponds to the setting change to _Wih . That is, the complexity of setting the threshold value of each unit in the intermediate layer is eliminated.

Next, the stored information stored in the basic control operation storage means 5 described with reference to FIG. 1 will be described according to the specific example shown in FIG. For example, as shown in FIG. 2, when the sensor output is in the binarization mode and the number of input units 3-h is three, the number of input patterns to the robot control means 3 is eight as shown in FIG. . Therefore, if the action pattern of the robot is, for example, two states of the moving state and the stopped state, the action pattern of the robot of "1" or "0" is determined for each of these eight input patterns. . As described above, it is already determined what kind of action the robot should take with respect to the detection pattern of the sensor means 1. Therefore, some of such information is stored in the basic control operation storage means 5. Would be preselected and stored. The fourth
It is also possible to store all eight input patterns and a small number of input patterns as shown in the figure.

In order to deepen the understanding of the contents of the example of FIG. 4, a specific example of the action pattern of the robot shown in FIG. 5 will be described. FIG. 5 specifically considers a robot having three optical sensors shown in FIG. 5 (a) and one motor for performing the action of “turning to the right”. Then, it is assumed that the robot wants to take the action of following a light emitting source that revolves around the robot as shown in FIG. At this time, as the sensor input pattern of the robot, the combinations shown in the input pattern column of FIG. 4 can be considered. For example, the input pattern of "0" in Fig. 4 is the state where all three optical sensors are OFF, and the input pattern of "4" is the state where the optical sensor is ON and the optical sensor is OFF, input of "6". The pattern is that the optical sensor is ON and the optical sensor is OFF. In order to make the robot follow the rotating light source, the output pattern (behavior) shown in the teacher signal column of FIG. 4 can be realized by network learning and training according to such input pattern. Good. For example, the input pattern of "0" in Fig. 4 is
Since both the optical sensors are in the OFF state, that is, no light is emitted from the light emitting source, the output pattern at this time represents "0", that is, "turn off the motor". The input pattern of "6" is the optical sensor,
Is ON and the optical sensor is OFF, that is, the state where the light source is captured (Fig. 5 (a)), so the control "turn off the motor" is indicated, and the input pattern of "4" is the optical sensor. Is ON, the light sensor is OFF, that is, the light source captured by the robot has moved further (Fig. 5 (b)), so it means "turn on the motor (turn right)". ing. That is, if the teacher signal as shown in FIG. 4 is obtained, the action pattern of the robot as shown in FIG. 5 is preferably controlled.

In order to realize such preferable control, according to the present invention, the weights W _ih and W _ji of the internal connection of the hierarchical network of the robot control means 3 are learned in accordance with the storage information stored in the basic control operation storage means 5. It is a decision to make. That is, the operation mode of the robot control means 3 is set to the learning mode, the stored information is sequentially read from the basic control operation storage means 5, and the values of the weights W _ih and W _ji are determined by using the learning algorithm of the back propagation method. It is configured to automatically determine.

Next, a learning procedure for determining the values of the weights W _ih and W _ji will be described. Here, the explanation of this learning procedure is given by further generalizing the output layer of the robot control means 3 as shown in FIG. 6 having a plurality of output units 3-j.

First, the initial value of the weight of the inner join is determined. This initial value is determined by a random number of 1 or less. This is because if the weight values are all the same or are symmetric with respect to the unit, the back propagation method does not change the weight and learning does not proceed, so random numbers are used to avoid this. Then, the data of the input pattern stored in the basic control operation storage means 5 and the data of the desired output pattern paired with the input pattern are sequentially read.
For example, as shown in FIG. 4, if there are eight pieces of stored information, all of these pieces of information will be sequentially read.

Next, the control parameters related to the back propagation method are input. Here, the learning rate, which is the coefficient of the amount of change in weight per incremental iterative learning, and the learning speed for suppressing the oscillation at the time of convergence are used as control parameters. Then, according to the algorithm of the back propagation method, the weight of the inner coupling is incrementally learned so that the output value of the output layer unit 3-j matches the desired output, and finally, the output value of the output layer unit and the desired value are obtained. When the error from the output value becomes smaller than the predetermined value for all input patterns, the learning is finished.

A specific algorithm for updating the weight of the hierarchical network will be described below. The following equation is obtained by analogy with the equations (1) and (2). That is, y _pi = 1 / (1 + exp (−x _pi + θ _i )) Expression (4) y _pj = 1 / (1 + exp (−x _pj + θ _j )) Expression (6) where y _ph : output from the h-th unit of the h-layer (input layer) to the p-th pattern input value y _pi : p Output from the i-th unit of the i-th layer (here, the middle layer) for the p-th pattern input value y _pj : Output from the j-th unit of the j-th layer (here, the output layer) for the p-th pattern input value x _pi : i Sum of p-th pattern input to layer i-th unit x _pj : Sum of p-th pattern input to layer j-th unit W _ih : Weight W between h-layer h-th unit and i-th layer i-th unit _ji : Weight between the i-th unit of the i-th layer and the j-th unit of the j-th layer Next, the sum of squares E _p of the error between the teacher input vector and the output vector of the network is calculated as the error of the network from these values.

Where E _p : error vector for p-th pattern input E: sum of error vectors for all pattern inputs d _pj : teacher signal to j-th layer j-th unit for p-th pattern input Here, the relationship between error vector and output layer vector In order to obtain Eq. (7) is partially differentiated with respect to y _pj , Get. Further, in order to obtain the relationship between the error vector and the input to the j-th layer, when the error vector is partially differentiated by x _pj , Get. However, in the present embodiment, one input unit 3'-h is provided in the input layer and a value of "1" is always input to this unit 3'-h. It realizes automatic adjustment. Furthermore, in order to obtain the relationship between the error vector and the weight between the ij layers, the error vector is partially differentiated with W _ji , Get the solution represented by the sum of products of

Next, when the change of the error vector E _p with respect to the output y _pi of the i layer is _calculated , Get. Furthermore, when the change in the error vector E _p with respect to the change in the sum x _pi to the i-th layer input unit is calculated, Get the solution represented by the sum of products of Furthermore, when the relation of the change of the error vector with respect to the change of the weight between the h-i layers is obtained, Get the solution represented by the sum of products of

From these, the relationship between the error vector for all input patterns and the weight between the i-j layers is obtained as follows.

In addition, the error vector for all input patterns and h−i
The relationship with the weight between layers is calculated as follows.

Since equations (14) and (15) show the rate of change of the error vector with respect to the change of weight between layers, the weight is changed so that this value is always negative. E, which is the sum of squared errors, can be asymptotically set to zero. Therefore, in the present embodiment, the change amount ΔW _ji per weight is set as follows, and this operation is repeated based on the gradient method to converge E to zero.

However, ε: learning rate (the same function as the gradient rate of the gradient method) Further, in the present invention, the learning speed is applied to the equations (16) and (17) for the purpose of suppressing the oscillation at the time of convergence in the gradient method. , ΔW _ih and ΔW _ji are set as follows.

However, α: learning rate constant t: number of times The above weights W _ih and W _ji are the units 3-i and 3-
It is stored in the storage device corresponding to each j, and the contents are modified by the feedback during the learning described above. Then, the finally determined learning result weights W _ih and W _ji will be used in the actual processing described below.
As this storage device, the basic control operation storage means 5 can be used, but it may be provided separately.

Next, control of the robot to be executed using the weights W _ih and W _ji of the internal connection of the hierarchical network determined in this way will be described.

When the learning of the hierarchical network is completed, the operation mode of the robot control means 3 is switched to the processing mode, that is, the mode for actually controlling the operation of the robot. In this processing mode, the input pattern composed of the detection signals of the sensors captured by the sensor means 1 composed of a plurality of sensors is input to the input layer of the hierarchical network of the robot control means 3. Then, the robot control means 3 obtains an output pattern by performing a product-sum operation and threshold processing on the input pattern using the weight value and the threshold determined in the learning mode, and outputs the obtained output pattern as a control signal. To the action pattern generating means 2. Then, the action pattern generation means 2 that has received this control signal will generate an action pattern signal corresponding to the control signal to define the action pattern of the robot. Therefore, by repeating such processing, the robot can take appropriate actions according to the detection patterns of the plurality of sensors.

When the contents of this process are specifically examined according to the example of FIG. 5, the relationship between the robot and the light emitting source is now the fifth.
In the state of Fig. (A), that is, the optical sensor of the robot is O
N, optical sensor is OFF, motor is OFF.
At this time, when the light emitting source moves to the right as shown in FIG. 5B, the optical sensor of the robot is turned on and the optical sensor of the robot is turned off. When this is input to the network shown in FIG. 2, the output pattern "1" representing the control "turn the motor ON (turn right)" is generated. Therefore, the robot turns right. This right turn is continued until two of the three optical sensors are turned on. In this case, as shown in Fig. 5 (c), when the optical sensor is in the ON state and the optical sensor is in the OFF state, the network outputs "0" indicating the control "turn off the motor". ， The robot stops. In this way, the robot inputs the sensor input signal pattern that is captured every moment into the network shown in FIG.
It is possible to follow the movement of the light emission source by controlling the motor according to the optimum output pattern that the network outputs every moment corresponding to the input pattern. In this example, the case where the light emitting source moves to the right has been described. However, even if the light emitting source moves to the left as shown in FIG. 5D, the robot can follow the same manner.

In this way, the robot is controlled to take appropriate actions. However, when the number of sensors and the number of control signals are large, the basic control operation storing means 5
Since it is not possible to store all of the data of the input pattern and the desired output pattern that makes a pair with the input pattern, the basic data is stored. From this, when the output pattern is obtained using the weight value and the threshold obtained by learning using this basic data, the desired robot behavior may not be obtained.
In such a case, in the present invention, the operation mode is switched to the learning mode, and the weight of the connection of the network at that stage is used as an initial value to set a pair of an input pattern and a desired output pattern at a time when a desired unobtainable time is obtained. Control of the robot by storing it in the basic control operation storage means 5 and automatically fine-adjusting the weight of the coupling so that the robot control means 3 can further combine and combine the input / output pattern pairs. The performance can be improved. Therefore,
Ultimately, optimal control of the robot will be realized.

FIG. 7 shows a network obtained as a result of learning a kind of parity check processing in the network by the back propagation method (automatic adjustment of weight and threshold). Here, Net1 shown in FIG. 7 (A) and Net2 shown in FIG. 7 (B) have the same characteristics for checking odd parity, that is, for three inputs that take "0" or "1". When the number of "1" is an odd number, the output layer outputs "1". In FIG. 7, the number next to the internal connection line is the weight, and the number in the circles representing the unit is the threshold value. Comparing Net1 and Net2, it can be seen that the weight and the threshold are completely different. This is because of the network redundancy, which makes these differences. As shown in FIG. 7, the output of the basic unit 30 is set to "1" and "0".
It is also possible to configure the network so that only the state of.

Next, the redundancy of the number of units in the middle layer that constitutes the hierarchical network will be described. FIG. 8 is a network that realizes the exclusive OR function, and is an example of the case where the redundancy of the number of intermediate layer units is not provided. In the exclusive OR, as shown in FIG. 9, the identification of the input pattern by the straight line (linear identification) is impossible with one straight line, and at least two straight lines are required as shown in FIG. 9 (B). Therefore, for this identification, as shown in FIG. 9 (A), at least two intermediate layer units are required. However, in the present invention, in order to automatically adjust the threshold values of the intermediate layer unit and the output layer unit, the input layer is provided with the threshold value input unit 3'-h having "1" as an input signal at all times. In the network shown, there is no redundancy in the number of hidden units relative to the number to be identified. In this case, the two middle layer units 3-i have to perform automatic adjustment including the threshold value of the output layer unit 3-j, and the number of times of repeated learning until the exclusive OR characteristic is adapted increases. On the other hand, Fig. 10 shows an example of a network with redundancy. As shown in the figure, if there is redundancy in the number of middle layer units,
Since the surplus units can be dedicated to the adjustment of the threshold value of the unit 3-j in the output layer, the number of times of repeated learning can be greatly reduced as compared with the case where there is no redundant unit.

Next, a specific calculation example of the weight of the inner connection will be described.

11 and 13 show the internal connection weights between the units when learning of the odd parity check function is completed.
11 to 13 have different weights but the same function. This is because the learning rate and the learning speed parameter are different and the redundancy of the number of hidden layer units. Figure 12 (A)
(B) and (C) respectively show an input and an output when an arbitrary pattern is input after the learning shown in FIG. 11 is completed. Further, FIGS. 14 (A), (B) and (C) respectively show inputs and outputs when an arbitrary pattern is input after the learning shown in FIG. 13 is completed. In the robot control means 3, since the calculation is performed by an analog value, the output value is not completely 1 or 0. However, if a threshold value is used, 1 or 0 is output from the output value shown in FIGS. 12 and 14. Clearly, the decision is easy.

In addition, Fig. 15 shows the result of learning the even parity check function on the same network as that on which the odd parity check function was learned, and shows the weight of each inner connection. 16 (A), (B) and (C) are respectively
Figure 15 shows the input and output when an arbitrary pattern is input after the learning shown in Fig. 15.

Next, an embodiment of the present invention for controlling the action pattern of a robot that tracks a moving object or escapes from a moving object will be described. This robot is designed to follow a moving object, which is a light emitting source and an ultrasonic wave source, while avoiding an obstacle, or to escape from a moving object while avoiding an obstacle. It is controlled, and as a driving source for tracking a moving object or escaping from a moving object, to take two propulsion motors for taking forward and backward actions and for making left and right actions. In addition to being equipped with two steering motors, a piezoelectric buzzer corresponding to human speech is equipped.
The motor and the piezoelectric buzzer are turned on in the embodiment.
It is controlled in the binary mode of / OFF. That the robot from having a five driving source, number of units of the output layer of the robot control unit 3 of the hierarchical network that is provided for control of the robot becomes five, behavior patterns robot which There are two ⁵ become.

Figure 17 shows the layout of the sensors that this robot uses to track and escape. As shown in this figure, the robot 100 has two head light sensors 1 corresponding to both eyes on the head.
01R, 101L and two head ultrasonic sensors 10 corresponding to both ears
Equipped with 2R and 102L, the body has two conductor light sensors 103R and 103L corresponding to both eyes, one body ultrasonic sensor (or transmitter) 104 corresponding to the ears, and contact with obstacles. It is equipped with three touch sensors 105F, 105R, 105L provided with a central angle of 120 degrees in order to detect the fact. The robot 100 further detects the fact that the rotation reaches, for example, the limit of 180 ° when the head and the body rotate to the limit rotation angle by the rotation of the steering motor included in the robot 100.
It is equipped with 106R and 106L. This head light sensor 101
R, 101L and body light sensor 103R, 103L detect light emitted from a moving object that is a target object, and head ultrasonic sensor 102R, 102L
The body ultrasonic sensor 104 operates so as to detect ultrasonic waves emitted by a moving object that is a target. Here, two sets of sensors corresponding to both eyes of the human being, head light sensors 101R and 101L and body light sensors 103R and 103L, are provided because the wavelength of light emitted by a moving object is different between tracking and flight. This is because it is necessary to prepare two types of photodetection sensors having sensitivity matched to this wavelength. Further, the head and body of the robot are integrally rotated with respect to the base of the robot, and the wheels of the robot are directed toward the front of the head in accordance with this rotation.

As described above, since this robot has 12 sensors, the number of units in the input layer of the hierarchical network of the robot control means 3 provided for controlling this robot is
It becomes 12 (13 if the threshold unit is added). Further, in the embodiment, since these sensors are configured to output the binary mode output, there are 2 ¹² detection patterns.

With respect to these 2 ¹² detection patterns, the action taken by the robot to track a moving object is inherently determined, and as described above, the basic control action storage means 5 stores such information. Will be configured to be preselected and stored. Figure 18 shows an example. In this example, the drive patterns to be taken by the robot drive source for the 36 detection patterns of the robot sensor are stored in the basic control operation storage means 5. Here, "HEAD, EAR" in the figure is the head ultrasonic sensor 102R, L, "HEAD, EYE" is the head optical sensor 101R, L,
“BODY, E” is the body ultrasonic sensor 104, “BODY, EYE” is the body light sensor 103R, L, and “BODY, TOUCH” is the touch sensor 105.
F, R, L, "BODY, LIM" represents the limit switch 106R, L, "RIGHT" is the right turn steering motor, "LEFT" is the left turn steering motor, and "FWD" is the forward drive Set the motor to "BWD"
Represents a reverse thrust motor and "BUZZ" represents a piezoelectric buzzer.

To deepen the understanding of the example of stored information in Fig. 18,
Some of them will be specifically described. For example, the 18th
The sensor detection pattern on the fifth line in the figure indicates that the head optical sensor 101L corresponding to the left eye of the head is ON. In such a case, since the moving object is in the front left direction, as shown by the teacher signal, turning on the steering motor L and turning on the propulsion motor F causes the vehicle to turn left while moving forward to track. Can be executed. The sensor detection pattern on the eighth line indicates that the head light sensor 101L is ON and the touch sensor 105R provided on the right side of the robot is ON. In such a case, the right side surface of the robot is in contact with the obstacle, but the moving object is in the front left direction. Therefore, as shown by the teacher signal, the steering motor L is turned on and the propulsion motor F is turned on. By turning it ON, it will be possible to perform tracking while moving forward while turning to the left. Further, the sensor detection pattern on the 15th row indicates that the head light sensor 101L and the head light sensor 101R corresponding to the right eye of the head are ON. In such a case, since the moving object is present in front of the front, as shown by the teacher signal, turning on the propulsion motor F allows the vehicle to move forward and perform tracking.

Regarding the automatic determination of the internal connection weights W _ih and W _ji of the hierarchical network of the robot control means 3 by the learning algorithm of the back propagation method using the storage information of this basic control operation storage means 5, It is basically the same as the robot of the embodiment described in the figure. Figure 19 shows the calculation results of the weights W _ih and W _ji obtained by executing the learning algorithm of this back propagation method. This calculation result is executed by using the number of units in the intermediate layer of the hierarchical network of the robot control means 3 as 5, and using the information stored in the basic control operation storage means 5 as shown in FIG. . Then, similarly to the robot in the embodiment of FIG. 5, the control of the robot for tracking the moving object is executed using the weights W _ih and W _ji of the internal connection of the hierarchical network determined in this way. It will be.

Next, the contents of this robot control will be specifically described with reference to the explanatory diagram shown in FIG.

Now, it is assumed that the relationship between the robot and the moving object having the light emission source and the transmission source is as shown in FIG. 20 (a), that is, the head light sensor 101L corresponding to the left eye of the head is in the ON state. When this sensor input signal is input to the hierarchical network for which the weight has been obtained, the output pattern is "steering motor L
N, turn on the propulsion motor F (turn left, move forward) ", an output vector (0,1,1,0,0) representing the control is generated. Therefore, the robot turns left. At this time, if the moving object moves and the robot tracks, as shown in Fig. 20 (b), the sensor input signal of the robot is that the head light sensor 101L is ON, and the touch sensor 105 is
When R is ON, that is, the right side of the robot hits an obstacle and the moving object is visible to the front right. When this sensor output signal is input to the network, the output vector (0, 1, 1 indicating the control "turn on the steering motor L and turn on the propulsion motor F (turn left and move forward)" this time. , 0,0) is generated. Therefore, the robot moves forward while turning to the left. At this time, as shown in FIG. 20 (c), if the moving object moves and the robot tracks, the sensor input signal of the robot is the head light sensor 101R,
Both the head light sensor 101L and the head light sensor 101L are in the ON state, that is, the moving object is captured in front. In this case, when this sensor input signal is input to the network, an output vector (0,0,1,0,0) representing the control "Turn on the propulsion motor (move forward)" is generated, and the robot Figure 20 (d)
As shown in, move forward toward the moving object. In this way, the robot inputs the sensor input signal pattern that is captured moment by moment into the hierarchical network of the robot control means 3, and the hierarchical network responds to the input pattern according to an appropriate output pattern that is output momentarily. A moving object can be tracked by controlling the motor.

For the convenience of explanation, the explanation of FIG.
Although the same control information (fifth line, eighth line, fifteenth line) stored in the basic control operation storage means 5 shown in the figure is used to track a moving object, , Even if the sensor detects a detection pattern which is not stored in the basic control operation storage means 5, an output pattern for tracking a moving object is generated by the weight of the learned hierarchical network. A moving object can be tracked by controlling the motor. Of course, when it becomes impossible to track a moving object with the output of the hierarchical network, the weight of the hierarchical network is changed by learning as in the robot of the embodiment shown in FIG.

In the present invention, even if the structure of the hierarchical network of the robot control means 3 is the same, if the control information of different control contents is stored in the basic control operation storage means 5, the weights W _ih and W _ji are obtained according to the control information, and the Control of different control contents can be executed. FIG. 21 shows that the robot executes control to escape from a moving object.
6 is an example of a basic control operation stored in a basic control operation storage unit 5. The body optical sensors 103R and 103L are used for both eyes to control this escape. This 21st
FIG. 22 shows the calculation results of the weights W _ih and W _ji obtained using the storage information of the basic control operation storage means 5 in the figure. The structure of the hierarchical network is exactly the same as that of the tracking. The control of the robot that moves to escape from the moving object using this weight can be executed as it is.

When two robots shown in Fig. 17 were actually used, one robot was set on the tracking side and the other one was set on the escape side, and when playing tag among the obstacles, one of them was an obstacle. It was possible to avoid the obstacles and escape well, while one avoids obstacles and often follows them. It was confirmed that even if the position of an obstacle is changed or an obstacle is added, humans can play tag even if they do not give their hands.

The optical sensor of this mobile robot is suitable as long as it detects modulated light when it is affected by ambient light, but it detects light that is not modulated if it is not affected by ambient light. It may be one. Similarly, an ultrasonic sensor was used in consideration of the presence of disturbance noise, but a microphone or the like is sufficient if there is no influence of disturbance noise. However, in such a case, the light and sound emitted by the moving object should be matched with that. Also,
In the embodiment, the touch sensor has been described on the assumption that it is a contact type, but a touch sensor such as a photoelectric switch or a proximity switch can also be mounted. The present invention is not limited to the specific configuration of the robot, and can be implemented as long as the robot has a function of freely moving in a two-dimensional space.

〔The invention's effect〕

As described above, according to the present invention, a pattern composed of a plurality of sensor input signals and an output pattern that defines the optimum action to be taken with respect to the input pattern are stored in a hierarchical network so that they are associated with each other. Therefore, humans do not have to identify all the sensor input patterns and the output patterns corresponding to them, and program them precisely, but only teach basic hierarchical I / O pattern pairs to the hierarchical network. Further, even for unknown input patterns other than the learned input / output pattern pair, an output pattern corresponding to the learned input pattern that is close to the input pattern can be generated. Can handle. In addition, if the desired behavior was not obtained as a result of actually controlling the robot with the weight of the connection of the network that completed the association of the input pattern and the output pattern with the basic input / output pattern pair, at that stage Using network connection weights as initial values, automatically finely adjusting connection weights so that pairs of input patterns and desired output patterns at the time when a desired result cannot be obtained can be further overlapped and associated. As a result, the control performance of the robot can be improved. So in the end,
It becomes possible to realize optimal control of the robot. Moreover, the hierarchical network is a processing method suitable for a machine having a parallel processing architecture, and an output pattern can be instantly generated when a sensor input pattern is taken in, which greatly contributes to flexible real-time control of a robot.

Further, according to the present invention, since the threshold layer unit is provided in the input layer of the hierarchical network and the redundant control more than the number to be identified is provided in the number of the units in the intermediate layer, the internal coupling between the units is suppressed. The adjustment of the weight and the threshold value of each unit can be performed automatically and in a simple way, and the learning can be performed without being aware of the threshold value and without deteriorating the adaptability of the network.

[Brief description of drawings]

FIG. 1 is a diagram for explaining the principle of the present invention, FIG. 2 is a block diagram of an embodiment of robot control means, FIG. 3 is a block diagram of a basic unit, FIG. 4 is an example of information stored in a basic control operation storage means, and a fifth example. FIG. 6 is a concrete example of the action pattern of the robot, FIG. 6 is a block diagram of another embodiment of the robot control means, FIG. 7 is an example of a network having an odd parity check function, and FIG. 8 is the number of intermediate layers is redundant. Exclusive-OR network without asterisk, Fig. 9 is an explanatory diagram for explaining the roles of exclusive-OR and middle tier units, Fig. 10 is an exclusive-OR network in which the number of middle tiers is redundant, and Fig. 11 is a learning result. Fig. 12 is an explanatory view of the weight of internal coupling (I), Fig. 12 is a processing example according to the weight of Fig. 11, Fig. 13 is an explanatory diagram of the weight of internal coupling (II) showing the learning result, Fig. 14 Shows an example of processing according to the weights in Fig. 13, and Fig. 15 shows the weights of the inner joins (III) showing the learning results. Explanatory diagram, FIG. 16 is a processing example according to the weight of FIG. 15, FIG. 17 is an explanatory diagram of a sensor equipped in the mobile robot, and FIG. 18 is an example of information stored in the basic control operation storage means of the mobile robot (I ), FIG. 19 is an explanatory diagram of the weight (I) of the internal coupling showing the learning result of the mobile robot, FIG. 20 is an explanatory diagram when tracking a moving object, and FIG. 21 is a basic control operation of the mobile robot. An example of information stored in the storage means (II), FIG. 22 is an explanatory diagram of the weight of internal coupling (II) showing the learning result of the mobile robot. In the figure, 1 is a sensor means, 2 is an action pattern generating means, 3 is a robot control means, 3'-h is a threshold value input unit, 5 is a basic control operation storing means, 30 is a basic unit, 31 is an accumulator, 32 Is a threshold processing unit, 101 is a head light sensor, 102 is a head ultrasonic sensor, 103
Is a body light sensor, and 105 is a touch sensor.

 ─────────────────────────────────────────────────── ─── Continued Front Page (72) Inventor Hideki Yoshizawa 1015 Kamiodanaka, Nakahara-ku, Kawasaki City, Kanagawa Prefecture, Fujitsu Limited (72) Inventor Nobuo Watanabe 1015, Kamiodanaka, Nakahara-ku, Kawasaki City, Kanagawa Prefecture Fujitsu Limited ( 72) Inventor Takashi Kimoto, 1015 Kamiodanaka, Nakahara-ku, Kawasaki-shi, Kanagawa, Fujitsu Limited (72) Inventor Asahi Kawamura, 1015, Kamikodanaka, Nakahara-ku, Kawasaki, Kanagawa (56) References 1-173202 (JP, A) JP-A-1-177603 (JP, A) FUJITSU Vol. 39, No. 3 (10.06.1988) PP. 175-184 NIKKEI ELECTRONIC S No. 427 (10.08.1987) PP. 115-127 Neural Network Vol. 1 (1988) PP. 251-265

Claims (1)

(57) [Claims] 1. A robot control method for controlling a robot that behaves freely in a two-dimensional space based on sensed external information, comprising a plurality of sensors for capturing external information surrounding the robot. A plurality of sensors form at least two pairs of light detection sensors that capture the external light information, two pairs of sound detection sensors that capture the external sound information, and one that captures the external obstacle information. A sensor means (1) including a plurality of obstacle sensors, and an action pattern generation means (2) for generating an action pattern signal that defines an action pattern of a robot performing a free action in a two-dimensional space.
A robot control means (3) for sending a control signal to the action pattern generation means (2) according to the detection pattern of the sensor means (1), and one of the sensor means (1) selected in advance or The robot control means (3) is provided with a basic control operation storage means (5) for storing control signal information to be sent by the robot control means (3) for a plurality of specific detection patterns. An accumulator (31) that receives one or a plurality of inputs and a weight to be multiplied with this input to obtain a sum of products, and an output from this accumulator (31) is converted by a threshold function to obtain a final value. A basic unit (30) having a threshold processing section (32) for obtaining an output is used as a unit unit, a plurality of the unit units (3-h) connected to the sensor means (1) are used as an input layer, and a plurality of units are used. Number of the above unit units (3-i As an intermediate layer, one or more intermediate layers are provided, and one or a plurality of the unit units (3-j) connected to the action pattern generating means (2) is used as an output layer, and the input layer is And the frontmost intermediate layer, between the intermediate layers, and between the final intermediate layer and the output layer to form an internal connection to form a hierarchical network, and the robot control means (3) The learning control is performed so that the stored information of the basic control operation storing means (5) can be realized, and the value of the weight of the hierarchical network provided by itself is set, and the hierarchical network of which the weight value is set is set. A robot control method characterized in that the output value of the output layer serves as a control signal to the action pattern generating means (2).