JP3200914B2 - Arrangement control method and apparatus - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an arrangement control method and apparatus suitable for use when a plurality of mobile robots arranged in a warehouse or a plurality of characters in a video game are caused to perform a group action, for example.

[0002]

2. Description of the Related Art In a case where a plurality of mobile robots are arranged in a warehouse and various objects are conveyed by the mobile robots, a program combining a plurality of processing steps is constructed in consideration of various conditions. Each mobile robot is controlled according to a program. Thereby, the mobile robot can be efficiently controlled, and the work can be efficiently performed.

[0003]

However, it is substantially impossible to design a program in consideration of all conditions. Therefore, as many conditions as possible are taken into consideration. However, the number of processing steps of the program becomes enormous, and the production thereof requires a lot of time and labor. This is particularly remarkable when a plurality of mobile robots do not act in isolation, but act as a group in consideration of the overall balance. In addition, there has been a problem that when an unexpected disturbance occurs, control becomes impossible.

The present invention has been made in view of such a situation, and is intended to easily and surely cope with a disturbance.

[0005]

An arrangement control method according to the present invention comprises a plurality of patterns relating to an arrangement of a plurality of controlled objects in a space.
Storage step for storing the
Out of a plurality of stored patterns
A selection step for selecting a turn, and a plurality of controlled objects,
Corresponding to the pattern selected by the processing of the selection step
The first instruction step of instructing
Detecting the arrangement state of the control target of
Actual control target arrangement detected by step processing
The state is the putter indicated in the process of the first instruction step.
Whether it corresponds to the arrangement state of the control target based on the
Detection step and the detection step
Actual control target arrangement status detected in step processing
And the pattern specified in the process of the first specifying step
It is determined that the arrangement state of the control target based on
When the pattern stored in the storage step
So that it is positioned corresponding to one of the other patterns
And a second instruction step for instructing the control target
It is characterized by. The control target can be a mobile robot. Stored in the processing of the storage step
Multiple patterns and multiple patterns detected in the detection step
The number of controlled objects is the mutual connection network
Can be combined. Interconnected type
The network is a pattern of one of several patterns
The first network in which the services are deployed, and for each controlled object,
The arrangement state that holds the arrangement state detected in the processing of the detection step
2 networks. Book
The arrangement control device according to the present invention provides an arrangement of a plurality of controlled objects in a space.
Storage means for storing a plurality of patterns related to
One of a plurality of patterns stored by the column
Selection means for selecting a pattern of
Located corresponding to the pattern selected by the selection means
Instruction means for instructing the control
Detecting means for detecting the installation state;
The actual arrangement state of the control target is determined by the first instruction means.
Arrangement state and correspondence of controlled objects based on specified pattern
The determination means for determining whether or not to perform
Placement state of the actual control target detected by the output means,
Control based on the pattern specified by the first specifying means
If it is determined that the target placement state does not correspond,
Of the patterns stored by the means, other patterns
Instructs the controlled object to be positioned corresponding to one of the
And second instruction means for performing the operation. control
The target can be a mobile robot. Record
A plurality of patterns stored by the
The positions of the controlled objects detected by the step are interconnected.
Can be connected by a combined network
Wear. Interconnected networks have multiple patterns
The first network where one of the patterns is developed
And the position detected by the detection means for each control target.
To include the second network
Wear.

[0006]

According to the arrangement control method and apparatus of the present invention,
Multiple patterns of arrangement of multiple controlled objects in space
Is stored, and from a plurality of stored patterns,
One pattern is selected. And multiple controlled objects
Instructs you to locate corresponding to the selected pattern
Then, the actual arrangement state of the control target is detected. Also,
The detected placement status of the control target is
Whether or not it corresponds to the arrangement state of the control object based on the turn
Determined and detected actual arrangement state of the control target and finger
Corresponds to the placement status of the control target based on the indicated pattern
If it is determined that the pattern is not
To be positioned corresponding to one of the other patterns
Instructed to be controlled.

[0007]

FIG. 1 is a block diagram showing the configuration of an embodiment of a mobile robot control system to which the arrangement control method and apparatus of the present invention are applied. A plurality of (five in this embodiment) mobile robots 2-1 are provided in the placement space (field) 1.
Through 2-5 are arranged. The plan net 3 is configured by an interconnected neural network (specific examples of the configuration are shown in FIGS. 9, 11, 12, and 1).
3 and FIG. 15), a wireless communication device 4
The mobile robots 2-1 through 2-5 are instructed by radio waves to the respective target positions (target movement (arrangement) positions) via the. In addition, the absolute position measuring device 5 measures the current position and posture of each of the mobile robots 2-1 to 2-5 in real time, for example, by using a beacon, a magnetic field measurement, and a measurement by an encoder, and feeds back to the plan net 3. It has been done.

FIG. 2 shows a mobile robot 2-1 (2-2 to 2).
−5 is also the same). The front wheel 11 is driven by a motor 20 and is directed in a predetermined direction. The rear wheels 12, 13 are driven by motors 18, 19 to rotate. A plurality of obstacle sensors 14 (eight in the case of the embodiment) are arranged on the outer periphery.
1 (FIG. 3), the obstacle sensing system 15 monitors the output of each obstacle sensor 14,
The detection result is output to the controller 16. The radio communication device 17 receives the radio wave output from the radio communication device 4, demodulates the radio wave, and outputs the demodulated radio wave to the controller 16. As shown in FIG. 3, the controller 16 including a CPU drives the motors 18, 19, and 20 according to the output of the obstacle detection system 15 so that the mobile robot 2-1 does not contact the obstacle 31. In response to the output from the wireless communication device 17,
The mobile robot 2-1 is moved to a predetermined destination position 32. Note that the target position 32 and the obstacle 31
Are overlapped, the distance from the obstacle 31 is given absolute priority over heading toward the target position 32.

FIG. 4 schematically shows a system constructed according to this embodiment. By setting appropriate connection weights between the neurons in the plan net 3 composed of mutual connection neural networks, the mobile robot 2-1
2 to 5 are stored (embedded).

The plan net 3 is a target which is considered to be optimal for an external input, that is, an operational input by an operator, or a current state of the mobile robots 2-1 to 2-5 input from the current position measuring device 5. A state pattern is generated from the energy minimization process of the network. The achieved target state pattern is converted into a form of a movement command to a target position, and transmitted to each of the mobile robots 2-1 to 2-5 via the wireless communication device 4. Each of the mobile robots 2-1 to 2-5 receives this command via the wireless communication device 17, and acts to move to a target position corresponding to the received command. The individual behavior control is independently performed inside each of the mobile robots 2-1 to 2-5. The states of the mobile robots 2-1 to 2-5 are fed back to the plan net 3 via the absolute position measuring device 5. If any of the mobile robots 2-1 to 2-5 cannot reach the target position due to an unexpected disturbance (entrance of the obstacle 31), the plan net 3 becomes unstable because the commanded pattern is not realized. Recall a new alternative plan with the state transition.

The target state pattern recalled by the plan net 3 and the actually achieved mobile robots 2-1 to 2-5
When the physical state pattern (actual state pattern measured by the absolute position measuring device 5) finally matches,
The state of the plan net 3 reaches the minimum solution (including the quasi-minimum solution) of the energy equilibrium point, and the state settles down until there is a new disturbance or operator input. At this time, the energy state of the entire system including the mobile robots 2-1 to 2-5 is also at the minimum solution (including the quasi-minimum solution) of the equilibrium point.

As shown in FIG. 5, the features of this system are as follows.
The physical state of each of the mobile robots 2-1 to 2-5 includes an absolute position measuring device 5 in a plan net 3 (an interconnected neural network) for making an action plan of the mobile robots 2-1 to 2-5 in the field 1. In that it is fed back via Thus, information can be exchanged between the control level (the direction from the plan robot 3 to the mobile robots 2-1 to 2-5) and the plan level (the direction from the mobile robots 2-1 to 2-5 to the plan net 3). As a result, not only the control level but also the plan level can be handled in real time against unexpected disturbances and the like, and the whole system becomes very strong.

In the present embodiment, the energy of the state of the entire system including the planning part and the physical control system of the mobile robots 2-1 to 2-5 is considered. At this time, the objective plan is achieved (mobile robot 2-
Positioning 1 to 2-5 at the destination position) means to settle the state of the system to an appropriate one of a plurality of energy sub-minimum solutions.

This will be described with reference to FIG. Now, for example, six state patterns p1 to p6 (arrangement patterns of the mobile robots 2-1 to 2-5) are stored in the plan net 3, and in the operation mode in the initial state,
It is assumed that any of these patterns can be taken (six minimum solutions exist). At present, mobile robot 2-
1 to 2-5 take the state pattern of p2 (FIG. 6).
(A)).

Thereafter, an operation mode change is input,
When the topology of the minimum solution of the network changes and the pattern p2 is no longer in a stable state, and the patterns p1, p3, p5, and p6 become patterns that can be taken in this operation mode, the entire system makes a state transition, and a stable state of p3 A pattern is taken (the mobile robots 2-1 to 2-5 move and take a state pattern of p3) (FIG. 6B).

Thereafter, when a disturbance occurs in the field 1 (for example, when an obstacle 31 enters), each mobile robot 2
-1 to 2-5 act independently so as not to collide with the obstacle 31. As a result, the state pattern of p3 cannot be maintained. At this time, the pattern p3 is not at the energy balance point in the entire system. As a result, the system makes a state transition and takes the state of the pattern p5 which is another stable minimum solution (the mobile robots 2-1 to 2-5 take the state pattern of p5) (FIG. 6 (C)).

The energy E of the whole system is expressed as follows. E = plan (Ld, Lr, op_mode) + control1 (|| Ld-Lr ||) + control2 (Lr, dist)

Here, Ld is the mobile robot 2-1 to 2-
5 is a vector representing the target state, and is represented by the firing state of the plan net 3. Lr is the mobile robot 2-1 to 2-
5 is a vector indicating the current state. op_mode indicates the operational mode. plan () is an energy function of the plan net 3, and embeds a desired plurality of state patterns Ld at the energy minimum equilibrium point and a plurality of quasi-minimum equilibrium points by adjusting the connection weight to an appropriate value. Can be. Further, the connection weight of the network is configured so as to satisfy Ld = Lr at these equilibrium points.

Control1 () is a monotonically increasing function, and by minimizing this function, the mobile robots 2-1 to 2-
The state of No. 5 can be made to follow the activated state (target state) of the plan net 3. control2 () is a function indicating the influence of disturbance on the states of the mobile robots 2-1 to 2-5, and the states of the mobile robots 2-1 to 2-5 transit in a direction to reduce the influence of the disturbance. For example, when an obstacle is a disturbance, the mobile robots 2-1 to 2-
The value of this function decreases as the distance between the obstacle 5 and the obstacle increases. dist represents a state of disturbance.

Next, a specific example of disposing the mobile robot at a predetermined position will be described. First, the mobile robots 2-1 to 2-5
The following describes an example in which each is not distinguished.

In this case, the following arrangement tasks are assumed. (1) There are a plurality of arrangement patterns for each operation mode. (2) Which mobile robot 2-1 corresponds to each arrangement pattern
To 2-5 may be arranged at any position on the field 1. (3) A plurality of mobile robots 2-1 to 2-5 cannot be arranged at one position (frame) on the field 1.

As shown in FIG. 7, the plan net 3 includes
The measurement position Lr [i] (i) of each mobile robot 2-1 to 2-5
= 1, 2, ..., n. In the case of the embodiment, n = 5) is input from the absolute position measuring device 5. Then, the target movement position Ld [i] of each of the mobile robots 2-1 to 2-5 is output from the firing state of the neuron of the plan net 3. The target movement position Ld [i] is instructed to each of the mobile robots 2-1 to 2-5 via the wireless communication device 4.

A predetermined operation mode is currently input to the plan net 3, and any one of three arrangement patterns p1, p2, and p3 can be adopted on the plan. In the pattern p1, three mobile robots are vertically arranged at the lower center in the field 1, and the other mobile robots are arranged one by one on the left and right of the lowest one. In the pattern p2, one mobile robot is disposed in the upper center of the field 1, and two mobile robots are respectively disposed on the left and right sides of the mobile robot one by one below. In the pattern p3, the mobile robots are arranged at the center on the right side of the field 1 so as to have a “U” shape.

Of these three patterns, the pattern
p1 cannot be achieved because the obstacle 31 exists in the field 1. Therefore, so that the arrangement state of any of the remaining patterns p2 and p3 (for example, pattern p3),
Each of the mobile robots 2-1 to 2-5 moves. At this time, which of the patterns p2 and p3 is achieved depends on the state before the mobile robots 2-1 to 2-5. For example, if the position state of the mobile robots 2-1 to 2-5 is relatively close to the pattern p3 before the obstacle 31 enters, the pattern p3 is easily achieved in the state after the obstacle 31 enters. Become.

FIG. 8 shows how the mobile robots 2-1 to 2-5 autonomously regenerate the arrangement state when the obstacle 31 enters the field 1. In the initial state, the arrangement state of the pattern p1 is stable (see FIG. 8).
(A)). Then, the mobile obstacle 31 is moved to the field 1
When a disturbance occurs to invade the inside (Fig. 8
(B)), each of the mobile robots 2-1 to 2-5 is an obstacle 3
It moves slowly and independently so as not to touch 1. The moved position state is fed back to the plan net 3, and the pattern p1 recalled on the plan net 3 becomes unstable. Then, the pattern recalled in the planet 3 finally makes a state transition from the pattern p1 to the pattern p3, and the mobile robots 2-1 to 2-5 correspond to the pattern p3.
Is generated and stabilized (FIG. 8C).

Next, a configuration example of the plan net 3 will be described with reference to FIG. The plan net 3 has a network layer structure, and forms one interconnected network as a whole. Each network layer is roughly divided into the following two layers.

(1) Group-Wide Plan Layer (Rare H, Rare 0) The rare H stores patterns P1 to P5, and develops a pattern corresponding to a command input from the operator to the rare 0. Therefore, mobile robot 2-1 is included in rare 0.
The entire selected arrangement pattern (arrangement pattern as a commanded group) of 2 to 5 is recalled. Rare 0 neurons are arranged on the xy plane, and the mobile robot 2-
It corresponds to each point (frame) of field 1 of 1 to 2-5 (possible positions that mobile robots 2-1 to 2-5 can take). That is, the rare H and the rare 0 constitute an associative memory network with an input portion.

(2) Individual mobile robots 2-1 to 2-
Layers corresponding to No. 5 (Rare 1 to 5) Rare 1 to 5 are layers corresponding to the mobile robots 2-1 to 2-5, respectively. Each rare 1-5 neuron
Like Rare 0, they are arranged on the xy plane. A positive input is made to a neuron corresponding to the current physical position of each of the mobile robots 2-1 to 2-5. In each of the rares 1 to 5, only one neuron can be fired, and the neuron represents the movement destination position of the corresponding mobile robot 2-1 to 2-5.

In the embodiment shown in FIG. 9, a "U" -shaped pattern p3 is recalled for rare 0, and rares 1 to 5 correspond to each neuron constituting this character "ko" for rare 0. One neuron is in a fired state. In the rares 1 to 3, the current positions of the mobile robots 2-1 to 2-3 match the target positions. On the other hand, in Rare 4 and Rare 5, the current positions of the mobile robots 2-4 and 2-5 are different from the target positions.
Therefore, in this case, as shown in FIG. 10, the mobile robots 2-4 and 2-5 move to the position (target position) of the neuron designated by rare 0.

As a constraint of the network, if a neuron at position (i, j) in Rare 0 (hereinafter referred to as A-gl [i, j]) is firing, one of Rare 1 to Rare 5 , The neuron at position (i, j) (hereinafter referred to as A [i, j,
k]. However, k represents the k-th one of the rares 1 to 5). At this time, in rare 0,
Without distinguishing between the mobile robots 2-1 to 2-5,
The positions as the mobile robots 2-1 to 2-5 are shown. That is, it is not necessary that a specific one of the mobile robots 2-1 to 2-5 be arranged at a predetermined position, and any one of the mobile robots 2-1 to 2-5 is arranged at a predetermined position. It is sufficient that a predetermined pattern is realized. In other words, the mobile robots 2-1 to 2
Which one of -5 moves to which position is executed by the cooperative operation between the mobile robots that behave independently.

This cooperative operation can be realized by setting a combination of mutual inhibition and mutual excitation as shown in FIGS. Such setting is performed, for example, by the following combination.

(1) The connection between the neurons A [i, j, k] and A [i, j, l] (where l ≠ k) is a negative connection. Here, the negative coupling is
This is a connection that prevents each neuron from firing at the same time (increases energy when fired simultaneously). That is, a predetermined rare (for example, rare 3) among rares 1 to 5
When the neuron at position (i, j) is firing, the corresponding position (i, j) of another rare (eg, rare 1,2,4,5)
In the neurons, firing is suppressed (FIG. 11). (2) In rare area i (i = 1 to 5), the connection between neurons is a negative connection. (3) Each neuron of rare i (i = 1 to 5) has a negative bias. (4) Rare 0 neuron A-gl [i, j] and rare 1 to 5
The connection of the neuron A [i, j, k] is positive. Here, the positive coupling is a coupling that excites each neuron to fire at the same time (the energy is reduced when firing at the same time). That is, the neuron A-gl [i,
When j] fires, the neurons A [i, j, k] of rare 1 to 5 also try to fire (FIG. 12). (5) In rare 0, operation input (target position of each mobile robot) and arrangement pattern (memory pattern)
Are matched, the connection weight of each neuron is adjusted so that the energy is minimized.

Next, with reference to FIGS. 13 to 16, an example of an arrangement that imposes restrictions on the positional relationship between individual mobile robots will be described. Case 1: There are four mobile robots, and the mobile robot 2-11 and the mobile robot 2-12 are arranged so as to always be close to each other (for example, arranged within one frame).
The mobile robot 2-13 and the mobile robot 2-14 are arranged so as to always keep a predetermined distance from each other (for example, a distance of 5 frames or more).

Such a constraint can be embedded in the plan net 3 as shown in FIG. 13, for example. The plan net 3 includes four mobile robots 2-11 to 2-1.
4 are composed of rares 11 to 14.
However, in this embodiment, the rare H and the rare 0 as the group-wide plan layer as described above are not provided.
Then, the above constraint is embedded in the net by taking the following connection.

(1) The rares 11 to 14 are mutually suppressed and bonded. (2) When the distance (coma distance) between the rare 11 and 12 neurons is 1, a positive connection is established. (3) If the distance (coma distance) between the rare 13 and 14 neurons is 5, a positive connection is established. (4) No coupling is provided except for the above (1) to (3).

In such a state, as shown in FIG. 13, when a positive input is applied to the rare 13 as an operation (operational) mode input, for example,
As shown in FIGS. 14A to 14D, for example, as shown in FIGS. 14A to 14D, the mobile robot 2-11 and the mobile robot 2-12 are always arranged close to a distance within one frame. Mobile robot 2-13 and mobile robot 2
−14 are always arranged at least 5 frames apart).

Case 2: Mobile robots 2-11 to 2-
14 are arranged so as to always form a loop pattern, as shown in FIGS.

In this case, similarly to the case 1, the constraints of the present case are embedded in the plan net 3 by setting the connection between the rares 11 to 14 as follows. (1) The connection between the neurons A [i, j, 1] and A [i + 1, j-1,2] is a positive connection. (2) The connection between the neurons A [i, j, 2] and A [i + 1, j + 1,3] is a positive connection. (3) The connection between the neurons A [i, j, 3] and A [i-1, j + 1,4] is a positive connection. (4) The connection between the neurons A [i, j, 4] and A [i-1, j-1,1] is a positive connection.

By setting the connection in this manner, as shown in FIGS. 16 (A) to 16 (D), the mobile robot 2-
11 to 2-14 can be arranged so as to always form a loop pattern.

As the neural net as the plan net 3, it is preferable to basically use a mutual equivalent weight connection represented by a Hopfield net. By doing so, it is possible to have a number of equilibrium points in the energy field of the network and to embed a lot of plan patterns in them. When the number of equilibrium points is increased in this way, in the planning process, the state falls to an undesired energy minimum point, and there is a high possibility that the state cannot be escaped therefrom. So, in such a case,
In addition to the usual analog and binary Hopfield net algorithms, a thermodynamic algorithm or a chaotic steepest descent method can be used to escape from the local energy minimum state and search for the minimum value. It is preferable to do so. This chaotic steepest descent method is described in IEICE, August 1991, Transaction A,
Vol. J74-ANo. 8, P1208-P121
5. "Dynamic characteristics of learning and memory recall in a neural network to which the chaotic steepest descent method is applied", or Japanese Patent Application No. 3-240467 (Japanese Patent Application No. 2-2989)
No. 84, Japanese Patent Application No. 2-414907 and Japanese Patent Application No. 3-1
No. 49688 (National priority application).

In the above description, the present invention is applied to a case where a mobile robot is arranged at a predetermined position. However, the present invention can also be applied to a case where a plurality of characters in a video game are group-controlled as controlled objects. it can. Further, the present invention can be applied to a case where a control target is arranged not only in a two-dimensional space but also in a three-dimensional space.

[0042]

According to the arrangement control method and apparatus of the present invention,
For example, multiple patterns related to the arrangement of multiple
Memorized patterns, and from among the memorized patterns,
Select one pattern. And multiple controlled objects
Instructs you to position it according to the selected pattern
Then, the actual arrangement state of the control target is detected. Also detect
The actual placement of the controlled objects in the specified pattern
Judge whether it corresponds to the arrangement state of the control target based on,
The actual placement status of the detected control target and the specified pattern
It is determined that the arrangement state of the control target based on the
When the pattern is
Instruct the controlled object to be located corresponding to either
As a result, even when a disturbance occurs, the control target can be simply and reliably positioned at a predetermined position without being disabled.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of a mobile robot control system to which an arrangement control method and apparatus of the present invention is applied.

FIG. 2 is a block diagram illustrating a configuration example of a mobile robot in FIG. 1;

FIG. 3 is a diagram illustrating a state in which a mobile robot moves around an obstacle.

FIG. 4 is a block diagram illustrating a control system when a disturbance occurs in the embodiment of FIG. 1;

FIG. 5 is a conceptual diagram illustrating a control state when disturbance occurs in the embodiment of FIG.

FIG. 6 is a diagram illustrating a state transition of an arrangement pattern of a mobile robot.

FIG. 7 is a block diagram illustrating an operation of arranging a mobile robot in accordance with a stored arrangement pattern.

FIG. 8 is a diagram illustrating a state in which the mobile robot autonomously moves in response to a disturbance.

FIG. 9 is a diagram showing a configuration example of a plan net 3 in FIG. 1;

FIG. 10 is a diagram illustrating how the mobile robot moves in accordance with the embodiment of FIG.

FIG. 11 is a view for explaining mutual suppression coupling of each rare constituting the plan net 3 in FIG. 1;

FIG. 12 is a diagram for explaining mutual excitation coupling of each of the rare elements constituting the plan net 3 in FIG. 1;

FIG. 13 is a diagram illustrating a configuration example of a neural network when mobile robots are arranged so as to maintain a predetermined relationship with each other.

FIG. 14 is a diagram illustrating a state in which mobile robots move while maintaining a predetermined relationship with each other, corresponding to the embodiment in FIG. 13;

FIG. 15 is a diagram illustrating a configuration example of another neural net when mobile robots are arranged so as to maintain a predetermined relationship with each other.

FIG. 16 is a diagram illustrating a state in which mobile robots move while maintaining a predetermined relationship with each other, corresponding to the embodiment in FIG. 15;

[Explanation of symbols]

 REFERENCE SIGNS LIST 1 placement space (field) 2-1 to 2-5 mobile robot 3 plan net 4 wireless communication device 5 absolute position measurement device 11 front wheel 12, 13 rear wheel 14 obstacle sensor 15 obstacle sensing system 16 controller 17 wireless communication device 31 Obstacles 32 destinations

Claims (8)

(57) [Claims] 1. An arrangement control method for arranging a plurality of control targets at predetermined positions in a predetermined space, wherein the plurality of control targets are disposed at predetermined positions in the space.
A storing step of storing a pattern; and a plurality of previous steps stored by the processing of the storing step.
Select a pattern to select one pattern from the
And step, the plurality of the control object, a first instruction step of instructing to be positioned in correspondence with the pattern selected by the process of the selection step, detection of detecting the actual arrangement of the control object Steps
And whether or not the actual arrangement state of the control target detected by the processing of the detection step corresponds to the arrangement state of the control target based on the pattern instructed in the processing of the first instruction step. The determining step and the processing of the determining step determine the processing of the detecting step.
The actual arrangement state of the controlled object detected by
To the pattern specified in the process of the first specifying step
It is determined that the arrangement state of the control
Before being stored in the processing of the storing step
Corresponding to one of the other patterns
A second instruction step for instructing the controlled object to
Arrangement control method characterized by comprising a-up. 2. The arrangement control method according to claim 1, wherein the control target is a mobile robot. (3) Stored in the processing of the storing step.
The plurality of patterns and the detection step.
The arrangement state of the plurality of control objects output is
Connected by a type network Claims characterized by
Item 2. The arrangement control method according to Item 1. (4) The interconnected network comprises a plurality of
A first pattern in which one of the patterns is developed
Network and the detection step for each control object.
Net holding the placement state detected in the processing of the
Work and 4. The arrangement according to claim 3, comprising:
Control method. 5. An arrangement control device for arranging a plurality of control targets at predetermined positions in a predetermined space, wherein the plurality of control targets are disposed at predetermined positions in the space.
Storage means for storing a pattern, and a plurality of the patterns stored by the storage means
Selecting means for selecting one of the patterns; first instructing means for instructing the plurality of controlled objects to be positioned corresponding to the pattern selected by the selecting means; Detecting means for detecting an arrangement state of the control target; and an actual arrangement state of the control object detected by the detection means, the arrangement state of the control object based on the pattern instructed by the first instruction means. Determining means for determining whether or not they correspond to each other; and an actual value detected by the detecting means by the determining means.
The arrangement state of the control object at the time and the first instruction means.
Distribution of the control target based on the pattern specified by
The storage means, when it is determined that the
Of the patterns stored by the
The control target so that it is positioned corresponding to any of the
And a second instructing means for instructing . Wherein said control target arrangement control device according to claim 5, characterized in that the mobile robot. 7. A plurality of data stored by said storage means.
And the plurality of patterns detected by the detection means.
The above-mentioned arrangement state of the control target is a mutual connection type network.
The arrangement control device according to claim 5, wherein the arrangement control device is connected by a hook . Claim 8. The interconnected network comprises a plurality of
A first pattern in which one of the patterns is developed
Network and the detection means for each of the control targets.
A second network that holds the arrangement state detected by the second network
When The arrangement control device according to claim 7, comprising:
Place.