JP6958517B2 - Manipulators and mobile robots - Google Patents

Description

The present invention relates to a manipulator and a mobile robot for transporting a work.

In recent years, in an apparatus for gripping and transporting a work, a method of moving the camera to take an image has been proposed in order to expand the imaging range of the camera for detecting the work. As a typical example, a hand-eye system in which a camera is attached to the tip of a robot arm is known. However, when the camera moves, the positional relationship between the camera and the work may not be preferable for imaging the work.

Therefore, in Patent Document 1, it is a method of controlling a robot arm mounted on an automatic guided vehicle, and if two marks can be recognized by an image input unit fixed to the robot arm and at least one of the above marks can be recognized. A method for controlling a robot arm is disclosed, in which the two marks can be simultaneously captured in the viewing area by removing the robot arm.

Further, in Patent Document 2, an image pickup device is attached to the robot arm, and the image pickup device generates an image of a region including a work. In the generated image, when the feature portion cannot be specified by pattern matching, the robot arm is operated so that the relative position or posture between the work and the imaging device and the lighting device changes, and the work is operated. Is imaged again, and pattern matching is performed again on the image generated by the image, and a method of gripping the work is disclosed.

Japanese Unexamined Patent Publication No. 11-320465 Japanese Unexamined Patent Publication No. 2015-160264

In the conventional technique as described above, when the work cannot be detected, the work can be detected by changing the position of the camera and re-imaging. However, when re-imaging the work, it takes extra time to move the camera to perform re-imaging and image analysis. Therefore, there is a problem that the transfer work time of the work is increased and the cost effectiveness is reduced.

One aspect of the present invention is to realize a manipulator having an improved work detection success rate in order to suppress an increase in transport work time due to resensing.

In order to solve the above problems, the manipulator according to one aspect of the present disclosure may include a robot arm that grips an object and a plurality of the objects provided on the robot arm. The operation of the robot arm is controlled so as to move the sensor unit that senses a possible predetermined space region by light or ultrasonic waves and the sensor unit to a sensing position corresponding to the sensing position information associated with the space region. The sensing result of the sensing position control unit and the sensor unit at the sensing position are analyzed, and the object identification unit that identifies the object to be gripped in this gripping operation and the object identification unit identify the object. The gripping motion control unit that controls the motion of the robot arm so as to grip the object to be gripped in the current gripping motion and the sensor unit at the sensing position are analyzed, and the next gripping motion is performed. It is provided with a sensing position updating unit that specifies a sensing position for the previous next sensing operation and updates the sensing position information.

According to the above configuration, since the object to be gripped in the current gripping operation is specified based on the sensing result sensed by the sensor unit, the object to be gripped by the robot arm can be gripped and conveyed. Further, in the next sensing, the sensor unit can move to a position where the object to be gripped next time can be sensed and sense the object. Therefore, it is possible to reduce the possibility that the object to be gripped next time cannot be detected and resensing is required.

The current sensing position and the next sensing position are different from each other. Therefore, there is a high possibility that the next sensing result will include a new (one after another) object to be gripped. Therefore, it is possible to detect the object to be gripped one after another and specify the position of the object.

The sensor unit is an imaging unit that captures an image of the predetermined spatial region, the sensing position information is imaging position information, the sensing position is an imaging position, and the sensing position control unit is the imaging position. It is an imaging position control unit that controls the operation of the robot arm so as to move the imaging unit to the imaging position according to the information, the sensing result is an image captured image, and the sensing operation is an imaging operation. The sensing position update unit may be configured to be an image pickup position update unit that updates the image pickup position information.

The sensing position update unit may analyze the sensing result by the sensor unit at the sensing position and update the sensing position information based on the position of the object to be gripped in the next gripping operation.

According to the above configuration, it is possible to obtain a sensing result that can more reliably detect an object to be gripped in the next gripping operation. Therefore, it is possible to further reduce the possibility that the object to be gripped next time cannot be detected and resensing is required.

As a result of analyzing the sensing result by the object identification unit, when the object to be gripped cannot be detected in the current gripping operation, the sensing position control unit moves the sensor unit by a predetermined amount. Even if the movement of the arm is controlled, the object identification unit analyzes the sensing result of the sensor unit performing sensing again at the position after movement, and identifies the object to be gripped in this gripping operation. good.

According to the above configuration, even if the object to be gripped cannot be detected in the sensing result sensed by the sensor unit, the manipulator can automatically search for and find the object to be gripped.

Any of the above-mentioned manipulators may be mounted on an automatic guided vehicle.

In order to solve the above problems, the mobile robot according to one aspect of the present disclosure includes any of the above-mentioned manipulators and an automatic guided vehicle on which the manipulators are mounted.

According to the above configuration, the manipulator can be moved by an automatic guided vehicle.

The sensing position control is further provided with a communication unit that transmits the sensing position information specified by the sensing position update unit to an external device by communication and receives the sensing position information based on the sensing result by another manipulator from the external device. The operation of the robot arm may be controlled so that the unit moves the sensor unit to a sensing position corresponding to the sensing position information received by the communication unit.

According to the above configuration, the amount of sensing position information that can be used by the manipulator is dramatically increased by communicating with each other and sharing the sensing position information between the plurality of manipulators and the external device. As a result, the possibility of moving the sensor unit to an appropriate position for sensing is improved, and the possibility of detecting an object to be gripped is improved. Therefore, the manipulator cannot detect the object to be gripped, and the possibility of performing sensing again can be reduced.

The external device may be a server described later or another manipulator. When the external device is another manipulator, the specific manipulator may have a server function, or the sensing position information may be transmitted and received between a plurality of manipulators.

When the gripping operation of the plurality of objects is repeated during the period when the automatic guided vehicle is not moving, the sensing position control unit does not use the sensing position information received by the communication unit. The movement control of the sensor unit may be performed by using the sensing position information specified by the sensing position updating unit in the previous gripping operation.

According to the above configuration, the sensor unit can be moved to a position where the object to be gripped next time can be sensed by the latest sensing position information generated by the manipulator itself. Further, it is not necessary to receive the sensing position information from the external device.

According to one aspect of the present disclosure, it is possible to realize a manipulator having an improved detection success rate of an object in order to suppress an increase in transport work time due to resensing.

It is a figure which shows typically the mobile robot which concerns on Embodiment 1. It is a block diagram which shows the main part structure of the mobile robot which concerns on Embodiment 1. FIG. The imaging regions imaged by the camera according to the first embodiment, (a) to (c), are diagrams schematically showing the imaging regions before the first to third workpiece transfer, respectively. It is a figure which shows typically the imaging area of the camera which concerns on Embodiment 1. FIG. It is a flowchart which shows an example of the processing flow in the control part which concerns on Embodiment 1. FIG. It is a figure which shows typically the information processing system which concerns on Embodiment 2. It is a block diagram which shows the main part structure of the mobile robot which concerns on Embodiment 2. It is a flowchart which shows an example of the processing flow in the control part which concerns on Embodiment 2.

[Embodiment 1]
Hereinafter, an embodiment according to one aspect of the present invention (hereinafter, also referred to as “the present embodiment”) will be described with reference to the drawings.

§1 Application example FIG. 1 schematically illustrates the mobile robot 1 according to the present embodiment. FIG. 2 is a block diagram illustrating a configuration of a main part of the mobile robot 1 according to the present embodiment. FIG. 3 shows an imaging region imaged by the camera (imaging unit) 14 according to the present embodiment, and FIGS. 3A to 3C are imaging regions before the first to third workpiece transfer, respectively. It is a figure which shows typically. First, an outline of an application example of the mobile robot 1 will be described with reference to FIGS. 1 to 3.

As shown in FIGS. 1 and 2, the mobile robot 1 is a device for transporting a work (object) 2. The mobile robot 1 includes a manipulator 10 and an automatic guided vehicle 50. The manipulator 10 includes a robot arm 11 and a housing portion 15. The manipulator 10 may be fixedly mounted on a fixed base or the like instead of the movable automatic guided vehicle 50.

The robot arm 11 is a member that performs a gripping operation on the work 2. The robot arm 11 includes a work gripping portion 13 for gripping the work 2 and a camera 14 at one end thereof.

The housing portion 15 includes a control device 20. The camera 14 captures an imaging region (spatial region) including a stocker 3 on which a plurality of works 2 can be placed.

As shown in FIG. 2, the control device 20 includes a control unit 21 and a first storage unit 30. The control unit 21 includes an image pickup position update unit 22, an object identification unit 23, a gripping operation control unit 24, an image pickup position control unit 25, an automatic guided vehicle control unit 26, and a camera control unit 27.

The imaging position control unit 25 (sensing position control unit) moves the camera 14 to the imaging position (sensing position) according to the imaging position information (sensing position information) associated with the imaging region, so that the robot arm 11 moves the camera 14. Control the operation of. Here, the imaging position information may be specified or updated by the user, or may be updated by the imaging position updating unit 22 (sensing position updating unit) as described later.

The object identification unit 23 analyzes the image (sensing result) captured by the camera 14 at the imaging position, and identifies the work 2 to be gripped in the current gripping operation. Further, the imaging position updating unit 22 analyzes the captured image, identifies the imaging position by the camera 14 before the next gripping operation, and updates the imaging position information. Here, the “next” gripping operation refers to the case where another work 2 is continuously transported after the work 2 specified by the object specifying unit 23 is gripped and transported, with respect to the other work 2. The gripping operation is shown.

The gripping motion control unit 24 controls the motion of the robot arm 11 so as to grip the work 2 to be gripped in the current gripping motion specified by the object identification unit 23.

The outline of the operation of the mobile robot 1 will be described with reference to FIG. As shown in FIG. 3A, the camera 14 images the imaging region A1 including the stocker 3 based on the imaging position information. The captured image is analyzed by the object identification unit 23, and the work 2a to be gripped is specified.

At this time, the imaging position updating unit 22 analyzes the captured image and specifies the next imaging position. For example, the imaging position updating unit 22 may specify the next imaging position so that the work 2b to be gripped next time is included in the predetermined range of the next captured image. The next imaging position may be a position where the work 2b to be gripped next time is imaged so as to be substantially the center of the imaging range. In this way, the imaging position updating unit 22 identifies the imaging position and updates the imaging position information stored in the first storage unit 30.

According to the configuration in which the imaging position updating unit 22 specifies the next imaging position, the camera 14 can image the imaging region including the stocker 3 from the position where the work 2b can be imaged in the next imaging. Therefore, it is possible to reduce the possibility that the work to be gripped next time cannot be detected and reimaging is required.

Further, according to the configuration in which the imaging position in which the work 2b is substantially centered is specified as the imaging position, an captured image capable of detecting the work 2b more reliably can be obtained. Therefore, the possibility that the work 2b to be gripped next time cannot be detected and reimaging is required can be further reduced.

Next, as shown in FIG. 3B, the image pickup region A2 is imaged by the camera 14 based on the updated image pickup position information. Here, too, the object identification unit 23 analyzes the captured image and identifies the work 2b as the gripping target, and the imaging position updating unit 22 analyzes the captured image and the imaging position is based on the position of the work 2c to be the next gripping target. Update the information. In this way, if the previous imaging position and the current imaging position are different from each other, there is a high possibility that the current captured image includes a new (next) object to be gripped (work 2c). Therefore, it is possible to detect the object to be gripped one after another and specify the position of the object.

Next, as shown in FIG. 3C, the image pickup region A3 is imaged by the camera 14 based on the updated image pickup position information. Here, the object specifying unit 23 specifies the work 2c as a gripping target, but since the imaging region A3 does not clearly include the other work 2, the imaging position updating unit 22 becomes the next gripping target. Work 2 cannot be detected.

In this case, the imaging position updating unit 22 may refer to the analysis result of the past captured image stored in the first storage unit 30. For example, the imaging position updating unit 22 analyzes the captured image captured by the imaging region A1 to identify the ungrasped work 2d as the next gripping target, and the imaging position so that the work 2d is substantially the center of the imaging range. The information may be updated.

With such a configuration, there is a higher possibility that the work 2 to be gripped next time can be detected. Therefore, it is possible to reduce the possibility that the work 2 to be gripped next time cannot be detected and reimaging is required.

§2 Configuration example (robot arm 11)
The robot arm 11 includes a joint portion 12 formed so as to be rotatable and flexible in an arbitrary direction. The number of joints 12 included in the robot arm 11 may be one or a plurality. Further, one end of the robot arm 11 is formed so as to be attached to the housing portion 15 in a rotatable and bendable state.

The work gripping portion 13 includes a vacuum pad capable of vacuum-sucking the work 2. The work gripping portion 13 is not limited to this, and may include, for example, a pair of claw portions for gripping the work 2 by sandwiching it.

The camera 14 includes a solid-state image sensor and a lens capable of three-dimensionally recognizing an image pickup target. As the solid-state image sensor, for example, a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide Semiconductor) image sensor or the like may be used. With such a configuration, the spatial position of the work 2 to be gripped can be accurately grasped. The camera 14 is not limited to such an example, and may include, for example, a solid-state image sensor and a lens capable of only capturing a two-dimensional image.

Further, the camera 14 may be provided not on the robot arm 11 provided with the work gripping portion 13, but on the robot arm dedicated to the camera 14. According to such a configuration, the transfer of the work 2 and the image pickup operation by the camera 14 can be performed independently.

The imaging information captured by the camera 14 is input to the control device 20. Further, the imaging information may be input to and stored in the first storage unit 30.

(Control device 20)
The control unit 21 included in the control device 20 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like, and controls each component. The first storage unit 30 is, for example, an auxiliary storage device such as a hard disk drive or a solid state drive, and stores various programs executed by the control unit 21, captured image data captured by the camera 14, image pickup position information, and the like. do.

The image pickup position update unit 22 and the object identification unit 23 may output each analysis result in the captured image to the first storage unit 30, and the first storage unit 30 may store the analysis result. Further, the stored analysis result may be appropriately read out by the control unit 21.

Further, the captured image analyzed by the imaging position updating unit 22 and the object identification unit 23 may be an captured image captured by the camera 14 in the past and stored in the first storage unit 30. According to such a configuration, the possibility that the image pickup position update unit 22 and the object identification unit 23 can detect the work 2 to be gripped by referring to the past captured image is further improved, and re-imaging is suppressed. can do.

The automatic guided vehicle control unit 26 controls the operation of the automatic guided vehicle 50 and moves the mobile robot 1 to a predetermined point. Further, the automatic guided vehicle control unit 26 may control the operation of the automatic guided vehicle 50 based on the imaging position information and the like, and finely adjust the position of the mobile robot 1.

The camera control unit 27 controls the imaging operation (sensing operation) of the camera 14.

(Automated guided vehicle 50)
The automatic guided vehicle 50 includes wheels 51. By controlling the operation of the wheel 51 by the automatic guided vehicle control unit 26, the automatic guided vehicle 50 can move to an arbitrary point. Therefore, the manipulator 10 mounted on the automatic guided vehicle 50 can transport the work 2 to a distant position at a distance that the robot arm 11 cannot reach. In addition, the work point of the manipulator 10 can be changed as appropriate.

The manipulator 10 is not limited to the automatic guided vehicle 50 because it is configured as a movable mobile robot 1. For example, it may be an unmanned aerial vehicle (drone) that can fly, or it may be a trolley that is manually moved.

§3 Operation example (movement of camera 14)
FIG. 4 schematically illustrates an imaging region A of the camera 14 according to the present embodiment. First, the significance of the camera 14 being movable will be described with reference to FIG.

As shown in FIG. 4, the camera 14 included in the mobile robot 1 captures, for example, a stocker 3 on which a plurality of works 2 are placed as an imaging region A. A plurality of stockers 3 may be provided three-dimensionally by being placed on a shelf 4 or the like.

In this case, the mobile robot 1 can include an arbitrary stocker 3 in the imaging region A by adjusting the position of the camera 14 by the operation of the robot arm 11 and the movement of the automatic guided vehicle 50.

However, as shown in FIG. 4, even if the camera is inside the imaging region A, the range blocked by the side wall of the stocker 3 and the range blocked by the work 2 placed on the front side when viewed from the camera 14 are not included. , It becomes a blind spot from the camera 14. Therefore, the work 2 that is not included in the captured image captured by the camera 14 may exist in the stocker 3.

In order to solve such a problem, for example, a camera 14 is provided at one end of the robot arm 11 so that the camera 14 can move. As a result, the position and direction of the camera 14 can be arbitrarily adjusted, and the blind spot can be minimized by photographing the stocker 3 from various directions.

On the other hand, in order to specify the imaging position where the camera 14 can optimally image the work 2, it is necessary to specify the imaging position, for example, by performing image analysis of the captured image captured by the camera 14 in advance. However, since the imaging by the camera 14 and the image analysis processing of the captured image require a certain amount of time, the working time of the mobile robot 1 increases as the number of imaging times increases.

Therefore, as a result of diligent studies, the inventor has determined the number of imaging times by improving the detection success rate of the work 2, and operates the manipulator 10 so as not to cause the delay, and the mobile robot provided with such a manipulator 10. I found 1.

(Processing flow of control unit 21)
FIG. 5 is a flowchart showing an example of a processing flow in the control unit 21 according to the present embodiment. An example of the processing flow in the control unit 21 will be described with reference to FIG.

First, the imaging position control unit 25 determines whether or not the imaging position information corresponding to the imaging region A including the work 2 to be gripped can be acquired from the first storage unit 30 (S1). When the imaging position information cannot be acquired (NO in S1), the control unit 21 acquires a standard value set in advance in the first storage unit 30 as the imaging position information by inputting the user (S2). ..

Next, when the imaging position information can be acquired (YES in S1), or when the imaging position information is specified in step S2, the imaging position control unit 25 of the robot arm 11 based on the imaging position information. The operation is controlled to move the camera 14 to the imaging position (S3). Then, the camera control unit 27 causes the camera 14 to take an image of the image pickup region A. The captured image is input to the object identification unit 23, and the image analysis is performed by the object identification unit 23 (S4).

Next, the object identification unit 23 determines whether or not the work 2 to be gripped is detected by the image analysis (S5). Here, when the work 2 to be gripped is not detected (NO in S5), the imaging position control unit 25 controls the operation of the robot arm 11 so as to move the position of the camera 14 by a predetermined amount (S6). ..

As the predetermined amount, an arbitrary value may be set depending on the type of the work 2 and the arrangement state. Further, the setting of the above arbitrary value may be set by the user. Further, the control unit 21 may automatically set and update the image based on the analysis result of the image captured by the image pickup position update unit 22 and the object identification unit 23 stored in the first storage unit 30.

Next, the camera control unit 27 causes the camera 14 to image the image pickup region A after the movement, and the object identification unit 23 analyzes the image captured by the camera 14 (S7). Then, the object identification unit 23 again determines whether or not the work 2 to be gripped is detected by the image analysis (S8). If the work 2 to be gripped is not detected (NO in S8), the process returns to step S6, and the processes from steps S6 to S8 are repeated until the work 2 to be gripped is detected.

In this way, according to the configuration in which imaging and image analysis are repeated until the work 2 to be gripped is detected, the mobile robot 1 can automatically search for and find the work 2 to be gripped.

Next, when the object identification unit 23 detects the work 2 to be gripped (YES in S5 or S8), the gripping motion control unit 24 controls the motion of the robot arm 11 to grip the work 2. The gripped work 2 is transported to the transport point (S9).

While the gripping and transporting are performed, the imaging position updating unit 22 analyzes the captured image. If there is a work 2 that has not yet been conveyed in the captured image, the work 2 is used as the next gripping target. As a result, the image pickup position by the camera 14 before the next gripping operation is specified, and the image pickup position information stored in the first storage unit 30 is updated (S10).

Next, the process is returned to step S3, and the position of the camera 14 is moved based on the imaging position information specified in step S10. After that, a series of processes are performed again.

By performing such processing, the camera 14 can image the imaging region A from a position where the work 2 to be gripped next time can be imaged in the next imaging. Therefore, it is possible to reduce the possibility that the work 2 to be gripped next time cannot be detected and reimaging (steps S6 to S8) is required.

[Embodiment 2]
Other embodiments of the present disclosure will be described below. For convenience of explanation, the members having the same functions as the members described in the above-described embodiment are designated by the same reference numerals, and the description thereof will not be repeated.

§1 Configuration example FIG. 6 is a diagram schematically showing an information processing system according to the present embodiment. FIG. 7 is a block diagram showing a configuration of a main part of the mobile robot according to the present embodiment. A configuration example of the mobile robot 1 and the information processing system according to the present embodiment will be described with reference to FIGS. 6 and 7.

As shown in FIGS. 6 and 7, the mobile robot 1a according to the present embodiment includes a first communication unit 40, and is configured to be able to communicate with another mobile robot 1b and a server (external device) 60. Is different from the mobile robot 1 according to the first embodiment. The symbols of the mobile robots 1a and 1b are attached to clearly indicate that they are different mobile robots, and the mobile robots 1a and 1b may be collectively referred to as the mobile robot 1.

(1st communication unit 40)
The first communication unit 40 communicates with the server (external device) 60 described later. The first communication unit 40 may perform priority communication using a cable or the like, or may perform wireless communication. Further, the first communication unit 40 may communicate with each other with the first communication unit 40 included in another mobile robot 1.

(Server 60)
The server 60 includes a second communication unit 61, an information management control unit 62, and a second storage unit 63. The information management control unit 62 controls writing to the second storage unit 63 according to the state change of the mobile robot 1 (updates the database according to the movement of the mobile robot 1 and the like), and via the second communication unit 61. Communication control (information transmission according to the movement of the mobile robot 1 and the like) is performed.

For example, the server 60 receives the image pickup position information generated by another mobile robot 1a (another manipulator) by the second communication unit 61, and stores the image pickup position information in the second storage unit 63. The imaging position information is transmitted from the server 60 to the mobile robot 1b or the like at any time. Further, the mobile robot 1a may receive the imaging position information generated and transmitted by itself from the server 60. As a result, the imaging position information can be shared among the plurality of mobile robots 1.

The information shared between the plurality of mobile robots 1 is not limited to the above-mentioned imaging position information. For example, as the imaging position information, the captured image data captured by the mobile robot 1 may be shared among the plurality of mobile robots 1 via the server 60.

By communicating with each other and sharing the imaging position information between the plurality of mobile robots 1 and the server 60 in this way, the amount of the imaging position information that can be used by the mobile robot 1 is dramatically increased. Since the mobile robot 1 can use the image pickup position information based on the image captured by another mobile robot 1a, the possibility of moving the camera 14 to an appropriate position and taking an image is improved. Therefore, the mobile robot 1 cannot detect the work 2 to be gripped, and the possibility of re-imaging can be reduced.

§2 Operation example FIG. 8 is a flowchart showing an example of a processing flow in the control unit 21 according to the present embodiment. An example of the processing flow in the control unit 21 will be described with reference to FIG.

First, the image pickup position control unit 25 determines whether or not the image pickup position information corresponding to the image pickup area A including the work 2 to be gripped can be acquired from the first storage unit 30 (S11). When the image pickup position information cannot be acquired (NO in S11), the control unit 21 receives the image pickup position information associated with the image pickup area A including the stocker 3 on which the work 2 to be gripped is placed from the server 60. Receive (S12).

If the imaging position information is not stored in the server 60, the server 60 waits until the imaging position information is acquired. The acquisition of the imaging position information may be performed by, for example, user input.

Next, when the imaging position information can be acquired (YES in S11), or when the imaging position information is received or specified in step S12, the imaging position control unit 25 causes the robot arm 11 to follow the imaging position information. The operation is controlled to move the camera 14 to the imaging position (S13). Then, the camera control unit 27 causes the camera 14 to take an image of the image pickup region A. The captured image is input to the object identification unit 23, and the image analysis is performed by the object identification unit 23 (S14).

Next, the object identification unit 23 determines whether or not the work 2 to be gripped is detected by the image analysis (S15). Here, when the work 2 to be gripped is not detected (NO in S15), the imaging position control unit 25 controls the operation of the robot arm 11 so as to move the position of the camera 14 by a predetermined amount (S16). ..

An arbitrary value may be set for the predetermined amount depending on the type of the work 2, the arrangement state, and the like. Further, the above arbitrary value may be set by the user. Further, the above-mentioned arbitrary value is automatically set and updated by the control unit 21 based on the analysis result of the image captured by the image pickup position update unit 22 and the object identification unit 23 stored in the first storage unit 30. May be good.

Next, the camera control unit 27 causes the camera 14 to image the image pickup region A of the movement destination, and the object identification unit 23 analyzes the image captured by the camera 14 (S17). and,
The object identification unit 23 again determines whether or not the work 2 to be gripped is detected by the image analysis (S18). If the work 2 to be gripped is not detected (NO in S18), the process returns to step S16, and the processes from steps S16 to S18 are repeated until the work 2 to be gripped is detected.

Further, the analysis result of the captured image may be transmitted from the first communication unit 40 to the server 60 and stored by the server 60. Then, the mobile robot 1 may receive the analysis result accumulated in the server 60, and the arbitrary value may be automatically set and updated based on the received analysis result.

Next, when the object identification unit 23 detects the work 2 to be gripped (YES in S15 or S18), the gripping motion control unit 24 controls the motion of the robot arm 11 to grip the work 2. The gripped work 2 is transported to the transport point (S19).

While the gripping and transporting are performed, the imaging position updating unit 22 analyzes the captured image, identifies the imaging position by the camera 14 before the next gripping operation, and stores it in the first storage unit 30. The captured imaging position information is updated (S20). Further, the image pickup position information generated by the image pickup position update unit 22 is transmitted to the server 60 by the first communication unit 40 (S21).

Next, the process is returned to step S11. At this time, when the manipulator 10 repeats the gripping operation of the plurality of works 2 during the period when the automatic guided vehicle 50 is not moving, the image pickup position control unit 25 receives the image pickup by the first communication unit 40. Instead of using the position information, the image pickup position update unit 22 may use the image pickup position information specified in the previous gripping operation to control the movement of the camera 14 (skip S11).

According to such a configuration, the camera 14 can be moved to a position where the work 2 to be gripped next time can be imaged by the latest imaging position information generated by the mobile robot 1 itself. Further, it is not necessary to receive the imaging position information from the server 60.

Further, the mobile robot 1 may receive the imaging position information associated with the space area on which the next gripping object is placed from the server 60. After that, a series of processes are performed again.

[Modification example]
In the above-described first and second embodiments, the case where the camera (imaging unit) 14 is used as the sensor for detecting a plurality of workpieces has been described. However, the present invention is not limited to this, and as a sensor (sensor unit) for detecting a plurality of workpieces in a predetermined spatial region, for example, LIDAR (Light Detection and Ranging or Laser Imaging Detection and Ranging) that performs sensing by light (laser), or super An ultrasonic sensor that senses with sound waves can be used. For example, the control device of the manipulator may obtain information (sensing result) of three-dimensional positions of a plurality of workpieces in a predetermined spatial region by sensing with LIDAR. Alternatively, the control device of the manipulator may obtain information on a sensing image (sensing result) instead of the captured image by sensing with an ultrasonic sensor.

[Example of realization by software]
The control block of the control unit 21 (particularly, the image pickup position update unit 22, the object identification unit 23, and the image pickup position control unit 25) is realized by a logic circuit (hardware) formed in an integrated circuit (IC chip) or the like. It may be realized by software.

In the latter case, the control unit 21 includes a computer that executes instructions of a program that is software that realizes each function. The computer includes, for example, one or more processors and a computer-readable recording medium that stores the program. Then, in the computer, the processor reads the program from the recording medium and executes it, thereby achieving the object of the present disclosure. As the processor, for example, a CPU (Central Processing Unit) can be used. As the recording medium, a "non-temporary tangible medium", for example, a ROM (Read Only Memory) or the like, a tape, a disk, a card, a semiconductor memory, a programmable logic circuit, or the like can be used. Further, a RAM (Random Access Memory) for expanding the above program may be further provided. Further, the program may be supplied to the computer via an arbitrary transmission medium (communication network, broadcast wave, etc.) capable of transmitting the program. It should be noted that one aspect of the present disclosure can also be realized in the form of a data signal embedded in a carrier wave, in which the above program is embodied by electronic transmission.

The present disclosure is not limited to the above-described embodiments, and various modifications can be made within the scope of the claims, and the embodiments obtained by appropriately combining the technical means disclosed in the different embodiments. Is also included in the technical scope of the present disclosure.

1,1a, 1b Mobile robot 2,2a, 2b, 2c, 2d, 2e Work (object)
10 Manipulator 11 Robot arm 14 Camera (imaging unit, sensor unit)
21 Control unit 22 Imaging position update unit (sensing position update unit)
23 Object identification unit 24 Gripping motion control unit 25 Imaging position control unit (sensing position control unit)
26 Automated guided vehicle control unit 40 First communication unit 50 Automated guided vehicle 60 Server (external device)
61 Second communication unit A, A1, A2, A3 Imaging area (spatial area)

Claims (8)

A robot arm that grips an object and
A sensor unit provided on the robot arm that senses a predetermined space area on which a plurality of the objects can be placed by light or ultrasonic waves.
A sensing position control unit that controls the operation of the robot arm so as to move the sensor unit to a sensing position corresponding to the sensing position information associated with the spatial region.
An object identification unit that analyzes the sensing result by the sensor unit at the sensing position and identifies the object to be gripped in this gripping operation, and an object identification unit.
A gripping motion control unit that controls the operation of the robot arm so as to grip the object to be gripped in the current gripping motion, which is specified by the object specifying unit.
A sensing position update unit that analyzes the sensing result by the sensor unit at the sensing position, identifies the sensing position for the next sensing operation before the next gripping operation, and updates the sensing position information.
Manipulator equipped with. The sensor unit is an imaging unit that captures an image of the predetermined spatial region.
The sensing position information is imaging position information, and is
The sensing position is an imaging position.
The sensing position control unit is an imaging position control unit that controls the operation of the robot arm so as to move the imaging unit to the imaging position according to the imaging position information.
The sensing result is a captured image.
The sensing operation is an imaging operation.
The manipulator according to claim 1, wherein the sensing position updating unit is an imaging position updating unit that updates the imaging position information. The sensing position update unit analyzes the sensing result by the sensor unit at the sensing position, and updates the sensing position information based on the position of the object to be gripped in the next gripping operation according to claim 1 or 2. The manipulator described. As a result of analyzing the sensing result by the object identification unit, when the object to be gripped cannot be detected in the current gripping operation,
The sensing position control unit controls the operation of the robot arm so as to move the sensor unit by a predetermined amount.
The object identification unit analyzes the sensing result of the sensor unit performing sensing again at the position after the movement, and identifies the object to be gripped in the current gripping operation, any one of claims 1 to 3. The manipulator described in the section. The manipulator according to any one of claims 1 to 4, which is mounted on an automatic guided vehicle. A communication unit is further provided, which transmits the sensing position information specified by the sensing position update unit to an external device by communication, and also receives the sensing position information based on the sensing result by another manipulator from the external device.
The manipulator according to claim 5, wherein the sensing position control unit controls the operation of the robot arm so as to move the sensor unit to a sensing position corresponding to the sensing position information received by the communication unit. When the gripping operation of the plurality of objects is repeated during the period when the automatic guided vehicle is not moving, the sensing position control unit does not use the sensing position information received by the communication unit. The manipulator according to claim 6, wherein the sensing position updating unit controls the movement of the sensor unit by using the sensing position information specified in the previous gripping operation. A mobile robot including the manipulator according to any one of claims 1 to 7 and an automatic guided vehicle on which the manipulator is mounted.

Images