Robot system

Abstract

The invention discloses a robot system. The robot system comprises a robot and an AI vision device. Comprising an imaging module used for shooting a video image of a robot working site in real time; the partitioning module is used for partitioning the shot video image into a plurality of different regions; the identification module is used for identifying whether a person enters the plurality of different areas or not; and the control module communicates with the robot and is used for controlling the robot according to the recognition result of the recognition module. The control module comprises a plurality of different areas, the plurality of different areas comprise a first virtual guardrail area surrounding the robot, and when the identification module identifies that a person enters the first virtual guardrail area, the control module sends a control instruction for stopping operation to the robot so as to control the robot to stop operation immediately. Therefore, the safety of the guardrail-free robot system can be improved.

Description

Technical Field

[0001] The present invention relates to a robot system, and in particular to a robot system without physical guardrails. Background Art

[0002] In the prior art, to ensure safety, it is usually necessary to install a fixed guardrail around the robot. While the robot is performing its work, the guardrail door is closed to prevent people from entering the guardrail. However, installing a fixed guardrail is very inconvenient. In addition, for mobile robots that need to be applied to different production equipment, since they need to move between different production equipment, it is impossible to install a fixed guardrail around the robot because the guardrail will affect the connection between the robot and the different production equipment. Therefore, in the prior art, there are no guardrails around mobile robots that need to move between different production equipment, which will lead to serious safety hazards in the robot system. Summary of the Invention

[0003] The purpose of the present invention is to solve at least one aspect of the above-mentioned problems and defects in the prior art.

[0004] According to one aspect of the present invention, a robot system is provided. The robot system includes: a robot and an AI vision device. The system includes: an imaging module for capturing real-time video images of the robot's work site; a partitioning module for dividing the captured video images into a plurality of different areas; a recognition module for identifying whether a person has entered the plurality of different areas; and a control module for communicating with the robot and controlling the robot based on the recognition results of the recognition module. The plurality of different areas include a first virtual guardrail area surrounding the robot. When the recognition module identifies that a person has entered the first virtual guardrail area, the control module sends a control instruction to the robot to stop working, so as to control the robot to stop working immediately.

[0005] According to an exemplary embodiment of the present invention, the multiple different areas also include a second virtual guardrail area surrounding the first virtual guardrail area; when the recognition module recognizes that no one enters the first virtual guardrail area but recognizes that someone enters the second virtual guardrail area, the control module sends a control instruction to the robot to slow down the operation to control the robot to reduce the operating speed.

[0006] According to another exemplary embodiment of the present invention, the multiple different areas also include a safety area located outside the second virtual guardrail area; when the recognition module recognizes that no one has entered the first and second virtual guardrail areas but recognizes that someone has entered the safety area, the control module sends a normal operation control instruction to the robot to allow the robot to operate normally.

[0007] According to another exemplary embodiment of the present invention, the robot system further includes a production device, the robot is connected to the production device, the robot is located in the first virtual guardrail area, and the production device is located outside the first virtual guardrail area but in the second virtual guardrail area.

[0008] According to another exemplary embodiment of the present invention, the robot is a mobile robot and is adapted to be connected to different production equipment, so that the robot can be applied to different production equipment.

[0009] According to another exemplary embodiment of the present invention, the recognition module can only recognize human features and cannot recognize features of objects other than the human body, so as to allow objects other than the human body to enter the first virtual guardrail area and the second virtual guardrail area.

[0010] According to another exemplary embodiment of the present invention, the human body features include human head features, human body features, human hand features, and human foot features.

[0011] According to another exemplary embodiment of the present invention, when any one of a person's head features, body features, hand features, and foot features is recognized in the first virtual guardrail area or the second virtual guardrail area, the recognition result of the recognition module is that someone has entered the first virtual guardrail area or the second virtual guardrail area.

[0012] According to another exemplary embodiment of the present invention, when none of the human head features, human body features, human hand features and human foot features are recognized in the first virtual guardrail area or the second virtual guardrail area, the recognition result of the recognition module is that no one has entered the first virtual guardrail area or the second virtual guardrail area.

[0013] According to another exemplary embodiment of the present invention, the imaging module includes a camera, the partitioning module, the identification module and the control module are functional modules integrated into the hardware of the camera, and the control module is connected to the robot via a signal line to communicate with the robot.

[0014] According to another exemplary embodiment of the present invention, when the recognition module recognizes that someone enters the first virtual guardrail area, the control module controls the moving parts of the robot to stop moving immediately; when the recognition module recognizes that no one enters the first virtual guardrail area but recognizes that someone enters the second virtual guardrail area, the control module controls the moving parts of the robot to reduce the moving speed; when the recognition module recognizes that no one enters the first virtual guardrail area and the second virtual guardrail area, the moving parts of the robot are not affected and move normally.

[0015] According to another exemplary embodiment of the present invention, the moving component of the robot includes a manipulator.

[0016] According to another exemplary embodiment of the present invention, the robot system includes a plurality of the AI ​​vision devices, and the plurality of AI vision devices are respectively arranged in a plurality of different orientations.

[0017] According to another exemplary embodiment of the present invention, when the robot receives a control instruction to stop working from any one of the plurality of AI vision devices, the robot stops working immediately.

[0018] According to another exemplary embodiment of the present invention, when the robot does not receive a control instruction to stop working but receives a control instruction to slow down working from any one of the plurality of AI vision devices, the robot immediately reduces the working speed.

[0019] According to another exemplary embodiment of the present invention, when the robot receives a control instruction to stop working and a control instruction to slow down working at the same time, the robot stops working immediately.

[0020] In the aforementioned exemplary embodiments of the present invention, the AI ​​vision device sets a virtual guardrail area for the robot and can identify whether a person enters the virtual guardrail area. When a person enters the virtual guardrail area, the AI ​​vision device controls the robot to stop or reduce its speed, thereby preventing accidents and improving the safety of the guardrail-less robot system.

[0021] Other objects and advantages of the present invention will become apparent from the following description of the present invention with reference to the accompanying drawings, which will help to provide a comprehensive understanding of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A functional block diagram of a robot system according to an exemplary embodiment of the present invention is shown;

[0023] Figure 2A functional block diagram of an AI vision device according to an exemplary embodiment of the present invention is shown. DETAILED DESCRIPTION

[0024] The technical solution of the present invention will be further described in detail below through examples and in conjunction with the accompanying drawings. In the specification, the same or similar reference numerals indicate the same or similar components. The following description of the embodiments of the present invention with reference to the accompanying drawings is intended to explain the overall inventive concept of the present invention and should not be construed as limiting the present invention.

[0025] In addition, in the following detailed description, for ease of explanation, numerous specific details are set forth to provide a comprehensive understanding of the disclosed embodiments. However, it is apparent that one or more embodiments can be practiced without these specific details. In other cases, well-known structures and devices are shown in diagrammatic form to simplify the accompanying drawings.

[0026] According to an overall technical concept of the present invention, a robot system is provided. The robot system includes: a robot and an AI vision device. The system includes: an imaging module for capturing real-time video images of the robot's work site; a partitioning module for dividing the captured video images into a plurality of different areas; a recognition module for identifying whether a person has entered the plurality of different areas; and a control module for communicating with the robot and controlling the robot based on the recognition results of the recognition module. The plurality of different areas include a first virtual guardrail area surrounding the robot. When the recognition module recognizes that a person has entered the first virtual guardrail area, the control module sends a control instruction to the robot to stop working, so as to control the robot to stop working immediately.

[0027] Figure 1 A functional block diagram of a robot system according to an exemplary embodiment of the present invention is shown; Figure 2 A functional block diagram of an AI vision device according to an exemplary embodiment of the present invention is shown.

[0028] like Figure 1 and Figure 2As shown, in an exemplary embodiment of the present invention, a robot system is disclosed. The robot system includes: a robot 1 and an AI (Artificial Intelligence) vision device 3. The AI ​​vision device 3 includes: an imaging module 30, a partitioning module 31, a recognition module 32 and a control module 33. The imaging module 30 is used to capture video images of the robot's work site in real time. The partitioning module 31 is used to divide the captured video images into multiple different areas A1, A2, and A3. The recognition module 32 is used to identify whether a person has entered the multiple different areas A1, A2, and A3. The control module 33 communicates with the robot 1 and is used to control the robot 1 according to the recognition result of the recognition module 32.

[0029] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the recognition module 32 is an artificial intelligence vision system that has been trained with large-scale models and can effectively recognize human characteristics and behaviors.

[0030] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the aforementioned multiple different areas A1, A2, and A3 include a first virtual guardrail area A1 surrounding the robot 1. When the recognition module 32 detects that a person has entered the first virtual guardrail area A1, the control module 33 sends a stop operation control instruction to the robot 1, causing the robot 1 to immediately stop operating.

[0031] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the multiple different areas A1, A2, and A3 also include a second virtual guardrail area A2 surrounding the first virtual guardrail area A1. When the recognition module 32 detects that no one has entered the first virtual guardrail area A1 but that someone has entered the second virtual guardrail area A2, the control module 33 sends a deceleration control instruction to the robot 1, thereby controlling the robot 1 to reduce its operating speed.

[0032] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the multiple different areas A1, A2, and A3 also include a safety area A3 located outside the second virtual guardrail area A2. When the recognition module 32 detects that no one has entered the first and second virtual guardrail areas A1 and A2, but detects that someone has entered the safety area A3, the control module 33 sends a normal operation control instruction to the robot 1, allowing the robot 1 to operate normally.

[0033] like Figure 1 and Figure 2As shown, in the illustrated embodiment, the robot system further includes a production device 2, and the robot 1 is connected to the production device 2. The robot 1 is located in a first virtual guardrail area A1, and the production device 2 is located outside the first virtual guardrail area A1 but in a second virtual guardrail area A2.

[0034] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the robot 1 is a mobile robot 1 and is adapted to be connected to different production equipment 2, so that the robot 1 can be used in different production equipment 2. In the illustrated embodiment, since there are no fixed guardrails around the robot 1, the robot 1 can move freely between different production equipment 2 and can easily dock with different production equipment 2.

[0035] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the recognition module 32 can only recognize human features and cannot recognize features of objects other than the human body, so as to allow objects other than the human body to enter the first virtual guardrail area A1 and the second virtual guardrail area A2.

[0036] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the human body features include human head features, human body features, human hand features, and human foot features.

[0037] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, when any one of the head features, body features, hand features and foot features of a person is recognized in the first virtual guardrail area A1 or the second virtual guardrail area A2, the recognition result of the recognition module 32 is that someone has entered the first virtual guardrail area A1 or the second virtual guardrail area A2.

[0038] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, when none of the head features, body features, hand features, and foot features of a person are recognized in the first virtual guardrail area A1 or the second virtual guardrail area A2, the recognition result of the recognition module 32 is that no one has entered the first virtual guardrail area A1 or the second virtual guardrail area A2.

[0039] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the imaging module 30 includes a camera, the partitioning module 31, the recognition module 32 and the control module 33 are functional modules integrated into the hardware 300 of the camera, and the control module 33 is connected to the robot 1 via a signal line to communicate with the robot 1.

[0040] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, when the recognition module 32 detects a person entering the first virtual guardrail area A1, the control module 33 controls the robot 1's moving parts 10 to immediately stop moving. If the recognition module 32 detects no one entering the first virtual guardrail area A1 but detects a person entering the second virtual guardrail area A2, the control module 33 controls the robot 1's moving parts 10 to slow down. If the recognition module 32 detects no one entering either the first or second virtual guardrail areas A1 and A2, the robot 1's moving parts 10 remain unaffected and continue to move normally.

[0041] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, the moving part 10 of the robot 1 includes a manipulator.

[0042] like Figure 1 and Figure 2 As shown in the illustrated embodiment, the robot system includes multiple AI vision devices 3, each of which is positioned in a variety of locations. This improves the safety level of the robot system. If one vision device 3 fails, the other AI vision devices 3 can still provide safety protection.

[0043] like Figure 1 and Figure 2 As shown, in the embodiment shown in the figure, when the robot 1 receives a control instruction to stop working from any one of the multiple AI vision devices 3, the robot 1 immediately stops working. After the robot 1 stops working, the entire robot system needs to be manually restarted.

[0044] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, when the robot 1 does not receive a control command to stop operation but receives a control command to slow down operation from any of the multiple AI vision devices 3, the robot 1 immediately reduces its operating speed. After the robot 1 reduces its operating speed, if the person entering the second safety fence area A2 leaves, the robot 1 can automatically resume normal operation under the control of the AI ​​vision device 3.

[0045] like Figure 1 and Figure 2 As shown, in the illustrated embodiment, when the robot 1 receives a control instruction to stop working and a control instruction to slow down working at the same time, the robot 1 stops working immediately.

[0046] Those skilled in the art will understand that the embodiments described above are exemplary and can be improved by those skilled in the art. The structures described in various embodiments can be freely combined without causing any conflicts in structure or principle. These changes should fall within the scope of protection of the present invention.

[0047] Although the present invention has been described in conjunction with the accompanying drawings, the embodiments disclosed in the drawings are intended to exemplify the preferred embodiments of the present invention and should not be construed as limiting the present invention.

[0048] Although some embodiments of the general inventive concept have been shown and described, it will be appreciated by those skilled in the art that changes may be made to these embodiments without departing from the principles and spirit of the general inventive concept, the scope of which is defined in the claims and their equivalents.

[0049] It should be noted that the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. In addition, any element reference in the claims should not be construed as limiting the scope of the invention.

Claims

1. A robot system, characterized in that: include: Robot (1); and AI vision device (3), including: An imaging module (30) is used to capture real-time video images of the robot's work site; A partitioning module (31) is used to divide the captured video image into a plurality of different areas (A1, A2, A3); an identification module (32) for identifying whether a person enters the plurality of different areas (A1, A2, A3); and a control module (33) communicating with the robot (1) and configured to control the robot (1) according to the recognition result of the recognition module (32), The multiple different areas (A1, A2, A3) include a first virtual guardrail area (A1) surrounding the robot (1); when the recognition module (32) recognizes that a person has entered the first virtual guardrail area (A1), the control module (33) sends a control instruction to the robot (1) to stop working, so as to control the robot (1) to stop working immediately.

2. The robot system according to claim 1, wherein: The plurality of different areas (A1, A2, A3) further include a second virtual guardrail area (A2) surrounding the first virtual guardrail area (A1); When the recognition module (32) recognizes that no one has entered the first virtual guardrail area (A1) but recognizes that someone has entered the second virtual guardrail area (A2), the control module (33) sends a deceleration control instruction to the robot (1) to control the robot (1) to reduce the operating speed.

3. The robot system according to claim 2, wherein: The plurality of different areas (A1, A2, A3) further include a safety area (A3) located outside the second virtual guardrail area (A2); When the recognition module (32) recognizes that no one has entered the first and second virtual guardrail areas (A1, A2) but recognizes that someone has entered the safety area (A3), the control module (33) sends a normal operation control instruction to the robot (1) to allow the robot (1) to operate normally.

4. The robot system according to claim 2, wherein: Also includes: a production device (2), said robot (1) being connected to said production device (2), The robot (1) is located in the first virtual guardrail area (A1), and the production equipment (2) is located outside the first virtual guardrail area (A1) but in the second virtual guardrail area (A2).

5. The robot system according to claim 4, wherein: The robot (1) is a mobile robot (1) and is suitable for being connected to different production equipment (2), so that the robot (1) can be applied to different production equipment (2).

6. The robot system according to claim 2, wherein: The recognition module (32) can only recognize human features but cannot recognize features of objects other than the human body, so as to allow objects other than the human body to enter the first virtual guardrail area (A1) and the second virtual guardrail area (A2).

7. The robot system according to claim 6, wherein: The human body features include human head features, human body features, human hand features and human foot features.

8. The robot system according to claim 7, wherein: When any one of a person's head feature, a person's body feature, a person's hand feature, and a person's foot feature is recognized in the first virtual guardrail area (A1) or the second virtual guardrail area (A2), the recognition result of the recognition module (32) is that a person has entered the first virtual guardrail area (A1) or the second virtual guardrail area (A2).

9. The robot system according to claim 7, wherein: When any one of a person's head feature, a person's body feature, a person's hand feature, and a person's foot feature is not recognized in the first virtual guardrail area (A1) or the second virtual guardrail area (A2), the recognition result of the recognition module (32) is that no one has entered the first virtual guardrail area (A1) or the second virtual guardrail area (A2).

10. The robot system according to claim 1, wherein: The imaging module (30) includes a camera, the partition module (31), the recognition module (32) and the control module (33) are functional modules integrated into the hardware (300) of the camera, and the control module (33) is connected to the robot (1) through a signal line to communicate with the robot (1).

11. The robot system according to claim 2, wherein: When the recognition module (32) recognizes that a person has entered the first virtual guardrail area (A1), the control module (33) controls the moving part (10) of the robot (1) to stop moving immediately; When the recognition module (32) recognizes that no one has entered the first virtual guardrail area (A1) but recognizes that someone has entered the second virtual guardrail area (A2), the control module (33) controls the moving part (10) of the robot (1) to reduce the moving speed; When the recognition module (32) recognizes that no one has entered the first virtual guardrail area (A1) and the second virtual guardrail area (A2), the moving part (10) of the robot (1) is not affected and moves normally.

12. The robot system according to claim 11, wherein: The moving part (10) of the robot (1) includes a manipulator.

13. The robot system according to any one of claims 1 to 12, characterized in that: The robot system comprises a plurality of the AI ​​vision devices (3), and the plurality of AI vision devices (3) are respectively arranged at a plurality of different positions.

14. The robot system according to claim 13, wherein: When the robot (1) receives a control instruction to stop working from any one of the plurality of AI vision devices (3), the robot (1) immediately stops working.

15. The robot system according to claim 13, wherein: When the robot (1) does not receive a control instruction to stop working but receives a control instruction to slow down working from any one of the plurality of AI vision devices (3), the robot (1) immediately reduces the working speed.

16. The robot system according to claim 13, wherein: When the robot (1) receives a control instruction to stop working and a control instruction to slow down working at the same time, the robot (1) stops working immediately.

Images