A robust gripping method and gripping system for moving objects based on speed modulation
Through technical means such as global RGB-D vision sensors and ranging sensors, stable clamping of moving objects is achieved, solving the problems of poor clamping stability and insufficient applicability in the existing technology, and improving the clamping of moving objects by robots Result success rate and stability.
Patent Information
- Application Number
- CN202111339134.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-12
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2041-11-12
AI Technical Summary
The prior art has low clamping stability during clamping of moving objects, which can easily cause damage to the object, and clamping hands interfere with the movement path of the object, resulting in failure of clamping and poor applicability.
Using a speed modulation-based method, the clamping workpiece at the end of the robot is controlled to track moving objects through a global RGB-D vision sensor, local vision and ranging sensor, to determine the clamping position and speed modulation, and achieve stable clamping.
It improves clamping accuracy and success rate, has high clamping stability and lossless clamping ability, and is suitable for robust clamping of moving objects.
Smart Images

Figure CN114012706B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of robot end clamping tools, in particular to a robust clamping method for a moving object based on speed modulation, and a robust clamping system for a moving object based on speed modulation. Background Art
[0002] Automation equipment is a powerful tool for manufacturing powerhouses. It must move towards high speed and intelligence. However, it is extremely difficult to robustly grip some moving objects, or the motion path is disturbed during the gripping process. An important means to improve the stability of robot gripping is to detect the speed of the gripper approaching the object, and to achieve robust gripping of the moving object by modulating the speed of the two grippers separately. There are many methods for gripping objects at present, but for the gripping of moving objects, there are generally problems such as low gripping stability, easy damage to the object, and grippers interfering with the object's motion path, resulting in gripping failure. It is often not applicable in the face of gripping moving objects and has poor practicality. Summary of the invention
[0003] The purpose of the present invention is to provide a robust gripping method for moving objects based on speed modulation, so as to solve the problems that the prior art mentioned in the above background technology is not applicable and is only applicable to the gripping of objects with regular motion paths. To achieve the above purpose, the present invention provides the following technical solutions:
[0004] The first aspect of the present invention discloses a method for robustly gripping a moving object based on speed modulation, the method comprising the following steps:
[0005] S1, based on the global RGB-D vision sensor, the robot end is controlled to hold the workpiece and track the moving object;
[0006] S2, determine the position of the clamped workpiece at the end of the robot;
[0007] S3, turning on the distance sensor on the clamped workpiece to sense the imbalance of the clamping;
[0008] S4. Modulate the clamping speed of the clamped workpiece. When the clamped workpiece contacts the surface of the moving object, the clamping speed is modulated to 0 to achieve stable clamping.
[0009] Preferably, the step S1 specifically includes:
[0010] S11, the clamped workpiece at the end of the robot predicts the tracking path according to the motion trajectory of the moving object;
[0011] S12. The robot performs active movement and controls the clamped workpiece to approach the moving object at high speed.
[0012] Preferably, the step S2 specifically includes:
[0013] S21, when the clamped workpiece at the end of the robot successfully tracks the moving object, the local vision of the clamped workpiece is started;
[0014] S22, clamping the workpiece to collect an image of the moving object;
[0015] S23, calculating the geometric center of the moving object according to the collected image;
[0016] S24, determining the clamping position of the clamped workpiece, and fine-tuning the position of the clamped workpiece.
[0017] Preferably, the step S3 specifically includes:
[0018] S31, start the distance measuring sensor on the clamped workpiece at the end of the robot to measure the distance between the clamped workpiece and the moving object;
[0019] S32. Calculate the clamping imbalance and use it as the data basis for clamping speed modulation of the workpiece.
[0020] Preferably, the step S4 specifically includes:
[0021] S41, determining the speed change rate of the clamped workpiece in the process of contacting the moving object according to the clamping imbalance amount;
[0022] S42, determining the preload amount when the clamped workpiece contacts the moving object and the modulation stroke of the clamped workpiece according to the deformation of the moving object and the preset bearing force;
[0023] S43, by driving the clamping workpiece speed modulation device, the clamping speed of the clamped workpiece is modulated to perform stable clamping of the moving object.
[0024] The second aspect of the present invention discloses a robust gripping system for moving objects based on speed modulation, including a robot, wherein the robot is a mechanical arm structure, and a workpiece clamping device is provided at the end of the robot, and the workpiece clamping device includes a first movable gripper and a second movable gripper, and the first movable gripper and the second movable gripper are respectively provided with ranging sensors, the workpiece clamping device is also provided with local vision, and the robot is also provided with a global RGB-D vision sensor.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] The method for robust gripping of moving objects based on speed modulation of the present invention can be installed in the corresponding gripping system. The gripping accuracy is improved in many aspects through strategies such as global RGB-D vision sensors, local vision and ranging sensors. The method for speed modulation and the driving mode of closed-loop drive are adopted. It has the characteristics of high gripping success rate, visual feedback function and speed modulation function, and is very suitable for the robust gripping of moving objects by robots. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a schematic flow chart of a method for robustly gripping a moving object based on speed modulation according to the present invention;
[0028] Figure 2 It is an overall schematic diagram of the robust gripping system for moving objects based on speed modulation of the present invention;
[0029] Figure 3 A schematic diagram of a moving object tracking process based on object motion path prediction according to the present invention;
[0030] Figure 4 It is a flow chart of the method for determining the clamping position based on local vision of the present invention;
[0031] Figure 5 It is a schematic diagram of the flow of clamping imbalance measurement based on distance perception of the present invention;
[0032] Figure 6 It is a schematic diagram of the clamping speed adjustment process based on the linear speed regulation model of the present invention;
[0033] Figure numerals: 1. robot; 2. clamping workpiece; 3. local vision; 4. first movable gripper; 5. second movable gripper; 6. distance sensor; 7. moving object; 8. motion trajectory; 9. global RGB-D vision sensor. DETAILED DESCRIPTION
[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0035] See also Figure 1 The present invention provides a technical solution: a robust gripping method for a moving object 7 based on speed modulation, the method comprising the following steps:
[0036] S1, based on the global RGB-D vision sensor 9, the gripping workpiece 2 at the end of the robot 1 tracks the moving object 7;
[0037] S2, determining the position of the clamped workpiece 2 at the end of the robot 1;
[0038] S3, turning on the distance sensor 6 on the clamped workpiece 2 to sense the imbalance of the clamping;
[0039] S4. Modulate the clamping speed of the clamped workpiece 2. When the clamped workpiece 2 contacts the surface of the moving object 7, the clamping speed is modulated to 0 to achieve stable clamping.
[0040] Specifically, see Figure 2 The present invention corresponds to the gripping method and discloses a robust gripping system for a moving object 7 based on speed modulation, including a robot 1, wherein the robot 1 is a mechanical arm structure, and a workpiece gripping 2 is arranged at the end of the robot 1, wherein the workpiece gripping 2 includes a first movable gripper 4 and a second movable gripper 5, wherein the first movable gripper 4 and the second movable gripper 5 are respectively provided with ranging sensors, and the workpiece gripping 2 is also provided with a local vision 3, and the robot 1 is also provided with a global RGB-D vision sensor 9.
[0041] More specifically, in order to improve the grasping accuracy, the present invention proposes a strategy of first locking and tracking the moving object 7 based on the global RGB-D vision sensor 9, and at the same time using the speed modulation method to adjust the distance between the two clamped workpieces 2 and the object. In the middle position of the two gripper halves, a local vision 3 is provided for fine-tuning the position of the clamping tool relative to the workpiece. Distance measuring sensors are respectively arranged on the two grippers to measure the distance from the gripper half to the object, thereby realizing speed modulation of the gripper approaching the object, and the two halves of the gripper can be driven in a closed loop separately to realize accurate speed modulation, and finally the present invention can realize stable and lossless robust clamping of the moving object 7.
[0042] Reference Figures 2 to 3 As a preferred embodiment of the present invention, step S1 specifically comprises:
[0043] S11, the clamped workpiece 2 at the end of the robot 1 predicts the tracking path according to the motion trajectory 8 of the moving object 7;
[0044] S12 , the robot 1 performs active movement and controls the clamped workpiece 2 to approach the moving object 7 at high speed.
[0045] Reference Figure 2 and Figure 4 As a preferred embodiment of the present invention, step S2 specifically includes:
[0046] S21, when the clamped workpiece 2 at the end of the robot 1 successfully tracks the moving object 7, the local vision 3 of the clamped workpiece 2 is started;
[0047] S22, clamping the workpiece 2 to collect an image of the moving object 7;
[0048] S23, calculating the geometric center of the moving object 7 according to the collected image;
[0049] S24, determining the clamping position of the workpiece 2, and fine-tuning the position of the workpiece 2.
[0050] Reference Figure 2 and Figure 5 As a preferred embodiment of the present invention, step S3 specifically includes:
[0051] S31, start the distance measuring sensor on the clamped workpiece 2 at the end of the robot 1 to measure the distance between the clamped workpiece 2 and the moving object 7;
[0052] S32, calculating the clamping imbalance amount and using it as the data basis for clamping speed modulation of the workpiece 2.
[0053] Reference Figure 2 and Figure 6 As a preferred embodiment of the present invention, step S4 specifically includes:
[0054] S41, determining the speed change rate of the clamped workpiece 2 in the process of contacting the moving object 7 according to the clamping imbalance amount;
[0055] S42, determining the preload amount when the clamped workpiece 2 contacts the moving object 7 and the modulation stroke of the clamped workpiece 2 according to the deformation of the moving object 7 and the preset bearing force;
[0056] S43 , by driving the speed modulation device for clamping the workpiece 2 , modulation of the clamping speed of the workpiece 2 is displayed, and stable clamping of the moving object 7 is performed.
[0057] Compared with the prior art, the present invention has the following beneficial effects:
[0058] The robust gripping method for a moving object 7 based on speed modulation of the present invention can be installed in a corresponding gripping system, and the gripping accuracy is improved in many aspects through strategies such as a global RGB-D vision sensor 9, a local vision 3, and a ranging sensor. It adopts a speed modulation method and a closed-loop drive mode, and has the characteristics of a high gripping success rate, a visual feedback function, and a speed modulation function. It is very suitable for the robust gripping of a moving object 7 by a robot 1.
Claims
1. A robust gripping method for moving objects based on velocity modulation, It is characterized in that The method comprises the following steps: S1, controlling the gripping workpiece (2) at the end of the robot (1) to track the moving object (7) based on the global RGB-D vision sensor (9); The step S1 specifically includes: S11, the gripping workpiece (2) at the end of the robot (1) predicts a tracking path according to the motion trajectory (8) of the moving object (7); S12, the robot (1) performs active movement and controls the clamped workpiece (2) to approach the moving object (7) at high speed; S2, determining the position of the clamped workpiece (2) at the end of the robot (1); The step S2 specifically includes: S21, when the clamped workpiece (2) at the end of the robot (1) successfully tracks the moving object (7), starting the local vision (3) of the clamped workpiece (2); S22, clamping the workpiece (2) to collect an image of the moving object (7); S23, calculating the geometric center of the moving object (7) according to the collected image; S24, determining a clamping position of the clamped workpiece (2), and fine-adjusting the position of the clamped workpiece (2); S3, turning on the distance sensor (6) on the clamped workpiece (2) to sense the imbalance of the clamping; S4, modulating the clamping speed of the clamped workpiece (2), and when the clamped workpiece (2) is in contact with the surface of the moving object (7), the clamping speed is modulated to 0, thereby achieving stable clamping; The robot (1) is a mechanical arm structure, and a workpiece clamping device (2) is provided at the end of the robot (1), and the workpiece clamping device (2) comprises a first movable clamping hand (4) and a second movable clamping hand (5), and the first movable clamping hand (4) and the second movable clamping hand (5) are respectively provided with distance measuring sensors; The step S3 specifically includes: S31, starting the distance measuring sensor on the clamped workpiece (2) at the end of the robot (1) to measure the distance between the clamped workpiece (2) and the moving object (7); S32, calculating the clamping unbalance amount and using it as a data basis for clamping speed modulation of the workpiece (2); The step S4 specifically includes: S41, determining the speed change rate of the clamped workpiece (2) in the process of contacting the moving object (7) according to the clamping imbalance amount; S42, determining the preload amount when the clamped workpiece (2) contacts the moving object (7) and the modulation stroke of the clamped workpiece (2) according to the deformation of the moving object (7) and the preset bearing force; S43, by driving the speed modulation device for clamping the workpiece (2), the clamping speed of the clamping workpiece (2) is modulated, and stable clamping of the moving object (7) is performed.
