CN-122008206-A - Robot jaw control method and related system, storage medium and program product

CN122008206ACN 122008206 ACN122008206 ACN 122008206ACN-122008206-A

Abstract

The application relates to the technical field of robots, in particular to a robot clamping jaw control method, a related system, a storage medium and a program product. The method comprises the steps of obtaining image information of a target object through an image acquisition unit arranged on a clamping jaw body, obtaining motor current information of each of the at least two motor drivers through the at least two motor drivers, calculating a first contact force value based on visual deformation information of the target object through a digital processing unit, calculating a second contact force value based on the motor current information, and then fusing the first contact force value and the second contact force value based on a preset fusion algorithm, so that a final estimated contact force value is obtained, wherein the final estimated contact force value is used for clamping force control of the target object. The multi-source and multi-mode sensing information is effectively fused to obtain more accurate and reliable contact force estimation.

Inventors

CHEN SIWEI
HU LIXIANG
ZHANG FAN

Assignees

深圳市智动未来科技有限公司
广东智动未来科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251031

Claims (10)

1. A control method for a robotic gripper, the control method comprising: Acquiring image information of a target object, wherein a clamping jaw body comprises at least two clamping pieces and at least two motor drivers which are in one-to-one correspondence with the at least two clamping pieces, the at least two motor drivers are respectively used for driving the at least two clamping pieces to move relatively so as to clamp the target object, and the image information of the target object at least comprises visual deformation information of the target object when the target object is clamped by the at least two clamping pieces; acquiring respective motor current information of the at least two motor drivers through the at least two motor drivers; Calculating a first contact force value based on visual deformation information of the target object, calculating a second contact force value based on the motor current information, and then fusing the first contact force value and the second contact force value based on a preset fusion algorithm, so as to obtain a final estimated contact force value, wherein the final estimated contact force value is used for clamping force control related to the target object.
2. The control method according to claim 1, wherein elastic members are respectively disposed on one or more of the at least two holding members, and when the target object is held by the at least two holding members, the elastic members of the one or more holding members each deform due to contact with the target object, the control method further comprising acquiring deformation amounts of the elastic members of the one or more holding members each, thereby acquiring elastic member deformation information associated with the target object, the elastic member deformation information associated with the target object being used for calibrating the calculation of the first contact force value.
3. The control method according to claim 2, wherein the digital processing unit calculates the first contact force value by an artificial intelligence model, learning and optimization of which is based on visual deformation information of the clamped object and elastic member deformation information associated with the clamped object acquired by the image acquisition unit.
4. The control method according to claim 1, characterized in that the image information of the target object further includes overall image data of the target object, the control method further comprising: determining an object category of the target object and a position and a posture of the target object by using an object recognition algorithm based on the overall image data of the target object; Determining a force control parameter of the target object for clamping force control related to the target object by accessing a material property database based on the object class of the target object, wherein the material property database comprises load characteristics and force control parameters respectively corresponding to different object classes based on priori knowledge; Based on the object class of the target object and the position and posture of the target object, determining initial gripping parameters of the target object by accessing the texture attribute database, wherein the initial gripping parameters of the target object comprise initial contact force and a safety force threshold.
5. The control method according to claim 4, characterized in that the control method further comprises: searching the object type, the position and the gesture of the object clamped by the robot clamping jaw, which are recorded in the history data, and when the object type of the clamped object in the history data is detected to be the same as the object type of the target object and the initial grabbing parameter of the clamped object is similar to the initial grabbing parameter of the target object, using the force control parameter of the clamped object as the force control parameter of the target object.
6. The control method according to any one of claims 1 to 5, characterized in that the jaw body includes a force control actuator to which the at least two motor drivers belong, the force control actuator includes a transmission mechanism constituted by a plurality of links, one or more of the plurality of links are internally embedded with a slip detection unit for detecting a contact surface dither due to a minute slip of the clamped object to determine whether or not slip has occurred, and when the slip detection unit detects the slip has occurred, the digital processing unit executes a gradient force compensation algorithm to suppress the slip.
7. The control method according to any one of claims 1 to 5, wherein the preset fusion algorithm comprises a dynamic weighted average between the first contact force value and the second contact force value, wherein the weighted parameter of the first contact force value has a higher confidence when the visual condition is good and the weighted parameter of the second contact force value has a higher confidence when the motor is running steady.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of claims 1 to 7 when executing the computer program.
9. A computer readable storage medium or computer program product, characterized in that the computer readable storage medium stores computer instructions, which when run on a computer device, cause the computer device to perform the method according to any of claims 1 to 7; Or alternatively Computer instructions contained in the computer program product when run on a computer device cause the computer device to perform the method according to any one of claims 1 to 7.
10. A control system for a robotic jaw, the control system comprising: The image acquisition unit is arranged on the clamping jaw body and is used for acquiring image information of a target object, wherein the clamping jaw body comprises at least two clamping pieces and at least two motor drivers which are in one-to-one correspondence with the at least two clamping pieces, the at least two motor drivers are respectively used for driving the at least two clamping pieces to move relatively so as to clamp the target object, and the image information of the target object at least comprises visual deformation information of the target object when the target object is clamped by the at least two clamping pieces; The at least two motor drivers are used for acquiring respective motor current information of the at least two motor drivers; And the digital processing unit is used for calculating a first contact force value based on the visual deformation information of the target object, calculating a second contact force value based on the motor current information, and then fusing the first contact force value and the second contact force value based on a preset fusion algorithm so as to obtain a final estimated contact force value, wherein the final estimated contact force value is used for controlling the clamping force of the target object.

Description

Robot jaw control method and related system, storage medium and program product Technical Field The application relates to the technical field of robots, in particular to the technical field of end effectors of robots, and particularly relates to a robot clamping jaw control method, a related system, a storage medium and a program product. Background The robot clamping jaw is used as a key component for the robot to execute complex operation tasks, and the intelligent level of the robot clamping jaw directly influences the overall performance of the robot. The control schemes of the robotic jaws of the prior art still have many problems in terms of visual perception, force control, adaptive gripping, and the intuitive and force-perceived accuracy of remote operation. For example, the scheme with separate vision and force control has low integration level, so that the system response delay is large, and the requirements of high-speed and high-precision operation are difficult to meet. For another example, the scheme of adopting static force control has defects in self-adaptability, relies on a preset fixed force threshold value for control, lacks the capability of dynamically adjusting a grabbing strategy according to characteristics of object types, materials, shapes and the like, is difficult to adapt to diversified workpieces and complex working environments, and often needs manual intervention when facing unknown or vulnerable objects. As another example, the approach of using direct force sensors has limitations, but high precision multidimensional force sensors can provide accurate force feedback, but are often costly, structurally fragile, bulky, and may have reduced reliability in certain extreme environments (e.g., strong electromagnetic interference, high temperature). For another example, the scheme of indirect force estimation has defects in precision and robustness, and the contact force is estimated indirectly through motor current, encoder data or visual information, etc., but the single-mode indirect force estimation method is often limited in precision, for example, estimation based on motor current is easily interfered by friction, inertia and motor nonlinear characteristics, and estimation based on vision (such as object deformation analysis) is possibly influenced by illumination change, shielding and optical characteristics of an object, and the robustness is poor under complex dynamic working conditions. For another example, the scheme of adopting remote operation force is perceived to be absent or not intuitive, in a scene (such as dangerous environment operation and telemedicine) where the robot clamping jaw is required to be remotely operated, an operator often has difficulty in accurately perceiving interaction force between the clamping jaw and the environment, and a remote operation system may lack fine force feedback, or the force feedback is not timely and intuitive, so that the operator easily misjudges, and the operated object or the clamping jaw is damaged. As another example, schemes employing virtual reality interactions have been inadequate in terms of precision force adjustment, focusing on position control or simple on-off operation, and lack an effective mechanism for fine, intuitive setting and adjustment of the jaw target clamping force. Disclosure of Invention Therefore, the application provides a robot clamping jaw control method, a related system, a storage medium and a program product, which have accurate contact force estimation capability based on multi-mode information through deep integrated visual perception and dynamic force control, and have rich expansion capability, for example, visual and accurate remote force control operation is realized by combining a virtual reality technology, so as to meet the requirements of increasingly complex industrial and service scenes. In a first aspect, the present application provides a control method for a robotic gripper. The control method comprises the steps of obtaining image information of a target object through an image acquisition unit arranged on a clamping jaw body, calculating a first contact force value based on the visual deformation information of the target object through a digital processing unit, calculating a second contact force value based on the motor current information, and then fusing the first contact force value and the second contact force value based on a preset fusion algorithm so as to obtain a final estimated contact force value, wherein the image information of the target object at least comprises visual deformation information of the target object when the target object is clamped by the at least two clamping pieces, obtaining motor current information of each of the at least two motor drivers through the at least two motor drivers, and calculating a first contact force value based on the visual deformation information of the target object through the digital processing unit. According to