A Novel Approach to Grasping Control of Soft Robotic Grippers based on Digital Twin

TL;DR

Results show that the DT-based approach can achieve satisfactory performance in real-time control of soft gripper manipulation, which can satisfy a wide range of industrial applications.

Abstract

This paper has proposed a Digital Twin (DT) framework for real-time motion and pose control of soft robotic grippers. The developed DT is based on an industrial robot workstation, integrated with our newly proposed approach for soft gripper control, primarily based on computer vision, for setting the driving pressure for desired gripper status in real-time. Knowing the gripper motion, the gripper parameters (e.g. curvatures and bending angles, etc.) are simulated by kinematics modelling in Unity 3D, which is based on four-piecewise constant curvature kinematics. The mapping in between the driving pressure and gripper parameters is achieved by implementing OpenCV based image processing algorithms and data fitting. Results show that our DT-based approach can achieve satisfactory performance in real-time control of soft gripper manipulation, which can satisfy a wide range of industrial applications.

Figures (5)

• Figure 1: The Framework of the Digital Twin System for the Pneumatic Soft Solution Robot Workstation. RWS means the Robot Web Service, with its detail presented in robot.
• Figure 2: The triple spaces mapping among Pneumatic Actuator Controller, Arc Parameters (Configuration Space), and Position orientation (Task Space). Robot Specific Mapping: Transform pressure $P$ to configuration space variables $\mathrm{k}_{4.1}, \emptyset_{4 \ldots 1}, l_{4..1}$. Next, robot-independent mapping - Configuration Space to Task Space by kinematics
• Figure 3: The 3D Vision Calibration Method to derive Specific Mapping for continuum flexible actuator: (a): The Physical Layout of Soft gripper, 3D depth Camera, and Laptop; (b) The calculated Arc Parameters $theta_{4..1}$ in calibrated world coordinates when Pressure $P = 100 Kpa$; (c) The triple polynomial fitting of Arc Parameters $theta_{4..1}$ versus Pressure $P$.
• Figure 4: Four Piecewise Robot Independant Mapping Soft Gripper: (a): Flexible gripper with robot working screenshot (b): Assembled Together Four-piece Soft gripper constant curvature model with four homogeneous transformation matrix $T$ in Unity 3D; (b): Arc Configuration Space for only One piece soft gripper when angle $\phi$ rotates the arc to new x' axis.
• Figure 5: Bending performance mapping between reality and DT performance about curvatures $\kappa_{4..1}$ versus varying pressure; The fourth picture is human-forced simulation with $\phi = [12,8.8,6,3.3]$ that do not actually exist in real production