Research on intelligent grasping strategy of pneumatic flexible gripper based on adaptive iterative learning strategy

Purpose For flexible grippers, people always hope that they can grasp objects accurately, stably and compliantly. This study aims to focus on robotic arm and flexible gripper, considers both position and grip control, while improving the compliantly of movements, which is a challenging task. Design/methodology/approach This study constructs the mathematical model of collaborative robotic arm and flexible gripper, designs an intelligent iterative learning control strategy with modular convolutional neural network and demonstrates the superiority of the proposed method over existing control methods through experiment. Findings The results show that compared to the existing methods, the proposed method can improve position accuracy while reducing chattering and improving initial transient impact force, thereby improving the operational compliantly and stability of the robotic arm and flexible gripper. And the control strategy proposed in this study is applied to grasp some typical flexible and brittle objects, which can effectively handle the flexible and brittle objects. Using the method proposed in this study, the robot’s end position error in the XYZ-direction is controlled within ±0.5 mm, and the Jerk in the XYZ-direction is within ±70mm/s³. Initially, when external interference is applied, the grasping force of the four fingers varies between 0.135 and 0.185 N. During the stable phase of external interference, the grasping force ranges from 0.140 to 0.160 N. Originality/value This study proposes an intelligent iterative learning control method with modular convolutional neural network for the combination of a collaborative robotic arm and a flexible gripper. While simplifying the control structure, it achieves dexterous and compliance grasping for the flexible, brittle and irregularly shaped objects. This study conducts physical experiments, thereby laying the foundation for the research of the dexterous and compliance grasping requirements for the flexible, brittle objects with different shapes.