A Variable Stiffness Soft Gripper Based on Rotational Layer Jamming.

This article presents the design and fabrication of a variable stiffness soft gripper based on layer jamming. Traditional layer jamming units have some limitations, such as complicated multistep fabrication, difficulties in system integration, and diminishing in stiffen effect. In this article, a variable stiffness soft gripper is proposed based on the rotational jamming layers to reduce the slippery phenomenon between layers. To fabricate the proposed complex design, a two-step fabrication method is presented. First, multimaterial 3D printing is applied to directly print out the soft finger body with jamming layers. Second, mold casting is used to fabricate the outer vacuum chamber. The proposed gripper contains a main framework and three identical variable stiffness soft fingers. To demonstrate the effectiveness of the design, the soft gripper is mounted on a robotic arm to test its ability of grasping heavy objects while following complex grasping trajectory. The gripper can successfully grasp an object up to 360 g. Grasping robustness of the proposed gripper can be guaranteed when the robotic arm is moving at acceleration up to 7 m/s2. The results prove that the proposed design of the soft gripper can improve the grippers grasping robustness during high-speed movement.

Robust Grasping of a Variable Stiffness Soft Gripper in High-Speed Motion Based on Reinforcement Learning.

Industrial robots are widely deployed to perform pick-and-place tasks at high speeds to minimize manufacturing time and boost productivity. When dealing with delicate or fragile goods, soft robotic grippers are better end effectors than rigid grippers due to their softness and safe interaction. However, high-speed motion causes the soft robotic gripper to vibrate, leading to damage of the objects or failed grasping. Soft grippers with variable stiffness are considered to be effective in suppressing vibrations by adding damping devices, but it is quite challenging to compromise between stiffness and compliance. In this article, a controller based on deep reinforcement learning is proposed to control the stiffness of the soft robotic gripper, which can accurately suppress the vibration with only a minor influence on its compliance and softness. The proposed controller is a real-time vibration control strategy, which estimates the output of the controller based on the current operating environment. To demonstrate the effectiveness of the proposed controller, experiments were done with a UR5 robotic arm. For different situations, experimental results show that the proposed controller responds quickly and reduces the amplitude of the oscillation substantially.