Continuum robot gripper adapts shape and fit for reliable grasping
A Support-Enhanced Granular-Jamming Gripper for RL-based Grasping with Continuum Manipulators
Robotics
Summary
Robotic arms that bend like tentacles can be great at moving in tight spots, but they sometimes miss their target because they're too soft and wobbly. To fix this, the authors created a special soft robotic hand that can change from flexible to firm, gripping objects better. They carefully chose the materials and design so this hand works well with the bending arm. Then they used a kind of learning software to help the robot know how to reach and grab things well. Their work shows how combining smart design and machine learning can make robots better at grabbing stuff without needing perfect models or control.
What this means in practice
- •For robotic automation engineers: Build continuum robot arms with adaptive grippers that adjust grip firmness to handle objects reliably despite positioning errors.
- •For medical device developers: Create robotic tools that navigate confined spaces and grasp tissues gently yet securely during minimally invasive surgeries.
Authors
Danyu Liu, Tianlin Zhang, Wei Chen, Wei Tang, Kecheng Qin, Zhongyu Li
Abstract
Continuum manipulators provide dexterous motion in confined spaces, but structural compliance, hysteresis, and load-dependent deformation leave residual position and orientation errors that can undermine reliable contact with rigid grippers. To address this limitation, this paper presents a lightweight support-enhanced granular-jamming gripper tailored to a continuum manipulator. The gripper maintains compliance before jamming while establishing a direct load path to the continuum manipulator tip after jamming. To improve its grasping performance, we systematically designed membrane materials, particles, filling ratios, and the internal support structure, and further identify geometry-dependent grasp boundaries with respect to contact offset and object shape. Building on these results, we construct a physical manipulation system integrating the continuum manipulator, granular-jamming gripper, visual feedback, tendon actuation, and pneumatic control. We then train a reinforcement-learning-based reaching controller in a randomized simulation and deploy it on the physical system, demonstrating how positioning control and contact level mechanical adaptation can complement each other in a modular grasp-and-release task. By introducing an adaptive structure that relaxes the need for highly accurate modeling and positioning control, this work explores a design paradigm that integrates physical and embodied intelligence.