Computational design of passive grippers

Abstract

This work proposes a novel generative design tool for passive grippers---robot end effectors that have no additional actuation and instead leverage the existing degrees of freedom in a robotic arm to perform grasping tasks. Passive grippers are used because they offer interesting trade-offs between cost and capabilities. However, existing designs are limited in the types of shapes that can be grasped. This work proposes to use rapid-manufacturing and design optimization to expand the space of shapes that can be passively grasped. Our novel generative design algorithm takes in an object and its positioning with respect to a robotic arm and generates a 3D printable passive gripper that can stably pick the object up. To achieve this, we address the key challenge of jointly optimizing the shape and the insert trajectory to ensure a passively stable grasp. We evaluate our method on a testing suite of 22 objects (23 experiments), all of which were evaluated with physical experiments to bridge the virtual-to-real gap. Code and data are at https://homes.cs.washington.edu/~milink/passive-gripper/

Diversity‐Based Topology Optimization of Soft Robotic Grippers

“…In the domain of rigid grasping, computational tools have been developed to optimize active and passive grippers for specific objects. Under the assumption that both the object and gripper are known rigid bodies, these find a geometry [26] or combination of geometry and path, [27,28] which allows a printed end-effector to perform grasping operations. This critical assumption is obviously not valid in soft robotics, where deformability is a key design feature.…”

Learn to Grasp Via Intention Discovery and Its Application to Challenging Clutter

“…Other works focus on designing end-effectors to grasp challenging objects instead of focusing on the grasping policy. The end effector can be designed by humans or discovered through learning algorithms [24]. However, end effectors with complicated designs often only apply to specific object types, reducing the robot's versatility and increasing the system's complexity.…”

Shape and Motion Optimization of Rigid Planar Effectors for Contact Trajectory Satisfaction

“…However, they fix object orientation within the jaws, omitting an important freedom that we include. Finally, Kodnongbua et al [8] design passive grippers. They first rank sets of contact locations, then use topology optimization to design a collisionfree gripper geometry and approach path.…”

“…While the former alone determines grasp quality, both determine geometric compatibility with the target objects. For example, Kodnongbua et al [8] first select contact points for passive grippers, and subsequently find collisionfree grippers to meet those contacts. In our previous work [9], we co-optimize shape and motion of rigid effectors to contact moving objects, constraining all points on the contact 1 Rebecca H. Jiang is with the Department of Aeronautics and Astronautics, Massachusetts Institute of Technology and is a Draper Scholar at The Charles Stark Draper Laboratory, Inc. rhjiang@mit.edu 2 Neel Doshi is with Amazon Robotics R&D. This research was conducted prior to Neel joining Amazon ndd@amazon.com 3 Ravi Gondhalekar is with The Charles Stark Draper Laboratory, Inc. rgondhalekar@draper.com 4 Alberto Rodriguez is with the Department of Mechanical Engineering, Massachusetts Institute of Technology albertor@mit.edu surface to be collision-free at all times.…”