Soft Robotic Dynamic In-Hand Pen Spinning

TL;DR

This paper introduces SWIFT, a real-world learning system for soft robotic hands to perform dynamic in-hand pen spinning without prior object models, achieving high success rates and demonstrating generalization to different objects.

Contribution

The work presents a novel real-world trial-and-error learning approach for soft robotic in-hand manipulation, eliminating the need for simulation or explicit object models.

Findings

SWIFT achieves 100% success rate on three different pens.

The system generalizes to spinning objects like a brush and screwdriver.

It learns robust in-hand spinning with minimal prior knowledge.

Abstract

Dynamic in-hand manipulation remains a challenging task for soft robotic systems that have demonstrated advantages in safe compliant interactions but struggle with high-speed dynamic tasks. In this work, we present SWIFT, a system for learning dynamic tasks using a soft and compliant robotic hand. Unlike previous works that rely on simulation, quasi-static actions and precise object models, the proposed system learns to spin a pen through trial-and-error using only real-world data without requiring explicit prior knowledge of the pen's physical attributes. With self-labeled trials sampled from the real world, the system discovers the set of pen grasping and spinning primitive parameters that enables a soft hand to spin a pen robustly and reliably. After 130 sampled actions per object, SWIFT achieves 100% success rate across three pens with different weights and weight distributions, demonstrating the system's generalizability and robustness to changes in object properties. The results highlight the potential for soft robotic end-effectors to perform dynamic tasks including rapid in-hand manipulation. We also demonstrate that SWIFT generalizes to spinning items with different shapes and weights such as a brush and a screwdriver which we spin with 10/10 and 5/10 success rates respectively. Videos, data, and code are available at https://soft-spin.github.io.