Dexterous Soft Hands Linearize Feedback-Control for In-Hand Manipulation

TL;DR

This paper introduces a feedback-control framework for dexterous soft hands that enables rapid learning of in-hand manipulation skills using linear feedback control based on deformation states, adaptable to object and hand variations.

Contribution

The paper proposes a novel linear feedback control method for soft hands using deformation states and explorative Jacobian estimation, enabling quick skill acquisition in real-world scenarios.

Findings

Generalizes manipulation skills to object size variations of 100%

Handles 360-degree palm inclination changes

Maintains performance with up to 50% actuator disabling

Abstract

This paper presents a feedback-control framework for in-hand manipulation (IHM) with dexterous soft hands that enables the acquisition of manipulation skills in the real-world within minutes. We choose the deformation state of the soft hand as the control variable. To control for a desired deformation state, we use coarsely approximated Jacobians of the actuation-deformation dynamics. These Jacobian are obtained via explorative actions. This is enabled by the self-stabilizing properties of compliant hands, which allow us to use linear feedback control in the presence of complex contact dynamics. To evaluate the effectiveness of our approach, we show the generalization capabilities for a learned manipulation skill to variations in object size by 100 %, 360 degree changes in palm inclination and to disabling up to 50 % of the involved actuators. In addition, complex manipulations can be obtained by sequencing such feedback-skills.