Surprisingly Robust In-Hand Manipulation: An Empirical Study

TL;DR

This paper demonstrates that simple in-hand manipulation skills on a dexterous robot hand are surprisingly robust to various object and execution variations, supported by an empirical analysis revealing key design principles.

Contribution

It introduces a set of robust in-hand manipulation skills and identifies fundamental principles for designing such skills based on empirical analysis.

Findings

Skills are robust to shape, size, weight, and placement variations.

Skills are insensitive to different execution speeds.

Three principles for skill design are identified.

Abstract

We present in-hand manipulation skills on a dexterous, compliant, anthropomorphic hand. Even though these skills were derived in a simplistic manner, they exhibit surprising robustness to variations in shape, size, weight, and placement of the manipulated object. They are also very insensitive to variation of execution speeds, ranging from highly dynamic to quasi-static. The robustness of the skills leads to compositional properties that enable extended and robust manipulation programs. To explain the surprising robustness of the in-hand manipulation skills, we performed a detailed, empirical analysis of the skills' performance. From this analysis, we identify three principles for skill design: 1) Exploiting the hardware's innate ability to drive hard-to-model contact dynamics. 2) Taking actions to constrain these interactions, funneling the system into a narrow set of possibilities. 3) Composing such action sequences into complex manipulation programs. We believe that these principles constitute an important foundation for robust robotic in-hand manipulation, and possibly for manipulation in general.