In-Hand Cube Reconfiguration: Simplified

We present a simple approach to in-hand cube reconfiguration. By simplifying planning, control, and perception as much as possible, while maintaining robust and general performance, we gain insights into the inherent complexity of in-hand cube reconfiguration. We also demonstrate the effectiveness of combining GOFAI-based planning with the exploitation of environmental constraints and inherently compliant end-effectors in the context of dexterous manipulation. The proposed system outperforms a substantially more complex system for cube reconfiguration based on deep learning and accurate physical simulation, contributing arguments to the discussion about what the most promising approach to general manipulation might be. Project website: https://rbo.gitlab-pages.tu-berlin.de/robotics/simpleIHM/

I. Introduction

In-hand cube reconfiguration has recently become a benchmark problem for robot manipulation [1]–[3] and in particular for the application of deep learning to robot manipulation [4]–[8]. The objective is to reorient a cube within a robot hand to any of its 24 axis-aligned configurations (see Fig. 1 for an example).