Enhancing Dexterity in Robotic Manipulation via Hierarchical Contact Exploration

TL;DR

This paper introduces HiDex, a hierarchical planning framework that enhances robotic dexterity by efficiently exploring contact sequences and motions, enabling complex manipulation tasks to be solved quickly and flexibly.

Contribution

The paper presents a novel hierarchical Monte-Carlo Tree Search framework for dexterous manipulation that integrates contact planning, object motion, and control optimization in a unified approach.

Findings

Solves diverse manipulation tasks in seconds

Handles high-dimensional contact spaces effectively

Flexible framework adaptable to different robots and scenarios

Abstract

Planning robot dexterity is challenging due to the non-smoothness introduced by contacts, intricate fine motions, and ever-changing scenarios. We present a hierarchical planning framework for dexterous robotic manipulation (HiDex). This framework explores in-hand and extrinsic dexterity by leveraging contacts. It generates rigid-body motions and complex contact sequences. Our framework is based on Monte-Carlo Tree Search and has three levels: 1) planning object motions and environment contact modes; 2) planning robot contacts; 3) path evaluation and control optimization. This framework offers two main advantages. First, it allows efficient global reasoning over high-dimensional complex space created by contacts. It solves a diverse set of manipulation tasks that require dexterity, both intrinsic (using the fingers) and extrinsic (also using the environment), mostly in seconds. Second, our framework allows the incorporation of expert knowledge and customizable setups in task mechanics and models. It requires minor modifications to accommodate different scenarios and robots. Hence, it provides a flexible and generalizable solution for various manipulation tasks. As examples, we analyze the results on 7 hand configurations and 15 scenarios. We demonstrate 8 tasks on two robot platforms.