Task-Driven Hybrid Model Reduction for Dexterous Manipulation

TL;DR

This paper introduces a reduced-order hybrid model for dexterous manipulation tasks that simplifies complex contact interactions, enabling real-time control with minimal performance loss and efficient online learning.

Contribution

The authors develop a method to learn simplified hybrid models with fewer modes, improving control efficiency and enabling rapid online adaptation in dexterous manipulation.

Findings

Reduced mode count by orders of magnitude with minimal performance loss

Achieved state-of-the-art manipulation performance with minimal online learning

Demonstrated real-time control in complex contact-rich tasks

Abstract

In contact-rich tasks, like dexterous manipulation, the hybrid nature of making and breaking contact creates challenges for model representation and control. For example, choosing and sequencing contact locations for in-hand manipulation, where there are thousands of potential hybrid modes, is not generally tractable. In this paper, we are inspired by the observation that far fewer modes are actually necessary to accomplish many tasks. Building on our prior work learning hybrid models, represented as linear complementarity systems, we find a reduced-order hybrid model requiring only a limited number of task-relevant modes. This simplified representation, in combination with model predictive control, enables real-time control yet is sufficient for achieving high performance. We demonstrate the proposed method first on synthetic hybrid systems, reducing the mode count by multiple orders of magnitude while achieving task performance loss of less than 5%. We also apply the proposed method to a three-fingered robotic hand manipulating a previously unknown object. With no prior knowledge, we achieve state-of-the-art closed-loop performance within a few minutes of online learning, by collecting only a few thousand environment samples.