M-EMBER: Tackling Long-Horizon Mobile Manipulation via Factorized Domain Transfer

TL;DR

This paper introduces M-EMBER, a factorized approach that decomposes long-horizon mobile manipulation tasks into primitive skills, enabling robots to perform complex activities like cleaning with improved success.

Contribution

M-EMBER is a novel method that combines skill decomposition, reinforcement learning, and skill composition to address long-horizon mobile manipulation challenges.

Findings

Achieves 53% success rate on cleaning_kitchen task

Successfully decomposes tasks into five learned visual skills

Demonstrates effective long-horizon manipulation in real robot

Abstract

In this paper, we propose a method to create visuomotor mobile manipulation solutions for long-horizon activities. We propose to leverage the recent advances in simulation to train visual solutions for mobile manipulation. While previous works have shown success applying this procedure to autonomous visual navigation and stationary manipulation, applying it to long-horizon visuomotor mobile manipulation is still an open challenge that demands both perceptual and compositional generalization of multiple skills. In this work, we develop Mobile-EMBER, or M-EMBER, a factorized method that decomposes a long-horizon mobile manipulation activity into a repertoire of primitive visual skills, reinforcement-learns each skill, and composes these skills to a long-horizon mobile manipulation activity. On a mobile manipulation robot, we find that M-EMBER completes a long-horizon mobile manipulation activity, cleaning_kitchen, achieving a 53% success rate. This requires successfully planning and executing five factorized, learned visual skills.