RObotic MAnipulation Network (ROMAN) -- Hybrid Hierarchical Learning for Solving Complex Sequential Tasks

TL;DR

ROMAN is a hybrid hierarchical learning framework that enables robots to perform complex, long-horizon manipulation tasks with robustness, adaptability, and failure recovery by integrating multiple learning strategies and specialized neural networks.

Contribution

The paper introduces ROMAN, a novel hybrid hierarchical framework combining behavioral cloning, imitation learning, and reinforcement learning for versatile robotic manipulation.

Findings

ROMAN successfully performs complex long-horizon tasks.

ROMAN demonstrates robustness to sensory noise.

ROMAN exhibits autonomous failure recovery.

Abstract

Solving long sequential tasks poses a significant challenge in embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is an active area of research. In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specialising in distinct re-combinable sub-tasks to generate their correct in-sequence actions for solving complex long-horizon manipulation tasks. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results demonstrate the significance and versatility of ROMAN's dynamic adaptability featuring autonomous failure recovery capabilities, and highlight its potential for various autonomous manipulation tasks that demand adaptive motor skills.