Human-centered collaborative robots with deep reinforcement learning

TL;DR

This paper introduces a reinforcement learning framework for human-centered collaborative robots that enables fluent, adaptive, and end-to-end learned coordination with humans in tasks like packaging, without requiring extensive data annotation.

Contribution

It presents an unsupervised, end-to-end reinforcement learning approach that improves human-robot collaboration fluency and adaptability in real-time tasks.

Findings

Enhanced coordination between human and robot in packaging tasks.

Faster adaptation to new human partners and tasks.

Elimination of extensive motion data annotation.

Abstract

We present a reinforcement learning based framework for human-centered collaborative systems. The framework is proactive and balances the benefits of timely actions with the risk of taking improper actions by minimizing the total time spent to complete the task. The framework is learned end-to-end in an unsupervised fashion addressing the perception uncertainties and decision making in an integrated manner. The framework is shown to provide more fluent coordination between human and robot partners on an example task of packaging compared to alternatives for which perception and decision-making systems are learned independently, using supervised learning. The foremost benefit of the proposed approach is that it allows for fast adaptation to new human partners and tasks since tedious annotation of motion data is avoided and the learning is performed on-line.