Human-centered collaborative robots with deep reinforcement learning
This work addresses coordination challenges in human-robot collaboration, offering incremental improvements by integrating perception and decision-making for faster adaptation to new partners and tasks.
The paper tackles the problem of human-robot collaboration by developing a reinforcement learning framework that balances timely actions with risk, resulting in more fluent coordination in packaging tasks compared to independent perception and decision-making systems.
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.