Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

TL;DR

Co-GAIL introduces a method for learning diverse and robust human-robot collaboration strategies by co-optimizing human and robot policies through interactive learning, improving performance across various tasks with real human operators.

Contribution

The paper proposes a novel co-optimization framework that learns human and robot policies simultaneously from demonstrations, enabling handling of diverse behaviors and strategy adaptation during online tasks.

Findings

Outperforms existing methods in simulated evaluations.

Effective in real human-robot interaction scenarios.

Handles diverse human behaviors and strategy shifts.

Abstract

We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human behaviors shown in the demonstrations and be robust when the humans adjust their strategies during online task execution. Our method co-optimizes a human policy and a robot policy in an interactive learning process: the human policy learns to generate diverse and plausible collaborative behaviors from demonstrations while the robot policy learns to assist by estimating the unobserved latent strategy of its human collaborator. Across a 2D strategy game, a human-robot handover task, and a multi-step collaborative manipulation task, our method outperforms the alternatives in both simulated evaluations and when executing the tasks with a real human operator in-the-loop. Supplementary materials and videos at https://sites.google.com/view/co-gail-web/home