Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration
This addresses the challenge of enabling robots to assist effectively in collaborative tasks with humans, though it appears incremental as it builds on existing imitation learning frameworks.
The paper tackles the problem of learning human-robot collaboration policies from human-human demonstrations, focusing on handling diverse human behaviors and robustness to strategy adjustments during execution. The method outperforms alternatives in simulated evaluations and real human-robot tasks across three domains, including a 2D strategy game, handover task, and collaborative manipulation task.
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