Coordination with Humans via Strategy Matching
This addresses the challenge of human-robot coordination in team collaborations, offering a method for robots to better adapt to human partners, though it is incremental as it builds on existing strategy recognition and learning techniques.
The paper tackles the problem of enabling robots to adapt to human partners in collaborative tasks by developing a computational framework that recognizes task-completion strategies from human-human interactions and learns robot policies for each strategy. Results from an online user study with 125 participants show that this framework improves task performance and collaborative fluency compared to state-of-the-art reinforcement learning methods.
Human and robot partners increasingly need to work together to perform tasks as a team. Robots designed for such collaboration must reason about how their task-completion strategies interplay with the behavior and skills of their human team members as they coordinate on achieving joint goals. Our goal in this work is to develop a computational framework for robot adaptation to human partners in human-robot team collaborations. We first present an algorithm for autonomously recognizing available task-completion strategies by observing human-human teams performing a collaborative task. By transforming team actions into low dimensional representations using hidden Markov models, we can identify strategies without prior knowledge. Robot policies are learned on each of the identified strategies to construct a Mixture-of-Experts model that adapts to the task strategies of unseen human partners. We evaluate our model on a collaborative cooking task using an Overcooked simulator. Results of an online user study with 125 participants demonstrate that our framework improves the task performance and collaborative fluency of human-agent teams, as compared to state of the art reinforcement learning methods.