Probabilistic Multimodal Modeling for Human-Robot Interaction Tasks
This work addresses a bottleneck in human-robot interaction for robotics applications, but it appears incremental as it builds on existing Interaction Primitives.
The paper tackles the problem of inefficient multimodal inference in human-robot interaction by introducing a reformulation of Interaction Primitives that handles nonlinearities, resulting in more accurate, robust, and faster inference compared to standard methods.
Human-robot interaction benefits greatly from multimodal sensor inputs as they enable increased robustness and generalization accuracy. Despite this observation, few HRI methods are capable of efficiently performing inference for multimodal systems. In this work, we introduce a reformulation of Interaction Primitives which allows for learning from demonstration of interaction tasks, while also gracefully handling nonlinearities inherent to multimodal inference in such scenarios. We also empirically show that our method results in more accurate, more robust, and faster inference than standard Interaction Primitives and other common methods in challenging HRI scenarios.