Learning and Blending Robot Hugging Behaviors in Time and Space

TL;DR

This paper presents B-BIP, an imitation learning algorithm enabling robots to respond adaptively and accurately in complex, multi-faceted hugging interactions, improving responsiveness and participant experience.

Contribution

Introduction of B-BIP, a novel blending Bayesian interaction primitive algorithm that generalizes previous methods for complex human-robot hugging interactions.

Findings

B-BIP achieves lower prediction error than existing methods.

Participants responded more favorably to B-BIP-controlled robots.

The algorithm adapts effectively to complex, multi-interaction scenarios.

Abstract

We introduce an imitation learning-based physical human-robot interaction algorithm capable of predicting appropriate robot responses in complex interactions involving a superposition of multiple interactions. Our proposed algorithm, Blending Bayesian Interaction Primitives (B-BIP) allows us to achieve responsive interactions in complex hugging scenarios, capable of reciprocating and adapting to a hugs motion and timing. We show that this algorithm is a generalization of prior work, for which the original formulation reduces to the particular case of a single interaction, and evaluate our method through both an extensive user study and empirical experiments. Our algorithm yields significantly better quantitative prediction error and more-favorable participant responses with respect to accuracy, responsiveness, and timing, when compared to existing state-of-the-art methods.