← Back to Benchmarks
simmediummanipulationmetric · varies
Dance2Hesitate: A Multi-Modal Dataset of Dancer-Taught Hesitancy for Understandable Robot Motion
Description
In human-robot collaboration, a robot's expression of hesitancy is a critical factor that shapes human coordination strategies, attention allocation, and safety-related judgments. However, designing hesitant robot motion that generalizes is challenging because the observer's inference is highly dependent on embodiment and context. To address these challenges, we introduce and open-source a multi-modal, dancer-generated dataset of hesitant motion where we focus on specific context-embodiment pair