Dance2Hesitate: A Multi-Modal Dataset of Dancer-Taught Hesitancy for Understandable Robot Motion
This work proposes the design of hesitation-aware robotic motion that is both generalizable and interpretable by humans to enhance coordination, attention allocation, and safety in human–robot collaboration. By integrating demonstrations from professional dancers with kinesthetic teaching on a Franka Emika Panda manipulator—captured via an RGB-D full-body motion tracking system—the study constructs the first multimodal dataset of hesitation behaviors spanning three distinct levels of hesitation. The dataset comprises 70 full-body trajectories, 84 upper-limb trajectories, and 66 robot trajectories, encompassing both task-specific scenarios (e.g., approaching a block tower) and free-space movements. This effort delivers the first structured, cross-modal recording of hesitation behaviors, which is publicly released to establish a reproducible benchmark for research on human–robot hesitation interaction.