34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pp.1056 - 1063
Abstract
Social robots utilize facial expressions to convey emotions, yet most rely on predefined animation sequences for each emotion, which can result in abrupt or unnatural transitions. To address this, we employ a Control Point (CP)-based approach that dynamically adjusts facial features, enabling seamless expression transitions without predefined animations. Our study explores whether a CP-based approach enables smoother and more natural facial expressions compared to commonly used facial expression methods. Furthermore, we validate its applicability by demonstrating its effectiveness on two distinct facial designs highlighting versatility across both tested designs.