TY - GEN
T1 - Human Hand Shape and Grasping Behavior Estimation using a Humanoid Hand with a Tactile Interface
AU - Saood, Adnan
AU - Tapus, Adriana
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2026.
PY - 2026/1/1
Y1 - 2026/1/1
N2 - Understanding and replicating human hand shape and grasping behavior are essential for improving physical human-robot interaction. In this work, we introduce a novel method for estimating both human hand geometry and grasping style using a tactile sensory humanoid hand. Our system integrates a silicone-based glove embedded with pressure sensors and mounted on a robotic hand, allowing users to perform naturalistic grasping gestures. By analyzing the tactile feedback generated during the interaction, we trained AI models to estimate individual hand shapes and classify grasping behaviors. A user study with 19 participants evaluated the comfort and usability of the system. Participants highlighted the softness and responsiveness of the glove. Feedback was used to identify key design improvements, including hand scaling, sensor distribution, and enhanced realism in tactile textures. Our results demonstrate the feasibility of using a tactile humanoid hand as an interactive tool for capturing nuanced human grasp style and hand size with 68% and 96%, respectively.
AB - Understanding and replicating human hand shape and grasping behavior are essential for improving physical human-robot interaction. In this work, we introduce a novel method for estimating both human hand geometry and grasping style using a tactile sensory humanoid hand. Our system integrates a silicone-based glove embedded with pressure sensors and mounted on a robotic hand, allowing users to perform naturalistic grasping gestures. By analyzing the tactile feedback generated during the interaction, we trained AI models to estimate individual hand shapes and classify grasping behaviors. A user study with 19 participants evaluated the comfort and usability of the system. Participants highlighted the softness and responsiveness of the glove. Feedback was used to identify key design improvements, including hand scaling, sensor distribution, and enhanced realism in tactile textures. Our results demonstrate the feasibility of using a tactile humanoid hand as an interactive tool for capturing nuanced human grasp style and hand size with 68% and 96%, respectively.
UR - https://www.scopus.com/pages/publications/105046871498
U2 - 10.1007/978-981-95-2398-6_6
DO - 10.1007/978-981-95-2398-6_6
M3 - Conference contribution
AN - SCOPUS:105046871498
SN - 9789819523979
T3 - Lecture Notes in Computer Science
SP - 75
EP - 86
BT - Social Robotics + AI - 17th International Conference, ICSR+AI 2025, Proceedings, Part 3
A2 - Staffa, Mariacarla
A2 - Cabibihan, John-John
A2 - Siciliano, Bruno
A2 - Rossi, Silvia
A2 - Sam Ge, Shuzhi
A2 - Bodenhagen, Leon
A2 - Tapus, Adriana
A2 - Cavallo, Filippo
A2 - Fiorini, Laura
A2 - Matarese, Marco
A2 - He, Hongsheng
PB - Springer Science and Business Media Deutschland GmbH
T2 - 17th International Conference on Social Robotics, ICSR+AI 2025
Y2 - 10 September 2025 through 12 September 2025
ER -