Eojin Ji

Soft pneumatic grippers are well-suited for grasping irregular objects owing to their inherent compliance and ability to adapt to a wide range of shapes and sizes. However, their ability to quantitatively estimate object size during the grasping process remains limited. To address this limitation, this study proposes a soft pneumatic gripper integrated with a piezoresistive CNT/PDMS composite sensor and investigates the feasibility of object size estimation using only sensor signals. The pressure-sensing characteristics of the CNT/PDMS sensor were evaluated over a pressure range of 0–500 kPa, and the 1 wt% CNT/PDMS sensor exhibited the highest sensitivity of approximately 0.016 kPa⁻¹ in the initial linear pressure region. To this end, the normalized resistance response under applied pneumatic pressure was analyzed independent of external visual information, and a size estimation method was established based on the relationship between initial contact pressure and object diameter. Grasping experiments using spherical objects of varying diameters revealed that the resistance response patterns were clearly distinguishable according to object size, with larger objects exhibiting significant resistance changes at lower applied pressures. These findings demonstrate the feasibility of estimating the size of a grasped object based on the grasp onset pressure derived from the sensor response. The results of this study provide a foundation for future soft robotic systems capable of recognizing contact conditions and object size through sensor-based feedback. Furthermore, these findings may be extended to adaptive manipulation technologies involving real-time pneumatic pressure control.