Hierarchical microstructure-enhanced flexible capacitive pressure sensor for high-accuracy fruit identification

The development of highly sensitive and versatile flexible pressure sensors presents significant potential for advancing precision in human-computer interaction systems, particularly in addressing challenges associated with discriminating objects possessing nearly identical visual characteristics. In this work, we fabricated a hierarchical microstructure-enhanced flexible capacitive pressure sensor through synergistic integration of polyvinylpyrrolidone (PVP), polydimethylsiloxane (PDMS), and laser-induced graphene (LIG). A sandpaper-assisted electrospinning technique was employed to create the dielectric layer consisting of PDMS@PVP nanofiber membrane (NM) with irregular concave microstructures, while porous LIG electrodes were precisely patterned onto PVP NMs using screen-printing technology. The incorporation of PDMS effectively enhanced interfacial adhesion and structural plasticity of PVP NM, while the sandpaper-templated concave microstructures in the NM dielectric layer substantially improved sensor sensitivity, particularly in medium-high pressure regimes. The optimized sensor demonstrates exceptional performance metrics including: remarkable sensitivity (0.338 kPa −1 in 0–1 kPa range), broad detection range (0–200 kPa), ultrafast response/recovery times (31/41 ms), ultralow detection limit (2.9 Pa), and outstanding durability (>3000 cycles). Capitalizing on these advancements, the sensor was successfully integrated into a robotic manipulator system, and a fruit identification system was developed, incorporating an embedded system with artificial intelligence algorithms. This integrated system achieves dual discrimination capabilities: distinguishing fruits with nearly identical size/weight characteristics (95.83 % accuracy) and identifying ripeness stages of individual fruits (100 % accuracy). This study establishes a robust technological strategy to overcome tactile recognition limitations for visually indistinguishable objects, demonstrating transformative potential for intelligent human-machine interface applications.