<p>Tactile sensing for dexterous robotic hands is essential for achieving human-like precision in manipulation. However, current tactile sensors face several challenges, such as insufficient durability, limited coverage, and poor conformability to the dexterous hand’s curved, jointed surfaces. In this study, we propose a stretchable distributed tactile sensor array designed for dexterous robotic hands. The sensor array consists of 18 sensing units distributed across the robotic hand, incorporating quasi-homogeneous functional layers interconnected by crosslinked interpenetrating networks, and composite electrodes that combine high conductivity with stretchability. This design results in a thin, soft, transparent, and stretchable tactile sensor array that integrates seamlessly with a commercial dexterous hand. The sensor array exhibits high interlayer tensile strength, high sensitivity, low hysteresis, along with excellent long-term reliability over 10000 loading cycles. The experimental results demonstrate that the distributed sensor array can accurately detect the tactile force across the entire robotic hand during object grasping. Based on convolutional neural network algorithms, the proposed tactile sensor array can accurately identify different types of objects with an accuracy of 90.1%, with results shown in real time on a digital twin interface. The proposed sensor array holds significant potential for embodied intelligence and robotics in adaptive grasping, safe manipulation, and remote teleoperation.</p>