Recent advances in spike-based neural coding for tactile perception

Tactile perception in artificial systems remains constrained by the von Neumann architecture, where the separation of memory and computation leads to significant latency and energy inefficiency. Neuromorphic engineering provides a biologically inspired alternative by adopting event-driven, spike-based coding, akin to neural signaling in human somatosensory systems. This review systematically examines spike-based neural coding techniques for tactile perception, focusing on three key aspects: encoding strategies, neuromorphic hardware implementations, and decoding methodologies. It compares rate coding and temporal coding in terms of biological plausibility and computational efficiency, particularly in dynamic and high-speed tactile tasks. A range of hardware platforms is evaluated, including oscillator-based encoding circuits, CMOS and memristor-based spiking neurons, and self-powered tactile sensors using triboelectric nanogenerators. On the decoding side, mechanisms such as spike-timing-dependent plasticity and spiking neural networks are analyzed for their potential to support adaptive, online learning in tactile systems. The review emphasizes co-design approaches that integrate sensing, encoding, and processing within a unified framework to achieve system-level efficiency. By bridging advances in functional materials, low-power hardware, and brain-inspired computation, this work outlines a roadmap toward artificial tactile systems with millisecond-level latency, sub-milliwatt power consumption, and high perceptual fidelity. These capabilities are essential for future applications in robotics, prosthetics, and wearable electronics.