Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering ...Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering provides abiologically inspired alternative by adopting event-driven,spike-based coding,akin to neural signaling in humansomatosensory systems.This review systematically examines spike-based neural coding techniques for tactileperception,focusing on three key aspects:encoding strategies,neuromorphic hardware implementations,anddecoding methodologies.It compares rate coding and temporal coding in terms of biological plausibility andcomputational efficiency,particularly in dynamic and high-speed tactile tasks.A range of hardware platforms isevaluated,including oscillator-based encoding circuits,CMOS and memristor-based spiking neurons,and self-poweredtactile sensors using triboelectric nanogenerators.On the decoding side,mechanisms such as spike-timing-dependentplasticity and spiking neural networks are analyzed for their potential to support adaptive,online learning in tactilesystems.The review emphasizes co-design approaches that integrate sensing,encoding,and processing within aunified framework to achieve system-level efficiency.By bridging advances in functional materials,low-powerhardware,and brain-inspired computation,this work outlines a roadmap toward artificial tactile systems withmillisecond-level latency,sub-milliwatt power consumption,and high perceptual fidelity.These capabilities areessential for future applications in robotics,prosthetics,and wearable electronics.展开更多
基金supported by the Stable Support Plan Program of Shenzhen Natural Science Fund[grant number 20231120204356001]the Guangdong Basic and Applied Basic Research Foundation[grant number 2024A1515030156]the funding from Tencent Robotics X.
文摘Tactile perception in artificial systems remains constrained by the von Neumann architecture,where the separation ofmemory and computation leads to significant latency and energy inefficiency.Neuromorphic engineering provides abiologically inspired alternative by adopting event-driven,spike-based coding,akin to neural signaling in humansomatosensory systems.This review systematically examines spike-based neural coding techniques for tactileperception,focusing on three key aspects:encoding strategies,neuromorphic hardware implementations,anddecoding methodologies.It compares rate coding and temporal coding in terms of biological plausibility andcomputational efficiency,particularly in dynamic and high-speed tactile tasks.A range of hardware platforms isevaluated,including oscillator-based encoding circuits,CMOS and memristor-based spiking neurons,and self-poweredtactile sensors using triboelectric nanogenerators.On the decoding side,mechanisms such as spike-timing-dependentplasticity and spiking neural networks are analyzed for their potential to support adaptive,online learning in tactilesystems.The review emphasizes co-design approaches that integrate sensing,encoding,and processing within aunified framework to achieve system-level efficiency.By bridging advances in functional materials,low-powerhardware,and brain-inspired computation,this work outlines a roadmap toward artificial tactile systems withmillisecond-level latency,sub-milliwatt power consumption,and high perceptual fidelity.These capabilities areessential for future applications in robotics,prosthetics,and wearable electronics.
