AI 中文总结
该综述以平台为中心，全面梳理硬件模糊系统的三类实现，对比各平台特性，指出研究缺口并提出未来方向，为相关研究者与从业者提供参考。
AI 中文摘要
模糊逻辑系统被广泛用于不确定性下的智能决策，在各类应用中兼具可解释性与鲁棒性。然而，实时边缘智能的日益增长需求，暴露了软件模糊推理的局限性：不可预测的延迟、过高的功耗以及低效的资源利用。这推动了对硬件加速的广泛研究，涵盖从定制模拟电路、数字ASIC到可重构FPGA、超低功耗微控制器等平台。本综述首次以平台为中心，对硬件模糊系统进行全面综述，将相关文献系统分为三大类：基于FPGA的实现、ASIC与定制VLSI实现、嵌入式、物联网（IoT）及TinyML平台。针对每一类，我们分析了架构组织、资源映射策略、实现权衡及关键设计挑战。跨平台对比分析显示，没有单一平台在所有指标上占据主导：FPGA提供灵活性与快速原型开发，ASIC实现峰值性能与能效，而嵌入式与TinyML系统则平衡了低功耗与成本，适用于边缘部署。尽管已取得显著进展，但仍存在关键研究缺口：缺乏标准化基准、规则库可扩展性有限、设计自动化不足，以及对在线学习与新兴存储技术的支持有限。我们概述了未来方向，包括基于忆阻器交叉阵列的存内模糊计算、与TinyML生态系统的集成、可解释硬件AI，以及开源设计自动化。本综述为从事硬件实现的模糊智能研究的科研人员与从业者提供参考。
英文摘要
Fuzzy logic systems are widely used for intelligent decision-making under uncertainty, offering interpretability and robustness across diverse applications. However, the growing demand for real-time edge intelligence has exposed the limitations of software-based fuzzy inference: unpredictable latency, excessive power consumption, and inefficient resource utilization. This has motivated extensive research into hardware acceleration, spanning platforms from custom analog circuits and digital ASICs to reconfigurable FPGAs and ultra-low-power microcontrollers. This survey presents the first comprehensive, platform-centric review of hardware fuzzy systems, systematically organizing the literature into three principal categories: FPGA-based implementations, ASIC and custom VLSI realizations, and embedded, IoT, and TinyML platforms. For each category, we analyze architectural organization, resource mapping strategies, implementation trade-offs, and key design challenges. Our cross-platform comparative analysis reveals that no single platform dominates across all metrics. FPGAs offer flexibility and rapid prototyping, ASICs deliver peak performance and energy efficiency, while embedded and TinyML systems balance low power and cost for edge deployment. Despite significant progress, critical research gaps persist: the absence of standardized benchmarks, limited scalability of rule bases, insufficient design automation, and limited support for online learning and emerging memory technologies. We outline future directions including in-memory fuzzy computing with memristive crossbars, integration with TinyML ecosystems, explainable hardware AI, and open-source design automation. This survey serves as a {reference for} researchers and practitioners working on hardware-enabled fuzzy intelligence.
Comments17 pages, 13 figures
