Next-generation wireless systems aim at fulfilling diverse application requirements but fundamentally rely on point-to-point transmission qualities. Aligning with recent AI-enabled wireless implementations, this paper introduces autonomic radios, 6G-AUTOR, that leverage novel algorithm-hardware separation platforms, softwarization of transmission (TX) and reception (RX) operations, and automatic reconfiguration of RF frontends, to support link performance and resilience. Hence, a software architecture can be provided to enable event-triggered operations for seamless hosting and execution environment. That is, those functions can be executed on an on-demand basis so that no resources will be preoccupied until the point of execution for better device efficiency. As a comprehensive transceiver solution, our design encompasses several ML-driven models, each enhancing a specific aspect of either TX or RX, leading to robust transceiver operation under tight constraints of future wireless systems. As for Tx scenarios, a data-driven spectrum sensing algorithm was implemented to obtain usages of current frequency bands for further use. Also, a data-driven radio management module was developed via deep Q-networks to support fast-reconfiguration of TX resource blocks (RB) and proactive multi-agent access. As for Rx scenarios, a fundamental tool - automatic modulation classification (AMC) which involves a complex correntropy extraction, followed by a convolutional neural network (CNN)-based classification, and a deep learning-based LDPC decoder were added to improve the reception quality and radio performance. Simulations of individual algorithms demonstrate that under appropriate training, each of the corresponding radio functions have either outperformed or have performed on-par with the benchmark solutions.

下一代无线系统旨在满足多样化的应用需求，但从根本上依赖于点对点的传输质量。与最新的人工智能无线实现相结合，本文介绍了自主无线电 6G-AUTOR，它利用新颖的算法-硬件分离平台、传输 (TX) 和接收 (RX) 操作的软件化以及射频前端的自动重新配置来支持链接性能和弹性。因此，可以提供软件架构来实现无缝托管和执行环境的事件触发操作。也就是说，这些功能可以按需执行，以便在执行点之前不会占用任何资源，从而提高设备效率。作为一个全面的收发器解决方案，我们的设计包含多个机器学习驱动的模型，每个模型都增强了 TX 或 RX 的特定方面，从而在未来无线系统的严格约束下实现稳健的收发器操作。对于Tx场景，实现了数据驱动的频谱感知算法来获取当前频段的使用情况以供进一步使用。此外，还通过深度 Q 网络开发了数据驱动的无线电管理模块，以支持 TX 资源块 (RB) 的快速重新配置和主动多代理访问。对于接收场景，添加了一个基本工具 - 自动调制分类（AMC），其中涉及复杂的相关熵提取，然后是基于卷积神经网络（CNN）的分类，以及基于深度学习的LDPC解码器以提高接收质量和广播表演。各个算法的模拟表明，在适当的训练下，每个相应的无线电功能都优于基准解决方案或与基准解决方案持平。