RF hardware design is a complicated, time-consuming, and expertise-bound process, which constrains the development and adoption of hardware innovation. Manual workflows do not scale to emerging wireless applications, while existing design generation strategies, e.g., learning-based approaches, lack training efficiency and generalizability across hardware types, frequency bands, operation modes, and substrate materials. In this paper, we present AutoRF, the first agentic framework for automated RF hardware design, supporting metasurfaces and antennas. It allows users to specify their demands and generate corresponding designs. We introduce extensible design abstractions to enable a modular framework. The core of the framework is an efficient and generalizable algorithm for design search and optimization, which utilizes LLMs to drive both circuit model simulator and EM simulator. To boost reliability and performance, we propose custom programming interfaces and a rule reviewer agent as feedback sources to train a specialized LLM. Evaluation demonstrates high success rate and significant optimization speedup; case studies with fabricated metasurface and antennas, ranging from 2.4 GHz to sub-THz, illustrate an ability to derive novel designs for next-generation wireless infrastructure.

Cross-technology communication (CTC) facilitates seamless interaction between different wireless technologies. Most existing methods use reverse engineering to derive the required transmission payload, generating a waveform that the target device can successfully demodulate. However, traditional approaches have certain limitations, including reliance on specific reverse engineering algorithms or the need for manual parameter tuning to reduce emulation distortion. In this work, we present NNCTC, a framework for achieving physical layer cross-technology communication through explainable neural networks, incorporating relevant knowledge from the wireless communication physical layer into the neural network models. We first convert the various signal processing components within the CTC process into neural network models, then build a training framework for the CTC encoder-decoder structure to achieve CTC. NNCTC significantly reduces the complexity of CTC by automatically deriving CTC payloads through training. We demonstrate how NNCTC implements CTC in WiFi systems using OFDM and CCK modulation. On WiFi systems using OFDM modulation, NNCTC outperforms the WEBee and WIDE designs in terms of error performance, achieving an average packet reception ratio (PRR) of 92.3% and an average symbol error rate (SER) as low as 1.3%. In WiFi systems using OFDM modulation, the highest PRR can reach up to 99%.

Cross-technology communication (CTC) enables seamless interactions between diverse wireless technologies. Most existing work is based on reversing the transmission path to identify the appropriate payload to generate the waveform that the target devices can recognize. However, this method suffers from many limitations, including dependency on specific technologies and the necessity for intricate algorithms to mitigate distortion. In this work, we present NNCTC, a Neural-Network-based Cross-Technology Communication framework inspired by the adaptability of trainable neural models in wireless communications. By converting signal processing components within the CTC pipeline into neural models, the NNCTC is designed for end-to-end training without requiring labeled data. This enables the NNCTC system to autonomously derive the optimal CTC payload, which significantly eases the development complexity and showcases the scalability potential for various CTC links. Particularly, we construct a CTC system from Wi-Fi to ZigBee. The NNCTC system outperforms the well-recognized WEBee and WIDE design in error performance, achieving an average packet reception rate (PRR) of 92.3% and an average symbol error rate (SER) as low as 1.3%.

Cross-technology communication (CTC) enables seamless interactions between diverse wireless technologies. Most existing work is based on reversing the transmission path to identify the appropriate payload to generate the waveform that the target devices can recognize. However, this method suffers from many limitations, including dependency on specific technologies and the necessity for intricate algorithms to mitigate distortion. To address these challenges, we present NNCTC, a Neural-Network-based Cross-Technology Communication framework which can achieve reliable and interpretable Cross-Technology Communication through a training process with an example of WiFi (OFDM and CCK) to both known and unknown modulation schemes.

A physical-layer modulator is crucial for IoT gateways, but current solutions face issues like limited extensibility and platform-specificity due to soldered chipsets for specific technologies or diverse software toolkits for software radios. With the rapid expansion of the Internet of Things (IoT), such limitations are hard to ignore as the demand for versatile wireless technologies has increased. This paper introduces a novel approach using neural networks as an abstraction layer for these modulators in IoT gateways, termed NN-defined modulators. This method overcomes the challenges of extensibility and portability across different hardware platforms. The NN-defined modulator employs a model-driven approach based on mathematical principles, resulting in a lightweight, hardware-acceleration-friendly structure. These modulators are containerized with necessary runtime, facilitating agile deployment on varied platforms. We tested NN-defined modulators on platforms like Nvidia Jetson Nano and Raspberry Pi, showing they perform comparably to traditional modulators while offering efficiency improvements. The implementation is memory-efficient and adds minimal latency. Additionally, we demonstrate real-world applications of our NN-defined modulators in generating ZigBee and WiFi packets, compatible with standard TI CC2650 (ZigBee) and Intel AX201 (WiFi NIC) devices.

A digital modulator plays a crucial role in converting symbols into signals in an IoT gateway. However, the ever-increasing modulation schemes pose practical challenges, such as flexibility for different schemes and portability with different hardware platforms. To address these challenges, we propose a new approach that employs a neural network as an abstraction layer for physical layer modulators, called the NN-defined modulator. We will demonstrate that the NN-defined modulator functions like traditional modulators and offers high portability and efficiency with example communication to ZigBee and WiFi.