# RF-Transformer: A Unified Backscatter Radio Hardware Abstraction

arXiv: https://arxiv.org/abs/2209.15195 · HTML: https://mlsanity.com/paper/2209.15195/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Sep 2022.

## Built on by (most cited first, 1 of 1)

- [Analog RF Computing: A New Paradigm for Energy-Efficient Edge AI Over MU-MIMO Systems](https://mlsanity.com/paper/2605.14331/) (2026)

## Abstract (arXiv)

This paper presents RF-Transformer, a unified backscatter radio hardware abstraction that allows a low-power IoT device to directly communicate with heterogeneous wireless receivers at the minimum power consumption. Unlike existing backscatter systems that are tailored to a specific wireless communication protocol, RF-Transformer provides a programmable interface to the micro-controller, allowing IoT devices to synthesize different types of protocol-compliant backscatter signals sharing radically different PHY-layer designs. To show the efficacy of our design, we implement a PCB prototype of RF-Transformer on 2.4 GHz ISM band and showcase its capability on generating standard ZigBee, Bluetooth, LoRa, and Wi-Fi 802.11b/g/n/ac packets. Our extensive field studies show that RF-Transformer achieves 23.8 Mbps, 247.1 Kbps, 986.5 Kbps, and 27.3 Kbps throughput when generating standard Wi-Fi, ZigBee, Bluetooth, and LoRa signals while consuming 7.6-74.2 less power than their active counterparts. Our ASIC simulation based on the 65-nm CMOS process shows that the power gain of RF-Transformer can further grow to 92-678. We further integrate RF-Transformer with pressure sensors and present a case study on detecting foot traffic density in hallways. Our 7-day case studies demonstrate RFTransformer can reliably transmit sensor data to a commodity gateway by synthesizing LoRa packets on top of Wi-Fi signals. Our experimental results also verify the compatibility of RF-Transformer with commodity receivers. Code and hardware schematics can be found at: https://github.com/LeFsCC/RF-Transformer.