Physical Layer Design for Ambient IoT

There is a growing demand for ultra low power and ultra low complexity devices for applications which require maintenance-free and battery-less operation. One way to serve such applications is through backscatter devices, which communicate using energy harvested from ambient sources such as radio waves transmitted by a reader. Traditional backscatter devices, such as RFID, are limited by range, interference, low connection density, and security issues. To address these problems, the Third Generation Partnership Project (3GPP) has started working on Ambient IoT (A-IoT). For the realization of A-IoT devices, various aspects ranging from physical layer design, to the protocol stack, to the device architecture should be standardized. In this paper, we provide an overview of the standardization efforts on the physical layer design for A-IoT devices. The various physical channels and signals are discussed, followed by link level simulations to compare the performance of various configurations of reader to device and device to reader channels.

On the Application of Deep Learning for Precise Indoor Positioning in 6G

Accurate localization in indoor environments is a challenge due to the Non Line of Sight (NLoS) nature of the signaling. In this paper, we explore the use of AI/ML techniques for positioning accuracy enhancement in Indoor Factory (InF) scenarios. The proposed neural network, which we term LocNet, is trained on measurements such as Channel Impulse Response (CIR) and Reference Signal Received Power (RSRP) from multiple Transmit Receive Points (TRPs). Simulation results show that when using measurements from 18 TRPs, LocNet achieves a 9 cm positioning accuracy at the 90th percentile. Additionally, we demonstrate that the same model generalizes effectively even when measurements from some TRPs randomly become unavailable. Lastly, we provide insights on the robustness of the trained model to the errors in ground truth labels used for training.

Enhancements for 5G NR PRACH Reception: An AI/ML Approach

Random Access is an important step in enabling the initial attachment of a User Equipment (UE) to a Base Station (gNB). The UE identifies itself by embedding a Preamble Index (RAPID) in the phase rotation of a known base sequence, which it transmits on the Physical Random Access Channel (PRACH). The signal on the PRACH also enables the estimation of propagation delay, often known as Timing Advance (TA), which is induced by virtue of the UE's position. Traditional receivers estimate the RAPID and TA using correlation-based techniques. This paper presents an alternative receiver approach that uses AI/ML models, wherein two neural networks are proposed, one for the RAPID and one for the TA. Different from other works, these two models can run in parallel as opposed to sequentially. Experiments with both simulated data and over-the-air hardware captures highlight the improved performance of the proposed AI/ML-based techniques compared to conventional correlation methods.