DRIFT: Joint Channel Estimation and Prediction for Pilotless 6G NTNs
A new paper proposes DRIFT, an iterative joint channel estimation and prediction framework for 6G non-terrestrial networks (NTNs) that significantly reduces pilot overhead. The method transmits pilots only in the initial slot and uses data-driven processing to enable spectral efficiency gains. Designed for low Earth orbit (LEO) NTNs with strict power constraints, DRIFT aims to provide accurate yet computationally efficient channel prediction, addressing the high inference complexity of many AI-based predictors. The framework is tailored to improve spectrum utilization in 6G systems, which rely on NTNs for ubiquitous connectivity and massive communication. The paper is available on arXiv under identifier 2605.31065.
Key facts
- DRIFT is an iterative joint channel estimation and prediction framework for 6G NTNs.
- It reduces pilot overhead by transmitting pilots only in the initial slot.
- The method is designed for LEO NTNs with strict power constraints.
- It aims to be accurate yet computationally efficient.
- The paper is on arXiv with ID 2605.31065.
- NTNs are expected to play a pivotal role in 6G systems.
- Channel prediction improves spectrum utilization efficiency.
- Many AI-based predictors have high inference complexity.
Entities
Institutions
- arXiv