Background
Millimeter-wave (mmWave) and terahertz (THz) frequency bands are growing in prevalence in current and future communication systems. These frequency ranges provide higher bandwidths, which enable the communication systems to efficiently meet the higher data requirements of high speed applications including augmented or virtual reality, autonomous vehicles, and smart cities. However, these frequencies typically require large antenna arrays, which use narrow directive beams to ensure sufficient receiving signal power. The selection of optimal beams requires a substantial training overhead, which makes it challenging to meet the low-latency and high-reliability requirements of these communication systems.
Invention Description
Researchers at Arizona State University have developed a new approach using distributed sensing and machine learning to optimize beam selection in mmWave and THz communication systems. This technology uses distributed nodes equipped with RGB cameras to capture environmental semantics, significantly reducing beam training overhead in mmWave and THz communication systems. This system enhances adaptability and efficiency in dynamic environments by focusing on the transmission of semantic data rather than raw images. This enables accurate prediction of optimal beams for high mobility applications.
Potential Applications:
- Augmented & virtual reality (AR/VR)
- Autonomous vehicles
- Smart cities & infrastructure
- High-speed, low-latency wireless communication networks
- Vehicle-to-infrastructure (V2I) communication systems
Benefits and Advantages:
- Enhanced adaptability – improves functionality in dynamic environments
- Efficient data storage and transmission – focuses on environmental semantics
- Accurate beam prediction – demonstrated through experimental results
- Improved system responsiveness – prioritizes contextually relevant information
Related Publication: Environment Semantic Communication: Enabling Distributed Sensing Aided Networks
