The field of wireless communication for autonomous systems is rapidly evolving, with a focus on improving the efficiency and reliability of data transmission. Recent developments have highlighted the importance of statistical modeling and machine learning approaches in optimizing network performance. The use of statistical traffic models can reduce the complexity of simulations and improve the design of wireless networks. Additionally, machine learning-based approaches have shown promise in predicting network performance and improving quality of service. These advancements have the potential to enhance the safety and efficiency of autonomous systems, such as autonomous vehicles and aviation communication systems. Noteworthy papers include:
- SkyNetPredictor, which proposes a machine learning-based approach for pre-flight network performance predictions in avionic communication systems.
- BAROC, which presents a framework for concealing packet losses in Low-Earth Orbit satellite networks, achieving significant improvements in video quality.
- Improving QoS Prediction in Urban V2X Networks, which leverages data from leading vehicles and historical trends to improve the prediction of downlink throughput in urban environments.