Descripción del proyecto
The rise of applications like smart cities and augmented reality has emphasized the critical importance of precise, low-latency localization and sensing (L&S) in the context of 6G communications. Meeting L&S demands involves inundating transceivers with extensive data from sources like pilot signals and sensors, creating redundancy that overwhelms communication networks. Addressing this redundancy is a key aspect of semantic communications, aiming to enhance energy efficiency and support 6G technology. Semantic communications prioritize transmitting useful information over mere data transmission. SAILS-6G's goal is to improve the energy efficiency of L&S without compromising utility by leveraging the principles of semantic communications. Historically, L&S optimization has focused on primary KPIs, such as accuracy, neglecting energy efficiency. SAILS-6G bridges this gap by integrating energy efficiency into L&S optimization through three WPs: WP1 addresses energy-constrained optimization issues using optimization theory tools. WP2 tackles complex nonlinear optimization challenges from WP1, employing learning structures. WP3 extends energy-efficient L&S algorithms from WP1 and WP2, considering distributed processing and privacy constraints. The applicant's expertise in information theory, optimization theory, and privacy-preserving learning, along with the supervisor's localization knowledge, supports these WPs. The outcome is optimized transceivers, reducing energy consumption while meeting L&S requirements. Their performance is evaluated against traditional methods and theoretical bounds. The ultimate aim is to introduce a groundbreaking framework for semantic L&S widely accepted in the scientific community, marking a significant field advancement. Building this framework boosts the applicant's scientific impact and strengthens his managerial, educational, and research skills, facilitated by the supervisor's network, advancing his journey towards a professorship.