Collaborative Research: NSF-MeitY: CNS Core: Small: Learning-Assisted Integrated Sensing, Communication and Security for 6G UAV Networks

Unmanned aerial vehicle (UAV)-enabled integrated sensing and communication (ISAC) have emerged as a promising technology for 6G wireless networks, aiming to improve user experience and enhance people’s lives. By leveraging millimeter wave (mmWave) communications, UAV-enabled ISAC systems are expected to deliver high-throughput, ultra-reliable, and low-latency wireless communications, along with highly accurate wireless sensing and localization within 6G networks. Simultaneously, artificial intelligence (AI) and machine learning (ML) are anticipated to transform platform-based ecosystems, business models, and services in future 6G networks. The key challenge is integrating UAV localization, mmWave communications, wireless sensing, and security with AI/ML for future 6G systems. A multidisciplinary team of six investigators from Auburn University (AU), Florida International University (FIU), the Indian Institute of Technology Kanpur (IIT Kharagpur), and the International Institute of Information Technology, Naya Raipur (IIIT, Naya Raipur) collaborate closely on a project focused on learning-assisted integrated sensing, communication, and security for 6G UAV networks. The educational plan of this project includes developing joint course materials on AI/ML for UAV networks and IoT, enhancing undergraduate and graduate-level courses at the participating institutions. Simulation tools and testbeds developed through this project offer students hands-on experience with cutting-edge technology. The project outcomes are disseminated via technical publications, conference keynotes/tutorials, IEEE distinguished lectures and seminars, a project website, and open-source repositories. The investigators are committed to encouraging participation from underrepresented groups through outreach programs at their institutions and the NSFBPC/REU/RET programs throughout the project. The project aims to develop deep learning (DL)-based localization and sensing in UAV mmWave networks, location-aided UAV mmWave communications, and joint UAV mmWave communication and radar co-design to improve mmWave spectrum utilization, wireless sensing performance, and UAV device security. The research agenda consists of five well integrated thrusts: (i) Learning-based mmWave UAV localization and wireless sensing; (ii) Joint design of location-aided UAV mmWave communications and sensing; (iii) Multiple UAV communications and sensing co-design; (iv) Learning-based RF fingerprinting for UAV security; and (v) Integration and assessment: the proposed techniques are implemented with both ray-tracing software tools (e.g., DeepMIMO), mmWave devices (e.g., TP-link Talon AD7200) and TI mmWave radars, Parrot AR Drone2.0 UAV, programmable (e.g. USRP) devices, and the NSF PAWR AERPAW testbed, and validated with extensive experiments in real, representative outdoor and indoor environments. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.