ABSTRACT

With the approach of the golden jubilee of the first mobile phone call made in 1973, it is astonishing to see how far wireless technology has come. More recently, the confluence of computing and communications has transformed wireless devices from merely communication devices into powerful computing and sensing platforms. Enabled by these capabilities and equipped with state-of-the-art sensors, cameras, and other non-radio frequency (non-RF) modalities, modern wireless devices are able to simultaneously perform multiple functions including communications, computing, and imaging. In order to exploit synergies across these functions, this project brings together a synergistic US-Finland team with the goal of laying the fundamental science needed to pioneer a novel paradigm of vision-guided wireless system design using which wireless devices can "view" and map their surrounding wireless environment and its features by fusing heterogeneous multimodal information sensed through their RF and non-RF capabilities. Under this new paradigm, wireless network devices can leverage diverse, sensed information about their environment in order to more effectively communicate and compute. This transformative concept contributes towards boosting the performance of future wireless systems (e.g., 6G) thus paving the way for new wireless applications with tangible societal impact, including advanced extended reality, drones, and connected autonomy. The research is coupled with a suite of collaborative education activities between the US and Finnish partners that involve transfer of ideas, joint tutorials and workshops, outreach events, joint mentoring of students, as well as broad dissemination efforts that help train a workforce skilled in advanced wireless communications and machine learning research.

This project develops a novel holistic framework that merges tools from machine learning, distributed optimization, communication theory, and wireless networking to yield key contributions: 1) Systematic approach that merges signal processing techniques with emerging machine learning frameworks in order to fuse heterogeneous information from multiple RF and non-RF modalities for faithfully mapping dynamic wireless environments, 2) New approaches for efficient wireless system design with specific emphasis on new communication strategies for vision-guided networking, 3) A novel framework that advances tools from distributed learning to develop new self-organizing algorithms that can perform cross-layer optimization of wireless functions and resources (e.g., spectrum, power, time) with minimal information exchange, 4) Fundamental analysis of the various properties and tradeoffs involved in the designed learning and optimization algorithms, and 5) Realistic validation of the proposed solutions using a mix of simulation and experimental tools.

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.

Please report errors in award information by writing to: awardsearch@nsf.gov.