CAREER: Wireless Collaborative Mixed Reality Networking: Foundations and Algorithms for Joint Communication, Computation, and Learning

Wireless collaborative mixed reality (WCMR) provides an interactive and immersive experience for a group of people that can move freely in an open space and will potentially revolutionize existing collaborative mission-critical training, such as firefighter drills and disaster response training. In order to provide the best immersive experience, WCMR differs drastically from traditional wireless applications in that they demand not only coordinated information to be transferred to collaborating agents in real-time but also fast computations in mobile mixed reality devices. Hence, WCMR requires fundamentally different designs than existing approaches that mainly focus on communication demands and predominantly assume that they are independently generated at different network agents. This project aims to develop joint communication, computation, and learning algorithms that explicitly exploit unique characteristics of WCMR and support emerging WCMR applications. Research outcomes from this CAREER project are constantly integrated into both undergraduate and graduate courses taught by the PI. This CAREER project also establishes outreach programs for both K-12 and college students to be exposed to state-of-the-art wireless and mixed reality technologies.

Different from traditional wireless networks, the design of efficient WCMR needs to enable both concurrent wireless communications and fast computations. Therefore, the system performance relies heavily on the extremely low-delay completion of all concurrent communication and computation tasks across the network, instead of independent communication tasks as in traditional wireless networks. As such, the proposed research is organized into the following three interdependent thrusts: (i) Serving concurrent WCMR traffic. This thrust focuses on the communication aspect of WCMR and will establish analytical foundations of adaptive algorithm design that efficiently serves the concurrent traffic with the goal of optimizing throughput, latency, and seamless user experience. (ii) Offloading compute-intensive WCMR tasks. This thrust addresses both communication and computation needs of WCMR, and will develop joint offloading and scheduling schemes that significantly boost the performance of WCMR to alleviate heavy computations in mobile mixed reality devices by leveraging powerful servers. (iii) Leveraging predictable WCMR user behavior. This thrust focuses on joint communication, computation, and learning design, and will further enhance network performance by exploiting predictable user behavior. Finally, we will implement the algorithms developed in this project in our existing platforms, and evaluate their corresponding performance.

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.