Situational Awareness Through Walls With Everyday RF Signals
Abstract
Situational awareness through walls is an important enabling capability for many applications. Assessing the situation through walls, however, is a considerably challenging and unsolved problem. In this research work, we propose a new foundation that can enable, for the first time, everyday Radio Frequency (RF) signals, such as WiFi, to build a complete situational awarenessthrough walls. Our approach is multi-disciplinary spanning wireless ommunications, robotics, and vision. More specifically, our proposed foundation has four underlying components. First, we propose a new methodology to translate the vast already-available vision data, e.g., several videos that arefreely available, to the RF domain. This enables us to instantly create a very large RF dataset, encompassing many different situations, for the purpose of analysis, training, and design, something that would have been infeasible if it had to be manually collected. Second, we propose a multi-dimensional signal processing pipeline, spanning time, frequency, and space domains, in conjunction with machine learning, in order to characterize and extract keyfeatures/signatures from the RF data pertaining to different situations. The number and location of the transmitting and receiving antennas can play a key role in the performance of RF-based situational awareness. In the third objective, we thus propose to use unmanned vehicles to emulate a large number of RF transmitter/receiver positions and enable the correspondingantenna position optimization via proper path planning. Finally, we run several experiments to validate the proposed foundation and understand its fundamental capabilities and limitations as a function of the given resources and complexity of the task. To the best of our knowledge, there is little work in the literature that has focused on enabling complete situational awareness in thismanner. Situational awareness is central to many applications as it is key to disaster relief, search and rescue, surveillance, and security missions. In particular, the ability to establish a situation through walls can be a considerably useful asset. The goal of the proposed work is to enable complete situational awareness through walls, which can significantly impact the aforementionedapplications. Furthermore, by bringing a foundational understanding to the capabilities and limitations of RF-based situational awareness, this work can provide a clear guideline for designing an RF-based system that can achieve the needed level of performance. This work further proposes to use unmanned vehicles to optimize the performance of RF-based situational awareness via proper path planning, thus making it immediately applicable to human-robotnetworks. Overall, this research effort can enable the successful deployment of a completethrough-wall situational awareness system, which can impact many applications.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Aug 31, 2020
- Source ID
- N000142012779
Entities
People
- Yasamin Mostofi
Organizations
- Office of Naval Research
- United States Navy
- University of California, Santa Barbara