Infrastructure monitoring in communications-constrained areas
By René Andrés García Franceschini ’19
During one of the first weeks of the fall semester of my junior year, I had a call with Andrew Weinert, a researcher at the Lincoln Laboratory, to try to narrow down what my SuperUROP project would be. Weinert works on the use of small Unmanned Aerial Systems (sUASs) to gather information after emergency situations. Emergency situations were in no short supply those days: Hurricanes Harvey and Irma had come and gone, and Hurricane Maria had just hit Dominica.
Knowing that Maria was a day away from devastating my home in Puerto Rico, Weinert suggested that I take this experience as motivation for improving emergency response in these devastated islands. Having personally been affected by the collapse of the communications infrastructure back home (I did not hear from my family for almost a week), I saw the importance of having effective emergency response in communications-constrained areas.
I thus decided to work with Professor Saurabh Amin on the use of sUASs for infrastructure monitoring in communications-constrained or -restricted areas, especially after emergency situations. Currently, sUASs are becoming more common in infrastructure inspections because of their increased levels of access and safety, compared to a human inspector. sUASs are currently being developed so that they can be controlled through GPS and 4G LTE signal, which opens the door to the possibility of automatically routed teams of drones carrying out tasks. However, because 4G LTE coverage can be variable after emergencies, my work tried to figure out better ways to route sUASs while accounting for this uncertainty.
To achieve this goal, I used an approach that combines tools for vehicle routing and geo-statistics. First, I adapted algorithms used for routing teams of agents that need to visit as many points of interest as possible to my scenario. Second, I introduced a kriging step, which attempts to predict the communications signal strength of unobserved locations based on all the locations that have been observed. This allowed the sUASs to simultaneously inspect nodes and learn about the communications-space of the map. In the end, this resulted in improved performance in terms of how many points of interest are inspected, how much computational time is required to make good solutions, and how many sUASs make it back to home base before time runs out.
Of course, conducting research is hardly meaningful if you cannot convey the information to others. Thankfully, the second half of SuperUROP is learning about different genres and means of communicating your work. Through SuperUROP, I got to engage with hundreds of other students carrying out research in fields that are opposite to my own, and I got to see what it was like to communicate research across academic fields. I also had the opportunity to network with amazing professors and industry leaders that are on the cutting edge of scientific research. And all of this while making $25 an hour.
Presenting my research during a SuperUROP poster session
Towards the end of the program, I was invited to record a short video about my experience. In the video, the interviewer asked me if I was doing this project because of Hurricane Maria. The reality was that I had discussed this project with Saurabh in May 2017, months before Maria even existed. However, through ridiculous serendipity my project evolved into the sole topic that I wanted to work on this year. In my work with Saurabh, I was able take a problem with real-world implications, model it, and use my Course 1 skillset to chip just the tiniest bit of it.