Autonomous Natural Disaster Relief Robotics

Introduction:

We are an undergraduate research group with a focus on designing, prototyping, and developing affordable unmanned aerial vehicles (UAVs) for the purpose of locating humans during floods. Each year, tens of thousands of people are the victims of natural disasters. People living in underprivileged nations are at a much greater risk of dying from these disasters, in part due to a lack of immediately available resources. Rescue systems such as helicopters and search planes, while effective in covering a wide area, are expensive to purchase and operate. This limits which nations can use the systems. 

Our solution:

As part of the Gemstone Honors Program at the University of Maryland, we aim to promote equity in disaster relief by designing search and rescue UAVs which are cheaper than the current market alternatives, so that nations with lower GDPs are able to afford them. To achieve this, the team will use commercial systems. The rise of DIY quadcopters as a hobby has led to a significant decrease in the cost of UAV components. Furthermore, developments in computer vision (CV) systems allow for the automatic detection of survivors. Such a system means the UAV can be directly integrated into rescue teams without increasing workload.

What will team ANDRR be doing?

Over the course of our research, the team will develop the various systems that make up a rescue UAV, with a focus on reducing cost wherever possible. This includes materials such as a camera detection system, autopilot, and radio links. After these systems are complete, the team will integrate them into a final product capable of utilizing CV to search a given area for survivors. 

Your donations will go towards the components used in our UAV, allowing the team to test a wide variety of components to ensure we produce the most cost-effective system possible.

Progress so far:

    Up to this point, the team has been focused on exploring the basics of UAV and CV systems. We’ve begun to develop a CV system for use on a raspberry pi, a low cost processor. You can see the results of this system in the slideshow. Moving forward we aim to increase the processing speed using advanced computer chips. The team has also begun testing a number of quadcopter components, from motors to radio control systems. Team ANDRR has inherited a few quadcopters from previous Gemstone teams, ARMIT and SWARM-AI. While these systems require updating, they serve as a good starting point for component testing. Your donations will help the team update these systems with more capable and modern components.

Gifts in support of the University of Maryland are accepted and managed by the University of Maryland College Park Foundation, Inc., an affiliated 501(c)(3) organization authorized by the Board of Regents. Contributions to the University of Maryland are tax deductible as allowed by law. Please see your tax advisor for details.