- After living through Hurricane Maria, which hit Puerto Rico in 2017, an IBM developer advocate created drone-based tech to avoid wasting lives in natural disasters.
- IBM hosts the brand new tool, DroneAid, and it’s open source.
- DroneAID uses visual feeds from drones to mark areas where people immediately require emergency services.
Pedro Cruz didn’t just pass though the wreckage that Hurricane Maria left in its path in Puerto Rico back in 2017. He watched the commotion in his hometown of San Juan by flying his drone overhead.
Maria made landfall on the southeast a part of the island around 8 p.m., Cruz recalls in an interview with Popular Mechanics. Once the storm subsided about 20 hours later, he began his mission to seek out his grandmother.
This content is imported from youTube. It’s possible you’ll have the opportunity to seek out the identical content in one other format, or it’s possible you’ll have the opportunity to seek out more information, at their site.
Because the infrastructure was completely decimated, he had no cellphone service to examine in on her. With only one quarter tank of gas left in his automotive, Cruz took a risk and drove the 25 miles it might take to locate her, he says.
“The road resulting in her house was all flooded,” says Cruz, 25, a self-taught computer programmer. “I had my drone and I flew it as much as [my grandmother’s] house. She heard the drone and waved out her window. She was alright.”
But not all were so lucky.
Rural destruction was especially tough on Puerto Ricans after Hurricane Maria hit. Helicopters flew over again and again, but didn’t see their sos signals.’
Over three million people were impacted by the Category 5 storm, but those in rural communities outside San Juan—like Humacao, on the eastern side of the island—felt probably the most strain. They were promised aid that never got here, Cruz says, in order that they began painting SOS signs like “food” and “water” on the bottom, in hopes of helicopters or planes noticing their cries.
But Cruz did not have a strategy to help the those who he saw.
So a 12 months later, he created DroneAID, software that uses artificial intelligence, powered by IBM Watson, to detect and count SOS messages on the bottom, fed by data from live drone feeds overhead.
The “Aha Moment”
After volunteering with one in every of the local nonprofits providing aid to rural Puerto Ricans, Cruz first noticed the hand-drawn SOS messages searching for food and water, which got his wheels turning. How could he be certain that helicopters would not miss people left behind after a disaster the following time something like this happened? How could he help people find their very own grandmothers?
“I had the ‘aha moment’ a few 12 months later when IBM got here to Puerto Rico,” for a coding hackathon, Cruz says. The goal was to create an answer for disaster recovery. All of it appeared to click, like gears fitting together in his brain.
“If there’s a way that we will mechanically assess a situation, we will save more people,” he thought. The thought prioritized not only speed of emergency responses, but additionally a more efficient system for providing aid.
As a volunteer, when Cruz brought water and supplies to homes, the recipients would thank him, but then tell him that the Red Cross or one other organization had already brought them supplies. This was problematic: Some folks were receiving double aid, and a few were receiving none.
If Cruz could use drones to flag places that also need assistance, rated by the extent of emergency, this sort of redundancy might be avoided, he thought.
How Drones Can Save Lives
Cruz’s system can mechanically plot the places where people require emergency services, by utilizing drone footage and AI.
DroneAID is powered by IBM’s AI powerhouse, Watson. It helped Cruz to coach his machine learning models, which took a number of iterations to get good.
First, he tried to write down “SOS” in his handwriting, which the model’s algorithms couldn’t read. So as an alternative, he trained his machine learning model to acknowledge the United Nations’s standardized humanitarian symbols. There are over 500 which have been released since 2012, and so they’re actually quite easy to discern.
As an alternative of setting fires and flooding streets to check DroneAID (or at the least finding crazy places to check the tech, like self-driving cars do), Cruz used a game engine to create simulated environments that look similar to real disasters. His fake floods and earthquakes were realistic enough to coach his AI system.
The system is now able to use, and any time a drone detects one in every of those UN humanitarian symbols, it creates a digitally generated map with icons showing where victims need assistance, in addition to the severity of every situation. That way, first responders can effectively prioritize their response.
Plus, connectivity is not any problem—key to disaster response, where infrastructure is often destroyed. The drones that Cruz is currently working with use their very own networking system, with GPS, 4G, and 5G all built-in.
Making Drones Open Source
Still, Cruz admits, there’s a protracted strategy to go along with DroneAID, which is partly why he decided to make the project open source for other developers.
Those coders could create a more nuanced app interface, or perhaps add latest sensors to drones like thermal imagery or lidar. The sheer amount of contributors could at the least make the present system more robust.
Cruz has one most important fear: that folks won’t adopt his system, leaving lives in danger. He’s giving workshops on DroneAID and the UN symbols to handle that problem. And he’s implementing more connectivity to other consumer drones so that people can generate more images that show areas in dire need.
He also wants diversity of disasters. Sure, he’s been through a hurricane and lived to inform the story, but what about other humanitarian crises?
“We would like to coach against other environments and make this embedded into all drones,” Cruz says. “Just as our iPhones have an SOS feature, imagine an SOS feature in your drone that’s connected to an app … and send it to first responders.”