Any drone pilot knows that navigating through tight spaces is tough. Consumer grade drones developed by companies like Skydio and DJI now have the sensors and software that make it possible for their aircraft to dodge obstacles while following a subject, but the team behind the GapFlyt project is upping the ante.
Obstacle avoidance without the sensors
Current drones on the market like the brand new DJI Mavic 2 feature plenty of obstacle avoidance sensors that help the drone see what’s around it. The drone Nitin J. Sanket and his team are using is the Parrot Bebop 2 equipped with an NVIDIA Jetson TX2 GPU that uses no obstacle avoidance sensors. This drone is on the cheaper side and came before a time where these sensors were being implemented in most drones.
The way this whole process works is through images taken by the Bebop. It takes multiple pictures to determine where the gap is and then makes its move through the opening at roughly 4.5mph. Take a look at the video below that highlights how the team from the University of Maryland was able to make this happen.
Although this is a pretty slow method of moving through obstacles, drones will no doubt become better at flying themselves and overcoming most obstacles through various improvements and overall, more research. It will be exciting to see what the GapFlyt team continues to deliver as they build upon what they have already started.
What do you think about GapFlyt’s research? Let us know in the comments below.
STAY IN TOUCH!
If you’d like to stay up to date with all the latest drone news, scoops, rumors and reviews, then follow us on Twitter, Facebook, YouTube, Instagram or sign up for our email newsletter DroneRise, that goes out every weekday morning at 6 am.
If you’d like to help us grow, you can buy your next drone through one of the following links directly from manufacturers, such as DJI, Parrot, Yuneec or retailers like Amazon, B&H, BestBuy or eBay. We will make a small commission and it will not cost you anything extra. Thank you!
Photo credit: Gapflyt