Drone Autonomously Avoiding Obstacles at 30 MPH

preview_player
Показать описание

Links to the research papers:

Andrew J. Barry and Russ Tedrake.
Pushbroom Stereo for High-Speed Navigation in Cluttered Environments.
In Proceedings of the 2015 IEEE International Conference on Robotics and Automation (ICRA), May 2015.

Andrew J. Barry, Helen Oleynikova, Dominik Honegger, Marc Pollefeys, and Russ Tedrake.
FPGA vs. Pushbroom Stereo Vision for MAVs. Vision-based Control and Navigation of Small Lightweight UAVs,
IROS Workshop, 2015.
Рекомендации по теме
Комментарии
Автор

I regularly fly airplanes with the fly-thu boxes or HITS (Highway-In-The-Sky) displayed on a flat screen display. It uses GPS and a terrain database to avoid obstacles and guide the pilot. You guys are using cameras. Great concept. I've often wondered when this technology would show up in drones. Nice!

birdmanm.
Автор

I think I like this project. Hard to tell since there are so many cuts in the video. I counted 36. That's ~4 seconds per shot on average.

BrianPeiris
Автор

I must say that's really awesome. I think you could combine quad propellers together with wings and tail if you want to tackle the dense Amazon forest. Thumbs up for the image processing and A.I.

ethanpng
Автор

Finally, something worthy of actually being called a drone.

r
Автор

That HUD reminds me of the drop ship going down to LV426 in the movie Aliens! Pretty neat!

BarnStangz
Автор

Great production on the video. I like the shot at 0:57 were you can see a third vehicle (probably a quadcopter) chase from above.

GotYourWallet
Автор

Excellent work. Looking forward to future progress on this project.

SYNFPVPILOT
Автор

Man this is so cool. Upload more of this!

natscorner
Автор

Did this with a Parrot AR Drone 2.0. and a little Javascript 3 years ago, only without the catapult. With The ability to program these drones, the possibilities are endless . - Inspired.

ndyaarthurmartha
Автор

Awesome work! Thank you for open sourcing the project - it will be fun to dig into :)

MiltonGeorges
Автор

Nice work and thanks for posting the research papers as well!
I hate to be that guy, but here's a quick feedback: the way the video was edited (speeding up the video playback, cutting off the scenes before the drones finish the maneuvers, etc.) puts big question marks to the actual results. It doesn't help with the credibility.

silvanojr
Автор

For Chrissake, Optimus. Ease off the music a bit wouldja?

markgolder
Автор

"Come on RC hurry up and get with the program." That autonomous plane was running off and leaving the chase plane. Impressive. Nice work.

MichaelSHartman
Автор

Really liked this video, thumbs up. Cheers from Sint Maarten

WeBeYachting
Автор

I bet the guy running in the background at 0:17 is the undergraduate researcher : )

BioRobotics
Автор

The "virtual tunnel" display is just so cool :o

Niohimself
Автор

Very cool but it hurt my brain to watch that footage. Do it with a multirotor so it's smooth?

JohnnyFPV
Автор

Nice technology. Horribly edited video.

JimNortonsAlcoholism
Автор

The interesting point is not the AI like ability to avoid obstacles but the detection ability that can interpret an object correctly however it's done.

xingthe-rubicon
Автор

wow! thats amazing! Well done guys! I hope techniques like these will soon be available for drones aswell. keep it up guys!

ramonteuling