Loading…
This event has ended. View the official site or create your own event → Check it out
This event has ended. Create your own
Learn more about the event and register now!
View analytic
Wednesday, October 12 • 11:45 - 12:35
Efficient Visual Avoidance and Control for UAVs with Embedded GPUs - Kabir Mohammed, UASys

Sign up or log in to save this to your schedule and see who's attending!

Indoor and outdoor navigation for small UAVs like quadrotors is still far from being a solved problem and most research and demonstration of visual navigation solutions have been conducted on traditional CPU architectures. Due to high computation demands of a full vision-based navigation stack (depth extraction, odometry, mapping, planning and control) a heavy and often power-hungry onboard computer is needed to simultaneously run all the tasks onboard.

For this presentation, we demonstrate a quadrotor UAV equipped with Nvidia's Jetson TX1 embedded GPU compute module and high-speed vision system, running our complete navigation stack onboard, at a tenth of the weight and power consumption. Our compact quadrotor is capable of tight, fast maneuvers and safe GPS-denied indoor hover, with onboard mapping, sense-and-avoid, precision landing and HD streaming.

Speakers
avatar for Kabir Mohammed

Kabir Mohammed

Co-founder and Technical Lead, UASys
I'm Kabir, a 18 year old student from India. I've worked with various open-source flight-control projects since 2007. I'm currently an active developer for PX4 Pro Autopilot project. I'm currently working on Artemis, my micro-aerial-vehicle research project on making autonomous obstacle avoidance and GPS-denied navigation possible for small multi-rotor craft. Our software stack is freely available on GitHub for anyone to replicate a similar... Read More →


Wednesday October 12, 2016 11:45 - 12:35
Salon 21 Dublin - Level 2
  • Experience Level Any

Attendees (42)