October 20-21, 2023 | New Orleans, Louisiana
View More Details & Registration

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for PX4 Developer Summit 2023 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Central Daylight Time (CDT / UTC-5). To see the schedule in your preferred timezone, please select from the drop-down menu to the right above "Filter by Date."

IMPORTANT NOTE: The timing of sessions is subject to change.

Sunday, October 22 • 2:50pm - 3:20pm
Powered by PX4: Learned UAV Gust Rejection with Fast, Hot-Wire Flow Sensors - Nathaniel Simon, Princeton University

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Unmanned aerial vehicles (UAVs) have enormous potential in domains such as search and rescue, infrastructure inspection, and package delivery. Each of these applications require performance in real-world conditions, including extreme wind and gusts. This remains a challenge for traditional multirotor platforms, which do not directly sense wind; conventional flow sensors are too slow, insensitive, or bulky for widespread integration on multirotor UAVs. Instead, drones typically observe the effects of wind indirectly through accumulated errors in position or trajectory tracking. To address this, Princeton University researchers integrated a novel flow sensor based on micro-electro-mechanical systems (MEMS) hot-wire technology onto a multirotor UAV powered by the PX4 Autopilot. To demonstrate the performance improvements enabled by fast flow sensing in windy conditions, a ‘wind-aware’ controller was trained using reinforcement learning in simulated wind gusts. Using PX4’s Offboard Mode and the ROS2 bridge, the wind-aware controller fuses the fast flow sensor data for autonomous gust rejection. In extensive hardware experiments, the wind-aware controller demonstrates improvements in gust rejection over baseline controllers in challenging windy conditions.

avatar for Nathaniel Simon

Nathaniel Simon

PhD Student, Princeton University
Nathaniel Simon is a robotics PhD Candidate at Princeton University in the Intelligent Robot Motion Lab and the Turbulence Group. He works to improve unmanned aerial vehicle (UAV) performance in the real-world: from designing flow sensors for fast gust rejection, to leveraging computer... Read More →

Sunday October 22, 2023 2:50pm - 3:20pm CDT
Celestin C
  Breakout Sessions
  • Presentation Slides Attached Yes