TY - GEN
T1 - FlowDrone
T2 - 2023 IEEE International Conference on Robotics and Automation, ICRA 2023
AU - Simon, Nathaniel
AU - Ren, Allen Z.
AU - Pique, Alexander
AU - Snyder, David
AU - Barretto, Daphne
AU - Hultmark, Marcus
AU - Majumdar, Anirudha
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Unmanned aerial vehicles (UAVs) are finding use in applications that place increasing emphasis on robustness to external disturbances including extreme wind. However, traditional multirotor UAV platforms do not directly sense wind; conventional flow sensors are too slow, insensitive, or bulky for widespread integration on UAVs. Instead, drones typically observe the effects of wind indirectly through accumulated errors in position or trajectory tracking. In this work, we integrate a novel flow sensor based on micro-electro-mechanical systems (MEMS) hot-wire technology developed in our prior work [1] onto a multirotor UAV for wind estimation. Our sensor is omnidirectional (in the plane), lightweight, fast, and accurate. In order to achieve superior hover performance in windy conditions, we train a 'wind-aware' residual-based controller via reinforcement learning using simulated wind gusts and their aerodynamic effects on the drone. In extensive hardware experiments, we demonstrate the wind-aware controller out-performing two strong 'wind-unaware' baseline controllers in challenging windy conditions. See: youtu.be/KWqkH9Z-338.
AB - Unmanned aerial vehicles (UAVs) are finding use in applications that place increasing emphasis on robustness to external disturbances including extreme wind. However, traditional multirotor UAV platforms do not directly sense wind; conventional flow sensors are too slow, insensitive, or bulky for widespread integration on UAVs. Instead, drones typically observe the effects of wind indirectly through accumulated errors in position or trajectory tracking. In this work, we integrate a novel flow sensor based on micro-electro-mechanical systems (MEMS) hot-wire technology developed in our prior work [1] onto a multirotor UAV for wind estimation. Our sensor is omnidirectional (in the plane), lightweight, fast, and accurate. In order to achieve superior hover performance in windy conditions, we train a 'wind-aware' residual-based controller via reinforcement learning using simulated wind gusts and their aerodynamic effects on the drone. In extensive hardware experiments, we demonstrate the wind-aware controller out-performing two strong 'wind-unaware' baseline controllers in challenging windy conditions. See: youtu.be/KWqkH9Z-338.
UR - http://www.scopus.com/inward/record.url?scp=85168710537&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85168710537&partnerID=8YFLogxK
U2 - 10.1109/ICRA48891.2023.10160454
DO - 10.1109/ICRA48891.2023.10160454
M3 - Conference contribution
AN - SCOPUS:85168710537
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5393
EP - 5399
BT - Proceedings - ICRA 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 29 May 2023 through 2 June 2023
ER -