Uploaded March 2019 | Updated November 2026, 19 minutes ago
By Florian Achermann, Nicholas R.J. Lawrance, René Ranftl, Alexey Dosovitskiy, Jen Jen Chung and Roland Siegwart.
This work was supported by the Intel Network on Intelligent Systems.
ABSTRACT: Obtaining an accurate estimate of the local wind remains a significant challenge for small unmanned aerial vehicles (UAVs). Small UAVs often operate at low altitudes near terrain, where the wind environment can be more complex than at higher altitudes. Combined with their relatively low mass, this makes small UAVs particularly susceptible to wind. In this paper we present an approach for predicting high-resolution wind fields based on a terrain elevation model and known inflow conditions. Our approach uses a deep convolutional neural network (CNN) to generate 3D wind estimates. We show that our approach produces wind estimates with lower prediction error than existing methods, and that inference can be performed on an on-board computer in less than two seconds. By providing the wind estimate to a sampling-based planner we show that the improved estimates allow the planner to generate safer paths in strong wind scenarios than with alternative wind estimation techniques.
By Florian Achermann, Nicholas R.J. Lawrance, René Ranftl, Alexey Dosovitskiy, Jen Jen Chung and Roland Siegwart.
This work was supported by the Intel Network on Intelligent Systems.
ABSTRACT: Obtaining an accurate estimate of the local wind remains a significant challenge for small unmanned aerial vehicles (UAVs). Small UAVs often operate at low altitudes near terrain, where the wind environment can be more complex than at higher altitudes. Combined with their relatively low mass, this makes small UAVs particularly susceptible to wind. In this paper we present an approach for predicting high-resolution wind fields based on a terrain elevation model and known inflow conditions. Our approach uses a deep convolutional neural network (CNN) to generate 3D wind estimates. We show that our approach produces wind estimates with lower prediction error than existing methods, and that inference can be performed on an on-board computer in less than two seconds. By providing the wind estimate to a sampling-based planner we show that the improved estimates allow the planner to generate safer paths in strong wind scenarios than with alternative wind estimation techniques.



![Visual-inertial teach and repeat powered by Google Tango
Visual-Inertial Teach and Repeat for Aerial Inspection
M Fehr, T Schneider, M Dymczyk, J Sturm, R Siegwart
Arxiv: https://arxiv.org/abs/1803.09650
Submitted to:
Workshop on Aerial Robotic Inspection and Maintenance
International Conference on Robotics and Automation 2018
Related Publications:
Real-time visual-inertial mapping, re-localization and planning onboard MAVs in unknown environments
M Burri, H Oleynikova, MW Achtelik, R Siegwart
A robust and modular multi-sensor fusion approach applied to mav navigation
S Lynen, MW Achtelik, S Weiss, M Chli, R Siegwart
Linear vs Nonlinear MPC for Trajectory Tracking Applied to Rotary Wing Micro Aerial Vehicles
M Kamel, M Burri, R Siegwart
Related Videos:
https://www.youtube.com/watch?v=tuUMwcTJx8s
https://www.youtube.com/watch?v=Ot76i9p2ZZo
https://www.youtube.com/watch?v=lrGSwAPzMOQ
Contact:
marius.fehr[at]mavt.ethz.ch
thomas.schneider[at]mavt.ethz.ch Visual-inertial teach and repeat powered by Google Tango](https://i.ytimg.com/vi/pDlQXsOrgI4/mqdefault.jpg)






