Florian Achermann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Florian Achermann has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Nicholas Lawrance
Autonomous Systems Lab, ETH Zurich, Zurich 8092, Switzerland
3 shared publications Roland Siegwart
Autonomous Systems Lab ETH Zürich Zürich Switzerland
2 shared publications- Roland Siegwart
Autonomous Systems Lab (ASL), ETH Zürich, Zürich, Switzerland
2 shared publications Andrey Kolobov
Microsoft Research, One Microsoft Way, Redmond, USA
1 shared publication- Bogdan Andrei Danciu
CAPS Laboratory, Department of Mechanical and Process Engineering 1 , ETH Zürich, 8092 Zürich
1 shared publication - Jaeyoung Lim
Autonomous Systems Lab, ETH Zrich, Zrich, Switzerland
1 shared publication
Latest Publications
- Open Access
- 15 August 2025
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 151 (773)
Evaluating machine‐learning models for wind‐speed downscaling from ECMWF‐IFS data
Accurate weather forecasts rely on computationally intensive high‐resolution models solving partial differential equations (PDEs) explicitly on a fine grid. Traditionally, downscaling is used to achieve a reduction of the computational cost by first solving a lower‐resolution weather model, providing the boundary conditions for a regional high‐resolution weather model. In recent years, the use of machine learning has been investigated to accelerate weather prediction further through learning the mapping from low‐resolution inputs to high‐resolution predictions—known as super‐resolution methods. In this work, we benchmark recent super‐resolution approaches used previously for downscaling wind predictions as well as new transformer‐based architecture on a novel dataset, with a large variety of input variables, consisting of European Centre for Medium‐Range Weather Forecasts Integrated Forecasting System (ECMWF‐IFS) data and predictions from a high‐resolution regional weather model over Switzerland, and test the generalization performance on weather forecasts from additional locations across Europe. We investigate the relevance of each input variable when downscaling wind further and propose Windflow‐SRnet, a transformer‐based neural network. Using the high‐resolution model as label, the proposed (and best‐performing) machine‐learning model resulted in an average wind‐speed prediction error of on a held‐out test set, a 35% reduction compared with the error for downscaling using linear interpolation.
- 15 August 2025
- Published by Wiley in Quarterly Journal of the Royal Meteorological Society
- Vol. 151 (773)
Open AccessEvaluating machine‐learning models for wind‐speed downscaling from ECMWF‐IFS data
Accurate weather forecasts rely on computationally intensive high‐resolution models solving partial differential equations (PDEs) explicitly on a fine grid. Traditionally, downscaling is used to achieve a reduction of the computational cost by first solving a lower‐resolution weather model, providing the boundary conditions for a regional high‐resolution weather model. In recent years, the use of machine learning has been investigated to accelerate weather prediction further through learning the mapping from low‐resolution inputs to high‐resolution predictions—known as super‐resolution methods. In this work, we benchmark recent super‐resolution approaches used previously for downscaling wind predictions as well as new transformer‐based architecture on a novel dataset, with a large variety of input variables, consisting of European Centre for Medium‐Range Weather Forecasts Integrated Forecasting System (ECMWF‐IFS) data and predictions from a high‐resolution regional weather model over Switzerland, and test the generalization performance on weather forecasts from additional locations across Europe. We investigate the relevance of each input variable when downscaling wind further and propose Windflow‐SRnet, a transformer‐based neural network. Using the high‐resolution model as label, the proposed (and best‐performing) machine‐learning model resulted in an average wind‐speed prediction error of on a held‐out test set, a 35% reduction compared with the error for downscaling using linear interpolation.
- Open Access
- 25 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-17
WindSeer: real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle
Real-time high-resolution wind predictions are beneficial for various applications including safe crewed and uncrewed aviation. Current weather models require too much compute and lack the necessary predictive capabilities as they are valid only at the scale of multiple kilometers and hours – much lower spatial and temporal resolutions than these applications require. Our work demonstrates the ability to predict low-altitude time-averaged wind fields in real time on limited-compute devices, from only sparse measurement data. We train a deep neural network-based model, WindSeer, using only synthetic data from computational fluid dynamics simulations and show that it can successfully predict real wind fields over terrain with known topography from just a few noisy and spatially clustered wind measurements. WindSeer can generate accurate predictions at different resolutions and domain sizes on previously unseen topography without retraining. We demonstrate that the model successfully predicts historical wind data collected by weather stations and wind measured by drones during flight.
- 25 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-17
Open AccessWindSeer: real-time volumetric wind prediction over complex terrain aboard a small uncrewed aerial vehicle
Real-time high-resolution wind predictions are beneficial for various applications including safe crewed and uncrewed aviation. Current weather models require too much compute and lack the necessary predictive capabilities as they are valid only at the scale of multiple kilometers and hours – much lower spatial and temporal resolutions than these applications require. Our work demonstrates the ability to predict low-altitude time-averaged wind fields in real time on limited-compute devices, from only sparse measurement data. We train a deep neural network-based model, WindSeer, using only synthetic data from computational fluid dynamics simulations and show that it can successfully predict real wind fields over terrain with known topography from just a few noisy and spatially clustered wind measurements. WindSeer can generate accurate predictions at different resolutions and domain sizes on previously unseen topography without retraining. We demonstrate that the model successfully predicts historical wind data collected by weather stations and wind measured by drones during flight.
- 22 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4599-4606
Safe Low-Altitude Navigation in Steep Terrain With Fixed-Wing Aerial Vehicles
Fixed-wing aerial vehicles provide an efficient way to navigate long distances or cover large areas for environmental monitoring applications. By design, they also require large open spaces due to limited maneuverability. However, strict regulatory and safety altitude limits constrain the available space. Especially in complex, confined, or steep terrain, ensuring the vehicle does not enter (ICS) can be challenging. In this work, we propose a strategy to find safe paths that do not enter (ICS) while navigating within tight altitude constraints. The method uses periodic paths to efficiently classify (ICS). A sampling-based planner creates collision-free and kinematically feasible paths that begin and end in safe periodic (circular) paths. We show that, in realistic terrain, using circular periodic paths can simplify the goal selection process by making it yaw agnostic and constraining yaw. We demonstrate our approach by dynamically planning safe paths in real-time while navigating steep terrain on a flight test in complex alpine terrain.
- 22 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (5) , 4599-4606
Safe Low-Altitude Navigation in Steep Terrain With Fixed-Wing Aerial Vehicles
Fixed-wing aerial vehicles provide an efficient way to navigate long distances or cover large areas for environmental monitoring applications. By design, they also require large open spaces due to limited maneuverability. However, strict regulatory and safety altitude limits constrain the available space. Especially in complex, confined, or steep terrain, ensuring the vehicle does not enter (ICS) can be challenging. In this work, we propose a strategy to find safe paths that do not enter (ICS) while navigating within tight altitude constraints. The method uses periodic paths to efficiently classify (ICS). A sampling-based planner creates collision-free and kinematically feasible paths that begin and end in safe periodic (circular) paths. We show that, in realistic terrain, using circular periodic paths can simplify the goal selection process by making it yaw agnostic and constraining yaw. We demonstrate our approach by dynamically planning safe paths in real-time while navigating steep terrain on a flight test in complex alpine terrain.
- 8 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 31 (2) , 26-38
Reinforcement Learning for Outdoor Balloon Navigation: A Successful Controller for an Autonomous Balloon
Autonomous ballooning allows for energy-efficient long-range missions but introduces significant challenges for planning and control algorithms, due to their single degree of actuation: vertical rate control through either buoyancy or vertical thrust. Lateral motion is typically due to the wind; thus, balloon flight is both nonholonomic and often stochastic. Finally, wind is very challenging to sense remotely, and estimates are often available only via low-temporal-and-spatial-frequency predictions from large-scale weather models and direct in situ measurements. In this work, reinforcement learning (RL) is used to generate a control policy for an autonomous balloon navigating between 3D positions in a time- and spatially varying wind field. The agent uses its position and velocity, the relative position of the target, and an estimate of the surrounding wind field to command a target altitude. The wind information contains local measurements and an encoding of global wind predictions from a large-scale numerical weather prediction (NWP) model around the current balloon location. The RL algorithm used in this work, the soft actor–critic (SAC), is trained with a reward favoring paths that reach as close as possible to the target, with minimum time and actuation costs. We evaluate our approach first in simulation and then with a controlled indoor experiment, where we generate an artificial wind field and reach a median distance of 23.4 cm from the target within a volume of 3.5 × 3.5 × 3.5 m over 30 trials. Finally, using a fully autonomous custom designed outdoor prototype capable of controlling altitude, long-range communication, redundant localization, and onboard computation, we validate our approach in a real-world setting. Over six flights, the agent navigates to predefined target positions, with an average target distance error of 360 m after traveling approximately 10 km within a volume of 22 × 22 × 3.2 km.
- 8 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 31 (2) , 26-38
Reinforcement Learning for Outdoor Balloon Navigation: A Successful Controller for an Autonomous Balloon
Autonomous ballooning allows for energy-efficient long-range missions but introduces significant challenges for planning and control algorithms, due to their single degree of actuation: vertical rate control through either buoyancy or vertical thrust. Lateral motion is typically due to the wind; thus, balloon flight is both nonholonomic and often stochastic. Finally, wind is very challenging to sense remotely, and estimates are often available only via low-temporal-and-spatial-frequency predictions from large-scale weather models and direct in situ measurements. In this work, reinforcement learning (RL) is used to generate a control policy for an autonomous balloon navigating between 3D positions in a time- and spatially varying wind field. The agent uses its position and velocity, the relative position of the target, and an estimate of the surrounding wind field to command a target altitude. The wind information contains local measurements and an encoding of global wind predictions from a large-scale numerical weather prediction (NWP) model around the current balloon location. The RL algorithm used in this work, the soft actor–critic (SAC), is trained with a reward favoring paths that reach as close as possible to the target, with minimum time and actuation costs. We evaluate our approach first in simulation and then with a controlled indoor experiment, where we generate an artificial wind field and reach a median distance of 23.4 cm from the target within a volume of 3.5 × 3.5 × 3.5 m over 30 trials. Finally, using a fully autonomous custom designed outdoor prototype capable of controlling altitude, long-range communication, redundant localization, and onboard computation, we validate our approach in a real-world setting. Over six flights, the agent navigates to predefined target positions, with an average target distance error of 360 m after traveling approximately 10 km within a volume of 22 × 22 × 3.2 km.