Research Projects


Long-term River Monitoring

In Europe, many river beds have been very strongly modified over the industrial revolution to act as drainage without real long term thoughts. Some of these rivers are now being "renaturalized" to improve their flood control and other environment services. This is achived by re-creating meanders or removing dams, but there is a lack of tools to monitor the effect of these changes on the river bed, shores and vegetation over time. The objective of the project will be to build tools to monitor, document and quantify the evolution of small rivers after large strutural work (dam removal, re-creation of meanders): we will record reference state using a street-view-like recording back-pack (laser, cameras, IMU, GPS) and then do regular surveys to build a 4D spatio-temporal model of these environments over 12 months or more. The challenges will be to obtain a precise 3D mapping of a natural/vegetal environment with very complex 3D structure and lighting conditions, as well as the temporal alignment of these dynamic environments to observe and monitor changes over time. Ultimately, we expect to be able to "fly" through the model in space and time using VR equipment.

This project is supported by the French region "Grand Est", the Water Agency for the Rhine and Meuse Watershed and the Zone Atelier Moselle.

Pictures coming soon...


Lakeshore Monitoring

The data related to this project is available on the Symphony Lake Dataset: a 3-year spatio-temporal survey of a 1km lake shore using an autonomous surface vessel.

View Larger Map

The goal of this first project is to monitor the shore of the Lake Symphonie in Metz, France with high-frequency over a significant time scale, using our Kingfisher platform. From these dataset, it will be possible to build an history of geo-referenced changes. This project is a stepping stone towards the deployment of the Kingfisher in more complex or more relevant missions. This will let us develop the autonomy component required for any real mission, test them in real scenarios and make sure their robustness level is satisfactory.

An example of the data we capture can be found in the following summary:


Sometimes a curious swan comes to see us:


Illustration of the lakeshore dataset we are collecting:


Automatically aligned timelapse accross seasons (S. Griffith):


Flourish: Aerial Datat Collection and Analysis and Automated Ground Intervention for Precision Farming

Flourish, started in April 2015, is a European Project coordinated by the Autonomous Systems Lab at ETH Zürich (Switzerland) with a focus on aerial and ground robotics for precision farming. The project abstract can be found below:

To feed a growing world population with the given amount of available farm land, we must develop new methods of sustainable farming that increase yield while reducing reliance on herbicides and pesticides. Precision agricultural techniques seek to address this challenge by monitoring key indicators of crop health and targeting treatment only to plants that need it. This is a time consuming and expensive activity and while there has been great progress on autonomous farm robots, most systems have been developed to solve only specialized tasks. This lack of flexibility poses a high risk of no return on investment for farmers. The goal of the Flourish project is to bridge the gap between the current and desired capabilities of agricultural robots by developing an adaptable robotic solution for precision farming. By combining the aerial survey capabilities of a small autonomous multi-copter Unmanned Aerial Vehicle (UAV) with a multi-purpose agricultural Unmanned Ground Vehicle, the system will be able to survey a field from the air, perform targeted intervention on the ground, and provide detailed information for decision support, all with minimal user intervention. The system can be adapted to a wide range of crops by choosing different sensors and ground treatment packages. This development requires improvements in technological abilities for safe accurate navigation within farms, coordinated multi-robot mission planning that enables large field survey even with short UAV flight times, multispectral three-dimensional mapping with high temporal and spatial resolution, ground intervention tools and techniques, data analysis tools for crop monitoring and weed detection, and user interface design to support agricultural decision making. As these aspects are addressed in Flourish, the project will unlock new prospects for commercial agricultural robotics in the near future.

The Flourish project will use the Bonirob autonomous ground robot:


Ros Task Manager

Developing a complete robotic system often requires combining multiple behaviours into a complex decision grid, with elements running in sequence or in parallel, eventually interrupting each others.

To solve this “age-old” problem, ROS provides two main tools:

  • Actionlib: a client-server architecture that provides a way to specify results to be achieved. While the server works on these results, it should report progresses and ultimately report when the task is completed.
  • Smach: a python API to define complex state machines. It can interact with ROS services and actions to define a complex behaviour, including nesting, interruptions and concurrence.

Combining Smach and Actionlib, one could build arbitrarily complex systems. Hence, why would another task management system be necessary?

The main argument in favour of our task scheduler is the simplicity of its use, particularly in comparison with Actionlib. As usual, simplicity is a trade-off against expressiveness. Simplicity can be sacrificed by linking our task scheduler with Actionlib and/or Smach to exploit the best of both worlds.

Our task manager is presented in a small article on HAL, and the framework is available on github. The video below illustrates what it can do in the context of a UAV-UGV collaboration inspired by the needs from the Flourish project (thanks to Badr El Hafidi for preparing the video).


Noptilus: Autonomous Navigation on Sensory-Motor Trajectories

Noptilus is a European Project coordinated by the Centre for Research and Technology – Hellas (CERTH). More information about the project can be found on the official project website. Initially the task of navigation with sensory-motor trajectories was allocated to the Autonomous Systems Lab at ETH Zürich under the direction of Prof R. Siegwart and Dr. C. Pradalier. When C. Pradalier moved to GeorgiaTech Lorraine in autumn 2012, the CNRS (through its UMI 2958, part of GeorgiaTech Lorraine) replaced ETHZ in the consortium. Noptilus was successfully completed on June 30th, 2015.

Sensory-motor trajectories are trajectories defined as sequence of motor controls and perception instead of sequence of state in some state-space. The advantage of sensory-motor trajectories is that they can be followed by "simply" comparing the current perception with the reference perceptions and without requiring either a precise localisation or the construction of a map of the environment. The closest related field is the field of visual servoing, where a system is driven to a given state described as a reference perception, only by comparing the current perception (typically images) with the reference one. Sensory-motor trajectories aims at extending the concept with sequences of perceptions instead of a single reference, and other modalities than images. In the particular context of Noptilus, the perception modality will be sonar images, either from an imaging sonar, a multi-beam sonar or a side-scan sonar, the latter being the modality currently under investigation. This will be applied to the underwater platforms of the Faculty of Engineering of Porto, Portugal. 



Limnobotics is a project co-led by C.Pradalier while at ETH Zurich. Its focus was on lake monitoring using an autonomous boat to keep track of algal blooms.

More information about the project can be found on its official website.