The goal of the Flourish project is to bridge the g ap between the current and desired capabilities of agricultural robots by developing a n adaptable robotic solution for precision farming. Thereby, combining the aerial survey capab ilities of a small autonomous multicopter Unmanned Aerial Vehicle (UAV) with a multi-p ur ose agricultural Unmanned Ground Vehicle (UGV), the system will be able to su rvey a field from the air, perform targeted intervention on the ground, and provide de tailed information for decision support, all with minimal user intervention. The system can be a dapted to a wide range of farm management activities and different crops by choosi ng d fferent sensors, status indicators and ground treatment packages. The gathered information can be used alongside existing precision agriculture machinery, for example, by pr oviding position maps for variable rate fertilizer application. The presentation will introduce the Flourish consor tium and the concept of this project using the results of the first year field campaign. Two k ey parts of the project will be shown in more detail: first, the field mapping by means of a n UAV. Particularly, the field 3D reconstruction approach (Khanna et al. 2015) and th e use of multi-spectral camera data to derive weed pressure or crop property maps (Liebisc h et al. 2014) with examples for subsequent crop management decision support. The se cond part will show the automated image acquisition by the UGV and a subsequent plant cl ssification with a four step pipeline differentiating crop from weed in real time (Lottes t al. 2015). The presentation will close with a short outlook on not shown project packages like automated orientation and movement of the UAV and UGV and the project’s time line.
[1]
Achim Walter,et al.
Remote, aerial phenotyping of maize traits with a mobile multi-sensor approach
,
2015,
Plant Methods.
[2]
A. Walter,et al.
Image based phenotyping during winter: a powerful tool to assess wheat genetic variation in growth response to temperature.
,
2015,
Functional plant biology : FPB.
[3]
Martin Rehak,et al.
Detection of crop properties by means of hyperspectral remote sensing from a micro UAV
,
2015
.
[4]
Frank Liebisch,et al.
Characterization of crop vitality and resource use efficiency by means of combining imaging spectroscopy based plant traits
,
2014,
2014 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).
[5]
Cyrill Stachniss,et al.
An effective classification system for separating sugar beets and weeds for precision farming applications
,
2016,
2016 IEEE International Conference on Robotics and Automation (ICRA).
[6]
Roland Siegwart,et al.
Beyond point clouds - 3D mapping and field parameter measurements using UAVs
,
2015,
2015 IEEE 20th Conference on Emerging Technologies & Factory Automation (ETFA).