Slawomir Sander (Grzonka)

Fabian Sellmann, Waldemar Bangert, Slawomir Grzonka, Martin Hänsel, Sebastian Haug, Arnd Kielhorn, Andreas Michaels, Kim Möller, Florian Rahe, Wolfram Strothmann, Dieter Trautz, and Arno Ruckelshausen

RemoteFarming.1: Human-machine interaction for a field-robot-based weed control application in organic farming

The collaborative research project RemoteFarming.1 integrates innovative agricultural engineering (field robotics, sensors, actuators) and web-based communication technologies. It aims to develop a robotic weed control system which integrates a human user as remote worker in the process. Thus, it drastically reduces the complexity of the problem in heterogeneous environments by not aiming to solve it using a fully autonomous system but integrating human-machine interaction as crucial component in the process. The system will be used for intra-row weed treatment in organic farming where weed control is currently conducted by hand. Within the project an autonomous field robot – based on the platform BoniRob - is being built. It is able to autonomously navigate on the field and has an actuator for mechanical weed treatment. Furthermore, it uses synchronously triggered cameras and lighting units at different wavelengths which can capture high-contrast images of the plants in a shaded space underneath the robot. The communication between the modules on the field robot - e. g. navigation module, sensor module and actuator module - is implemented using the open-source framework ROS (robot operating system). First, the detection/identification of weeds in RemoteFarming.1 is performed in a web-based approach solely by a remote worker, who marks the weeds in images captured by the robot on the field. Afterwards the mechanical actuator of the robot moves to those positions in the field which have been marked and eliminates the weed plants. Further developments in the project lead to a not fully but increasingly autonomous and still robust weed control system. RemoteFarming.1 helps to improve the working conditions by avoiding manual labor and shifting the workplace to a comfortable web interface.


@inproceedings{sellmann2014remotefarming, title={RemoteFarming. 1: Human-machine interaction for a field-robot-based weed control application in organic farming}, author={Sellmann, Fabian and Bangert, Waldemar and Grzonka, Slawomir and H{\"a}nsel, Martin and Haug, Sebastian and Kielhorn, Arnd and Michaels, Andreas and M{\"o}ller, Kim and Rahe, Florian and Strothmann, Wolfram and others}, booktitle={Proc. 4th International Conference on Machine Control and Guidance (MCG). Braunschweig, 19th-20th March}, year={2014} }

Paper (pdf file):

full paper