Joint Lab Künstliche Intelligenz & Data Science

Kooperation des Leibniz-Instituts für Agrartechnik und Bioökonomie Potsdam und der Universität Osnabrück


Navigation und Suche der Universität Osnabrück


Hauptinhalt

Topinformationen

Verena Tessaro

PhD student

E-Mail

Coppenrath Innovation Centre
Hamburger Straße 24
LOK 15, Raum 01.14.03A
49084 Osnabrück
Tel.:  +49 541 969-6341

Simulation of Environment Sensors – towards digital twins of autonomous agricultural machines

Perception of the environment is a basic requirement for all cognitive robotic tasks. In agriculture the unstructured and living – thus evolving and developing – environment is a constant challenge. A Digital Twin of environment sensors (Lidar, camera) shall be developed, including the sensor hardware-in-the-loop, to automatically collect feedback on the model quality. Critical features are the realtime capability of the simulation and the very small Sim-to-Real-gap in order to synthetise
data with integrated ground truth annotations. The feedback data will be used to re-train and improve the models accordingly. Digital Twins are a highly researched field. The goal is to develop Digital Twin simulations of sensor outputs, in unstructured environments, with changing and challenging ambient conditions, in order to synthetise training data for control algorithms. Thus by simulating environments and environmental sensors, to create enough data for the development of control applications.

 

Project team: Verena Tessaro (Ph.D. Studentin), Prof. Dr.-Ing. Mario Porrmann (UOS), Prof. Dr.-Ing. Cornelia Weltzien (ATB), Prof. Dr.-Ing. Heiko Tapken (HOS)

GIL Tagung 2024

Find the digital version of the conference poster here: GIL 2024 POSTER