Research and Innovation
are Key

Roboception is actively engaged in research and innovation, cooperates with Universities and Research Institutions is involved in strengthening the robotic competences across Europe. In addition to actively coordinating the Topic Group “Perception” in euRobotics aisbl, Roboception is involved in publicly funded projects on national (BFS, BMWi, BMBF) and European level.


Roboception is a proud member of the following associations and organizations:

Current Projects


Robotics, especially in the area of social interaction between humans and machines, is increasingly seen as a key technology that plays an important role in creating value and improving working conditions in various sectors such as industry, services, medicine and private life. A research network called FORSocialRobots, funded by the Bavarian Research Foundation, aims to improve the social capabilities of robots and develop new applications in six relevant areas and five scientific subprojects to increase their acceptance and effectiveness.


AutASa focuses on enhancing efficiency by integrating intelligent robotic assistance in semi-autonomous waste disposal, empowering humans to leverage their cognitive skills for a more productive collaboration with assistive robots.


Manual and automated production lines must evolve to “produce more and diverse with less”, however they need to address shortcomings such as e.g. lack of cognitive perception systems to allow autonomous reasoning. SMARTHANDLE will research technologies to address these needs and support European industry.


KI5GRob addresses in a new way how machine learning can be efficiently used in robotics by tightly linking cloud technologies and robotics in a tight control loop, and how the concept pursued can fundamentally simplify the programming and maintenance of robotic systems.


The 5gsmartfact project (Future Wireless Connected and Automated Industry Enabled by 5G) is to study, develop, optimize and assess the deployment of 5G networks factory environments and automation applications.


The focus of the KI4HE project is on improved environmental perception, self-localization, and assisted remote control of vehicles in hard-to-reach difficult-to-access environments.


Supported by the Bavarian Ministry of Economic Affairs, Regional Development and Energy (StMWi), the consortium is working towards a robotic assistant system and machine vision for the assembly of unstable components in customer-individual products.

Completed Projects

Read More
Roboception is the coordinator of this project, funded by the Federal Ministry of Education and Research (BMBF). Its objective is the development of human motion prediction using a combination of three deep neural networks (NN).
Read More
Robust perception capabilities for robots to support elderly users in a home environment, funded by the German Federal Ministry of Education and Research (BMBF).
Read More
Mobile dual arm robotic workers with embedded cognition for hybrid and dynamically reconfigurable manufacturing systems, funded under the project number 723616 within the Horizon 2020 FoF2 – 2016 program.
Read More
Pace-keeping 3D-reconstruction and analysis (Schritthaltende 3D-Rekonstruktion und -Analyse), funded by the Bavarian Science Foundation (BFS).
Read More
Mobile, ad-hoc cooperating robot teams (Mobile, ad-hoc kooperierende Roboterteams), funded by the Bavarian Science Foundation (BFS).
Read More
Robot-supported interaction systems for performance-impaired employees, funded by the Bavarian State Ministry of Economic Affairs, Regional Development and Energy.
Read More
The goal of the project is to develop concepts and coordinated evaluation electronics that make it possible to combine a wide range of sensors, measurement processes and AI methods into a safety-oriented sensor system. The aim is to enable robots to be operated more cost-effectively and efficiently, yet safely in the human workspace.


Roboception is actively engaged in research and innovation. For that reason, we are creating publicly available data sets.

Synthetic dataset for learning parallel-jaw grasping from stereo images: includes four different datasets, with automatically labelled training data for predicting parallel jaw grasps from stereo-matched depth images. For more details, please refer to the publication:

“Automatic generation of realistic training data for learning parallel-jaw grasping from synthetic stereo images”

Justus Drögemüller, Carlos X. Garcia, Elena Gambaro, Michael Suppa, Jochen Steil, Maximo A. Roa.

Proc. IEEE Int Conf. On Advanced Robotics (ICAR), 2021.

Research Partners

Roboception is proud to regularly provide demo products for testing and development purposes to research facilities such as:

Contact Us

Free Feasibility & Demo

You would like to find out whether our portfolio is suitable for your robotic application? Simply request a feasibility study free of charge, and get a live demo of our products.

Try & Buy

Would you like to try out one of our sensors and software solutions? Our Try-&-Buy-option gives you the chance to test our products before you decide, and to be sure you make the right choice for your application.