Care-O-bot 3, Care-O-bot 4, mobile service robots, Fraunhofer Institute for Manufacturing Engineering and Automation, Stuttgart, Germany

Some of the features of Fraunhofer IPA's household service robot, Care-O-bot 3, are demonstrated.

Click to expand...

Care-O-bot is the product vision of a mobile service robot to assist humans in their daily life developed at Fraunhofer IPA. The meanwhile third generation of this more than 15 year old development series is characterized by a product like system design and for the first time provides the potential to apply manipulating mobile service robots in everyday environments. As an interactive butler, Care-O-bot 3 is able to move reliably among humans, to detect and grasp typical household objects, and to safely exchange them with humans.

Click to expand...

Care-O-bot is the product vision of a mobile robot assistant to actively support humans in domestic environments. The meanwhile fourth generation of this successful development series is more agile and modular than its predecessors and offers various ways of interaction. It also stands out through the use of cost-reducing construction principles. Individual robot platforms can be configured for a wide range of applications.

Click to expand...

The video showcases our person recognition method and exemplifies the training and recognition stages. The recognition performance under changing illumination conditions, facial expressions and varying head poses as well as the detection tracker are showcased within several scenes such as a dining table setting, office activities, or a group assembly.
The person detection and identification software is publicly available from wiki.ros.org/cob_people_perception .

Publication at:
R. Bormann, T. Zwölfer, J. Fischer, J. Hampp, and M. Hägele. Person recognition for service robotics applications. In Humanoids 2013, IEEE-RAS International Conference on Humanoid Robots, pages 260–267, 2013.

Click to expand...

The video contains three sequences of an integrated multi-sensor-based human tracking and identification system. First, the single modules are explained and visualized while demonstrating the task of identifying all three present people with the guidance of the ceiling camera based human tracker. Second, the unguided search of a certain user is shown. Finally, the same task is solved more efficiently with the assistance of the tracking system.
The person detection and identification software of this work is publicly available from wiki.ros.org/cob_people_perception .

Publication at:

N. Hu, R. Bormann, T. Zwölfer, and B. Kröse. Multi-user identification and efficient user approaching by fusing robot and ambient sensors. In 2014 IEEE International Conference on Robotics and Automation (ICRA), pages 5299–5306, May 2014.

Click to expand...

Schunk, the clamping and gripping specialist, showcased in Hannover Messe Care-o-bot 4, a mobile service robot developed in cooperation with Fraunhofer Institute.

Click to expand...

In professional office cleaning business, floor cleaning and waste disposal account for 70% of the daily cleaning efforts. Within the research project AutoPnP a Care-O-bot 3 service robot has been enabled for doing these tasks completely autonomously.
The video features all steps of the cleaning activities. First, the robot is inspecting the room for trash bins and dirty spots at the ground. Then the found trash bin is grasped, cleared into a collection bin and brought back. Following, an autonomous tool change between robot hand and vacuum cleaner is shown. The attached vacuum cleaner is then used to clean the ground.

Publications:
R. Bormann, F. Weisshardt, G. Arbeiter, and J. Fischer. Autonomous dirt detection for cleaning in office environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages 1252–1259, May 2013.

R. Bormann, J. Hampp, and M. Hagele. New Brooms Sweep Clean – An Autonomous Robotic Cleaning Assistant for Professional Office Cleaning. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), May 2015.

Click to expand...

The safety of mobile service robots is essential, especially when they move in public environments. Particularly challenging are applications in the environment of stationary care where the robots get in contact with people who are not familiar with them and who may require special protection. Therefore, in the S³ research project (2018-2021) technologies have been developed that improve the perception and manipulation capabilities of service robots, with a particular focus on safety. The project received funding from the German Federal Ministry of Education and Research.

The further development of appropriate software technologies for environment detection, the safe grasping of objects and their integration on the "Care-O-bot® 4" research platform were the focus of the work at Fraunhofer IPA. This enables the robot to reliably recognize people, determine what they are doing thanks to machine learning methods, and adapt its behavior in such a way that everything runs safely. The researchers validated the developed technologies in an exemplary application, which can be seen in the video. In the context of this application, the robot supports the staff of a residential care facility by fetching empty bottles from residents' rooms, taking them to the kitchen of the living area where the staff can refill them, and finally returning them to the residents' room.

Expert contact:
Florenz Graf, Phone: +49 711 970-1286, [email protected]

Click to expand...