InBOT

[Translate to Englisch:] InBOT- Interactive Behaviour Operated Trolley

The robot InBOT is developed, in order to examine and forward the use of robotics technologies in everyday environments of humans.

[Translate to Englisch:] InBOT

The focus is set on two aspects. On the one hand, on the close interaction with the user and the distribution of the control between robot and user. For this purpose, a force-sensitive grip is provided, by means of which the user can push the robot like a shopping trolley, however, without having to move the weight of the vehicle by his own efforts. In addition, he is supported by assistants, such as the automatic obstacle avoidance or a path planning assistant. When the user does not have the robot under his direct control by means of the grip, he can still influence it, since InBOT continuously observes its user through a stereo camera system. Due to that, he can follow his user or guide him to a desired destination.

 

Proactive avoidance of mobile obstacles

The second aspect that is focused on, is the dynamic of the environment itself. This is on the one hand the constant change of the supermarket's topology, for example through putting up and taking down special offers. This is approached through RFID transponders, installed on the ground, in order to not cover them in no circumstances. On the other hand, there are also many movable objects in a supermarket. The robot has to interact with them or avoid them.

InBOT's navigation system is characterised by the fact that it is independent of a detailed map. It consists of two main components: The first component is the task planning. Tasks are managed here and the path to the desired destination is planned on the basis of topological areas. RFID transponder barriers are used as landmarks, which are extremely tough to detect. The second component is the local navigation. It consists of a hierarchic behaviour network with proactive and reactive behaviour modules and directly works on sensor data.

Through the integrated concept of "Control Sharing", users and robots can exert control at the same time. Orthogonally arranged to the control architecture, it enables the user to directly and intuitively intervene in all layers of control. In this way, InBOT can follow its user, guide him or even be controlled on the grip without the robot having to give up its basic skills, like the navigation or obstacle avoidance.

[Translate to Englisch:] Navigationskonzept
Navigation concept
[Translate to Englisch:] Flexibler Aufgabenplaner
Flexible task planner
[Translate to Englisch:] RFID Barrieren als Landmarken
RFID barriers as landmarks
[Translate to Englisch:] Das Verhaltensnetz
The behaviour network

Contact person

Dr.-Ing. Arne Rönnau

Department Manager

more

Career

Arne Roennau studied Electrical Engineering at the University of Karlsruhe (TH), today's Karlsruhe Institute of Technology (KIT), from 2002 to 2008. The focus of his studies was on control and robotics. His thesis was focussed on sensor-based 3D environmental modelling and foot point planning for the six-legged walking robot LAURON.

From 2008 to 2011, Arne Roennau worked as a robotics expert in the department Interactive Diagnosis and Service Systems (IDS) at FZI. During this time, he worked on the localization of mobile robots, real-time control of AGVs as well as the optimization of multi-legged walking robots.

In 2019, Arne Rönnau earned his doctorate summa cum laude at the Karlsruhe Institute of Technology (KIT) on "Model-based design and optimization of multi-legged walking robots".

His current work focuses on Open Source Software (OSS), in particular ROS (Robot Operating System), human-robot collaboration (HRC), design of innovative service robotics applications such as the BratWurst Bot as well as learning deep neural networks/AI. His most important concern is the evaluation and transfer of these technologies into industrial, real world applications. Arne Rönnau is project manager in numerous public and industrial projects and coordinator of several national research projects.

Since 2011, Arne Roennau heads the department Interactive Diagnostic and Service Systems (IDS) within the research division Intelligent Systems and Production Engineering (ISPE). Besides, Arne Roennau is also the head of the FZI Living Lab Service Robotics since 2012.

Publications

Meine Veröffentlichungen sind in meinem Google Scholar Profil zu finden.

zu den Publikationen

Contact

Phone: +49 721 9654-228
E-Mail: roennau@dont-want-spam.fzi.de

hide details