The activities of the last two months are two-folded. We further consolidated our results from the user study at Harting and proceeded with the integration of perception in the FlexIRob-Setup.

Our submission "A User Study on Kinesthetic Teaching and Learning for Efficient Reconfiguration of Redundant Robot" is now finally accepted for publication in the Journal of Human Robot Interaction. With this publication we also get the opportunity to present our results at the HRI 2013 conference in Tokyo. To summarize the achieved results, with this publication we evaluated with workers from our industrial partner the esisting FlexIRob setup and an enhanced version of it where we introduced a new controller which supports the user in a teach-in task by keeping track of the task-independent environmental constraints learned in a previous configuration step.

As dissemination activities, we have presented the results of the user study to the workers which have participated in the study. Further, the idea of the FlexIRob system and the conducted user study have been introduced to Harting's costumers through an article in the tec.News (issue 23, p.16).

In addition to the above points, we have implemented in the last two months the perception chain which applies the Articulated Scene Model approach to co-worker scenarios. We have defined middleware specific data formats (here Robotic Service Bus and Robotics Systems Types) to provide the captured Kinect data to all components of our system (e.g., the simulation or the robot arm) and implemented the new components within the system framework. Currently, we are working on the integration of our dynamic obstacle avoidance concept on the FlexIRob demonstrator, the Kuka LWR IV, aiming at a first calibration of the robot arm and the camera(s) and the visualization of dynamic obstacles in the simulation of the robot arm and its environment as a first test.