A message from the ECHORD coordinator Alois Knoll

The construction of the tripod micromanipulator has been finished. The concept includes high precision motion resolution for tip and tilt angles as well as Z-direction, mechanical protection, and integrated machine vision. Image processing routines have been implemented for identifying lenses of different types and to...

The last two months have shown a slow continuation of the previous joint work on the project. A significant part of our work in this period was focused on preparations for Automatica. 1) Automatica 2012: We set up the hardware system necessary for our appearance at Automatica and modified the necessary software to fit that...

Image processing routines for automated lens pickup have been implemented. That includes routines for calibrating camera coordinate systems with the robot base coordinate system and for finding out translational and rotational offsets between robot TCP and target camera view (camera attached to robot TCP or to...

The tripod has been assembled and was put to operation successfully including the clamping mechanism of the protection module. The animations have been extended to show the tip and tilt rotational motion. Additionally, a video was taped showing similar movements in reality. All objectives of the experiment have been achieved.

The flexprass experiment shall prove feasibility of combining lightweight desktop robots capable of close human-machine collaboration (Schunk) with high-precision manipulators (Fraunhofer IPT), e.g., needed for automated assembly of optical systems and lasers. Partners configured customized manipulator based on PowerCube...

During the last two months the consortium has been performing first real world experiments and further work on our simulation and learning methods has been performed. 1) After further preparations for the real world experiments in the SCAPE 2-finger setup were accomplished we performed a larger batch of real world...

During the last two months the consortium has been performing further real world experiments with the first application of learning methods. Further work on our simulations and evaluations of those has been performed. 1) A new sampling strategy was developed and implemented. We used the new method to do an analysis for the...

For learning object models, we made initial scan alignment more robust by adapting the point-pair feature object detection and pose estimation method of Papazov et al. (ACCV 2010). We only allow transformations that are close to the expected ones in the RANSAC step. For active object perception, we extended the simulation...

During the last two months we have been performing further experiments to evaluate our priority adjustment methods. Further work was also done on our dynamic simulation methods. 1) Experiments with suction cup setup: We have performed extensive experiments with a suction cup setup. Initially we performed a baseline with...

We conducted experiments where the robot has to actively perceive partially occluded objects which showed that considering object detection results when planning the next view can help finding more objects. We integrated the components developed in ActReMa into a bin-picking application, performed by the cognitive service...