In the last two months we have concentrated on the integration of a 3D Vision sensor into the FlexIRob scenario and the implementation of a detection of dynamic obstacles in the workspace of the robot arm.

First, a calibration of the sensor (here, Kinect camera) and the robot arm is realized by using the end effector position as a source for corresponding points between the two coordinate systems from which the transformation from the camera's coordinate system to the robot's coordinate system can be computed using Singular Value Decomposition. By simply ensuring through manual maneuvering of the robot arm that the end-effector is the closest point in the camera, the detection of the end-effector in the 3D sensor can be realized as simple nearest point detection. The advantage of this approach is that it is independent from knowing the appearance of the concrete end-effector.

Second, the FlexIRob system detects the robot arm in the visual sensor by estimating the arm through four cylinders which closely envelope the segments of the arm and the end-effector, transforming these cylinders into the camera's coordinate system, and excluding all 3D points within these four cylinders from the raw scene.

The third component of our perception subsystem focuses on the separation of the scene layer into static obstacles which are already encoded in the redundancy resolution of the robot arm and dynamic obstacles which appear spontaneously and should be avoided through an appropriate strategy during normal task completion. We realized this separation by integrating the Articulated Scene Model approach.

Last, the 3D points being part of the dynamic layer are clustered into connected components and represented as 3D boxes.

The intermediate results of all steps described above are depicted in the picture below.



Further, we are pleased to announce that our paper "Assisted Gravity Compensation to Cope with the Complexity of Kinesthetic Teaching on Redundant Robots" was accepted for publication at the International Conference on Robotics and Automation 2013. And Sebastian Wrede will give on the 5th of March a talk at the HRI2013 in Tokyo on our journal publication "A User Study on Kinesthetic Teaching of Redundant Robots in Task and Configuration Space". Interested people can also visit us at our stand on the Hannovermesse (08.04.-12.04.2013).