Institute for Cognitive Systems (ICS), fundamental understanding and creation of cognitive systems, Munchen, Germany

Position Based Visual Servoing for dual arm Manipulation on the PR2 robot. Wolfgang Burger, Emmanuel Dean and Gordon Cheng. This video shows the obtained results of a Bachelor thesis. The main goal is control the pose of both arms of the PR2 robot using Visual information.

Click to expand...

This video is a media attachment to the following paper: Automatic Segmentation and Recognition of Human Activities from Observation based on Semantic Reasoning, Karinne Ramirez-Amaro, Michael Beetz, Gordon Cheng. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), September 2014.

This video presents a framework that combines different signals via semantic reasoning to enable robots for on-line segmentation and recognition of human activities from observation. In other words, the robot understands and infers what the human is doing with 85% accuracy. Additionally, we show how the robot learns new activities on the fly.

Click to expand...

This video is a media attachment to the following paper:
"A fast and scalable system for visual attention, object based attention and object recognition for humanoid robots". Andreas Holzbach, Gordon Cheng. 2014 IEEE-RAS International Conference on Humanoid Robots. November 18-20th 2014. Madrid. Spain.

Click to expand...

This video is a media attachment to the following paper:
"Forming Goal-directed Memory for Cognitive Development". Erhard Wieser and Gordon Cheng, Proceedings of the Workshop on Developmental Robotics, IEEE International Conference on Humanoid Robots, pp. 38-39, 2012.

Click to expand...

This video is a media attachment to the following paper:
"Predictive Action Selector for Generating Meaningful Robot Behaviour". Erhard Wieser and Gordon Cheng, IEEE International Conference on Development and Learning and on Epigenetic Robotics, pp. 180-186, 2014.

Click to expand...

Video media attachment to the journal paper: "Understanding the Intention of Human Activities through Semantic Perception: Observation, Understanding and Execution on a Humanoid Robot." Karinne Ramirez Amaro, Michael Beetz and Gordon Cheng. Advanced Robotics Journal, to appear in vol. 29, issue 5, Special Issue on Humanoid Robotics (1) which will be published in March 2015.

Click to expand...

This video shows the grasping of different objects with a 3-finger gripper mounted on a UR 10 robotic arm. This is the work of Michael Stenzel in his Bachelor Thesis, supervised by Dr. Emmanuel Dean.

Click to expand...

Tactile sensing feedback provides feasible solutions to robotic dexterous manipulation tasks. In this paper, we present a novel tactile based framework for detecting/correcting slips and regulating grasping forces while manipulating deformable objects with the dynamic center of mass. This framework consists of a tangential force based slip detection method and a deformation prevention approach relying on weight estimation. Moreover, we propose a new strategy for manipulating deformable heavy objects. Objects with different stiffnesses, surface textures, and centers of mass are tested in experiments. Results show that proposed approaches are capable of handling objects with uncertainties in their characteristics, and also robust to external disturbances.

Click to expand...