CoP-Man -- Perception for Mobile Pick-and-Place in Human Living Environments

While many specific perception tasks have been addressed in the context of robot manipulation, the problem of how to design and realize comprehensive and integrated robot perception systems for manipulation tasks has received little attention so far. In this paper, we describe and discuss the design and realization of COP-MAN, a perception system that is tailored for personal robots performing pick-and-place tasks, such as setting the table, loading the dishwasher, and cleaning up, in human living environments. We describe our approach to decomposing and structuring the perception tasks into subtasks in order to make the overall perception system effective, reliable, and fast. Distinctive characteristics and features of COP-MAN include semantic perception capabilities, passive perception and a knowledge processing interface to perception. The semantic perception capabilities enable the robot to perceive the environment in terms of objects of given categories, to infer functional and affordance based information about objects and the geometric and part-based reconstruction of objects for grasping. Passive perception allows for real-time coarse-grained perception of the dynamic aspects, and the knowledge processing interface to perception enables the robot to query the information it needs, which is then automatically acquired through active perception routines.

[1]  Nico Blodow,et al.  Fast geometric point labeling using conditional random fields , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[2]  Ian Horswill,et al.  Analysis of Adaptation and Environment , 1995, Artif. Intell..

[3]  Zoltan-Csaba Marton,et al.  Probabilistic categorization of kitchen objects in table settings with a composite sensor , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Vincent Lepetit,et al.  Keypoint recognition using randomized trees , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Nico Blodow,et al.  Fast Point Feature Histograms (FPFH) for 3D registration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[6]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[7]  Michael Beetz,et al.  Acquisition of a dense 3D model database for robotic vision , 2009, 2009 International Conference on Advanced Robotics.

[8]  Nico Blodow,et al.  Towards 3D Point cloud based object maps for household environments , 2008, Robotics Auton. Syst..

[9]  Nico Blodow,et al.  Learning informative point classes for the acquisition of object model maps , 2008, 2008 10th International Conference on Control, Automation, Robotics and Vision.

[10]  Markus Ulrich,et al.  CAD-based recognition of 3D objects in monocular images , 2009, 2009 IEEE International Conference on Robotics and Automation.

[11]  Allan D. Jepson,et al.  The Computational Perception of Scene Dynamics , 1997, Comput. Vis. Image Underst..

[12]  Dejan Pangercic,et al.  Visual Scene Detection and Interpretation using Encyclopedic Knowledge and Formal Description Logic , 2009 .

[13]  Allan D. Jepson,et al.  Computational Perception of Scene Dynamics , 1996, ECCV.

[14]  Michael Beetz,et al.  Detecting and segmenting objects for mobile manipulation , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[15]  Nico Blodow,et al.  Model-based and learned semantic object labeling in 3D point cloud maps of kitchen environments , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Lucian Cosmin Goron,et al.  Reconstruction and Verification of 3D Object Models for Grasping , 2009, ISRR.

[17]  Nico Blodow,et al.  Functional object mapping of kitchen environments , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Michael Beetz,et al.  3D model selection from an internet database for robotic vision , 2009, 2009 IEEE International Conference on Robotics and Automation.

[19]  Jeffrey Mark Siskind,et al.  Reconstructing force-dynamic models from video sequences , 2003, Artif. Intell..

[20]  Michael Beetz,et al.  Real-time perception-guided motion planning for a personal robot , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.